Method and apparatus for wireless communication

Abstract

The application discloses a method and device for wireless communication. A first node transmits first type capability information, wherein the first type capability information comprises MIMO related parameters of a first frequency band; and transmits first information, wherein the first information comprises a first type identification list, any first type identification in the first type identification list indicates a trainable model; wherein whether the trainable model indicated by at least one first type identification in the first type identification list in the first information is applied to the first frequency band depends on the MIMO related parameters on the first frequency band. The application can optimize the reporting of capability information, and has good compatibility.

Description

Method and apparatus for wireless communication

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on January 3, 2024, with application number 2024100121391 and invention name “Method and Apparatus for Wireless Communication”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to methods and devices in wireless communication systems, and more particularly to solutions and devices for AI (Artificial Intelligence) / ML (Machine Learning) models in wireless communication systems. Background Art

[0003] In traditional wireless communications, UE (User Equipment) reports may include at least one of a variety of auxiliary information, such as CSI (Channel Status Information), auxiliary information related to beam management, auxiliary information related to positioning, etc. CSI includes CSI-RS Resource Indicator (CRI), Rank Indicator (RI), Precoding Matrix Indicator (PMI), or Channel Quality Indicator (CQI), etc.

[0004] Based on the UE's reports, the network device selects appropriate transmission parameters for the UE, such as the cell to be camped on, MCS (Modulation and Coding Scheme), TPMI (Transmitted Precoding Matrix Indicator), TCI (Transmission Configuration Indication), and other parameters. Furthermore, UE reports can be used to optimize network parameters, such as achieving better cell coverage and switching base stations based on UE location.

[0005] In cellular systems such as LTE (Long Term Evolution) and NR (New Radio), network devices such as base stations or core network equipment send capability query commands to UEs, and the UE then sends capability information to the network devices. The network devices respect the received UE capability information when configuring or scheduling the UE. The UE capability information includes band-specific MIMO (Multiple-Input Multiple-Output) parameters, including parameters related to beam measurement, RS (Reference Signal) resource measurement, CSI reporting, codebook parameters, and more.

[0006] As AI / ML technologies continue to mature, their application to communications has become a research hotspot. For example, in NRR (release) 18, CSI compression, beam management, and positioning technologies based on AI (Artificial Intelligence) or ML (Machine Learning) were studied. AI / ML is also likely to become a research focus in 6G communications. Summary of the Invention

[0007] One application of trainable models such as AI / ML is to process information on wireless channels, which can achieve performance far exceeding that of traditional signal processing algorithms in some specific areas. The inventors have found through research that the processing of wireless channel information by models such as AI / ML may rely on the capabilities of traditional signal processing to switch between AI / ML and traditional signal processing, and to perform functions such as AI / ML performance detection and AI / ML performance calibration. Through further research, the inventors have found that the generation of AI / ML models requires training on a large amount of data, and the training function may be deployed on the communication device side or on a remote server. The existing UE capability reporting mechanism cannot well support capability reporting related to trainable models such as AI / ML.

[0008] In response to the above problems, the present application discloses a solution. It should be noted that although a large number of embodiments of the present application are developed for AI / ML, they are also applicable to solutions based on traditional capabilities such as signal processing, in the absence of conflict; especially considering that a unified implementation method can significantly reduce hardware complexity or save costs. The specific channel processing or reconstruction algorithm is likely to be non-standardized or implemented by the hardware equipment manufacturer. In the absence of conflict, the embodiments and features in the embodiments of any node of the present application can be applied to any other node. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be arbitrarily combined with each other.

[0009] When necessary, for explanation of the terms in this application, reference may be made to the description of the specification protocols TS37 series and TS38 series of 3GPP (3rd Generation Partner Project).

[0010] The present application discloses a method in a first node for wireless communication, comprising:

[0011] Sending first-category capability information, wherein the first-category capability information includes MIMO-related parameters of a first frequency band; sending first information, wherein the first information includes a first-category identifier list, and any first-category identifier in the first-category identifier list indicates a trainable model;

[0012] Wherein, whether the trainable model indicated by at least one first category identifier in the first category identifier list in the first information is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0013] As an embodiment, the above method associates the reporting of the trainable model with codebook parameters, reduces reporting signaling overhead, and saves air interface resources.

[0014] As an embodiment, the above method avoids reporting the first type identifier for each frequency band, reduces reporting signaling overhead, and saves air interface resources.

[0015] As an embodiment, when a trainable model is not applied to the first frequency band, the first node will not be configured with the trainable model for the first frequency band.

[0016] As an embodiment, when a trainable model is not applied to the first frequency band, the first node assumes that the trainable model will not be configured for the first frequency band.

[0017] As an embodiment, when a trainable model is not applied to the first frequency band, even if the trainable model is configured for the first frequency band, the first node abandons performing operations based on the trainable model, such as calculating and reporting CSI based on the trainable model, calculating and reporting position assistance information based on the trainable model, and so on.

[0018] As an embodiment, when a trainable model is not applied to the first frequency band, even if the trainable model is configured for the first frequency band, the first node uses traditional reporting instead of reporting based on the trainable model. The traditional reporting may be traditional CSI, traditional beam-related reporting information, etc.

[0019] Specifically, according to one aspect of the present application, it is characterized in that the MIMO-related parameters of the first frequency band include codebook parameters. When the codebook parameters of the MIMO-related parameters of the first frequency band do not include a first-class codebook, the trainable model indicated by the at least one first-class identifier in the first-class identifier list is not available for the first frequency band; the first-class codebook is non-constant modulus.

[0020] Compared with traditional constant modulus codebooks, such as codebooks based on IFFT (Inverse Fast Fourier Transform), non-constant modulus codebooks can provide higher quantization accuracy; the frequency band that does not support the first type of codebook does not support the trainable model, which can avoid discontinuity in CSI feedback accuracy.

[0021] Furthermore, the above method can avoid using a low-precision codebook to calibrate or monitor the performance of the trainable model, and can effectively ensure the performance of the trainable model.

[0022] As an embodiment, the first type of codebook is an enhanced second type of codebook.

[0023] As an embodiment, the accuracy of the first type of codebook is not lower than that of the enhanced second type of codebook.

[0024] As an embodiment, any vector in the first type of codebook is obtained by linear superposition of multiple vectors.

[0025] As an embodiment, each of the multiple vectors represents a beam direction or a time path.

[0026] As an embodiment, each of the multiple vectors represents a beam direction, a time path, or a Doppler frequency shift.

[0027] Specifically, according to one aspect of the present application, it is characterized in that the MIMO-related parameters of the first frequency band include beam measurement-related parameters. When the beam measurement parameters of the MIMO-related parameters of the first frequency band do not include measuring the first type of RS resources, the trainable model indicated by the at least one first type identifier in the first type identifier list is not available for the first frequency band.

[0028] The above method associates the trainable model with traditional RS resource measurement and has good compatibility.

[0029] As an embodiment, the first type of RS resources are downlink RS resources outside of SSB (SS / PBCH block, synchronization signal physical broadcast channel block).

[0030] The above embodiments help ensure the performance of the trainable model.

[0031] As an embodiment, the first type of RS resources are CSI-RS resources.

[0032] As an embodiment, the first type of RS resources are non-periodic CSI-RS resources.

[0033] As an embodiment, the first type of RS resources are CSI-RS resources for measuring L1-RSRP (Layer 1 reference signal received power).

[0034] As an embodiment, the beam measurement parameter of the MIMO-related parameter of the first frequency band does not include measuring the first type of RS resources, which means that the maximum number of measured first type RS resources indicated by the beam measurement parameter of the MIMO-related parameter of the first frequency band is 0.

[0035] Specifically, according to one aspect of the present application, it is characterized in that the first type of capability information includes reporting type information; when the reporting type information on the first frequency band does not include the first type of reporting, the trainable model indicated by the at least one first type identifier in the first type identifier list in the first information is not available for the first frequency band; the first type of reporting is used to determine the performance of the trainable model.

[0036] The above method associates the trainable model with traditional CSI reporting and has good compatibility.

[0037] As an embodiment, the first type of reporting is obtained based on a traditional signal processing algorithm.

[0038] As an embodiment, the first type of reporting indicates original (Raw) channel information.

[0039] As an embodiment, the first type of reporting is non-periodic.

[0040] As an embodiment, the first type of reporting is non-periodic CSI.

[0041] As an embodiment, the first type of reporting is non-periodic PMI.

[0042] Specifically, according to one aspect of the present application, it is characterized in that the sending of the first information is triggered by any condition in the first condition set;

[0043] Among them, one of the conditions in the first condition set is that at least one first-class identifier currently supported by the first node does not belong to the most recently reported first-class identifier list; the first-class identifier list in the first information includes the at least one first-class identifier currently supported by the first node.

[0044] The above method enables the sending of the first information to be triggered by the updating of the first category identifier list, thereby improving the reporting flexibility of the first information.

[0045] As an embodiment, the above method ensures that the function corresponding to the first information is not necessarily deployed inside the first node, thereby improving the degree of freedom of deployment.

[0046] Specifically, according to one aspect of the present application, it is characterized by comprising:

[0047] receiving second information requesting capability information of the first node;

[0048] The sending of the first information is triggered by the receiving of the second information.

[0049] As an embodiment, one of the conditions in the first condition set is the receipt of the second information.

[0050] As an embodiment, the second information and the first information are both RRC (Radio Resource Control) layer signaling.

[0051] As an embodiment, the second information and the first information are both non-access layer signaling.

[0052] As an embodiment, the second information and the first information are both RRC layer signaling, and the second information and the first information are UECapabilityEnquiry message and UECapabilityInformation message respectively.

[0053] As an embodiment, the second information and the first information are both non-access stratum (NAS) signaling, and the second information and the first information are RequestCapabilities message and ProvideCapabilities message respectively.

[0054] Specifically, according to one aspect of the present application, one of the conditions in the first condition set is that at least one first-category identifier currently supported by the first node does not belong to a most recently reported first-category identifier list, and the list includes at least one of the following:

[0055] After the most recently reported first category identifier list, the application server of the first node is replaced;

[0056] After the most recently reported first category identifier list, the first node receives signaling from an application server, where the signaling from the application server indicates the first category identifiers currently supported by the first node.

[0057] The present application discloses a method in a second node for wireless communication, which includes:

[0058] Receiving first-category capability information, wherein the first-category capability information includes MIMO-related parameters of a first frequency band; receiving first information, wherein the first information includes a first-category identifier list, wherein any first-category identifier in the first-category identifier list indicates a trainable model;

[0059] Wherein, whether the trainable model indicated by at least one first category identifier in the first category identifier list in the first information is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0060] As an embodiment, when a trainable model is not applied to the first frequency band, the second node will not configure the trainable model for the sender of the second information for the first frequency band.

[0061] As an embodiment, when a trainable model is not applied to the first frequency band, the second node assumes that the sender of the second information will not perform an operation based on the trainable model for the first frequency band.

[0062] As an embodiment, when a trainable model is not applied to the first frequency band, even if the trainable model is configured for the first frequency band, the second node assumes that it is unable to obtain feedback based on the trainable model, such as CSI calculated and reported based on the trainable model, location assistance information calculated and reported based on the trainable model, and so on.

[0063] As an embodiment, when a trainable model is not applied to the first frequency band, even if the trainable model is configured for the first frequency band, the second node assumes that what is received is a traditional report rather than a report based on the trainable model, and the traditional report may be a traditional CSI, a traditional beam-related reporting information, etc.

[0064] Specifically, according to one aspect of the present application, it is characterized by comprising:

[0065] a second transmitter, sending second information requesting capability information of the first node;

[0066] The sending of the first information is triggered by the receiving of the second information.

[0067] Specifically, according to one aspect of the present application, it is characterized in that the MIMO-related parameters of the first frequency band include codebook parameters. When the codebook parameters of the MIMO-related parameters of the first frequency band do not include a first-class codebook, the trainable model indicated by the at least one first-class identifier in the first-class identifier list is not available for the first frequency band; the first-class codebook is non-constant modulus.

[0068] Specifically, according to one aspect of the present application, it is characterized in that the MIMO-related parameters of the first frequency band include beam measurement-related parameters. When the beam measurement parameters of the MIMO-related parameters of the first frequency band do not include measuring the first type of RS resources, the trainable model indicated by the at least one first type identifier in the first type identifier list is not available for the first frequency band.

[0069] Specifically, according to one aspect of the present application, it is characterized in that the first type of capability information includes reporting type information; when the reporting type information on the first frequency band does not include the first type of reporting, the trainable model indicated by the at least one first type identifier in the first type identifier list in the first information is not available for the first frequency band; the first type of reporting is used to determine the performance of the trainable model.

[0070] Specifically, according to one aspect of the present application, it is characterized in that the sending of the first information is triggered by any condition in the first condition set;

[0071] Among them, one of the conditions in the first condition set is that at least one first-class identifier currently supported by the first node does not belong to the most recently reported first-class identifier list; the first-class identifier list in the first information includes the at least one first-class identifier currently supported by the first node.

[0072] Specifically, according to one aspect of the present application, one of the conditions in the first condition set is that at least one first-category identifier currently supported by the first node does not belong to a most recently reported first-category identifier list, and the list includes at least one of the following:

[0073] After the most recently reported first category identifier list, the application server of the first node is replaced;

[0074] After the most recently reported first category identifier list, the first node receives signaling from an application server, where the signaling from the application server indicates the first category identifiers currently supported by the first node.

[0075] The present application discloses a first node for wireless communication, comprising:

[0076] A first transmitter sends first-type capability information, wherein the first-type capability information includes MIMO-related parameters of a first frequency band; and sends first information, wherein the first information includes a first-type identifier list, and any first-type identifier in the first-type identifier list indicates a trainable model.

[0077] Wherein, whether the trainable model indicated by at least one first category identifier in the first category identifier list in the first information is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0078] Specifically, according to one aspect of the present application, the first node is characterized by including:

[0079] a first receiver, receiving second information requesting capability information of the first node;

[0080] The sending of the first information is triggered by the receiving of the second information.

[0081] The present application discloses a second node used for wireless communication, comprising:

[0082] A second receiver receives first-category capability information, wherein the first-category capability information includes MIMO-related parameters of a first frequency band; and receives first information, wherein the first information includes a first-category identifier list, wherein any first-category identifier in the first-category identifier list indicates a trainable model.

[0083] Wherein, whether the trainable model indicated by at least one first category identifier in the first category identifier list in the first information is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0084] Specifically, according to one aspect of the present application, the second node is characterized by including:

[0085] a second transmitter, sending second information requesting capability information of the first node;

[0086] The sending of the first information is triggered by the receiving of the second information. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings:

[0088] FIG1 shows a flow chart of communication of a first node according to an embodiment of the present application;

[0089] FIG2 shows a schematic diagram of a network architecture according to an embodiment of the present application;

[0090] FIG3 is a schematic diagram showing an embodiment of a radio protocol architecture of a user plane and a control plane according to an embodiment of the present application;

[0091] FIG4 shows a schematic diagram of hardware modules of a communication node according to an embodiment of the present application;

[0092] FIG5 shows a flow chart of transmission between a first node and a second node according to an embodiment of the present application;

[0093] FIG6 shows a schematic diagram of third information transmission according to an embodiment of the present application;

[0094] FIG7 shows a schematic diagram of multiple frequency bands according to an embodiment of the present application;

[0095] FIG8 shows a flowchart of measuring in a first RS resource according to one embodiment of the present application;

[0096] FIG9 shows a schematic diagram of a system of trainable models according to one embodiment of the present application;

[0097] FIG10 shows a flowchart of transmission of first channel information according to an embodiment of the present application;

[0098] FIG11 shows a schematic diagram of a first encoder according to an embodiment of the present application;

[0099] FIG12 shows a schematic diagram of a first function according to an embodiment of the present application;

[0100] FIG13 shows a schematic diagram of a decoding layer group according to an embodiment of the present application;

[0101] FIG14 shows a structural block diagram of a processing device used in a first node according to an embodiment of the present application;

[0102] FIG15 shows a structural block diagram of a processing device used in a second node according to an embodiment of the present application. DETAILED DESCRIPTION

[0103] The technical solution of the present application will be further described in detail below in conjunction with the accompanying drawings. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other in any way.

[0104] Example 1

[0105] Embodiment 1 illustrates a flowchart of communication of a first node according to an embodiment of the present application, as shown in FIG1 .

[0106] The first node 100 sends first-type capability information and first information in step 101;

[0107] In embodiment 1, the first category capability information includes MIMO-related parameters of the first frequency band; the first information includes a first category identifier list, and any first category identifier in the first category identifier list indicates a trainable model; for the trainable model indicated by at least one first category identifier in the first category identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0108] As an embodiment, the first type of capability information is an RRC layer message.

[0109] As an embodiment, the first type of capability information includes part or all of the fields in the UECapabilityInformation message.

[0110] As an embodiment, the first type of capability information includes part or all of the fields in the UE-NR-Capability message.

[0111] As an embodiment, the first type of capability information is rf-Parameters IE (Information Element, information unit).

[0112] As an embodiment, the first type of capability information is BandNR IE.

[0113] As a sub-embodiment of the above embodiment, the first information does not belong to the BandNR IE.

[0114] As an embodiment, the first type of capability information includes multiple sub-capability information, the multiple sub-capability information are respectively for multiple frequency bands, and the first frequency band is any frequency band among the multiple frequency bands.

[0115] As an embodiment, the MIMO-related parameters are configured per band (PerBand) or are specific for a certain band (specific for a certain band).

[0116] As a sub-embodiment of the above embodiment, the first information is not configured for each band.

[0117] As a sub-embodiment of the above embodiment, the first information is configured per UE.

[0118] As a sub-embodiment of the above embodiment, the first information is configured per RAT (Radio Access Technology).

[0119] As an embodiment, the MIMO-related parameters include part or all of the fields in MIMO-ParametersPerBand.

[0120] As an embodiment, the MIMO-related parameters include codebook parameters (CodebookParameters).

[0121] As an embodiment, the MIMO-related parameters include parameters related to beam measurement, such as the maximum number of RS resources (SSB or CSI-RS) for L1-RSRP, the maximum number of CSI-RS resources for L1-RSRP, the recommended number of repetitions of CSI-RS resources per resource set, the CSI-RS density for L1-RSRP, and the like.

[0122] As an embodiment, when the CSI-RS density for L1-RSRP of the MIMO-related parameters of the first frequency band is less than a first threshold, the trainable model indicated by at least one first category identifier in the first category identifier list is not available for the first frequency band.

[0123] As an embodiment, when the number of repetitions of the CSI-RS resources recommended per resource set of the MIMO-related parameters of the first frequency band is less than a second threshold, the trainable model indicated by the at least one first category identifier in the first category identifier list is not available for the first frequency band.

[0124] The above two embodiments can meet the measurement accuracy requirements for the trainable model.

[0125] As an embodiment, the first threshold is greater than 3 REs (Resource Elements) per PRB (Physical Resource Block).

[0126] As an embodiment, the first threshold does not exceed 12 REs (Resource Elements) per PRB (Physical Resource Block).

[0127] As an embodiment, the second threshold is not less than 2.

[0128] As an embodiment, the second threshold is no greater than 256.

[0129] As an embodiment, the MIMO-related parameters include CSI measurement-related parameters, such as the maximum number of RS resources (SSB or CSI-RS) for CSI feedback, the maximum number of CSI-RS resources for CSI feedback, the maximum CSI-IM (Interference Measurement) density for CSI feedback, and the like.

[0130] As an embodiment, the trainable model is an AI model.

[0131] As an embodiment, the trainable model is an ML model.

[0132] As an embodiment, the trainable model is a nonlinear model.

[0133] As an embodiment, the trainable model is known to both the UE and the network device.

[0134] As an embodiment, the trainable model is maintained by the UE and the network device respectively.

[0135] As an embodiment, the first information is a NAS (Non-access stratum) message, and the first information is sent to a location service center.

[0136] As an embodiment, the first information is an AS (Access stratum) message, and the first information is sent to a base station.

[0137] As an embodiment, the first node is in an RRC connected state.

[0138] As an embodiment, any first-category identifier in the first-category identifier list is a non-negative integer.

[0139] As an embodiment, any first-category identifier in the first-category identifier list indicates a trainable model, including: any first-category identifier in the first-category identifier list indicates a set of parameters, and the set of parameters is used to generate a trainable model.

[0140] As an embodiment, the set of parameters is obtained after training.

[0141] Those skilled in the art should know that for different types of AI / ML models, the content included in the set of parameters may be different. For example, for CNN (Conventional Neural Networks), the set of parameters may include the threshold of the activation function, the size of the convolution kernel, the step size of the convolution kernel, the weights between feature maps, etc.

[0142] As an embodiment, any first-category identifier in the first-category identifier list indicates a trainable model, including: any first-category identifier in the first-category identifier list indicates a set of parameters, and the set of parameters is used to indicate an applicable scenario of a trainable model.

[0143] As an embodiment, any first-category identifier in the first-category identifier list indicates a trainable model, including: any first-category identifier in the first-category identifier list is used to index a trainable model.

[0144] As a sub-embodiment of the above embodiment, the trainable model is maintained separately on the first node side and the network device side, and the trainable model maintained by the first node is different from the trainable model on the network device side.

[0145] As an embodiment, any first-category identifier in the first-category identifier list indicates a trainable model, including: any first-category identifier in the first-category identifier list indicates an executable file, and the executable file is used to generate a trainable model.

[0146] As an embodiment, the first category identifier list in the first information includes all first category identifiers currently supported by the first node.

[0147] As an embodiment, the first information indicates physical layer capabilities.

[0148] As an embodiment, the first information belongs to Phy-Parameters.

[0149] As an embodiment, the first information belongs to supportedBandListNR.

[0150] As an embodiment, the first information indicates radio frequency capability.

[0151] As an embodiment, the first information belongs to RF-Parameters.

[0152] As an embodiment, the first type of capability information and the first information belong to the same RRC message.

[0153] As an embodiment, the first type of capability information and the first information belong to the same UECapabilityInformation message.

[0154] As an embodiment, the first type of capability information and the first information belong to the same UE-NR-Capability message.

[0155] As an embodiment, the first type capability information and the first information belong to the same rf-Parameters IE.

[0156] As an embodiment, the first type of capability information and the first information are both sent via PUSCH (Physical Uplink Shared Channel).

[0157] As an embodiment, the first type of capability information and the first information are both transmitted via UL-SCH (Uplink Shared Channel).

[0158] As an embodiment, the first type of capability information is an RRC message, and the first information is a NAS message.

[0159] As a sub-embodiment of the above embodiment, the first information is sent to LMF (Location Management Function).

[0160] Example 2

[0161] Embodiment 2 illustrates a schematic diagram of a network architecture according to an embodiment of the present application, as shown in FIG2 . FIG2 illustrates the system architecture of 5G NR (New Radio), LTE (Long-Term Evolution) and LTE-A (Long-Term Evolution Advanced). The 5G NR or LTE network architecture 200 may be referred to as 5GS (5G System) / EPS (Evolved Packet System) or some other appropriate 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. EPS can be interconnected with other access networks, but these entities / interfaces are not shown for simplicity. As shown, the EPS provides packet-switched services, however, those skilled in the art will readily appreciate that the various concepts presented throughout this disclosure can be extended to networks providing circuit-switched services or other cellular networks. The NG-RAN includes an NR Node B (gNB) 203 and other gNBs 204. The gNB 203 provides user and control plane protocol termination towards the UE 201. The gNB 203 may be connected to other gNBs 204 via an Xn interface (e.g., backhaul). The gNB 203 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 appropriate terminology. The gNB 203 provides an access point to the EPC / 5G-CN 210 for the UE 201. Examples of UE 201 include a cellular phone, a smartphone, a Session Initiation Protocol (SIP) phone, a laptop computer, a personal digital assistant (PDA), a satellite radio, non-terrestrial base station communications, satellite mobile communications, a global positioning system, a multimedia device, a video device, a digital audio player (e.g., an MP3 player), a camera, a game console, a drone, an aircraft, a narrowband Internet of Things device, a machine type communication device, a land vehicle, an automobile, a wearable device, or any other similarly functional device. Those skilled in the art may also refer to UE 201 as a mobile station, a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless 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 gNB 203 connects to the EPC / 5G-CN 210 via the S1 / NG interface. The EPC / 5G-CN 210 includes the MME (Mobility Management Entity) / AMF (Authentication Management Field) / UPF (User Plane Function) 211, other MMEs / AMFs / UPFs 214, the S-GW (Service Gateway) 212, and the P-GW (Packet Data Network Gateway) 213. The MME / AMF / UPF 211 is the control node that handles signaling between the UE 201 and the EPC / 5G-CN 210. Generally, the MME / AMF / UPF 211 provides bearer and connection management. All user Internet Protocol (IP) packets are transmitted through the S-GW 212, which is itself connected to the P-GW 213. The P-GW 213 provides UE IP address allocation and other functions. The P-GW 213 is connected to the Internet service 230. The Internet service 230 includes operator-specific Internet protocol services, which may include the Internet, intranet, IMS (IP Multimedia Subsystem), and packet-switched streaming services.

[0162] As an embodiment, the UE201 corresponds to the first node in this application, and the gNB203 corresponds to the second node in this application.

[0163] As an embodiment, the UE 201 supports generating reports using AI (Artificial Intelligence) or ML (Machine Learning).

[0164] As an embodiment, the UE 201, in conjunction with the application server on the UE side, supports the use of AI (Artificial Intelligence) or ML (Machine Learning) to generate reports.

[0165] As a sub-embodiment of the above two embodiments, the reporting is used for purposes such as channel information feedback, beam management, or positioning.

[0166] As an embodiment, the UE 201 supports generating a trained model using training data or generating part of the parameters in the trained model using trained data.

[0167] As an embodiment, the UE 201 supports determining at least part of the parameters of a CNN (Conventional Neural Networks) for CSI reconstruction through training.

[0168] As an embodiment, the UE 201 supports determining a transformer for CSI reconstruction through training.

[0169] As an embodiment, the UE 201 is a terminal supporting Massive-MIMO.

[0170] As an embodiment, the gNB203 supports Massive-MIMO based transmission.

[0171] As an embodiment, the gNB203 supports decompression of CSI using AI or deep learning.

[0172] As an embodiment, the gNB203 supports mobility prediction using AI or deep learning, such as predicting the beam that the UE201 is about to enter.

[0173] As an embodiment, the gNB203 is a macrocellular base station.

[0174] As an embodiment, the gNB203 is a micro cell base station.

[0175] As an embodiment, the gNB203 is a picocell (PicoCell) base station.

[0176] As an embodiment, the gNB203 is a home base station (Femtocell).

[0177] As an embodiment, the gNB203 is a base station device that supports large delay difference.

[0178] As an embodiment, the gNB203 is a flying platform device.

[0179] As an embodiment, the gNB203 is a satellite device.

[0180] As an embodiment, the first node and the second node in the present application are the UE201 and the gNB203 respectively.

[0181] As an embodiment, the second node in the present application includes the gNB203 and a core network function.

[0182] As an embodiment, the core network function is LMF.

[0183] As an embodiment, the one core network function is used to manage AI / ML models.

[0184] As an embodiment, the core network function is connected to the UE201 via AMF.

[0185] Example 3

[0186] Embodiment 3 illustrates a schematic diagram of an embodiment of a user plane and control plane radio protocol architecture according to the present application, as shown in FIG3 . FIG3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for a user plane 350 and a control plane 300. FIG3 illustrates the radio protocol architecture of the control plane 300 for a first node device (a UE or RSU in V2X, a vehicle-mounted device, or a vehicle-mounted communication module) and a second node device (a gNB, a UE or RSU in V2X, a vehicle-mounted device, or a vehicle-mounted communication module), or between two UEs, using three layers: Layer 1, Layer 2, and Layer 3. Layer 1 (L1) is the lowest layer and implements various PHY (physical layer) signal processing functions. The L1 layer will be referred to herein as PHY 301. Layer 2 (L2) 305 sits above PHY 301 and is responsible for the link between the first and second node devices, as well as between two UEs, via PHY 301. The L2 layer 305 includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the second node device. The PDCP sublayer 304 provides data encryption and integrity protection. The PDCP sublayer 304 also provides inter-zone mobility support for the first node device to the second node device. The RLC sublayer 303 provides segmentation and reassembly of data packets, and retransmits lost data packets through ARQ. The 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 various radio resources (e.g., resource blocks) in a cell between 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) of the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and configuring 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). The radio protocol architecture for the first node device and the second node device in the user plane 350 is substantially the same as the corresponding layers and sublayers in the control plane 300 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. However, the PDCP sublayer 354 also provides header compression for upper layer data packets to reduce wireless transmission overhead.The L2 layer 355 in the user plane 350 also includes an SDAP (Service Data Adaptation Protocol) sublayer 356. The SDAP sublayer 356 is responsible for mapping between QoS flows and data radio bearers (DRBs) to support service diversity. Although not shown, the first node device may have several upper layers above the L2 layer 355, including a network layer (e.g., an IP layer) terminated at the P-GW on the network side and an application layer terminated at the other end of the connection (e.g., a remote UE, a server, etc.).

[0187] As an embodiment, the wireless protocol architecture in FIG3 is applicable to the first node in this application.

[0188] As an embodiment, the wireless protocol architecture in FIG3 is applicable to the second node in this application.

[0189] As an embodiment, the reference signal transmitted in the RS resource in this application is generated by the PHY301.

[0190] As an embodiment, the CSI in this application is generated in the PHY 301 .

[0191] As an embodiment, the first type of capability information in the present application is generated in the RRC sublayer 306.

[0192] As a sub-embodiment of the above embodiment, the first information in this application is generated in the RRC sublayer 306.

[0193] As a sub-embodiment of the above embodiment, the first information and the second information in this application are both generated in the RRC sublayer 306.

[0194] As a sub-embodiment of the above embodiment, the first information in this application is generated in the MAC sublayer 302.

[0195] The above sub-embodiment can realize fast UE capability reporting and is more suitable for variable UE capabilities.

[0196] Example 4

[0197] Embodiment 4 shows a schematic diagram of hardware modules of a communication node according to an embodiment of the present application, as shown in FIG4. FIG4 is a block diagram of a first communication device 450 and a second communication device 410 communicating with each other in an access network.

[0198] 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 .

[0199] 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 .

[0200] During transmission from the second communication device 410 to the first communication device 450, upper layer data packets from the core network are provided to the controller / processor 475 at the second communication device 410. The controller / processor 475 implements L2 layer functionality. During transmission from the second communication device 410 to the first communication device 450, the 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., the physical layer). The transmit processor 416 implements channel coding and interleaving to facilitate forward error correction (FEC) at the second communication device 410, as well as mapping of signal constellations based on various modulation schemes (e.g., binary phase-shift keying (BPSK), quadrature phase-shift keying (QPSK), M-phase-shift keying (M-PSK), and M-quadrature amplitude modulation (M-QAM)). The multi-antenna transmit processor 471 performs digital spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming on the coded and modulated symbols to generate one or more spatial streams. The transmit processor 416 then maps each spatial stream to a subcarrier, multiplexes it with a reference signal (e.g., a pilot) 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 multicarrier symbol stream. Each transmitter 418 converts the baseband multi-carrier symbol stream provided by the multi-antenna transmit processor 471 into a radio frequency stream, and then provides it to a different antenna 420.

[0201] During transmission from the second communication device 410 to the first communication device 450, at the first communication device 450, each receiver 454 receives a signal via its corresponding antenna 452. Each receiver 454 recovers the information modulated onto the RF carrier and converts the RF stream into a baseband multi-carrier symbol stream, which is provided to the receive processor 456. The receive processor 456 and the multi-antenna receive processor 458 implement various L1 signal processing functions. The 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 multi-carrier symbol stream, after the receive analog precoding / beamforming operations, from the time domain to the frequency domain using a fast Fourier transform (FFT). In the frequency domain, the receive processor 456 demultiplexes the physical layer data signal and reference signal, where the reference signal is used for channel estimation. The data signal undergoes multi-antenna detection in the multi-antenna receive processor 458 to recover any spatial streams destined for the first communication device 450. The symbols on each spatial stream are demodulated and recovered in the receive processor 456, and soft decisions are generated. The receive processor 456 then deinterleaves and channel decodes the soft decisions to recover the upper layer data and control signals 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 code and data. The memory 460 may be referred to as a computer-readable medium. During 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, and control signal processing to recover upper layer data packets from the core network. The upper layer data packets are then provided to all protocol layers above the L2 layer. Various control signals may also be provided to the L3 layer for L3 processing.

[0202] During 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 the controller / processor 459. The data source 467 represents all protocol layers above the L2 layer. Similar to the transmission functionality 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 allocation, implementing L2 layer functions for the user plane and control plane. 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, and modulation mapping, while the multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming. The transmit processor 468 then modulates the resulting spatial stream into a multi-carrier / single-carrier symbol stream. After analog precoding and beamforming operations in the multi-antenna transmit processor 457, the stream is provided to 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 RF symbol stream before providing it to the antenna 452.

[0203] During transmission from the first communications device 450 to the second communications device 410, the functionality at the second communications device 410 is similar to the reception functionality at the first communications device 450 described for transmission from the second communications device 410 to the first communications device 450. Each receiver 418 receives RF signals via its corresponding antenna 420, converts the received RF signals into 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 L1 layer functionality. A controller / processor 475 implements L2 layer functionality. The controller / processor 475 may be associated with a memory 476 storing program codes and data. The memory 476 may be referred to as a computer-readable medium. During transmission from the first communications device 450 to the second communications device 410, the controller / processor 475 provides demultiplexing between transport and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover upper layer data packets from the UE 450. Upper layer packets from controller / processor 475 may be provided to the core network.

[0204] As an embodiment, the first communication device 450 apparatus includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used together with the at least one processor, and the first communication device 450 apparatus at least: sends first-class capability information and sends first information; wherein, the first-class capability information includes MIMO-related parameters of the first frequency band; the first information includes a first-class identifier list, and any first-class identifier in the first-class identifier list indicates a trainable model; for the trainable model indicated by at least one first-class identifier in the first-class identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0205] As an embodiment, the first communication device 450 includes: a memory storing a computer-readable instruction program, wherein the computer-readable instruction program generates an action when executed by at least one processor, the action including: sending first-class capability information and sending first information; wherein the first-class capability information includes MIMO-related parameters of a first frequency band; the first information includes a first-class identifier list, and any first-class identifier in the first-class identifier list indicates a trainable model; for the trainable model indicated by at least one first-class identifier in the first-class identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0206] As an embodiment, the second communication device 410 apparatus includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used together with the at least one processor. The second communication device 410 apparatus at least: receives first-class capability information and receives first information, wherein the first-class capability information includes MIMO-related parameters of a first frequency band; the first information includes a first-class identifier list, and any first-class identifier in the first-class identifier list indicates a trainable model; for the trainable model indicated by at least one first-class identifier in the first-class identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0207] As an embodiment, the second communication device 410 apparatus includes: a memory storing a computer-readable instruction program, wherein the computer-readable instruction program generates an action when executed by at least one processor, the action including: receiving first-class capability information and receiving first information, wherein the first-class capability information includes MIMO-related parameters of a first frequency band; the first information includes a first-class identifier list, and any first-class identifier in the first-class identifier list indicates a trainable model; for the trainable model indicated by at least one first-class identifier in the first-class identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0208] As a sub-embodiment of the above two embodiments, the first information may be transparent to the second node, or the second node does not parse the first information.

[0209] As a sub-embodiment of the above two embodiments, the first information is distributed by the second node to the core network function on the network side through signaling such as a container.

[0210] The above two sub-embodiments are applicable to reporting of NAS-related capability information and have good compatibility with existing systems.

[0211] As an embodiment, the first communication device 450 corresponds to the first node in this application.

[0212] As an embodiment, the second communication device 410 corresponds to the second node in this application.

[0213] As an embodiment, the first communication device 450 is a UE, and the second communication device 410 is a base station.

[0214] As an embodiment, the antenna 452, the receiver 454, the multi-antenna reception processor 458, and the reception processor 456 are used for measurement on RS resources.

[0215] As an embodiment, the controller / processor 459 is used for measurements on RS resources.

[0216] As an embodiment, the controller / processor 459 is used to generate the first type of capability information.

[0217] As an embodiment, the controller / processor 459 is used to generate the first information.

[0218] As an embodiment, the antenna 452, the transmitter 454, the multi-antenna transmit processor 457, the transmit processor 468, and the controller / processor 459 are used to send the first type of capability information and the first information.

[0219] As an embodiment, the antenna 420, the transmitter 418, the multi-antenna transmit processor 471, and the transmit processor 416 are used to send a reference signal on RS resources.

[0220] As an embodiment, the controller / processor 475 is configured to send a reference signal on the RS resource.

[0221] As an embodiment, the antenna 420, the receiver 418, the multi-antenna reception processor 472, the reception processor 470, and the controller / processor 475 are used to receive the first type of capability information.

[0222] As an embodiment, the antenna 420, the receiver 418, the multi-antenna reception processor 472, the reception processor 470, and the controller / processor 475 are used to receive the first information.

[0223] Example 5

[0224] Embodiment 5 illustrates a flow chart of transmission between a first node and a second node according to an embodiment of the present application, as shown in FIG5 . In FIG5 , the steps in block F1 are optional.

[0225] For the first node N1, in step S100, second information is received, wherein the second information requests capability information of the first node; in step S101, the first type of capability information and the first information are sent;

[0226] For the second node N2, the second information is sent in step S200; the first type capability information and the first information are received in step S201.

[0227] In Example 5, the sending of the first information is triggered by the reception of the second information, and the first-category capability information includes MIMO-related parameters of the first frequency band; the first information includes a first-category identifier list, and any first-category identifier in the first-category identifier list indicates a trainable model; for the trainable model indicated by at least one first-category identifier in the first-category identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0228] As an embodiment, the first type capability information, the second information and the first information are all RRC layer signaling, and the first node N1 and the second node N2 are UE and base station respectively.

[0229] As a sub-embodiment of the above embodiment, the second information and the first information are a UECapabilityEnquiry message and a UECapabilityInformation message respectively.

[0230] As an embodiment, the first type of capability information is RRC layer signaling, the second information and the first information are both non-access stratum (NAS) signaling; the first node N1 includes UE, and the second node N2 includes a base station and a core network function on the network side.

[0231] As a sub-embodiment of the above embodiment, the second information and the first information are a RequestCapabilities message and a ProvideCapabilities message respectively.

[0232] As a sub-embodiment of the above embodiment, the first node N1 includes an application server on the UE side.

[0233] As an embodiment, the application server is installed by the UE through an executable file.

[0234] As an embodiment, the application server provides OTT (Over-the-Top) service.

[0235] As an embodiment, the application server is deployed outside the UE.

[0236] As an embodiment, the MIMO-related parameters of the first frequency band include codebook parameters. When the codebook parameters of the MIMO-related parameters of the first frequency band do not include a first-class codebook, the trainable model indicated by at least one first-class identifier in the first-class identifier list is not available for the first frequency band; the first-class codebook is non-constant modulus.

[0237] As an embodiment, the first type codebook is an enhanced type II codebook (Enhanced Type II Codebook).

[0238] As an embodiment, the accuracy of the first type of codebook is not lower than that of the enhanced second type of codebook.

[0239] As an embodiment, the first type of codebook includes an enhanced second type codebook, an enhanced second type port selection codebook (Enhanced Type II Port Selection Codebook), a further enhanced second type port selection codebook (Further enhanced Type II port selection codebook), an enhanced second type codebook for CJT (Coherent Joint Transmission, consistent joint transmission) (Enhanced Type II codebook for CJT), a further enhanced second type port selection codebook for CJT (Further enhanced Type II port selection codebook for CJT), an enhanced second type codebook for predicted PMI (Enhanced Type II codebook for predicted PMI), and a further enhanced second type port selection codebook for predicted PMI (Further enhanced Type II port selection codebook for predicted PMI) One or more.

[0240] As an embodiment, the MIMO-related parameters of the first frequency band include beam measurement-related parameters. When the beam measurement parameters of the MIMO-related parameters of the first frequency band do not include measuring first-class RS resources, the trainable model indicated by at least one first-class identifier in the first-class identifier list is not available for the first frequency band.

[0241] As an embodiment, the number of REs in each PRB per port of the first type of RS resources is greater than 3.

[0242] As an embodiment, the first type of RS resources are non-zero power (NZP-) CSI-RS resources.

[0243] As an embodiment, the first type of RS resources are non-periodic non-zero power CSI-RS resources.

[0244] As an embodiment, the first type of RS resources are non-zero power CSI-RS resources of two ports.

[0245] As an embodiment, the beam measurement parameter of the MIMO-related parameter of the first frequency band does not include measuring the first type of RS resources, which means that: the beam measurement-related parameter indicates the maximum number of first type RS resources for beam measurement, and the beam measurement-related parameter of the MIMO-related parameter of the first frequency band is 0.

[0246] As an embodiment, the beam measurement related parameter is maxNumberCSI-RS-Resource.

[0247] As an embodiment, the beam measurement related parameter is maxNumberCSI-RS-ResourceTwoTx.

[0248] As an embodiment, the first-class capability information includes reporting type information; when the reporting type information on the first frequency band does not include the first-class reporting, the trainable model indicated by the at least one first-class identifier in the first-class identifier list in the first information is not available for the first frequency band; the first-class reporting is used to determine the performance of the trainable model.

[0249] As an embodiment, the first type of reporting is non-periodic.

[0250] As an embodiment, the first type of reporting is non-periodic CSI.

[0251] As an embodiment, the first type of reporting is non-periodic PMI.

[0252] As an embodiment, the reporting type information on the first frequency band does not include the first type of reporting, which means that the reporting type information on the first frequency band is 0, and the reporting type information on the first frequency band has the largest number of first type of reporting.

[0253] As an embodiment, the reporting type information is maxNumberAperiodicCSI-PerBWP-ForCSI-Report.

[0254] As an embodiment, the reporting type information is maxNumberPeriodicCSI-PerBWP-ForBeamReport.

[0255] As an embodiment, the sending of the first information is triggered by any condition in a first condition set; wherein, one of the conditions in the first condition set is that at least one first-class identifier currently supported by the first node N1 does not belong to the most recently reported first-class identifier list; the first-class identifier list in the first information includes the at least one first-class identifier currently supported by the first node N1.

[0256] As an embodiment, one of the conditions in the first condition set is the receipt of the second information.

[0257] As an embodiment, one of the conditions in the first condition set is that at least one first-category identifier currently supported by the first node N1 does not belong to the most recently reported first-category identifier list, including: after the most recently reported first-category identifier list, the application server of the first node N1 is replaced.

[0258] As an embodiment, the replacement of the application server of the first node N1 includes: the first node N1 is switched from the first application server to the second application server.

[0259] As an embodiment, the first application server and the second application server are both deployed on the first node N1.

[0260] As an embodiment, the first application server and the second application server are two different applications.

[0261] As an embodiment, the first application server and the second application server are two different executable files.

[0262] As an embodiment, the first application server and the second application server are both deployed on remote servers outside the first node N1; switching from the first application server to the second application server is triggered by the movement of the first node N1, or triggered by the first node N1 executing a new application.

[0263] As an embodiment, one of the conditions in the first condition set is that at least one first-class identifier currently supported by the first node N1 does not belong to the most recently reported first-class identifier list, including: after the most recently reported first-class identifier list, the first node N1 receives signaling from the application server, and the signaling from the application server indicates the first-class identifier currently supported by the first node N1.

[0264] Similarly, the application server in the above embodiment is deployed in the first node N1, or deployed on a remote server outside the first node N1.

[0265] As an embodiment, the signaling from the application server is NAS signaling.

[0266] As an embodiment, the signaling from the application server is application layer signaling, that is, outside the scope of 3GPP.

[0267] Example 6

[0268] Example 6 illustrates a schematic diagram of the third information transmission according to an embodiment of the present application, as shown in FIG6 .

[0269] For the application server S1, the third information is sent in step S400; for the first node N1, the third information is received in step S500;

[0270] In Example 6, the third information indicates multiple first-class identifiers currently supported by the first node N1; the reception of the third information is used to trigger the sending of the first information; at least one of the multiple first-class identifiers does not belong to the first-class identifier list most recently reported by the first node N1 to the second node N2; the first-class identifier list in the first information includes the multiple first-class identifiers.

[0271] As an embodiment, the application server is an application program installed in the first node N1, and the third information is transmitted within the first node N1.

[0272] As an embodiment, the application server is a remote server outside the first node N1, and the transmission path of the third information includes an air interface.

[0273] Example 7

[0274] Embodiment 7 illustrates a schematic diagram of multiple frequency bands according to an embodiment of the present application, as shown in FIG7. In FIG7, frequency band #1, frequency band #2, ..., frequency band #F are F frequency bands indicated by the first type of capability information.

[0275] As an embodiment, the first type of capability information includes sub-capability information, and the multiple sub-capability information respectively indicate the F frequency bands, and the first frequency band is any frequency band among the F frequency bands.

[0276] As an embodiment, the F frequency bands are F NR frequency bands.

[0277] As an embodiment, the sub-capability information is BandNR IE.

[0278] As an embodiment, the sub-capability information includes part or all of the fields in BandNR, and the frequency band is indicated by FreqBandIndicatorNR in the corresponding sub-capability information.

[0279] As an embodiment, the first type of capability information is a supportedBandListNR IE, the first information is RRC signaling and the first information does not belong to the supportedBandListNR IE.

[0280] As a sub-embodiment of the above embodiment, the first type of capability information and the first information belong to one RF-Parameters IE.

[0281] As a sub-embodiment of the above embodiment, the first type of capability information and the first information belong to one UECapabilityInformationIE.

[0282] As a sub-embodiment of the above embodiment, the first type of capability information and the first information belong to the RF-Parameters IE in a UECapabilityInformationIE and the Phy-Parameters IE in the UECapabilityInformationIE respectively.

[0283] The above embodiments maintain good compatibility while avoiding configuring the first information for each frequency band, thus saving signaling overhead.

[0284] Example 8

[0285] Embodiment 8 illustrates a flowchart of measurement in the first RS resource according to an embodiment of the present application, as shown in FIG8 .

[0286] In step S500 , the first node N1 performs measurement in the first RS resource; the second node N2 sends a reference signal in the first RS resource.

[0287] Using measurements in the first RS resource, the trainable model in this application can be used to generate inferred information. In conjunction with Example 5, the first node N1 reports the inferred information to the second node N2. The type of inferred information varies with the application scenario. A typical implementation is disclosed below in conjunction with CSI feedback. However, those skilled in the art will appreciate that the methods and apparatus of this application are applicable to other implementations or inferred information other than CSI feedback, such as beam prediction, positioning information, and the like.

[0288] The first node N1 measures the reference signal in at least the first RS resource to obtain an original (Raw) channel matrix or a precoding matrix, and uses a first encoder to generate first channel information using the obtained original channel matrix or the precoding matrix; the first node N1 feeds back the first channel information to the second node N2, and the second node N2 inputs the first channel information into a first decoder to obtain recovered channel parameters; the first decoder can be considered as the inverse operation of the first encoder, and the first encoder and the first decoder are both obtained through training, that is, they belong to a trainable model.

[0289] As an embodiment, the first channel information indicates a precoding matrix.

[0290] As an embodiment, the recovered channel parameter is a precoding matrix.

[0291] As an embodiment, the precoding matrix is ​​in spatial-frequency domain.

[0292] As an embodiment, the precoding matrix is ​​angular-delay domain projection.

[0293] As an embodiment, the first channel information indicates a raw channel matrix (rawchannelmatrix).

[0294] As an embodiment, the recovered channel parameter is the original channel matrix.

[0295] As an embodiment, the original channel matrix is ​​in the space-frequency domain.

[0296] As an embodiment, the original channel matrix is ​​in the angle delay domain.

[0297] As an embodiment, the first channel information is used to determine a phase, or an amplitude, or a coefficient between at least two antenna ports.

[0298] As an embodiment, the first channel information is used to determine at least one eigenvector.

[0299] As an embodiment, the first channel information is used to determine at least one characteristic value.

[0300] The legal codebook can be used to monitor or calibrate the performance of the first encoder and / or the first decoder; that is, the first node N1 periodically or irregularly reports the PMI to the second node N2. Generally speaking, how to select the precoding matrix from the legal codebook is implementation-dependent and is determined by each manufacturer. Common solutions include maximizing spatial projection or maximizing channel capacity. A typical but non-limiting implementation is described below:

[0301] The first node N1 first measures the downlink RS (eg, the first RS resource) to obtain the original channel matrix (or the precoding matrix indicated by the first channel information) H r×t , where r, t are the number of receiving antennas and the number of antenna ports for transmission respectively; when using the precoding matrix W t×lUnder the condition of , the coded channel parameter matrix is ​​H r×t W t×l , where l is the rank or number of layers; H is calculated using criteria such as SINR (Signal Interference Noise Ratio), EESM (Exponential Effective SINR Mapping), or RBIR (Received Block Mean Mutual Information Ratio). r×t W t×l Furthermore, the calculation of the equivalent channel capacity may also take into account noise and interference estimation by the first node N1. If the downlink RS includes RS resources for interference measurement, the first node N1 may use these RS resources to more accurately measure interference or noise. The first node N1 selects a precoding matrix corresponding to the maximum equivalent channel capacity from the legal codebook as the virtual precoding matrix.

[0302] In order to improve the accuracy of monitoring or calibration, the legal codebook is the first type of codebook in this application.

[0303] It should be additionally noted that, when the first node N1 and the second node N2 adopt different channel reconstruction models, their understandings of the precoding matrix indicated by the first channel information may be different.

[0304] Typically, the first channel information is generated based on an artificial intelligence method.

[0305] As an embodiment, the first channel information is transmitted on a first physical layer channel.

[0306] As an embodiment, the first physical layer channel is PUSCH (Physical Uplink Shared Channel).

[0307] As an embodiment, the first physical layer channel is PUCCH (Physical Uplink Control Channel).

[0308] Example 9

[0309] Embodiment 9 illustrates a schematic diagram of a system including a trainable model according to an embodiment of the present application, as shown in FIG9 . FIG9 includes a first processor, a second processor, a third processor, and a fourth processor.

[0310] In Example 9, the first processor sends a first data set to the second processor, the second processor generates a target first-category parameter group based on the first data set, the second processor sends the generated target first-category parameter group to the third processor, the third processor uses the target first-category parameter group to process the second data set to obtain a first-category output, and then sends the first-category output to the fourth processor.

[0311] As an embodiment, the third processor sends first-type feedback to the second processor, where the first-type feedback is used to trigger recalculation or updating of the target first-type parameter group.

[0312] As an embodiment, the fourth processor sends a second type of feedback to the first processor, and the second type of feedback is used to generate the first data set or the second data set, or the second type of feedback is used to trigger the sending of the first data set or the second data set.

[0313] As an embodiment, the first processor generates the first data set and the second data set based on measurements of a first wireless signal, where the first wireless signal includes a downlink RS.

[0314] As an embodiment, the second data set is obtained based on the measurement of the first RS resources.

[0315] As an embodiment, the first processor and the third processor belong to a first node, and the fourth processor belongs to a second node.

[0316] As an embodiment, the first type of output includes the at least first channel information.

[0317] As an embodiment, the first type of output includes multiple non-codebook reports, and the first channel information is one of the multiple non-codebook reports.

[0318] As an embodiment, the second processor belongs to the first node.

[0319] As an embodiment, the trainable model includes the third processor.

[0320] As an embodiment, the trainable model includes the second processor and the third processor.

[0321] As an embodiment, the trainable model includes the fourth processor and the third processor.

[0322] The above embodiment avoids transferring the first data set to the second node.

[0323] As an embodiment, the second processor belongs to the second node.

[0324] The above embodiment reduces the complexity of the first node.

[0325] As an embodiment, the first data set is training data (TrainingData), the second data set is interference data (InterferenceData), the second processor is used to train a model, and the trained model is described by the target first type parameter group.

[0326] As an embodiment, the third processor constructs a model according to the target first-category parameter group, then inputs the second data set into the constructed model to obtain the first-category output, and then sends the first-category output to the fourth processor.

[0327] As a sub-embodiment of the above embodiment, the third processing machine includes the first encoder of the present application, the first encoder is described by the target first-type parameter group, and the generation of the first-type output is performed by the first encoder.

[0328] As an embodiment, the third processor calculates the error between the first type of output and actual data to determine the performance of the trained model; the actual data is the data received after the second data set and transmitted by the first processor.

[0329] The above embodiment is particularly suitable for prediction-related reporting.

[0330] As an embodiment, the third processing machine recovers a reference data set based on the first type of output, and an error between the reference data set and the second data set is used to generate the first type of feedback.

[0331] The restoration of the reference data set usually adopts an inverse operation similar to the target first-category parameter group. The above embodiment is particularly suitable for CSI compression-related reporting.

[0332] As an embodiment, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the second processor will recalculate the target first type parameter group.

[0333] As a sub-embodiment of the above embodiment, the third processing machine includes a first reference decoder of the present application, wherein the first reference decoder is described by the target first type parameter set, the input of the first reference decoder includes the first type output, and the output of the first reference decoder includes the reference data set.

[0334] Typically, when the error is too large or has not been updated for too long, the performance of the trained model is considered unsatisfactory.

[0335] As an embodiment, the third processor belongs to the second node, and the first node reports the target first-category parameter group to the second node.

[0336] Example 10

[0337] Embodiment 10 illustrates a flow chart of transmitting first channel information according to an embodiment of the present application, as shown in FIG10. In FIG10, the first reference decoder is optional.

[0338] In embodiment 10, the first encoder and the first decoder belong to the first node and the second node respectively; wherein the first encoder belongs to the first transmitter, and the first decoder belongs to the second receiver.

[0339] The first transmitter generates the at least first channel information using a first encoder; wherein the input of the first encoder includes a first channel input, the first encoder is obtained through training; and the first channel input is obtained based on a measurement of a first RS resource group;

[0340] The first node feeds back the first channel information to the second node via an air interface;

[0341] The second receiver generates a first restored channel matrix using a first decoder; wherein the input of the first decoder includes the first channel information, and the first decoder is obtained through training.

[0342] The first encoder and the first decoder should theoretically be mutually inverse operations to ensure that the first channel input is identical to the first restored channel matrix.

[0343] As an embodiment, due to factors such as implementation complexity, air interface overhead, or delay, the first encoder and the first decoder in Example 10 cannot ensure complete cancellation, so the first channel input and the first recovered channel matrix cannot ensure to be exactly the same, resulting in different understandings of the precoding matrix represented by the first channel information by both parties.

[0344] As an embodiment, the first channel input is an original channel matrix.

[0345] As an embodiment, the first channel input is a precoding matrix.

[0346] As an embodiment, the first transmitter further includes a first reference decoder, the input of the first reference decoder includes the first channel information, and the output of the first reference decoder includes a first monitoring output.

[0347] As an embodiment, the first channel matrix is ​​the first monitoring output, and the first reference decoder and the first decoder cannot be considered to be the same.

[0348] In the above embodiment, the first reference decoder and the first decoder may be independently generated or maintained, so although their purpose is to perform the inverse operation of the first encoder, the two may only be approximate.

[0349] As an embodiment, the first transmitter includes the third processor in Embodiment 9.

[0350] As an embodiment, the first channel input belongs to the second data set in Example 9.

[0351] As an embodiment, the training of the first encoder is performed at the first node.

[0352] As an embodiment, the training of the first encoder is performed by the second node.

[0353] As an embodiment, the first restored channel matrix is ​​only known to the second node.

[0354] As an embodiment, the first restored channel matrix and the first channel matrix cannot be considered to be the same.

[0355] As an embodiment, the trainable model includes the first encoder.

[0356] As an embodiment, the trainable model includes the first encoder and the first decoder.

[0357] Example 11

[0358] Embodiment 11 illustrates a schematic diagram of a first encoder according to an embodiment of the present application, as shown in Figure 11. In Figure 11, the first encoder includes P1 coding layers, namely coding layers #1, #2, ..., #P1.

[0359] As an embodiment, P1 is 2, that is, the P1 coding layers include coding layer #1 and coding layer #2, wherein coding layer #1 and coding layer #2 are convolutional layers and fully connected layers, respectively; in the convolutional layer, at least one convolution kernel is used to convolve the first channel input to generate a corresponding feature map, and at least one feature map output by the convolutional layer is reshaped into a vector input to the fully connected layer; the fully connected layer converts the one vector into first channel information. For a more detailed description, please refer to CNN-related technical literature, such as Chao-Kai Wen, Deep Learning for Massive MIMO CSI Feedback, IEEE WIRELESS COMMUNICATIONS LETTERS, VOL. 7, NO. 5, OCTOBER 2018, etc.

[0360] As an embodiment, the P1 is 3, that is, the P1 encoding layer includes a fully connected layer, a convolutional layer, and a pooling layer.

[0361] Example 12

[0362] Embodiment 12 illustrates a schematic diagram of a first function according to an embodiment of the present application, as shown in FIG12. In FIG12, the first function includes a preprocessing layer and P2 decoding layer groups, namely decoding layer groups #1, #2, ..., #P2, each decoding layer group including at least one decoding layer.

[0363] The structure of the first function is applicable to the first decoder and the first reference decoder in embodiment 10.

[0364] As an embodiment, the preprocessing layer is a fully connected layer, which expands the size of the first channel information to the size of the first channel input.

[0365] As an embodiment, any two decoding layer groups in the P2 decoding layer groups have the same structure, which includes the number of decoding layers included, the size of input parameters and output parameters of each decoding layer included, etc.

[0366] As an embodiment, the second node indicates the structure of P2 and the decoding layer group to the first node, and the first node indicates other parameters of the first function through the second signaling.

[0367] As an embodiment, the other parameters include at least one of a threshold of an activation function, a size of a convolution kernel, a step size of a convolution kernel, and a weight between feature maps.

[0368] Example 13

[0369] Embodiment 13 illustrates a schematic diagram of a decoding layer group according to an embodiment of the present application, as shown in FIG13. In FIG13, decoding layer group #j includes L layers, namely layers #1, #2, ..., #L; the decoding layer group is any one of the P2 decoding layer groups.

[0370] As an embodiment, L is 4, the first layer in the L layer is the input layer, and the last three layers of the L layer are convolutional layers. For a more detailed description, please refer to CNN-related technical literature, such as Chao-Kai Wen, Deep Learning for Massive MIMO CSI Feedback, IEEE WIRELESS COMMUNICATIONS LETTERS, VOL.7, NO.5, OCTOBER 2018, etc.

[0371] As an embodiment, the L layer includes at least one convolutional layer and one pooling layer.

[0372] Example 14

[0373] Embodiment 14 illustrates a structural block diagram of a processing device in a first node according to an embodiment of the present application, as shown in FIG14. In FIG14, the processing device 1600 in the first node includes a first receiver 1601 and a first transmitter 1602; wherein the first receiver 1601 is optional.

[0374] The first receiver 1601 receives second information requesting capability information of the first node; the first transmitter 1602 sends the first type of capability information and the first information;

[0375] In Example 14, the sending of the first information is triggered by the reception of the second information; the first-class capability information includes MIMO-related parameters of the first frequency band; the first information includes a first-class identifier list, and any first-class identifier in the first-class identifier list indicates a trainable model; for the trainable model indicated by at least one first-class identifier in the first-class identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0376] As an embodiment, the MIMO-related parameters of the first frequency band include codebook parameters. When the codebook parameters of the MIMO-related parameters of the first frequency band do not include a first-class codebook, the trainable model indicated by at least one first-class identifier in the first-class identifier list is not available for the first frequency band; the first-class codebook is non-constant modulus.

[0377] As an embodiment, the MIMO-related parameters of the first frequency band include beam measurement-related parameters. When the beam measurement parameters of the MIMO-related parameters of the first frequency band do not include measuring first-class RS resources, the trainable model indicated by at least one first-class identifier in the first-class identifier list is not available for the first frequency band.

[0378] As an embodiment, the first-class capability information includes reporting type information; when the reporting type information on the first frequency band does not include the first-class reporting, the trainable model indicated by the at least one first-class identifier in the first-class identifier list in the first information is not available for the first frequency band; the first-class reporting is used to determine the performance of the trainable model.

[0379] As an embodiment, the sending of the first information is triggered by any condition in the first condition set;

[0380] Among them, one of the conditions in the first condition set is that at least one first-class identifier currently supported by the first node does not belong to the most recently reported first-class identifier list; the first-class identifier list in the first information includes the at least one first-class identifier currently supported by the first node.

[0381] As an embodiment, one of the conditions in the first condition set is that at least one first-category identifier currently supported by the first node does not belong to a most recently reported first-category identifier list, including at least one of the following:

[0382] After the most recently reported first category identifier list, the application server of the first node is replaced;

[0383] After the most recently reported first category identifier list, the first node receives signaling from an application server, where the signaling from the application server indicates the first category identifiers currently supported by the first node.

[0384] As an embodiment, the first node 1600 is a user equipment.

[0385] As an embodiment, the first transmitter 1602 includes at least one of the antenna 452, transmitter / receiver 454, multi-antenna transmitter processor 457, transmit processor 468, controller / processor 459, memory 460 and data source 467 in FIG4 of the present application.

[0386] As an embodiment, the first transmitter 1602 includes the antenna 452, transmitter / receiver 454, multi-antenna transmitter processor 457, transmit processor 468, controller / processor 459, memory 460 and data source 467 in FIG. 4 of the present application.

[0387] As an embodiment, the first receiver 1601 includes at least the first five of the antenna 452, receiver 454, multi-antenna receiving processor 458, receiving processor 456, controller / processor 459, memory 460 and data source 467 in Figure 4 of the present application.

[0388] As an embodiment, the first receiver 1601 includes at least the first four of the antenna 452, receiver 454, multi-antenna receiving processor 458, receiving processor 456, controller / processor 459, memory 460 and data source 467 in Figure 4 of the present application.

[0389] As an embodiment, the first receiver 1601 includes at least the first three of the antenna 452, receiver 454, multi-antenna receiving processor 458, receiving processor 456, controller / processor 459, memory 460 and data source 467 in Figure 4 of the present application.

[0390] Example 15

[0391] Embodiment 15 illustrates a structural block diagram of a processing device in a second node according to an embodiment of the present application, as shown in FIG15. In FIG15, the processing device 1700 in the second node includes a second transmitter 1701 and a second receiver 1702, wherein the second transmitter 1701 is optional.

[0392] The second transmitter 1701 sends second information, wherein the second information requests capability information of the first node; the second receiver 1702 receives the first type of capability information and the first information;

[0393] In Example 15, the sending of the first information is triggered by the reception of the second information, and the first-class capability information includes MIMO-related parameters of the first frequency band; the first information includes a first-class identifier list, and any first-class identifier in the first-class identifier list indicates a trainable model; for the trainable model indicated by at least one first-class identifier in the first-class identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO-related parameters on the first frequency band.

[0394] As an embodiment, the first information is sent after the first type capability information.

[0395] As an embodiment, the MIMO-related parameters of the first frequency band include codebook parameters. When the codebook parameters of the MIMO-related parameters of the first frequency band do not include a first-class codebook, the trainable model indicated by at least one first-class identifier in the first-class identifier list is not available for the first frequency band; the first-class codebook is non-constant modulus.

[0396] As an embodiment, the MIMO-related parameters of the first frequency band include beam measurement-related parameters. When the beam measurement parameters of the MIMO-related parameters of the first frequency band do not include measuring first-class RS resources, the trainable model indicated by at least one first-class identifier in the first-class identifier list is not available for the first frequency band.

[0397] As an embodiment, the first-class capability information includes reporting type information; when the reporting type information on the first frequency band does not include the first-class reporting, the trainable model indicated by the at least one first-class identifier in the first-class identifier list in the first information is not available for the first frequency band; the first-class reporting is used to determine the performance of the trainable model.

[0398] As an embodiment, the sending of the first information is triggered by any condition in a first condition set; wherein, one of the conditions in the first condition set is that at least one first-class identifier currently supported by the first node does not belong to the most recently reported first-class identifier list; the first-class identifier list in the first information includes the at least one first-class identifier currently supported by the first node.

[0399] As an embodiment, one of the conditions in the first condition set is that at least one first-category identifier currently supported by the first node does not belong to a most recently reported first-category identifier list, including at least one of the following:

[0400] After the most recently reported first category identifier list, the application server of the first node is replaced;

[0401] After the most recently reported first category identifier list, the first node receives signaling from an application server, where the signaling from the application server indicates the first category identifier currently supported by the first node;

[0402] As an embodiment, the second node 1700 is a base station device.

[0403] As an embodiment, the second node 1700 includes a base station device and a core network function.

[0404] As an embodiment, the second transmitter 1701 includes the antenna 420, the transmitter 418, the transmit processor 416, and the controller / processor 475.

[0405] As an embodiment, 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.

[0406] As an embodiment, the second transmitter 1701 includes the antenna 420, the transmitter 418, the transmit processor 416, and the controller / processor 475.

[0407] As an embodiment, 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.

[0408] As an embodiment, the second receiver 1702 includes the antenna 420, the receiver 418, the multi-antenna reception processor 472, the reception processor 470, and the controller / processor 475.

[0409] As an embodiment, the second receiver 1702 includes the controller / processor 475.

[0410] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a hard disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module unit in the above embodiment can be implemented in the form of hardware or in the form of a software functional module. This application is not limited to any specific form of combination of software and hardware. The user equipment, terminal and UE in this application include but are not limited to drones, communication modules on drones, remote-controlled aircraft, aircraft, small aircraft, mobile phones, tablet computers, notebooks, vehicle-mounted communication equipment, wireless sensors, internet cards, Internet of Things terminals, RFID terminals, NB-IOT terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, internet cards, vehicle-mounted communication equipment, low-cost mobile phones, low-cost tablet computers and other wireless communication devices. The base stations or system devices in this application include but are not limited to macrocell base stations, microcell base stations, home base stations, relay base stations, gNB (NR node B) NR node B, TRP (Transmitter Receiver Point) and other wireless communication devices.

[0411] Those skilled in the art will appreciate that the present application may be implemented in other specific forms without departing from its core or essential features. Therefore, the presently disclosed embodiments should be considered in all respects as illustrative and not restrictive. The scope of the invention is determined by the appended claims, not the foregoing description, and all modifications within the meaning and range of equivalents are intended to be included therein.

Claims

1. A first node for use in wireless communication, characterized in that, Comprising: A first transmitter that transmits first - type capability information, where the first - type capability information includes MIMO - related parameters of a first frequency band; and transmits first information, where the first information includes a first - type identifier list, and any first - type identifier in the first - type identifier list indicates a trainable model. Among them, for the trainable model indicated by at least one first - type identifier in the first - type identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO - related parameters on the first frequency band.

2. The first node according to claim 1, characterized in that, The MIMO - related parameters of the first frequency band include codebook parameters. When the codebook parameters of the MIMO - related parameters of the first frequency band do not include a first - type codebook, the trainable model indicated by at least one first - type identifier in the first - type identifier list is not available for the first frequency band; the first - type codebook is non - constant - modulus.

3. The first node according to claim 1 or 2, characterized in that The MIMO - related parameters of the first frequency band include beam measurement - related parameters. When the beam measurement parameters of the MIMO - related parameters of the first frequency band do not include measuring a first - type RS resource, the trainable model indicated by at least one first - type identifier in the first - type identifier list is not available for the first frequency band.

4. The first node according to any one of claims 1 to 3, characterized in that, The first - type capability information includes reporting type information; when the reporting type information on the first frequency band does not include a first - type report, the trainable model indicated by at least one first - type identifier in the first - type identifier list in the first information is not available for the first frequency band; the first - type report is used to determine the performance of the trainable model.

5. The first node according to any one of claims 1 to 4, characterized in that The transmission of the first information is triggered by any condition in a first condition set. Among them, one condition in the first condition set is that at least one first - type identifier currently supported by the first node does not belong to the first - type identifier list reported most recently; the first - type identifier list in the first information includes at least one first - type identifier currently supported by the first node.

6. The first node according to any one of claims 1 to 5, characterized in that, Comprising: A first receiver that receives second information, where the second information requests the capability information of the first node. Among them, the transmission of the first information is triggered by the reception of the second information.

7. The first node according to claim 5 or 6, characterized in that, One condition in the first condition set that at least one first - type identifier currently supported by the first node does not belong to the first - type identifier list reported most recently includes at least one of the following: After the first - type identifier list reported most recently, the application server of the first node is replaced. After the first - type identifier list reported most recently, the first node receives a signaling from the application server, and the signaling from the application server indicates the first - type identifier currently supported by the first node.

8. A second node for use in wireless communication, characterized in that, Comprising: A second receiver that receives first - type capability information, where the first - type capability information includes MIMO - related parameters of a first frequency band; and receives first information, where the first information includes a first - type identifier list, and any first - type identifier in the first - type identifier list indicates a trainable model. Among them, for the trainable model indicated by at least one first type identifier in the first type identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO related parameters on the first frequency band.

9. The second node according to claim 8, characterized in that, Including: A second transmitter that transmits second information, where the second information requests the capability information of a first node; Among them, the transmission of the first information is triggered by the reception of the second information.

10. A method in a first node for wireless communication, characterized in that, Including: Transmit first type capability information, where the first type capability information includes MIMO related parameters of a first frequency band; transmit first information, where the first information includes a first type identifier list, and any first type identifier in the first type identifier list indicates a trainable model; Among them, for the trainable model indicated by at least one first type identifier in the first type identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO related parameters on the first frequency band.

11. A method in a second node for wireless communication, characterized in that, Including: Receive first type capability information, where the first type capability information includes MIMO related parameters of a first frequency band; Receive first information, where the first information includes a first type identifier list, and any first type identifier in the first type identifier list indicates a trainable model; Among them, for the trainable model indicated by at least one first type identifier in the first type identifier list in the first information, whether it is applied to the first frequency band depends on the MIMO related parameters on the first frequency band.

Images