Method and apparatus for monitoring-related reporting

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 a CSI report related to prediction accuracy. Processing of the CSI report occupies one or more CSI processing units (CPUs). A first uplink symbol carrying the CSI report is determined on the basis of the number of symbols related to CSI computation. The number of the one or more CPUs and / or the number of symbols is determined on the basis of whether or not the CSI report is associated with one or more future time instances.

Description

Method and apparatus for reporting related to monitoring

[0001] This specification relates to a method and apparatus for reporting related to monitoring.

[0002] Mobile communication systems were developed to provide voice services while ensuring user mobility. However, mobile communication systems have expanded their scope to include data services as well as voice. Currently, due to the explosive increase in traffic leading to resource shortages and users demanding higher-speed services, more advanced mobile communication systems are required.

[0003] The requirements for next-generation mobile communication systems largely include the ability to accommodate explosive data traffic, a dramatic increase in transmission rates per user, a significantly increased number of connected devices, very low end-to-end latency, and high energy efficiency. To achieve this, various technologies are being researched, such as dual connectivity, massive multiple input multiple output (MMIMO), in-band full duplex, non-orthogonal multiple access (NOMA), super wideband support, and device networking.

[0004] Standardization discussions regarding the performance monitoring operation of UE-side AI / ML in the beam management field of the Rel-19 AI / ML WI have been conducted. Specifically, performance monitoring of CSI predictions (e.g., CSI including at least one of predicted RS (predicted CRI, predicted SSBRI), predicted L1-RSRP, and / or predicted PMI) may be performed. As an example, a terminal may transmit a report (e.g., CSI report) related to monitoring the accuracy of predicted information (e.g., predicted CRI, predicted SSBRI, and / or predicted PMI, etc.). As an example, the report may include a prediction accuracy indicator (e.g., Prediction Accuracy Indicator).

[0005] If a terminal periodically performs performance monitoring reports, the following problems may occur according to the existing method.

[0006] Compared to the CSI Processing Units (CPUs) and time (e.g., Z, Z' symbols) required for processing and computation associated with existing CSI reports, a CSI report intended to monitor and report the prediction accuracy of predicted CSI based on inference from AI / ML models may require more CPUs and time. Therefore, the number of CPUs, Z, and Z' determined or defined by existing methods may not be suitable for performing performance monitoring reporting.

[0007] The purpose of this specification is to propose a method for solving the aforementioned problems.

[0008] The technical problems to be solved in this specification are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which this specification belongs from the description below.

[0009] A method according to one embodiment of the present specification for solving the aforementioned problem comprises the steps of receiving configuration information related to Channel State Information (CSI) and transmitting a CSI report related to prediction accuracy. The processing of the CSI report occupies at least one CPU (CSI Processing Unit). The first uplink symbol carrying the CSI report is determined based on the number of symbols related to CSI computation. The number of at least one CPU and / or the number of symbols is characterized by being determined based on whether the CSI report is associated with one or more future time instances.

[0010] As described above, the number of CPUs / symbols suitable for CSI reporting related to prediction accuracy can be determined / utilized based on defined criteria (one or more future time instances).

[0011] If the number of CPUs / number of symbols (Z, Z') is used as a value consistently larger than existing defined values ​​without specific criteria, the terminal's CSI processing performance may not be fully utilized, and the time required for monitoring-related reporting may be unnecessarily delayed.

[0012] According to the embodiments of this specification, performance monitoring reporting can be performed based on the number of CPUs and the number of symbols (Z, Z') most suitable for the UE capability and the monitoring target. Therefore, it is possible to prevent cases where performance monitoring reporting is not properly performed due to insufficient time for the number of CPUs or CSI calculation. Furthermore, since an optimized number of CPUs / number of symbols (Z, Z') is used for CSI reporting related to monitoring, procedures related to performance monitoring can be improved in terms of terminal performance utilization, reliability, and latency.

[0013] The effects obtainable in this specification are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which this specification belongs from the description below.

[0014] Figure 1 is a diagram illustrating the overall functions from the perspective of an AI / ML model.

[0015] Figure 2 illustrates a general form of an AI / ML-related procedure performed between a network and a terminal.

[0016] Figure 3 illustrates an example of AI / ML-based beam management operation.

[0017] Figure 4 illustrates an example of an AI / ML-based CSI measurement / reporting operation.

[0018] Figure 5 illustrates an example of an AI / ML-based positioning operation.

[0019] Figure 6 is a flowchart showing an example of a CSI-related procedure.

[0020] FIG. 7 shows an example of a CSI reporting setting according to an embodiment of the present specification.

[0021] FIG. 8 shows another example of a CSI reporting setting according to an embodiment of the present specification.

[0022] FIG. 9 is a flowchart illustrating a method according to one embodiment of the present specification.

[0023] FIG. 10 is a flowchart illustrating a method according to another embodiment of the present specification.

[0024] FIG. 11 is a drawing showing the configuration of a first device and a second device according to an embodiment of the present specification.

[0025] In this specification, "A or B" may mean "only A," "only B," or "both A and B." Alternatively, in this specification, "A or B" may be interpreted as "A and / or B." For example, in this specification, "A, B or C" may mean "only A," "only B," "only C," or "any combination of A, B and C."

[0026] A slash ( / ) or a comma used in this specification may mean "and / or." For example, "A / B" may mean "A and / or B." Accordingly, "A / B" may mean "only A," "only B," or "both A and B." For example, "A, B, C" may mean "A, B or C."

[0027] In this specification, "at least one of A and B" may mean "only A," "only B," or "both A and B." Additionally, in this specification, the expressions "at least one of A or B" or "at least one of A and / or B" may be interpreted as synonymous with "at least one of A and B."

[0028] Additionally, in this specification, "at least one of A, B and C" may mean "only A," "only B," "only C," or "any combination of A, B and C." Also, "at least one of A, B or C" or "at least one of A, B and / or C" may mean "at least one of A, B and C."

[0029] Additionally, parentheses used in this specification may mean "for example." Specifically, when indicated as "control information (PDCCH)," "PDCCH" may be proposed as an example of "control information." In other words, "control information" in this specification is not limited to "PDCCH," and "PDCCH" may be proposed as an example of "control information." Furthermore, even when indicated as "control information (i.e., PDCCH)," "PDCCH" may be proposed as an example of "control information."

[0030] In the following explanation, 'when, if, in case of' can be replaced with 'based on'.

[0031] Technical features described individually within a single drawing in this specification may be implemented individually or simultaneously.

[0032] Hereinafter, preferred embodiments according to the present specification will be described in detail with reference to the accompanying drawings. The detailed description disclosed below, together with the accompanying drawings, is intended to describe exemplary embodiments of the present specification and is not intended to represent the only embodiment in which the present specification may be practiced. The following detailed description includes specific details to provide a complete understanding of the present specification.

[0033] In this specification, a terminal is a user-side device (user equipment, UE) or a consumer-side device, and may also be referred to as a first node that receives / transmits signals from / to a base station / second node / IAB node / Transmission-Reception Point (TRP). A terminal may correspond to a physical node or a logical node. A terminal may correspond to a user-side endpoint or an intermediate point between other endpoints. In communication between two points not limited to endpoints (including one-to-one / many-to-one / one-to-many / many-to-many communication), a terminal may correspond to a served node. A terminal may be a fixed-location node or a non-fixed-location (or mobile) node.

[0034] In this specification, a Base Station (BS) is a device on the network side and may also be referred to as a second node / IAB node / x-NodeB (x-NodeB, where x may be an abbreviation related to Radio Access Technology (RAT)) / Transmission-Reception Point (TRP). A Base Station may correspond to a physical node or a logical node. A Base Station may correspond to an endpoint on the network side or an intermediate point between other endpoints. In communication between two points not limited to endpoints (including one-to-one / many-to-one / one-to-many / many-to-many communication), a Base Station may correspond to a serving node. A Base Station may be a node with a fixed location or a node with an indefinite location.

[0035] In this specification, higher layer parameters may be set for the terminal, pre-set, or pre-defined. For example, a base station may transmit higher layer parameters to the terminal. For example, the terminal may transmit parameters such as capability to the base station as higher layer parameters. For example, higher layer parameters may be transmitted via RRC (radio resource control) signaling or MAC (medium access control) signaling.

[0036] In this specification, information / state / parameters being "configured" or "pre-configured" may be interpreted as the information / state / parameters being provided / pre-provided to the terminal through pre-defined signaling (e.g., SIB, MAC, RRC) from the base station. In this specification, information / state / parameters being "defined" or "pre-defined" may be interpreted as being known or stored in advance by the base station and the terminal without signaling between the base station and the terminal.

[0037] < AI / ML for Wireless Communication >

[0038] With the advancement of computing technology, artificial intelligence (AI) and machine learning (ML) are being adopted across various industries and technological fields. In the field of wireless communication, various discussions are underway regarding the application of AI models trained on ML; notably, the 3GPP standardization process refers to this as AI / ML. In this specification, we use the term "AI / ML" following the terminology currently in use during the 3GPP standardization discussions; however, "AI / ML" may be referred to by various other terms depending on the progress of standardization and implementation in the future. For example, it may be referred to as a "transmission / reception mode" or a "signal / channel / operation / transmission / reception configuration" set for AI / ML, but is not limited thereto. The meanings of the terms currently used in the 3GPP standardization process are briefly summarized as follows.

[0039] - AI / ML Model: Refers to a data-driven algorithm that applies AI / ML technology to generate a set of outputs containing predictive information and / or decision parameters based on a set of inputs.

[0040] - Data collection: This is the process of collecting data necessary for AI / ML model training, data analysis, and inference from network nodes, management entities, or terminals.

[0041] - AI / ML Training: An online or offline process of training an AI model by learning features and patterns that best represent data and acquire an AI / ML model trained for inference.

[0042] - AI / ML Inference: This is the process of making predictions or deriving decisions based on collected data and AI models using trained AI models. Meanwhile, depending on whether the AI / ML model is configured on both the transmitting and receiving devices or on only one, it can be classified into (i) two-sided models and (ii) one-sided models. In the case of (i) two-sided models, cooperative inference is performed through paired AI / ML models. Cooperative inference refers to cooperation between the network and the UE, where one side performs part of the inference and the other performs the remainder. (ii) One-sided models are divided into UE-side models and network-side models. In the case of one-sided models, inference is performed entirely by the UE / network-side models.

[0043] 1. Life Cycle Management (LCM) for AI / ML models

[0044] For AI / ML models, LCM is a concept that encompasses all overall procedures for the model, such as data collection, model training, model deployment, model inference, model monitoring, and model updates.

[0045] Figure 1 is a diagram illustrating the overall functions from the perspective of an AI / ML model.

[0046] Referring to FIG. 1, 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).

[0047] 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) performs data preparation and can provide input data processed through data preparation.

[0048] 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).

[0049] 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) delivered from the Data Collection function (10).

[0050] Trained / Updated Model (21): If there is a Model Storage function (50), it is used to transfer trained, validated, and tested AI / ML models to the Model Storage function (50) or to transfer updated versions of the models to the Model Storage function (50).

[0051] The Management function (30) is a function that monitors the operation of an AI / ML model or an AI / ML function.

[0052] Management Instruction (32) is information required as input to manage the Inference function (40). The relevant information may include the selection / (de)activation / switching of an AI / ML model or an AI / ML-based function, and may also include a fallback to a non-AI / ML operation (i.e., not relying on the inference process).

[0053] A Model Transfer / Delivery Request (33) can be used to request model(s) from Model Storage (50).

[0054] Performance Feedback / Retraining Request (31) refers to information required as input to Model Training function (20) (e.g., for the purpose of retraining or updating the model).

[0055] 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 the 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 the data collection (10). If necessary, the inference function (40) may also perform data preparation (e.g., data pre-processing and cleaning, forming and transformation) based on the inference data (13) provided by the data collection function (10).

[0056] 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 an AI / ML model generated by the Inference function (30), and the details of the inference output may vary depending on the use case.

[0057] The Model Storage function (50) is a function that stores a trained / updated model that can be used to perform the Inference function (40).

[0058] Model Transfer / Delivery (51) is used to transfer an AI / ML model to an inference function.

[0059] 2. General AI / ML related procedures between the network and the terminal

[0060] Figure 2 illustrates the general form of AI / ML-related procedures performed between a network and a terminal. While Figure 1 examined the LCM from the perspective of an AI / ML model, Figure 2 describes the general form of procedures performed between a terminal and a network from the perspective of signaling / protocols.

[0061] (1) AI / ML related setup procedure

[0062] Referring to FIG. 2, an AI / ML-related configuration procedure may be performed between the network and the terminal (B05). The AI / ML-related configuration procedure may include information exchange through at least one upper-layer signaling between the terminal and the network, and / or prior preparation / subsequent operations at the terminal / network respectively before / after the upper-layer signaling.

[0063] Specifically, the configuration procedure related to AI / ML may include, but is not limited to, at least one of the following: (i) reporting the capability of the AI / ML-related terminal, (ii) data collection, (iii) model training, (iv) model delivery / transmission, (v) selection of AI / ML functions / models, and (vi) configuration of various operations performed based on the AI / ML model (e.g., AI / ML-based CSI / Positioning / Beam Management).

[0064] (i) The terminal can inform the network of its capabilities, such as models and functions related to AI / ML, that it supports through UE Capability reporting. The network can provide AI / ML-related settings to the terminal based on the terminal's capabilities related to AI / ML reported by the terminal.

[0065] (ii) AI / ML-related configuration procedures may include data collection related to the training / inference of AI / ML models and / or the provision of configuration information regarding data collection. The configuration information regarding data collection may relate to how to configure the method / operation of data collection.

[0066] (iii) AI / ML-related configuration procedures may include training AI / ML models online or offline and / or providing configuration information for AI / ML model training. The configuration information for AI / ML model training may relate to how to configure the method / behavior, etc., of training the AI / ML model.

[0067] (iv) AI / ML-related configuration procedures may include transmitting / transmitting configuration information for a model. The configuration information for a model may include parameters that constitute the AI / ML model and / or an identifier (ID) for the AI / ML model.

[0068] The provided AI / ML model may be a model trained by the network or a model that requires self-training at the terminal. Even when a model trained by the network is provided, the terminal may perform fine-tuning or retraining as necessary. Meanwhile, if a model trained by the network is provided, the terminal may provide data for training to the network.

[0069] (v) The configuration procedure related to AI / ML may include the configuration of how to select AI / ML Functionality / models and / or the selection process for AI / ML Functionality / models. In UE-side AI / ML models or two-sided AI / ML models, the selection of the UE part may be performed through instructions / signaling from the network or the terminal may select it itself. The selection of AI / ML Functionality / models may be performed when multiple AI / ML Functionality / models are configured / provided.

[0070] (vi) The configuration procedure related to AI / ML may include configuration information for various inference operations performed based on AI / ML models, e.g., AI / ML-based CSI measurement / reporting, AI / ML-based positioning, and / or AI / ML-based beam management.

[0071] (2) Operation based on inference by AI / ML models

[0072] Referring again to FIG. 2, the network and / or terminal can 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 (B10). If the AI / ML model is a one-sided model, the inference of the AI / ML model can be performed at 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 can be performed at the network and the terminal, and depending on the implementation, such inference can be performed cooperatively between the network and the terminal.

[0073] (i) Actions performed based on the inference of an AI / ML model may include AI / ML-based CSI measurement / reporting. AI / ML-based CSI measurement / reporting is intended to improve CSI feedback and may be related to overhead reduction / CSI compression, accuracy improvement, and / or CSI prediction.

[0074] (ii) Actions performed based on the inference of an AI / ML model may include AI / ML-based beam management. AI / ML-based beam management may be related to beam prediction in the time domain, reduction of overhead / latency in the spatial domain, and / or improvement of beam selection accuracy.

[0075] (iii) Actions performed based on the inference of an AI / ML model may include AI / ML-based positioning. AI / ML-based positioning may be relevant to improving positioning accuracy in various scenarios, for example, in non-line-of-sight environments.

[0076] (3) Procedures for AI / ML management

[0077] The network and / or terminal can perform procedures for the management of AI / ML Functionality / model or the settings therefor (B15).

[0078] The network and / or terminal may perform monitoring of AI / ML Functionality / model during the AI / ML model inference or operation based thereon (B10) for the management procedure (B15).

[0079] The management procedure may include, for example, at least one of activation / deactivation, switching, model update, and / or fallback operation for AI / ML Functionality / model. For the signaling of the management procedure, various 3GPP signaling schemes, such as RRC, MAC-CE, DCI, etc., may be used.

[0080] As an example of model switching, multiple model groups are configured, and switching between them can be performed based on models having a common model structure or partially common substructures, and models within the same group may be associated with different input / output formats or processing.

[0081] Model updating involves modifying the parameters used by the model to suit channel conditions that change over time, and fine-tuning is an example of model updating.

[0082] Fallback: In a wireless communication system using an AI / ML model, this may refer to the operation of not using the AI / ML model or operating in a pre-configured / defined default mode when the reliability of the AI / ML model decreases due to internal or external environmental factors.

[0083] For example, the decision on whether to perform a management procedure can be made by the network. For instance, the network may decide to perform the management procedure upon network initiation, or the network may decide to perform the management procedure upon terminal initiation and request.

[0084] As another example, the decision on whether to perform a management procedure can be made by the terminal. For instance, the terminal's decision on the management procedure may be triggered when an event condition set by the network is satisfied, performed by reporting the terminal's decision to the network, or performed autonomously by the terminal.

[0085] 3. Specific operation examples based on AI / ML model inference

[0086] (1) Beam management

[0087] Figure 3 illustrates an example of AI / ML-based beam management operation.

[0088] Referring to FIG. 3, the network / terminal can perform a configuration procedure related to AI / ML-based beam management (C05). The network / terminal can perform a configuration procedure for an AI / ML model to be used for AI / ML-based beam management, and an exchange of configuration information for upper-layer signaling for AI / ML-based beam management. For example, at least one of information related to model inference, configuration for a first set / second set beam, monitoring performance, and assistance information for data collection and beam measurement may be signaled.

[0089] The network / terminal can perform measurements on the first set of beams (C10). The beam measurements may be related to RSRP measurements.

[0090] A network / terminal can obtain information about a second set of beams based on measurement results for a first set of beams (C15). For example, the network / terminal can perform AI / ML inference by using the measurement results for the first set of beams as AI / ML input data. Beam ID information may also be additionally provided as AI / ML input data. Information about the second set of beams may correspond to AI / ML output data. The AI / ML output data may be related to, for example, the probability that each beam will become a top-N beam, the predicted RSRP, etc., for predicting future beam quality, but is not limited thereto.

[0091] According to an embodiment, the network / terminal can transmit and receive information about the acquired second set of beams.

[0092] Specifically, AI / ML-based beam management operations may include at least one of the following BM-Case 1 and BM-Case 2.

[0093] - BM-Case 1: Prediction of the second set of DL beams in the spatial domain through the first set of beam measurements

[0094] - BM-Case 2: Prediction of the second set of DL beams in the time domain through the first set of beam measurements

[0095] In BM-Case 1 and / or 2, both AI / ML model training and inference may be performed on the network or on the terminal. The first set of beams and the second set of beams may be different beams. Or the first set of beams may be a subset of the second set of beams. Or, particularly in BM-Case 2, the first set of beams and the second set of beams may be the same beam.

[0096] The report corresponding to the inference of the UE-side model for BM-Case 1 may relate to the RSRP for the predicted top N beams. The report may include, for example, the predicted RSRP values, and as an example, the predicted RSRP values ​​may be reported together with the actual measured RSRP.

[0097] UE-side AI / ML model inference for BM-Case 2 can report inference results for N future time points through a single report. The report for each time point can correspond to the report in BM-Case 1.

[0098] 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 terminal may report information necessary for the network to calculate performance metrics, for example, by reporting measurement results (e.g., RSRP) and / or RS index for a set of resources for monitoring. (ii) For UE-assisted performance monitoring, the terminal may calculate performance metrics.

[0099] With respect to the NW-side model for BM-Case 1 / 2, quantization of the reported RSRP may be supported, for example, differential RSRP reporting may be supported along existing quantization steps and ranges. The reported content may include information on the RSRP and the corresponding upper N beam, where N can be set by the network.

[0100] With respect to the configuration of the first set of beams and the second set of beams of the UE-side model of BM Case-1, two resource sets may be configured separately for each of the first set and the second set, and the resource sets may be provided through CSI reporting settings. The terminal may perform inference / measurement on the resource set of the first set of beams. The terminal may not be expected to perform measurement / inference on the resource set of the second set of beams. The beam information in the inference report may include resource set information for the first set.

[0101] In relation to the UE-side model, the associated ID may be provided through the CSI framework. The terminal may assume identical / similar characteristics for DL ​​transmit beams / sets (lists) for the same associated ID.

[0102] Regarding UE-assisted performance monitoring for the UE-side models of BM-Case 1 and 2, the following methods may be considered.

[0103] i) Compare prediction results based on resources for monitoring and use the top 1 or top K beam prediction accuracy.

[0104] 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 prediction beams.

[0105] iii) Use the difference information between the measured RSRP and the predicted RSRP for the corresponding beam of the resources for monitoring.

[0106] iv) Probability information that the predicted beam will become one of the top 1 or N beams

[0107] For reporting inference results for the UE-side model, quantization of RSRP may be supported, and differential RSRP with existing quantization steps may be supported. The scope of RSRP reporting is such that differential RSRP among multiple beams is supported in the case of BM-case 1, and differential RSRP among multiple beams at multiple time points is supported in the case of BM-case 2.

[0108] For BM-Case 2 of the UE-side model, the network can be configured to report inferences about N future times to the terminal.

[0109] (2) CSI prediction and / or compression

[0110] Figure 4 illustrates an example of an AI / ML-based CSI measurement / reporting operation.

[0111] Referring to FIG. 4, the network / terminal can perform a configuration procedure related to AI / ML-based CSI (D05). The network / terminal can perform a configuration procedure for an AI / ML model to be used for AI / ML-based CSI, and for the exchange of configuration information for upper-layer signaling for AI / ML-based CSI measurement / reporting. For example, at least one of information related to model inference, settings for RS / resources to be used for CSI measurement, monitoring performance, data collection, and conditions / resources for CSI reporting may be signaled.

[0112] The terminal can perform CSI measurements based on AI / ML model inference (D10). The AI / ML model used by the terminal for CSI measurements may be a UE-side AI / ML model corresponding to a one-side AI / ML model, or an AI / ML model corresponding to the terminal part of a two-side AI / ML model.

[0113] The terminal may report CSI to the network based on the results of CSI measurements (D15). CSI reporting may be performed periodically or non-periodically depending on the configuration, and in the case of non-period CSI reporting, network instructions (not shown), such as DCI, that trigger it may be additionally signaled. CSI reporting may include AI / ML-based CSI content and may additionally include legacy CSI content (e.g., non-AI / ML-based RI, PMI, CQI, etc.) (depending on the configuration / scheduling). AI / ML-based CSI content may be related to at least one of 1) CSI compression to reduce the overhead of CSI reporting and 2) CSI prediction for future time points in the time domain.

[0114] The network can acquire CSI based on the terminal's CSI report.

[0115] If a two-sided AI / ML model is configured, the network can reconstruct the CSI by using the terminal's CSI report as input data to the AI / ML model configured in the network (D20). The inference (output) of the AI / ML model configured in the network may be the reconstructed CSI. In such a two-sided AI / ML model, the terminal-side AI / ML model part can be understood as a CSI encoder, and the network-side AI / ML model part can be understood as a concept similar to a CSI decoder.

[0116] CSI compression is CSI compression in the spatial-frequency domain and can primarily be based on two-sided AI / ML models. CSI prediction can primarily be based on one-sided, specifically UE-side AI / ML models.

[0117] In CSI compression based on a two-sided AI / ML model, AI / ML model training may include at least one of the following: (i) Type 1, in which the two-sided AI / ML model is jointly trained at either the terminal or the network; (ii) Type 2, in which the terminal and the network each jointly train the corresponding parts of the two-sided AI / ML model; and (iii) Type 3, in which the terminal and the network each separately train the corresponding parts of the two-sided AI / ML model, wherein the training of the terminal is mainly related to CSI generation and the training of the network is mainly related to CSI reconstruction. Joint training means that the CSI generation / reconstruction models are trained in the same loop for forward / backward delays, and separate training may mean a sequential method in which one of the terminals or the network starts training first, and then the other performs training.

[0118] (3) Positioning

[0119] Figure 5 illustrates an example of an AI / ML-based positioning operation.

[0120] Referring to FIG. 5, the network / terminal can perform a setup procedure related to AI / ML-based positioning (E05). The network / terminal can perform measurements for positioning (E10). The measurements for positioning may be related to PRS and / or SRS measurements. Based on the measurement results, the network / terminal can obtain information regarding terminal positioning (E15). For example, the network / terminal can perform AI / ML inference by using the measurement results for PRS / SRS as AI / ML input data. The information regarding terminal positioning may correspond to AI / ML output data. The AI / ML output data may be, for example, terminal location or assistance information that serves as the basis for determining terminal location, but is not limited thereto.

[0121] < CSI Related Actions >

[0122] Channel state information (CSI) may include at least one of a channel quality indicator (CQI), a precoding matrix indicator (PMI), a CSI-RS resource indicator (CRI), an SS / PBCH block resource indicator (SSBRI), a layer indicator (LI), a rank indicator (RI), Layer 1-RSRP (Layer 1-Reference Signal Received Power), and / or Layer 1-SINR (Layer 1-Signal-to-Interference-plus-Noise Ratio).

[0123] In the case of the CSI prediction described below, the CSI related to the prediction may include at least one of the predicted CQI (predicted CQI, P-CQI), predicted PMI (predicted PMI, P-PMI), predicted CRI (predicted CRI, P-CRI), predicted SSBRI (predicted SSBRI, P-SSBRI), predicted LI (predicted LI, P-LI), predicted RI (predicted RI, P-RI), predicted L1-RSRP (predicted L1-RSRP, P-L1-RSRP) and / or predicted L1-SINR (predicted L1-SINR, P-L1-SINR).

[0124] When monitoring the performance / accuracy of the CSI prediction described below, the CSI related to prediction accuracy may include a Prediction Accuracy Indicator (PAI). For example, the PAI may indicate the accuracy of predicted downlink reference signal(s) (e.g., predicted CRI(s) and / or predicted SSBRI(s)), and the PAI may be interpreted / replaced as a Reference Signal-Prediction Accuracy Indicator (RS-PAI). For example, the PAI may indicate the accuracy of predicted CSI (e.g., predicted PMI), and the PAI may be interpreted / replaced as a Channel State Information-Prediction Accuracy Indicator (CSI-PAI).

[0125] Figure 6 is a flowchart showing an example of a CSI-related procedure.

[0126] Referring to FIG. 6, to perform one of the uses 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) via radio resource control (RRC) signaling (S610).

[0127] The configuration information related to the above CSI may include at least one of CSI-IM (interference management) resource information, CSI measurement configuration information, CSI resource configuration information, CSI-RS resource information (e.g., M≥1 CSI-ResourceConfig resource setting), or CSI report configuration information (e.g., N≥1 CSI-ReportConfig reporting setting). As an example, the configuration information may include at least one of one or more CSI resource settings and / or one or more CSI reporting settings.

[0128] For example, the configuration information may include a first CSI resource setting for measurement and a second CSI resource setting for prediction. As a specific example, the measurement related to the prediction of CSI described below may be performed based on the first CSI resource setting. The terminal may perform L1-RSRP measurements on CSI-RS resources or SS / PBCH block resources associated with the first CSI resource setting. As a specific example, the prediction of CSI described below may be performed based on the second CSI resource setting. Based on the L1-RSRP measurements, the terminal may perform predictions on CSI-RS resources or SS / PBCH block resources associated with the second CSI resource setting. In other words, using L1-RSRPs as measurement metrics, the best CRI / best SSBRI (e.g., P-CRI(s), P-SSBRI(s)) may be predicted.

[0129] For example, the above configuration information may include a first CSI reporting setting related to prediction and a second CSI reporting setting related to prediction accuracy.

[0130] Information related to CSI resource configuration can be expressed as CSI-ResourceConfig IE. Information related to CSI resource configuration defines a group including at least one of an NZP (non-zero power) CSI-RS resource set, a CSI-IM resource set, or a CSI-SSB resource set. That is, the information related to CSI resource configuration includes a CSI-RS resource set list, and the CSI-RS resource set list may 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.

[0131] Information related to CSI report configuration (e.g., CSI-ReportConfig IE) includes a reportConfigType parameter representing time domain behavior and a reportQuantity parameter representing the CSI-related quantity to be reported. The time domain behavior may be periodic, aperiodic, or semi-persistent.

[0132] The above reportQuantity parameter includes the channel quality indicator (CQI), precoding matrix indicator (PMI), CSI-RS resource indicator (CRI), SS / PBCH block resource indicator (SSBRI), layer indicator (LI), rank indicator (RI), L1-RSRP (Layer 1-Reference Signal Received Power), L1-SINR (Layer 1-Signal-to-Interference-plus-Noise Ratio), predicted CQI (P-CQI), predicted PMI (P-PMI), predicted CRI (P-CRI), predicted SSBRI (P-SSBRI), predicted LI (P-LI), predicted RI (P-RI), predicted L1-RSRP (P-L1-RSRP), and / or predicted L1-SINR (predicted It can be set to a value representing at least one of L1-SINR, P-L1-SINR) and / or Prediction Accuracy Indicator (PAI) (or RS-PAI).

[0133] For example, the reportQuantity parameter can be set to cri, ssb-Index, cri-RSRP, or ssb-Index-RSRP. cri represents the CSI-RS resource indicator (CRI). RSRP represents the L1-RSRP (Layer 1-Reference Signal Received Power). ssb-Index represents the SS / PBCH block resource indicator (SSBRI).

[0134] For example, the reportQuantity parameter can be set to p-cri, p-ssb-index, p-cri-RSRP, or p-ssb-index-RSRP. p-cri represents the predicted CRI (predicted CRI, P-CRI). p-ssb-index represents the predicted SSBRI (predicted SSBRI, P-SSBRI). p-cri-RSRP represents the predicted CRI (predicted CRI, P-CRI) and predicted L1-RSRP (predicted L1-RSRP, P-L1-RSRP). p-ssb-index-RSRP represents the predicted SSBRI (predicted SSBRI, P-SSBRI) and predicted L1-RSRP (predicted L1-RSRP, P-L1-RSRP).

[0135] For example, the reportQuantity parameter can be set to pai (or rs-pai). pai (or rs-pai) represents PA (or RS-PAI).

[0136] The measurement resource may include settings for downlink signals and / or downlink resources for which the terminal will perform measurements to determine feedback information. The measurement resource may be set as a set of ZP and / or NZP CSI-RS resources associated with a CSI reporting setting. The NZP CSI-RS resource set may include a CSI-RS set or an SSB set. For example, L1-RSRP may be measured against a CSI-RS set or against an SSB set.

[0137] The terminal measures the CSI based on configuration information related to the above CSI (S620). The CSI measurement may include (1) a process of receiving the terminal's CSI-RS (S621) and (2) a process of computing the CSI through the received CSI-RS (S622). The terminal reports the CSI to the base station (S630).

[0138] resource setting

[0139] Each CSI resource setting 'CSI-ResourceConfig' contains a configuration for S≥1 CSI resource sets (given by the higher layer parameter csi-RS-ResourceSetList). The CSI resource setting corresponds to the CSI-RS-resourcesetlist, where S represents the number of configured CSI-RS resource sets. Here, the list of S≥1 CSI resource sets includes either or both of the NZP CSI-RS resource set(s) and the SS / PBCH block (SSB) set(s) used for L1-RSRP computation, or includes CSI-IM resource set(s).

[0140] Next, one or more CSI resource settings for channel measurement (CM) and interference measurement (IM) are established through higher layer signaling.

[0141] - CSI-IM resource for interference measurement.

[0142] - NZP CSI-RS resources for interference measurement.

[0143] - NZP CSI-RS resources for channel measurement.

[0144] That is, the CMR (channel measurement resource) may be an NZP CSI-RS for CSI acquisition, and the IMR (Interference measurement resource) may be an NZP CSI-RS for CSI-IM and IM.

[0145] Here, CSI-IM (or ZP CSI-RS for IM) is primarily used for inter-cell interference measurements.

[0146] Also, the NZP CSI-RS for IM is mainly used for intra-cell interference measurement from multi-users.

[0147] A UE can assume that the CSI-RS resource(s) for channel measurement set for one CSI reporting and the CSI-IM / NZP CSI-RS resource(s) for interference measurement (when the NZP CSI-RS resource(s) are used for interference measurement) have a QCL relationship with respect to 'QCL-TypeD' on a resource-by-resource basis.

[0148] As examined, resource setting can refer to a resource set list.

[0149] 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, semi-persistent, or aperiodic resource setting.

[0150] One reporting setting (e.g., CSI-ReportConfig) can be associated with up to three resource settings (e.g., CSI-ResourceConfig). For example, one CSI reporting setting may include the ID (e.g., CSI-ResourceConfigId) of at least one CSI resource setting. The at least one CSI resource setting may include a CSI resource setting associated with a measurement.

[0151] Beam Management (BM)

[0152] 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 terms.

[0153] - Beam measurement: An operation in which a base station or UE measures the characteristics of a received beamforming signal.

[0154] - Beam determination: The operation in which a base station or UE selects its transmit beam (Tx beam) / receive beam (Rx beam).

[0155] - Beam sweeping: An operation that covers a spatial area using transmitting and / or receiving beams for a set time interval in a predetermined manner.

[0156] - Beam report: An operation in which the UE reports information about the beam-formed signal based on beam measurements.

[0157] The BM procedure can be divided into (1) a DL BM procedure using an SS (synchronization signal) / PBCH (physical broadcast channel) Block or CSI-RS, and (2) a UL BM procedure using an SRS (sounding reference signal).

[0158] In addition, each BM procedure may include Tx beam sweeping to determine the Tx beam and Rx beam sweeping to determine the Rx beam.

[0159] DL BM

[0160] The DL BM procedure may include (1) transmission to beamformed DL RS (reference signals) of the base station (e.g., CSI-RS or SS Block (SSB)) and (2) beam reporting of the terminal.

[0161] Here, beam reporting may include preferred DL RS ID(identifier)(s) and the corresponding L1-RSRP(Reference Signal Received Power).

[0162] The above DL RS ID may be SSBRI (SSB Resource Indicator) or CRI (CSI-RS Resource Indicator).

[0163] An example of beam forming using SSB and CSI-RS will be examined in detail below.

[0164] 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, while CSI-RS can be used for fine beam measurement. SSB can be used for both Tx beam sweeping and Rx beam sweeping.

[0165] Rx beam sweeping using SSBs can be performed as the UE changes the Rx beam across multiple SSB bursts for the same SSBRI. Here, one SS burst includes one or more SSBs, and one set of SS bursts includes one or more SSB bursts.

[0166] The DL BM procedure is examined below.

[0167] Configuration for beam reporting using SSB is performed during CSI / beam configuration in the RRC connected state (or RRC connected mode).

[0168] - The terminal receives configuration information from the base station. As a specific example, the terminal receives from the base station a CSI-ResourceConfig IE containing a CSI-SSB-ResourceSetList containing SSB resources used for BM.

[0169] Table 1 shows an example of CSI-ResourceConfig IE. As shown in Table 1, BM configuration using SSB is not defined separately, and SSB is configured like a CSI-RS resource.

[0170]

[0171] In Table 1, the csi-SSB-ResourceSetList parameter represents 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.

[0172] - The terminal receives a DownLink Reference Signal (DL RS) from the base station. As a specific example, the terminal receives an SSB resource from the base station based on the CSI-SSB-ResourceSetList.

[0173] - The terminal transmits a beam report to the base station. As a specific example, if a CSI-ReportConfig related to reporting on SSBRI (SSB Resource Indicator) and L1-RSRP is configured, the terminal reports the best SSBRI and the corresponding L1-RSRP to the base station.

[0174] That is, if 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.

[0175] And, if the terminal has a CSI-RS resource configured 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 in terms of 'QCL-TypeD'.

[0176] Here, the above QCL Type D may mean that the antenna ports are QCL-connected in terms of spatial Rx parameters. When a terminal receives multiple DL antenna ports that are in a QCL Type D relationship, it is acceptable to apply the same receiving beam. Additionally, the terminal does not expect CSI-RS to be established in an RE that overlaps with the RE of the SSB.

[0177] The configuration for beam reporting using CSI-RS is performed in the same manner as the configuration for beam reporting using SSB described above, so a redundant explanation is omitted. The operation of the beam reporting procedure using CSI is described below.

[0178] - The terminal receives configuration information from the base station. As a specific example, the terminal receives from the base station a CSI-ResourceConfig IE containing a CSI-SSB-ResourceSetList containing CSI resources used for BM (e.g., NZP CSI-RS resource set IE).

[0179] - The terminal receives CSI-RS resources within the NZP CSI-RS resource set through different Tx beams (DL spatial domain transmission filters) of the base station.

[0180] - The terminal selects (or determines) the best beam.

[0181] - The terminal reports the ID and associated quality information (e.g., L1-RSRP) for the selected beam to the base station. In this case, the reportQuantity of the CSI report config can be set to 'cri-RSRP'.

[0182] Explanation regarding Rel-17 / 18 beam management >

[0183] In Rel-17, DL DCI (e.g., DCI format 1-1 or 1-2) can indicate both the DL TCI state and the UL TCI state, or it can indicate only the UL TCI state without specifying the DL TCI state. Consequently, the methods used in the existing R15 / R16 for configuring UL beam and power control (PC) are replaced in Rel-17 by the aforementioned method of indicating the UL TCI state. More specifically, in R17, a single UL TCI state can be indicated through the TCI field of the DL DCI; this UL TCI state is applied to all PUSCHs and all PUCCHs after a certain period known as the beam application time, and can be applied to some or all of the indicated SRS resource sets. Additionally, the base station can utilize DCI and / or MAC-CE to perform a terminal common beam update, which performs indication / updates for multiple specific DL / UL channel / RS combinations using a single beam (utilizing joint or separate TCI states). For the target channel / RS of the common beam update, UE-dedicated CORESET and UE-dedicated reception on PDSCH are available for DL, and DG / CG-PUSCH and all or subset of dedicated PUCCH are available for UL, and additionally, AP CSI-RS for tracking / BM and SRS can be set as target channel / RS.In Rel-18, considering the M-TRP environment, the method of indicating multiple UL TCI states (and / or DL ​​TCI states) through the TCI field of DL DCI was standardized, and depending on the S-DCI based M-TRP environment and the M-DCI based M-TRP environment, uplink and downlink resources to which each indicated TCI is applied can be defined / configured.

[0184] In this document, ' / ' means 'and', 'or', or 'and / or' depending on the context.

[0185] In this specification, 'beam' may refer to a source RS for a 'spatial filter' or 'spatial relation', and may be interpreted as a QCL (type-D) RS, a TCI state, or (in the case of an uplink) a spatial relation RS.

[0186] For example, in this specification, 'beam' may refer to a spatial filter determined based on the reference RS or the source RS. The spatial filter may include a spatial domain filter, a spatial domain transmission filter, and a spatial domain receive filter. For example, in this specification, 'beam' may be interpreted or substituted with a reference signal index (RS index), a reference signal resource index (RS resource index), and / or a resource indicator (e.g., RS index, SSB index, CSI-RS resource index, SRS resource index, SSB Resource Indicator (SSBRI), CSI-RS Resource Indicator (CRI), etc.).

[0187] For example, a beam associated with a UL may be referred to as i) a spatial filter (for uplink transmission or uplink reception), ii) a spatial domain filter (for uplink transmission or uplink reception), iii) an uplink spatial domain transmission filter, iv) an uplink spatial domain receive filter, v) an uplink transmission spatial filter (UL Tx spatial filter) or vi) an uplink receive spatial filter (UL Rx spatial filter).

[0188] For example, a beam associated with DL may be referred to as i) a spatial filter (for downlink transmission or downlink reception), ii) a spatial domain filter (for downlink transmission or downlink reception), iii) a downlink spatial domain transmission filter, iv) a downlink spatial domain receive filter, v) a downlink transmission spatial filter (DL Tx spatial filter), or vi) a downlink receive spatial filter (DL Rx spatial filter).

[0189] In NR standards, QCL configuration via TCI state settings and spatial relation configuration are utilized to configure the UL / DL transmit / receive beams of a terminal. In the Rel-15 NR standard, RRC and MAC CE signaling are primarily used for uplink and downlink transmit / receive beams. Dynamic signaling has been permitted only for the PDSCH receive beam by utilizing the TCI state field of the DL grant DCI. A unified TCI framework was introduced through the Rel-17 / 18 NR standards. Specifically, a method was introduced to dynamically manage the common beam by using DCI to indicate the indicated TCI for the receive / transmit beams. Meanwhile, in the Rel-18 AI / ML study item, a study was conducted on performance evaluation and specification impact regarding spatial beam prediction and temporal beam prediction sub-use cases in the field of beam management. This study discussed NW / UE-side AI / ML operations that predict the best beam of Set A based on Set B measurements. In the case of UE-side AI / ML, the behavior of the terminal measuring Set B and reporting the predicted Set A beam can be discussed in the Rel-19 AI / ML work item. In this case, if the terminal's beam prediction performance is poor, actions such as switching the terminal-side AI / ML model / functionality or falling back to non-AI / ML-based conventional beam management instead of AI / ML-based beam management (measurement / reporting) are necessary.

[0190] This specification proposes a performance monitoring method for a terminal-side AI / ML model and proposes an operation in which the terminal reports performance monitoring results to a base station when a specific event occurs.

[0191] < Background related to UE-initiated BM >

[0192] In existing LTE / NR systems, the reporting of terminal CSI / beam information is determined / controlled by the base station / network (except in the case of BFR). This network-initiated / triggered reporting method has a limitation in that terminals must be configured / instructed to send CSI / beam information frequently in environments where the wireless channel is likely to change rapidly. In such environments, problems arise where the overhead of UL resources for CSI / beam reporting and the related DL measurement RS increase, and the terminal's power consumption also increases due to frequent uplink transmissions. Furthermore, the more terminals there are within the cell / TRP coverage area, the greater the UL resource overhead becomes, as UL resources must be allocated to each terminal. To overcome these limitations of network-initiated / triggered reporting, the UE-initiated / triggered reporting method or the event-based / triggered reporting method has recently emerged.

[0193] In UE-initiated / triggered reporting or event-based / triggered reporting methods, the terminal decides whether to report and when to report. By performing the report only when necessary (e.g., only when a specific event occurs), UL resource overhead and terminal power consumption can be reduced. Motivated by this, standardization for UE-initiated / triggered beam reporting is scheduled to proceed in NR Rel-19. Furthermore, in 6G communication systems, UE-initiated / triggered or event-based transmission methods may be more actively expanded and applied to ensure the efficient operation of uplink resources.

[0194] In NR systems, representative reporting methods for event-based or UE-initiated / triggered information include SR (scheduling request) and BFR (beam failure recovery). SR reports whether PUSCH allocation is required for UL-SCH transmission, while BFR reports whether a BF has occurred and information related to the new beam. This information is transmitted to the base station via explicit or implicit means (e.g., delivering the new beam index as PRACH resource selection information). The aforementioned SR / BFR information is transmitted either simultaneously or in installments through one or two UL resources (e.g., BFRQ on PUCCH + beam information via MAC-CE on PUSCH).

[0195] In this specification, information transmitted to a network based on the terminal's event and / or via UE-initiated / triggered transmission methods as described above (e.g., SR, BFRQ, new beam information, etc.) is referred to as "event information" for the sake of convenience of explanation. Event information consists of one or more information parts / blocks, and encoding / rate matching / RE mapping may be performed on each part / block unit. Each information part / unit may be transmitted via a different transmission method (e.g., BFRQ via UCI as L1 message, new beam information via MAC-CE as L2 message).

[0196] < Background related to AI / ML beam management >

[0197] In the Rel-18 AI / ML study item, performance analysis and potential specification impact were studied through evaluation when NW and / or UE-side AI / ML models were operating in three use cases: CSI compression / prediction, beam management, and positioning. In particular, for the beam management use case, the study was conducted by dividing the sub-use cases into BM-case1 and BM-case2 to analyze performance and potential specification impact regarding spatial domain beam prediction and temporal beam prediction. The WID objectives of the AI / ML BM, as well as BM-case1 and BM-case2, are summarized in Tables 2 through 4 below.

[0198] - WID goals for AI / ML BM

[0199]

[0200] - BM-case1: Spatial domain downlink beam prediction for beam set A based on measurement results of beam set B

[0201]

[0202] - BM-case2: Temporal downlink beam prediction for Beam Set A based on historical measurement results of Beam Set B

[0203]

[0204] In addition, an example of the operation for data collection of an AI / ML model in a beam management use case is shown in Table 5 below.

[0205]

[0206] In addition, an example of the operation for inference of an AI / ML model in a beam management use case is shown in Table 6 below.

[0207]

[0208] < Method for beam prediction >

[0209] As cited above, a discussion was held regarding NW / UE-sided AI / ML operations that predict the best beam of Set A based on Set B measurements. In the case of UE-sided AI / ML, an operation is required for the terminal to measure Set B and report the predicted Set A beam. In the case of NW-sided AI / ML, an operation is required for the terminal to report the Set B measurements.

[0210] Based on the background described above, the following examines the beam measurement / reporting configuration method for base station-side AI / ML and terminal-side AI / ML, as well as the subsequent base station / terminal operations.

[0211] In this specification, ' / ' may be interpreted as 'and', 'or', or 'and / or' depending on the context.

[0212] Proposal 1

[0213] For beam prediction operations of an NW-sided AI / ML model or / and a UE-sided AI / ML model, a method of setting one or more combinations associated with a specific CSI-ReportConfig may be considered. Each combination may include i) one or more Set A's and ii) one or more Set B's associated with each of the one or more Set A's. A base station may set the one or more combinations associated with a specific CSI-ReportConfig to a terminal.

[0214] For example, a specific CSI-ReportConfig may be associated with or linked to multiple CSI-ResourceConfigs. The multiple CSI-ResourceConfigs may include a CSI-ResourceConfig associated with Set A and a CSI-ResourceConfig associated with Set B. As a specific example, a specific CSI-ReportConfig may include information regarding the multiple CSI-ResourceConfigs (e.g., the ID of each of the multiple CSI-ResourceConfigs; CSI-ResourceConfigId). As a specific example, multiple CSI-ResourceConfigs associated with a specific CSI-ReportConfig may be configured.

[0215] For example, multiple CSI resource sets may be configured or connected to a CSI-ResourceConfig for a specific CSI-ReportConfig. The multiple CSI resource sets may include a CSI resource set associated with Set A and a CSI resource set associated with Set B. As a specific example, a specific CSI-ReportConfig may include information about the CSI-ResourceConfig (e.g., CSI-ResourceConfigId). The CSI-ResourceConfig may include multiple CSI resource sets.

[0216] In the examples above, CSI-ResourceConfig can be associated with channel measurement.

[0217] In the following examples, the method of setting / connecting one or more of the above combinations (Set A / Set B combinations) is explained in more detail.

[0218] Example 1 of Proposal 1)

[0219] The base station can configure / connect one Set A and one or more Set Bs for a specific CSI-ReportConfig for beam prediction purposes. A CSI-ReportConfig based on Example 1) will be described below with reference to FIG. 7.

[0220] FIG. 7 illustrates an example of a CSI report configuration according to an embodiment of the present specification. Specifically, FIG. 7 illustrates Set A / Set B based on CSI-ReportConfig. Referring to FIG. 7, CSI-ReportConfig#1 may be associated with Set A and three Set Bs. The three Set Bs include i) Set B configured based on 1 / 8 of the beams (e.g., RS indices or RS resources) in Set A, ii) Set B configured based on 1 / 16 of the beams in Set A, and iii) Set B configured based on the beams in Set A and other beams.

[0221] Subsequently, information regarding which Set B the terminal will utilize for beam measurement / reporting purposes for the specific CSI-ReportConfig may be indicated. For example, one of the Set Bs associated with the specific CSI-ReportConfig may be activated. As a specific example, the base station may transmit information (e.g., an activation message) to the terminal to activate one of the Set Bs associated with the specific CSI-ReportConfig. The information may be transmitted based on MAC CE or DCI.

[0222] Example 2 of Proposal 1)

[0223] For a specific CSI-ReportConfig for beam prediction purposes, the base station may set / connect i) a plurality of Set A's and ii) a plurality of Set B's associated / related with each of the plurality of Set A's. A CSI-ReportConfig based on Example 2) will be described below with reference to FIG. 8.

[0224] FIG. 8 illustrates another example of a CSI report configuration according to an embodiment of the present specification. Specifically, FIG. 8 illustrates combinations of Set A / Set B based on CSI-ReportConfig. Referring to FIG. 8, CSI-ReportConfig#1 may be associated with three combinations.

[0225] Set A / B combination #1 may include Set A (Set A #1) and two Set Bs. The two Set Bs include i) Set B configured based on 1 / 4 of the beams (e.g., RS indices or RS resources) in Set A #1 and ii) Set B configured based on 1 / 8 of the beams in Set A #1.

[0226] Set A / B combination #2 may include Set A (Set A #2) and three Set Bs. The three Set Bs include i) a Set B configured based on 1 / 8 of the beams (e.g., RS indices or RS resources) in Set A #2, ii) a Set B configured based on 1 / 16 of the beams in Set A #2, and iii) a Set B configured based on the beams in Set A #2 and other beams.

[0227] Set A / B combination #3 may include Set A (Set A #3) and two Set Bs. The two Set Bs include i) Set B configured based on 1 / 4 of the beams (e.g., RS indices or RS resources) in Set A #3 and ii) Set B configured based on the beams in Set A #3 and other beams.

[0228] Subsequently, information may be provided regarding which Set A and which Set B (associated with / related to the said Set A) the terminal will utilize for beam measurement / reporting purposes for the said specific CSI-ReportConfig. For example, i) a specific Set A among a plurality of Set As associated with the said specific CSI-ReportConfig and ii) a specific Set B among a plurality of Set Bs associated with the said specific Set A may be activated. As a specific example, the base station may transmit information (e.g., an activation message) to the terminal to activate the specific Set A and the specific Set B associated with the said specific CSI-ReportConfig. The information may be transmitted based on MAC CE or DCI.

[0229] For example, in the embodiment of Proposal 1 above, Set B may be configured / connected to a specific CSI-ReportConfig as a separate CSI resource set from Set A.

[0230] For example, in an embodiment of Proposal 1 above, Set B may be configured to include some of the multiple CSI resources within the CSI resource set configured as Set A. Base station signaling related to the configuration of Set B may be performed. For example, there may be beams corresponding to 64 CSI resources in Set A. In this case, a specific Set B may be configured based on a 64-bitmap. Specifically, the 64-bitmap represents the CSI resources belonging to the specific Set B among the 64 CSI resources within Set A.

[0231] Additionally, for environments where Set A and Set B have no intersection (e.g., when Set A and Set B are different), Set B can be defined / configured as follows.

[0232] For example, Set B may be defined / configured based on i) CSI resource(s) within Set A and ii) coefficient value(s) applied to said CSI resource(s). As a specific example, one or more beams of Set B may be configured based on a linear combination. The linear combination may be based on a CSI resource and coefficient values ​​associated with said resource.

[0233] For example, one or more beams of Set B can be set based on a 2D-bitmap for a beamforming range (e.g., horizontal angle, vertical angle).

[0234] Characteristically, when an embodiment of Proposal 1 is utilized for UE-side AI / ML, the terminal may report information to the base station indicating a preferred Set A and / or Set B for terminal-side beam prediction operations. As a specific example, among the Set A's and Set B's based on the above-described embodiments 1 and 2, the terminal may report a preferred Set A and / or a preferred Set B to the base station. Subsequently, the base station may activate the combination of Set A and Set B preferred by the terminal for the corresponding specific CSI-ReportConfig (using MAC CE signaling, etc.).

[0235] Effects of the above Proposal 1

[0236] When a terminal performs a report on the Set B beam through the Set A / B beam set setting operation of the above proposal 1, the base station can perform a beam prediction operation for Set A using NW-sided AI / ML, and the terminal can derive the predicted Set A beam by using the Set B beam measurement (as input data for UE-sided AI / ML).

[0237] Furthermore, NW / UE-side AI / ML models / functionalities may vary, and the size of the input data may even be variable for specific models / functionalities. In this case, based on the present embodiment, various combinations of Set A and Set B may be pre-configured to the terminal by the base station. A combination of Set A and Set B suitable for the AI / ML model / functionality of the NW / UE may be adaptively activated / instructed in response to changes in the input data size (via MAC CE or DCI). Through this operation, effects such as delay reduction and improved beam prediction performance can be achieved.

[0238] Proposal 2

[0239] The base station may set a reportQuantity in the terminal for beam measurement / reporting of the terminal with respect to the CSI-ReportConfig of Proposal 1 above, which is related to the reports of Alt 1) to Alt 5) below. For example, the reportQuantity may be set to a value representing a report based on at least one of Alt 1) to Alt 5) and information included in the said report.

[0240] Alt 1)

[0241] Based on the reportQuantity set by the base station, the terminal may report L1-RSRP values ​​for one or more Channel Measurement Resources (CMRs) associated with Set B to the CSI-ReportConfig of Proposal 1. The one or more CMRs associated with Set B may be i) all CMRs within Set B, ii) N (N is a natural number) CMRs having the highest L1-RSRP value within Set B, or iii) specific N CMRs within Set B set / instructed by the base station.

[0242] Alt 2)

[0243] Based on the reportQuantity set by the base station, the terminal may perform reporting as follows. For the CSI-ReportConfig of Proposal 1 above, the terminal may report i) L1-RSRP values ​​for one or more CMRs associated with Set B and ii) L1-RSRP values ​​for one or more CMRs associated with Set A.

[0244] One or more CMRs associated with the above Set A may be i) specific N CMRs in Set A that have a connection relationship (by base station preset) with the CMRs in Set B reported by the terminal, ii) N CMRs in Set A that have the highest L1-RSRP value, or iii) specific N CMRs in Set A that are set / instructed by the base station.

[0245] Characteristically, reports related to Set A that are additionally reported to reports related to Set B may be performed only for some of the total reporting instances of the above CSI-ReportConfig (e.g., 1 / X of the total reporting instances, where X is a natural number). In order to match the reporting payloads identically or similarly when reporting related to both Set B and Set A is performed versus when reporting related to Set B is performed only, the following embodiments may be considered when Set A is also reported.

[0246] i) When reporting the L1-RSRP of the best CMR in Set B, a step size of 2 dB or more may be applied. For example, the legacy step size may be 1 dB.

[0247] ii) Within Set B (while utilizing a step size of 2 dB or more when reporting L1-RSRP of the best CMR), a larger step size may be applied for differential reporting when reporting L1-RSRP of the non-best CMR. For example, according to the legacy standard, the step size for differential reporting is 2 dB, but according to the present embodiment, a step size of 4 dB, 6 dB, or 8 dB may be applied.

[0248] iii) The number of CMRs reported in Set B may be reduced, or reporting for some CMRs in Set B may be omitted (e.g., omit N CMRs with the lowest L1-RSRP value).

[0249] Additionally, the reporting granularity for expressing L1-RSRP may differ between the reporting for Set B and the reporting for Set A.

[0250] Alt 3)

[0251] Based on the reportQuantity set by the base station, the terminal may report one or more predicted best CMRs associated with Set A (based on Set B beam measurement) and predicted L1-RSRP values ​​for the CSI-ReportConfig of Proposal 1.

[0252] One or more predicted best CMRs associated with the above Set A may be specific K CMRs (where K is a natural number) set / instructed by the base station (corresponding to the highest predicted L1-RSRP value of Top-K).

[0253] Alt 4)

[0254] Based on the reportQuantity set by the base station, the terminal may perform reporting as follows. For the CSI-ReportConfig of Proposal 1 above, the terminal may report i) one or more predicted best CMRs related to Set A (based on Set B beam measurement) and their predicted L1-RSRP values, and ii) L1-RSRP values ​​(actually measured) for one or more CMRs related to Set A.

[0255] One or more CMRs associated with the above Set A may be i) specific N CMRs within Set A that have a connection relationship (by base station preset) with the predicted best CMR associated with Set A reported by the terminal, ii) N CMRs within Set A that have the highest L1-RSRP value, or iii) specific N CMRs within Set A that are set / instructed by the base station.

[0256] Characteristically, reports related to Set A that are additionally reported to reports related to the predicted CMR of Set A may be performed only for some of the total reporting instances of the above CSI-ReportConfig (e.g., 1 / X of the total reporting instances, where X is a natural number). In order to match the reporting payloads identically or similarly when reporting related to both the predicted CMR of Set A and Set A is performed versus when reporting related only to the predicted CMR of Set A is performed, the following embodiments may be considered when Set A is also reported.

[0257] i) When reporting the predicted L1-RSRP of the predicted best CMR in Set A, a step size of 2 dB or more may be applied. For example, the legacy step size may be 1 dB.

[0258] ii) Within Set A (while utilizing a step size of 2 dB or more when reporting the predicted L1-RSRP of the predicted best CMR), a larger step size may be applied for differential reporting when reporting the predicted L1-RSRP of the predicted non-best CMR. For example, according to the legacy standard, the step size for differential reporting is 2 dB, but according to the present embodiment, a step size of 4 dB, 6 dB, or 8 dB may be applied.

[0259] iii) The number of predicted CMRs reported in Set A may be reduced, or reporting for some CMRs in Set A may be omitted (e.g., omit N CMRs with the lowest L1-RSRP values).

[0260] Additionally, the reporting granularity for the (predicted) L1-RSRP in the predicted CMR-related report for Set A and in the report for Set A may differ.

[0261] Alt 5)

[0262] Based on the reportQuantity set by the base station, the terminal may perform reporting as follows. The terminal may report based on Alt 3 to Alt 4, but may report based on Alt 1 when certain conditions are met. This will be explained in detail below.

[0263] Based on the determination by the terminal that the performance of the predicted best beam of Set A, based on UE-sided AI / ML, is below a threshold, the terminal may revert to Alt 1 and perform a report. The terminal may report L1-RSRP values ​​for one or more CMRs associated with Set B.

[0264] The report of Proposal 2 above can be performed using P / SP / A CSI on PUSCH / PUCCH.

[0265] Effects of Proposal 2

[0266] In the above proposal 2, Alt 1 and Alt 2 can be utilized to obtain input data for NW-sided AI / ML (by having the terminal report the actually measured results of Set A / B). In particular, Alt 2 can be helpful in performing AI / ML performance monitoring by comparing the quality of the Set A beam predicted by the base station with the actual quality of the Set A beam.

[0267] In addition, Alt 3 to Alt 5 in the above proposal 2 can be utilized for UE-sided AI / ML. In particular, Alt 4 can be helpful for the base station to perform performance monitoring of UE-sided AI / ML because the terminal compares and reports the predicted Set A beam and the measured Set A beam. Alt 5 can have the effect of reverting to legacy beam management (based on the terminal's decision) by having the terminal perform performance monitoring of UE-sided AI / ML.

[0268] The operations of Proposal 1 and Proposal 2 above are applicable to both spatial domain beam prediction and temporal domain beam prediction. For example, when the operations of Alt 1 to Alt 5 of Proposal 2 above are applied to temporal domain beam prediction, when performing reporting on specific CMRs of Set A and Set B, reports / information on multiple time instances may be included in the report of Proposal 2.

[0269] The above embodiments may be operated by a combination of specific embodiments.

[0270] < Method for UE report on AI / ML model performance monitoring>

[0271] As described above, the Rel-18 AI / ML study item discussed NW / UE-sided AI / ML operations that predict the best beam of Set A based on Set B measurements. In the case of UE-sided AI / ML, an operation in which the terminal measures Set B and reports the predicted Set A beam may be discussed in the Rel-19 AI / ML work item. Methods for such operations were proposed in Proposal 1 and Proposal 2. When performing UE-sided AI / ML beam prediction operations including the examples above, if the terminal's beam prediction performance is poor, operations such as switching the terminal's AI / ML model / functionality or falling back to non-AI / ML-based conventional beam management instead of AI / ML-based beam management may be required.

[0272] Performance monitoring for such AI / ML models is also necessary for network-side AI / ML. In this case, the terminal measures and reports the Set A beam. Subsequently, the actual Set A best beam and the predicted Set A best beam are compared on the network side; if performance falls short of a certain standard, a fallback operation to model / functionality switching or conventional beam management can be performed transparently by the UE.

[0273] In the case of UE-side AI / ML, the terminal can monitor model performance simply by configuring the base station to allow the terminal to measure Set A beam. However, considering the traditional role of a terminal as a slave node, hybrid monitoring—where the terminal reports performance monitoring results to the base station and the base station makes decisions such as model / functionality switching or fallback to conventional beam management (considering system-level / cell-level situations)—can be considered to improve wireless communication reliability. For example, for hybrid monitoring, the terminal can periodically report performance monitoring results to the base station. In addition to such periodic reporting, an event-triggered reporting method can be considered to save resource overhead. Specifically, the terminal may perform reporting only when an event occurs that causes a problem with the prediction performance of the UE-side AI / ML model.

[0274] Based on the background described above, the following examines the performance monitoring method of the terminal-side AI / ML model and the operation by which the terminal reports performance monitoring results to the base station upon the occurrence of a specific event.

[0275] Proposal 3

[0276] When the terminal performs beam prediction operations using UE-side AI / ML, it may report performance monitoring results to the base station indicating that the performance of the AI / ML model has dropped below a standard when events such as the options below occur, in order to monitor the performance of the AI / ML model.

[0277] For example, the actions and agreements related to performance monitoring can be based on the following Table 7.

[0278]

[0279] Option 1)

[0280] An event can be defined based on the difference in RSRP values.

[0281] For example, the condition related to the event may be defined as being satisfied based on the difference between the RSRP value of the actual measured Top-K best beam associated with Set A and the RSRP value of the predicted Top-K best beam associated with Set A (based on the output result of the UE-sided AI / ML model) exceeding a specific threshold. In this specification, the satisfaction of the condition related to the event may be interpreted or substituted as the occurrence of the event.

[0282] For example, if the difference in RSRP value between the Top-1 beam among the actual measured Top-K best beams and the Top-1 beam among the predicted Top-K best beams exceeds a specific threshold, the event may be defined as occurring (it may be defined as the condition related to the event being satisfied).

[0283] For example, if the sum of the differences in RSRP values ​​(K differences in RSRP values) (absolute values) between the actual measured Top-K best beams and the predicted Top-K best beams exceeds a specific threshold, the event may be defined as occurring (it may be defined as the conditions related to the event being satisfied).

[0284] For example, if the sum of the absolute differences (of K values) between the predicted RSRP of the Kth best beam and the actual measured L1-RSRP value of the Kth best beam among the predicted Top-K best beams exceeds a specific threshold, the above event may be defined as occurring (the condition related to the above event may be defined as being satisfied).

[0285] The sum of all K difference values ​​mentioned above can represent sum_(k=1 to K) |predicted RSRP - actual measured L1-RSRP| for k=1, 2, … , K. (|predicted RSRP - actual measured L1-RSRP| is the absolute value of the difference in RSRP values.)

[0286] In the above, the base station may set an error (RSRP) margin value to compensate for temporary measurement errors and prediction errors. Even if the RSRP difference value (or the sum of RSRP difference values) exceeds the specific threshold, the terminal may not determine it as a prediction error if the exceeded value falls within the margin value. As a specific example, it may be assumed that the RSRP difference value (or the sum of RSRP difference values) is greater than the specific threshold by X. If X is less than or equal to the margin value, the terminal may determine that the event according to the present embodiment has not occurred.

[0287] Option 2)

[0288] An event can be defined based on the mismatch of the best beam (Top-1 beam).

[0289] For example, when comparing the actual measured Top-K best beam associated with Set A with the predicted Top-K best beam associated with Set A (based on the output of the UE-sided AI / ML model), a mismatch in the best beam (Top-1 beam) can be defined as satisfying the conditions associated with the event.

[0290] As a specific example, the event may be defined as having occurred based on the fact that the actual measured Top-1 best beam associated with Set A is different from the predicted Top-1 best beam (based on the output result of the UE-sided AI / ML model) (it may be defined as the condition associated with the event being satisfied).

[0291] Option 3)

[0292] An event can be defined based on prediction accuracy.

[0293] For example, when comparing the actual measured Top-K best beam associated with Set A with the predicted Top-K best beam associated with Set A (based on the output of the UE-sided AI / ML model), a condition related to an event can be defined as being satisfied based on the existence of more than K_threshold incorrect answers.

[0294] As a specific example, it can be assumed that among the predicted Top-K best beams, M predicted best beams match M actual measured best beams (corresponding according to RSRP order), and KM predicted best beams differ from KM actual measured best beams (when KM exceeds K_threshold). In this case, whether an event occurs can be determined based on the prediction accuracy set by the base station. The base station may transmit information to the terminal regarding specific beam combinations for which prediction accuracy (e.g., the match between the measured Top-X best beam and the predicted Top-X best beam) must be guaranteed.

[0295] For example, the information may indicate that the measured Top-1 best beam and the predicted Top-1 best beam must match. In other words, the prediction accuracy indicated based on the information may indicate the match of one beam (Top-1 best beam).

[0296] For example, the information may indicate that the measured Top-2 best beams and the predicted Top-2 best beams should match. In other words, the prediction accuracy indicated based on the information may indicate the match of the two beams (Top-2 best beams).

[0297] For example, the information may indicate that the measured Top-3 best beams and the predicted Top-3 best beams should match. In other words, the prediction accuracy indicated based on the information may indicate the match of the three beams (Top-3 best beams).

[0298] It can be assumed that the base station sets K_threshold to 2, and the terminal compares the predicted Top-K best beams with the measured Top-K best beams and detects three discrepancies (e.g., KM (3) > K_threshold (2)). In this case, whether an event based on the present embodiment occurs can be determined as follows.

[0299] For example, if the predicted Top-2 best beams match the measured Top-2 best beams, the terminal may not consider it a prediction error (it may consider it as not satisfying the conditions related to the event).

[0300] For example, if at least one of the predicted Top-2 best beams does not match at least one of the measured Top-2 best beams, the terminal may determine this as a prediction error (it may determine that the event-related condition is satisfied). Specifically, if the first predicted beam among the predicted Top-2 best beams does not match the first measured beam among the measured Top-2 best beams, it may be determined that the event-related condition is satisfied. Specifically, if the second predicted beam among the predicted Top-2 best beams does not match the second measured beam among the measured Top-2 best beams, it may be determined that the event-related condition is satisfied. Specifically, if the predicted Top-2 best beams do not match the measured Top-2 best beams, it may be determined that the event-related condition is satisfied.

[0301] The operation of option 3 above can also be utilized when comparing the actual measured best beam and the predicted best beam for N instances during the temporal domain beam prediction operation. For example, the occurrence of the event of option 3 can be determined based on the (set / defined) N_threshold.

[0302] Option 4)

[0303] An event can be defined based on a confidence level or / and probability.

[0304] For example, conditions related to an event may be defined as being satisfied based on the confidence level or / and probability of the terminal AI / ML model for the predicted best beam (based on the output result of the UE-sided AI / ML model) related to Set A being below a specific threshold.

[0305] An event based on a combination of one or more of the options of Proposal 3 above may be defined. For example, an event may be defined as occurring based on the condition related to Option 1 and the condition related to Option 2 being satisfied together.

[0306] Additionally, for each of the above options, the terminal may report performance monitoring results instantaneously when an event occurs in a single instance performing Set A actual measured beam measurement / reporting (shorter than the reporting period for Set A predicted beam). To account for the occurrence of temporary errors, the terminal may perform performance monitoring result reporting based on a counter. Specifically, a counter (=I) related to the number of event occurrences may be defined. Based on the occurrence of each of the above events at least I times (within a specific time window), the terminal may report performance monitoring results. Through this operation, the reliability of the performance monitoring result reporting can be ensured. Separately from or in addition to the above counter operation, a timer (terminal AI / ML model / functionality-specific) that triggers the reporting of performance monitoring results for a terminal-specific AI / ML model / functionality (equivalent to the above event occurrence condition) is set / defined for the terminal. When the timer expires, the terminal reports the performance monitoring results for that specific AI / ML model / functionality to the base station and performs an operation to reset / restart the timer. If the timer operation is performed in the terminal in addition to the counter operation, the timer that is currently running can be reset / restarted when a performance monitoring result report for a specific AI / ML model / functionality of the terminal is performed due to the occurrence of the event(s) of Proposal 1.

[0307] As an alternative solution to the event definition / setting of Proposal 1 above, the following actions may be performed when 'the terminal determines, based on performance monitoring results, that an abnormality has occurred in the beam prediction function for a specific AI / ML model / functionality' and / or when the terminal wishes to request a fallback to non-predicted beam-based operation (i.e., non-AI / ML based beam management). For the said terminal-specific AI / ML model / functionality, the terminal may operate based on at least one of the following i) to iii).

[0308] i) The terminal can report performance monitoring results to the base station.

[0309] ii) The terminal may perform the operations of Proposal 2 or / and 3 below.

[0310] iii) The terminal can request fallback from the base station using non-predicted beam-based operation (i.e., non-AI / ML based beam management).

[0311] Additionally, regarding the method of reporting the predicted beam associated with Set A and the actual measured beam associated with Set A together, as in Alt 4 of Proposal 2, a method of reporting the number of incorrect answers (number of mismatched beams) rather than reporting the actual measured beam associated with Set A may be considered. As a specific example, the terminal may report i) the predicted Top-K best beam associated with Set A, and ii) the number of predicted beams that are mismatched when comparing the actual measured Top-K best beam with the predicted Top-K best beam.

[0312] For example, regarding the reporting of the number of incorrect answers above, the number of incorrect answers itself may be reported based on the ceil(log2(K)) bit.

[0313] For example, regarding the reporting of the number of incorrect answers, the incorrectness or discrepancy of each beam among the Top-K predicted beams based on the K-bitmap may be reported. Specifically, if the bit value (3rd bit value) of the K-bitmap is 1, it may mean that the predicted beam and the measured beam according to the corresponding order (3) match. Specifically, if the bit value (3rd bit value) of the K-bitmap is 0, it may mean that the predicted beam and the measured beam according to the corresponding order (3) do not match.

[0314] According to one embodiment, the base station can perform performance monitoring of UE-sided AI / ML based on such terminal reports and determine terminal-side AI / ML model / functionality switching or fallback to conventional beam management.

[0315] According to one embodiment, the operation of Alt 5 of Proposal 2 may be performed in combination with Proposal 3. For example, based on the fulfillment of at least one of the options of Proposal 3, the terminal may revert to the reporting operation of Alt 1. When at least one of the options of Proposal 3 occurs, the terminal may revert to an operation according to conventional beam management.

[0316] Proposal 4

[0317] When the event described in Proposal 3 occurs, the terminal can report the terminal AI / ML performance monitoring results to the base station by utilizing the signaling method / medium below.

[0318] Option 1) dedicated SR-PUCCH

[0319] According to one embodiment, an environment in which a NW controls a UE-sided AI / ML model / functionality switching / refine can be assumed. The terminal may report one of the following i) to iv) to the base station based on the 2 bits of the SR-PUCCH codepoint (e.g., 00, 01, 10, 11).

[0320] i) Set A / B beam set change request

[0321] ii) model / functionality switching request

[0322] iii) model / functionality stop / hold request

[0323] iv) Fallback request (to conventional beam management)

[0324] According to one embodiment, an environment may be assumed in which the UE independently performs switching / refine regarding the UE-side AI / ML model / functionality. The terminal may independently switch / stop the model / functionality or stop the AI / ML-based beam prediction.

[0325] The terminal may report one of the following i) to iv) to the base station based on the 2 bits of the SR-PUCCH codepoint (e.g., 00, 01, 10, 11).

[0326] i) model / functionality switching report

[0327] ii) model / functionality stop report

[0328] iii) Hold request / report regarding prediction or model / functionality

[0329] iv) report hold notification

[0330] The above "model / functionality stop report" may mean that the terminal will no longer perform predictions due to beam prediction performance issues and will not perform reports (related to the predictions).

[0331] In the case of the aforementioned "hold request / report regarding prediction or model / functionality" or "report hold notification," it can be interpreted as the terminal reporting to the base station that it "will not make predictions for the time being." After a certain period (agreed upon / conventioned between the base station and the terminal), the terminal may resume prediction operations (after applying a new model or maintenance). Additionally, the aforementioned "hold request / report regarding prediction or model / functionality" or "report hold notification" may also be interpreted as the terminal reporting to the base station that it "will not make reports for the time being." The terminal and the base station may perform actions such as releasing the relevant CSI reporting resources (e.g., PUCCH, PUSCH) for a certain period (agreed upon / conventioned between the base station and the terminal). During this period, the base station may flexibly utilize the relevant time / frequency resources (e.g., allocating the relevant time / frequency resources to other terminals). After the certain period, the terminal may resume beam prediction reporting.

[0332] The terminal can report monitoring results solely through the SR-PUCCH transmission of option 1 above. Therefore, the base station may not allocate a UL grant to the terminal after receiving the SR-PUCCH.

[0333] Option 2) Dedicated SR-PUCCH + PUSCH MAC CE (subject to a subsequent UL grant)

[0334] The terminal can transmit a PUSCH based on the UL grant allocated via SR-PUCCH. The terminal can perform performance monitoring reporting by utilizing the MAC CE message associated with the PUSCH. Specifically, the MAC CE message may include the performance monitoring result values ​​of options 1 to 4 of the above proposal 1 (such as what event occurred and what threshold value was exceeded).

[0335] For example, an environment in which the NW controls the UE-sided AI / ML model / functionality switching / refine, similar to option 1 above, may be assumed. The terminal may transmit the MAC CE message containing information indicating one or more of the following i) to v) to the base station.

[0336] i) Set A / B beam set change request

[0337] ii) model / functionality switching / stop request

[0338] iii) fallback request (to conventional beam management)

[0339] iv) Preferred Set A / B combination

[0340] v) Preferred model / functionality

[0341] For example, an environment may be assumed in which the UE independently performs switching / refine on the UE-side AI / ML model / functionality. (Similar to option 1 above) the terminal may independently switch / stop the model / functionality or stop the AI / ML-based beam prediction. The terminal may transmit the MAC CE message containing information indicating one of the following i) to iv) to the base station.

[0342] i) model / functionality switching report

[0343] ii) model / functionality stop report

[0344] iii) Hold request / report regarding prediction or model / functionality

[0345] iv) report hold notification

[0346] Option 3) UE-initiated CFRA

[0347] Similar to option 1 above, SSB indices related to the following i) to vii) can be predefined / set in the terminal by the base station.

[0348] i) Set A / B beam set change request

[0349] ii) model / functionality switching / stop request

[0350] iii) fallback request (to conventional beam management)

[0351] iv) model / functionality switching report

[0352] v) model / functionality stop report

[0353] vi) Hold request / report regarding prediction or model / functionality

[0354] vii) report hold notification

[0355] When a terminal transmits a PRACH based on a specific SSB index among the above SSB indices, one of the predefined performance monitoring reports between the base station and the terminal (e.g., i) to vii) may be transmitted to the base station. Upon receiving a PRACH based on a specific SSB index among the above SSB indices, the base station determines that a report related to the specific SSB index (e.g., one of i) to vii) has been performed and may perform a subsequent operation related thereto.

[0356] The terminal can report monitoring results by transmitting only a PRACH. For example, the base station may not transmit a RAR to the terminal after receiving the PRACH (RAR transmission omitted). For example, the base station may transmit a RAR scheduling DCI and a RAR PDSCH. The RAR MAC CE of the RAR PDSCH may not include a UL grant.

[0357] Option 4) PRACH + Msg 3 PUSCH MAC CE (by UL grant of the subsequent RAR MAC CE)

[0358] In a manner similar to option 2 above, the terminal may transmit a PUSCH based on an allocated UL grant via (CBRA / CFRA) PRACH transmission. The terminal may perform performance monitoring reporting by utilizing a MAC CE message associated with the PUSCH. Specific embodiments regarding the method of configuring the MAC CE message may be the same as those in option 2.

[0359] In the above options, the terminal can report event details (e.g., the event of Proposal 1) that occurred in a specific AI / ML model / functionality and / or the corresponding performance monitoring results (e.g., the accuracy / error rate of the predicted beam in Proposal 1, the difference in RSRP value between the predicted beam and the actual measured beam, and the confidence level and / or probability, etc.) by utilizing a PUSCH scheduled after SR-PUCCH or CFRA.

[0360] Effects of the above Proposals 3 and 4

[0361] The terminal can report the performance monitoring results for the terminal AI / ML model / functionality of Proposal 4 to the base station only when the event of Proposal 3 occurs. This allows for a reduction in resource overhead. Based on the terminal's AI / ML monitoring results, the base station can decide on model / functionality stop / switching or fallback to a legacy BM (if the base station manages the terminal's AI / ML model / functionality). In particular, as in option 1 of Proposal 4, if there is a problem with beam prediction performance when the terminal manages its own AI / ML model / functionality, the terminal can temporarily suspend prediction and reorganize. Since reporting resources are released and can be allocated to other terminals while the terminal's prediction is suspended, the flexibility of resource utilization can be increased.

[0362] The performance monitoring reporting method of Proposal 4 above can also be utilized for performance monitoring reporting using periodic / static resources rather than event-triggered actions.

[0363] Proposal 5

[0364] (When the event described in Proposal 3 occurs) the terminal may transmit a report (e.g., a monitoring result report) to the base station. At this time, based on the report, a switch of the relevant Set A configuration regarding a specific AI / ML model / functionality (related to beam management) may be requested from the base station. In other words, the report may include information indicating a switch of the Set A configuration.

[0365] More specifically, the base station can set one or more candidate values ​​for Set A. The terminal can perform model inference based on the Set B settings associated with a specific Set A. If a performance anomaly occurs, the terminal can provide feedback (event-based) on a preferred Set A index among the candidate values.

[0366] As one of the candidate values ​​of the above Set A, a default Set A (e.g., Set A index #0) (related to non-AI / ML based beam management) can be set / defined. The terminal can request a fallback to non-AI / ML based beam management by feeding back this default Set A to the base station.

[0367] For example, if there are about 2 to 4 candidate values ​​for Set A, a switch / fallback request or feedback (e.g., monitoring report) for the terminal's Set A settings can be transmitted to the base station in the form of a new UCI type based on PUCCH format 0 / 1.

[0368] For example, a switch / fallback request for a terminal's Set A configuration or such feedback (e.g., monitoring report) can be transmitted to a base station using SR-PUCCH, similar to Proposal 2 above. Each index of the Set A candidate values ​​can be encoded in 2 bits of SR-PUCCH. As described above, when a terminal requests a switch for a Set A configuration to a base station in the form of a new UCI type or requests a switch for a Set A configuration to a base station using SR-PUCCH, a candidate Set A identical to Set B may be indicated among the candidate values ​​of Set A configured by the base station.

[0369] Specifically, the Set A indices encoded in the SR-PUCCH 2 bits may include Set A indices related to non-AI / ML based beam management or / and Set A indices having the property that Set A = Set B. When a terminal requests / feedback the said Set A index to a base station through the method of Proposal 5, the said feedback (monitoring report) may signify a request for fallback to non-AI / ML based beam management. In other words, the base station may interpret the said feedback (monitoring report) as a request for fallback to non-AI / ML based beam management and operate accordingly.

[0370] For example, i) multiple Set A candidate values ​​set by the base station may each be associated with different CSI-reportConfigs. For example, ii) multiple Set A candidate values ​​set by the base station may simultaneously be associated with a single CSI-reportConfig.

[0371] In the case of Method ii, the number of beams / CMRs (e.g., number of CRIs / SSBRIs) configured / existing within each of the multiple Set As may differ. Therefore, when a base station changes and configures Set A in response to a terminal's request to change the Set A configuration, a problem may arise in which the number of bits required to represent the CRI / SSBRIs reported through the corresponding single CSI-reportConfig differs. For example, in the case of a Set A having the property that Set A = Set B, the number of beams / CMRs may be fewer than that of other Set As. To prevent this problem, the number of bits required to represent the CRI / SSBRIs may be determined based on the Set A containing the maximum number of beams among the multiple Set As (the Set A with the most beams).

[0372] For example, a bit size of log2 (number of beams / CMRs in Set A containing the maximum number of beams) may be required to represent CRI / SSBRI. In this case, for Set A candidates other than the Set A containing the beam with the maximum value, CRI / SSBRI is represented using the bit size proposed above, and the following embodiment may be considered.

[0373] CRI / SSBRI can be expressed by utilizing only as many codepoints as the number of beams included in each Set A, starting from the LSB. This is explained in detail using an example where Sets A #0~2 have 16 beams and Set A #3 has 4 beams. In the case of Sets A #0~2, all 4 bits can be utilized to express CRI / SSBRI. In the case of Set A #3, only 4 codepoints out of the 4 bits—0000, 0001, 0010, and 0011 starting from the LSB—can be utilized to express CRI / SSBRI.

[0374] In the above example, if the terminal uses a codepoint other than the four codepoints 0000, 0001, 0010, and 0011 when beam reporting for the CRI / SSBRI representation of Set A #3, the base station may recognize / interpret it as an error case. Specifically, the base station may ignore the beam report for the corresponding CRI / SSBRI local index of Set A #3.

[0375] When a switch / fallback request or feedback of the Set A setting of Proposal 3 above is reported based on a new UCI type, an additional priority based on at least one of the following embodiments may be set / defined relative to the terminal operation related to CSI priority described in Table 8 below.

[0376]

[0377] Example 1) Beam-related CSI = Report (monitoring report) of Proposal 5 above = / > predicted Set A beam-related CSI (inference report) > non-beam-related CSI

[0378] Example 2) beam-related CSI > monitoring report of Proposal 5 above = / > predicted Set A beam-related CSI (inference report) > non-beam-related CSI

[0379] Example 3) Monitoring report of Proposal 5 above = / > predicted Set A beam-related CSI (inference report) > beam-related CSI > non-beam-related CSI

[0380] Example 4) Monitoring report of Proposal 5 above = / > predicted Set A beam-related CSI (inference report) > beam-related CSI = measured Set A / B beam-related CSI > non-beam-related CSI

[0381] Example 5) Measured Set A / B beam-related CSI = beam-related CSI > Report (monitoring report) of Proposal 5 above = / > Predicted Set A beam-related CSI related CSI (inference report) > non-beam-related CSI

[0382] Example 6) Regarding the priority of the CSI-reporConfig level, the report of Proposal 5 may have a higher priority if it conflicts with a CSI report directed based on the existing legacy CSI report config. If the report of Proposal 5 conflicts with the LTM-CSI report config, the report of Proposal 5 has a lower priority than the report based on the LTM-CSI report config. Alternatively, the report of Proposal 5 may have a lower priority than both the legacy CSI report config and the LTM-CSI report config.

[0383] In the embodiments described above, 'beam related CSI' refers to a CSI report carrying L1-RSRP or L1-SINR of Table 8. 'non-beam related CSI' refers to a CSI report not carrying L1-RSRP or L1-SINR of Table 8. For example, the value (k) for determining the priority value may vary based on the above embodiments 1 to 6. It will be explained in detail below with reference to embodiment 1.

[0384] For example, referring to Example 1, the monitoring report and / or predicted Set A beam related CSI (inference report) of Proposal 5 may have a higher priority than a CSI report that does not include L1-RSRP or L1-SINR. Specifically, a value for determining the priority value associated with the monitoring report and / or predicted Set A beam related CSI (inference report) of Proposal 5 (e.g., k=0) may be lower than a value for determining the priority value associated with a CSI report that does not include L1-RSRP or L1-SINR (e.g., k=1).

[0385] For example, referring to Example 1, the monitoring report and / or predicted Set A beam related CSI (inference report) of Proposal 5 may have the same priority as the CSI report containing L1-RSRP or L1-SINR. Specifically, the value for determining the priority value associated with the monitoring report and / or predicted Set A beam related CSI (inference report) of Proposal 5 (e.g., k=0) may be the same as the value for determining the priority value associated with the CSI report containing L1-RSRP or L1-SINR (e.g., k=0).

[0386] As in Proposals 4 and 5 above, when a terminal utilizes SR-PUCCH to report / request performance monitoring results for terminal-specific AI / ML functionality, the following matters may be considered. From the perspective of the base station, it can be expected that the terminal will require UL-SCH allocation. However, from the perspective of the terminal, UL-SCH may not be necessary if there is no more information to send. To enable the base station to determine whether UL-SCH is needed by the terminal, the following embodiment may be considered. A specific dedicated SR PUCCH resource may be allocated for SR-PUCCH transmission such as in Proposals 4 and 5 above.

[0387] On the other hand, after an SR-PUCCH transmission such as Proposal 4 and Proposal 5, the terminal can transmit subsequent information (e.g., details regarding performance monitoring output, etc.) to the base station based on MAC-CE. In this case, the SR-PUCCH such as Proposal 4 and Proposal 5 can share SR PUCCH resources of a general logical channel (e.g., SR PUCCH resource requesting UL-SCH resources for new transmission) similar to BFR.

[0388] For example, when a terminal reports such as Proposal 4 and Proposal 5 using SR-PUCCH, the terminal may report to the base station via the SR-PUCCH an indicator indicating whether a subsequent UL-SCH is required. The base station may schedule or not schedule the UL-SCH depending on the terminal's instruction (UL-SCH required / unnecessary).

[0389] In the case of the latter in the above paragraph (an operation in which an SR-PUCCH such as Proposal 4 and Proposal 5 shares the SR PUCCH resource of a general logical channel), additional priority-related operations may be set / defined in relation to legacy operations in which an SR for BFR has priority relative to other SRs as shown in Table 9 below.

[0390]

[0391] For example, a pending SR related to SR-PUCCH, such as in the above proposals 4 and 5, may have a higher priority than other SRs. A pending SR related to SR-PUCCH, such as in the above proposals 4 and 5, may have a lower priority than a pending SR related to BFR (SR for SCell beam failure recovery and / or SR for beam failure recovery of a BFD-RS set of Serving Cell).

[0392] Effect of Proposal 5 above: If an abnormality in performance occurs while performing performance monitoring on a specific AI / ML model / functionality of the terminal, the terminal can request the base station to change to (preferred) Set A. In other words, the terminal can request the base station to utilize a model / functionality with better inference performance. Additionally, it can request a fallback to conventional beam management operation. More specifically, in situations where the performance of AI / ML-based beam management is very poor, the performance of beam management can be managed through fallback to maintain it above a certain level.

[0393] Proposal 6

[0394] The base station may configure a Set X for performance monitoring purposes for the terminal to monitor the performance of a terminal-specific AI / ML model / functionality. For example, the Set X may be configured in a separate CSI-reportConfig (e.g., a separate report configuration for monitoring). In other words, a report configuration (CSI-reportConfig) related to performance monitoring (prediction accuracy) may include information regarding the Set X. For example, the Set X may be configured in a report configuration (CSI-reportConfig) related to Set A / Set B. In other words, a report configuration (CSI-reportConfig) related to measurement / prediction may include information regarding the Set X.

[0395] The above Set X may have the property that it is a subset of Set A. This will be explained in detail below.

[0396] For example, the above Set X can be mapped to a subset with the same size as Set A (e.g., X) (e.g., if the size of Set A is X1, the size of Set X is X2=X1). In this case, each resource in Set X can correspond one-to-one with each resource in Set A. Specifically, the nth resource in Set X can be mapped to the nth resource in Set A.

[0397] For example, the above Set X can be mapped to a subset smaller than the size of Set A (e.g., if the size of Set A is X1, the size of the above Set X is Y). <X1). 이러한 경우, 상기 Set X의 Y개의 자원들이 Set A의 X1개의 자원들(예측을 위한 X1개의 자원들)에 매핑될 수 있다. 구체적인 예로, 상기 Set X에 대한 정보는 비트맵에 기초하여 설정될 수 있다(예: bitmap with Y non-zero bits among X1 bits).

[0398] For example, the number of beams (number of resources) of the above Set X may be greater than the number of beams (number of resources set for measurement) of Set B.

[0399] For example, one or more Set Xs associated with a specific Set A may be configured. The base station may instruct the terminal to use a specific Set X among the one or more Set Xs for terminal AI / ML model / functionality performance monitoring.

[0400] Effect of the above proposal 6: In preparation for setting a full set of Set A for performance monitoring of the terminal AI / ML model / functionality, overhead between the base station and the terminal can be reduced through the setting of Set X. In addition, overhead for the DL RS transmitted by the base station for actual performance monitoring can also be reduced. Furthermore, regarding the above-mentioned Set X setting, the base station can perform the Set X setting based on the trend of the terminal reporting a predicted Set A beam based on AI / ML prior to the current point in time by the base station implementation.

[0401] Below, specific embodiments related to constraints on metric methods that can be utilized for performance monitoring of UE-sided AI / ML models supported by the terminal are described.

[0402] In the beam management agenda of the Rel-19 AI / ML WI, discussions on standardization are underway regarding the operation of reporting inference results obtained by performing beam prediction using UE-sided AI / ML models. The inference result reporting method may be based on the following agreement.

[0403] Fundamentally, the inference of a terminal UE-sided AI / ML model assumes an operation that utilizes input data based on measurements from the Set B beam set to generate the top K beams within the Set A beam set (the beam set for prediction) as output data. In this process, cases are considered where the Set B beam set is a subset of the Set A beam set, or where the Set B and Set A beam sets are distinct sets (e.g., where Set B consists of beams with wide beamwidths and Set A consists of beams with narrow beamwidths).

[0404] The details of the agreement related to this are as shown in Table 10 below.

[0405]

[0406] According to the above agreement, Opt 1 / 2 may be utilized as follows.

[0407] For example, in the case of Opt 1, it can be utilized when the terminal uses a classification model as the algorithm of a UE-sided AI / ML model. For example, in the case of Opt 2, it can be utilized when the terminal uses a regression model (which calculates the predicted RSRP value) as the algorithm of a UE-sided AI / ML model.

[0408] In addition, as shown in the agreement below (Table 11), it was agreed that the Type 1 performance monitoring (Option 2) method is supported during beam prediction operations based on the terminal's UE-sided AI / ML model. Specifically, according to the Option 2 method of Type 1 performance monitoring, the terminal calculates a metric and reports it to the base station for performance monitoring of the terminal-side AI / ML model. Furthermore, to determine this metric, discussions are underway regarding the metric definition methods for Alt 1 to Alt 4, as shown in the second agreement below (Table 11).

[0409]

[0410] Based on this background, we propose a method for determining the metrics (i.e., Alt 1 to Alt 4) supported by the terminal when reporting performance monitoring for a UE-sided AI / ML model based on the inference result report reporting method (i.e., Opt 1 to Opt 4) supported by the terminal in Rel-19 AI / ML beam management.

[0411] Proposal 7

[0412] A method for determining the metrics (i.e., Alt 1 to Alt 4) supported by the terminal when reporting performance monitoring for a UE-sided AI / ML model based on the inference result report reporting method (i.e., Opt 1 to Opt 4) supported by the terminal.

[0413] Example 1)

[0414] The terminal can support an inference result report method corresponding to the above Opt 1 (Beam information on predicted Top K beam(s) among a set of beams).

[0415] The terminal can only support a UE-sided AI / ML model performance monitoring method based on metrics corresponding to Alt 1 or / and Alt 2 in the above metric discussion.

[0416] Specifically, if the terminal indicates through UE capability reporting that only the inference result report method for Opt 1 is supported, the base station may configure / instruct the terminal to perform performance monitoring reporting using metrics corresponding to Alt 1 or / and Alt 2. The base station may not configure / instruct the terminal to perform performance monitoring reporting using metrics other than Alt 1 or / and Alt 2.

[0417] This embodiment takes into account the following technical considerations. Since the terminal supporting Opt 1 utilizes an AI / ML model that cannot calculate predicted RSRP, it is impossible to calculate metrics other than Alt 1 or / and Alt 2. Therefore, the terminal can perform performance monitoring reporting based on Embodiment 1.

[0418] Example 2)

[0419] The terminal can support an inference result report method corresponding to the above Opt 2 (Beam information on predicted Top K beam(s) among a set of beams and RSRP of predicted Top K beam(s) among a set of beams).

[0420] For example, the terminal may support a performance monitoring method based on a metric corresponding to Alt 3 in addition to a UE-sided AI / ML model performance monitoring method based on a metric corresponding to Alt 1 or / and Alt 2 in the above metric discussion.

[0421] For example, if the terminal additionally reports UE capability for Alt 4, the terminal may support a performance monitoring method based on metrics corresponding to Alt 4.

[0422] This embodiment takes into account the following technical considerations. In the case of a terminal supporting Opt 2, since it utilizes an AI / ML model capable of calculating predicted RSRP, it is possible to calculate metrics for Alt 3 or Alt 4 in addition to Alt 1 or / and Alt 2. Accordingly, the terminal can perform performance monitoring reporting based on Embodiment 2.

[0423] Example 3)

[0424] The terminal may support an inference result report method corresponding to the Opt 3 (Beam information on predicted Top K beam(s) among a set of beams and probability information of predicted Top K beam(s) among a set of beams) or / and Opt 4 (Beam information on predicted Top K beam(s) among a set of beams, RSRP of predicted Top K beam(s) among a set of beams, and confidence information of the RSRP).

[0425] The terminal can support a UE-sided AI / ML model performance monitoring method based on all metrics (Alt 1 to Alt 4), including Alt 4, among the metrics discussed above.

[0426] The effects derived from the embodiments of Proposal 7 above are as follows.

[0427] The metric that can be calculated varies depending on the inference result report method. Based solely on the UE capability report for the inference result report method (without reporting the UE capability for the performance monitoring method), the base station can identify the performance monitoring method that can be supported for the terminal's UE-sided AI / ML model and set / instruct the performance monitoring report. Since there is no need for the UE capability for the performance monitoring method to be separately / additionally set / defined and reported, this embodiment has advantages in terms of implementation complexity of procedures related to performance monitoring and signaling overhead.

[0428] As another embodiment of Proposal 7, in order for a terminal to report a UE capability that allows metric reporting for Alt 3, it may need to support a UE capability for Opt 2 in the form of a prerequisite. Or / and, in order for a terminal to report a UE capability that allows metric reporting for Alt 4, it may need to support a UE capability for Opt 2 / Opt 3 / Opt 4 in the form of a prerequisite.

[0429] Proposal 8

[0430] Below, we examine the following when a performance monitoring report for a UE-sided AI / ML model is performed (based on the metrics of Alt 1 to Alt 4) in a BM-case 2 environment where the terminal performs temporal beam prediction: i) the method of defining the metric, ii) the method of calculating Z / Z' / CPU, and iii) the method of defining the event for event-based performance monitoring reporting.

[0431] Example 1)

[0432] In BM-case 2, based on a reporting method in which the terminal reports the predicted top K beam or / and the corresponding predicted RSRP for each instance of multiple future instances (multiple future time instances), the terminal may operate according to the following i) or ii) when reporting performance monitoring for UE-sided AI / ML (based on base station configuration / instruction).

[0433] i) The terminal may calculate and report metrics for at least one specific future instance (e.g., if metrics are calculated and reported for a single future instance, it becomes identical to the performance monitoring reporting method of BM-case 1).

[0434] ii) The terminal can perform performance monitoring reporting by calculating metrics for all future instances configured by the base station (e.g., the payload can be calculated by multiplying the payload of the performance monitoring reporting method of BM-case 1 by the number of all future instances).

[0435] In the case of the above method ii), the absolute amount of metrics to be calculated and the amount of metrics to be reported may increase. The above method i) has the advantage of reducing overhead in terminal calculation / reporting and enabling the base station to perform performance monitoring because it performs metric calculation / reporting for some future instances based on base station settings / instructions.

[0436] Example 2)

[0437] For example, Z and Z' values ​​greater than the previously defined Z and Z' values ​​(Table 12) can be set / defined for RSRP-related CSI reports for performance monitoring reporting of UE-sided AI / ML models of terminals.

[0438]

[0439] For example, Z and Z' values ​​corresponding to SINR-related CSI reports can be set / defined as shown in Table 13 below for performance monitoring reporting of the UE-sided AI / ML model of the terminal (considering the greater amount of computation for metric calculations, such as calculating the difference between RSRP values ​​and the computation time for simply measuring RSRP values).

[0440]

[0441] For example, the Z and Z' values ​​for the performance monitoring report can be set / defined through the terminal (new) capability report. The newly defined Z / Z' values ​​can be determined as (Z / Z' + alpha), which is the value obtained by adding an offset value alpha to the legacy values. For example, the alpha value can be expressed as the legacy Z / Z' multiplied by a specific scaling value (beta) (e.g., new Z / Z' = Z / Z' + Z / Z' * beta). For example, the scaling value can be determined based on the number of future instances and / or the maximum number of beams reported per instance. For example, the scaling value (beta) can be a value determined based on the terminal's capability.

[0442] As an additional embodiment, a method may be considered in which the Z and Z' values ​​increase in proportion to the number of metrics reported during performance monitoring reporting.

[0443] Example 3)

[0444] Performance monitoring reports for UE-sided AI / ML models on the terminal are

[0445] For RSRP / SINR related CSI reports, more CPUs (multiple CPUs) than the previously defined CPUs (Table 14) can be occupied.

[0446]

[0447] For example, performance monitoring reports can have the same CPU value as existing RSRP / SINR-related CSI reports.

[0448] For example, different Z, Z', and CPU counts may be required depending on whether it is a performance monitoring report for spatial domain DL Tx beam prediction or a performance monitoring report for temporal DL Tx beam prediction. Specifically, the Z, Z', and CPU counts for a performance monitoring report for temporal DL Tx beam prediction (e.g., the first value) may be greater than the Z, Z', and CPU counts for a performance monitoring report for spatial domain DL Tx beam prediction (e.g., the second value). Specifically, the Z, Z', and CPU counts for a performance monitoring report for temporal DL Tx beam prediction (e.g., the first value) may be smaller than the Z, Z', and CPU counts for a performance monitoring report for spatial domain DL Tx beam prediction (e.g., the second value).

[0449] For example, the number of Z, Z', and CPUs for performance monitoring reporting for temporal DL Tx beam prediction can be determined by adding or multiplying the number of Z, Z', and CPUs for performance monitoring reporting for spatial domain DL Tx beam prediction by an offset value (or vice versa).

[0450] As an additional embodiment, when reporting performance monitoring, the number of CPUs may increase in proportion to the number of metrics reported by the terminal. In other words, the number of CPUs for performance monitoring reporting may be determined based on the number of metrics reported by the terminal.

[0451] Example 4)

[0452] When reporting on performance monitoring for a UE-sided AI / ML model of a terminal, the CPU occupancy timeline (time interval during which CPU(s) are occupied) may be defined based on one of the following i) to iv). More specifically, CPU(s) may be occupied from a point in time based on one of the following i) to iv) until the time of the performance monitoring report.

[0453] i) From the first symbol of the (historical) beam measurement CMR during Set B measurement for inference reporting to the time of performance monitoring reporting

[0454] ii) From the time of reporting inference results to the time of reporting performance monitoring

[0455] iii) When measuring a resource set for monitoring purposes, from the first symbol of the beam measurement CMR to the time of performance monitoring reporting

[0456] iv) From the time of base station configuration / instruction for performance monitoring to the time of performance monitoring reporting

[0457] Example 5)

[0458] According to Option 4) of Proposal 3, event-based performance monitoring reporting is performed. Specifically, by setting counter = I, the terminal can report performance monitoring results if a specific event occurs I or more times (within a specific time window). At this time, the counter associated with the occurrence of the event can be calculated / determined as follows.

[0459] A new method for calculating a counter by considering BM-case 2, which performs temporal beam prediction, is proposed.

[0460] For example, a counter=I may be set / defined for the case where an event in which the metrics of the above Alt 1 to Alt 4 increase / decrease to a specific threshold or fall below a specific threshold occurs in at least one specific time instance among future time instances for inference reporting (based on base station settings / instructions). Based on the said counter, the terminal may perform an event-based performance monitoring report if the said event occurs I or more times (within a specific time window).

[0461] For example, a counter = I may be set / defined for the event in which the metric of the above Alt 1 to Alt 4 increases / decreases to a specific threshold or falls for N or more instances among future time instances for inference reporting (the natural number N value is defined in the specification or set by the base station, including N = every future time instances). Based on the said counter, the terminal may perform event-based performance monitoring reporting if the said event occurs I or more times (within a specific time window).

[0462] Meanwhile, the Rel-18 AI / ML study discussed NW / UE-sided AI / ML operations that predict the best beam of Set A based on Set B measurements. In the case of UE-sided AI / ML, the terminal needs to measure Set B and report the predicted Set A beam, whereas in the case of NW-sided AI / ML, the terminal needs to report the Set B measurements.

[0463] The standardization agreements for UE-sided AI / ML to date are as follows.

[0464] Agreement

[0465] For UE-side models, at least for BM-Case1, the following is supported regarding the content of the inference result report.

[0466] Option 1: Beam information for the predicted Top K beams within the beam set

[0467] Option 2: Beam information for the predicted Top K beams within the beam set, and the RSRP of the predicted Top K beams

[0468] At least K=1, and for the maximum value, use FFS

[0469] For beam information, FFS

[0470] For the definition of the predicted Top K beam, FFS

[0471] For the definition of the reported RSRP where applicable, FFS

[0472] For other information within the report along with potential down selections among the following options, FFS

[0473] Option 3: Beam information for the predicted Top K beams within the beam set, and probability information for the predicted Top K beams

[0474] Regarding the quantization method of probability information, FFS

[0475] The probability information is the probability that the beam will become the Top 1 or Top K beam.

[0476] Option 4: Beam information for the predicted Top K beams within the beam set, the RSRP of the predicted Top K beams, and the reliability information of the corresponding RSRPs

[0477] Regarding the definition of the reported RSRP, FFS

[0478] Regarding the definition of reliability information and quantization methods, FFS

[0479] Other options are not excluded either.

[0480] Here, the beam set is Set A, which refers to the beams for UE prediction.

[0481] Conclusion

[0482] For the UE-side model, at least during inference, the configuration of Set B (Set B) for measurement is taken from the current CSI framework.

[0483] Agreement

[0484] Regarding UE-side AI / ML model inference, in the case of BM-Case2, one report supports reporting inference results for N (N≥1, FFS for N) future time points.

[0485] The inference result information for a given point in time is identical to one report in BM-Case1.

[0486] Note: Overhead reduction is not excluded.

[0487] Details are on FFS.

[0488] Agreement

[0489] Regarding the RSRP of the predicted Top K beam among the inference result reports for the UE-side model of BM-Case1, if applicable, the following options are additionally investigated.

[0490] Option A: Predicted RSRP

[0491] Option B: Predicted RSRP if the beam is not configured for the corresponding measurement, measured L1-RSRP if the beam is configured for the corresponding measurement

[0492] The predicted RSRP is based on the AI / ML output.

[0493] Note: Supporting both Option A and Option B is not excluded.

[0494] Agreement

[0495] For the UE-side model, at least for BM Case-1, CSI-ReportConfig is used for the inference result reporting configuration.

[0496] For details within CSI-ReportConfig, consider FFS, at a minimum, the following:

[0497] Alternative 1: One CSI-ResourceConfigId is configured for Set B.

[0498] FFS: How can the UE determine information about Set A?

[0499] Alternative 2: A single CSI-ResourceConfigId is configured for both Set A and Set B

[0500] FFS: How to configure resource sets of Set A and Set B in CSI-ResourceConfig

[0501] Alternative 3: Separate CSI-ResourceConfigIds are configured for Set A and Set B, respectively.

[0502] Alternative 4: A single CSI-ResourceConfigId is configured for Set B, and Set A is configured using a separate set of resources not represented by the CSI-ResourceConfigId.

[0503] FFS: How to configure / direct a separate set of resources for Set A

[0504] Note: Using separate CSI-ReportConfigs for Set A and Set B is also not excluded.

[0505] Note: Measurements are not performed for Set A, and are performed only for Set B according to CSI-ReportConfig.

[0506] Regarding the association between Set A and Set B, regardless of the presence or absence of additional IE, FFS.

[0507] Other necessary components are not excluded.

[0508] Agreement

[0509] The following working assumptions have been established.

[0510] Working Assumption

[0511] In the inference result report for the UE-side model of BM-Case 2, the predicted RSRP of the beam is the predicted RSRP, and this predicted RSRP is based on the AI / ML output.

[0512] Agreement

[0513] For UE-side models, at least for the quantization of RSRP values ​​in inference result reports, the following is supported:

[0514] Support for differential RSRP reporting using existing quantization steps and ranges for L1-RSRP reporting

[0515] For BM-Case1, differential RSRP reporting between multiple beams is supported.

[0516] For BM-Case2, support for differential RSRP reporting between multiple beams across multiple time points.

[0517] Details are FFS

[0518] Agreement

[0519] For the UE-side model, at least in the case of BM Case-1, in the inference result report

[0520] In the CSI report configuration, two resource sets can be configured separately for Set A and Set B.

[0521] Whether to support configuring a resource set solely for Set B is FFS.

[0522] The UE performs measurements on the resource set of Set B for inference, and the UE is not expected to measure the resource set of Set A for inference.

[0523] The beam information in the inference report refers to the resource set of Set A.

[0524] Agreement

[0525] With respect to the UE-side AI / ML models in BM-Case1 and BM-Case2, **Option 2 (UE-supported performance monitoring)** shall be further reviewed, including at least the following alternatives:

[0526] Alternative 1: Compare the Top 1 or Top K beams based on prediction results and measurements from resource sets / resources for monitoring, along with the presence or absence of margins for Top 1 or Top K beam prediction accuracy.

[0527] Alternative 2: Resource set for actual L1-RSRP measurements of one or more predicted Top K beams and monitoring / L1-RSRP difference information based on L1-RSRP measurements from resources

[0528] Alternative 3: RSRP difference information between the predicted RSRP and the measured L1-RSRP of the resource set / corresponding beam(s) of the resource for monitoring

[0529] Note: Resources of Set B for monitoring are not excluded and can be studied.

[0530] Note: This applies only if the model can predict RSRP.

[0531] Alternative 4: Probability information that the predicted beam(s) will become the Top 1 or Top K beams

[0532] Note: This applies only when the model can generate probability information.

[0533] FFS: For Alternatives 1 / 2 / 3, further review the details regarding how to configure resource sets / resources for monitoring.

[0534] Example: Whether / method to use the entire set of Set A for measurement. If not used, how to acquire measurements from the predicted Top 1 or Top K beams to calculate prediction accuracy or RSRP difference.

[0535] For all alternatives, we investigate whether performance information is calculated on a sample-by-sample basis (one-shot) or on a sample set basis (window).

[0536] Agreement

[0537] For the UE-side model of BM-Case 2, to report inference results, NW supports configuring the UE for N future points in time where applicable.

[0538] FFS: How to determine the reference time for those points in time

[0539] FFS: Predictable duration value at time N

[0540] In addition, Opt1 utilizing Associated ID was agreed upon to ensure consistency between training and inference during beam prediction operations using UE-sided AI / ML, as shown in Table 15 below. Discussions are scheduled to proceed regarding where the associated ID will be set and what assumptions (UE assumptions) a terminal can make when having the same associated ID.

[0541]

[0542] Based on this background, we propose a method to ensure consistency between training and inference during AI / ML operations on the terminal side, and propose subsequent terminal operations. In particular, we describe a proposal regarding what similar properties the terminal can assume regarding the similar properties of a DL Tx beam or beam set / list associated with the same associated ID.

[0543] Proposal 9

[0544] Proposal for the definition of similar properties for a DL Tx beam within a specific beam set / list or / and beam set that a terminal can assume when the DL Tx beam within the beam set is assigned the same associated ID from a base station.

[0545] Proposal 9-1

[0546] When the same associated ID is assigned between a specific beam set / list or between different beam sets / lists, the similar properties that the terminal can assume between the beam sets / lists may be the following attributes.

[0547] Example 1)

[0548] In the case of the same associated ID, it can be assumed that the relationship between Set A and Set B (e.g., Set B is a subset of Set A, Set B and Set A are different, etc.) is maintained by the base station. More specifically, if Set B is a subset of Set A, it can be assumed that the terminal maintains ratios such as 1 / 2, 1 / 4, 1 / 8, 1 / 16, ..., 1 / N (N is a natural number greater than or equal to 2). For example, it can be assumed that the terminal maintains the Xth ratio (X is a natural number less than or equal to N) within the ratios.

[0549] For example, an associated ID can be assigned / configured together (with the same ID) to a beam / resource set for Set A and a beam / resource set for Set B.

[0550] For example, an associated ID can be assigned / configured to a CSI-ReportConfig or CSI-ResourceConfig that is configured / connected with a beam / resource set for Set A and a beam / resource set for Set B.

[0551] Example 2)

[0552] The terminal can assume that the number of horizontal beams and vertical beams of Set A or / and Set B (in base station global / local coordination) are maintained (identical) by the base station.

[0553] For example, an associated ID can be assigned / set to a beam / resource set for Set A or a beam / resource set for Set B, respectively.

[0554] For example, an associated ID can be assigned / set together (with the same ID) to a beam / resource set for Set A and a beam / resource set for Set B.

[0555] Proposal 9-2

[0556] When the same associated ID is assigned between DL Tx beams within a specific beam set or between different DL Tx beams, the similar properties that the terminal can assume between DL Tx beams within that beam set / list or between those different DL Tx beams may be the following attributes.

[0557] Example 1)

[0558] The terminal may assume that the spatial downlink transmission filter or / and (analog) beam coefficients utilized / applied by the base station for forming the DL Tx beam are maintained identically / similarly by the base station.

[0559] Example 2)

[0560] The terminal can assume that the 3 dB beam width of the corresponding DL Tx beam is maintained identically or similarly by the base station.

[0561] Example 3)

[0562] The terminal can assume that the beam angle of the corresponding DL Tx beam (main lobe) is maintained identically or similarly by the base station.

[0563] Example 4)

[0564] The terminal can assume that the degree of (Tx power) suppression for the side lobe of the corresponding DL Tx beam is maintained by the base station to be the same or similar.

[0565] Information regarding how similar the embodiments of Proposal 9-1 or / and Proposal 9-2 are can be signaled from the base station to the terminal.

[0566] For example, in the case of Example 2, the base station may transmit information to the terminal indicating that the 3 dB beam width difference between the DL Tx beam or the different DL Tx beams that can be judged to be similar is within A degree (where A is a real or natural number).

[0567] For example, in the case of Example 3, the base station may transmit information to the terminal indicating that the difference in beam angle between the DL Tx beam or the different DL Tx beams that can be judged to be similar is within B degrees (where B is a real number or a natural number).

[0568] For example, in the case of Example 4, the base station may transmit information to the terminal indicating that the maximum power difference for a side lobe that can be judged to be similar between the DL Tx beam or the different DL Tx beams is within C dB (where C is a real or natural number).

[0569] For example, if the same associated ID is assigned / set for the beam set / list to which the DL Tx beam(s) belong, the terminal can operate for the DL Tx beam(s) based on the embodiments of Proposal 9-2.

[0570] For example, if the same associated ID is assigned / set for different beam sets / lists to which different DL Tx beam(s) belong, the terminal can operate with respect to the different DL Tx beam(s) based on the embodiments of Proposal 9-2.

[0571] An example of a terminal (or base station) operation based on at least one of the aforementioned embodiments (e.g., at least one of the embodiments of Proposal 9) is as follows.

[0572] 1) The terminal (base station) receives (transmits) settings related to beam measurement / reporting.

[0573] The above settings may include reporting settings related to Set A and Set B.

[0574] Depending on whether an associated ID is set in relation to Set A and Set B, the terminal may assume the UE assumption of Proposal 9 above.

[0575] 2) The terminal (base station) receives (transmits) a message scheduling the transmission of a beam measurement report.

[0576] The transmission of the above report scheduled by the base station may have periodic / semi-persistent / dynamic time domain behavior.

[0577] 3) The terminal (base station) transmits (receives) a beam measurement report based on the above message.

[0578] The UE assumption for the above report may be based on the embodiments of Proposal 9.

[0579] The above embodiments may be operated by a combination of specific embodiments.

[0580] An example of a terminal (or base station) operation based on at least one of the aforementioned embodiments (e.g., at least one of the embodiments of Proposals 1 to 9) is as follows.

[0581] 1) A terminal (base station) receives (transmits) settings related to event-triggered AI / ML model / functionality performance monitoring reporting. The settings may include information related to at least one of Proposal 1 to Proposal 9.

[0582] 2) The terminal (base station) receives (transmits) a message scheduling the transmission of the performance monitoring report. The transmission of the performance monitoring report may be performed based on a UE-triggered operation. In this case, this step (step 2)) may be omitted.

[0583] 3) The terminal (base station) transmits (receives) the above performance monitoring report.

[0584] The transmission of the above report may be performed based on the occurrence of the event of Proposal 3. Specifically, the above report may be transmitted based on the fulfillment of conditions related to the event of Proposal 3. The above report may be transmitted (received) based on embodiments of Proposals 4 to 9.

[0585] The above terminal / base station operations are merely examples, and each operation (or step) is not necessarily essential; depending on the terminal / base station implementation method, the AI / ML model / functionality performance monitoring reporting operation of the terminal according to the aforementioned embodiments may be omitted or added.

[0586] In terms of implementation, the operations of the base station / terminal according to the embodiments described above (e.g., operations based on at least one of proposals 1 to 9) can be processed by the device of FIG. 11 (e.g., the processor (110, 210) of FIG. 11).

[0587] In addition, the operations of the base station / terminal according to the above-described embodiment (e.g., operations based on at least one of proposals 1 to 9) may be stored in memory (e.g., 140, 240 of FIG. 11) in the form of instructions / programs (e.g., instruction, executable code) for driving at least one processor (e.g., 110, 210 of FIG. 11).

[0588] The embodiments described above will be explained in detail below with reference to FIGS. 9 and FIGS. 10 in terms of the operation of the terminal and base station. The methods described below are distinguished only for convenience of explanation, and it is understood that a part of one method may be substituted with a part of another method or combined with one another and applied.

[0589] FIG. 9 is a flowchart illustrating a method according to one embodiment of the present specification.

[0590] Referring to FIG. 9, a method according to one embodiment of the present specification includes a step of receiving setting information related to CSI (S910) and a step of transmitting a CSI report related to prediction accuracy (S920).

[0591] In S910, the terminal receives configuration information related to Channel State Information (CSI) from the base station.

[0592] For example, the above configuration information may include information based on at least one of the above-described CSI-related operations and proposals 1 to 9. As a specific example, the above configuration information may include i) one or more reporting settings (e.g., N≥1 CSI-ReportConfig reporting setting) and ii) one or more resource settings (e.g., M≥1 CSI-ResourceConfig resource setting).

[0593] Each of the above one or more reporting configurations may be associated with up to three resource configurations. In other words, each reporting configuration may include the IDs (e.g., CSI-ResourceConfigId) of up to three resource configurations.

[0594] The above one or more reporting settings may include i) a first reporting setting related to prediction and ii) a second reporting setting related to prediction accuracy.

[0595] For example, the report quantity of the first report setting above may be set to p-cri, p-cri-RSRP, p-ssb-index, or p-ssb-index-RSRP. p-cri represents the predicted CSI-RS Resource Indicator (P-CRI). p-ssb-index represents the predicted SSB Resource Indicator (P-SSBRI). In p-cri-RSRP or p-ssb-index-RSRP, RSRP represents the predicted Layer1-Reference Signal Received Power (P-L1-RSRP).

[0596] For example, the above prediction may be performed based on a measurement. The measurement may be performed based on a first resource configuration (e.g., CSI-ResourceConfig) associated with the first reporting configuration. For example, the first reporting configuration may be linked to a first resource configuration associated with the measurement and a second resource configuration associated with the prediction. The first reporting configuration may include the ID of the first resource configuration and the ID of the second resource configuration. Each ID may be based on the CSI-ResourceConfigId.

[0597] For example, the above measurements may include Layer1-Reference Signal Received Power (L1-RSRP) measurements. Based on the L1-RSRP measurements, i) at least one predicted CSI-RS Resource Indicator (P-CRI), ii) at least one predicted SSB Resource Indicator (P-SSBRI), and / or iii) at least one predicted Layer1-Reference Signal Received Power (P-L1-RSRP) may be determined.

[0598] More specifically, predictions for CSI-RS resources or SSB resources associated with the second resource configuration may be performed based on the L1-RSRP measurements. Specifically, predicted L1-RSRPs of CSI-RS resources or SSB resources associated with the second resource configuration may be determined. For example, best CRI(s) or best SSBRI(s) may be determined based on the order or ranking of the predicted L1-RSRPs. For example, at least one P-CRI or at least one P-SSBRI included in the first CSI report described below may be based on the best CRI(s) or best SSBRI(s).

[0599] For example, the report quantity of the second report setting above can be set to pai (or rs-pai).

[0600] The above one or more resource settings may include i) a first resource setting and a second resource setting related to the first reporting setting and ii) a third resource setting related to the second reporting setting.

[0601] Each resource configuration (e.g., CSI-ResourceConfig) may include information about a resource set (e.g., csi-SSB-ResourceSetList or nzp-CSI-RS-ResourceSetList based on csi-RS-ResourceSetList). For example, the resources within the resource set may be SSB resources or CSI-RS resources based on csi-RS-ResourceSetList. csi-SSB-ResourceSetList may include information for referencing the SSB resources (e.g., CSI-SSB-ResourceSetIds). nzp-CSI-RS-ResourceSetList may include information for referencing the CSI-RS resources (e.g., NZP-CSI-RS-ResourceSetIds).

[0602] For example, the first resource setting may include information about a first resource set for measurement (e.g., Set B described above). As a specific example, the first resource setting may include a list of SSB resources or CSI-RS resources for measurement.

[0603] For example, the second resource setting may include information regarding a second resource set for the prediction (e.g., Set A described above). As a specific example, the second resource setting may include a list of SSB resources or CSI-RS resources for the prediction.

[0604] For example, the third resource setting may include information regarding a third resource set for measurement (e.g., Set X described above). As a specific example, the third resource setting may include a list of SSB resources or CSI-RS resources for measurement. In this case, the resources of the third resource set may be mapped to the resources of the second resource set.

[0605] As explained in Proposal 6, Set X related to performance monitoring (prediction accuracy) can be based on a subset of Set A.

[0606] According to one embodiment, the resources based on the third resource set may be mapped to a subset of the resources of the second resource set.

[0607] According to one embodiment, the size of the third resource set may be smaller than or equal to the size of the second resource set. For example, if the size of the second resource set is X and the size of the third resource set is Y, then Y = X or Y <X일 수 있다. 상기 제3 자원 세트와 관련된 설정 / 지시의 구체적인 예로, 상기 제2 자원 세트의 서브세트(subset)에 매핑된 상기 제3 자원 세트는 비트맵에 기초하여 지시될 수 있다(예: X개의 bit들 중 Y개의 bit들은 non-zero인 비트맵). 다시 말하면, 상기 제3 자원 설정은 Y개의 자원들을 나타내는 정보(예: csi-RS-ResourceSetList) 및 매핑 정보(상기 비트맵)(예: RSMappingtoSetA)를 포함할 수 있다.

[0608] In S920, the terminal transmits a CSI report related to prediction accuracy to the base station.

[0609] According to one embodiment, the processing of the CSI report may occupy at least one CPU (CSI Processing Unit). The first uplink symbol carrying the CSI report may be determined based on the number of symbols (e.g., Z, Z') associated with the CSI computation. The number of the at least one CPU and / or the number of symbols may be determined based on whether the CSI report is associated with one or more future time instances. This embodiment may be based on Proposal 8.

[0610] For example, the number of at least one CPU or the number of symbols may be determined as i) a first value or ii) a second value different from the first value.

[0611] As a specific example, based on the fact that the above CSI report is associated with one or more future time instances (e.g., BM-case 2), the number of at least one CPU or the number of symbols may be determined as the second value. As a specific example, the second value may be greater than the first value.

[0612] According to one embodiment, the number of symbols may be determined based on at least one of i) whether the CSI report is associated with one or more future time instances, ii) terminal capability (UE capability), iii) a value defined in a table (e.g., the legacy value described above, a value based on Table 12 / Table 13), iv) an offset value (e.g., the alpha described above) and / or v) a scaling value (e.g., the beta described above). This embodiment may be based on at least one of embodiments 2) to 4) of Proposal 8.

[0613] According to one embodiment, the method may further include a first CSI report transmission step. Specifically, the terminal may transmit a first CSI report related to a prediction to a base station. The CSI report related to the prediction accuracy may be a second CSI report transmitted after the transmission of the first CSI report. In other words, the first CSI report transmission step may be performed prior to S910.

[0614] According to one embodiment, the first CSI report may include predicted information for each of the one or more future time instances. The second CSI report may include information related to a future time instance for monitoring among the one or more future time instances. This embodiment may be based on Embodiment 1) of Proposal 8.

[0615] According to one embodiment, the report quantity (e.g., Alt 1 to Alt 4) associated with the second CSI report may be determined based on the report quantity (e.g., Opt 1 to Opt 4) associated with the first CSI report. This embodiment may be based on Proposal 9.

[0616] According to one embodiment, the first CSI report may be based on an inference report / predicted Set A beam-related CSI. The first CSI report may include predicted information (predicted CSI parameter(s)). The first CSI report may include predicted CSI parameter(s) (e.g., P-CRI(s), P-SSBRI(s), and / or P-L1-RSRP(s)) based on the report quantity of the first report setting. Specifically, the first CSI report may include at least one of i) at least one predicted CSI-RS Resource Indicator (P-CRI), ii) at least one predicted SSB Resource Indicator (P-SSBRI), and / or iii) at least one predicted Layer1-Reference Signal Received Power (P-L1-RSRP).

[0617] According to one embodiment, the second CSI report may be based on a monitoring report. The second CSI report may include information related to monitoring the performance / accuracy of the CSI prediction. The second CSI report may include CSI parameters (e.g., PAI or RS-PAI) based on the report quantity (e.g., pai or rs-pai) of the second report setting. Specifically, the second CSI report may include a Prediction Accuracy Indicator (PAI). The PAI may be interpreted / replaced with a Reference Signal-Prediction Accuracy Indicator (RS-PAI).

[0618] For example, the above PAI may be based on the accuracy rate of Proposal 4 described above. The accuracy rate may be determined based on whether the actual measured best beam based on measurement matches the top K beam(s) based on prediction. Specifically, the above PAI may be determined based on whether at least one of the resources determined based on measurement related to the third resource set maps to the at least one P-CRI or the at least one P-SSBRI.

[0619] For example, the 1st / 2nd CSI report can be interpreted / substituted with the 1st / 2nd CSI.

[0620] According to one embodiment, the setting information may include a first reporting setting related to prediction and a second reporting setting related to prediction accuracy. The first reporting setting may include i) a first resource setting for measurement and ii) a second resource setting for prediction.

[0621] According to one embodiment, an associated ID may be set based on the first reporting setting. Based on the associated ID, the relationship between Set A and Set B (Set B is a subset of Set A) may be determined. Specifically, based on the fact that the associated ID is set based on the first reporting setting, all resources within the first resource set based on the first resource setting may be among the resources within the second resource set based on the second resource setting. This embodiment may be based on Embodiment 1) of Proposal 9-1.

[0622] In other words, based on the fact that one associated ID is set based on the first reporting setting, the terminal can expect that all resources within the first resource set based on the first resource setting are among the resources within the second resource set based on the second resource setting.

[0623] In other words, based on the fact that one associated ID is set based on the first report setting, the first resource setting may be a subset of the second resource setting.

[0624] For example, the associated ID may be associated with similar properties of a downlink transmission beam (DL Tx beam), a beam set, or a beam list. As a specific example, based on the fact that the same associated ID is configured to be associated with different resource sets, the terminal may assume the similar properties for resources among said different resource sets (CSI-RS resources and / or SS / PBCH block resources).

[0625] The operation based on the above-described S910 to S920 and the first CSI report transmission step can be implemented by the device of FIG. 11. For example, referring to FIG. 11, the terminal (200) can control one or more transceivers (230) and / or one or more memories (240) to perform the operation based on S910 to S920 and the first CSI report transmission step.

[0626] The embodiments described above will be explained in detail below in terms of base station operation.

[0627] The steps S1010 to S1020 and the first CSI report receiving step described below correspond to the operations based on the steps S910 to S920 and the first CSI report transmitting step described in FIG. 9. Considering the above correspondence, redundant descriptions are omitted. That is, the specific description of the base station operation described below can be replaced by the description / embodiment of FIG. 9 corresponding to the operation.

[0628] FIG. 10 is a flowchart illustrating a method according to another embodiment of the present specification.

[0629] Referring to FIG. 10, a method according to another embodiment of the present specification includes a step of transmitting setting information related to CSI (S1010) and a step of receiving a CSI report related to prediction accuracy (S1020).

[0630] In S1010, the base station transmits configuration information related to Channel State Information (CSI) to the terminal.

[0631] In S1020, the base station receives a CSI report related to prediction accuracy from the terminal.

[0632] According to one embodiment, the processing of the CSI report may occupy at least one CPU (CSI Processing Unit). The first uplink symbol carrying the CSI report may be determined based on the number of symbols associated with the CSI computation. The number of the at least one CPU and / or the number of symbols may be determined based on whether the CSI report is associated with one or more future time instances.

[0633] According to one embodiment, the method may further include a first CSI report reception step. Specifically, the base station may receive a first CSI report related to a prediction from a terminal. The CSI report related to the prediction accuracy may be a second CSI report received after the reception of the first CSI report. In other words, the first CSI report reception step may be performed prior to S1010.

[0634] The operation based on the above-described S1010 to S1020 and the first CSI report reception step can be implemented by the device of FIG. 11. For example, referring to FIG. 11, the base station (100) can control one or more transceivers (130) and / or one or more memories (140) to perform the operation based on S1010 to S1020 and the first CSI report reception step.

[0635] The operations / terms based on the embodiments described above are described under the assumption of an existing system (e.g., a 5G system). However, this is for the convenience of explanation and is not intended to limit the scope of application of the technical problems and means for solving problems that are to be solved by this specification to a specific system. That is, the technical problems / technical issues / problems mentioned in this specification may exist in other systems (e.g., a 6G system). It is evident that the embodiments of this specification can be extended to solve problems that exist in other systems as well. Therefore, for the extended application of the embodiments of this specification to other systems, terms defined / described based on a 5G system may be replaced / changed with terms defined in said other systems (or generalized terms not specific to one system). For example, PRACH, PUSCH, PUCCH, or SRS may be replaced / changed to uplink signals (or uplink channels). For example, SSB, CSI-RS, PDSCH, and PDCCH may be replaced / changed to downlink signals (or downlink channels).

[0636] Hereinafter, an apparatus to which the embodiments of the present specification can be applied (an apparatus implementing the method / operation according to the embodiments of the present specification) will be described with reference to FIG. 11.

[0637] FIG. 11 is a drawing showing the configuration of a first device and a second device according to an embodiment of the present specification.

[0638] The first device (100) may include a processor (110), an antenna unit (120), a transceiver (130), and a memory (140).

[0639] The processor (110) performs baseband-related signal processing and may include an upper layer processing unit (111) and a physical layer processing unit (115). The upper layer processing unit (111) may process operations of the MAC layer, RRC layer, or higher upper layers. The physical layer processing unit (115) may process operations of the PHY layer. For example, if 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, if the first device (100) is a first terminal device in terminal-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).

[0640] The antenna section (120) may include one or more physical antennas, and if 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, operating systems, applications, etc. related to the operation of the first device (100), and may include components such as a buffer.

[0641] The processor (110) of the first device (100) may be configured to implement the operation of the base station in base station-terminal communication (or the operation of the first terminal device in terminal-terminal communication) in the embodiments described in this disclosure.

[0642] The second device (200) may include a processor (210), an antenna unit (220), a transceiver (230), and a memory (240).

[0643] The processor (210) performs baseband-related signal processing and may include an upper layer processing unit (211) and a physical layer processing unit (215). The upper layer processing unit (211) may process operations of the MAC layer, RRC layer, or higher upper layers. The physical layer processing unit (215) may process operations of the PHY layer. For example, if 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, if the second device (200) is a second terminal device in terminal-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).

[0644] The antenna section (220) may include one or more physical antennas, and may support MIMO transmission and reception if it includes multiple antennas. The transceiver (230) may include an RF transmitter and an RF receiver. The memory (240) may store information processed by the processor (210) and software, operating systems, applications, etc. related to the operation of the second device (200), and may include components such as a buffer.

[0645] The processor (210) of the second device (200) may be configured to implement the operation of the terminal in base station-terminal communication (or the operation of the second terminal device in terminal-terminal communication) in the embodiments described in this disclosure.

[0646] In the operation of the first device (100) and the second device (200), the details described in the examples of the present disclosure regarding the base station and terminal (or the first terminal and the second terminal in terminal-to-terminal communication) in base station-to-terminal communication may be applied in the same way, and redundant descriptions are omitted.

[0647] 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 Low Power Wide Area Network (LPWAN) technology and may be implemented according to standards such as LTE Cat NB1 and / or LTE Cat NB2, but is not limited to the names mentioned above.

[0648] 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 referred to by various names such as eMTC (enhanced Machine Type Communication). For example, LTE-M technology may be implemented in 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 names mentioned above.

[0649] Additionally or generally, the wireless communication technology implemented in the device of the present disclosure may include at least one of ZigBee, Bluetooth, and a Low Power Wide Area Network (LPWAN) for low-power communication, but is not limited to the names mentioned above. 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 referred to by various names.

Claims

In terms of method, A step of receiving configuration information related to Channel State Information (CSI); and The method includes the step of transmitting a CSI report related to prediction accuracy; The processing of the above CSI report occupies at least one CPU (CSI Processing Unit), and The first uplink symbol carrying the above CSI report is determined based on the number of symbols associated with CSI computation, and A method characterized in that the number of at least one CPU and / or the number of symbols is determined based on whether the CSI report is associated with one or more future time instances. In Article 1, A method characterized in that the number of at least one CPU or the number of symbols is determined as i) a first value or ii) a second value different from the first value. In Article 2, A method characterized in that, based on the fact that the above CSI report is associated with the above one or more future time instances, the number of at least one CPU or the number of symbols is determined by the second value. In Article 1, A method characterized in that the number of symbols is determined based on at least one of i) whether the CSI report is associated with one or more future time instances, ii) terminal capability (UE capability), iii) a value defined in a table, iv) an offset value and / or v) a scaling value. In Article 1, The method further includes the step of transmitting a first CSI report related to a prediction; and A method characterized in that the CSI report related to the above prediction accuracy is a second CSI report transmitted after the transmission of the first CSI report. In Article 5, The above first CSI report includes predicted information for each of the above one or more future time instances, and A method characterized in that the above second CSI report includes information related to a future time instance for monitoring among the above one or more future time instances. In Article 5, A method characterized in that the report quantity related to the second CSI report is determined based on the report quantity related to the first CSI report. In Article 1, The above setting information includes a first reporting setting related to prediction and a second reporting setting related to the prediction accuracy, and A method characterized in that the above-mentioned first reporting setting includes i) a first resource setting for measurement and ii) a second resource setting for prediction. In Article 8, A method characterized in that, based on the first reporting setting, an associated ID is set, and all resources within the first resource set based on the first resource setting are among the resources within the second resource set based on the second resource setting. In Article 9, A method characterized in that the above-mentioned associated ID is associated with similar properties of a downlink transmission beam (DL Tx beam), a beam set, or a beam list. In the terminal, One or more transmitters / receivers; One or more processors; and It includes one or more memories connected to the above one or more processors and storing instructions, A terminal characterized by the above instructions enabling the terminal to perform all steps of the method according to any one of claims 1 to 10, based on execution by the one or more processors. In a device comprising one or more memories and one or more processors connected to said one or more memories, An apparatus characterized in that the above one or more memories store instructions that cause the apparatus to perform all steps of the method according to any one of claims 1 to 10, based on execution by the above one or more processors. In a non-transitory computer-readable storage medium for storing instructions, A non-transitory computer-readable storage medium characterized by instructions executable by one or more processors that cause a terminal to perform all steps of the method according to any one of claims 1 to 10. In terms of method, A step of transmitting configuration information related to Channel State Information (CSI); and The method includes the step of receiving a CSI report related to prediction accuracy; The processing of the above CSI report occupies at least one CPU (CSI Processing Unit), and The first uplink symbol carrying the above CSI report is determined based on the number of symbols associated with CSI computation, and A method characterized in that the number of at least one CPU and / or the number of symbols is determined based on whether the CSI report is associated with one or more future time instances. In the case of a base station, One or more transmitters / receivers; One or more processors; and It includes one or more memories connected to the above one or more processors and storing instructions, A base station characterized by the above instructions, based on execution by one or more processors, having the base station perform all steps of the method according to claim 14.

Images