Channel reconstruction method, base station and terminal

Abstract

The present disclosure provides a base station, a terminal, and a channel reconstruction method performed by the base station and the terminal. The base station comprises: a sending unit configured to send channel state information reference signals of a plurality of ports to a terminal, wherein the channel state information reference signals of the plurality of ports have a first density in the frequency domain in one time interval; a receiving unit configured to receive precoding matrix indication information of a first granularity from the terminal; and a processing unit configured to determine a channel of a second granularity according to the precoding matrix indication information of the first granularity, and perform downlink precoding on the channel, wherein the second granularity is finer than the first granularity.

Description

Technical Field

[0001] This disclosure relates to the field of wireless communication, and more specifically to a channel reconstruction method and a corresponding base station and terminal. Background Technology

[0002] In a communication system, the base station sends a downlink reference signal to the UE. The UE performs channel estimation based on the downlink reference signal and sends Type I or Type II precoding matrix indication (PMI) information to the base station. The base station can determine the corresponding codeword and code-related combinations to reconstruct the channel based on the PMI information sent by the UE, and use the reconstructed channel for downlink precoding. Currently, the Type II PMI information sent by the UE is subband-level PMI information, which results in large quantization granularity in both the spatial and frequency domains, as well as large quantization granularity of the combination coefficients. Accordingly, the base station reconstructs the subband-level channel based on the subband-level PMI information sent by the UE. On the other hand, in a 5G NR system, the base station can perform precoding using the reconstructed channel on a physical resource block bundling (PRB) basis, and the granularity of PRB bundling is usually much smaller than the granularity of the PMI information.

[0003] For example, with a communication bandwidth of 100MHz between the base station and the UE and a subcarrier spacing (SCS) of 30kHz, a subband can include 16 resource blocks (RBs). The UE can transmit Type II PMI information at the subband (i.e., 16 RBs) level. On the other hand, the minimum size of physical resource block binding can be 2 RBs, which is much smaller than the granularity of PMI information.

[0004] Furthermore, when reconstructing the subband-level channel based on the sub-PMI information, it introduces significant errors in the quantization noise of the spatial domain and coefficients. This reduces the ability of various multiple-input multiple-output (MIMO) precoding methods to eliminate inter-user interference. Therefore, it is necessary to reduce the quantization noise.

[0005] However, in existing communication systems, if the granularity of the precoding matrix indication (PMI) information sent by the UE is increased, it is necessary to send a high-density channel state information reference signal (CSI-RS) to the UE, which increases the resource overhead of the reference signal.

[0006] Similarly, when a UE demodulates based on a demodulation reference signal (DMRS), the granularity of the reconstructed channel is limited by the density of the received DMRS. However, in existing communication systems, increasing the density of the DMRS requires increasing the resource overhead of the reference signal. Summary of the Invention

[0007] According to one aspect of this disclosure, a base station is provided. The base station includes: a transmitting unit configured to transmit channel state information reference signals of a plurality of ports to a terminal, wherein the channel state information reference signals of the plurality of ports have a first density in the frequency domain during a time interval; a receiving unit configured to receive precoding matrix indication information of a first granularity from the terminal; and a processing unit configured to determine a channel of a second granularity based on the precoding matrix indication information of the first granularity, and to perform downlink precoding on the channel, wherein the second granularity is finer than the first granularity.

[0008] According to another aspect of this disclosure, a terminal is provided. The terminal includes: a receiving unit configured to receive channel state information reference signals from a plurality of ports, wherein the channel state information reference signals from the plurality of ports have a first density in the frequency domain during a time interval; a processing unit configured to determine precoding matrix indication information of a first granularity based on the channel state information reference signals during the time interval; and a transmitting unit configured to transmit the precoding matrix indication information to a base station, so that the base station reconstructs a downlink channel of a second granularity based on the precoding matrix indication information, wherein the second granularity is finer than the first granularity.

[0009] According to another aspect of this disclosure, a terminal is provided. The terminal includes: a receiving unit configured to receive a demodulated reference signal of a second density; and a processing unit configured to perform a preliminary channel estimation based on the demodulated reference signal to determine a channel with a third granularity; and to perform interpolation and denoising processing on the third-granularity channel using a super-resolution network to obtain a channel with a fourth granularity, wherein the fourth granularity is finer than the third granularity.

[0010] According to another aspect of this disclosure, a channel reconstruction method performed by a base station is provided, comprising: transmitting channel state information reference signals of a plurality of ports to a terminal, wherein the channel state information reference signals of the plurality of ports have a first density in the frequency domain during a time interval; receiving precoding matrix indication information of a first granularity from the terminal; determining a channel of a second granularity based on the precoding matrix indication information of the first granularity; and performing downlink precoding on the channel, wherein the second granularity is finer than the first granularity.

[0011] According to another aspect of this disclosure, a channel reconstruction method performed by a terminal is provided, comprising: receiving channel state information reference signals from a plurality of ports, wherein the channel state information reference signals from the plurality of ports have a first density in the frequency domain during a time interval; determining precoding matrix indication information of a first granularity based on the channel state information reference signals during the time interval; and sending the precoding matrix indication information to a base station so that the base station reconstructs a downlink channel of a second granularity based on the precoding matrix indication information, wherein the second granularity is finer than the first granularity.

[0012] According to another aspect of this disclosure, a channel reconstruction method performed by a terminal is provided, comprising: receiving a demodulation reference signal of a second density; performing a preliminary channel estimation based on the demodulation reference signal to determine a channel having a third granularity; and interpolating and denoising the third-granularity channel using a super-resolution network to obtain a channel with a fourth granularity, wherein the fourth granularity is finer than the third granularity. Attached Figure Description

[0013] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0014] Figure 1 This is a schematic diagram illustrating how a base station reconstructs a channel based on feedback from a terminal in a communication system.

[0015] Figure 2 This is a schematic block diagram illustrating a base station according to an embodiment of the present disclosure.

[0016] Figure 3A This is a schematic diagram showing 32-port CSI-RS transmitted in a single time slot according to 3GPP standard release 15 for 5G NR.

[0017] Figure 3B This is a schematic diagram illustrating an example of how a transmitting unit sends 32-port CSI-RS to a terminal according to this disclosure.

[0018] Figure 3C This is a schematic diagram illustrating, according to another example of the present disclosure, that the transmitting unit transmits 32-port CSI-RS to the terminal.

[0019] Figure 4 This is a schematic block diagram illustrating a terminal according to an embodiment of the present disclosure.

[0020] Figure 5 This is a schematic block diagram illustrating a terminal according to another embodiment of the present disclosure.

[0021] Figure 6 This is a flowchart of a channel reconstruction method performed by a base station according to an embodiment of the present disclosure.

[0022] Figure 7 This is a flowchart of a channel reconstruction method performed by a terminal according to an embodiment of the present disclosure.

[0023] Figure 8 This is a flowchart of a channel reconstruction method performed by a terminal according to an embodiment of the present disclosure.

[0024] Figure 9 This is a schematic diagram of the hardware structure of a device according to an embodiment of the present disclosure. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this disclosure more apparent, exemplary embodiments according to this disclosure will now be described in detail with reference to the accompanying drawings. In the drawings, the same reference numerals denote the same elements throughout. It should be understood that the embodiments described herein are merely illustrative and should not be construed as limiting the scope of this disclosure. Furthermore, the terminals described herein may include various types of terminals, such as user equipment (UE), mobile terminals (or mobile stations), or fixed terminals; however, for convenience, the terms "terminal" and "UE" are sometimes used interchangeably below.

[0026] Figure 1 This is a schematic diagram illustrating how a base station reconstructs a channel based on feedback from a terminal in a communication system. For example... Figure 1 As shown, terminal 110 performs channel estimation based on the downlink reference signal and obtains Type I or Type II precoding matrix indication (PMI) information based on the channel estimation result to send to base station 120. Base station 120 reconstructs the channel based on the PMI information sent by the UE and uses the reconstructed channel for downlink precoding. The ideal spatial-temporal channel H that the base station expects to obtain can be expressed by the following formula (1):

[0027]

[0028] The spatial-temporal channel H can be viewed as the superposition of N multipath components, each with an amplitude of α. i It can be written as a delay τ i , Horizontal angle of arrival Vertical angle of arrival θ i Phase φ iThe function F. Currently, it is very difficult to estimate each parameter in the above formula one by one based on the downlink reference signal, thus making it difficult to accurately recover the channel.

[0029] Specifically, in the current communication system, terminal 110 transmits subband-level Type II PMI information. This results in large quantization granularity in both the spatial and frequency domains, as well as large quantization granularity in the combination coefficients. Correspondingly, the channel reconstructed by base station 120 based on the PMI information is also a subband-level channel, which makes the granularity of the reconstructed channel coarse. On the other hand, in a 5G NR system, the base station can precode the reconstructed channel using physical resource block bindings, and the granularity of physical resource block bindings is usually much smaller than the granularity of the PMI information.

[0030] Furthermore, when reconstructing the subband-level channel based on the sub-PMI information, it introduces significant errors in the quantization noise of the spatial domain and coefficients. This reduces the ability of various multiple-input multiple-output (MIMO) precoding methods to eliminate inter-user interference. Therefore, it is necessary to reduce the quantization noise.

[0031] However, in existing communication systems, if the granularity of the precoding matrix indication (PMI) information sent by the UE is increased, it is necessary to send a high-density channel state information reference signal (CSI-RS) to the UE, which increases the resource overhead of the reference signal.

[0032] Similarly, when a UE demodulates based on a demodulation reference signal (DMRS), the granularity of the reconstructed channel is limited by the density of the received DMRS. However, in existing communication systems, increasing the density of the DMRS requires increasing the resource overhead of the reference signal.

[0033] In embodiments according to this disclosure, it is proposed to determine a second-granularity channel based on a first-granularity precoding matrix indication information during channel reconstruction, thereby enabling the acquisition of a channel with finer granularity while reducing signaling overhead.

[0034] The following is for reference. Figure 2 To illustrate a base station according to an embodiment of the present disclosure. Figure 2 This is a schematic block diagram illustrating a base station according to one embodiment of the present disclosure. Figure 2 As shown, a base station 200 according to one embodiment of this disclosure may include a transmitting unit 210, a receiving unit 220, and a processing unit 230. In addition to the transmitting unit, receiving unit, and processing unit, the base station 200 may also include other components; however, since these components are not relevant to the content of this disclosure embodiment, their illustrations and descriptions are omitted here.

[0035] like Figure 2As shown, the transmitting unit 210 of base station 200 transmits channel state information reference signals for multiple ports to the terminal, wherein the channel state information reference signals for multiple ports have a first density in the frequency domain during a time interval. The receiving unit 220 receives precoding matrix indication information of a first granularity from the terminal. Specifically, the precoding matrix indication information of the first granularity is determined by the terminal based on the channel state information reference signals for multiple ports.

[0036] Then, the processing unit 230 is configured to determine a channel of a second granularity based on the precoding matrix indication information of the first granularity, and to perform downlink precoding on the channel. According to an example of this disclosure, the base station can perform interpolation and denoising operations during channel reconstruction based on PMI information using a super-resolution network, so that the granularity of the PMI information fed back by the terminal can be the granularity of the PMI information used in current communication systems, or a coarser granularity. Furthermore, even if the granularity of the PMI information fed back from the terminal is coarse, a high-precision channel can be obtained using a super-resolution network. Correspondingly, the channel state information reference signal (CSI-RS) sent by the transmitting unit 210 to the terminal for determining the PMI information can also have a lower density.

[0037] According to one example of this disclosure, the density currently supported in the 5G NR standard is 1 / 2 resource element per port per resource block (1 / 2 RE per RB per Port). Transmitting unit 210 can transmit CSI-RS with a density of 1 / 2 resource element per resource block. Alternatively, transmitting unit 210 can transmit CSI-RS with a density of 1 / 4, 1 / 8, 1 / 16, or 1 / 32 resource elements per port per resource block.

[0038] For example, within a time interval, the channel state information reference signal for each port does not repeat in at least four consecutive resource blocks in the frequency domain. In the examples according to this disclosure, a time interval may be a period of time during which the base station transmits multiple port CSI-RS signals at once for communication with the terminal. For example, a time interval may be one or more time slots, one or more symbol time periods, etc.

[0039] For example, the CSI-RS that the transmitting unit 210 can transmit to the terminal may have a lower density than the CSI-RS in 3GPP standard release 15 of 5G NR (New Radio). Figure 3A This is a schematic diagram illustrating 32-port CSI-RS transmitted in a single time slot according to 3GPP standard release 15 for 5G NR. (See diagram for example.) Figure 3AAs shown, the CSI-RS for the 32 ports is divided into two groups. The CSI-RS for ports 0-15 is transmitted in the first resource block (RB), the CSI-RS for ports 16-31 is transmitted in the second RB, and the CSI-RS transmitted in the first and second RBs are repeated in the third and fourth RBs, respectively.

[0040] As described above, in the example according to this disclosure, the CSI-RS that the transmitting unit 210 can transmit to the terminal may have a higher... Figure 3A The CSI-RS shown is characterized by low density. For example, when transmitting channel state information reference signals for at least 32 ports in a time interval, the multiple port CSI-RS can be divided into at least two groups. And in a time interval, the at least two groups of channel state information reference signals are distributed across the at least four consecutive resource blocks.

[0041] The following will combine Figure 3B and Figure 3C The density of CSI-RS transmitted by the transmitting unit 210 to the terminal is described in the example according to this disclosure. Figure 3B This is a schematic diagram illustrating an example of how a transmitting unit sends 32-port CSI-RS data to a terminal, according to this disclosure. Figure 3B As shown, within a time interval, the transmitting unit 210 can transmit CSI-RS in a low-density combo structure. Specifically, in a subframe, the 32-port CSI-RS is divided into 4 groups. CSI-RS of ports 0-7 are transmitted in the first RB, CSI-RS of ports 8-15 are transmitted in the second RB, CSI-RS of ports 16-23 are transmitted in the third RB, and CSI-RS of ports 24-31 are transmitted in the fourth RB.

[0042] Figure 3C This is a schematic diagram illustrating another example according to this disclosure, showing a transmitting unit sending 32-port CSI-RS to a terminal. (See diagram below.) Figure 3C As shown, within a time interval, the transmitting unit 210 may not repeatedly transmit CSI-RS from multiple ports. Specifically, the transmitting unit 210 may transmit CSI-RS on some of the RBs used for transmitting CSI-RS in the existing communication system, and not transmit CSI-RS on other RBs used for transmitting CSI-RS in the existing communication system, thereby reducing the density of CSI-RS. Figure 3C As shown, in a subframe, the CSI-RS of the 32 ports is divided into 4 groups. The CSI-RS of ports 0-15 is transmitted in the first RB, the CSI-RS of ports 16-31 is transmitted in the third RB, and no CSI-RS is transmitted in the second and fourth RBs.

[0043] As described above, the processing unit 230 uses a super-resolution network to determine the channel at the second granularity based on the precoding matrix indication information at the first granularity, so that even if the granularity of the PMI information fed back from the terminal is coarse, a high-precision channel can be obtained using the super-resolution network.

[0044] According to an example of this disclosure, processing unit 230 can perform channel reconstruction based on the precoding matrix indication information to obtain a first channel, and use a super-resolution network to interpolate and denoise the first-granularity channel to obtain a second-granularity channel. For example, receiving unit 220 can receive sub-band level type II PMI information from a terminal. Specifically, the type II PMI information may include spatial codeword selection information, amplitude and phase information of the wideband and sub-band level codeword combination coefficients, and may also include frequency domain codeword selection information. Processing unit 230 can use the amplitude and phase information in the PMI information received by receiving unit 220 to perform amplitude and phase weighting on the spatial (also referred to as "beam domain")-frequency domain channel codewords of multiple beams, and merge the weighted vectors to obtain a first channel with sub-band level. Next, processing unit 230 uses a super-resolution network to interpolate and denoise the first-granularity channel to obtain a second channel, wherein the second channel has a second granularity, and the second granularity is finer than the first granularity. For example, as mentioned above, the first-granularity channel can be a subband-level channel. In this case, the second-granularity channel can be a subcarrier-level or resource block (RB)-level channel.

[0045] Optionally, before inputting the first channel at the first granularity into the super-resolution network, the processing unit 230 can preprocess the first channel to facilitate subsequent super-resolution network operations. For example, if the first channel is a spatial-frequency domain channel, the processing unit 230 can perform a Fourier transform on the first channel to convert it into a beam-delay domain channel. Furthermore, since the channel delay component is mainly concentrated at the beginning of the delay domain channel matrix in the beam-delay domain, the processing unit 320 can truncate the delay domain channel, retaining the beginning, and divide the truncated data into two channels, real and imaginary, as input to the super-resolution network. By transforming the first channel to be processed to the delay domain and grading the data, the computational complexity of the super-resolution network can be reduced.

[0046] Processing unit 230 can use various super-resolution networks. The first channel at the first granularity can be interpolated and denoised using a method similar to that used for image interpolation and denoising with a super-resolution network. Furthermore, the super-resolution network can be pre-trained using a high-density reference signal. For example, transmitting unit 210 can also transmit a high-density reference signal to at least one of the user equipment and data acquisition device, and receive feedback information from at least one of the user equipment and data acquisition device regarding the first channel state information reference signal. Processing unit 230 can use the feedback information regarding the first channel state information reference signal to train the super-resolution network, so that the super-resolution network learns to obtain a candidate set of parameters and functions F of the channel as shown in the above formula (1) corresponding to specific feedback information through interpolation and denoising processing. Thus, in actual deployment, processing unit 230 can input the first channel obtained according to the precoding matrix indication information fed back by the terminal into the trained super-resolution network to accurately recover the channel.

[0047] For example, processing unit 230 can use at least one of a Very Deep Super Resolution (VDSR) network and a Cascading Residual Network (CARN) to interpolate and denoise the channel at the first granularity to obtain a second channel. Specifically, processing unit 230 can use a VDSR with 16-20 layers and a kernel size of 3 to interpolate and denoise the channel at the first granularity to obtain a second channel. Since deep networks are beneficial for learning features in the channel, using deep networks can improve channel recovery. Furthermore, according to an example of this disclosure, a residual network structure can be applied in a deep super resolution network. Specifically, the input can be superimposed before the output layer to enhance the correspondence between the output and the input.

[0048] Alternatively, the processing unit 230 may also use a cascaded residual convolutional network formed by introducing multiple small convolutional networks into the residual structure. In the cascaded residual network, each small convolutional network can be a 3-layer convolutional network with a kernel size of 3. Compared to deep super-resolution networks, cascaded residual networks can achieve better performance with less complexity.

[0049] Finally, processing unit 230 performs downlink precoding on the second channel for transmission to the terminal. In the embodiment described in conjunction with FIG3, after the base station's processing unit performs conventional channel reconstruction based on the precoding matrix indication information, it uses a super-resolution network to interpolate and denoise the first-granularity channel to obtain a second channel with finer granularity for downlink precoding.

[0050] Furthermore, according to another example of this disclosure, in addition to interpolation and denoising, a neural network can also be used to perform channel reconstruction based on precoding matrix indication information of the first granularity received from the terminal. For example, processing unit 230 can perform channel reconstruction, interpolation, and denoising based on the precoding matrix indication information of the first granularity using a neural network including a super-resolution network to obtain a second channel of the second granularity.

[0051] Specifically, the processing unit 230 can use a first sub-network to perform channel reconstruction, interpolation, and denoising processing based on the precoding matrix indication information of the first granularity to obtain a second channel, and perform downlink precoding on the channel of the second granularity, wherein the second granularity is finer than the first granularity. The first sub-network can be a first sub-neural network.

[0052] According to one example of this disclosure, the input dimension of the first sub-network may be higher than the output dimension of the first sub-network. In other words, the first sub-network adopts a high-dimensional input and low-dimensional output design. Due to the use of high-dimensional input, the original information from the pre-encoded matrix indication information can be preserved, and due to the use of low-dimensional output, dimensionality reduction during network processing can reduce network complexity and training difficulty.

[0053] Specifically, the input to the first sub-network may be precoding matrix indication information from the terminal or preprocessed precoding matrix indication information, and the first sub-network may reconstruct the input from the precoding matrix indication information. According to an example of this disclosure, the first sub-network may weightedly combine the amplitude and phase of the input data. For example, the precoding matrix indication information may include amplitude information and phase information. Further, the amplitude information may include broadband beam information, broadband amplitude information, and sub-band amplitude information of each beam through which the base station communicates with the terminal, as well as sub-band phase information of each sub-band. The first sub-network may combine the broadband beam information, broadband amplitude information, and sub-band amplitude information of each beam to obtain a channel amplitude matrix. Specifically, the first sub-network may obtain the channel amplitude matrix in each polarization direction according to the beam's polarization direction. Furthermore, the first sub-network may obtain the real and imaginary parts of the matrix based on the broadband beam information and the phase information of each sub-band. Similarly, the first sub-network may obtain the real and imaginary parts of the matrix in each polarization direction according to the beam's polarization direction. Then, the first sub-network can multiply the channel amplitude matrix in each polarization direction with the real part matrix and the imaginary part matrix respectively to obtain the beam-frequency domain channel matrix (also simply referred to as "beam-frequency domain channel").

[0054] For example, base station 400 communicates with the terminal using beams in two polarization directions. The first sub-network can obtain the channel amplitude matrices A1 and A2 in the two polarization directions, and the channel phase matrices (i.e., the real and imaginary parts) Pr1, Pr2, Pi1, and Pi2 in the two polarization directions. The first sub-network can obtain the beam-frequency domain channel matrices Hr1, Hr2, Hi1, and Hi2 using the following formula (2):

[0055] Hr1 = A1 * Pr1, Hr2 = A2 * Pr2;

[0056] Hi1=A1*Pi1,Hi2=A2*Pi2……(2)

[0057] In formula (2), "*" indicates the multiplication of corresponding matrix elements.

[0058] Next, the first sub-network can perform a Fourier transform on the beam-frequency domain channel to transform it into a beam-delay domain channel. Furthermore, since the channel delay component is mainly concentrated at the beginning of the delay domain channel matrix in the beam-delay domain, the first sub-network can truncate the delay domain channel to reduce the dimensionality of the output.

[0059] According to one example of this disclosure, the first sub-network may include a fully connected layer (dense layer) and is used to reconstruct the input precoded matrix indication information. Specifically, the fully connected layer weightedly combines the amplitude and phase of the input data to obtain a beam-frequency domain channel, converts the beam-frequency domain channel into a beam-delay domain channel, and truncates the beam-delay domain channel to reduce the dimensionality of the network output. Alternatively, since the operation required in the weighted combining process is only the element-wise multiplication of the individual matrices, the corresponding fully connected layer can be replaced with a partially connected layer that only connects the elements that need to be directly multiplied.

[0060] According to another example of this disclosure, the first sub-network may further include one or more super-resolution networks for interpolation and denoising. The one or more super-resolution networks may be positioned before or after the aforementioned fully connected or partially connected layers. Furthermore, the aforementioned fully connected or partially connected layers may be positioned between multiple super-resolution networks.

[0061] For example, a super-resolution network can be set up before the fully connected layer or partially connected layer to interpolate and denoise the precoding matrix indication information from the terminal. The interpolated and denoised data is then input into the fully connected layer or partially connected layer for channel reconstruction and dimensionality reduction. Alternatively, the precoding matrix indication information from the terminal can first be input into the fully connected layer or partially connected layer for channel reconstruction and dimensionality reduction, and then the resulting channel can be input into the super-resolution network for interpolation and denoising. Yet another example is that the precoding matrix indication information from the terminal can be input into a first super-resolution network for denoising. The denoised data is then input into the fully connected layer or partially connected layer for channel reconstruction and dimensionality reduction. Finally, the dimensionality-reduced channel is input into a second super-resolution network for interpolation.

[0062] Alternatively, according to another example of this disclosure, processing unit 230 may also perform at least one of temporal channel estimation enhancement and temporal prediction on multiple second channels obtained from precoding matrix indication information transmitted multiple times from the same terminal via a second sub-network. For example, the first sub-network may process precoding matrix indication information transmitted once by the terminal (e.g., transmitted in a single time slot) and perform channel reconstruction, interpolation, and denoising based on the precoding matrix indication information transmitted once by the terminal. The second sub-network includes at least one of an RNN and an LSTM network, and the second sub-network may input precoding matrix indication information transmitted multiple times by the same terminal into a value RNN / LSTM network to achieve at least one of temporal channel estimation enhancement and temporal prediction.

[0063] Combined with the above Figure 2 Corresponding to the described base station, the terminal also receives CSI-RS with lower density and determines precoding matrix indication information based on the lower-density CSI-RS. The following will combine... Figure 4 A terminal according to one embodiment of the present disclosure will be described.

[0064] Figure 4 This is a schematic block diagram illustrating a terminal according to an embodiment of the present disclosure. Figure 4 As shown, a terminal 400 according to another embodiment of this disclosure may include a receiving unit 410, a processing unit 420, and a transmitting unit 430. In addition to the transmitting unit, receiving unit, and processing unit, the terminal 400 may also include other components; however, since these components are not relevant to the content of this disclosure, their illustrations and descriptions are omitted here.

[0065] like Figure 4 As shown, the receiving unit 410 receives channel state information reference signals from multiple ports, wherein, within a time interval, the channel state information reference signals from the multiple ports have a first density in the frequency domain. This has been combined with... Figure 2 Figure 3 provides a detailed description of multi-port CSI-RS with low density, so it will not be repeated here.

[0066] Processing unit 420 determines precoding matrix indication information of a first granularity based on channel state information reference signals over a time interval. This first granularity precoding matrix indication information is sub-band level precoding matrix indication information. As described above, the base station determines a second granularity channel based on the first granularity precoding matrix indication information using a super-resolution network, thereby achieving high-precision channel even if the granularity of the PMI information fed back from the terminal is coarse. In this case, the granularity of the PMI information can be further increased. For example, the granularity of the PMI information determined by processing unit 420 can be coarser than the granularity of the PMI information specified in 3GPP standard release 15 for 5G NR.

[0067] According to one example of this disclosure, the size of the subband used when the terminal 400 communicates with its corresponding base station can be increased. For example, the resource blocks included in the subband may include more resource blocks than those included in the subband in 3GPP standard release 15 of 5G NR. This can further reduce signaling overhead. For example, the resource blocks included in the subband may be twice or more than those included in the subband in 3GPP standard release 15 of 5G NR.

[0068] According to another example of this disclosure, while increasing the size of the subband used when the terminal 400 communicates with its corresponding base station, the quantization level of amplitude and phase feedback in the PMI information can be increased. For example, it can be increased to 16-PSK or 32-PSK. Due to the increased subband size, the signaling overhead remains substantially unchanged even when the quantization level of amplitude and phase feedback is increased.

[0069] Then, the transmitting unit 430 transmits the precoding matrix indication information to the base station so that the base station can reconstruct a downlink channel of a second granularity based on the precoding matrix indication information, wherein the second granularity is finer than the first granularity. As described above, the base station can obtain a high-precision channel using the super-resolution network even if the granularity of the PMI information fed back from the terminal is coarse by performing interpolation and denoising during channel reconstruction based on the precoding matrix indication information of the first granularity. In this case, according to an example of this disclosure, the period during which the processing unit 420 determines the PMI information and the period during which the transmitting unit 430 transmits the PMI information to the base station can be extended. This can further reduce signaling overhead. For example, the period during which the PMI information is transmitted can be 1.5 times, 2 times, or longer than the period during which the PMI information is transmitted in 3GPP standard release 15 of 5G NR. In addition, the period during which the CSI-RS is transmitted can be increased in a similar manner to the period during which the PMI information is transmitted. For example, the period during which the PMI information is transmitted and the CSI-RS transmission period can be configured to a slot length of 960 slots, a slot length of 1280 slots, or longer.

[0070] In combination with the above Figure 2-4 The base station and terminal described in this disclosure embodiment propose to determine the second-granularity channel based on the precoding matrix indication information of the first granularity during channel reconstruction, thereby providing the possibility of obtaining a channel with finer granularity while reducing signaling overhead.

[0071] Similar to determining the second-granularity channel based on the precoding matrix indication information of the first granularity, another embodiment of this disclosure proposes a similar operation for the demodulation reference signal (DMRS) to obtain a high-precision channel based on a low-density DMRS. Hereinafter, references... Figure 5 To illustrate a terminal according to another embodiment of this disclosure. Figure 5 This is a schematic block diagram illustrating a terminal according to another embodiment of the present disclosure. Figure 5 As shown, a terminal 500 according to one embodiment of this disclosure may include a receiving unit 510 and a processing unit 520. In addition to the receiving unit and the processing unit, the terminal 500 may also include other components; however, since these components are not relevant to the content of this disclosure embodiment, their illustrations and descriptions are omitted here.

[0072] like Figure 5As shown, receiving unit 510 can receive a demodulation reference signal (DMRS) of second density. Processing unit 520 can perform preliminary channel estimation based on the demodulation reference signal to determine a channel with a third granularity, and use a super-resolution network to interpolate and denoise the channel with the third granularity to obtain a channel with a fourth granularity, wherein the fourth granularity is finer than the third granularity. For example, processing unit 520 can perform preliminary least square (LS) channel estimation on the received signal on the DMRS to determine a channel with a third granularity, and then use a super-resolution network to interpolate and denoise the channel with the third granularity to obtain a channel with a fourth granularity.

[0073] Because the processing unit 520 can perform interpolation and denoising operations during channel reconstruction based on DMRS information through a super-resolution network, the frequency density of the DMRS can be at the granularity of the DMRS used in current communication systems, or even lower. Furthermore, even with a low frequency density of the DMRS, a high-precision channel can be obtained using a super-resolution network.

[0074] According to one example of this disclosure, the density of DMRS can be 1 port per port per resource block or less. For example, for 12 ports, the DMRS density can be 1 port per port per resource block; while for 6 ports, the DMRS density can be 1 / 2 port per port per resource block. Furthermore, for example, DMRS can be transmitted using orthogonal coverage codes (OCC). As another example, DMRS can also be transmitted using time-domain orthogonal coverage codes (TD-OCC) or frequency-domain orthogonal coverage codes (FD-OCC).

[0075] According to another example of this disclosure, processing unit 520 can use various super-resolution networks. The first channel at a first granularity can be interpolated and denoised using a method similar to that used for image interpolation and denoising with a super-resolution network. Furthermore, the super-resolution network can be pre-trained using a high-density reference signal. Thus, in actual deployment, processing unit 520 can input the first channel obtained according to the precoding matrix indication information fed back from the terminal into the trained super-resolution network to accurately recover the channel.

[0076] For example, processing unit 520 can use at least one of a Very Deep Super Resolution (VDSR) network and a Cascading Residual Network (CARN) to interpolate and denoise the channel at the first granularity to obtain a second channel. Specifically, processing unit 520 can use a VDSR with 16-20 layers and a kernel size of 3 to interpolate and denoise the channel at the first granularity to obtain a second channel. Since deep networks are beneficial for learning features in the channel, using deep networks can improve channel recovery. Furthermore, according to an example of this disclosure, a residual network structure can be applied in a deep super resolution network. Specifically, the input can be superimposed before the output layer to enhance the correspondence between the output and the input.

[0077] Alternatively, the processing unit 520 may also use a cascaded residual convolutional network formed by introducing multiple small convolutional networks into the residual structure. In the cascaded residual network, each small convolutional network can be a 3-layer convolutional network with a kernel size of 3. Compared to deep super-resolution networks, cascaded residual networks can achieve better performance with less complexity.

[0078] Below, refer to Figure 6 This invention describes a channel reconstruction method according to an embodiment of the present disclosure. Figure 6 This is a flowchart of a channel reconstruction method 600 performed by a base station according to an embodiment of the present disclosure. Since the steps of the channel processing method 600 correspond to the operation of the base station 200 described above with reference to the figures, detailed descriptions of the same content are omitted here for simplicity.

[0079] like Figure 6 As shown, in step S601, channel state information reference signals for multiple ports are sent to the terminal, wherein the channel state information reference signals for multiple ports have a first density in the frequency domain during a time interval. In step S602, precoding matrix indication information of the first granularity is received from the terminal. Specifically, the precoding matrix indication information of the first granularity is determined by the terminal based on the channel state information reference signals for multiple ports.

[0080] Then, in step S603, a second-granularity channel is determined based on the precoding matrix indication information of the first granularity, and downlink precoding is performed on the channel. According to an example of this disclosure, the base station can perform interpolation and denoising operations during channel reconstruction based on PMI information using a super-resolution network, so that the granularity of the PMI information fed back by the terminal can be the granularity of the PMI information used in current communication systems, or a coarser granularity. Furthermore, even if the granularity of the PMI information fed back from the terminal is coarse, a high-precision channel can be obtained using a super-resolution network. Correspondingly, the channel state information reference signal (CSI-RS) sent by the transmitting unit 210 to the terminal for determining the PMI information can also have a lower density.

[0081] According to one example of this disclosure, the density currently supported in the 5G NR standard is 1 / 2 resource element per port per resource block (1 / 2 RE per RB per Port). Transmitting unit 210 can transmit CSI-RS with a density of 1 / 2 resource element per resource block. Alternatively, transmitting unit 210 can transmit CSI-RS with a density of 1 / 4, 1 / 8, 1 / 16, or 1 / 32 resource elements per port per resource block.

[0082] For example, within a time interval, the channel state information reference signal for each port does not repeat in at least four consecutive resource blocks in the frequency domain. In the example according to this disclosure, a time interval may be a period of time during which the base station transmits multiple port CSI-RS for communication with the terminal. For example, a time interval may be one or more time slots, one or more symbol time periods, etc. As another example, in step S601, the CSI-RS that can be transmitted to the terminal may have a lower density than the CSI-RS in 3GPP standard release 15 of 5G NR (New Radio).

[0083] As described above, in step S603, a super-resolution network is used to determine the channel at the second granularity based on the precoding matrix indication information at the first granularity. Thus, even if the granularity of the PMI information fed back from the terminal is coarse, a high-precision channel can be obtained using the super-resolution network.

[0084] According to an example of this disclosure, in step S603, channel reconstruction can be performed based on the precoding matrix indication information to obtain a first channel, and a super-resolution network can be used to interpolate and denoise the first-granularity channel to obtain a second-granularity channel. For example, in step S603, sub-band level type II PMI information can be received from the terminal. Specifically, the type II PMI information may include sub-band level amplitude information and phase information. In step S603, the amplitude information and phase information in the PMI information received by the receiving unit 220 can be used to perform amplitude and phase weighting on the spatial domain (also referred to as "beam domain")-frequency domain channel codewords of multiple beams, and the weighted vectors are merged to obtain a first channel with sub-band level. Next, in step S603, a super-resolution network is used to interpolate and denoise the first-granularity channel to obtain a second channel, wherein the second channel has a second granularity, and the second granularity is finer than the first granularity. For example, as described above, the first-granularity channel may be a sub-band level channel. In this case, the second-granularity channel can be a subcarrier-level or resource block (RB)-level channel.

[0085] Optionally, before inputting the first channel of the first granularity into the super-resolution network, the first channel can be preprocessed in step S603 to facilitate subsequent super-resolution network operations. For example, if the first channel is a spatial-frequency domain channel, a Fourier transform can be performed on the first channel in step S603 to convert the spatial-frequency domain channel into a beam-delay domain channel. Furthermore, since the channel delay component is mainly concentrated at the beginning of the delay domain channel matrix in the beam-delay domain, the delay domain channel can be truncated in step S603, retaining the beginning, and the truncated data can be divided into two channels, real and imaginary, as input to the super-resolution network. By transforming the first channel to be processed to the delay domain and truncating the data, the computational complexity of the super-resolution network can be reduced.

[0086] In step S603, various super-resolution networks can be used. Interpolation and denoising of the first channel at the first granularity can be performed using methods similar to those used for image interpolation and denoising with a super-resolution network. Furthermore, the super-resolution network can be pre-trained using a high-density reference signal.

[0087] In step S603, downlink precoding is also performed on the second channel for transmission to the terminal. In the embodiment described in conjunction with FIG3, after the base station's processing unit performs conventional channel reconstruction based on the precoding matrix indication information, it uses a super-resolution network to interpolate and denoise the first-granularity channel to obtain a second channel with finer granularity for downlink precoding.

[0088] Furthermore, according to another example of this disclosure, in addition to interpolation and denoising, a neural network can also be used to perform channel reconstruction based on precoding matrix indication information of the first granularity received from the terminal. For example, in step S603, a second channel of the second granularity can be obtained by performing channel reconstruction, interpolation, and denoising based on the precoding matrix indication information of the first granularity using a neural network including a super-resolution network.

[0089] Specifically, in step S603, a second channel can be obtained by performing channel reconstruction, interpolation, and denoising processing based on the precoding matrix indication information of the first granularity through a first sub-network, and downlink precoding can be performed on the channel of the second granularity, wherein the second granularity is finer than the first granularity. The first sub-network can be a first sub-neural network.

[0090] According to one example of this disclosure, the input dimension of the first sub-network may be higher than the output dimension of the first sub-network. In other words, the first sub-network adopts a high-dimensional input and low-dimensional output design. Due to the use of high-dimensional input, the original information from the pre-encoded matrix indication information can be preserved, and due to the use of low-dimensional output, dimensionality reduction during network processing can reduce network complexity and training difficulty.

[0091] Specifically, the input to the first sub-network may be precoding matrix indication information from the terminal or preprocessed precoding matrix indication information, and the first sub-network may reconstruct the input from the precoding matrix indication information. According to an example of this disclosure, the first sub-network may weightedly combine the amplitude and phase of the input data. For example, the precoding matrix indication information may include amplitude information and phase information. Further, the amplitude information may include broadband beam information, broadband amplitude information, and sub-band amplitude information of each beam through which the base station communicates with the terminal, as well as sub-band phase information of each sub-band. The first sub-network may combine the broadband beam information, broadband amplitude information, and sub-band amplitude information of each beam to obtain a channel amplitude matrix. Specifically, the first sub-network may obtain the channel amplitude matrix in each polarization direction according to the beam's polarization direction. Furthermore, the first sub-network may obtain the real and imaginary parts of the matrix based on the broadband beam information and the phase information of each sub-band. Similarly, the first sub-network may obtain the real and imaginary parts of the matrix in each polarization direction according to the beam's polarization direction. Then, the first sub-network can multiply the channel amplitude matrix in each polarization direction with the real part matrix and the imaginary part matrix respectively to obtain the beam-frequency domain channel matrix (also simply referred to as "beam-frequency domain channel").

[0092] Next, the first sub-network can perform a Fourier transform on the beam-frequency domain channel to transform it into a beam-delay domain channel. Furthermore, since the channel delay component is mainly concentrated at the beginning of the delay domain channel matrix in the beam-delay domain, the first sub-network can truncate the delay domain channel to reduce the dimensionality of the output.

[0093] According to one example of this disclosure, the first sub-network may include a fully connected layer (dense layer) and is used to reconstruct the input precoded matrix indication information. Specifically, the fully connected layer weightedly combines the amplitude and phase of the input data to obtain a beam-frequency domain channel, converts the beam-frequency domain channel into a beam-delay domain channel, and truncates the beam-delay domain channel to reduce the dimensionality of the network output. Alternatively, since the operation required in the weighted combining process is only the element-wise multiplication of the individual matrices, the corresponding fully connected layer can be replaced with a partially connected layer that only connects the elements that need to be directly multiplied.

[0094] According to another example of this disclosure, the first sub-network may further include one or more super-resolution networks for interpolation and denoising. The one or more super-resolution networks may be positioned before or after the aforementioned fully connected or partially connected layers. Furthermore, the aforementioned fully connected or partially connected layers may be positioned between multiple super-resolution networks.

[0095] Alternatively, according to another example of this disclosure, Figure 6 The method may further include performing at least one of temporal channel estimation enhancement and temporal prediction on multiple second channels obtained from precoding matrix indication information transmitted multiple times from the same terminal via a second sub-network. For example, the first sub-network may process precoding matrix indication information transmitted once by the terminal (e.g., transmitted within a single time slot) and perform channel reconstruction, interpolation, and denoising based on the precoding matrix indication information transmitted once by the terminal. The second sub-network includes at least one of an RNN and an LSTM network, and the second sub-network may input precoding matrix indication information transmitted multiple times by the same terminal into the RNN / LSTM network to achieve at least one of temporal channel estimation enhancement and temporal prediction.

[0096] Combined with the above Figure 6 Correspondingly, the method described also receives CSI-RS with lower density in the method executed at the terminal, and determines precoding matrix indication information based on the CSI-RS with lower density. The following will combine... Figure 7 A channel reconstruction method performed by a terminal according to an embodiment of the present disclosure is described. Figure 7This is a flowchart of a channel reconstruction method 700 performed by a terminal according to an embodiment of the present disclosure. Since the steps of the channel processing method 700 correspond to the operation of the terminal 400 described above with reference to the figures, detailed descriptions of the same content are omitted here for simplicity.

[0097] like Figure 7 As shown, in step S701, channel state information reference signals from multiple ports are received, wherein, within a time interval, the channel state information reference signals from the multiple ports have a first density in the frequency domain. This has been combined with... Figure 2 Figure 3 provides a detailed description of multi-port CSI-RS with low density, so it will not be repeated here.

[0098] In step S702, a first-granularity precoding matrix indication (PMI) is determined based on the channel state information reference signal over a time interval. This first-granularity PMI is a sub-band level PMI. As described above, the base station determines a second-granularity channel using a super-resolution network based on the first-granularity PMI, thereby achieving high-precision channel accuracy even if the PMI information fed back from the terminal is coarse-grained. In this case, the granularity of the PMI information can be further increased. For example, the granularity of the PMI information determined in step S702 can be coarser than the granularity of the PMI information specified in 3GPP standard release 15 for 5G NR.

[0099] According to one example of this disclosure, the size of the subband used when the terminal 400 communicates with its corresponding base station can be increased. For example, the resource blocks included in the subband may include more resource blocks than those included in the subband in 3GPP standard release 15 of 5G NR. This can further reduce signaling overhead. For example, the resource blocks included in the subband may be twice or more than those included in the subband in 3GPP standard release 15 of 5G NR.

[0100] According to another example of this disclosure, while increasing the size of the subband used when the terminal communicates with its corresponding base station, the quantization level of amplitude and phase feedback in the PMI information can be increased. For example, it can be increased to 16-PSK or 32-PSK. Because the subband size is increased, the signaling overhead remains substantially unchanged even when the quantization level of amplitude and phase feedback is increased.

[0101] Then, in step S703, the precoding matrix indication information can be sent to the base station so that the base station can reconstruct a downlink channel of a second granularity based on the precoding matrix indication information, wherein the second granularity is finer than the first granularity. As described above, the base station can obtain a high-precision channel using a super-resolution network even if the granularity of the PMI information fed back from the terminal is coarse by performing interpolation and denoising during channel reconstruction based on the precoding matrix indication information of the first granularity. In this case, according to an example of this disclosure, the period for determining the PMI information and sending the PMI information to the base station can be extended. This can further reduce the resource overhead of the reference signal. For example, the period for sending the PMI information can be 1.5 times, 2 times, or longer than the period for sending the PMI information in 3GPP standard release 15 of 5G NR. In addition, the period for sending the PMI information can be similarly delayed as the period for sending CSI-RS.

[0102] In combination with the above Figure 6-7 The channel reconstruction method described in this disclosure proposes to determine a second-granularity channel based on a first-granularity precoding matrix indication information during channel reconstruction, thereby providing the possibility of obtaining a channel with finer granularity while reducing signaling overhead.

[0103] Similar to determining the second-granularity channel based on the precoding matrix indication information of the first granularity, another embodiment of this disclosure proposes a similar operation for the demodulation reference signal (DMRS) to obtain a high-precision channel based on a low-density DMRS. Hereinafter, references... Figure 8 To illustrate a channel reconstruction method based on DMRS performed by a terminal according to another embodiment of the present disclosure. Figure 8 This is a flowchart of a channel reconstruction method 800 performed by a terminal according to an embodiment of the present disclosure. Since the steps of the channel processing method 800 correspond to the operation of the terminal 500 described above with reference to the figures, detailed descriptions of the same content are omitted here for simplicity.

[0104] like Figure 8 As shown, in step S801, a demodulation reference signal (DMRS) of the second density is received. In step S802, a preliminary channel estimation is performed based on the demodulation reference signal to determine a channel with a third granularity, and a super-resolution network is used to interpolate and denoise the channel with the third granularity to obtain a channel with a fourth granularity, wherein the fourth granularity is finer than the third granularity. For example, in step S802, a preliminary least squares (LS) channel estimation can be performed on the received signal on the DMRS to determine a channel with a third granularity, and then a super-resolution network is used to interpolate and denoise the channel with the third granularity to obtain a channel with a fourth granularity.

[0105] Since interpolation and denoising operations can be performed by the super-resolution network during channel reconstruction based on DMRS information in step S802, the frequency density of DMRS can be at the granularity of DMRS used in current communication systems, or at a lower frequency density. Furthermore, even with a low frequency density of DMRS, a high-precision channel can still be obtained using the super-resolution network.

[0106] According to one example of this disclosure, the density of DMRS can be 1 port per port per resource block or less. For example, for 12 ports, the DMRS density can be 1 port per port per resource block; while for 6 ports, the DMRS density can be 1 / 2 port per port per resource block. Furthermore, for example, DMRS can be transmitted using orthogonal coverage codes (OCC). As another example, DMRS can also be transmitted using time-domain orthogonal coverage codes (TD-OCC) or frequency-domain orthogonal coverage codes (FD-OCC).

[0107] According to another example of this disclosure, various super-resolution networks can be used in step S802. The first channel at the first granularity can be interpolated and denoised using a method similar to that used for image interpolation and denoising with a super-resolution network. Furthermore, the super-resolution network can be pre-trained using a high-density reference signal. Thus, in actual deployment, in step S802, the first channel obtained according to the precoding matrix indication information fed back from the terminal can be input into the trained super-resolution network for accurate channel recovery.

[0108] For example, in step S802, at least one of a Very Deep SuperResolution (VDSR) network and a Cascading Residual Network (CARN) can be used to interpolate and denoise the channel at the first granularity to obtain a second channel. Specifically, in step S802, a VDSR with 16-20 layers and a kernel size of 3 can be used to interpolate and denoise the channel at the first granularity to obtain a second channel. Since deep networks are beneficial for learning features in the channel, using deep networks can improve channel recovery. Furthermore, according to an example of this disclosure, a residual network structure can be applied in a deep super-resolution network. Specifically, the input can be superimposed before the output layer to enhance the correspondence between the output and the input.

[0109] Alternatively, in step S802, a cascaded residual convolutional network can be used, formed by introducing multiple small convolutional networks into the residual structure. In the cascaded residual network, each small convolutional network can be a 3-layer convolutional network with a kernel size of 3. Compared to deep super-resolution networks, cascaded residual networks can achieve better performance with lower complexity.

[0110] <Hardware Structure>

[0111] Furthermore, the block diagrams used in the above description of the embodiments illustrate blocks based on function. These functional blocks (structural units) are implemented through any combination of hardware and / or software. Moreover, the means of implementing each functional block are not particularly limited. That is, each functional block can be implemented using a single device that is physically and / or logically combined, or it can be implemented using multiple devices by directly and / or indirectly (e.g., via wired and / or wireless) connecting two or more physically and / or logically separate devices.

[0112] For example, a first network element in one embodiment of this disclosure can function as a computer performing the wireless communication method of this disclosure. Figure 9 This is a schematic diagram of the hardware structure of the device 900 (base station, terminal) according to an embodiment of the present disclosure. The device 900 (base station, terminal) described above can be configured as a computer device that physically includes a processor 910, a memory 920, a storage device 930, a communication device 940, an input device 950, an output device 960, a bus 970, etc.

[0113] Additionally, in the following description, the word "device" can be replaced with circuit, device, unit, etc. The hardware structure of the first network element may include one or more of the devices shown in the figure, or may not include some of the devices.

[0114] For example, only one processor 910 is shown, but there can also be multiple processors. Furthermore, processing can be performed by a single processor, or by more than one processor simultaneously, sequentially, or using other methods. Additionally, processor 910 can be mounted on more than one chip.

[0115] The functions of device 900 are implemented, for example, by reading the specified software (program) into hardware such as processor 910 and memory 920, thereby enabling processor 910 to perform calculations, control the communication performed by communication device 940, and control the reading and / or writing of data in memory 920 and storage 330.

[0116] The processor 910, for example, enables the operating system to operate, thereby controlling the computer as a whole. The processor 910 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic devices, registers, etc. For example, the aforementioned processing units can be implemented by the processor 910.

[0117] Furthermore, the processor 910 reads programs (program code), software modules, data, etc., from the memory 930 and / or communication device 940 into the memory 920, and performs various processes accordingly. As a program, a program that causes the computer to perform at least a portion of the actions described in the above embodiments can be employed. For example, the processing unit of the first network element can be implemented by a control program stored in the memory 920 and operated by the processor 910; similarly, other functional blocks can be implemented.

[0118] Memory 920 is a computer-readable recording medium, and may be constituted by at least one of the following: Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Programmable ROM (EEPROM), Random Access Memory (RAM), or other suitable storage media. Memory 920 may also be referred to as a register, cache, main memory (main storage device), etc. Memory 920 may store executable programs (program code), software modules, etc., for implementing the methods involved in one embodiment of this disclosure.

[0119] The memory 930 is a computer-readable recording medium, which may be constituted by at least one of the following: a flexible disk, a floppy disk, a magneto-optical disk (e.g., a CD-ROM (Compact Disc ROM), a Digital Universal Optical Disk, a Blu-ray disc), a removable disk, a hard disk drive, a smart card, a flash memory device (e.g., a card, a stick, a key driver), a magnetic stripe, a database, a server, or other suitable storage media. The memory 930 may also be referred to as an auxiliary storage device.

[0120] The communication device 940 is hardware (transmitting and receiving device) used for communication between computers via wired and / or wireless networks, and is also referred to as a network device, network controller, network interface card (NIC), communication module, etc. To implement, for example, frequency division duplex (FDD) and / or time division duplex (TDD), the communication device 940 may include high-frequency switches, duplexers, filters, frequency synthesizers, etc. For example, the aforementioned transmitting and receiving units can be implemented using the communication device 940.

[0121] Input device 950 is an input device that accepts input from external sources (e.g., keyboard, mouse, microphone, switch, button, sensor, etc.). Output device 960 is an output device that performs output to external sources (e.g., display, speaker, light-emitting diode (LED) lamp, etc.). Alternatively, input device 950 and output device 960 can also be integrated into a single structure (e.g., a touch panel).

[0122] Furthermore, the processor 910, memory 920, and other devices are connected via a bus 970 for communication. The bus 970 can consist of a single bus or different buses between devices.

[0123] Furthermore, electronic devices may include hardware such as microprocessors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), programmable logic devices (PLDs), and field-programmable gate arrays (FPGAs), which can be used to implement some or all of the functional blocks. For example, processor 710 can be installed using at least one of these hardware components.

[0124] (Modified Example)

[0125] Furthermore, the terms used in this specification and / or those necessary for understanding this specification may be used interchangeably with terms that have the same or similar meanings. For example, a channel and / or symbol may also be a signal (signaling). Additionally, a signal may also be a message. A reference signal may also be simply referred to as RS (Reference Signal), and depending on the applicable standard, may also be called a pilot, pilot signal, etc. Furthermore, a component carrier (CC) may also be referred to as a cell, frequency carrier, carrier frequency, etc.

[0126] Furthermore, the information and parameters described in this specification can be expressed in absolute values, relative values ​​to specified values, or other corresponding information. For example, wireless resources can be indicated by a specified index. Moreover, the formulas used to apply these parameters may differ from those explicitly disclosed in this specification.

[0127] The names used for parameters, etc., in this specification are not limiting in any way. For example, various channels (Physical Uplink Control Channel (PUCCH), Physical Downlink Control Channel (PDCCH), etc.) and information elements can be identified by any appropriate name, and therefore the various names assigned to these various channels and information elements are not limiting in any way.

[0128] The information, signals, etc., described in this specification can be represented using any of a wide variety of different technologies. For example, data, commands, instructions, information, signals, bits, symbols, chips, etc., that may be mentioned in all of the above descriptions can be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any combination thereof.

[0129] Furthermore, information and signals can be output from upper layers to lower layers and / or from lower layers to upper layers. Information and signals can be input or output via multiple network nodes.

[0130] Input or output information and signals can be stored in a specific location (such as memory) or managed through a management table. Input or output information and signals can be overwritten, updated, or supplemented. Output information and signals can be deleted. Input information and signals can be sent to other devices.

[0131] The notification of information is not limited to the methods / implementations described in this specification, and may also be carried out by other methods. For example, the notification of information may be implemented by physical layer signaling (e.g., downlink control information (DCI), uplink control information (UCI)), upper layer signaling (e.g., radio resource control (RRC) signaling, broadcast information (master information block (MIB), system information block (SIB) etc.), media access control (MAC) signaling), other signals, or combinations thereof.

[0132] In addition, physical layer signaling can also be referred to as L1 / L2 (Layer 1 / Layer 2) control information (L1 / L2 control signals), L1 control information (L1 control signals), etc. Furthermore, RRC signaling can also be referred to as RRC messages, such as RRC connection setup messages, RRC connection reconfiguration messages, etc. Additionally, MAC signaling can be communicated, for example, through a MAC control unit (MAC CE (Control Element)).

[0133] Furthermore, notification of specified information (e.g., notification of “for X”) is not limited to being made explicitly, but can also be made implicitly (e.g., by not making notification of the specified information, or by notifying other information).

[0134] The determination can be made by a value represented by 1 bit (0 or 1), by a true or false Boolean value, or by a numerical comparison (e.g., a comparison with a specified value).

[0135] Whether it is called software, firmware, middleware, microcode, hardware description language, or any other name, software should be broadly interpreted as commands, command sets, code, code segments, program code, programs, subroutines, software modules, application programs, software applications, software packages, routines, subroutines, objects, executable files, execution threads, steps, functions, etc.

[0136] Furthermore, software, commands, information, etc., can be sent or received via a transmission medium. For example, when software is sent from a website, server, or other remote resource using wired technologies (coaxial cable, optical fiber, twisted pair, digital subscriber line (DSL), etc.) and / or wireless technologies (infrared, microwave, etc.), these wired and / or wireless technologies are included within the definition of transmission medium.

[0137] The terms “system” and “network” used in this manual are interchangeable.

[0138] In this manual, the terms "base station (BS)," "wireless base station," "eNB," "gNB," "cell," "sector," "cell group," "carrier," and "component carrier" are used interchangeably. Base stations are sometimes also referred to as fixed stations, NodeBs, eNodeBs (eNBs), access points, transmitting points, receiving points, femtocells, small cells, etc.

[0139] A base station can accommodate one or more (e.g., three) cells (also called sectors). When a base station accommodates multiple cells, the entire coverage area of ​​the base station can be divided into multiple smaller areas, each of which can also provide communication services through a base station subsystem (e.g., an indoor small cell (remote radio head (RRH))). Terms such as "cell" or "sector" refer to a portion or the entire coverage area of ​​the base station and / or base station subsystem that provides communication services within that coverage area.

[0140] In this specification, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" are used interchangeably. A mobile station is sometimes also referred to by those skilled in the art as a user station, mobile unit, user unit, radio unit, remote unit, mobile device, radio device, wireless communication device, remote device, mobile user station, access terminal, mobile terminal, wireless terminal, remote terminal, handheld device, user agent, mobile client, client, or several other appropriate terms.

[0141] Furthermore, the wireless base station in this specification can also be replaced by a user terminal. For example, various methods / implementations of this disclosure can also be applied to a structure that replaces the communication between the wireless base station and the user terminal with communication between multiple user terminals (D2D, Device-to-Device). In this case, the functions of the electronic device described above can be regarded as the functions of the user terminal. In addition, terms such as "uplink" and "downlink" can also be replaced with "side". For example, the uplink channel can also be replaced with the side channel.

[0142] Similarly, the user terminal in this specification can also be replaced by a wireless base station. In this case, the functions of the user terminal described above can be regarded as the functions of the first communication device or the second communication device.

[0143] In this specification, specific actions performed via a base station may sometimes also be performed via its upper node, depending on the circumstances. Clearly, in a network consisting of one or more network nodes with a base station, various actions performed for communication with a terminal can be performed via the base station, one or more network nodes other than the base station (considering, but not limited to, Mobility Management Entities (MMEs), Serving Gateways (S-GWs), etc.), or combinations thereof.

[0144] The various methods / implementations described in this specification can be used individually or in combination, and can be switched during execution. Furthermore, the processing steps, sequences, flowcharts, etc., of the various methods / implementations described in this specification can be rearranged as long as there are no contradictions. For example, regarding the methods described in this specification, various step units are given in an exemplary order, but the method is not limited to the specific order given.

[0145] The methods / implementations described in this specification can be applied to systems utilizing Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), Super 3G, IMT-Advanced, 4G, 5G, Future Radio Access (FRA), New-RAT (Radio Access Technology), New Radio (NR), New Radio Access (NX), Future Generation Radio Access (FX), Global System for Mobile Communications (GSM), CDMA3000, Ultra Mobile Broadband (UMB), IEEE 920.11 (Wi-Fi), and IEEE... Systems based on and / or extended from WiMAX (registered trademark), IEEE 920.16, Ultra-Wideband (UWB), Bluetooth (registered trademark), other suitable wireless communication methods.

[0146] The use of the word "based on" in this specification does not imply "based on only" unless explicitly stated in other paragraphs. In other words, the use of "based on" refers to both "based on only" and "based on at least".

[0147] Any reference to units using the names "first," "second," etc., as used in this specification is not intended to fully define the number or order of these units. These names may be used in this specification as a convenient method of distinguishing two or more units. Therefore, reference to a first unit and a second unit does not imply that only two units may be used, or that the first unit must take precedence over the second unit in some form.

[0148] The term "determining" as used in this specification sometimes encompasses a variety of actions. For example, "determining" can refer to actions such as calculating, computing, processing, deriving, investigating, looking up (e.g., searching in tables, databases, or other data structures), and ascertaining. Furthermore, "determining" can also refer to actions such as receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, and accessing (e.g., accessing data in memory). Additionally, "determining" can refer to actions such as resolving, selecting, choosing, establishing, and comparing. In other words, "determining" can encompass several actions.

[0149] As used in this specification, the terms "connected," "coupled," or any variations thereof refer to any direct or indirect connection or combination between two or more units, including situations where one or more intermediate units exist between two mutually "connected" or "coupled" units. The combination or connection between units can be physical, logical, or a combination of both. For example, "connected" can also be replaced by "accessed." In this specification, it can be understood that two units are "connected" or "coupled" by using one or more wires, cables, and / or printed electrical connections, and, as several non-limiting and non-exhaustive examples, by using electromagnetic energy with wavelengths in the radio frequency region, microwave region, and / or light (both visible and invisible light) region.

[0150] When the terms "including," "comprising," and variations thereof are used in this specification or claims, these terms are open-ended, just like the term "possess." Furthermore, the term "or" as used in this specification or claims is not an XOR expression.

[0151] The present disclosure has been described in detail above; however, it will be apparent to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered ways without departing from the spirit and scope defined by the claims. Therefore, the description herein is for illustrative purposes only and is not intended to be restrictive.

Claims

1. A base station, comprising: The transmitting unit is configured to transmit channel state information reference signals of multiple ports to the terminal, wherein the channel state information reference signals of the multiple ports have a first density in the frequency domain during a time interval; The receiving unit is configured to receive precoding matrix indication information of the first granularity from the terminal; The processing unit is configured to perform channel reconstruction based on the precoding matrix indication information at the first granularity to determine a first channel, use a neural network to perform interpolation and denoising processing on the first channel at the first granularity to determine a second channel at the second granularity, and perform downlink precoding on the second channel, wherein... The second particle size is finer than the first particle size.

2. The base station as described in claim 1, wherein The channel state information reference signals of the multiple ports are low-density channel state information reference signals in the frequency domain.

3. The base station as described in claim 2, wherein The transmitting unit transmits channel state information reference signals for at least 32 ports in a time interval; Based on the plurality of ports, the channel state information reference signal is divided into at least two groups; and During a time interval, the at least two sets of channel state information reference signals are distributed across the at least four consecutive resource blocks.

4. A terminal, comprising: The receiving unit is configured to receive channel state information reference signals from multiple ports, wherein the channel state information reference signals from multiple ports have a first density in the frequency domain during a time interval. The processing unit is configured to determine precoding matrix indication information of a first granularity based on a channel state information reference signal over a time interval; as well as The transmitting unit is configured to transmit the precoding matrix indication information to a base station, so that the base station performs channel reconstruction based on the first-granularity precoding matrix indication information to determine a first channel, and uses a neural network to interpolate and denoise the first channel at the first granularity to determine a second channel at the second granularity, wherein... The second particle size is finer than the first particle size.

5. The terminal as described in claim 4, wherein The precoding matrix indication information of the first granularity is the precoding matrix indication information with coarse granularity.

6. A terminal, comprising: The receiving unit is configured to receive the demodulated reference signal of the second density. The processing unit is configured to perform preliminary channel estimation based on the demodulated reference signal to determine a channel with a third granularity, and to perform interpolation and denoising processing on the third-granularity channel using a super-resolution network to obtain a channel with a fourth granularity. The fourth particle size is finer than the third particle size.

7. The terminal as claimed in claim 6, wherein The demodulation reference signal is a low-density channel state information reference signal in the frequency domain.

8. A channel reconstruction method performed by a base station, comprising: The channel state information reference signals of multiple ports are sent to the terminal, wherein the channel state information reference signals of the multiple ports have a first density in the frequency domain during a time interval; Receive the first-granularity precoding matrix indication information from the terminal; Channel reconstruction is performed based on the precoding matrix indication information at the first granularity to determine a first channel. A neural network is then used to interpolate and denoise the first channel at the first granularity to determine a second channel at the second granularity. Downlink precoding is then performed on the second channel. The second particle size is finer than the first particle size.

9. A channel reconstruction method performed by a terminal, comprising: Receive channel state information reference signals from multiple ports, wherein the channel state information reference signals from the multiple ports have a first density in the frequency domain during a time interval; The first-granularity precoding matrix indication information is determined based on the channel state information reference signal over a time interval; as well as The precoding matrix indication information is sent to the base station so that the base station can perform channel reconstruction based on the first-granularity precoding matrix indication information to determine a first channel, and use a neural network to interpolate and denoise the first channel at the first granularity to determine a second channel at the second granularity, wherein... The second particle size is finer than the first particle size.

10. A channel reconstruction method performed by a terminal, comprising: Receive the demodulated reference signal of the second density; A preliminary channel estimate is performed based on the demodulated reference signal to determine a channel with a third granularity; A super-resolution network is used to interpolate and denoise the third-granularity channel to obtain a fourth-granularity channel, wherein... The fourth particle size is finer than the third particle size.

Images