CN117279098A

CN117279098A - Method and apparatus for wireless communication

Info

Publication number: CN117279098A
Application number: CN202210657469.7A
Authority: CN
Inventors: 张晓博
Original assignee: Shanghai Langbo Communication Technology Co Ltd
Current assignee: Shanghai Langbo Communication Technology Co Ltd
Priority date: 2022-06-10
Filing date: 2022-06-10
Publication date: 2023-12-22
Also published as: WO2023236923A1

Abstract

The invention discloses a method and a device for wireless communication. A first node receives a first message, the first message being used to determine a first set of RS resources and a first set of frequency band resources, the first set of RS resources including at least one RS resource; a first transmitter that transmits first channel information; wherein the measurement for the first RS resource group is used to generate at least one channel matrix, where the at least one channel matrix is subjected to a first operation to obtain Q1 channel matrices, and the number of channel matrices included in the at least one channel matrix is smaller than Q1; the Q1 channel matrices are used to generate the first channel information, and the number of subbands included in the at least one subband is used to determine a load size of the first channel information. The method and the device can improve the performance of channel information and have good compatibility.

Description

Method and apparatus for wireless communication

Technical Field

The present application relates to methods and apparatus in a wireless communication system, and more particularly to schemes and apparatus for CSI (Channel Status Information, channel state information) in a wireless communication system.

Background

In conventional wireless communications, a UE (User Equipment) report may include at least one of a plurality of assistance information, such as CSI (Channel Status Information, channel state information), beam Management (Beam Management) related assistance information, positioning related assistance information, and so on. Wherein the CSI includes at least one of CRI (CSI-RS Resource Indicator, channel state information reference signal resource indication), RI (Rank Indicator), PMI (Precoding Matrix Indicator, precoding indication) or CQI (Channel quality Indicator, channel quality indication).

The network device selects appropriate transmission parameters for the UE, such as camping cell, MCS (Modulation and Coding Scheme ), TPMI (Transmitted Precoding Matrix Indicator, transmit precoding matrix indication), TCI (Transmission Configuration Indication, transmit configuration indication), and the like, according to the UE's report. In addition, UE reporting may be used to optimize network parameters, such as better cell coverage, switching base stations based on UE location, etc.

In an NR (New Radio) system, priorities of CSI reports are defined, and the priorities are used to determine whether to allocate CPU (CSI Processing Unit ) resources for respective CSI reports for updating or whether to discard (drop) the respective CSI reports.

Disclosure of Invention

As the number of antennas increases, the conventional PMI feedback method brings about a large amount of redundancy overhead, and thus, in the NR (release) 18, AI (Artificial Intelligence) or ML (Machine Learning) based CSI compression is a standing term. In conventional multi-antenna systems, the calculation of CQI is typically conditioned on PMI; the CQI is calculated, for example, on the assumption that PMI reported by a UE (User Equipment) is adopted by a base station. The applicant found through research that how conventional CSI reporting supports subband-based PMI reporting, AI-or ML-based CSI compression supports similar functions would be challenging.

In view of the above, the present application discloses a solution. It should be noted that although a number of embodiments of the present application are directed to AI/ML expansion, the present application is also applicable to schemes based on conventional, e.g. linear channel reconstruction; especially considering that the specific channel reconstruction algorithm is likely to be non-standardized or self-implemented by the hardware device manufacturer. Furthermore, the unified UE reporting scheme can reduce the implementation complexity or improve the performance. Embodiments and features of embodiments in any node of the present application may be applied to any other node without conflict. The embodiments of the present application and features in the embodiments may be combined with each other arbitrarily without conflict.

Where necessary, the term in the present application may be explained with reference to descriptions of the specification protocol TS37 series and TS38 series of 3GPP (3 rd Generation PartnerProject, third generation partnership project).

The application discloses a method in a first node used for wireless communication, comprising:

receiving a first message, the first message being used to determine a first RS (Reference Signal) resource group and a first frequency band resource group, the first RS resource group including at least one RS resource, the first frequency band resource group including at least one subband (subband);

transmitting first channel information;

wherein the measurements for the first set of RS resources are used to generate at least one channel matrix, each of the at least one channel matrix corresponding to one of the at least one sub-band; obtaining Q1 channel matrixes by the at least one channel matrix through a first operation, wherein Q1 is a positive integer greater than 1, and the number of the channel matrixes included in the at least one channel matrix is smaller than Q1; the Q1 channel matrices are used to generate the first channel information, and the number of subbands included in the at least one subband is used to determine a load size of the first channel information.

As an embodiment, the above method adjusts the load size of the first channel information according to the number of sub-bands included in the at least one sub-band, thereby improving the transmission efficiency of the first channel information.

As an embodiment, the above method allows the sender of the first message to flexibly adjust the number of sub-bands included in the first frequency band resource group, thereby improving feedback efficiency; in particular the number of sub-bands comprised by said at least one sub-band is not affected by the number of channel matrices required for the generation of said first channel information.

As an embodiment, the first channel information is an output after the Q1 channel matrices are input to a first encoder.

As a sub-embodiment of the above embodiment, the first encoder is obtained by training, and each input for obtaining the training of the first encoder is composed of Q1 channel parameter matrices, where the Q1 channel parameter matrices are in one-to-one correspondence with Q1 consecutive frequency domain resources.

As an embodiment, the Q1 consecutive frequency domain resources are Q1 subbands, respectively.

As an embodiment, the Q1 consecutive frequency domain resources respectively include at least one PRB (Physical Resource Block ).

As an embodiment, the Q1 consecutive frequency domain resources respectively include at least two PRBs.

As one embodiment, the first operation includes: and the Q1 channel matrixes are respectively the same as matrixes obtained by multiplying the first channel matrixes by Q1 complex numbers, and the at least one channel matrix is composed of the first channel matrixes.

In particular, according to an aspect of the present application, the above method is characterized in that the load size of the first channel information decreases with a decrease of the number of subbands included in the at least one subband.

The method can achieve balance in the aspects of CSI precision and air interface overhead.

Specifically, according to one aspect of the present application, the method is characterized by comprising:

the first transmitter transmits second auxiliary information; wherein the second auxiliary information is used to indicate the first operation.

The above method ensures that the receiver of the first channel information and the first node have the same understanding of the first operation.

the first receiver receives first auxiliary information; wherein the first auxiliary information is used to indicate the first operation.

Specifically, according to an aspect of the present application, the method is characterized in that the first operation includes: the second channel matrix is the same as a matrix obtained by multiplying Q2 complex numbers by Q2 channel matrices respectively and then adding the complex numbers, wherein at least one channel matrix consists of the Q2 channel matrices, and Q2 is a positive integer greater than 1; the second channel matrix is any one of the Q1 channel matrices.

As an embodiment, the above method can simulate the frequency domain correlation of the wireless channel, and reduce the noise included in the output of the first encoder.

In particular, according to one aspect of the present application, the above method is characterized in that said Q2 complex numbers are valid for a first duration, said first channel information being the output after inputting at least said Q1 channel matrices into a first encoder; the first encoder is active for a second duration; the second duration and the first duration only partially overlap; the first channel information is generated within an overlap of the second duration and the first duration.

As an embodiment, the above method reduces the hardware complexity for generating the first encoder or for generating the Q2 complex numbers.

The application discloses a method in a second node for wireless communication, comprising:

transmitting a first message, the first message being used to determine a first set of RS resources and a first set of frequency band resources, the first set of RS resources including at least one RS resource, the first set of frequency band resources including at least one subband;

receiving first channel information;

wherein the first channel information is used to describe Q1 channel matrices, the Q1 channel matrices being obtained by a first operation of at least one channel matrix, the at least one channel matrix being generated based on measurements for the first RS resource group, each of the at least one channel matrix corresponding to one of the at least one sub-bands; the Q1 is a positive integer greater than 1, and the number of channel matrices included in the at least one channel matrix is smaller than the Q1; the number of subbands included in the at least one subband is used to determine a load size of the first channel information.

receiving second auxiliary information; wherein the second auxiliary information is used to determine the first operation.

transmitting first auxiliary information; wherein the first auxiliary information is used to determine the first operation.

The application discloses a first node for wireless communication, comprising:

a first receiver that receives a first message, the first message being used to determine a first set of RS resources and a first set of frequency band resources, the first set of RS resources including at least one RS resource, the first set of frequency band resources including at least one subband;

a first transmitter that transmits first channel information;

The application discloses a second node for wireless communication, comprising:

a second transmitter that transmits a first message, the first message being used to determine a first set of RS resources and a first set of frequency band resources, the first set of RS resources including at least one RS resource, the first set of frequency band resources including at least one subband;

A second receiver that receives the first channel information;

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the following drawings in which:

FIG. 1 illustrates a flow chart of communication of a first node according to one embodiment of the present application;

FIG. 2 shows a schematic diagram of a network architecture according to one embodiment of the present application;

fig. 3 shows a schematic diagram of an embodiment of a radio protocol architecture of a user plane and a control plane according to an embodiment of the present application;

FIG. 4 illustrates a hardware block diagram of a communication node according to one embodiment of the present application;

FIG. 5 illustrates a transmission flow diagram between a first node and a second node according to one embodiment of the present application;

fig. 6 shows a transmission flow diagram of second assistance information according to an embodiment of the present application;

FIG. 7 illustrates a schematic diagram of a first band resource group in accordance with one embodiment of the present application;

FIG. 8 illustrates a schematic diagram of a first operation according to one embodiment of the present application;

FIG. 9 illustrates a schematic diagram of an artificial intelligence processing system according to one embodiment of the present application;

fig. 10 shows a flow chart of transmission of first channel information according to an embodiment of the present application;

FIG. 11 shows a schematic diagram of a first encoder according to an embodiment of the present application;

FIG. 12 shows a schematic diagram of a first decoder according to one embodiment of the present application;

FIG. 13 illustrates a schematic diagram of an encoder according to an embodiment of the present application;

FIG. 14 shows a schematic diagram of a first function according to one embodiment of the present application;

FIG. 15 illustrates a schematic diagram of a decoding layer group in accordance with one embodiment of the present application;

FIG. 16 illustrates a block diagram of a processing device for use in a first node according to one embodiment of the present application;

FIG. 17 shows a block diagram of a processing apparatus for use in a second node according to one embodiment of the present application;

fig. 18 illustrates a flow chart of measurements in a first RS resource group according to one embodiment of the present application.

Detailed Description

The technical solution of the present application will be further described in detail with reference to the accompanying drawings, and it should be noted that, without conflict, the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other.

Example 1

Embodiment 1 illustrates a flow chart of communication of a first node according to one embodiment of the present application, as shown in fig. 1.

The first node 100 receives in step 101 a first message, the first message being used to determine a first set of RS resources and a first set of frequency band resources, the first set of RS resources comprising at least one RS resource, the first set of frequency band resources comprising at least one subband; transmitting first channel information in step 101;

in embodiment 1, the measurements for the first RS resource group are used to generate at least one channel matrix, each of the at least one channel matrix corresponding to one of the at least one sub-bands; obtaining Q1 channel matrixes by the at least one channel matrix through a first operation, wherein Q1 is a positive integer greater than 1, and the number of the channel matrixes included in the at least one channel matrix is smaller than Q1; the Q1 channel matrices are used to generate the first channel information, and the number of subbands included in the at least one subband is used to determine a load size of the first channel information.

As an embodiment, the first set of frequency band resources consists of the at least one subband.

Typically, the at least one channel matrix is composed of a plurality of channel matrices, and the at least one sub-band is composed of a plurality of sub-bands, and the plurality of channel matrices are in one-to-one correspondence with the plurality of sub-bands.

As an embodiment, the plurality of channel matrices are continuous or discontinuous.

Typically, the first operation is performed by the first node 100.

As an embodiment, the number of subbands included in the first set of frequency band resources is greater than the number of subbands included in the at least one subband; no subband in the first set of frequency band resources is outside the at least one subband and belongs to Q1 consecutive subbands in common with the at least one subband.

As one embodiment, the range of values of the number of subbands included in the at least one subband is divided into Q3 sub-ranges, the Q3 sub-ranges corresponding to Q3 candidate load sizes, respectively; the candidate load size corresponding to the sub-range of the number of sub-bands included in the at least one sub-band is the load size of the first channel information, and Q3 is a positive integer greater than 1 and not greater than Q1.

As an embodiment, said range of values of said number of subbands comprised in said at least one subband comprises a positive integer from 1 to Q1-1.

As one embodiment of the above embodiments, the Q3 is less than the Q1-1.

As an embodiment, the first sub-range and the second sub-range are any two sub-ranges of the Q3 sub-ranges; the maximum value in the first sub-range is smaller than the minimum value of the second sub-range, and the candidate load size corresponding to the first sub-range is smaller than the candidate load size corresponding to the second sub-range; or, the maximum value in the first sub-range is larger than the minimum value of the second sub-range, and the candidate load size corresponding to the first sub-range is larger than the candidate load size corresponding to the second sub-range.

As one embodiment, at least one of the Q3 sub-ranges includes a plurality of candidate values for the number of sub-bands included in the at least one sub-band.

As one embodiment, the load size of the first channel information decreases as the number of subbands included in the at least one subband decreases.

As an embodiment, the payload size is the number of bits included.

As an embodiment, the load size of the first information is used to determine the amount of RE (Resource Element) occupied by the first channel information.

As an embodiment, a channel matrix comprises for or corresponds to a subband: the one channel matrix indicates parameters of channels on the one subband.

As an embodiment, a channel matrix comprises for or corresponds to a subband: the one channel matrix is calculated based on an assumption that a wireless signal or a data channel is transmitted on the one subband.

As an embodiment, the first message is used to configure the at least first channel information.

As an embodiment, the first message is higher layer signaling.

As an embodiment, the first message comprises RRC signaling.

As an embodiment, the first message comprises a CSI-ReportConfig IE (Information Element ).

As an embodiment, each element in each channel matrix of the at least one channel matrix is used to determine a phase, or amplitude, or coefficient (coefficient) between two antenna ports.

As an embodiment, each of the at least one channel matrix comprises at least one eigenvector.

As an embodiment, each of the at least one channel matrix comprises at least one eigenvalue and one eigenvector.

As an embodiment, each of the at least one channel matrix comprises an original channel matrix (Raw Channel Matrix).

As an embodiment, each of the at least one channel matrix is used to determine at least one precoding matrix.

As an embodiment, for each of the at least one subband, the first channel information is used to determine a precoding matrix.

As an embodiment, the first RS resource group comprises at least one downlink RS resource for channel measurement (channel measurement).

As a sub-embodiment of the above embodiment, the first RS resource group includes at least one downlink RS resource for interference measurement (interference measurement).

As an embodiment, the measurement for the first RS resource group comprises channel measurement made in the at least one downlink RS resource for channel measurement.

As an embodiment, the measurement for the first RS resource group comprises an interference measurement made in the at least one downlink RS resource for interference measurement.

As an embodiment, any RS resource in the first RS resource group is a downlink RS resource.

As an embodiment, any RS resource in the first RS resource group is one CSI-RS (Channel Status Information Reference Signal, channel state information reference signal) resource.

As an embodiment, the first message is used to determine a subband for which the first channel information is intended.

As an embodiment, the first RS resource group is indicated by a resource escoforchannelmeasurement, or CSI-IM-resource escoforinterface, or nzp-CSI-RS-resource escoforinterface in the first message.

As an embodiment, the first set of frequency band resources is indicated by csi-ReportingBand in the first message.

As an embodiment, any sub-band of the first set of frequency band resources comprises at least one PRB (Physical Resource Block ).

As an embodiment, the first band resource group belongs to a first BWP (Bandwidth part).

As an embodiment, the number of PRBs included in all the subbands in the first band resource group except for the outermost subband in the first BWP is P1, where P1 is a positive integer multiple of 4.

As an embodiment, the P1 is indicated by higher layer signaling.

As an embodiment, the P1 relates to the number of PRBs included in the first BWP.

As an embodiment, if the first band resource group includes a first sub-band in the first BWP, the first sub-band includes a number of PRBs of P1- (Ns mod P1), where Ns is an index of a starting PRB in the first BWP; if the first band resource group includes the last (last) sub-band in the first BWP, the last (last) sub-band includes a number of PRBs (ns+nw) mod P1 or P1, where Nw is the number of PRBs included in the first BWP.

As an embodiment, P1 is one of 4, 8, 16 or 32.

As an embodiment, the first channel information is transmitted on a physical layer channel.

As an embodiment, the one physical layer channel is PUSCH (Physical Uplink Shared Channel ).

As an embodiment, the one physical layer channel is PUCCH (Physical Uplink Control Channel ).

The above embodiment uses a simpler manner to extend the first channel matrix to meet the input requirement of the encoder, where the Q1 complex numbers may be calculated by the first node 100, configured by a second node, or predetermined.

In this application, the specific implementation of the first operation may be not fixed, for example, the first channel matrix is multiplied by one complex number, and the step that may be taken is to first multiply the amplitude of the one complex number and then multiply the phase of the one complex number; the above-described embodiments therefore describe only the effect after the first operation is performed.

As an embodiment, the Q1 complex numbers are known to both the first node 100 and the receiver of the first channel information.

As one embodiment, the first operation includes: and the Q1 channel matrixes are respectively the same as matrixes obtained by multiplying the first channel matrix by the Q1 square matrixes, the at least one channel matrix is composed of the first channel matrix, and the Q1 square matrixes are reversible.

The above embodiment uses Q1 amplification matrices to extend the first channel matrix to meet the input requirement of the encoder, where the Q1 square matrices can more accurately reflect the frequency domain correlation characteristic of the wireless channel or the multipath characteristic of the time domain, so as to reduce the interference brought by the encoder.

As an embodiment, the Q1 square matrix is known to both the first node 100 and the receiver of the first channel information.

As one embodiment, the first operation includes: the second channel matrix is the same as a matrix obtained by multiplying Q2 complex numbers by Q2 channel matrices respectively and then adding the complex numbers, wherein at least one channel matrix consists of the Q2 channel matrices, and Q2 is a positive integer greater than 1; the second channel matrix is any one of the Q1 channel matrices.

An advantage of the above-described embodiments is that it enables a second node to conveniently perform an inverse operation to the first operation.

As one embodiment, the Q2 complex numbers vary as the second channel matrix varies among the Q1 matrices.

Example 2

Embodiment 2 illustrates a schematic diagram of a network architecture according to one embodiment of the present application, as shown in fig. 2. Fig. 2 illustrates the system architecture of 5G NR (new radio, new air interface), LTE (Long-Term Evolution) and LTE-a (Long-Term Evolution Advanced, enhanced Long-Term Evolution). The 5G NR or LTE network architecture 200 may be referred to as 5GS (5 GSystem)/EPS (Evolved Packet System ) some other suitable terminology. EPS 200 may include a UE (User Equipment) 201, ng-RAN (next generation radio access Network) 202, epc (Evolved Packet Core )/5G-CN (5G Core Network) 210, hss (Home Subscriber Server ) 220, and internet service 230. The EPS may interconnect with other access networks, but these entities/interfaces are not shown for simplicity. As shown, EPS provides packet-switched services, however, those skilled in the art will readily appreciate that the various concepts presented throughout this application may be extended to networks providing circuit-switched services or other cellular networks. The NG-RAN includes NR node bs (gnbs) 203 and other gnbs 204. The gNB203 provides user and control plane protocol termination towards the UE 201. The gNB203 may be connected to other gnbs 204 via an Xn interface (e.g., backhaul). The gNB203 may also be referred to as a base station, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a Basic Service Set (BSS), an Extended Service Set (ESS), a TRP, or some other suitable terminology. The gNB203 provides the UE201 with an access point to the EPC/5G-CN 210. Examples of UE201 include a cellular telephone, a smart phone, a Session Initiation Protocol (SIP) phone, a laptop, a Personal Digital Assistant (PDA), a satellite radio, a non-terrestrial base station communication, a satellite mobile communication, a global positioning system, a multimedia device, a video device, a digital audio player (e.g., MP3 player), a camera, a game console, an drone, an aircraft, a narrowband internet of things device, a machine-type communication device, a land-based vehicle, an automobile, a wearable device, or any other similar functional device. Those of skill in the art may also refer to the UE201 as a mobile station, a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless communication device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, a client, or some other suitable terminology. The gNB203 is connected to the EPC/5G-CN 210 through an S1/NG interface. EPC/5G-CN 210 includes MME (Mobility Management Entity )/AMF (Authentication Management Field, authentication management domain)/UPF (User Plane Function ) 211, other MME/AMF/UPF214, S-GW (Service Gateway) 212, and P-GW (Packet Date Network Gateway, packet data network Gateway) 213. The MME/AMF/UPF211 is a control node that handles signaling between the UE201 and the EPC/5G-CN 210. In general, the MME/AMF/UPF211 provides bearer and connection management. All user IP (Internet Protocal, internet protocol) packets are transported through the S-GW212, which S-GW212 itself is connected to P-GW213. The P-GW213 provides UE IP address assignment as well as other functions. The P-GW213 is connected to the internet service 230. Internet services 230 include operator-corresponding internet protocol services, which may include, in particular, the internet, intranets, IMS (IP Multimedia Subsystem ) and packet-switched streaming services.

As an embodiment, the UE201 corresponds to the first node in the present application, and the gNB203 corresponds to the second node in the present application.

As an embodiment, the UE201 supports the generation of reports using AI (Artificial Intelligence ) or Machine Learning (Machine Learning).

As an embodiment, the UE201 supports generating a trained model using training data or generating a part of parameters in a trained model using training data.

As an embodiment, the UE201 supports determining at least part of the parameters of the CNN (Conventional Neural Networks, convolutional neural network) for CSI reconstruction by training.

As an embodiment, the UE201 is a Massive-MIMO enabled terminal.

As an embodiment, the gNB203 supports Massive-MIMO based transmission.

As an embodiment, the gNB203 supports decompression of CSI using AI or deep learning.

As an embodiment, the gNB203 is a macro cell (marcocelluar) base station.

As one example, the gNB203 is a Micro Cell (Micro Cell) base station.

As an embodiment, the gNB203 is a PicoCell (PicoCell) base station.

As an example, the gNB203 is a home base station (Femtocell).

As an embodiment, the gNB203 is a base station device supporting a large delay difference.

As an embodiment, the gNB203 is a flying platform device.

As one embodiment, the gNB203 is a satellite device.

As an embodiment, the first node and the second node in the present application are the UE201 and the gNB203, respectively.

Example 3

Embodiment 3 shows a schematic diagram of an embodiment of a radio protocol architecture according to one user plane and control plane of the present application, as shown in fig. 3. Fig. 3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for the user plane 350 and the control plane 300, fig. 3 shows the radio protocol architecture for the control plane 300 for a first node device (RSU in UE or V2X, in-vehicle device or in-vehicle communication module) and a second node device (gNB, RSU in UE or V2X, in-vehicle device or in-vehicle communication module), or between two UEs, in three layers: layer 1, layer 2 and layer 3. Layer 1 (L1 layer) is the lowest layer and implements various PHY (physical layer) signal processing functions. The L1 layer will be referred to herein as PHY301. Layer 2 (L2 layer) 305 is above PHY301 and is responsible for the links between the first node device and the second node device and the two UEs through PHY301. The L2 layer 305 includes a MAC (Medium Access Control ) sublayer 302, an RLC (Radio Link Control, radio link layer control protocol) sublayer 303, and a PDCP (Packet Data Convergence Protocol ) sublayer 304, which terminate at the second node device. The PDCP sublayer 304 provides data ciphering and integrity protection, and the PDCP sublayer 304 also provides handover support for the first node device to the second node device. The RLC sublayer 303 provides segmentation and reassembly of data packets, retransmission of lost data packets by ARQ, and RLC sublayer 303 also provides duplicate data packet detection and protocol error detection. The MAC sublayer 302 provides mapping between logical and transport channels and multiplexing of logical channels. The MAC sublayer 302 is also responsible for allocating the various radio resources (e.g., resource blocks) in one cell among the first node devices. The MAC sublayer 302 is also responsible for HARQ operations. The RRC (Radio Resource Control ) sublayer 306 in layer 3 (L3 layer) in the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the second node device and the first node device. The radio protocol architecture of the user plane 350 includes layer 1 (L1 layer) and layer 2 (L2 layer), and the radio protocol architecture for the first node device and the second node device in the user plane 350 is substantially the same for the physical layer 351, the PDCP sublayer 354 in the L2 layer 355, the RLC sublayer 353 in the L2 layer 355, and the MAC sublayer 352 in the L2 layer 355 as the corresponding layers and sublayers in the control plane 300, but the PDCP sublayer 354 also provides header compression for upper layer data packets to reduce radio transmission overhead. Also included in the L2 layer 355 in the user plane 350 is an SDAP (Service DataAdaptation Protocol ) sublayer 356, the SDAP sublayer 356 being responsible for mapping between QoS flows and data radio bearers (DRBs, data Radio Bearer) to support diversity of traffic. Although not shown, the first node apparatus may have several upper layers above the L2 layer 355, including a network layer (e.g., IP layer) that terminates at the P-GW on the network side and an application layer that terminates at the other end of the connection (e.g., remote UE, server, etc.).

As an embodiment, the radio protocol architecture in fig. 3 is applicable to the first node in the present application.

As an embodiment, the radio protocol architecture in fig. 3 is applicable to the second node in the present application.

As an embodiment, the reference signal in the present application is generated in the PHY301.

As an embodiment, the first channel information in the present application is generated in the PHY301.

As an embodiment, the first channel information in the present application is generated in the MAC sublayer 302.

As an embodiment, the first message in the present application is generated in the RRC sublayer 306.

As an embodiment, the first message in the present application is generated in the MAC sublayer 302.

Example 4

Embodiment 4 shows a schematic diagram of hardware modules of a communication node according to an embodiment of the present application, as shown in fig. 4. Fig. 4 is a block diagram of a first communication device 450 and a second communication device 410 communicating with each other in an access network.

The first communication device 450 includes a controller/processor 459, a memory 460, a data source 467, a transmit processor 468, a receive processor 456, a multi-antenna transmit processor 457, a multi-antenna receive processor 458, a transmitter/receiver 454, and an antenna 452.

The second communication device 410 includes a controller/processor 475, a memory 476, a receive processor 470, a transmit processor 416, a multi-antenna receive processor 472, a multi-antenna transmit processor 471, a transmitter/receiver 418, and an antenna 420.

In the transmission from the second communication device 410 to the first communication device 450, upper layer data packets from the core network are provided to a controller/processor 475 at the second communication device 410. The controller/processor 475 implements the functionality of the L2 layer. In the transmission from the second communication device 410 to the first communication device 450, a controller/processor 475 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation to the first communication device 450 based on various priority metrics. The controller/processor 475 is also responsible for retransmission of lost packets and signaling to the first communication device 450. The transmit processor 416 and the multi-antenna transmit processor 471 implement various signal processing functions for the L1 layer (i.e., physical layer). A transmit processor 416 performs channel coding and interleaving to facilitate Forward Error Correction (FEC) at the second communication device 410, as well as mapping of signal clusters based on various modulation schemes, e.g., binary Phase Shift Keying (BPSK), quadrature Phase Shift Keying (QPSK), M-phase shift keying (M-PSK), M-quadrature amplitude modulation (M-QAM). The multi-antenna transmit processor 471 digitally space-precodes the coded and modulated symbols, including codebook-based precoding and non-codebook-based precoding, and beamforming processing, to generate one or more spatial streams. A transmit processor 416 then maps each spatial stream to a subcarrier, multiplexes with reference signals (e.g., pilots) in the time and/or frequency domain, and then uses an Inverse Fast Fourier Transform (IFFT) to generate a physical channel carrying the time domain multicarrier symbol stream. The multi-antenna transmit processor 471 then performs transmit analog precoding/beamforming operations on the time domain multi-carrier symbol stream. Each transmitter 418 converts the baseband multicarrier symbol stream provided by the multiple antenna transmit processor 471 to a radio frequency stream and then provides it to a different antenna 420.

In a transmission from the second communication device 410 to the first communication device 450, each receiver 454 receives a signal at the first communication device 450 through its respective antenna 452. Each receiver 454 recovers information modulated onto a radio frequency carrier and converts the radio frequency stream into a baseband multicarrier symbol stream that is provided to a receive processor 456. The receive processor 456 and the multi-antenna receive processor 458 implement various signal processing functions for the L1 layer. A multi-antenna receive processor 458 performs receive analog precoding/beamforming operations on the baseband multi-carrier symbol stream from the receiver 454. The receive processor 456 converts the baseband multicarrier symbol stream after receiving the analog precoding/beamforming operation from the time domain to the frequency domain using a Fast Fourier Transform (FFT). In the frequency domain, the physical layer data signal and the reference signal are demultiplexed by the receive processor 456, wherein the reference signal is to be used for channel estimation, and the data signal is subjected to multi-antenna detection in the multi-antenna receive processor 458 to recover any spatial stream destined for the first communication device 450. The symbols on each spatial stream are demodulated and recovered in a receive processor 456 and soft decisions are generated. A receive processor 456 then deinterleaves and channel decodes the soft decisions to recover the upper layer data and control signals that were transmitted by the second communication device 410 on the physical channel. The upper layer data and control signals are then provided to the controller/processor 459. The controller/processor 459 implements the functions of the L2 layer. The controller/processor 459 may be associated with a memory 460 that stores program codes and data. Memory 460 may be referred to as a computer-readable medium. In the transmission from the second communication device 410 to the second node 450, the controller/processor 459 provides demultiplexing between transport and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover upper layer data packets from the core network. The upper layer packets are then provided to all protocol layers above the L2 layer. Various control signals may also be provided to L3 for L3 processing.

In the transmission from the first communication device 450 to the second communication device 410, a data source 467 is used at the first communication device 450 to provide upper layer data packets to a controller/processor 459. Data source 467 represents all protocol layers above the L2 layer. Similar to the transmit functions at the second communication device 410 described in the transmission from the second communication device 410 to the first communication device 450, the controller/processor 459 implements header compression, encryption, packet segmentation and reordering, and multiplexing between logical and transport channels based on radio resource allocations, implementing L2 layer functions for the user and control planes. The controller/processor 459 is also responsible for retransmission of lost packets and signaling to the second communication device 410. The transmit processor 468 performs channel coding, interleaving, modulation mapping, the multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based precoding and non-codebook-based precoding, and beamforming processing, and then the transmit processor 468 modulates the generated spatial stream into a multi-carrier/single-carrier symbol stream, which is analog precoded/beamformed in the multi-antenna transmit processor 457 before being provided to the different antennas 452 via the transmitter 454. Each transmitter 454 first converts the baseband symbol stream provided by the multi-antenna transmit processor 457 into a radio frequency symbol stream and provides it to an antenna 452.

In the transmission from the first communication device 450 to the second communication device 410, the function at the second communication device 410 is similar to the receiving function at the first communication device 450 described in the transmission from the second communication device 410 to the first communication device 450. Each receiver 418 receives radio frequency signals through its corresponding antenna 420, converts the received radio frequency signals to baseband signals, and provides the baseband signals to a multi-antenna receive processor 472 and a receive processor 470. The receive processor 470 and the multi-antenna receive processor 472 collectively implement the functions of the L1 layer. The controller/processor 475 implements L2 layer functions. The controller/processor 475 may be associated with a memory 476 that stores program codes and data. Memory 476 may be referred to as a computer-readable medium. In the transmission from the first communication device 450 to the second communication device 410, a controller/processor 475 provides demultiplexing between transport and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover upper layer data packets from the UE 450. Upper layer packets from the controller/processor 475 may be provided to the core network.

As an embodiment, the first communication device 450 apparatus includes: at least one processor and at least one memory including computer program code; the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus of the first communication device 450 to at least: receiving a first message, the first message being used to determine a first set of RS resources and a first set of frequency band resources, the first set of RS resources including at least one RS resource, the first set of frequency band resources including at least one subband; transmitting first channel information; wherein the measurements for the first set of RS resources are used to generate at least one channel matrix, each of the at least one channel matrix corresponding to one of the at least one sub-band; obtaining Q1 channel matrixes by the at least one channel matrix through a first operation, wherein Q1 is a positive integer greater than 1, and the number of the channel matrixes included in the at least one channel matrix is smaller than Q1; the Q1 channel matrices are used to generate the first channel information, and the number of subbands included in the at least one subband is used to determine a load size of the first channel information.

As an embodiment, the first communication device 450 includes: a memory storing a program of computer-readable instructions that, when executed by at least one processor, produce acts comprising: receiving the first message; and transmitting the at least first channel information.

As an embodiment, the second communication device 410 apparatus includes: at least one processor and at least one memory including computer program code; the at least one memory and the computer program code are configured for use with the at least one processor. The second communication device 410 means at least: transmitting a first message, the first message being used to determine a first set of RS resources and a first set of frequency band resources, the first set of RS resources including at least one RS resource, the first set of frequency band resources including at least one subband; receiving first channel information; wherein the first channel information is used to describe Q1 channel matrices, the Q1 channel matrices being obtained by a first operation of at least one channel matrix, the at least one channel matrix being generated based on measurements for the first RS resource group, each of the at least one channel matrix corresponding to one of the at least one sub-bands; the Q1 is a positive integer greater than 1, and the number of channel matrices included in the at least one channel matrix is smaller than the Q1; the number of subbands included in the at least one subband is used to determine a load size of the first channel information.

As an embodiment, the second communication device 410 apparatus includes: a memory storing a program of computer-readable instructions that, when executed by at least one processor, produce acts comprising: sending the first message; receiving the at least first channel information;

as an embodiment, the first communication device 450 corresponds to a first node in the present application.

As an embodiment, the second communication device 410 corresponds to a second node in the present application.

For one embodiment, the first communication device 450 is a UE and the second communication device 410 is a base station.

As an embodiment, the antenna 452, the receiver 454, the multi-antenna receive processor 458, the receive processor 456 are used for the measurements for the first RS resource group.

As an embodiment, the controller/processor 459 is used for the measurement for the first RS resource group.

As an embodiment, the controller/processor 459 is used to generate the at least first channel information.

As an embodiment, the antenna 452, the transmitter 454, the multi-antenna transmit processor 457, the transmit processor 468, the controller/processor 459 is used to transmit the at least first channel information.

As an embodiment, the antenna 420, the transmitter 418, the multi-antenna transmit processor 471, the transmit processor 416 is configured to transmit a reference signal on at least one RS resource of the first set of RS resources.

For one embodiment, the controller/processor 475 is configured to transmit a reference signal on at least one RS resource in the first set of RS resources.

As an embodiment, the antenna 420, the receiver 418, the multi-antenna receive processor 472, the receive processor 470, the controller/processor 475 is configured to receive the at least first channel information.

Example 5

Embodiment 5 illustrates a transmission flow diagram between a first node and a second node according to one embodiment of the present application, as shown in fig. 5. The first auxiliary information in fig. 5 is optional.

For the first node N1, in step S100, a first message is received; transmitting first channel information in step S101;

for the second node N2, in step S200, the first message is sent; receiving the first channel information in step S201;

in embodiment 5, the first message is used to determine a first set of RS resources and a first set of frequency band resources, the first set of RS resources including at least one RS resource, the first set of frequency band resources including at least one subband; the measurements for the first set of RS resources are used to generate at least one channel matrix, each of the at least one channel matrix corresponding to one of the at least one sub-band; obtaining Q1 channel matrixes by the at least one channel matrix through a first operation, wherein Q1 is a positive integer greater than 1, and the number of the channel matrixes included in the at least one channel matrix is smaller than Q1; the Q1 channel matrices are used to generate the first channel information, and the number of subbands included in the at least one subband is used to determine a load size of the first channel information.

As an embodiment, the first channel information is non-codebook based.

As an embodiment, the first channel information is used to describe Q1 channel matrices, i.e. the Q1 channel matrices are used to generate the channel information.

As an embodiment, the second node N2 recovers Q1 reference channel matrices according to the first channel information in step S201; performing a second operation on the Q1 reference channel matrices to obtain at least one recovered channel matrix, each of the at least one recovered channel matrix corresponding to one of the at least one subband.

The second operation may be considered as an inverse of the first operation; generally, how the second operation is performed depends on the implementation algorithm of the hardware vendor; for example, if the first operation is equivalent to a matrix operation, the second matrix is an inverse of the one matrix or a generalized inverse; the second operation may also be performed, for example, as part of artificial intelligence decoding.

As an embodiment, the Q1 reference channel matrices are not identical to the Q1 channel matrices.

The embodiment avoids limiting the first node and the second node to adopt completely matched encoders and decoders, is beneficial to the realization flexibility of different equipment manufacturers, and reduces the hardware complexity.

As an embodiment, the at least one recovered channel matrix corresponds one-to-one to the at least one channel matrix.

As an embodiment, the second node N2 transmits first auxiliary information in step S200, and the first node N1 receives the first auxiliary information in step S100; the first auxiliary information is used to indicate the first operation.

Typically, the first auxiliary information includes higher layer signaling, such as MAC CE (Control Element) or RRC signaling.

As an embodiment, the first auxiliary information is used to configure parameters of the first operation, such as Q1 complex numbers, Q1 square matrices, or Q2 complex numbers in embodiment 1.

As an embodiment, the parameters of the first operation are validated until they are reconfigured.

Fig. 5 does not limit the front-to-back relationship between the first assistance information and the transmission time of the first message, and the first assistance information is transmitted before, after, or in the same RRC message.

Example 6

Embodiment 6 illustrates a transmission flow diagram of the second auxiliary information according to one embodiment of the present application, as shown in fig. 6.

For the first node N1, in step S1001, second auxiliary information is transmitted;

for the second node N2, in step S2001, second auxiliary information is received;

in embodiment 6, the second auxiliary information is used to indicate the first operation.

As an embodiment, the second auxiliary information is used to indicate parameters of the first operation, such as Q1 complex numbers, Q1 square matrices, or Q2 complex numbers in embodiment 1.

The parameters of how the first node calculates the first operation may be determined by the hardware device manufacturer, e.g. by frequency domain correlation fitting of the wireless channel, or by multipath fitting in the time domain, or by selecting a set of parameters that minimize the encoder interference.

Typically, the second auxiliary information includes higher layer signaling, such as MAC CE (Control Element) or RRC signaling.

As an embodiment, the sending of the second assistance information is before receiving the first message.

As an embodiment, the sending of the second assistance information is after receiving the first message.

As an embodiment, a channel matrix includes at least one eigenvector (eigenevector).

As an embodiment, a channel matrix includes at least one eigenvector (eigenvector) and an eigenvalue corresponding to each eigenvector of the at least one eigenvector.

Example 7

Embodiment 7 illustrates a schematic diagram of a first band resource group according to one embodiment of the present application, as shown in fig. 7. In fig. 7, the blank squares represent one subband, and the gray filled squares represent one subband in the first band resource group.

In embodiment 7, the first band resource group includes Q2 subbands (shown in fig. 7 with boxes filled with #1, #2, #3, …, # q2), and the measurements for the first RS resource group are used to generate Q2 channel matrices, where the Q2 channel matrices are in one-to-one correspondence with the Q2 subbands; the Q2 channel matrixes are subjected to first operation to obtain Q1 channel matrixes, wherein Q1 is a positive integer larger than Q2; the Q1 channel matrices are used to generate first channel information, and the Q2 is used to determine a load size of the first channel information.

As an embodiment, the first set of frequency band resources includes a number of subbands greater than Q2, and there is no subband outside the Q2 subbands in the first set of frequency band resources and the Q2 subbands together belong to Q1 consecutive subbands.

Example 8

Embodiment 8 illustrates a schematic diagram of a first operation according to one embodiment of the present application, as shown in fig. 8.

In embodiment 8, at least one channel matrix is subjected to the first operation to obtain Q1 channel matrices.

As an embodiment, the at least one channel matrix is composed of Q2 channel matrices (e.g. in embodiment 7), each of the Q2 channel matrices includes V column vectors, a V-th column vector (V is from 1 to V) is taken from each of the Q2 channel matrices to form a matrix of Q2 columns, and the first operation includes multiplying the matrix of Q2 columns by a first matrix to obtain a matrix of Q1 columns, and Q1 column vectors in the matrix of Q1 columns are V-th column vectors of the Q1 channel matrices, respectively, and the first matrix is a Q2 row and a Q1 column.

The above embodiment is a more general description, for example, when Q1 is 1, the first matrix is degraded into a vector, that is, the Q1 complex numbers in the present application, and for example, when Q1 is 1, the Q1 complex numbers in the present application are a column vector in the first matrix.

As an embodiment, V is 1.

As an embodiment, the V is not greater than 8.

As an embodiment, the V is indicated by RI fed back by the first node.

As an embodiment, the first node transmits second assistance information, which is used to determine the first matrix.

As an embodiment, the Q2 channel matrices correspond to Q2 subbands, respectively, and the first matrix is related to the positions of the Q2 subbands.

As an embodiment, the Q2 subbands belong to Q1 consecutive subbands in the first BWP, and the positions of the Q2 subbands in the Q1 consecutive subbands are the same as the positions of the Q2 channel matrices in the Q1 channel matrices.

In the above embodiment, only Q1-Q2 column vectors in the first matrix need to be determined, and the column vectors corresponding to the Q2 channel matrices are fixed.

How to calculate the first matrix may be determined by the hardware device manufacturer or by a codebook-like scheme, a non-limiting embodiment of which is described below.

Assuming Q2 is 3, the first matrix is represented as follows:

wherein the v-th matrix of the matrix M corresponds to the Q2 channel matrices ₁ Column vector, v ₂ Column vector sum v ₃ The three column vectors are respectively And->For the v-th column vector out of these three column vectors in the matrix M is +.>Wherein the v-th column vector is spaced from the v-th column vector in matrix M ₁ The closer the column vectors, m _1,v The larger; similar m _2,v And m _3,v Similar features are also present.

As an embodiment, to ensure that the first node and the second node understand the first matrix identically, the first auxiliary information or the second auxiliary information only needs to indicate that in the above formulaM of (2) _1,v ,m _2,v And m _3,v And f.

Example 9

Embodiment 9 illustrates a schematic diagram of an artificial intelligence processing system according to one embodiment of the present application, as shown in fig. 9. Fig. 9 includes a first processor, a second processor, a third processor, and a fourth processor.

In embodiment 9, the first processor sends a first data set to the second processor, the second processor generates a target first type parameter set according to the first data set, the second processor sends the generated target first type parameter set to the third processor, and the third processor processes the second data set by using the target first type parameter set to obtain a first type output, and then sends the first type output to the fourth processor.

As one embodiment, the third processor sends a first type of feedback to the second processor, the first type of feedback being used to trigger a recalculation or update of the target first type of parameter set.

As an embodiment, the fourth processor sends a second type of feedback to the first processor, the second type of feedback being used to generate the first data set or the second data set, or the second type of feedback being used to trigger the sending of the first data set or the second data set.

As one embodiment, the first processor generates the first data set and the second data set from measurements of a first wireless signal, the first wireless signal including a downlink RS.

As an embodiment, the second data set is based on measurements of the first set of RS resources.

As an embodiment, the first processor and the third processor belong to a first node, and the fourth processor belongs to a second node.

As an embodiment, the first class of output comprises the at least first channel information.

As an embodiment, the first type of output comprises channel information belonging to a first type of the at least first channel information.

As an embodiment, the second processor belongs to the first node.

The above embodiments avoid the transfer of the first data set to the second node.

As an embodiment, the second processor belongs to a second node.

The above-described embodiments reduce the complexity of the first node.

As an embodiment, the first Data set is Training Data (Training Data) and the second Data set is interference Data (Interference Data), and the second processor is configured to train a model, the trained model being described by the target first class parameter set.

Since the occupied frequency domain resources of the first data set tend to be deterministic, the subband patterns (or frequency domain locations) supported by the input of the trained model may also be limited.

As one embodiment, the third processor constructs a model according to the target first class parameter set, then inputs the second data set into the constructed model to obtain the first class output, and then sends the first class output to the fourth processor.

As a sub-embodiment of the above embodiment, the third processor includes a first encoder of the present application, the first encoder being described by the target first class parameter set, the generation of the first class output being performed by the first encoder.

As one embodiment, the third processor calculates an error of the first class output from actual data to determine a performance of the trained model; the actual data is data transferred by the first processor received after the second data set.

The above embodiments are particularly suitable for prediction related reporting.

As one embodiment, the third processor uses the recovered reference data set from the first type of output, and the error of the reference data set from the second data set is used to generate the first type of feedback.

The recovery of the reference data set typically uses an inverse operation similar to the target first type parameter set, and the above embodiments are particularly suitable for reporting CSI compression correlations.

As one embodiment, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model cannot meet the requirements, the second processor may recalculate the target first class parameter set.

As a sub-embodiment of the above embodiment, the third processor includes a first reference decoder of the present application, the first reference decoder being described by the target first class parameter set. The input of the first reference decoder comprises the first class of output and the output of the first reference decoder comprises the reference data set.

Typically, the performance of the trained model is considered unsatisfactory when the error is excessive or not updated for too long.

As an embodiment, the third processor belongs to a second node, and the first node reports the target first class parameter set to the second node.

Example 10

Embodiment 10 illustrates a flow chart of transmission of first channel information according to one embodiment of the present application, as shown in fig. 10. In fig. 10, the first reference decoder is optional.

In embodiment 10, the first encoder and the first decoder belong to a first node and a second node, respectively; wherein the first encoder belongs to a first receiver and the first decoder belongs to a second receiver.

The first receiver generating the at least first channel information using a first encoder; wherein the input of the first encoder comprises a first channel input, the first encoder being obtained by training; the first channel input is derived from measurements for a first set of RS resources; the first channel input comprises Q1 channel matrices; the first node feeds back first channel information to the second node through an air interface;

The second receiver generating at least one recovered channel matrix using the first decoder, the at least one recovered channel matrix corresponding one-to-one to the at least one channel matrix measured by the first node; wherein the input of the first decoder comprises the first channel information, and the first decoder is obtained through training.

As an embodiment, the first node maintains a first reference decoder, which obtains a first monitor output according to the first channel information, and an error between the first monitor output and the Q1 channel matrices may be used to monitor performance of the first encoder, and a common error may be a mean square error, a cosine similarity, or the like.

As an embodiment, the first reference decoder and the first decoder are independently generated or independently maintained, so both may be only approximate, although their purpose is to perform the inverse operation of the first encoder.

As an embodiment, the first receiver includes the third processor of embodiment 9.

As an embodiment, the first channel input belongs to the second data set of embodiment 9.

As an embodiment, the training of the first encoder is performed at the first node.

As an embodiment, the training of the first encoder is performed by the second node.

As an embodiment, the at least one recovered channel matrix is known only to the second node.

As an embodiment, the at least one channel matrix is known only to the first node.

As an embodiment, the at least one recovered channel matrix and the at least one channel matrix cannot be considered to be identical.

Example 11

Embodiment 11 illustrates a schematic diagram of a first encoder according to one embodiment of the present application, as shown in fig. 11. In fig. 11, the first sub-decoder is optional.

In embodiment 11, the first encoder includes a first sub-encoder and a second sub-encoder, and the first channel information is generated after a first channel input including Q1 channel matrices sequentially passes through the first sub-encoder and the second sub-encoder.

In embodiment 11, the first data set employed for training of the first sub-encoder comprises channel matrices for consecutive at least Q1 sub-bands, the output of the first sub-encoder being taken as input to the first sub-decoder to obtain a second monitor output, the error between the second monitor output and the Q1 channel matrices being used to monitor the performance of the first sub-encoder.

As an embodiment, the second sub-encoder is obtained by training.

Example 12

Embodiment 12 illustrates a schematic diagram of a first decoder according to one embodiment of the present application, as shown in fig. 12.

In embodiment 12, the at least one recovered channel matrix is obtained after the first channel information has sequentially passed through the second sub-decoder and the second operation.

How the second operation is implemented is determined by the hardware device manufacturer, for example, the output of the second sub-decoder includes Q1 recovered channel matrices, i.e., the second sub-decoder corresponds to the inverse operation of the first encoder, and the Q1 recovered channel matrices are multiplied by the inverse of the first matrix to obtain the at least one recovered channel matrix.

In addition, the second operation may also be implemented using an artificial intelligence algorithm, the output of the second sub-decoder is not limited to Q1 restored channel matrices, and the second sub-encoder and the second operation as a whole do not need to be distinguished.

Example 13

Embodiment 13 illustrates a schematic diagram of an encoder according to an embodiment of the present application, as shown in fig. 13. In fig. 13, the first encoder includes P1 encoding layers, i.e., encoding layers #1, #2, # P1.

The one encoder of embodiment 13 is applicable to one or more of the first encoder, the first sub-encoder, or the second sub-encoder of the present application.

As an embodiment, the P1 is 2, that is, the P1 coding layers include a coding layer #1 and a coding layer #2, and the coding layer #1 and the coding layer #2 are a convolution layer and a full link layer, respectively; at the convolutional layer, at least one convolutional kernel is used to convolve the first channel input to generate a corresponding feature map, at least one feature map of the convolutional layer output is reformed (reshape) into a vector input to the full concatenation layer; the full link layer converts the one vector into an output (e.g., first channel information). For more details, reference may be made to CNN-related technical literature, such as, for example, chao-Kai Wen, deep Learning for Massive MIMO CSI Feedback, IEEE WIRELESS COMMUNICATIONS LETTERS, VOL.7, NO., octber 2018, and the like.

As an embodiment, the P1 is 3, that is, the P1 coding layers include a full-concatenated layer, a convolutional layer, and a pooling layer.

Example 14

Embodiment 14 illustrates a schematic diagram of a first function according to one embodiment of the present application, as shown in fig. 14. In fig. 14, the first function includes a pre-processing layer, and P2 decoding groups of layers, i.e., decoding groups of layers #1, #2, # P2, each decoding group of layers including at least one decoding layer.

The structure of the first function is applicable to one or more of the first decoder, the first sub-decoder, the second sub-decoder, and the first reference decoder of the present application.

As an embodiment, the preprocessing layer is a full link layer that enlarges the size of the first channel information to the size of the first channel input.

As an embodiment, the structure of any two decoding layer groups of the P2 decoding layer groups is the same, the structure includes the number of decoding layers included, the size of the input parameter and the size of the output parameter of each decoding layer included, and so on.

As an embodiment, the second node indicates the structure of the P2 and the decoding layer group to the first node, which indicates other parameters of the first function through the second signaling.

As an embodiment, the other parameter includes at least one of a threshold of the activation function, a size of the convolution kernel, a step size of the convolution kernel, and a weight between feature maps.

Example 15

Embodiment 15 illustrates a schematic diagram of a decoding layer group according to one embodiment of the present application, as shown in fig. 15. In fig. 15, decoding layer group #j includes L layers, i.e., layers #1, #2, #l; the decoding layer group is any decoding layer group of the P2 decoding layer groups.

As an embodiment, the L is 4, the first layer of the L layers is an input layer, and the three subsequent layers of the L layers are all convolution layers, and for more details reference may be made to technical literature related to CNN, such as, for example, chao-Kai Wen, deep Learning for Massive MIMO CSI Feedback, IEEE WIRELESS COMMUNICATIONS LETTERS, VOL.7, NO., octber 2018, and the like.

As an embodiment, the L layers include at least one convolution layer and one pooling layer.

Example 16

Embodiment 16 illustrates a block diagram of a processing apparatus for use in a first node according to one embodiment of the present application; as shown in fig. 16. In fig. 16, a processing device 1600 in a first node includes a first receiver 1601 and a first transmitter 1602.

The first receiver 1601 receives a first message, the first message being used to determine a first RS resource group and a first frequency band resource group, the first RS resource group including at least one RS resource, the first frequency band resource group including at least one subband; a first transmitter 1602 that transmits first channel information;

in embodiment 16, the measurements for the first RS resource group are used to generate at least one channel matrix, each of the at least one channel matrix corresponding to one of the at least one sub-bands; obtaining Q1 channel matrixes by the at least one channel matrix through a first operation, wherein Q1 is a positive integer greater than 1, and the number of the channel matrixes included in the at least one channel matrix is smaller than Q1; the Q1 channel matrices are used to generate the first channel information, and the number of subbands included in the at least one subband is used to determine a load size of the first channel information.

As an embodiment, the first transmitter 1602 transmits second auxiliary information; wherein the second auxiliary information is used to indicate the first operation;

as an embodiment, the first receiver 1601 receives first auxiliary information; wherein the first auxiliary information is used to indicate the first operation.

As an embodiment, the first side information is used to indicate the Q2 complex numbers.

As an embodiment, the second side information is used to indicate the Q2 complex numbers.

As one embodiment, the Q2 complex numbers are valid for a first duration, the first channel information being an output after inputting at least the Q1 channel matrices into a first encoder; the first encoder is active for a second duration; the second duration and the first duration only partially overlap; the first channel information is generated within an overlap of the second duration and the first duration.

As one embodiment, the second duration is a fraction of the first duration.

As one embodiment, the first duration is a fraction of the second duration.

As an embodiment, the first node 1600 is a user equipment.

As one example, the first transmitter 1602 includes at least one of the antenna 452, the transmitter/receiver 454, the multi-antenna transmitter processor 457, the transmit processor 468, the controller/processor 459, the memory 460, and the data source 467 of fig. 4 of the present application.

As one example, the first transmitter 1602 includes an antenna 452, a transmitter/receiver 454, a multi-antenna transmitter processor 457, a transmit processor 468, a controller/processor 459, a memory 460, and a data source 467 of fig. 4 of the present application.

As one example, the first receiver 1601 includes at least the first five of the antenna 452, the receiver 454, the multi-antenna receive processor 458, the receive processor 456, the controller/processor 459, the memory 460, and the data source 467 of fig. 4 of the present application.

As an example, the first receiver 1601 includes at least the first four of the antenna 452, the receiver 454, the multi-antenna receive processor 458, the receive processor 456, the controller/processor 459, the memory 460, and the data source 467 of fig. 4 of the present application.

As an example, the first receiver 1601 includes at least the first three of the antenna 452, the receiver 454, the multi-antenna receive processor 458, the receive processor 456, the controller/processor 459, the memory 460, and the data source 467 of fig. 4 of the present application.

Example 17

Embodiment 17 illustrates a block diagram of a processing apparatus for use in a second node according to one embodiment of the present application; as shown in fig. 17. In fig. 17, the processing means 1700 in the second node comprises a second transmitter 1701 and a second receiver 1702.

The second transmitter 1701 transmits a first message, the first message being used to determine a first set of RS resources and a first set of frequency band resources, the first set of RS resources comprising at least one RS resource, the first set of frequency band resources comprising at least one subband;

A second receiver 1702 that receives first channel information;

in embodiment 17, the first channel information is used to describe Q1 channel matrices, where the Q1 channel matrices are obtained by performing a first operation on at least one channel matrix, the at least one channel matrix is generated based on a measurement for the first RS resource group, and each channel matrix in the at least one channel matrix corresponds to one subband in the at least one subband; the Q1 is a positive integer greater than 1, and the number of channel matrices included in the at least one channel matrix is smaller than the Q1; the number of subbands included in the at least one subband is used to determine a load size of the first channel information.

As an embodiment, the second transmitter 1701 transmits first auxiliary information; wherein the first auxiliary information is used to determine the first operation;

as an embodiment, the second receiver 1702 receives second auxiliary information; wherein the second auxiliary information is used to determine the first operation.

As an embodiment, the second node 1700 is a base station device.

As an example, the second transmitter 1701 includes the antenna 420, the transmitter 418, the transmit processor 416, and the controller/processor 475.

As an example, the second transmitter 1701 includes the antenna 420, the transmitter 418, the multi-antenna transmit processor 471, the transmit processor 416, and the controller/processor 475.

As an example, the second receiver 1702 includes the antenna 420, the receiver 418, the multi-antenna receive processor 472, the receive processor 470, and the controller/processor 475.

The second receiver 1702, as one embodiment, includes the controller/processor 475.

Example 18

Embodiment 18 illustrates a flow chart of measurements in a first RS resource group according to one embodiment of the present application, as shown in fig. 18.

The first node N1 performs measurement in the first RS resource group in step S500; the second node N2 transmits a reference signal in at least part of the RS resources of the first RS resource group.

As an embodiment, the at least part of the RS resources comprise RS resources for channel measurement.

The specific implementation of the measurement performed by the first node N1 in the first RS resource group is determined by the hardware device manufacturer, and a non-limiting example is given below:

the first node measures a channel parameter matrix for each PRB, the channel parameter matrix being Nt rows Nr columns, wherein each element is a channel impulse response; the Nt and the Nr are the number of antenna ports and the number of receiving antennas in one RS resource, respectively; the first node combines the channel parameter matrices measured on all PRBs in each sub-band to obtain the channel matrix of each sub-band. The input of the first encoder comprises a channel matrix of some or all of the subbands in the first set of band resources or the input of the first encoder comprises eigenvectors of the channel matrix of some or all of the subbands in the first set of band resources.

Those of ordinary skill in the art will appreciate that all or a portion of the steps of the above-described methods may be implemented by a program that instructs associated hardware, and the program may be stored on a computer readable storage medium, such as a read-only memory, a hard disk or an optical disk. Alternatively, all or part of the steps of the above embodiments may be implemented using one or more integrated circuits. Accordingly, each module unit in the above embodiment may be implemented in a hardware form or may be implemented in a software functional module form, and the application is not limited to any specific combination of software and hardware. User equipment, terminals and UEs in the present application include, but are not limited to, unmanned aerial vehicles, communication modules on unmanned aerial vehicles, remote control airplanes, aircraft, mini-planes, mobile phones, tablet computers, notebooks, vehicle-mounted communication devices, wireless sensors, network cards, internet of things terminals, RFID terminals, NB-IOT terminals, MTC (Machine Type Communication ) terminals, eMTC (enhanced MTC) terminals, data cards, network cards, vehicle-mounted communication devices, low cost mobile phones, low cost tablet computers, and other wireless communication devices. The base station or system device in the present application includes, but is not limited to, a macro cell base station, a micro cell base station, a home base station, a relay base station, a gNB (NR node B) NR node B, a TRP (Transmitter Receiver Point, transmitting and receiving node), and other wireless communication devices.

It will be appreciated by those skilled in the art that the present application may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. Accordingly, the presently disclosed embodiments are considered in all respects to be illustrative and not restrictive. The scope of the invention is indicated by the appended claims rather than by the foregoing description, and all changes that come within the meaning and range of equivalents are intended to be embraced therein.

Claims

1. A first node for wireless communication, comprising:

a first transmitter that transmits first channel information;

2. The first node of claim 1, wherein the load size of the first channel information decreases as the number of subbands included in the at least one subband decreases.

3. The first node according to claim 1 or 2, comprising:

the first receiver receives first auxiliary information; wherein the second auxiliary information is used to indicate the first operation;

or,

the first transmitter transmits second auxiliary information; wherein the first auxiliary information is used to indicate the first operation.

4. A first node according to any of claims 1 to 3, characterized in that the first operation comprises: the second channel matrix is the same as a matrix obtained by multiplying Q2 complex numbers by Q2 channel matrices respectively and then adding the complex numbers, wherein at least one channel matrix consists of the Q2 channel matrices, and Q2 is a positive integer greater than 1; the second channel matrix is any one of the Q1 channel matrices.

5. The first node of claim 4, wherein the Q2 complex numbers are valid for a first duration, and wherein the first channel information is an output after inputting at least the Q1 channel matrices into a first encoder; the first encoder is active for a second duration; the second duration and the first duration only partially overlap; the first channel information is generated within an overlap of the second duration and the first duration.

6. A second node for wireless communication, comprising:

a second receiver that receives the first channel information;

7. The second node of claim 6, wherein the load size of the first channel information decreases as the number of subbands included in the at least one subband decreases.

8. The second node according to claim 6 or 7, comprising:

the second transmitter transmits first auxiliary information; wherein the first auxiliary information is used to determine the first operation;

or,

the second receiver receives second auxiliary information; wherein the second auxiliary information is used to determine the first operation.

9. The second node according to any of claims 6 to 8, wherein the first operation comprises: the second channel matrix is the same as a matrix obtained by multiplying Q2 complex numbers by Q2 channel matrices respectively and then adding the complex numbers, wherein at least one channel matrix consists of the Q2 channel matrices, and Q2 is a positive integer greater than 1; the second channel matrix is any one of the Q1 channel matrices.

10. The second node of claim 9, wherein the Q2 complex numbers are valid for a first duration, the first channel information being an output after inputting at least the Q1 channel matrices into a first encoder; the first encoder is active for a second duration; the second duration and the first duration only partially overlap; the first channel information is generated within an overlap of the second duration and the first duration.

11. A method in a first node for wireless communication, comprising:

receiving a first message, the first message being used to determine a first set of RS resources and a first set of frequency band resources, the first set of RS resources including at least one RS resource, the first set of frequency band resources including at least one subband;

transmitting first channel information;

12. A method in a second node for wireless communication, comprising:

Receiving first channel information;