Method and apparatus for reporting channel state information

Abstract

A method according to an embodiment of the present specification comprises the steps of: receiving configuration information related to channel state information (CSI); and transmitting at least one CSI report on the basis of a priority rule. The at least one CSI report includes: i) a first CSI report including a measurement result related to beam prediction; and / or ii) a second CSI report including an inference result related to the beam prediction. The at least one CSI report has a higher priority than a priority for a third CSI report not carrying reference signal received power (RSRP) and / or signal-to-interference noise ratio (SINR).

Description

Method and device for reporting channel status information

[0001] This specification relates to a method and device for reporting channel state information.

[0002] Mobile communication systems were developed to provide voice services while ensuring user activity. However, they have expanded beyond voice to include data services. Currently, explosive growth in traffic is leading to resource shortages and users are demanding faster services, necessitating a more advanced mobile communication system.

[0003] Next-generation mobile communication systems must support explosive data traffic growth, dramatically increasing data rates per user, a vastly increased number of connected devices, ultra-low end-to-end latency, and high energy efficiency. To achieve these goals, various technologies are being studied, including dual connectivity, massive multiple input multiple output (MIMO), in-band full duplex, non-orthogonal multiple access (NOMA), super wideband support, and device networking.

[0004] Meanwhile, measurement and reporting operations for beam management are defined. For example, beam-related information may be reported based on preset or defined priority rules. In this case, the beam-related information may be reported based on preset or defined times and / or CSI processing units (CPUs).

[0005] According to the measurement and reporting operation for beam management, beam-related Channel State Information (CSI) based on an Artificial Intelligence (AI) / Machine Learning (ML) model can be reported. At this time, the AI / ML model-based beam-related CSI report may be i) a CSI report in which a terminal measures and reports a beam for a network-side (NW-sided) AI / ML model and / or ii) a CSI report in which a beam predicted by a terminal-side (UE-sided) AI / ML model is reported. If a CSI report not related to an existing AI / ML model and a beam-related CSI report based on an AI / ML model collide, the priority may be ambiguous, making it difficult to determine which CSI report to transmit.

[0006] For example, when a conventional beam-related CSI report and an AI / ML model-based beam-related CSI report collide, it may be ambiguous from the terminal and / or network perspective to determine whether i) to transmit the conventional beam-related CSI report and not transmit the AI / ML model-based beam-related CSI report, ii) to transmit the AI / ML model-based beam-related CSI report and not transmit the conventional beam-related CSI report, or iii) to multiplex and transmit the two CSI reports together. The purpose of this specification is to propose a method for solving the above-described problem.

[0007] Meanwhile, AI / ML model-based beam-related CSI can report more beams than conventional beam-related CSI. Furthermore, AI / ML model-based beam-related CSI reports may require more computational effort than conventional CSI reports due to the additional AI / ML model inference process. If the same amount of resources are allocated to AI / ML model-based beam-related CSI reports as conventional CSI reports, the AI / ML model-based beam-related CSI reports may be incompletely performed.

[0008] For example, if the same processing time and / or CSI processing unit (CPU) is allocated to a beam-related CSI report based on an AI / ML model as to a conventional CSI report, beam measurement and / or beam prediction for beam prediction may be performed incompletely. Another object of the present specification is to propose a method for solving the above-described problem.

[0009] The technical problems to be achieved in this specification are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which the present invention pertains from the description below.

[0010] In order to solve the above-described technical problem, a method according to one embodiment of the present specification includes a step of receiving configuration information related to channel state information (CSI) and a step of transmitting at least one CSI report based on a priority rule.

[0011] The at least one CSI report comprises i) a first CSI report including measurement results related to beam prediction and / or ii) a second CSI report including inference results related to the beam prediction.

[0012] The at least one CSI report has a higher priority than a priority of a third CSI report that does not carry Reference Signal Received Power (RSRP) and / or Signal-to-Interference Noise Ratio (SINR).

[0013] As described above, by clarifying the priority rules between the AI / ML model-based beam-related CSI report and the existing CSI report, the above-described problem (e.g., when a CSI report not related to the existing AI / ML model and a beam-related CSI report based on the AI / ML model collide, the priority is ambiguous, making it difficult to accurately determine which CSI report should be transmitted) can be solved.

[0014] The above measurement results may include RSRP and / or SINR.

[0015] The above inference results may include predicted RSRP and / or predicted SINR.

[0016] The above inference result may be an output of a model based on the above measurement result.

[0017] The above first CSI report may have a higher priority than the above second CSI report.

[0018] The above second CSI report may have a higher priority than the above first CSI report.

[0019] A CSI report based on a CSI reporting setting related to LTM (L1 / L2 Triggered Mobility) may have a higher priority than the priority for at least one CSI report.

[0020] The at least one CSI report may be transmitted based on a first symbol number associated with a CSI computation time.

[0021] The number of the first symbols may be greater than the number of the second symbols defined for the report quantity associated with RSRP.

[0022] As described above, the accuracy of beam prediction can be improved by setting or defining the processing time for AI / ML model-based CSI reports to be longer than the existing CSI report processing time.

[0023] The number of the first symbols may be determined based on the number of beams included in the at least one CSI report.

[0024] The number of the first symbols may be set and / or defined based on UE capability.

[0025] The number of first CSI processing units (CSI Processing Units, CPUs) associated with one of the at least one CSI report may be greater than the number of second CPUs associated with a CSI report for RSRP or SINR.

[0026] As described above, the accuracy of beam prediction can be improved by setting or defining the number of CPUs occupied by the AI / ML model-based CSI report to be greater than the number of CPUs occupied by the existing CSI report.

[0027] The number of the first CPUs may be determined based on the number of beams included in the at least one CSI report.

[0028] The number of the above first CPUs can be set and / or defined based on terminal capability (UE capability).

[0029] The above first CPUs may be occupied from the time of starting beam measurement for the at least one CSI report until the time of transmitting the at least one CSI report.

[0030] The first CSI report may be related to an input of the first model, and the second CSI report may be related to an output of the second model.

[0031] The above first model may be a network-sided model,

[0032] The above second model may be a user equipment-sided model.

[0033] A terminal according to another embodiment of the present disclosure includes one or more transceivers, one or more processors, and one or more memories connected to the one or more processors and storing instructions.

[0034] The above instructions are characterized in that they cause the terminal to perform all steps of any one of the above methods based on being executed by the one or more processors.

[0035] According to another embodiment of the present disclosure, a device comprises one or more memories and one or more processors connected to the one or more memories. The one or more memories are characterized in that they store instructions that cause the device to perform all steps of any one of the above methods based on instructions executed by the one or more processors.

[0036] A non-transitory computer-readable medium according to another embodiment of the present disclosure stores instructions, the instructions being executable by one or more processors, characterized in that they cause a terminal to perform all steps of any one of the above methods.

[0037] A method according to another embodiment of the present disclosure includes a step of transmitting configuration information related to channel state information (CSI) and a step of receiving at least one CSI report based on a priority rule.

[0038] The at least one CSI report comprises i) a first CSI report including measurement results related to beam prediction and / or ii) a second CSI report including inference results related to the beam prediction.

[0039] The at least one CSI report has a higher priority than a priority of a third CSI report that does not carry Reference Signal Received Power (RSRP) and / or Signal-to-Interference Noise Ratio (SINR).

[0040] A base station according to another embodiment of the present disclosure includes one or more transceivers, one or more processors, and one or more memories coupled to the one or more processors and storing instructions.

[0041] The above instructions are characterized in that they cause the base station to perform all steps of the method based on being executed by the one or more processors.

[0042] According to conventional techniques, when CSI reports unrelated to existing AI / ML models collide with AI / ML model-based beam-related CSI reports, priority ambiguity can make it difficult to determine which CSI report should be transmitted. This can degrade beam prediction accuracy and waste uplink resources due to CSI reports for relatively less important beams.

[0043] According to embodiments of the present disclosure, when a terminal performs a beam-related CSI report based on an AI / ML model, the priority between the AI / ML model-based beam-related CSI report and the existing CSI report is clearly defined, so that the terminal can appropriately perform a CSI report for a relatively important beam. Accordingly, the accuracy of beam prediction can be improved, and fast beam switching is possible based on a clear priority. This can reduce the probability of failure during beam search or beam switching, thereby improving connection reliability.

[0044] According to the operation according to the prior art, the AI / ML model-based beam-related CSI report may be performed incompletely because the same amount of resources are allocated to the AI / ML model-based beam-related CSI report as the existing CSI report.

[0045] According to embodiments of the present disclosure, by clearly defining the processing time and / or the number of occupied CSI processing units (CPUs) for AI / ML model-based beam-related CSI reports, the processing time required for AI / ML model inference is guaranteed, and AI / ML model-based beam-related CSI reports can be performed more completely. This can improve beam prediction accuracy, enhance the reliability of beam selection and beam switching procedures based on CSI reports, and further improve the stability and sustainability of wireless connections.

[0046] The effects that can be obtained from this specification are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by those skilled in the art to which the present invention pertains from the description below.

[0047] Figure 1 shows an example of beam forming using SSB and CSI-RS.

[0048] Figure 2 is a flowchart showing an example of a DL BM procedure.

[0049] FIG. 3 illustrates an example of a CSI reporting setting according to an embodiment of the present specification.

[0050] Figure 4 is a diagram to explain overall functions from an AI / ML model perspective.

[0051] Figure 5 illustrates a general form of AI / ML related procedures performed between a network and a terminal.

[0052] Figure 6 illustrates an example of AI / ML-based beam management operations.

[0053] FIG. 7 is a flowchart illustrating a method according to one embodiment of the present specification.

[0054] FIG. 8 is a flowchart illustrating a method according to another embodiment of the present specification.

[0055] FIG. 9 is a drawing showing the configuration of a first device and a second device according to an embodiment of the present specification.

[0056] Hereinafter, preferred embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. The detailed description set forth below, together with the accompanying drawings, is intended to illustrate exemplary embodiments of the present disclosure and is not intended to represent the only embodiments in which the present disclosure may be implemented. The following detailed description includes specific details to provide a thorough understanding of the present disclosure.

[0057] In some cases, to avoid ambiguity in the concepts of this specification, well-known structures and devices may be omitted or illustrated in block diagram form focusing on the core functions of each structure and device.

[0058] Hereinafter, downlink (DL) refers to communication from a base station to a terminal, and uplink (UL) refers to communication from a terminal to a base station. In downlink, a transmitter may be part of a base station, and a receiver may be part of a terminal. In uplink, a transmitter may be part of a terminal, and a receiver may be part of a base station. A base station may be expressed as a first communication device, and a terminal may be expressed as a second communication device. A base station (BS) may be replaced by terms such as a fixed station, Node B, eNB (evolved-NodeB), gNB (Next Generation NodeB), BTS (base transceiver system), access point (AP: Access Point), network (5G network), AI system, RSU (road side unit), vehicle, robot, drone (Unmanned Aerial Vehicle, UAV), AR (Augmented Reality) device, VR (Virtual Reality) device, etc. In addition, the terminal may be fixed or mobile, and may be replaced with terms such as UE (User Equipment), MS (Mobile Station), UT (user terminal), MSS (Mobile Subscriber Station), SS (Subscriber Station), AMS (Advanced Mobile Station), WT (Wireless terminal), MTC (Machine-Type Communication) device, M2M (Machine-to-Machine) device, D2D (Device-to-Device) device, vehicle, robot, AI module, drone (Unmanned Aerial Vehicle, UAV), AR (Augmented Reality) device, VR (Virtual Reality) device, etc.

[0059] < Beam Management (BM) >

[0060] BM procedures are L1 (layer 1) / L2 (layer 2) procedures for acquiring and maintaining a set of base station (e.g., gNB, TRP, etc.) and / or terminal (e.g., UE) beams that can be used for downlink (DL) and uplink (UL) transmission / reception, and may include the following procedures and terminology.

[0061] - Beam measurement: An operation in which a base station or UE measures the characteristics of a received beam-forming signal.

[0062] - Beam determination: An operation in which a base station or UE selects its own transmit beam (Tx beam) / receive beam (Rx beam).

[0063] - Beam sweeping: The operation of covering a spatial area using a transmit and / or receive beam over a predetermined time interval in a predetermined manner.

[0064] - Beam report: An operation in which a UE reports information about a beam-formed signal based on beam measurement.

[0065] The BM procedure can be divided into (1) a DL BM procedure using SS (synchronization signal) / PBCH (physical broadcast channel) Block or CSI-RS, and (2) a UL BM procedure using SRS (sounding reference signal).

[0066] Additionally, each BM procedure may include Tx beam sweeping to determine the Tx beam and Rx beam sweeping to determine the Rx beam.

[0067] DL BM

[0068] The DL BM procedure may include (1) transmission of beamformed DL RSs (reference signals) (e.g., CSI-RS or SS Block (SSB)) of the base station and (2) beam reporting of the terminal.

[0069] Here, beam reporting may include preferred DL RS ID(identifier)(s) and corresponding L1-RSRP (Reference Signal Received Power).

[0070] The above DL RS ID may be an SSBRI (SSB Resource Indicator) or a CRI (CSI-RS Resource Indicator).

[0071] Figure 1 shows an example of beam forming using SSB and CSI-RS.

[0072] As shown in Figure 1, SSB beams and CSI-RS beams can be used for beam measurement. The measurement metric is L1-RSRP per resource / block. SSB is used for coarse beam measurement, and CSI-RS can be used for fine beam measurement. SSB can be used for both Tx beam sweeping and Rx beam sweeping.

[0073] Rx beam sweeping using SSB can be performed by the UE changing the Rx beam for the same SSBRI across multiple SSB bursts, where one SS burst contains one or more SSBs, and one SS burst set contains one or more SSB bursts.

[0074] Figure 2 is a flowchart showing an example of a DL BM procedure.

[0075] The configuration for beam report using SSB is performed during CSI / beam configuration in RRC connected state (or RRC connected mode).

[0076] - The terminal receives configuration information from the base station. As a specific example, the terminal receives a CSI-ResourceConfig IE including a CSI-SSB-ResourceSetList including SSB resources used for BM from the base station (S210).

[0077] Table 1 shows an example of the CSI-ResourceConfig IE. As shown in Table 1, BM configuration using SSB is not defined separately, and SSB is configured as a CSI-RS resource.

[0078]

[0079] In Table 1, the csi-SSB-ResourceSetList parameter indicates a list of SSB resources used for beam management and reporting in a single CSI-RS resource set. Here, the SSB resource set can be set to {SSBx1, SSBx2, SSBx3, SSBx4, …}. For example, the SSB index can be defined from 0 to 63.

[0080] - The terminal receives a downlink reference signal (DL RS) from the base station. As a specific example, the terminal receives an SSB from the base station based on the CSI-SSB-ResourceSetList (S220).

[0081] - The terminal transmits a beam report to the base station. For example, if CSI-ReportConfig related to reporting on SSBRI (SSB Resource Indicator) and L1-RSRP is set, the terminal reports the best SSBRI and its corresponding L1-RSRP to the base station (S230).

[0082] That is, when the reportQuantity of the above CSI-ReportConfig IE is set to 'ssb-Index-RSRP', the terminal reports the best SSBRI and the corresponding L1-RSRP to the base station.

[0083] And, if the terminal sets the CSI-RS resource in the same OFDM symbol(s) as the SSB (SS / PBCH Block) and 'QCL-TypeD' is applicable, the terminal can assume that the CSI-RS and SSB are quasi co-located from the 'QCL-TypeD' perspective.

[0084] Here, the QCL TypeD may mean that the antenna ports are QCL-connected from a spatial Rx parameter perspective. When a terminal receives multiple DL antenna ports in a QCL Type D relationship, the same reception beam may be applied. In addition, the terminal does not expect the CSI-RS to be configured in an RE that overlaps with the SSB RE.

[0085] < CSI-related actions >

[0086] In NR (New Radio) systems, CSI-RS (channel state information-reference signal) is used for time / frequency tracking, CSI computation, L1 (layer 1)-RSRP (reference signal received power) computation, and mobility. Here, CSI computation is related to CSI acquisition, and L1-RSRP computation is related to beam management (BM).

[0087] Figure 3 is a flowchart showing an example of a CSI-related procedure.

[0088] Referring to FIG. 3, in order to perform one of the purposes of CSI-RS, a terminal (e.g., user equipment, UE) receives configuration information related to CSI from a base station (e.g., general Node B, gNB) through RRC (radio resource control) signaling (S310).

[0089] The configuration information related to the above CSI may include at least one of CSI-IM (interference management) resource related information, CSI measurement configuration related information, CSI resource configuration related information, CSI-RS resource related information, or CSI report configuration related information.

[0090] CSI resource configuration related information can be expressed as CSI-ResourceConfig IE. The CSI resource configuration related information defines a group including at least one of a non-zero power (NZP) CSI-RS resource set, a CSI-IM resource set, or a CSI-SSB resource set. That is, the CSI resource configuration related information includes a CSI-RS resource set list, and the CSI-RS resource set list can include at least one of an NZP CSI-RS resource set list, a CSI-IM resource set list, or a CSI-SSB resource set list. A CSI-RS resource set is identified by a CSI-RS resource set ID, and one resource set includes at least one CSI-RS resource. Each CSI-RS resource is identified by a CSI-RS resource ID.

[0091] Information related to the CSI report configuration includes a reportConfigType parameter indicating a time domain behavior and a reportQuantity parameter indicating a CSI-related quantity to be reported. The time domain behavior may be periodic, aperiodic, or semi-persistent.

[0092] The above reportQuantity parameter may be related to at least one of a channel quality indicator (CQI), a precoding matrix indicator (PMI), a CSI-RS resource indicator (CRI), an SSB resource block indicator (SSBRI), a layer indicator (LI), a rank indicator (RI), and a layer 1-reference signal received strength (L1-Reference Signal Received Strength (RSRP).

[0093] Measurement resources may include configurations for downlink signals and / or downlink resources on which a terminal will perform measurements to determine feedback information. Measurement resources may be configured as ZP and / or NZP CSI-RS resource sets associated with CSI reporting configurations. The NZP CSI-RS resource set may include a CSI-RS set or an SSB set. For example, L1-RSRP may be measured for a CSI-RS set or an SSB set.

[0094] The terminal measures CSI based on configuration information related to the CSI (S320). The CSI measurement may include (1) a process of receiving a CSI-RS by the terminal (S321) and (2) a process of calculating CSI using the received CSI-RS (S322). The terminal reports the CSI to the base station (S330).

[0095] Resource setting

[0096] Each CSI resource setting 'CSI-ResourceConfig' contains a configuration for S≥1 CSI resource sets (given by the higher layer parameter csi-RS-ResourceSetList). A CSI resource setting corresponds to a CSI-RS-resourcesetlist, where S represents the number of configured CSI-RS resource sets. Wherein, the list of S≥1 CSI resource sets contains either or both of NZP CSI-RS resource set(s) and SS / PBCH block (SSB) set(s) used for L1-RSRP computation, or contains CSI-IM resource set(s).

[0097] One or more CSI resource settings for channel measurement (CM) and interference measurement (IM) are configured via higher layer signaling.

[0098] - CSI-IM resource for interference measurement.

[0099] - NZP CSI-RS resources for interference measurement.

[0100] - NZP CSI-RS resources for channel measurement.

[0101] That is, the CMR (channel measurement resource) can be NZP CSI-RS for CSI acquisition, and the IMR (Interference measurement resource) can be NZP CSI-RS for CSI-IM and IM.

[0102] Here, CSI-IM (or ZP CSI-RS for IM) is mainly used for inter-cell interference measurement.

[0103] And, NZP CSI-RS for IM is mainly used for intra-cell interference measurement from multi-user.

[0104] A UE may assume that the CSI-RS resource(s) configured for channel measurement for one CSI reporting and the CSI-IM / NZP CSI-RS resource(s) for interference measurement (when NZP CSI-RS resource(s) are used for interference measurement) are in a QCL relationship with respect to 'QCL-TypeD' per resource.

[0105] As we have seen, resource setting can mean a resource set list.

[0106] For aperiodic CSI, each trigger state set using the higher layer parameter CSI-AperiodicTriggerState is associated with one or more CSI-ReportConfigs, and each CSI-ReportConfig is linked to a periodic or semi-persistent or aperiodic resource setting.

[0107] One reporting setting can be linked to up to three resource settings.

[0108] < Description of Rel-17 / 18 Beam Management >

[0109] In Rel-17, both the DL TCI state and the UL TCI state can be indicated through DL DCI (e.g., DCI format 1-1 or 1-2), or only the UL TCI state can be indicated without indicating the DL TCI state. Accordingly, the methods used for configuring UL beam and power control (PC) in the existing Rel-15 / Rel-16 are replaced in Rel-17 with the above UL TCI state indication method. More specifically, in Rel-17, one UL TCI state can be indicated through the TCI field of DL DCI, and the UL TCI state is applied to all PUSCHs and all PUCCHs after a certain time called the beam application time, and can be applied to some or all of the indicated SRS resource sets. In addition, the base station can perform a terminal common beam update by using DCI and / or MAC-CE to perform indication / update for multiple specific DL / UL channel / RS combinations of terminals with one beam in common (using joint or separate TCI states). The target channels / RS of the common beam update include UE-dedicated CORESET, UE-dedicated reception on PDSCH for DL, DG / CG-PUSCH, all or a subset of dedicated PUCCH for UL, and additionally, AP CSI-RS for tracking / BM, SRS can be set as target channels / RS.In Rel-18, considering the M-TRP environment, standardization has been carried out on how multiple UL TCI states (and / or DL ​​TCI states) are indicated through the TCI field of DL DCI, and uplink / downlink resources to which multiple indicated TCIs are applied can be defined / configured depending on the S-DCI based M-TRP environment and the M-DCI based M-TRP environment.

[0110] AI / ML for Wireless Communication

[0111] With the advancement of computing technology, artificial intelligence (AI) and machine learning (ML) are being adopted in various industries and technical fields. In the field of wireless communications, various discussions are underway to apply AI models trained based on ML, and this is referred to as AI / ML in the 3GPP standardization process. Although this specification describes “AI / ML” according to the terminology used in the 3GPP standardization process, “AI / ML” may be referred to by various other terms depending on the progress and implementation of the standard in the future. For example, it may be referred to as “transmission / reception mode” or “signal / channel / operation / transmission / reception configuration” configured for AI / ML, but is not limited thereto. The meaning of the terms currently used in the 3GPP standardization process is briefly summarized as follows.

[0112] - AI / ML model: A data-driven algorithm that applies AI / ML technology to generate a set of outputs containing prediction information and / or decision parameters based on a set of inputs.

[0113] - Data collection: The process of collecting data required for AI / ML model training, data analysis, and inference from network nodes, management entities, or terminals.

[0114] - AI / ML Training: An online or offline process of training an AI model by learning features and patterns that best represent the data and obtain a trained AI / ML model for inference.

[0115] - Offline training: The process of training a model based on a previously collected data set, and the trained model is used or provided for future inference.

[0116] - Online training: This is a method in which the model is trained in real time when new training sample data is acquired and used for inference.

[0117] - AI / ML Inference: This is the process of making predictions or inducing decisions based on collected data and the AI ​​model using a trained AI model. Meanwhile, depending on whether the AI / ML model is set up on both the transmitting and receiving devices or only on one of them, it can be divided into (i) a two-sided model and (ii) a one-sided model. (i) In the case of the two-sided model, collaborative inference is performed through paired AI / ML models. Collaborative inference refers to cooperation between the network and the UE, in which one party performs part of the inference and the other party performs the rest of the inference. (ii) The one-sided model is divided into a UE-side model and a network-side model. In the one-sided model, inference is performed entirely by the UE / network-side model.

[0118] 1. Life Cycle Management (LCM) for AI / ML models

[0119] LCM for AI / ML models is a concept that encompasses all the overall procedures for AI / ML models, including data collection, model training, model deployment, model inference, model monitoring, and model updates.

[0120] LCM for AI / ML models can be broadly categorized into functionality-based LCM and model ID-based LCM. In functionality-based LCM, the network can instruct the activation / deactivation / fallback / switching of specific functions, even if the target AI / ML model may not be identified by the network. In model ID-based LCM, the network can instruct the activation / deactivation / selection / switching of AI / ML models identified by their AI / ML model ID.

[0121] Figure 4 is a diagram to explain overall functions from an AI / ML model perspective.

[0122] Referring to FIG. 4, a general AI / ML functional framework can be configured to include a data collection function (10), a model training function (20), a management function (30), an inference function (40), and a model storage function (50).

[0123] The Data Collection function (10) is a function that provides input data to the Model Training function (20), Management function (30), and Inference function (40). The Data Collection function (10) can perform data preparation and provide input data processed through data preparation.

[0124] Here, training data (11) refers to data required as input for the AI / ML Model Training function (20). Monitoring data (12) refers to data required as input for the Management (30) of the AI / ML model or AI / ML function. Inference data (13) refers to data required as input for the AI / ML Inference function (30).

[0125] The Model Training function (20) is a function that performs AI / ML model training, validation, and testing, and can generate model performance metrics that can be used as part of the AI / ML model testing procedure. If necessary, the Model Training function (20) can perform data preparation (e.g., data pre-processing and cleaning, forming, and transformation) based on the Training Data (11) transmitted from the Data Collection function (10).

[0126] Trained / Updated Model (21): If there is a Model Storage function (50), it is used to pass a trained, validated and tested AI / ML model to the Model Storage function (50) or to pass an updated version of the model to the Model Storage function (50).

[0127] The Management function (30) is a function that monitors the operation of the AI / ML model or AI / ML function. In addition, the Management function (30) may perform a decision to ensure appropriate inference operation based on data received from the Data Collection function (10) (i.e., Monitoring Data (12)) and / or data received from the Inference function (40) (i.e., Inference Output (41)).

[0128] Management Instruction (32) is information required as input to manage the Inference function (40). The relevant information may include selection / (de)activation / switching of an AI / ML model or AI / ML-based function, and may also include fallback to non-AI / ML operations (i.e., not relying on the inference process).

[0129] A Model Transfer / Delivery Request (33) can be used to request model(s) from Model Storage (50).

[0130] A Performance Feedback / Retraining Request (31) refers to information required as input to the Model Training function (20) (e.g., for the purpose of (re)training or updating the model).

[0131] The Inference function (40) is a function that provides output from the process of applying an AI / ML model or AI / ML function using data (i.e., Inference Data (13)) provided by Data Collection (10) as input. Data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) may also be performed based on the Inference Data (13) delivered by Data Collection (10). If necessary, the Inference function (40) may also perform data preparation (e.g., data preprocessing and cleaning, forming, and transformation) based on the Inference Data (13) provided by Data Collection function (10).

[0132] Inference Output (41) is data used in the Management function (30) to monitor the performance of an AI / ML model or AI / ML function. Inference Output (41) may include the inference output of the AI / ML model generated by the Inference function (30), and the details of the inference output may vary depending on the use case.

[0133] The Model Storage function (50) stores a learned / updated model that can be used to perform the Inference function (40). The Model Storage function (50) illustrated in FIG. 4 can be used as a reference point (if any) when applicable to protocol termination, model transmission / delivery, and related processes. Furthermore, the Model Storage function (50) is merely an example and is not intended to limit the storage location of actual AI / ML models, and may be omitted.

[0134] Model Transfer / Delivery (51) is used to transfer AI / ML models to inference functions.

[0135] 2. General AI / ML-related procedures between networks and terminals

[0136] Figure 5 illustrates the general form of AI / ML-related procedures performed between a network and a terminal. While Figure 4 examined LCM from an AI / ML model perspective, Figure 5 describes the general form of procedures performed from a signaling / protocol perspective between a terminal and the network.

[0137] (1) Setting procedures related to AI / ML

[0138] Referring to FIG. 5, an AI / ML-related configuration procedure may be performed between a network and a terminal (S510). The AI / ML-related configuration procedure may include information exchange between the terminal and the network via at least one upper-layer signaling, and / or preparatory / follow-up operations at the terminal / network, respectively, before / after the upper-layer signaling.

[0139] Specifically, the AI / ML-related configuration procedure may include, but is not limited to, at least one of (i) AI / ML-related terminal capability reporting, (ii) data collection, (iii) model training, (iv) model transfer / transfer, (v) AI / ML function / model selection, and (vi) configuration for various operations performed based on AI / ML models (e.g., AI / ML-based CSI / Positioning / Beam Management).

[0140] (i) A terminal can report to the network its capabilities, such as models / functionalities supported by the terminal in relation to AI / ML, through UE Capability Reporting. The network can provide AI / ML-related settings to the terminal based on the AI / ML-related capabilities reported by the terminal.

[0141] (ii) AI / ML-related configuration procedures may include data collection and / or provision of configuration information related to AI / ML model training / inference, etc. Configuration information related to data collection may relate to how to configure the method / action of data collection, etc.

[0142] (iii) AI / ML-related configuration procedures may include online or offline AI / ML model training and / or providing configuration information for AI / ML model training. Configuration information for AI / ML model training may relate to how to configure the method / operation of training the AI / ML model, etc.

[0143] (iv) The AI / ML-related configuration procedure may include transmitting / delivering configuration information for the model. The configuration information for the model may include parameters configuring the AI / ML model and / or an identifier (ID) for the AI / ML model.

[0144] The AI / ML model provided can be either a network-trained model or a model that requires self-training on the terminal. Even if a network-trained model is provided, the terminal can perform fine-tuning / retraining processes as needed. Meanwhile, if a network-trained model is provided, the terminal can provide training data to the network.

[0145] Meanwhile, AI / ML models can be categorized into Type A models, which can be identified without over-the-air (OTA) signaling, and Type B models, which are identified through OTA signaling. A model ID can be assigned during the model identification process, which can be further subdivided into terminal-initiated and network-initiated methods.

[0146] (v) The AI / ML-related configuration procedure may include a configuration of how to select an AI / ML Functionality / model and / or a selection process for the AI / ML Functionality / model. Selection of the UE part in a UE-side AI / ML model or a two-sided AI / ML model may be performed through instructions / signaling from the network or may be performed by the UE itself. Selection of the AI / ML Functionality / model may be performed when multiple AI / ML Functionality / models are configured / provided.

[0147] (vi) The AI / ML-related setup procedure may include setup information for various inference operations performed based on AI / ML models, for example, AI / ML-based CSI measurement / reporting, AI / ML-based Positioning, and / or AI / ML-based Beam Management.

[0148] (2) Actions based on inference from AI / ML models

[0149] Referring back to FIG. 5, the network and / or the terminal may perform inference of the AI / ML model through the trained AI / ML model, and perform various operations based on the inference of the AI / ML model (S520). If the AI / ML model is a one-sided model, the inference of the AI / ML model may be performed on either the network or the terminal where the AI / ML model is configured. If the AI / ML model is a two-sided model, each part of the inference of the AI / ML model may be performed on the network and the terminal, and such inference may be performed cooperatively between the network and the terminal depending on the implementation.

[0150] (i) Actions performed based on the inference of the AI / ML model may include AI / ML-based CSI measurement / reporting. The AI / ML-based CSI measurement / reporting may be for improving CSI feedback, and may be related to overhead reduction / CSI compression, accuracy improvement, and / or CSI prediction.

[0151] (ii) The actions performed based on the inference of the AI / ML model may include AI / ML-based beam management. The AI / ML-based beam management may be related to beam prediction in the time domain, reducing overhead / delay in the spatial domain, and / or improving beam selection accuracy.

[0152] (iii) Actions performed based on the inference of the AI / ML model may include AI / ML-based positioning. AI / ML-based positioning may be relevant to improving positioning accuracy in various scenarios, such as non-line-of-sight environments.

[0153] (3) Procedures for AI / ML management

[0154] The network and / or terminal can perform procedures for managing AI / ML Functionality / model or settings thereof (S530).

[0155] The network and / or terminal may perform monitoring of AI / ML Functionality / model during the process of AI / ML model inference or operation based thereon (B10) for management procedures (B15).

[0156] Management procedures may include, for example, at least one of activation / deactivation, switching, model update, and / or fallback operations for AI / ML Functionality / models. Signaling for management procedures may use various 3GPP signaling methods, such as RRC, MAC-CE, and DCI.

[0157] As an example of model switching, multiple model groups are formed, and switching between them, groups can be performed based on models having a common model structure or partially common sub-structures, and models within the same group can be related to different input / output formats or processing.

[0158] Model updating is the process of changing the parameters used by the model to adapt them to changing channel conditions over time, and fine-tuning is an example of model updating.

[0159] fallback: In a wireless communication system using an AI / ML model, when the reliability of the AI / ML model is reduced due to internal / external environmental factors, it can mean not using the AI / ML model or operating in a default operation mode that is set / defined in advance.

[0160] For example, the decision to perform a management procedure may be made by the network. For example, the network may decide to perform a management procedure upon network initiation, or upon terminal initiation and request.

[0161] As another example, the decision to perform a management procedure can be made by the terminal. For example, the terminal's decision to perform a management procedure can be triggered by the satisfaction of an event condition set by the network, by reporting the terminal's decision to the network, or by the terminal performing the decision autonomously.

[0162] 3. Specific examples of actions based on AI / ML model inference

[0163] beam management

[0164] Figure 6 illustrates an example of AI / ML-based beam management operations.

[0165] Referring to FIG. 6, the network / terminal may perform a configuration procedure related to AI / ML-based beam management (S610). The network / terminal may exchange configuration information for upper layer signaling for AI / ML-based beam management and perform a configuration procedure for an AI / ML model to be used for AI / ML-based beam management. For example, at least one of information related to model inference, configuration for the first set / second set of beams, monitoring performance, data collection, and assistance information for beam measurement may be signaled.

[0166] The network / terminal can perform measurements on the first set of beams (S620). The beam measurements may be related to RSRP measurements.

[0167] The network / terminal can obtain information about the second set of beams based on the measurement results for the first set of beams (S630). For example, the network / terminal can perform AI / ML inference using the measurement results for the first set of beams as AI / ML input data. Beam ID information may be additionally provided as AI / ML input data. The information about the second set of beams may correspond to AI / ML output data. The AI / ML output data may be related to prediction of future beam quality, such as, but not limited to, the probability that each beam will become a top-N beam and the predicted RSRP.

[0168] In some embodiments, the network / terminal may transmit and receive information about the acquired second set of beams.

[0169] Specifically, the AI / ML-based beam management operation may include at least one of the following BM-Case 1 and BM-Case 2.

[0170] - BM-Case 1: Prediction of the second set of DL beams in the spatial domain using the first set of beam measurements.

[0171] - BM-Case 2: Prediction of the second set of DL beams in the time domain using the first set of beam measurements.

[0172] In BM-Case 1 and / or 2, both AI / ML model training and inference can be performed in the network or at the terminal. The first set of beams and the second set of beams can be different beams. Alternatively, the first set of beams can be a subset of the second set of beams. Alternatively, particularly in BM-Case 2, the first set of beams and the second set of beams can be the same beams.

[0173] The report corresponding to the inference of the UE-side model for BM-Case 1 may relate to the predicted RSRP for the upper N beams. The report may include, for example, the predicted RSRP value, and for example, the predicted RSRP value may be reported together with the actually measured RSRP.

[0174] UE-side AI / ML model inference for BM-Case 2 can report inference results for N future time points in a single report. Each time point report can correspond to the report for BM-Case 1.

[0175] For performance monitoring of the UE-side model for BM-Case 1 / 2, (i) network side performance monitoring and / or (ii) UE-assisted performance monitoring may be supported. (i) For network side performance monitoring, the UE may report information necessary for the network to calculate performance metrics, for example, measurement results (e.g., RSRP) and / or RS index for a resource set for monitoring. (ii) For UE-assisted performance monitoring, the UE may also calculate performance metrics.

[0176] Regarding the NW-side model for BM-Case 1 / 2, quantization of reported RSRPs may be supported, e.g., differential RSRP reporting may be supported along with existing quantization steps and ranges. The reported content may include information about the RSRP and the corresponding upper N beams, where N may be configured by the network.

[0177] Regarding the configuration of the first set of beams and the second set of beams in the UE-side model of BM Case-1, two resource sets may be separately configured for each of the first set and the second set, and the corresponding resource sets may be provided through the CSI reporting configuration. The terminal may perform inference / measurement for the resource set of the first set of beams. The terminal may not be expected to perform measurement / inference for the resource set of the second set of beams. The beam information of the inference report may include resource set information for the first set.

[0178] In relation to the UE-side model, relevant IDs can be provided via the CSI framework. UEs can assume identical / similar characteristics for DL ​​transmission beams / sets (lists) with the same relevant ID.

[0179] Regarding UE-assisted performance monitoring for the UE-side models of BM-Case 1 and 2, the following methods can be considered.

[0180] i) Compare prediction results based on resources for monitoring and use the top 1 or top K beam prediction accuracy.

[0181] ii) Use RSRP difference information based on RSRP measurements of resources for monitoring and actual RSRP measurements for at least one of the top N predicted beams.

[0182] iii) Use the difference information between the measured RSRP and the predicted RSRP for the corresponding beam of the resources for monitoring.

[0183] iv) Probability information about the predicted beam being one of the top 1 or N beams.

[0184] Quantization of RSRP can be supported for reporting inference results for UE-side models, and differential RSRP with existing quantization steps can be supported. The scope of RSRP reporting is that differential RSRP can be supported among multiple beams in the case of BM-case 1, and differential RSRP can be supported among multiple beams at multiple viewpoints in the case of BM-case 2.

[0185] For BM-Case 2 of the UE-side model, the network can be configured to report inferences for N future time points to the terminal.

[0186] UE initiated BM related background

[0187] In existing LTE / NR systems, reporting of CSI / beam information is determined / controlled by the base station / network (except in the case of BFR). However, this NW (network)-initiated / triggered report has a limitation in that the terminal must be configured / instructed to send CSI / beam information frequently in environments where the wireless channel is likely to change rapidly / highly. In such environments, the UL resource overhead for CSI / beam reporting and the related DL measurement RS overhead increase, and the power consumption of the terminal also increases due to frequent uplink transmission. Furthermore, the UL resource overhead increases as the number of terminals within the cell / TRP coverage increases, as UL resources must be allocated to each terminal. To overcome the limitations of this NW-initiated / triggered report, the UE-initiated / triggered report method or event-based / triggered report method has recently emerged.

[0188] UE-initiated / triggered reporting or event-based / triggered reporting allows the UE to determine whether and when to report. For example, by performing reporting only when necessary (e.g., when a specific event occurs), UL resource overhead and UE power consumption are reduced. With this motivation, standardization of UE-initiated / triggered beam reporting is expected in NR Rel-19. Furthermore, in 6G communication systems, UE-initiated / triggered or event-based transmission methods may be more actively expanded and adopted to efficiently manage uplink resources.

[0189] In the NR system, there are two representative reporting methods for event-based or UE-initiated / triggered information: SR (scheduling request) and BFR (beam failure recovery). SR reports whether PUSCH allocation is necessary for UL-SCH transmission, and BFR reports whether BF occurs and new beam-related information. This information is conveyed / transmitted to the base station in an explicit or implicit manner (e.g., new beam index transmitted as PRACH resource selection information), and is conveyed at once or in parts through one or two UL resources (e.g., BFRQ (beam failure recovery request) transmitted through PUCCH + beam information transmitted through MAC-CE on PUSCH).

[0190] In this specification, information (e.g., SR, BFRQ, new beam information, etc.) transmitted to the network based on a terminal event and / or through a UE-initiated / triggered transmission method as described above may be conveniently expressed as 'event information'.

[0191] For example, event information may be composed of one or more information parts / blocks, and encoding / rate matching / RE mapping may be performed for each part / block.

[0192] For example, each information part / unit can be transmitted in a different transport method (e.g., in NR Release 16 and later, BFRQ is transmitted as an L1 message over UCI, and new beam information is transmitted as an L2 message over MAC-CE).

[0193] AI / ML beam management related background

[0194] In Release 18, for three use cases: CSI compression / prediction, beam management, and positioning, a study was conducted on performance analysis and potential specification impact through evaluation when network (NW) and / or user equipment (UE) side AI / ML models are operated. In particular, in the beam management use case, the sub-use cases were divided into BM-case1 and BM-case2, and performance analysis and potential specification impact were studied for spatial domain beam prediction and temporal domain beam prediction. BM-case1 and BM-case2 are summarized in Tables 2 to 4 below.

[0195] - AI / ML BM's WID goals

[0196]

[0197] - BM-case1: Spatial domain downlink beam prediction for beam set A based on measurement results for beam set B.

[0198]

[0199] - BM-case2: Temporal downlink beam prediction for beam set A based on past measurement results for beam set B.

[0200]

[0201] Additionally, an example of the operation for data collection of AI / ML models in the Beam management use case is shown in Table 5 below.

[0202]

[0203] Additionally, an example of the operation for inference of AI / ML model in Beam management use case is as shown in Table 6 below.

[0204]

[0205] As cited above, the Release 18 AI / ML study discussed NW / UE sided AI / ML operations that predict the best beam of Set A based on Set B measurements.

[0206] For UE-sided AI / ML, the terminal is required to measure Set B and report the predicted Set A beam. For NW-sided AI / ML, the terminal is required to report the Set B measurement.

[0207] In the latter (NW sided AI / ML), when the terminal performs Set B measurement / report, a standardization discussion is underway regarding what information (e.g., beam ID, RSRP, beam pattern ID, beam group ID, and bitmap information, etc.) to use to compose the beam-related information to be reported.

[0208] Table 7 below summarizes the standardization agreements reached to date.

[0209]

[0210] The first agreement above concerns the Set B beam report for the NW-sided AI / ML model. Further study points regarding content are described, as in the FFS on the report content for beam-related information. The relevant proposals are captured in Table 8 below.

[0211]

[0212] For reference, the content of the existing NR beam report is SSBRI / CRI + L1-RSRP / SINR, but in the above proposals, more than 4 beams are reported when reporting beam ID and / or L1-RSRP in the report content related to Set B, so in order to reduce reporting overhead, there was discussion about not reporting the beam ID at all or reporting bitmap information indicating the beam pattern ID or beam IDs to be reported instead of the beam ID. Specifically, you can refer to the contents of Table 9 below.

[0213]

[0214] Based on this background, this specification proposes a method for setting up beam measurement / reporting for base station-side AI / ML, and proposes a subsequent beam reporting operation for the terminal.

[0215] In this specification, ' / ' means 'and', 'or', or 'and / or' depending on the context.

[0216] In this specification, Set A, Set B, Set C, etc. may be defined as follows for convenience of explanation. However, 'Set A', 'Set B', and 'Set C' are only for distinguishing beams, and are not intended to limit the technical ideas of this specification to the terms.

[0217] Set A: The entire beam / beam pair set for beam prediction.

[0218] Set B: A set of beam / beam pairs corresponding to the information used as input to the AI / ML model.

[0219] Set C: beam / beam pair set where the terminal performs actual measurement

[0220] Problem to be solved 1

[0221] The UE can report i) Set A / B beam for NW sided AI / ML or ii) predicted Set A beam if Set B beam measurement / report is configured / indicated for UE-sided AI / ML. If an AI / ML related beam report (e.g., Set A / B beam report for NW sided AI / ML, predicted Set A beam report if Set B beam measurement / report is configured / indicated for UE-sided AI / ML, etc.) collides with another CSI report, one of them may be dropped or the two reports may be multiplexed on one side. In this case, defining the priority of the AI / ML related beam report may be required. Table 10 below shows the CSI priority information described in 3GPP TS 38.214.

[0222]

[0223] Priority formula in Table 10 above Referring to , the smaller the value of the priority formula, the higher the priority, and a total of four priority levels can be considered.

[0224] First, the priority can be determined based on the type of channel carrying the CSI. Specifically, AP (aperiodic) CSI reports carried on PUSCH ) > SP (semi-persistent) CSI reports carried on PUSCH( ) > SP CSI reports carried on PUCCH( ) > P(periodic) CSI report( carried on PUCCH ) has the highest priority.

[0225] Next, the priority can be determined based on the type of CSI being reported, and whether the CSI is beam reporting related CSI. Specifically, beam related CSI reports( ) > non-beam related CSI reports( ) have a higher priority in that order. At this time, i) the beam related CSI reports are CSI reports that carry L1-RSRP and / or L1-SINR, and ii) the non-beam related CSI reports represent CSI reports that do not carry L1-RSRP and / or L1-SINR.

[0226] Next, priority can be determined according to the serving cell index (c), and then priority can be determined in order of reportConfigID(s).

[0227] Proposal 1 proposes a method to solve problem 1 described above.

[0228] Proposal 1

[0229] i) Priority of the measurement report for Set A / B beams and / or ii) priority of the report for predicted Set A beam(s) (based on UE sided AI / ML output) according to Set B beam measurement results may be based on the embodiments below. The two different CSI reports (i) measured Set A / B beam related CSI and ii) predicted Set A beam related CSI) may be described as AI / ML based beam related CSI below.

[0230] In this specification, beam-related CSI may refer to existing beam-related CSI. As a specific example, the beam-related CSI may be a CSI report based on an existing legacy CSI report configuration, and may be CSI carrying L1-RSRP and L1-SINR.

[0231] In the present specification, i) the beam related CSI and ii) the AI / ML based beam related CSI may indicate CSI carrying L1-RSRP and / or L1-SINR, and iii) the non-beam related CSI may indicate CSI that does not carry L1-RSRP and / or L1-SINR.

[0232] - Example 1 of Proposal 1) beam related CSI = AI / ML based beam related CSI > non-beam related CSI

[0233] According to embodiment 1 of proposal 1, beam-related CSI and AI / ML-based beam-related CSI can have the same priority. In this case, i) beam-related CSI and ii) AI / ML-based beam-related CSI have higher priorities than non-beam-related CSI.

[0234] - Example 2 of Proposal 1) beam related CSI > AI / ML based related CSI > non-beam related CSI

[0235] According to embodiment 2 of proposal 1, AI / ML based beam related CSI can i) have a lower priority than beam related CSI, and ii) have a higher priority than non-beam related CSI.

[0236] - Example 3 of Proposal 1) AI / ML based beam-related CSI > beam-related CSI > non-beam-related CSI

[0237] According to embodiment 3 of proposal 1, AI / ML-based beam-related CSI may have a higher priority than beam-related CSI. In this case, the beam-related CSI may have a higher priority than non-beam-related CSI.

[0238] A case may be considered where the priorities of i) predicted Set A beam-related CSI and ii) measured Set A / B beam-related CSI included in the above AI / ML based beam-related CSI are different from each other.

[0239] - Embodiment 4 of Proposal 1) predicted Set A beam related CSI > beam related CSI = measured Set A / B beam related CSI > non-beam related CSI

[0240] According to Example 4 of Proposal 1, the priority of the measured Set A / B beam-related CSI may be the same as the priority of the existing beam-related CSI. In this case, the predicted Set A beam-related CSI may have a higher priority than the priority of the measured Set A / B beam-related CSI.

[0241] - Embodiment 5 of Proposal 1) measured Set A / B beam related CSI = beam related CSI > predicted Set A beam related CSI > non-beam related CSI

[0242] According to Example 5 of Proposal 1, the priority of the measured Set A / B beam-related CSI may be the same as the priority of the existing beam-related CSI. In this case, the priority of the measured Set A / B beam-related CSI may have a higher priority than the predicted Set A beam-related CSI.

[0243] - Example 6 of Proposal 1) Priority according to report config level

[0244] According to Example 6 of Proposal 1, priority based on report configuration level can be considered. A new CSI report configuration can be configured / defined for AI / ML-based beam-related CSI. At this time, there is a need to define a priority between AI / ML-based beam-related CSI based on the newly configured / defined report configuration and CSI based on the existing CSI report configuration.

[0245] For example, if AI / ML based beam related CSI conflicts with CSI reporting based on existing legacy CSI report config, it may have higher priority.

[0246] For example, if AI / ML based beam related CSI conflicts with CSI based on LTM (L1 / L2 Triggered Mobility)-CSI report config, it may have a lower priority.

[0247] For example, AI / ML based beam related CSI has a lower priority than ii) the priority of CSI reporting based on legacy CSI report config and ii) the priority of CSI reporting based on LTM-CSI report config.

[0248] The operation of the above proposal 1 can eliminate ambiguity when AI / ML-related beam reports and other CSI reports collide.

[0249] Problem to be solved 2

[0250] When the base station triggers an aperiodic CSI report, the Z and Z' values ​​are defined depending on what the reportQuantity of the corresponding CSI-reportConfig is.

[0251] Z is the computation time that must be guaranteed from the end of the last symbol of the PDCCH that triggers the CSI report(s) to the aperiodic CSI report of the terminal.

[0252] Z' is the computation time that must be guaranteed from the time end of the last symbol among all triggered sub-configurations when i) an aperiodic CSI-RS resource for channel measurements, ii) an aperiodic CSI-IM used for interference measurement, and iii) an aperiodic NZP CSI-RS for interference measurement for CSI-ReportConfig, or iv) when multiple sub-configurations are included in CSI-ReportConfig, to the aperiodic CSI report of the terminal.

[0253] At this time, for AI / ML related Set A / B beam reports, reports are performed for a large number of beams compared to the legacy beam report, and especially for the beam report for predicted Set A, a longer computation time may be required than the legacy beam report because it includes the amount of calculation for producing model output.

[0254] Additionally, in these cases, more CPU (CSI processing unit) occupancy rules for existing legacy beam reporting may be required.

[0255] In addition, when the reportQuantity related to the AI / ML based beam related CSI report is newly defined, the Z and Z' values ​​and / or the number of CPUs of the AI / ML based beam related CSI report need to be newly set and / or defined based on the newly defined reportQuantity.

[0256] A method to solve these problems is described in Proposal 2.

[0257] Proposal 2

[0258] Compared to legacy beam reporting, AI / ML-related methods that require more computational power may be considered, such as setting / defining i) Z and Z' of Set A / B beam reports and / or ii) Z and Z' values ​​of beam reports for predicted Set A.

[0259] Proposal 2-1) The beam report for Set A / B and / or predicted Set A may have Z and Z' values ​​set / defined to be larger than the Z and Z' values ​​of the existing RSRP-related CSI report.

[0260] At this time, the Z and Z' values ​​of the existing RSRP-related CSI report can be set / defined as shown in the table below.

[0261]

[0262] In Table 11 above, (Z3, Z3') represent the Z and Z' values ​​when reportQuantity is set to 'cri-RSRP', 'ssb-Index-RSRP', 'cri-RSRP- Index' or 'ssb-Index-RSRP- Index '.

[0263] (Z1, Z1') represent the values ​​of Z and Z' when i) the CSI to be transmitted corresponds to wideband frequency-granularity, and ii) reportQuantity is set to 'ssb-Index-SINR', 'cri-SINR', 'ssb-Index-SINR-Index', or 'cri-SINR-Index'.

[0264] For example, SINR-related CSI reports may require more computational effort than simply measuring RSRP values. Therefore, the Z and Z' values ​​corresponding to SINR-related CSI reports may be set / defined considering a longer computation time than simply measuring RSRP values.

[0265] As an example, a method may be considered in which the Z and Z' values ​​increase in proportion to i) the number of beams reported in the Set A / B beam report and / or ii) the number of beams reported in the beam report for the predicted Set A.

[0266] For example, the Z and Z' values ​​may increase in proportion to the number of measurement beams in Set A and / or the number of measurement beams in Set B.

[0267] For example, the Z and Z' values ​​can be set / defined as 'max(a*b*c, min_value)'. In this case, a represents a UE capability reporting scaling factor, b represents a value determined by the number of measurement beams (or number of reported beams) of Set A and / or the number of measurement beams (or number of reported beams) of Set B, c represents a default Z / Z' value (fixed Z / Z' value), and min_value can represent the minimum required time.

[0268] As another example, the values ​​Z and Z' can be calculated as 'min(a*b*c, max_value)', where max_value can represent the maximum time required. This ensures that the computation time for calculating Z and Z' does not take too long for the time interval considered.

[0269] For example, the c value or min_value can be set / defined as the Z and Z' values ​​utilized in non-AI / ML environments.

[0270] For example, if certain conditions (e.g., the number of beams being reported, the number of measurement beams in Set A, the number of measurement beams in Set B, etc. are less than a certain value) are met (and the occupied CPU / APU (AI processing unit) so far is small), the Z / Z' value can be set / defined to a very small value. This allows the terminal to perform very fast reporting.

[0271] In the above embodiments, the measurement report for the Set A / B beam and the beam report for the predicted Set A may have different Z and Z' values.

[0272] For example, i) the measurement report for Set A / B beams may have the same Z and Z' values ​​as the existing RSRP / SINR-related Z and Z' values, and ii) the beam report for predicted Set A may have larger Z and Z' values.

[0273] For example, in the above proposals, the Z' value related to AI / ML beam management can be utilized as the computation time that must be guaranteed from the CSI reference resource to the periodic / semi-persistent report when reporting the measurement report for Set A / B beams with periodic / semi-persistent properties and / or the beam report for the predicted Set A.

[0274] Through the above proposal 2-1, the terminal can secure sufficient computation time and fully perform AI / ML-related aperiodic beam reports.

[0275] Proposal 2-2) The beam report for Set A / B and / or the beam report for predicted Set A may occupy a large amount of CPU (e.g., a value greater than 1) compared to the existing RSRP / SINR-related CSI report.

[0276] At this time, the existing RSRP / SINR related CSI report is a CSI report with i) LTM-CSI-ReportConfig or ii) CSI-ReportConfig (and CSI-RS-ResourceSet with no trs-Info configured) where the upper layer parameter reportQuantity is set to 'cri-RSRP', 'ssb-Index-RSRP', 'cri-SINR', 'ssb-Index-SINR', 'cri-RSRP-Index', 'ssb-Index-RSRP-Index', 'cri-SINR-Index', 'ssb-Index-SINR-Index', or 'none', CPU occupancy value. This can be set to 1

[0277] For example, the Set A / B beam report may have the same CPU value as the existing RSRP / SINR related CSI report, and the beam report for the predicted Set A may occupy a CPU corresponding to a value greater than 1.

[0278] For example, different Z and Z' values ​​and / or CPU counts may be required depending on whether spatial domain DL Tx beam prediction or temporal DL Tx beam prediction is performed. As a specific example, the Z and Z' values ​​and / or CPU counts for temporal DL Tx beam prediction may be greater or less than the Z and Z' values ​​and / or CPU counts for spatial domain DL Tx beam prediction.

[0279] For example, the Z and Z' values ​​and / or the number of CPUs for temporal DL Tx beam prediction can be determined by adding or multiplying an offset value to the Z and Z' values ​​and / or the number of CPUs for spatial domain DL Tx beam prediction.

[0280] As another example, the number of Z and Z' and / or the number of CPUs for spatial domain DL Tx beam prediction can be determined by adding or multiplying an offset value to the Z and Z' values ​​and / or the number of CPUs for temporal DL Tx beam prediction.

[0281] For example, when reporting a beam report for Set A / B and / or a beam report for predicted Set A, a method may be considered in which the CPU value (number) increases in proportion to the number of beams reported.

[0282] For example, the CPU value may increase in proportion to the number of measurement beams in Set A and / or the number of measurement beams in Set B.

[0283] For example, the value of the CPU may be set / defined as 'max(a*b*c, min_value)'. In this case, a represents a UE capability reporting scaling factor, b represents a value determined by the number of measurement beams (or number of beams to be reported) of Set A and / or the number of measurement beams (or number of beams to be reported) of B, c represents a default CPU value (fixed CPU value), and min_value may represent a minimum CPU value.

[0284] As another example, the CPU value can be set / defined as 'min(a*b*c, max_value)', where max_value can represent the maximum CPU value. This can prevent the beam reports for Set A / B and / or the beam reports for the predicted Set A from occupying excessively large CPU values.

[0285] For example, c value or min_value can be set / defined as CPU values ​​utilized (related to RSRP / SINR) in non-AI / ML environments.

[0286] It may be considered that the beam report for Set A / B and / or the beam report for predicted Set A follow the existing CPU occupancy timeline. In this case, in the case of temporal DL Tx beam prediction operation, the terminal may i) perform measurement reports for Set A / B beams corresponding to multiple instances, or ii) perform reports for predicted (multiple instance) Set A based on Set B beam measurements corresponding to multiple instances.

[0287] As a specific example of a case where a terminal performs a measurement report for a Set A / B beam corresponding to multiple instances, the CPU occupancy timeline can be defined from the first symbol of the historical beam measurement CMR (Channel Measurement Resource) during Set A / B measurement to the time of reporting the Set A / B measurement report for historical multiple instances.

[0288] As a specific example where the terminal performs a report on the predicted (multiple instance) Set A based on the Set B beam measurement corresponding to multiple instances, the CPU occupancy timeline can be defined from the first symbol of the historical beam measurement CMR at the time of the Set B measurement to the time of reporting on the predicted (multiple instance) Set A based on the measurement.

[0289] The number of CPUs can be managed considering the increased computational load of AI / ML-related beam measurement / report through the above proposal 2-2.

[0290] An example of a terminal (or base station) operation based on at least one of the embodiments described above (e.g., at least one of the embodiments of Proposals 1 and 2) is as follows.

[0291] 1) The terminal (base station) can receive (transmit) settings related to beam measurement / reporting.

[0292] The above settings may include settings related to Set A and Set B of Proposal 1.

[0293] 2) The terminal (base station) can receive (transmit) a message scheduling the transmission of beam measurement reports.

[0294] The transmission of the above beam measurement report scheduled by the base station may have a time domain behavior of periodic / semi-persistent / dynamic.

[0295] 3) The terminal (base station) can transmit (receive) a beam measurement report based on the above message.

[0296] The content of the above report may be based on the embodiments of the above proposals 1 and 2.

[0297] The above terminal / base station operations are only an example, and each operation (or step) is not necessarily essential, and the beam measurement / reporting operations of the terminal according to the above-described embodiments may be omitted or added depending on the terminal / base station implementation method.

[0298] In terms of implementation, the operations of the base station / terminal according to the embodiments described above (e.g., beam measurement / reporting operations of the terminal based on at least one of the embodiments of proposals 1 and 2) can be processed by the device of FIG. 9 described below (e.g., processor (110, 210) of FIG. 9).

[0299] In addition, the operations of the base station / terminal according to the above-described embodiment (e.g., beam measurement / reporting operation of the terminal based on at least one of the embodiments of proposals 1 and 2) may be stored in a memory (e.g., 140, 240 of FIG. 9) in the form of a command / program (e.g., instruction, executable code) for driving at least one processor (e.g., 110, 210 of FIG. 9).

[0300] The embodiments described below are specifically described with reference to FIGS. 7 and 8 in terms of the operation of the terminal and base station. The methods described below are distinguished for convenience of explanation, and it is understood that some components of one method may be substituted for or combined with some components of another method.

[0301] FIG. 7 is a flowchart illustrating a method according to one embodiment of the present specification.

[0302] Referring to FIG. 7, a method according to one embodiment of the present specification includes a step of receiving configuration information related to channel state information (CSI) (S710) and a step of transmitting at least one CSI report based on a priority rule (S720).

[0303] In S710, the terminal receives configuration information related to channel state information (CSI) from the base station.

[0304] The above configuration information can be received based on upper level measurement signaling (e.g. RRC signaling).

[0305] Specifically, the configuration information may include information based on at least one of i) beam management, ii) CSI-related operations, iii) AI / ML, and / or iv) Proposals 1 and 2.

[0306] For example, the configuration information may include information related to a CSI report. A report quantity may be set based on the configuration information. The report quantity may be related to information reported by the terminal. For example, the report quantity may be set to indicate at least one of i) a Reference Signal (RS) index (e.g., SSB Resource Indicator (SSBRI) and / or CSI-RS Resource Indicator (CRI), ii) Reference Signal Received Power (RSRP), iii) a Signal to Interference and Noise Ratio (SINR), iv) a Channel Quality Indicator (CQI), and / or v) a Precoding Matrix Indicator (PMI).

[0307] In S720, the terminal may transmit at least one CSI report to the base station based on priority rule(s). When different types of CSI reports collide, the terminal may i) not transmit a CSI report and transmit another CSI report, or ii) multiplex the different types of CSI reports, based on the priority rule. As a specific example, the terminal may transmit a CSI report with a higher priority and drop a CSI report with a lower priority based on the collision of CSI reports with different priorities. The terminal may multiplex and transmit the multiple CSI reports based on the collision of multiple different CSI reports with the same priority.

[0308] For example, the CSI report may include information set to be reported based on the configuration information.

[0309] For example, the CSI report may include at least one of i) Reference Signal (RS) index (e.g., SSB Resource Indicator (SSBRI) and / or CSI-RS Resource Indicator (CRI), ii) Layer 1-Reference Signal Received Power (L1-RSRP), iii) Layer 1-Signal to Interference and Noise Ratio (L1-SINR), vi) Channel Quality Indicator (CQI), and / or v) Precoding Matrix Indicator (PMI).

[0310] The at least one CSI report comprises i) a CSI report including a measurement result related to beam prediction and / or ii) a CSI report including an inference result related to the beam prediction.

[0311] The above at least one CSI report may indicate an AI / ML based beam related CSI report. As a specific example, the UE may i) report Set A / B beams for NW sided AI / ML or ii) report predicted Set A beams when Set B beam measurement / report is configured / instructed for UE-sided AI / ML. In this case, i) Set A beams may indicate the entire beam (or beam pair set) for beam prediction, ii) Set B beams may indicate beams (or beam pair sets) corresponding to information used as inputs of an AI / ML model for beam prediction, and iii) predicted Set A beams may indicate beams (or beam pair sets) corresponding to outputs inferred / predicted by the AI / ML model among the Set A beams (or beam pair sets).

[0312] A CSI report including measurement results related to the above beam prediction may correspond to a CSI report reporting the Set A / B beam. For convenience of explanation in this specification, the CSI report including measurement results related to the above beam prediction may be expressed as a first CSI report.

[0313] Additionally, a CSI report including an inference result related to the beam prediction may correspond to a CSI report reporting the predicted Set A beam. For convenience of explanation in this specification, the CSI report including an inference result related to the beam prediction may be expressed as a second CSI report.

[0314] The at least one CSI report has a higher priority than a priority of a CSI report that does not carry Reference Signal Received Power (RSRP) and / or Signal-to-Interference Noise Ratio (SINR). The CSI report that does not carry the RSRP and / or SINR may correspond to a non-beam related CSI report, and for convenience of description in this specification, the non-beam related CSI report may be expressed as a third CSI report.

[0315] As a specific example, based on a collision between the at least one CSI report and the third CSI report, the terminal may transmit the at least one CSI report and not transmit the third CSI report.

[0316] According to one embodiment, the first CSI report and the second CSI report may have a higher priority than the priority of the existing beam-related CSI report. In this case, the existing beam-related CSI report is a CSI report that carries RSRP and / or SINR and represents a CSI report that is not related to beam prediction. For the convenience of explanation in this specification, 'different from the inference of the AI / ML model' may be expressed as 'existing', and the existing beam-related CSI report may be expressed as the fourth CSI report.

[0317] As a specific example, based on a collision between the first CSI report and / or the second CSI report and the fourth CSI report, the terminal may transmit the first CSI report and / or the second CSI report and not transmit the fourth CSI report. This embodiment may be based on embodiment 3 of proposal 1.

[0318] According to one embodiment, the first CSI report and the second CSI report may have the same priority as the priority of the fourth CSI report.

[0319] As a specific example, based on the collision of the first CSI report and / or the second CSI report and the fourth CSI report, the terminal may i) transmit the first CSI report and / or the second CSI report and the fourth CSI report together, or ii) multiplex and transmit the first CSI report and / or the second CSI report and the fourth CSI report. This embodiment may be based on Embodiment 1 of Proposal 1.

[0320] According to one embodiment, the first CSI report and the second CSI report may have a lower priority than the priority of the fourth CSI report.

[0321] As a specific example, based on a collision between the first CSI report and / or the second CSI report and the fourth CSI report, the terminal may transmit the first CSI report and / or the second CSI report and not transmit the fourth CSI report. This embodiment may be based on Embodiment 2 of Proposal 1.

[0322] For example, the measurement result may include RSRP and / or SINR, and the inference result may include predicted RSRP and / or predicted SINR.

[0323] For example, the inference result may be an output of a model based on the measurement result.

[0324] A method in which the priority of the first CSI report and the priority of the second CSI report are set and / or defined differently may be considered.

[0325] In one embodiment, the first CSI report has a higher priority than the priority of the second CSI report. As a specific example, i) the first CSI report may have the same priority as the priority of the fourth CSI report, and ii) the first CSI report and the fourth CSI report may have a higher priority than the priority of the second CSI report.

[0326] For a more specific example, based on the collision between the first CSI report and the second CSI report, the terminal may transmit the first CSI report and not transmit the second CSI report. This embodiment may be based on embodiment 5 of proposal 1.

[0327] In one embodiment, the second CSI report may have a higher priority than the priority of the first CSI report. As a specific example, i) the first CSI report may have the same priority as the priority of the fourth CSI report, and ii) the second CSI report may have a higher priority than the priority of the first CSI report and the priority of the fourth CSI report.

[0328] For a more specific example, based on the collision between the second CSI report and the first CSI report, the terminal may transmit the second CSI report and not transmit the first CSI report. This embodiment may be based on embodiment 4 of proposal 1.

[0329] When a CSI-ReportConfig related to at least one CSI report is newly defined, a priority rule needs to be defined in case a conflict occurs between the at least one CSI report based on the newly defined CSI-ReportConfig and the CSI report based on the existing CSI-ReportConfig.

[0330] According to one embodiment, a CSI report based on a CSI reporting configuration related to LTM (L1 / L2 Triggered Mobility) may have a higher priority than the priorities of at least one CSI report. In other words, the CSI report based on the CSI reporting configuration related to the LTM may have a higher priority than the priorities of the first CSI report and the second CSI report. As a specific example, the reporting configuration related to the LTM may be LTM-CSI-ReportConfig.

[0331] As a more specific example, based on a collision between i) the first CSI report and / or the second CSI report and ii) a CSI report based on a CSI report setting related to the LTM, the terminal may transmit the CSI report based on the CSI report setting related to the LTM and may not transmit the first CSI report and / or the second CSI report.

[0332] As a specific example, the first CSI report and / or the second CSI report may have a higher priority than the priority of a CSI report based on an existing legacy CSI report config.

[0333] As a more specific example, based on a collision between the first CSI report and / or the second CSI report and a CSI report based on the existing legacy CSI report config, the terminal may transmit the first CSI report and / or the second CSI report and not transmit the CSI report based on the existing legacy CSI report config.

[0334] As another example, the first CSI report and / or the second CSI report may have a lower priority than i) a CSI report based on a CSI report configuration associated with the LTM and ii) a CSI report based on the existing legacy CSI report config.

[0335] As a more specific example, based on a collision between i) the first CSI report and / or the second CSI report and ii) the CSI report based on the CSI report configuration related to the LTM and / or the CSI report based on the existing legacy CSI report config, the terminal may transmit the CSI report based on the CSI report configuration related to the LTM and / or the CSI report based on the existing legacy CSI report config, and may not transmit the first CSI report and / or the second CSI report. This embodiment may be based on Embodiment 6 of Proposal 1.

[0336] Through the operation of the above proposal 1, when i) the AI / ML based beam related CSI report and ii) another type of CSI report collide, the terminal can eliminate ambiguity in transmission of the AI / ML based beam related CSI report by transmitting the CSI report based on the set / defined priority rule.

[0337] The AI / ML based beam related CSI report transmits reports for a larger number of beams compared to the existing beam related CSI report (the fourth CSI report). In particular, the CSI report reporting the predicted Set A beam (the second CSI report) includes a larger amount of computation for outputting the AI / ML model. Accordingly, i) the AI / ML based beam related CSI report may require a longer computation time than the computation time of the fourth CSI report, and ii) the AI / ML based beam related CSI report may require more CPUs compared to the CPU (CSI Processing Unit) occupancy rule of the fourth CSI report.

[0338] To solve such a problem, i) a method for setting / defining the computation time of the first CSI report and / or the second CSI report and / or ii) a method for setting / defining the number of CPUs occupied by the first CSI report and / or the second CSI report may be considered.

[0339] In addition, when the reportQuantity related to the AI / ML based beam related CSI report is newly defined, it may be considered that the Z and Z' values ​​and / or the number of CPUs of the AI / ML based beam related CSI report are newly set and / or defined based on the newly defined reportQuantity.

[0340] According to one embodiment, the at least one CSI report may be transmitted based on a number of symbols (a first number of symbols) associated with a CSI computation time.

[0341] For example, the first symbol count may be greater than the symbol count (second symbol count) defined for the report quantity related to RSRP. In this case, the report quantity related to RSRP may represent a report quantity related to measurement of an existing RSRP. In other words, in the report quantity related to RSRP (e.g., 'cri-RSRP', 'ssb-Index-RSRP', 'cri-RSRP- Index', or 'ssb-Index-RSRP- Index'), 'RSRP' may represent an existing RSRP different from an RSRP related to inference of an AI / ML model (e.g., measured RSRP and / or predicted RSRP).

[0342] As a specific example, the second symbol count may represent Z and Z' values ​​defined for the reporting quantity associated with the RSRP.

[0343] As a more specific example, the number of second symbols is Z3 and Z -3 ' values ​​can be represented. At this time, the Z3 and Z3' values ​​can represent the Z and Z' values ​​when reportQuantity is set to 'cri-RSRP', 'ssb-Index-RSRP', 'cri-RSRP- Index' or 'ssb-Index-RSRP- Index '.

[0344] When a base station triggers an aperiodic CSI report, the Z and Z' values ​​can be defined depending on what the reportQuantity of the corresponding CSI-reportConfig is.

[0345] For example, Z may represent the computation time that must be guaranteed from the end of the last symbol of the PDCCH that triggers the CSI report(s) to the aperiodic CSI report of the terminal.

[0346] For example, Z' may represent a computation time that must be guaranteed from the temporal end point of the last symbol among all triggered sub-configurations when i) an aperiodic CSI-RS resource for channel measurements, ii) an aperiodic CSI-IM used for interference measurement, and iii) an aperiodic NZP CSI-RS for interference measurement for CSI-ReportConfig, or iv) when multiple sub-configurations are included in CSI-ReportConfig, to the aperiodic CSI report of the terminal. In this case, the computation time may be expressed as the number of symbols.

[0347] For example, the first symbol count may be Z and Z' values ​​associated with the first CSI report and / or the second CSI report.

[0348] As a specific example, the Z and Z' values ​​associated with the first CSI report and / or the second CSI report may be set / defined to be greater than the Z and Z' values ​​defined for the report quantity associated with the RSRP.

[0349] As a more specific example, the Z and Z' values ​​associated with the first CSI report and / or the second CSI report may be set / defined to be greater than the Z3 and Z3' values.

[0350] The Z and Z' values ​​may be considered when the first CSI report and / or the second CSI report includes information related to SINR. When a CSI report includes information related to SINR, a greater amount of computation may be required than a CSI report that simply includes information related to RSRP. This embodiment may be based on Proposal 2-1.

[0351] According to one embodiment, the at least one CSI report may be transmitted based on a number of symbols (a third number of symbols).

[0352] For example, the number of third symbols may be greater than the number of symbols (the number of fourth symbols) defined for the reporting quantity related to SINR. In this case, the reporting quantity related to SINR may represent the reporting quantity related to the measurement of existing SINR. In other words, in the reporting quantity related to SINR (e.g., 'cri-SINR', 'ssb-Index-SINR', 'cri-SINR- Index', or 'ssb-Index-SINR- Index'), 'SINR' may represent an existing SINR that is different from the SINR related to the inference of the AI / ML model (e.g., measured SINR and / or predicted SINR).

[0353] As a specific example, the fourth symbol number may represent Z and Z' values ​​defined for the reporting quantity related to the SINR.

[0354] As a more specific example, the fourth symbol number may represent the values ​​Z1 and Z1'. In this case, the values ​​Z1 and Z1' may represent the values ​​Z and Z' when i) the CSI to be transmitted corresponds to a wideband frequency-granularity, and ii) reportQuantity is set to 'ssb-Index-SINR', 'cri-SINR', 'ssb-Index-SINR- Index', or 'cri-SINR- Index'.

[0355] For example, the third symbol number may be Z and Z' values ​​associated with the first CSI report and / or the second CSI report.

[0356] As a specific example, the Z and Z' values ​​associated with the first CSI report and / or the second CSI report may be set and / or defined to be greater than the Z and Z' values ​​defined for the reporting quantity associated with the SINR.

[0357] As a more specific example, the Z and Z' values ​​associated with the first CSI report and / or the second CSI report may be set and / or defined to be greater than the Z1 and Z1' values. The present embodiment may be based on Proposal 2-1.

[0358] According to one embodiment, the number of first symbols may be set and / or defined differently based on whether it is spatial domain DL Tx beam prediction or temporal domain DL Tx beam prediction.

[0359] For example, the number of first symbols associated with temporal DL Tx beam prediction may be greater than or less than the number of first symbols associated with spatial domain DL Tx beam prediction.

[0360] For example, the number of first symbols associated with temporal DL Tx beam prediction may be determined by adding or multiplying an offset value to the number of first symbols associated with spatial domain DL Tx beam prediction.

[0361] As another example, the number of first symbols associated with spatial domain DL Tx beam prediction can be determined by adding or multiplying an offset value to the number of first symbols associated with temporal DL Tx beam prediction.

[0362] According to one embodiment, the number of first symbols may be determined based on the number of beams included in the at least one CSI report.

[0363] For example, the Z and Z' values ​​associated with the first CSI report and / or the second CSI report may be determined (increased or decreased) in proportion to the number of beams reported in the first CSI report and / or the number of beams reported in the second CSI report.

[0364] For example, the Z and Z' values ​​associated with the first CSI report and / or the second CSI report may be determined (increased or decreased) in proportion to the number of measurement beams of Set A and / or the number of measurement beams of Set B. This embodiment may be based on Proposal 2-1.

[0365] According to one embodiment, the number of first symbols may be set and / or defined based on UE capability.

[0366] For example, the Z and Z' values ​​related to the first CSI report and / or the second CSI report may be set / defined as 'max(a*b*c, min_value)'. In this case, a represents a UE capability reporting scaling factor, b represents a value determined by the number of measurement beams (or the number of beams to be reported) of Set A and / or the number of measurement beams (or the number of beams to be reported) of Set B, c represents a default Z / Z' value (a fixed Z / Z' value), and min_value may represent a minimum required time.

[0367] For example, the c value or min_value may be set / defined as the number of the second symbols. As a specific example, the c value or min_value may be set / defined as the Z and Z' values ​​associated with a CSI report associated with an existing RSRP.

[0368] As another example, the Z and Z' values ​​associated with the first CSI report and / or the second CSI report may be calculated as 'min(a*b*c, max_value)'. In this case, max_value may represent the maximum required time. Through this, the Z and Z' values ​​associated with the first CSI report and / or the second CSI report may be prevented from being determined to be too large. This embodiment may be based on Proposal 2-1.

[0369] According to one embodiment, the Z and Z' values ​​associated with the first CSI report and / or the second CSI report may be set / defined to be very small values ​​based on satisfying certain conditions (e.g., when the number of reporting beams, the number of measurement beams of Set A, the number of measurement beams of Set B, etc. are less than or equal to certain values).

[0370] For example, based on i) the number of beams being reported, the number of measurement beams in Set A, the number of measurement beams in Set B, etc. being below a certain value, and ii) the occupied CPU / APU (AI processing unit) being small, the Z and Z' values ​​associated with the first CSI report and / or the second CSI report can be set / defined to very small values. This allows the terminal to quickly transmit the CSI report when a certain condition is satisfied. This embodiment can be based on Proposal 2-1.

[0371] In one embodiment, the first CSI report and the second CSI report may have different Z and Z' values.

[0372] For example, i) the first CSI report may have values ​​equal to the existing RSRP / SINR-related Z and Z' values, and ii) the second CSI report may have values ​​Z and Z' greater than the existing RSRP / SINR-related Z and Z' values. This embodiment may be based on Proposal 2-1.

[0373] According to one embodiment, in the embodiments based on the proposal 2-1, the Z' value associated with the first CSI report and / or the second CSI report may be used as a computation time that must be guaranteed from the CSI reference resource to the periodic / semi-persistent report when generating a measurement report for a Set A / B beam of periodic / semi-persistent property and / or a beam report for a predicted Set A.

[0374] As a specific example, the Z' value associated with the first CSI report may be used as the computation time that must be guaranteed from the CSI reference resource to the periodic / semi-persistent report when reporting the measurement for the Set A / B beam of the periodic / semi-persistent attribute.

[0375] As a specific example, the Z' value associated with the second CSI report may be used as the computation time that must be guaranteed from the CSI reference resource to the periodic / semi-persistent report when reporting a beam for the predicted Set A of periodic / semi-persistent properties.

[0376] Through the above proposal 2-1, the terminal can secure sufficient computation time and then fully perform the AI / ML related aperiodic beam report (the first CSI report and / or the second CSI report).

[0377] According to one embodiment, the number of CSI processing units (CPUs) associated with one of the at least one CSI report (the number of first CPUs) may be greater than the number of CPUs associated with a CSI report for RSRP or SINR (the number of second CPUs). In this case, the CSI report for RSRP or SINR may represent the fourth CSI report for the existing RSRP or SINR.

[0378] For example, the number of the second CPUs may represent the CPU occupancy value occupied in the fourth CSI report.

[0379] As a concrete example, the CSI report related to the existing RSRP / SINR (the 4th CSI report) may have the CPU occupancy value O_CPU set to 1 if i) the CSI report has LTM-CSI-ReportConfig or ii) the CSI report has CSI-ReportConfig (and CSI-RS-ResourceSet with no trs-Info configured) in which the upper layer parameter reportQuantity is set to 'cri-RSRP', 'ssb-Index-RSRP', 'cri-SINR', 'ssb-Index-SINR', 'cri-RSRP-Index', 'ssb-Index-RSRP-Index', 'cri-SINR-Index', 'ssb-Index-SINR-Index', or 'none'.

[0380] For example, the number of the first CPUs may be a value exceeding 1.

[0381] As another example, i) the number of CPUs associated with the first CSI report may be equal to the number of second CPUs, and ii) the number of CPUs associated with the second CSI report may be greater than the number of second CPUs. This embodiment may be based on Proposal 2-2.

[0382] According to one embodiment, the number of the first CPUs may be set and / or defined differently based on whether spatial domain DL Tx beam prediction or temporal domain DL Tx beam prediction is performed.

[0383] For example, the number of first CPUs associated with temporal DL Tx beam prediction may be greater than or less than the number of first CPUs associated with spatial domain DL Tx beam prediction.

[0384] For example, the number of first CPUs related to temporal DL Tx beam prediction can be determined by adding or multiplying an offset value to the number of first CPUs related to spatial domain DL Tx beam prediction.

[0385] As another example, the number of first CPUs associated with spatial domain DL Tx beam prediction may be determined by adding or multiplying an offset value to the number of first CPUs associated with temporal DL Tx beam prediction. This embodiment may be based on Proposal 2-2.

[0386] According to one embodiment, the number of the first CPUs may be determined based on the number of beams included in the at least one CSI report.

[0387] For example, the number of the first CPUs may be determined (increased or decreased) in proportion to i) the number of beams reported in the first CSI report and / or ii) the number of beams reported in the second CSI report.

[0388] For example, the number of the first CPUs can be determined (increased or decreased) in proportion to i) the number of measurement beams of Set A and / or ii) the number of measurement beams of Set B.

[0389] According to one embodiment, the number of the first CPUs can be set and / or defined based on the performance of the terminal.

[0390] For example, the number of the first CPUs may be set and / or defined as 'max(a*b*c, min_value)'. In this case, a represents a UE capability reporting scaling factor, b represents a value determined by the number of measurement beams (or number of reported beams) of Set A and / or the number of measurement beams (or number of reported beams) of B, c represents a default CPU value (fixed CPU value), and min_value may represent a minimum CPU value.

[0391] As another example, the number of the first CPUs can be set / defined as 'min(a*b*c, max_value)'. In this case, max_value can represent the maximum CPU value. This can prevent too many CPUs from being occupied when the terminal transmits the first CSI report and / or the second CSI report.

[0392] For example, the c value or min_value may be set / defined as the number of the second CPUs. As a specific example, the c value or min_value may be set / defined as the number of CPUs used for the CSI report (the fourth CSI report) related to the existing RSRP and / or SINR. This embodiment may be based on Proposal 2-2.

[0393] According to one embodiment, the first CPUs may be occupied from the time of starting measurement for the at least one CSI report until the time of transmitting the at least one CSI report.

[0394] It may be considered that the terminal follows the existing CPU occupancy timeline when transmitting the first CSI report and / or the second CSI report. In this case, in the case of a temporal DL Tx beam prediction operation, the terminal may i) perform the first CSI report corresponding to multiple instances, or ii) perform the second CSI report corresponding to multiple instances based on Set B beam measurements corresponding to multiple instances.

[0395] As a specific example, when the terminal transmits the first CSI report corresponding to multiple instances, the CPUs of the first CSI report may be occupied from the time point at which beam measurement for the first CSI report starts until the time point at which the first CSI report is transmitted. In other words, when the terminal transmits the first CSI report corresponding to multiple instances, the CPU occupancy timeline of the first CSI report may be defined as from the first symbol of a past beam measurement CMR (Channel Measurement Resource) during Set A / B measurement until the time point at which a Set A / B measurement report for past multiple instances is reported.

[0396] As a specific example, when the terminal transmits the second CSI report corresponding to multiple instances, the CPUs of the second CSI report may be occupied from the time point at which beam measurement for the second CSI report starts until the time point at which the second CSI report is transmitted. In other words, when the terminal performs a report for the predicted Set A corresponding to multiple instances based on beam measurements of Set B corresponding to multiple instances, the CPU occupancy timeline of the second CSI report may be defined from the first symbol of a past beam measurement CMR at the time of Set B measurement until the time point at which a report for the predicted Set A corresponding to multiple instances is transmitted based on the measurements. This embodiment may be based on Proposal 2-2.

[0397] Through embodiments according to the above proposal 2-2, the increased amount of computation can be considered in managing the number of CPUs for AI / ML-related beam measurement / reporting.

[0398] In one embodiment, the first CSI report may be related to an input of the first model, and the second CSI report may be related to an output of the second model.

[0399] For example, the first model may be a network-sided model, and the second model may be a user equipment-sided model.

[0400] The operations based on S710 to S720 described above can be implemented by the device of FIG. 9. For example, referring to FIG. 9, the terminal (200) can control one or more transceivers (230) and / or one or more memories (240) to perform operations based on S710 to S720.

[0401] The embodiments described below are specifically described in terms of base station operation.

[0402] S810 to S820 described below correspond to S710 to S720 described in FIG. 7. Considering the above correspondence, redundant descriptions are omitted. The specific descriptions of base station operations described below may be replaced by the corresponding descriptions / exemplifications of FIG. 7.

[0403] FIG. 8 is a flowchart illustrating a method according to another embodiment of the present specification.

[0404] Referring to FIG. 8, a method according to another embodiment of the present specification includes a step of transmitting configuration information related to channel state information (CSI) (S810) and a step of receiving at least one CSI report based on a priority rule (S820).

[0405] In S810, the base station transmits configuration information related to CSI to the terminal.

[0406] In S820, the base station receives at least one CSI report from the terminal based on a priority rule.

[0407] The at least one CSI report comprises i) a first CSI report including measurement results related to beam prediction and / or ii) a second CSI report including inference results related to the beam prediction.

[0408] The at least one CSI report has a higher priority than a priority of a third CSI report that does not carry Reference Signal Received Power (RSRP) and / or Signal-to-Interference Noise Ratio (SINR).

[0409] The operations based on S810 to S820 described above can be implemented by the device of FIG. 9. For example, referring to FIG. 9, the base station (100) can control one or more transceivers (130) and / or one or more memories (140) to perform the operations based on S810 to S820.

[0410] The operations / terms based on the embodiments described above have been described assuming a 5G system. However, this is for convenience of explanation and is not intended to limit the scope of application of the technical problems and problem-solving means to be solved by this specification to a specific system. The technical problems / technical issues / problems mentioned in this specification may equally exist in other systems (e.g., 6G systems). It is self-evident that the embodiments of this specification can be expanded and applied to solve problems equally existing in the other systems. Therefore, for the expanded application of the embodiments of this specification to other systems, the terms defined / described based on the 5G system may be replaced / changed with terms defined in the other systems (or generalized terms not specific to one system). For example, PRACH, PUSCH, PUCCH, or SRS may be replaced / changed with uplink signals (or uplink channels). For example, SSB, CSI-RS, PDSCH, and PDCCH may be replaced / changed with downlink signals (or downlink channels).

[0411] Hereinafter, a device to which an embodiment of the present specification can be applied (a device that implements a method / operation according to an embodiment of the present specification) is described with reference to FIG. 9.

[0412] FIG. 9 is a drawing showing the configuration of a first device and a second device according to an embodiment of the present specification.

[0413] The first device (100) may include a processor (110), an antenna unit (120), a transceiver (130), and a memory (140).

[0414] The processor (110) performs baseband-related signal processing and may include a higher layer processing unit (111) and a physical layer processing unit (115). The higher layer processing unit (111) may process operations of a MAC layer, an RRC layer, or higher layers. The physical layer processing unit (115) may process operations of a PHY layer. For example, when the first device (100) is a base station device in base station-terminal communication, the physical layer processing unit (115) may perform uplink reception signal processing, downlink transmission signal processing, etc. For example, when the first device (100) is a first terminal device in terminal-to-terminal communication, the physical layer processing unit (115) may perform downlink reception signal processing, uplink transmission signal processing, sidelink transmission signal processing, etc. In addition to performing baseband-related signal processing, the processor (110) may also control the overall operation of the first device (100).

[0415] The antenna unit (120) may include one or more physical antennas, and when it includes multiple antennas, it may support MIMO transmission and reception. The transceiver (130) may include an RF (Radio Frequency) transmitter and an RF receiver. The memory (140) may store information processed by the processor (110), and software, an operating system, applications, etc. related to the operation of the first device (100), and may also include components such as a buffer.

[0416] The processor (110) of the first device (100) may be configured to implement the operation of the base station in the base station-to-terminal communication (or the operation of the first terminal device in the terminal-to-terminal communication) in the embodiments described in the present disclosure.

[0417] The second device (200) may include a processor (210), an antenna unit (220), a transceiver (230), and a memory (240).

[0418] The processor (210) performs baseband-related signal processing and may include a higher layer processing unit (211) and a physical layer processing unit (215). The higher layer processing unit (211) may process operations of a MAC layer, an RRC layer, or higher layers. The physical layer processing unit (215) may process operations of a PHY layer. For example, when the second device (200) is a terminal device in base station-terminal communication, the physical layer processing unit (215) may perform downlink reception signal processing, uplink transmission signal processing, etc. For example, when the second device (200) is a second terminal device in terminal-to-terminal communication, the physical layer processing unit (215) may perform downlink reception signal processing, uplink transmission signal processing, sidelink reception signal processing, etc. In addition to performing baseband-related signal processing, the processor (210) may also control the overall operation of the second device (210).

[0419] The antenna unit (220) may include one or more physical antennas, and when it includes multiple antennas, it may support MIMO transmission and reception. The transceiver (230) may include an RF transmitter and an RF receiver. The memory (240) may store information processed by the processor (210), software, an operating system, applications, etc. related to the operation of the second device (200), and may also include components such as a buffer.

[0420] The processor (210) of the second device (200) may be configured to implement operations of the terminal in base station-to-terminal communication (or operations of the second terminal device in terminal-to-terminal communication) in the embodiments described in the present disclosure.

[0421] In the operation of the first device (100) and the second device (200), the same explanations given for the base station and the terminal (or the first terminal and the second terminal in the terminal-to-terminal communication) in the examples of the present disclosure may be applied, and redundant explanations are omitted.

[0422] Here, the wireless communication technology implemented in the device of the present disclosure may include LTE, NR, and 6G, as well as Narrowband Internet of Things (NB-IoT) for low-power communication. For example, NB-IoT technology may be an example of LPWAN (Low Power Wide Area Network) technology and may be implemented in standards such as LTE Cat NB1 and / or LTE Cat NB2, and is not limited to the above-described names.

[0423] Additionally or alternatively, the wireless communication technology implemented in the device of the present disclosure may perform communication based on LTE-M technology. For example, LTE-M technology may be an example of LPWAN technology and may be called by various names such as eMTC (enhanced Machine Type Communication). For example, LTE-M technology may be implemented by at least one of various standards such as 1) LTE CAT 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-Bandwidth Limited), 5) LTE-MTC, 6) LTE Machine Type Communication, and / or 7) LTE M, and is not limited to the above-described names.

[0424] Additionally or alternatively, the wireless communication technology implemented in the device of the present disclosure may include at least one of ZigBee, Bluetooth, and Low Power Wide Area Network (LPWAN), which take low-power communication into account, and is not limited to the above-described names. For example, ZigBee technology can create personal area networks (PANs) related to small / low-power digital communication based on various standards such as IEEE 802.15.4, and may be called by various names.

Claims

1. In the method, A step of receiving configuration information related to channel state information (CSI); and A step of transmitting at least one CSI report based on a priority rule; wherein said at least one CSI report comprises i) a first CSI report including measurement results related to beam prediction and / or ii) a second CSI report including inference results related to said beam prediction, A method, characterized in that the at least one CSI report has a higher priority than a priority of a third CSI report that does not carry Reference Signal Received Power (RSRP) and / or Signal-to-Interference Noise Ratio (SINR).

2. In paragraph 1, The above measurement results include RSRP and / or SINR, A method, characterized in that the above inference result includes a predicted RSRP and / or a predicted SINR.

3. In paragraph 1, A method characterized in that the above inference result is an output of a model based on the above measurement result.

4. In paragraph 1, A method, characterized in that the first CSI report has a higher priority than the second CSI report.

5. In paragraph 1, A method, characterized in that the second CSI report has a higher priority than the first CSI report.

6. In paragraph 5, A method, characterized in that a CSI report based on a CSI report setting related to LTM (L1 / L2 Triggered Mobility) has a higher priority than the priority of at least one CSI report.

7. In paragraph 1, The at least one CSI report is transmitted based on a first symbol number associated with a CSI computation time, A method, characterized in that the number of first symbols is greater than the number of second symbols defined for a report quantity related to RSRP.

8. In paragraph 7, A method, characterized in that the number of the first symbols is determined based on the number of beams included in the at least one CSI report.

9. In paragraph 7, A method, characterized in that the number of first symbols is set and / or defined based on UE capability.

10. In paragraph 1, A method, characterized in that the number of first CSI processing units (CSI Processing Units, CPUs) associated with one of the at least one CSI report is greater than the number of second CPUs associated with a CSI report for RSRP or SINR.

11. In paragraph 10, A method, characterized in that the number of the first CPUs is determined based on the number of beams included in the at least one CSI report.

12. In paragraph 10, A method characterized in that the number of the first CPUs is set and / or defined based on terminal capability (UE capability).

13. In paragraph 10, A method characterized in that the first CPUs are occupied from the time of starting beam measurement for the at least one CSI report until the time of transmitting the at least one CSI report.

14. In paragraph 1, The above first CSI report is related to the input of the first model, A method characterized in that the second CSI report is related to the output of the second model.

15. In paragraph 13, The above first model is a network-sided model, A method characterized in that the second model is a user equipment-sided model.

16. At the terminal, One or more transmitters and receivers; one or more processors; and One or more memories connected to said one or more processors and storing instructions, A terminal characterized in that the instructions, based on being executed by the one or more processors, cause the terminal to perform all steps of the method according to any one of claims 1 to 15.

17. In a device comprising one or more memories and one or more processors connected to the one or more memories, A device characterized in that said one or more memories store instructions that cause said device to perform all steps of a method according to any one of claims 1 to 15, based on being executed by said one or more processors.

18. In a non-transitory computer-readable medium storing instructions, A non-transitory computer-readable medium characterized in that the instructions executable by one or more processors cause a terminal to perform all steps of a method according to any one of claims 1 to 15.

19. In the method, A step of transmitting configuration information related to channel state information (CSI); and A step of receiving at least one CSI report based on a priority rule; wherein said at least one CSI report comprises i) a first CSI report including measurement results related to beam prediction and / or ii) a second CSI report including inference results related to said beam prediction, A method, characterized in that the at least one CSI report has a higher priority than a priority of a third CSI report that does not carry Reference Signal Received Power (RSRP) and / or Signal-to-Interference Noise Ratio (SINR).

20. At the base station, One or more transmitters and receivers; one or more processors; and One or more memories connected to said one or more processors and storing instructions, A base station characterized in that the instructions, based on being executed by the one or more processors, cause the base station to perform all steps of the method according to claim 19.

Images