Method for CSI reporting and device therefor

Abstract

A method according to an embodiment of the present specification comprises the steps of: transmitting a UECapabilityInformation message; receiving configuration information related to CSI; and transmitting a CSI report including predicted information based on a second resource configuration. The configuration information includes a report configuration related to prediction. The CSI report is transmitted only when at least X latest consecutive transmission occasions are received for each of resources in a measurement resource set based on the first resource configuration, and the CSI report is dropped otherwise. The value of X is indicated on the basis of the UECapabilityInformation message.

Description

Method and apparatus for CSI reporting

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

[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 L1-RSRP, etc.). As an example, the report may include a Prediction Accuracy Indicator (e.g., PAI).

[0005] Meanwhile, temporal DL Tx beam prediction (e.g., BM-case2) through a UE-side AI / ML model can be performed as follows. After observations of multiple Set B transmission occasions are performed (after the transmission occasions are received), predictions for one or more time instances can be performed using this as input data.

[0006] At this time, due to CPU(s) occupancy caused by the processing of the CSI report related to the above prediction or conflicts with other DL channels / RSs, a large number of Set B transmission occasions may be dropped or the terminal may fail to receive the transmission occasion normally. In such cases, due to a lack of input data, it is difficult for the terminal to report accurate beam prediction results (related to BM-case2).

[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 above-described problem comprises the steps of transmitting a terminal performance information (UECapabilityInformation) message, receiving configuration information related to channel state information (CSI), and transmitting a CSI report including predicted information based on the second resource configuration. The configuration information includes a reporting configuration related to the prediction. The reporting configuration includes i) information related to a first resource configuration for measurement, ii) information related to a second resource configuration for prediction, and / or iii) information regarding the number of one or more time instances. The CSI report is transmitted only when at least X latest consecutive transmission occasions are received for each of the resources in the resource set for measurement based on the first resource configuration, and otherwise, the CSI report is dropped. The value of X is indicated based on the UECapabilityInformation message.

[0010] Therefore, if transmission occasions related to the input of the UE-side model are not properly received due to CPU occupancy or other issues (e.g., collision), dropping the corresponding CSI report can prevent information with low predictive performance from being reported and utilized.

[0011] According to the embodiments of this specification, the accuracy and safety of the prediction-based beam management operation of the UE-side model can be improved by preventing information with degraded prediction performance from being applied or utilized in subsequent beam management operations according to BM-case2. More specifically, by preventing the forced reporting of inference results when input data is insufficient, unnecessary control signaling and incorrect beam switching / maintenance decisions can be reduced. As a result, wireless resource utilization efficiency is improved, and the possibility of beam-related link performance degradation can be reduced.

[0012] In addition, it is possible to prevent the transmission (Tx) power consumption of the terminal that is consumed in transmitting CSI reports containing invalid beam prediction results, and to improve the battery efficiency of the terminal by omitting unnecessary subsequent processing operations through conditional drop.

[0013] Furthermore, by configuring the system to report the minimum number of transmission occasions (X) requiring normal reception for observations (measurements) related to beam prediction as a UE capability, the robustness of AI / ML models and hardware computational capabilities, which vary by terminal, can be flexibly reflected in the beam management procedure. Additionally, this has the effect of guaranteeing the validity of input data for AI / ML-based beam prediction. It can enhance the consistency and reproducibility of internal UE inference results and, from a network perspective, more reliably ensure the quality of reported results.

[0014] In addition, if a base station does not receive a CSI report triggered / activated by the terminal, the base station may operate by interpreting / assuming that it did not receive a transmission occasion based on the value reported by the terminal, thereby ensuring that subsequent operations of the base station for receiving the terminal's transmission occasion are properly performed.

[0015] 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.

[0016] Figure 1 is a diagram illustrating the overall functions from the perspective of an AI / ML model.

[0017] Figure 2 illustrates a general form of an AI / ML-related procedure performed between a network and a terminal.

[0018] Figure 3 illustrates an example of AI / ML-based beam management operation.

[0019] Figure 4 illustrates an example of an AI / ML-based CSI measurement / reporting operation.

[0020] Figure 5 illustrates an example of an AI / ML-based positioning operation.

[0021] Figure 6 is a flowchart showing an example of a CSI-related procedure.

[0022] Figure 7 illustrates a procedure for applicable functionality reporting.

[0023] Figure 8 is a diagram illustrating the CPU occupancy time associated with BM-Case 2.

[0024] FIG. 9 is a flowchart illustrating a method according to one embodiment of the present specification.

[0025] FIG. 10 is a flowchart illustrating a method according to another embodiment of the present specification.

[0026] FIG. 11 is a drawing showing the configuration of a first device and a second device according to an embodiment of the present specification.

[0027] 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."

[0028] 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."

[0029] 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."

[0030] 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."

[0031] 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."

[0032] In the following explanation, 'when, if, in case of' can be replaced with 'based on'.

[0033] Technical features described individually within a single drawing in this specification may be implemented individually or simultaneously.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] < AI / ML for Wireless Communication >

[0040] 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.

[0041] - 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.

[0042] - 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.

[0043] - 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.

[0044] - 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.

[0045] 1. Life Cycle Management (LCM) for AI / ML models

[0046] 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.

[0047] Figure 1 is a diagram illustrating the overall functions from the perspective of an AI / ML model.

[0048] 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).

[0049] 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.

[0050] 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).

[0051] 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).

[0052] 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).

[0053] The Management function (30) is a function that monitors the operation of an AI / ML model or an AI / ML function.

[0054] 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).

[0055] A Model Transfer / Delivery Request (33) can be used to request model(s) from Model Storage (50).

[0056] 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).

[0057] 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).

[0058] 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.

[0059] The Model Storage function (50) is a function that stores a trained / updated model that can be used to perform the Inference function (40).

[0060] Model Transfer / Delivery (51) is used to transfer an AI / ML model to an inference function.

[0061] 2. General AI / ML related procedures between the network and the terminal

[0062] 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.

[0063] (1) AI / ML related setup procedure

[0064] 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.

[0065] 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).

[0066] (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.

[0067] (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.

[0068] (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.

[0069] (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.

[0070] 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.

[0071] (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.

[0072] (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.

[0073] (2) Operation based on inference by AI / ML models

[0074] 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.

[0075] (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.

[0076] (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.

[0077] (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.

[0078] (3) Procedures for AI / ML management

[0079] The network and / or terminal can perform procedures for the management of AI / ML Functionality / model or the settings therefor (B15).

[0080] 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).

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 3. Specific operation examples based on AI / ML model inference

[0088] (1) Beam management

[0089] Figure 3 illustrates an example of AI / ML-based beam management operation.

[0090] 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.

[0091] The network / terminal can perform measurements on the first set of beams (C10). The beam measurements may be related to RSRP measurements.

[0092] 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.

[0093] According to an embodiment, the network / terminal can transmit and receive information about the acquired second set of beams.

[0094] Specifically, AI / ML-based beam management operations may include at least one of the following BM-Case 1 and BM-Case 2.

[0095] - BM-Case 1: Prediction of the second set of DL beams in the spatial domain through the first set of beam measurements

[0096] - BM-Case 2: Prediction of the second set of DL beams in the time domain through the first set of beam measurements

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] Regarding UE-assisted performance monitoring for the UE-side models of BM-Case 1 and 2, the following methods may be considered.

[0105] i) Compare prediction results based on resources for monitoring and use the top 1 or top K beam prediction accuracy.

[0106] 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.

[0107] iii) Use the difference information between the measured RSRP and the predicted RSRP for the corresponding beam of the resources for monitoring.

[0108] iv) Probability information that the predicted beam will become one of the top 1 or N beams

[0109] 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.

[0110] For BM-Case 2 of the UE-side model, the network can be configured to report inferences about N future times to the terminal.

[0111] (2) CSI prediction and / or compression

[0112] Figure 4 illustrates an example of an AI / ML-based CSI measurement / reporting operation.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] The network can acquire CSI based on the terminal's CSI report.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] (3) Positioning

[0121] Figure 5 illustrates an example of an AI / ML-based positioning operation.

[0122] 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.

[0123] < CSI Related Operations >

[0124] 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).

[0125] 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).

[0126] 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).

[0127] Figure 6 is a flowchart showing an example of a CSI-related procedure.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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).

[0136] 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).

[0137] For example, the reportQuantity parameter can be set to pai (or rs-pai). pai (or rs-pai) represents PA (or RS-PAI).

[0138] 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.

[0139] 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).

[0140] resource setting

[0141] 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).

[0142] Next, one or more CSI resource settings for channel measurement (CM) and interference measurement (IM) are established through higher layer signaling.

[0143] - CSI-IM resource for interference measurement.

[0144] - NZP CSI-RS resources for interference measurement.

[0145] - NZP CSI-RS resources for channel measurement.

[0146] 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.

[0147] Here, CSI-IM (or ZP CSI-RS for IM) is primarily used for inter-cell interference measurements.

[0148] Also, the NZP CSI-RS for IM is mainly used for intra-cell interference measurement from multi-users.

[0149] 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.

[0150] As examined, resource setting can refer to a resource set list.

[0151] 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.

[0152] 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.

[0153] Beam Management (BM)

[0154] 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.

[0155] - Beam measurement: An operation in which a base station or UE measures the characteristics of a received beamforming signal.

[0156] - Beam determination: The operation in which a base station or UE selects its transmit beam (Tx beam) / receive beam (Rx beam).

[0157] - Beam sweeping: An operation that covers a spatial area using transmitting and / or receiving beams for a set time interval in a predetermined manner.

[0158] - Beam report: An operation in which the UE reports information about the beam-formed signal based on beam measurements.

[0159] 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).

[0160] In addition, each BM procedure may include Tx beam sweeping to determine the Tx beam and Rx beam sweeping to determine the Rx beam.

[0161] DL BM

[0162] 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.

[0163] Here, beam reporting may include preferred DL RS ID(identifier)(s) and the corresponding L1-RSRP(Reference Signal Received Power).

[0164] The above DL RS ID may be SSBRI (SSB Resource Indicator) or CRI (CSI-RS Resource Indicator).

[0165] An example of beam forming using SSB and CSI-RS will be examined in detail below.

[0166] 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.

[0167] 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.

[0168] The DL BM procedure is examined below.

[0169] Configuration for beam reporting using SSB is performed during CSI / beam configuration in the RRC connected state (or RRC connected mode).

[0170] - 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.

[0171] 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.

[0172]

[0173] 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.

[0174] - 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.

[0175] - 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.

[0176] 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.

[0177] 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'.

[0178] 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.

[0179] 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.

[0180] - 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).

[0181] - 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.

[0182] - The terminal selects (or determines) the best beam.

[0183] - 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'.

[0184] Explanation regarding Rel-17 / 18 beam management >

[0185] 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.

[0186] 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.

[0187] 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.).

[0188] 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).

[0189] 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).

[0190] In this document, ' / ' means 'and', 'or', or 'and / or' depending on the context.

[0191] In the Rel-18 AI / ML study item, performance analysis through evaluation and potential specification impact were studied for NW and / or UE-side AI / ML models operating in three use cases: CSI compression / prediction, beam management, and positioning (refer to TR38.843). In the subsequent Rel-19, standardization is underway for the use cases of beam management, CSI prediction, and positioning.

[0192] In the NR standard, when a terminal performs CSI-related reporting, the CSI-ResourceConfig for channel / interference measurement is associated / linked with the CSI-ReportConfig setting for CSI reporting, allowing the terminal to perform CSI / beam reporting based on DL RS measurements. In this case, depending on the terminal's parallel processing capability, the maximum number of CSI measurements / reports that can be performed simultaneously is N. cpu As a value, it can be reported to the base station through UE capability reporting, and depending on what report value various CSI reports (i.e., CSI-ReportConfig) have (e.g., reportQuantity set respectively for CSI reporting or beam reporting), it determines how much CSI preprocessing unit (CPU) value is occupied (i.e., O cpu It is defined by the standard regarding ). In addition, these specific CSI-related reports are O cpuThe standard also defines a timeline regarding the period of occupation, specifically from which point in time to which point. The CSI processing criteria are explained in detail below.

[0193] 5.2.1.6 CSI Processing Criteria

[0194] The terminal (UE) is the number of simultaneous CSI calculations N supported by the parameter simultaneousCSI-ReportsPerCC or [simultaneousCSI-SubReportsPerCC-r18] on a single component carrier. CPU Indicates [simultaneousCSI-ReportsAllCC] or [simultaneousCSI-SubReportsAllCC-r18] across all component carriers. If, on one component carrier, the terminal (UE) is configured with at least one CSI report setting having a sub-configuration, the terminal (UE) must use the parameter [simultaneousCSI-SubReportsPerCC-r18] on that component carrier. Otherwise, the terminal (UE) must use simultaneousCSI-ReportsPerCC on that component carrier. If, on any one component carrier, the terminal (UE) is configured with at least one CSI reporting setting having a sub-configuration, the terminal (UE) must use [simultaneousCSI-SubReportsAllCC-r18]. Otherwise, the terminal (UE) must use simultaneousCSI-ReportsAllCC. If the terminal (UE) is N CPUIf simultaneous CSI calculations are supported, the terminal (UE) is for processing N CSI reports. CPU It is said to have CSI processing units. If L CPUs are occupied for the calculation of CSI reports in a given OFDM symbol, the terminal (UE) has N CPU - It has L unoccupied CPUs. There are N CSI reports, N CPU -L CPUs start occupying their respective CPUs in the same unoccupied OFDM symbol, where each CSI report n=0,..,N-1 In the case corresponding to , the terminal (UE) is not required to update NM of requested CSI reports with the lowest priority (in accordance with Section 5.2.5). Here, 0≤M≤N, and M is It is the largest value that satisfies .

[0195] The terminal (UE) is N CPU It is not expected to consist of an aperioditic CSI trigger state containing more than a certain number of reporting settings. Processing of a CSI report occupies a certain number of CPUs for a certain number of symbols as follows.

[0196] - O CPUFor a CSI report having a CSI-ReportConfig with a CSI-RS-ResourceSet configured with the higher layer parameter trs-Info, where =0, the higher layer parameter reportQuantity is set to 'none'

[0197] - O CPU For a CSI report (CSI report) with LTM-CSI-ReportConfig =1, or a CSI report (CSI report) with CSI-ReportConfig where the upper tier parameter reportQuantity is set to 'cri-RSRP', 'ssb-Index-RSRP', 'cri-SINR', 'ssb-Index-SINR', 'cri-RSRP-Index', 'ssb-Index-RSRP-Index', 'cri-SINR-Index', 'ssb-Index-SINR-Index' or 'none' (and CSI-RS-ResourceSet where the upper tier parameter trs-Info is not configured

[0198] - O CPU =(Y+1)·X, for a CSI report having a CSI-ReportConfig where the upper layer parameter reportQuantity is set to 'tdcp' and the number of delays Y configured by the upper layer parameter Y is given, where the value of X∈{1,2} is reported by the terminal capability (UE capability).

[0199] - For a CSI report (CSI report) having a CSI-ReportConfig where the upper-level parameter reportQuantity is set to 'cri-RI-PMI-CQI', 'cri-RI-i1', 'cri-RI-i1-CQI', 'cri-RI-CQI', or 'cri-RI-LI-PMI-CQI',

[0200] - If max{ μPDCCH, μCSI-RS, μUL} ≤ 3 and L=0 CPUs are occupied, if CSI corresponds to a single CSI and corresponds to wideband frequency-granularity, and corresponds to up to 4 CSI-RS ports within a single resource without a CRI report, and if codebookType is set to 'typeI-SinglePanel' or reportQuantity is set to 'cri-RI-CQI', and a CSI report is triggered non-periodically without transmitting a transport block or a PUSCH containing HARQ-ACK or both, O CPU =N CPU ,

[0201] - If CSI-ReportConfig is configured so that codebookType is set to 'typeI-SinglePanel', and the corresponding CSI-RS resource set for channel measurement consists of 2 resource groups and N resource pairs, O CPU =X·N+M, where X is the number of CPUs occupied by a pair of CMRs that are the target of mTRP-CSI-numCPU-r17, and M is defined in Section 5.2.1.4.2.

[0202] - If CSI-ReportConfig contains a list of L sub-configurations provided by the parent parameter csi-ReportSubConfigToAddModList,

[0203] - , in the case of periodic CSI reporting, here is the total number of CSI-RS resources corresponding to the i-th sub-configuration.

[0204] - , in the case of aperioditic and semi-persistent CSI reporting, here is the total number of CSI-RS resources corresponding to the i-th sub-configuration, where the i-th sub-configuration is from the specified N sub-configurations among the L sub-configurations included in CSI-ReportConfig, where N≤L and N≥1.

[0205] - CSI-ReportConfig is configured so that the upper-level parameter reportQuantity is set to 'cri-RI-PMI-CQI' and codebookType is set to 'typeII-CJT-r18' or 'typeII-CJT-PortSelection-r18', and the corresponding NZP-CSI-RS-ResourceSet for channel measurement is 1 <N_TRP≤4개의 자원(resources)으로 구성되는 경우, O CPU =ceil(X·N TRP ), where X∈{1,1.5,2} is reported by the UE capability indication.

[0206] - If CSI-ReportConfig is configured such that the upper-level parameter reportQuantity is set to 'cri-RI-PMI-CQI' and codebookType is set to 'typeII-Doppler-r18' or 'typeII-Doppler-PortSelection-r18',

[0207] - If the corresponding CSI-RS resource set for channel measurement is aperioditic and consists of K CSI-RS resources, then when K=12, O CPU =8 and when K<12 O CPU =Y_1·K, where Y_1∈{1,2,3} is reported by the UE capability indication.

[0208] - If the corresponding CSI-RS resource set for channel measurement is periodic or semi-persistent and consists of a single CSI-RS resource, then when N_4=1, O CPU =4 and when N_4>1 O CPU =max(Y_2·N_4, 4), where the value of N_4 is configured by the upper layer parameter N4, and Y_2∈{1,2,3} is reported by the UE capability indication.

[0209] - In other cases (otherwise), O CPU =K s , here K s is the number of CSI-RS resources within the CSI-RS resource set for channel measurement.

[0210] For a CSI report with a CSI-ReportConfig where the upper layer parameter reportQuantity is not set to 'none', or for a CSI report with an LTM-CSI-ReportConfig, the CPU(s) are occupied for a certain number of OFDM symbols as follows.

[0211] - Periodic or semi-persistent CSI reports (excluding initial semi-persistent CSI reports on PUSCH following the PDCCH that triggers the report, and semi-persistent CSI reports on PUSCH configured so that the upper-level parameter codebookType is set to 'typeII-Doppler-r18' or 'typeII-Doppler-PortSelection-r18') are periodic CSI reports corresponding to CSI-ReportConfig containing a list of subconfigurations provided by csi-ReportSubConfigToAddModList, starting from the first symbol of the earliest of each CSI-RS / CSI-IM / SSB occasion not later than the corresponding CSI reference resource for channel or interference measurement. Starting from the first symbol of the earliest of each CSI-RS / CSI-IM resource associated with all configured sub-configurations for the report,Or, occupy CPU(s) from the first symbol of the earliest of each CSI-RS / CSI-IM resource associated with all activated / triggered sub-configurations for a semi-persistent CSI report corresponding to a CSI-ReportConfig containing a list of sub-configurations provided by csi-ReportSubConfigToAddModList, to the last symbol of the configured PUSCH / PUCCH carrying the report.

[0212] - An aperiodic CSI report occupies CPU(s) from the first symbol after the PDCCH that triggers the CSI report until the last symbol of the scheduled PUSCH carrying the report. If the PDCCH reception contains two PDCCH candidates from each of the two search space sets, as described in Section 10.1 of [6, TS 38.213], the PDCCH candidate that ends later in time is used for the purpose of determining the CPU occupation duration.

[0213] - An initial semi-persistent CSI report on PUSCH following a PDCCH trigger occupies CPU(s) from the first symbol after the PDCCH until the last symbol of the scheduled PUSCH carrying the report. If the PDCCH reception contains two PDCCH candidates from each of the two search space sets, as described in Section 10.1 of [6, TS 38.213], the PDCCH candidate that ends later in time is used for the purpose of determining the CPU occupation duration.

[0214] - A semi-persistent CSI report on PUSCH configured such that the upper-level parameter codebookType is set to 'typeII-Doppler-r18' or 'typeII-Doppler-PortSelection-r18' occupies CPU(s) from the first symbol of the KP-th latest among consecutive periodic / semi-persistent CSI-RS occasions that are not later than the CSI reference resource to the last symbol of PUSCH carrying the report. Here, K P∈ The value of {1,2,4} is determined by the terminal capability (UE capability).

[0215] For a CSI report with a CSI-ReportConfig having a CSI-RS-ResourceSet where the upper layer parameter reportQuantity is set to 'none' and the upper layer parameter trs-Info is not configured, the CPU(s) are occupied for a certain number of OFDM symbols as follows.

[0216] - Semi-persistent CSI reports (excluding initial semi-persistent CSI reports on PUSCH following the PDCCH that triggers the report) are from the first symbol of the earliest of each transmission occasion of the periodic or semi-persistent CSI-RS / SSB resources for channel measurement for L1-RSRP computation, to the last symbol of the latest of the CSI-RS / SSB resources for channel measurement for L1-RSRP computation in each transmission occasion. Occupies CPU(s) up to the symbol.

[0217] - An aperiodic CSI report is from the first symbol after the PDCCH that triggers the CSI report, the Z3 symbol after the first symbol after the PDCCH that triggers the CSI report, and after the last symbol of the latest of each CSI-RS / SSB resource. CPU(s) are occupied up to the last symbol among the symbols. Here, the aforementioned CSI-RS / SSB resources are for channel measurement for L1-RSRP calculation.

[0218] Here (Z3, ) is defined in Table 3.

[0219] In the Rel-19 AI / ML work item, discussions are underway regarding the possibility that when a terminal utilizes UE-side AI / ML to perform CSI reporting, operations similar to those of a CPU may be performed in AI / ML-based CSI reporting, as the terminal's AI / ML-related parallel computing power or computing resources (e.g., memory, hardware capability of GPUs for inference / actuation, etc.) may be limited. The relevant consensus points are as follows.

[0220] Agreement @ 9.1.1 Specification support for beam management

[0221] For the UE-side model, the existing CPU mechanism is used as a starting point for AI / ML-based CSI processing.

[0222] Future review (FFS) on whether to share overall CPU or count separately between legacy CSI reporting and AI / ML-based CSI reporting, and between AI / ML features / functionalities.

[0223] Further review (FFS) is required regarding whether it is fully applicable to BM-Case 1 and / or BM-Case 2.

[0224] Agreement @ 9.1.3 Specification support for CSI prediction

[0225] Regarding CSI prediction using a UE-side model, further study is conducted on the following matters concerning CSI processing criteria and timelines, at least with respect to inference.

[0226] - Whether to share CPUs or count them separately between legacy CSI reporting and AI / ML-based CSI reporting

[0227] - Whether to share processing units among AI / ML related features / functionalities or to count them separately

[0228] - Whether a new timeline is required for inference / whether it is updated, and whether a different timeline is required when functionality switches / activates

[0229] - Whether the legacy framework for active CSI-RS resources and port counting can be reused

[0230] Note: We strive to research CSI processing criteria that consider both BM cases and CSI cases, and use existing solutions as a starting point.

[0231] Meanwhile, the computing power or resources related to AI / ML on the terminal may vary depending on the UE vendor and UE implementation. Furthermore, even when performing inference under identical conditions (e.g., identical report content) for the same UE-side AI / ML reporting scenario (e.g., beam prediction reporting, CSI prediction reporting, positioning reporting, etc.), the amount of computing power or resources occupied or consumed may differ from terminal to terminal. Additionally, for specific UE-side AI / ML reporting scenarios, the terminal may not always be able to perform actuation or inference for all models or functionalities (due to issues such as terminal computing power and memory), and may need to receive specific models or functionalities from the NW-side and / or UE-side servers. This means that even if a terminal possesses the capability for specific AI / ML-related CSI reporting and positioning-related reporting, whether or not it can perform such reporting may be determined by whether the relevant UE-side AI / ML model or functionality is currently available. Consequently, Rel-19 standardization discussions are underway to allow the availability of such models or functionality to be reported to the base station through an applicability report procedure. The details of these standardization discussions are as follows.

[0232] <RAN2 논의>

[0233] For the functionality-based LCM of the UE-sided model for the beam management use case, RAN2 has been researching and reviewing the signaling procedure for applicable functionality reporting.

[0234] RAN2 agreed on the following understanding regarding terminologies:

[0235] - Supported functionalities refer to functionalities that a terminal (UE) can direct using UE capability information (via RRC / LPP signaling).

[0236] - Applicable functionalities refer to functionalities that the terminal (UE) is ready to apply for inference.

[0237] - Activated functionalities refer to functionalities that are already enabled to perform inference.

[0238] RAN2 also derived the following Agreement and signaling procedure (see Fig. 7) regarding applicable functionality reporting for the beam management UE-sided model:

[0239] Figure 7 illustrates a procedure for applicable functionality reporting.

[0240] Step 1: The Network sends a UECapabilityEnqiry message to a terminal (UE) to initiate a procedure for a terminal (UE) reporting its AI / ML supported functionalities.

[0241] Step 2: The terminal (UE) transmits a UECapabilityInformation message containing supported functionalities at the UE side to the network.

[0242] "Step 3": The following configurations are provided from the network (NW) to the terminal (UE):

[0243] 1) The terminal (UE) is allowed to perform UAI reporting (UE Assistance Information, UAI reporting) through OtherConfig.

[0244] 2) The network may provide network-side additional conditions. RRC signaling and whether it is mandatory or optional will be reviewed later (FFS).

[0245] 3) Configuration of supported functionalities (e.g., inference configuration) will be reviewed later (FFS). Content of configuration will also be reviewed later (FFS).

[0246] (Between "Step 3" and "Step 4") The UE determines applicable functionalities based on network-side additional conditions (if provided), UE-side additional conditions (conditions known internally to the UE), and model availability in the device. Whether other configurations (e.g., inference configurations) may be considered by the UE is to be reviewed later (FFS). How applicable functionality is determined when network-side additional conditions are not provided in Step 3 is also to be reviewed later (FFS).

[0247] "Step 4": The device (UE) reports applicable functionality in the following scenarios:

[0248] 1) When configured to provide applicable functionality via UAI and when there is a change in applicable functionality

[0249] 2) In response to a network-side additional condition requesting applicable functionality reporting in Step 3. Other network configurations (e.g., inference configuration) will be reviewed later (FFS).

[0250] Step 5:

[0251] 1) If an inference configuration based on supported functionality is not provided in step 3 (i.e., if an inference configuration is provided in step 5), the Network configures an inference configuration for the UE after reporting applicable functionality.

[0252] 2) If an inference configuration based on supported functionality is provided in step 3, whether to provide an updated configuration depends on the network implementation.

[0253] RAN2 also agreed that an applicable functionality may be activated by receiving its inference configuration when that inference configuration is provided at Step 5. The initial activation state is to be reviewed later (FFS). The initial state of the applicable functionality is to be reviewed later (FFS) when the inference configuration of the supported functionality is provided at Step 3. Additional L1 / L2 signaling for activation / deactivation is to be reviewed later (FFS). Whether multiple applicable functionalities can be activated simultaneously is to be reviewed later (FFS). What the granularity of the functionality is is to be reviewed later (FFS).

[0254] The above Agreements were made based on the following assumptions:

[0255] The network-side additional condition is assumed to be the associated ID in RAN2 (this is an assumption made by many companies).

[0256] 1. UAI is supported, and the RRCReconfigurationComplete message can be used to report applicable functionality. The goal should be to align the design regarding how applicable functionalities are signaled. Applicability reporting content will be reviewed later (FFS).

[0257] 2. Whether the inference configuration can be signaled in step 3 will be reviewed later (FFS).

[0258] 3. When an applicable AI functionality becomes non-applicable, the UE may report this to the Network. How this is signaled (e.g., explicitly / implicitly) will be reviewed later (FFS). Different scenarios, such as whether it concerns active functionality, will be considered.

[0259] 4. The initiation of data collection and the configuration for data collection are under network control. How the network (NW) determines whether data collection should be initiated (e.g., via UE requests, via the UE directly, or via a UE server) will be reviewed later (FFS).

[0260] 5. For the discussion of AI / ML BM LCM operations, existing procedures and terminologies of the CSI Framework must be used, including those defined for aperioditic, semipersistent on PUCCH, semipersistent on PUSCH, and periodic reporting configurations (as / if defined on RAN1 while waiting for a response LS from RAN1).

[0261] 6. As of now, RAN2 does not define specific terminology for the activation or deactivation of AI / ML models. This discussion may be addressed again later.

[0262] Agreements

[0263] 1. When a functionality configured to be reported via UAI by the Network changes from a non-applicable state to an applicable state, the UE may report this to the Network. Detailed design to be reviewed later (FFS).

[0264] 2. When functionality becomes non-applicable, the terminal (UE) does not autonomously deactivate. The network (NW) is expected to deactivate active functionality when it receives a report from the terminal (UE) that the functionality is non-applicable.

[0265] 3. Whether the UE explicitly reports "non-applicable" functionality when there is a change in applicability will be reviewed later (FFS). Verify that this aligns with the RAN1 configuration design.

[0266] 4. Applicable functionality reporting during handover is supported using the same RRC procedure as the baseline as the RRC procedure specified within the same cell. Specifically, network-side additional conditions and / or inference configurations related to the target gNB are transmitted by the target gNB as part of the handover command (HO command), and in response, the terminal (UE) transmits an applicability report (either RRCReconfigurationComplete or UAI) to the target gNB after completing the handover.

[0267] 5. Source cell UAI can be transmitted from a source cell to a target cell using existing signaling. RAN2 does not consider further optimizations regarding UAI.

[0268] 6. For a BM use case for a UE-side model, data collection related configurations (e.g., measurement resources configuration) and associated IDs may be included in the training data collection configuration.

[0269] 7. Data Collection Configuration - For UE-side model training, the UE may send a request for data collection. What the request includes will be reviewed later (FFS).

[0270] 8. The network can provide data collection configuration at any point in time, regardless of whether there is a UE request.

[0271] 9. Methods for network control regarding the initiation and configuration of data collection are as follows:

[0272] The network can determine when to start / stop data collection and transmit the configuration.

[0273] The network can set whether the terminal (UE) is allowed to initiate a request for data collection.

[0274] 10. When the terminal (UE) is unable to perform data collection based on the received configuration, whether an indication from the terminal to the network is required will be reviewed later (FFS).

[0275] Agreements

[0276] 1. Inference configuration / parameters may be signaled in step 3, and / or inference configuration may be signaled in step 5 (i.e., option a and option b of RAN1).

[0277] 2. The full inference configuration is transmitted from CSI-ReportConfig.

[0278] 3. Upon receiving the full inference configuration, the terminal (UE) sends an initial applicability report from RRCReconfigurationComplete. The UAI may be sent to update the applicability.

[0279] 4. Signaling details for Option B (e.g., whether signaling occurs in CSI-ReportConfig or otherconfig) will be reviewed later (FFS).

[0280] Agreements applicability reporting and management

[0281] Explicit reporting of applicability / inapplicability is supported in initial and subsequent reporting, but only changed applicability is reported in subsequent reports. Whether to report the explicit cause is subject to future review (FFS).

[0282] If option A is set in step 3, for periodic CSI reporting, the terminal (UE) autonomously activates the applicable functionalities as reported via RRCReconfigurationComplete in step 4 (i.e., there is no need to wait for RRCReconfiguration in step 5).

[0283] The provided periodic CSI configuration must match the reported UE capabilities.

[0284] Option B will be reviewed later (FFS).

[0285] Semi-persistent and aperiodic CSI reporting of applicable functionality is enabled according to the legacy CSI framework:

[0286] - Semi-persistent reporting: Enabled by MAC CE / DCI

[0287] - Aperioditic CSI reporting: Activated by DCI

[0288] <RAN1 논의>

[0289] Agreement

[0290] - In Step 3, the following configurations are provided from the network (NW) to the terminal (UE):

[0291] - The terminal (UE) is allowed to perform UAI reporting through OtherConfig.

[0292] - The applicability report is based on A) and / or B).

[0293] - The container is designed by RAN2.

[0294] - A) One or more CSI-ReportConfigs for inference configuration (where the associated ID can be configured in the CSI framework applied as the working assumption)

[0295] - Note: The CSI report configuration for UE-side model inference cannot be activated immediately upon receiving step 3.

[0296] - B) One set or multiple sets of inference-related parameters for the applicability report only (not for inference)

[0297] - The container is designed by RAN2.

[0298] - As a starting point, a set of inference-related parameters selected from the IEs within CSI-ReportConfig and / or the IEs referenced by CSI-ReportConfig. For example, as follows:

[0299] - The associated ID

[0300] - Note: This does not mean that the associated ID is mandatory.

[0301] - Set A related information

[0302] - Set B related information

[0303] - Report content related information

[0304] - For BM-Case 2,

[0305] - Time instances related information for measurements

[0306] - Time instances related information for prediction

[0307] - In Step 4, the terminal (UE) reports applicability to all of the set(s) of inference-related parameters of one or more of A) and / or B).

[0308] - Further review regarding what other information is needed / what is needed along with applicability (FFS).

[0309] - If A) is set in step 3,

[0310] - Applicable aperiodic CSI Report and semi-persistent CSI Report can be activated / triggered by the network (NW) after applicability is reported.

[0311] - Applicable periodic CSI Report is considered activated only if the applicability of the corresponding CSI-ReportConfig is reported in RRCReconfigurationComplete.

[0312] - In Step 5, the network (NW) may optionally configure CSI-ReportConfig for inference configuration in RRCReconfiguration, where the associated ID may be configured in the CSI framework applied as a working assumption.

[0313] - Note: Step 5 may be optional if the terminal (UE) is already configured with CSI-ReportConfig in Step 3.

[0314] Conclusion

[0315] For the CSI-ReportConfig for inference configuration provided in step 5,

[0316] - Aperioditic CSI Report and semi-persistent CSI Report can be enabled / triggered by the network (NW) after RRCReconfigurationComplete.

[0317] - Periodic CSI Report is considered activated after RRCReconfigurationComplete.

[0318] - Note: The UE is not expected to be configured with a set of inference parameters that is non-applicable or a CSI-ReportConfig for inference settings for a non-applicable CSI-ReportConfig.

[0319] Any specification impact is a separate discussion.

[0320] To summarize the above discussion, similar to the existing UE capability report, the terminal can perform reporting on AI / ML supported functionalitys in Step 2, and in Step 4, the terminal can report to the NW regarding currently available functionalitys among these AI / ML supported functionalitys via an applicable functionality report. This reporting can be performed through the signaling procedures of UAI reporting via OtherConfig or / and RRCReconfigurationComplete. This reporting can be used to report available functionalitys or / and unavailable functionalitys. Since the terminal status regarding available / unavailable functionality may change even after the initial report, a subsequent report may be performed additionally.

[0321] Based on these standard discussions, the terminal's AI / ML-related computing power, parallel processing power / capability, memory consumption, or / and computing resources (hereinafter collectively referred to as "computing resources") occupied or consumed by the functionality that the terminal reports to the base station as applicable (or non-applicable) (hereinafter, the terminal's hardware capabilities are collectively called "computing resources") may vary by functionality depending on the size of the AI / ML model provided to the terminal by the server or trained by the terminal, or the type of AI / ML algorithm. There is a problem in that such varying computing resource occupancy / consumption by AI / ML functionality or model may not be static values, and even for the same functionality, the computing resources occupied or consumed can vary depending on the terminal implementation, terminal hardware capability, model size, and differences in AI / ML algorithms. Accordingly, the degree of occupancy / consumption of computing resources for such terminal-side specific functionality is related to the CPU (i.e., O) occupied by a specific CSI-ReportConfig in the existing NR. cpu It may be difficult to define values ​​like ) by standards or report them as static values ​​by UE capability reporting. Specifically, as the concept of legacy CPUs expands into AI / ML-based processing units (APUs) following the introduction of AI / ML-related features, the APU values ​​occupied / consumed may vary depending on the terminal-side functionality.

[0322] Based on this background, the present specification proposes a method for reporting, together with an applicability report, the CSI processing unit or / and AI / ML-based processing unit occupied by a specific report when a terminal performs beam prediction, CSI prediction, and positioning-related reporting using UE-sided AI / ML, and proposes a subsequent terminal operation.

[0323] For example, an AI / ML based processing unit, an AI / ML related processing unit, or an APU refers to the maximum processing unit or / and maximum processing resource (cf. N) related to AI / ML that the terminal reports (via UE capability). cpu The value occupied / consumed by a specific terminal-side AI / ML functionality / model within the legacy NR) value (cf, O cpu It may mean in legacy NR). The APU value occupied / consumed by a specific functionality / model of such a terminal may be expressed as an integer value or a real value, as a multiple of a specific unit value, or as one or more resources / units.

[0324] For example, 'APU' refers to a CPU involved in the processing of AI / ML model-based CSI reports (e.g., CSI reports related to prediction or CSI reports related to performance monitoring (e.g., prediction accuracy)). In other words, 'APU' is merely a term to distinguish it from conventional CPUs, and is not intended to limit the technical concept according to the embodiments of this specification to 'APU'. As a specific example, the CPU involved in the processing of conventional CSI reports may be referred to as the 'First CPU', and the CPU involved in the processing of the aforementioned AI / ML model-based CSI reports may be referred to as the 'Second CPU'. As a specific example, the number of First CPU(s) occupied for the processing of the CSI reports is O CPU Represented as, and the number of second CPU(s) occupied for processing the aforementioned AI / ML model-based CSI report is O CPU,x (e.g., O CPU,1 , O CPU,2 , O CPU,3 It can be expressed as .. etc.

[0325] In this specification, ' / ' may be interpreted as 'and', 'or', or 'and / or' depending on the context.

[0326] Proposal 1

[0327] When the terminal performs a report to the base station regarding UE-side AI / ML-related applicable functionality, the CSI processing unit (CPU) (i.e., O) occupied / consumed by each reported applicable ( / non-applicable) functionality cpuIt can report together with ) or / and AI / ML related processing unit (APU) values. More specifically, the terminal can report applicable functionality (functionalities) or / and non-applicable functionality (functionalities) by utilizing signaling of UAI reporting via OtherConfig or / and RRCReconfigurationComplete, and can report CPU or / and APU values ​​occupied / consumed by said functionality.

[0328] For example, applicable functionality may be represented by a CSI-ReportConfig related to inference (i.e., Option A of the background above related to applicability) or / and an inference-related parameter set (i.e., Option B of the background above related to applicability) by base station configuration, and the terminal may report that a specific inference-related CSI-ReportConfig or / and an inference-related parameter set configured by the base station as above is applicable (or non-applicable), and may also report the CSI processing unit (CPU) or / and AI / ML-related processing unit (APU) values ​​occupied or consumed by the said inference-related CSI-ReportConfig or / and inference-related parameter set. Such reporting may be performed by at least one of the following embodiments.

[0329] Example 1)

[0330] In reporting applicable functionality of Proposal 1 above, the terminal may report only the AI / ML related processing unit (APU) values ​​occupied / consumed by specific applicable / non-applicable functionality. If the reported functionality also occupies / consumes non-AI related CPU values ​​of legacy NR, these CPU values ​​may be defined by the legacy specification or by CPU values ​​newly defined for Rel-19 operation.

[0331] Example 2)

[0332] In the reporting of applicable functionality of the above Proposal 1, the terminal reports the AI / ML related processing unit (APU) value occupied / consumed by a specific applicable / non-applicable functionality, and simultaneously reports the CSI processing unit (CPU) value occupied / consumed by the said functionality (i.e., O cpu ) can also be reported. As another example, in applicable functionality reporting, the terminal can report the CSI processing unit (CPU) values ​​(i.e., O) occupied / consumed by specific applicable / non-applicable functionality. cpu Can only report )

[0333] Example 3)

[0334] In reporting applicable functionality of the above Proposal 1, the terminal is the AI / ML related processing unit (APU) value or / and CSI processing unit (CPU) value (i.e., O) occupied by a specific applicable / non-applicable functionality cpuIn addition to ), the CSI processing unit (CPU) value occupied by the CSI-ReportConfig that can be configured to perform performance monitoring for the corresponding functionality (i.e., O cpu ) or / and AI / ML related processing unit (APU) values ​​can be reported together.

[0335] Example 4)

[0336] In reporting applicable functionality according to Proposal 1 above, the terminal may report at least one of the following for a specific applicable / non-applicable functionality: i) a minimum processing time (Z / Z') value required when the terminal performs inference on the functionality and reports, ii) an additional processing time (additional timing offset) required in addition to the existing (legacy NR) Z / Z', or / and iii) a required memory-related capability (e.g., buffer status / memory status, or degree of memory / buffer occupancy, etc.).

[0337] Example 5)

[0338] The terminal may first report the (default) CPU value or / and (default) APU value occupied / consumed by a specific (supported) functionality utilizing the terminal's UE-side AI / ML (for a specific (sub)-use-case (e.g., beam prediction, CSI prediction, positioning, etc.)) via a UE capability report (e.g., corresponding to Step 2 in the applicability report procedure described in the background above), and then perform an additional applicability report (e.g., UAI reporting via OtherConfig or / and RRCReconfigurationComplete, in Step 4). The additional applicability report may include the CPU value or / and APU value (+ / - value) additionally occupied / consumed by the specific functionality.

[0339] For example, the APU value occupied / consumed by a specific functionality can be expressed as 1*x or 1+x. The value of x is 1 by default (the value reported via UE capability), and additional values ​​such as x=-0.5 / 0.5 / 1 / 2 may be reported through the applicability report submitted by the terminal. If (additional) CPU / APU values ​​for applicable / non-applicable functionality are not reported in the terminal applicability report, it may mean that the CPU / APU value reported in the capability report (Step 2) is applied for that functionality. For example, a default value may be reported, and additional values ​​may be reported. Specifically, the minimum processing time (Z / Z') value required for inference and reporting of the specific functionality mentioned in Example 4 above, the processing time (additional timing offset) additionally required in addition to the existing (legacy NR) Z / Z', or / and the default value for the required memory-related capability are reported through the UE capability report, and additional values ​​(+ / - values) may be reported later through the applicability report.

[0340] For example, the terminal may report candidate values ​​regarding the CPU value, APU value, minimum processing time (Z / Z') value occupied by a specific (supported) functionality, additional processing time required in addition to the existing Z / Z' (additional timing offset), and / or required memory-related capability values ​​through a UE capability report. Subsequently, when performing an applicability report, the terminal may report to the base station one candidate value corresponding to the applicable / non-applicable functionality among the multiple candidate values. This embodiment takes into account that regarding AI / ML models (for the same purpose) for a specific supported functionality of a specific sub-use-case, there may be a light model with low computational complexity and a heavy model with high computational complexity. The terminal may report candidate values ​​corresponding to multiple AI / ML models or algorithms available in terms of hardware capability in Step 2, and report the exact value for the specific functionality reported in Step 4 from among the candidate values.

[0341] In the above embodiments, the terminal reports a plurality of applicable / non-applicable functionalitys and may report a CPU value, APU value, Z / Z' value, Z / Z' related additional timing offset, or / and memory related capability for each functionality.

[0342] The base station can set / instruct the operation that the terminal must perform among the terminal operations of the above embodiments through base station setting / switching / activation / deactivation.

[0343] For example, in the embodiments of Proposal 1 above, the CPU, APU, minimum processing time (Z / Z') value occupied / consumed by a specific functionality, the additional processing time required in addition to the existing Z / Z' (additional timing offset), or / and the required memory-related capability may vary depending on the specific use-case (e.g., beam prediction (e.g., BM-case 1, BM-case 2), CSI prediction, and positioning). As a specific example regarding UE capability reporting, for BM-case 2, an offset related to the minimum processing time (Z / Z') value (e.g., Z3 / Z3') may be reported as a UE capability.

[0344] For example, in the embodiments of the above proposal 1, the CPU, APU, minimum processing time (Z / Z') value occupied / consumed by a specific functionality, the additional processing time (additional timing offset) required in addition to the existing Z / Z', or / and the required memory-related capability may also differ depending on the use-case, as may be the maximum value of the CSI processing unit (CPU) or / and AI / ML related processing unit (APU) that can be performed simultaneously when the terminal performs terminal report(s) utilizing UE-side AI / ML reported through the UE capability report.

[0345] For example, the maximum CPU / APU value for beam prediction, the maximum CPU / APU value for CSI prediction, and the maximum CPU / APU value for positioning can each be reported separately to the base station. Multiple terminal reports corresponding to each use-case, such as AI / ML-related CSI reports or / and positioning-related reports, can be performed (simultaneously) by the terminal, provided that they do not exceed the maximum CPU / APU value for each use-case.

[0346] According to Proposal 1, the following effects can be derived.

[0347] When a terminal reports the maximum value of a CSI processing unit (CPU) or / and an AI / ML related processing unit (APU) that can be executed simultaneously when performing terminal report(s) utilizing UE-side AI / ML through a UE capability report, the base station can determine the CPU or / and APU values ​​occupied or consumed by the UE-side AI / ML related functionality that the base station activates / will activate through the terminal report of Proposal 1, and based on these reported values, can perform activation / deactivation of the terminal's AI / ML related functionality so as not to exceed the maximum value of the terminal's CPU or / and APU (based on the capability report). Additionally, if the sum of the CPU or / and APU values ​​of multiple terminal AI / ML related functions activated simultaneously exceeds the maximum value of the CPU / APU based on the UE capability report (cf. N cpuIn the event that the value of the terminal is exceeded (in legacy NR), the terminal may drop or not perform measurement / inference / report for low-priority AI / ML related functionality without ambiguity between the base station and the terminal (so as not to exceed the maximum value of the terminal CPU or / and APU).

[0348] In addition, unlike non-AI / ML based CSI reporting where the Z / Z' value is clearly defined according to the existing ReportQuantity, as in Examples 4 / 5 of Proposal 1 above, in the case of AI / ML based CSI reporting, the minimum processing time consumed for AI / ML inference may vary depending on the terminal implementation. Through the UE capability report or applicability report, the terminal can eliminate ambiguity by sharing the timing constraints or memory constraints that the base station must guarantee between the terminal and the base station by reporting the minimum processing time or memory capability required when performing inference and reporting on the inference result for a specific supported / applicable functionality.

[0349] By extending the operation of Proposal 1 (Examples 1 to 5) above, when a two-sided model is utilized in CSI compression, when the applicable functionality (functionalities) of the two-sided model is reported, the CPU / APU value of the terminal occupied by the two-sided model (the terminal-side model of the two-sided model), the minimum processing time (Z / Z') value, the additional processing time required in addition to the existing Z / Z' (additional timing offset), or / and the required memory-related capability may also be reported. Likewise, when positioning information is reported using terminal UE-side AI / ML for positioning (e.g., Case 1: UE-based positioning with UE-side model, direct AI / ML or AI / ML assisted positioning), when the applicable functionality (functionalities) of the said UE-side model is reported, the terminal's CPU / APU value occupied by said functionality, the minimum processing time (Z / Z') value, the additional processing time required in addition to the existing Z / Z' (additional timing offset), or / and the required memory-related capability may also be reported.

[0350] 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 1) is as follows.

[0351] 1) The terminal (base station) receives (transmits) settings related to UE capability reporting.

[0352] 2) The terminal (base station) transmits (receives) the UE capability report.

[0353] The above UE capability report may include CPU / APU values ​​for specific (supported) functionality related to terminal-side AI / ML based on Proposal 1, minimum processing time (Z / Z') values, additional processing time required in addition to the existing Z / Z' (additional timing offset), or / and required memory-related capability values.

[0354] 3) The terminal (base station) receives (transmits) settings related to applicable / non-applicable functionality reporting.

[0355] 4) The terminal (base station) transmits (receives) an applicable / non-applicable functionality report.

[0356] The above applicable / non-applicable functionality report may include CPU / APU values, minimum processing time (Z / Z') values, additional processing time (additional timing offset) required in addition to the existing Z / Z', and / or required memory-related capability values ​​for specific (applicable / non-applicable) functionality related to terminal-side AI / ML based on Proposal 1.

[0357] 5) The terminal (base station) receives (transmits) report settings related to specific functionality and transmits (receives) AI / ML related reports.

[0358] The above terminal / base station operation is merely an example, and each operation (or step) is not necessarily essential; depending on the terminal / base station implementation method, the beam measurement / reporting operation of the terminal according to the aforementioned embodiments may be omitted or added.

[0359] < Background related to AI / ML beam management >

[0360] In the beam management use case, the sub-use cases were divided into BM-case1 and BM-case2, and a study was conducted on the performance analysis and potential specification impact of spatial domain beam prediction and temporal beam prediction.

[0361] In the Rel-18 AI / ML study, discussions were held regarding NW / UE-sided AI / ML operations that predict the best beam of Set A based on Set B measurements. For UE-sided AI / ML, an operation is required where the terminal measures Set B and reports the predicted Set A beam, while for NW-sided AI / ML, an operation is required where the terminal reports the Set B measurements.

[0362] The standardization agreements for Rel-19 UE-sided AI / ML to date are as follows.

[0363] Agreement

[0364] For UE-side models, at least for BM-Case1, the following is supported regarding the content of the inference result report.

[0365] Option 1: Beam information for the predicted Top K beams within the beam set

[0366] Option 2: Beam information for the predicted Top K beams within the beam set, and the RSRP of the predicted Top K beams

[0367] At least K=1, and for the maximum value, use FFS

[0368] For beam information, FFS

[0369] For the definition of the predicted Top K beam, FFS

[0370] For the definition of the reported RSRP where applicable, FFS

[0371] For other information within the report along with potential down selections among the following options, FFS

[0372] Option 3: Beam information for the predicted Top K beams within the beam set, and probability information for the predicted Top K beams

[0373] Regarding the quantization method of probability information, FFS

[0374] The probability information is the probability that the beam will become the Top 1 or Top K beam.

[0375] 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

[0376] Regarding the definition of the reported RSRP, FFS

[0377] Regarding the definition of reliability information and quantization methods, FFS

[0378] Other options are not excluded either.

[0379] Here, the beam set is Set A, which refers to the beams for UE prediction.

[0380] Agreement

[0381] For UE-side AI / ML models in BM-Case1 and BM-Case2:

[0382] Support Type 1 Performance Monitoring, includes the following two options:

[0383] Option 1 (NW-side performance monitoring):

[0384] UE sends reports to NW (to calculate performance metrics in NW)

[0385] Measurement results from resource sets for monitoring (e.g., L1-RSRP and / or RS index) are supported as report content.

[0386] Other content is FFS

[0387] The report is set / triggered by at least NW

[0388] Note: This may or may not have an additional spec impact.

[0389] Option 2 (UE-supported performance monitoring):

[0390] UE calculates performance metrics

[0391] Regarding how to report and what to report, FFS

[0392] Whether to trigger reporting based on events for Option 1 and / or Option 2 is FFS

[0393] FFS Type 2 Performance Monitoring

[0394] Agreement

[0395] The following working assumptions have been established.

[0396] Working Assumption

[0397] 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.

[0398] Agreement

[0399] For UE-side models, at least for the quantization of RSRP values ​​in inference result reports, the following is supported:

[0400] Support for differential RSRP reporting using existing quantization steps and ranges for L1-RSRP reporting

[0401] For BM-Case1, differential RSRP reporting between multiple beams is supported.

[0402] For BM-Case2, support for differential RSRP reporting between multiple beams across multiple time points.

[0403] Details are FFS

[0404] Agreement

[0405] For the UE-side model, at least for BM Case-1, two resource sets can be configured separately for Set A and Set B in the CSI report configuration in the inference result report.

[0406] Whether to support configuring a resource set solely for Set B is FFS.

[0407] 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.

[0408] The beam information in the inference report refers to the resource set of Set A.

[0409] Agreement

[0410] With respect to the UE-side AI / ML models in BM-Case1 and BM-Case2, for Option 2 (UE-supported performance monitoring), support at least Alternative 1: determine Top 1 or Top K beam prediction accuracy (with or without margins) by comparing the Top 1 or Top K beams based on the prediction results and measurements from the resource set / resources.

[0411] FFS: Detailed definition of the metric, including whether to configure or define a window for calculation

[0412] FFS: Includes other details related to how to configure resource sets / resources for monitoring, e.g.

[0413] Example: Whether / how to use the entire set of Set A for measurement. If the entire Set A is not configured, whether / how to define a metric.

[0414] FFS: Other Alternatives

[0415] Agreement

[0416] In BM-Case 2 of the UE-side model, the reference time of the earliest time instance for the prediction result considers at least the following potential down-selection alternatives:

[0417] Option 1: Based on the UL slot for reporting

[0418] Option 2: Based on CSI reference resources corresponding to the report

[0419] Option 3: Based on the latest transmission time of the CSI-RS / SSB resource within Set B for measurement for reporting, and this transmission time is not later than the CSI reference resource

[0420] Agreement

[0421] For UE-side AI / ML models, for BM-Case1, at least for inference, and for at least Set B, the following CSI-RS resource types for CMR are supported:

[0422] Periodic (P) CSI-RS

[0423] Semi-persistent (SP) CSI-RS

[0424] Aperiodic (AP) CSI-RS

[0425] For UE-side AI / ML models, for BM-Case 2, at least for inference, and for at least Set B, the following CSI-RS resource types for CMR are supported:

[0426] Periodic (P) CSI-RS

[0427] Semi-persistent (SP) CSI-RS

[0428] FFS: Aperiodic (AP) CSI-RS

[0429] Note: The above CSI-RS resources refer to resources used for beam management.

[0430] Agreement

[0431] For at least UE-side model monitoring of Monitoring Type 1 Option 2 (if applicable), consider at least the following options and include potential down-selection for monitoring configuration:

[0432] Option 1: Resource set(s) for monitoring and reporting configuration are configured within the CSI reporting configuration used for inference (if applicable).

[0433] FFS: Resource set(s) for monitoring

[0434] The UE measures resource set(s) for monitoring

[0435] FFS: When / how to report monitoring results

[0436] Option 2: Dedicated resource set(s) and reporting configuration for monitoring are configured within the dedicated CSI reporting configuration used for monitoring.

[0437] The dedicated reporting configuration used for monitoring is linked to the inference reporting configuration.

[0438] FFS: A method to check connectivity between RSs within resource set(s) for monitoring and Set A beams.

[0439] The UE measures resource set(s) for monitoring

[0440] FFS: When to report monitoring results

[0441] Agreement

[0442] For the UE-sided model, at least for BM-Case 1, the beam information in the inference result report is the CRI / SSBRI of the resource in Set A.

[0443] Agreement

[0444] For the UE-sided model for inference, in both BM-Case 1 and BM-Case 2, when Set A and Set B are configured within the CSI report configuration,

[0445] For Set A and Set B, two CSI-ResourceConfig IDs (CSI-ResourceConfigId) are configured separately, respectively.

[0446] Agreement

[0447] For Monitoring Type 1 Option 2 of UE-side model monitoring (where applicable), support is provided for reusing the CSI framework in the configuration for monitoring result reports in L1 signaling:

[0448] The dedicated resource set(s) for monitoring and the report configuration for monitoring are configured within the dedicated CSI report configuration used for monitoring.

[0449] The ID of the inference report configuration is configured within the configuration for monitoring to link the inference report configuration and the monitoring report configuration.

[0450] How to identify connections between RSs within resource set(s) for monitoring and Set A beams will be reviewed later (FFS).

[0451] Future review (FFS) on whether to support all combinations of time domain behavior of reportConfigType for inference reports and reportConfigType for monitoring reports

[0452] Timing-related issues will be reviewed later (FFS)

[0453] The terminal (UE) measures the dedicated resource set(s) for monitoring.

[0454] Agreement

[0455] For the report content of the inference results for the UE-sided model, the largest RSRP value is quantized into a 7-bit value in the range of [-140, -44] dBm with a step size of 1 dB, and the differential RSRP is quantized into a 4-bit value with a step size of 2 dB.

[0456] Note: The model output is a UE implementation matter and does not need to be RSRP subject to dBm value.

[0457] Agreement

[0458] For the report content of the inference results of the UE-sided model for BM-Case 1, the RSRP of the predicted beam(s) in the report of inference results is the predicted RSRP, where the predicted RSRP is based on the AI / ML output.

[0459] Note: How to reflect this in the specification is a separate discussion.

[0460] Agreement

[0461] For UE-side AI / ML model inference and BM-Case 2, in the quantization of RSRP values ​​of inference results in a report across multiple future time instances, the largest RSRP value based on the prediction of all time instances is the reference RSRP, and differential RSRPs in the report are computed relative to the reference RSRP.

[0462] Time instance information of the beam with the largest RSRP is additionally indicated in the report.

[0463] Agreement

[0464] Regarding inference, in the case of BM-Case 2 of the UE-side model,

[0465] The time gap between two consecutive future time instances is configured by the RRC, and the number N of future time instance(s) is configured by the RRC.

[0466] The time gap is [10ms, 20ms, 40ms, 80ms, 160ms]

[0467] N = [1, 2, 4, 8]

[0468] The reference time for the earliest time instance of the predicted results is based on the most recent occasion of the CSI-RS / SSB resource in Set B for measurement.

[0469] Here, the most recent occasion of the CSI-RS / SSB resource of Set B is the latest CSI-RS / SSB occasion no later than the corresponding CSI reference resource of the corresponding inference report.

[0470] Agreement

[0471] For the UE-sided model, the following is supported for the configuration of resources for data collection purposes:

[0472] CSI-ReportConfig can be used to configure resources for data collection purposes without CSI reporting.

[0473] One CSI-ResourceConfigId is configured for Set A.

[0474] One CSI-ResourceConfigId is configured for Set B.

[0475] Note: The UE performs measurement on all resources.

[0476] One or two associated IDs can be configured within the CSI-ReportConfig.

[0477] If Set B is identical to Set A or is a subset of Set A (i.e., if the NZP-CSI-RS-ResourceId / SSB-Index in the resource set for Set B is within the NZP-CSI-RS-ResourceId / SSB-Index in the resource set for Set A), one associated ID is constructed.

[0478] Otherwise, one associated ID is configured for Set A, and another one associated ID is configured for Set B.

[0479] Future Review (FFS): Whether to support aperioditic CSI RS and / or how to support

[0480] Note: This is not related to whether or how the delivery / transmission of the collected data for training the UE-sided model is supported.

[0481] Agreement

[0482] For the UE-sided model, in the CSI-ReportConfig for inference,

[0483] One or two associated IDs can be configured within the CSI-ReportConfig.

[0484] If Set B is identical to Set A or is a subset of Set A (i.e., if the NZP-CSI-RS-ResourceId / SSB-Index in the resource set for Set B is within the NZP-CSI-RS-ResourceId / SSB-Index in the resource set for Set A), one associated ID is constructed.

[0485] Otherwise, one associated ID is configured for Set A, and another one associated ID is configured for Set B.

[0486] Further Review (FFS): Applicability of aperioditic CSI RS for at least BM-Case 1

[0487] In addition to the aforementioned details regarding the CSI preprocessing unit (CPU) (e.g., existing operations defined in the standard and consensus matters related to AI / ML-based CSI reporting), the standard defines the minimum processing time of the terminal for CSI reports as follows. The values ​​of Z and Z' may be defined in the standard or reported by the terminal UE capability report.

[0488] First, we examine the previously defined behavior regarding CSI processing time.

[0489] When a CSI request field on DCI triggers CSI report(s) on PUSCH, the UE must provide a valid CSI report for the nth triggered report in the following cases:

[0490] The first uplink symbol carrying the relevant CSI report(s), including the effect of the timing advance, is symbol Z ref If you do not start earlier, and

[0491] The first uplink symbol carrying the nth CSI report, including the effect of the timing advance, is symbol Z' ref If it does not start earlier than (n).

[0492] Here, Z ref is from the end of the last symbol of the PDCCH that triggers the CSI report(s). It is subsequently defined as the next uplink symbol where the CP begins. Z' ref (n) is from the end of the last symbol of the latest in time among the following when aperiodic CSI-RS is used for channel measurement for the nth triggered CSI report It is subsequently defined by the following uplink symbol where the CP begins: an aperiodic CSI-RS resource for channel measurement, an aperiodic CSI-IM used for interference measurement, and an aperiodic NZP CSI-RS for interference measurement for CSI-ReportConfig (or for all triggered subconfigurations if CSI-ReportConfig includes multiple subconfigurations). T switch is defined in Section 6.4 and of Table 2 This applies only when applicable.

[0493] If the PUSCH directed by the DCI overlaps with another PUCCH or PUSCH, the CSI report(s) are multiplexed in accordance with the procedures of Section 9.2.5 of [6, TS 38.213] and, where applicable, Section 5.2.5; otherwise, the CSI report(s) are transmitted over the PUSCH directed by the DCI.

[0494] When a CSI request field on DCI triggers CSI report(s) on PUSCH, the first uplink symbol carrying said CSI report(s), including the effect of the timing advance, is symbol Z ref If you start earlier:

[0495] - If HARQ-ACK or transport blocks are not multiplexed on PUSCH, the UE can ignore the scheduling DCI.

[0496] When a CSI request field on DCI triggers a CSI report(s) on PUSCH, the first uplink symbol carrying the nth CSI report, including the effect of the timing advance, is symbol Z' ref If you start earlier than (n):

[0497] - If the number of triggered reports is one and HARQ-ACKs or transmission blocks are not multiplexed on PUSCH, the UE can ignore the scheduling DCI.

[0498] - Otherwise, the UE is not required to update the CSI for the nth triggered CSI report.

[0499] As described in Section 10.1 of [6, TS 38.213], if a PDCCH reception contains two PDCCH candidates from two respective sets of search spaces, the PDCCH candidate ending later in time is used to determine the last symbol of the PDCCH that triggers the CSI report(s).

[0500] Z, Z' and μ are defined as follows:

[0501] and and, where M is the number of CSI report(s) updated in accordance with Section 5.2.1.6, and corresponds to the m-th updated CSI report and is defined as follows:

[0502] - Table 2's , max{ μ PDCCH , μ CSI-RS , μ UL} ≤ 3, and when L=0 CPU is occupied (according to Section 5.2.1.6), a CSI is triggered without a PUSCH having a transmission block or HARQ-ACK or both, the CSI to be transmitted is a single CSI and corresponds to a wideband frequency-granularity corresponding to up to 4 CSI-RS ports within a single resource without CRI reporting, and CodebookType is set to 'typeI-SinglePanel' or reportQuantity is set to 'cri-RI-CQI'.

[0503] - Table 3 , if the CSI to be transmitted corresponds to broadband frequency granularity corresponding to up to 4 CSI-RS ports within a single resource without CRI reporting, and CodebookType is set to 'typeI-SinglePanel' or reportQuantity is set to 'cri-RI-CQI'.

[0504] - Table 3 , if the CSI to be transmitted corresponds to a broadband frequency granularity and reportQuantity is set to 'ssb-Index-SINR', 'cri-SINR', 'ssb-Index-SINR-Index', or 'cri-SINR-Index'.

[0505] - Table 3 , if reportQuantity is set to 'cri-RSRP', 'ssb-Index-RSRP', 'cri-RSRP-Index', or 'ssb-Index-RSRP-Index'. Here follows the capability beamReportTiming reported by the UE and KB l ...depends on the UE reported capability beamSwitchTiming defined in [13, TS 38.306], or when CSI reporting is configured with LTM-CSI-ReportConfig for L1-RSRP measurements.

[0506] - Table 3 or , depending on the UE reported capability, the codebookType is set to 'typeII-CJT-r18' or 'typeII-CJT-PortSelection-r18' and the corresponding NZP-CSI-RS-ResourceSet for channel measurements If composed of resources.

[0507] - Table 3 Using , CSI report It is configured as such, and the codebookType is set to 'typeII-Doppler-r18' or 'typeII-Doppler-PortSelection-r18', and the corresponding NZP-CSI-RS-ResourceSet for channel measurement is non-periodic with K CSI-RS resources.

[0508] - Table 3 Using , here =56.(K P -1) or 56.K P It is a symbol, and in accordance with reported UE capabilities, The ∈ {1,2,4} value is indicated by the UE capability, and the CSI report is Configured as such, where codebookType is set to 'typeII-Doppler-r18' or 'typeII-Doppler-PortSelection-r18', and the corresponding NZP-CSI-RS-ResourceSet for channel measurement is periodic or semi-persistent having a single CSI-RS resource.

[0509] - Table 3 Using or , depending on UE reported capability, CSI reporting It is configured as such, and the codebookType is set to 'typeII-Doppler-r18', and the corresponding NZP-CSI-RS-ResourceSet for channel measurement is non-periodic with K CSI-RS resources.

[0510] - Table 3 Using or , depending on UE reported capability, CSI reporting Configured as such, with codebookType set to 'typeII-Doppler-r18', and the corresponding NZP-CSI-RS-ResourceSet for channel measurement having a single CSI-RS resource in the case of periodic or semi-static.

[0511] - In other cases, Table 3 .

[0512] - μ in Tables 2 and 3 is min (μ PDCCH , μ CSI-RS , μ UL Corresponds to ). Here, μ PDCCH corresponds to the subcarrier interval of the PDCCH in which the DCI was transmitted, and μ UL corresponds to the subcarrier interval of the PUSCH to which the CSI report will be transmitted, and μ CSI-RSIt corresponds to the minimum subcarrier interval of the non-periodic CSI-RS triggered by DCI.

[0513]

[0514] Table 2 shows CSI computation delay requirement 1.

[0515]

[0516] Table 3 shows CSI computation delay requirement 2.

[0517] Meanwhile, the following discussions are underway regarding the CPU and AI / ML-related processing units occupied by the inference result reporting settings (including BM-case1 and BM-case2) utilizing the UE-side mode of Rel-19 AI / ML BM and CSI prediction.

[0518] Agreement

[0519] A dedicated AI / ML processing unit (PU) is introduced for AI / ML features for the device (UE).

[0520] The above AI / ML processing unit (AI / ML PU) is used to quantify the simultaneous processing of multiple CSI reports that are the subject of at least CSI-related AI / ML use cases (e.g., CSI compression (if supported), CSI prediction, BM spatial prediction, BM temporal prediction).

[0521] Agreement

[0522] With respect to the CSI report corresponding to the CSI-ReportConfig for Type 1 option 2 monitoring for the UE-sided model, am.

[0523] Note: The occupation duration is a separate discussion.

[0524] (FL2) Proposal 4.1-xa (APU in general)

[0525] Regarding the UE-side model, at least for AI / ML-based beam management, and at least for the processing of CSI reports for inference,

[0526] Regarding dedicated AI / ML processing units, This is occupied.

[0527] Further review (FFS)

[0528] additionally, or It can be reported by the UE capability.

[0529] The same occupation time applies to both the dedicated APU and the CPU (if reported).

[0530] (FL0 / FL2) Proposal 4.1-1a (Data Collection)

[0531] Regarding the UE-sided model, in relation to the CSI-ReportConfig for data collection, am.

[0532] To summarize the above, since the CSI report configuration for the performance monitoring report performs operations similar to existing beam measurement / report, O CPU It was agreed to occupy 1, and in the case of the CSI report setup for data collection, O CPU Discussions are being held regarding the operation between base station terminals occupying 0. Additionally, in the case of report settings for reporting inference results, discussions are underway regarding the simultaneous occupation of the AI / ML-related processing unit and the CPU. At this time, the discussion regarding the CPU occupied by the report settings for reporting inference results and the timeline of the AI / ML PU is explained with reference to Fig. 8.

[0533] Figure 8 is a diagram illustrating the CPU occupancy time associated with BM-Case 2.

[0534] Specifically, FIG. 8 illustrates the CSI processing criteria in BM-Case 2. Referring to FIG. 8, in the CSI report settings for inference related to BM-case 2 as described above, the terminal performs observations (e.g., reception) for multiple transmission occasions related to Set B. Prediction can be performed by utilizing the result values ​​of these multiple measurement occasions as inference inputs. Specifically, the terminal can report predicted Top-K beam(s) (e.g., K CRI(s) or K SSBRI(s)) and / or corresponding predicted RSRP values ​​for one or more future instances. The CSI report settings [represent] the AI / ML-related PU value O from the last transmission occasion of Set B resource(s) prior to the slot corresponding to / corresponding to the CSI reference resource. APU Occupies the value.

[0535] For example, the occupancy may be released at the last symbol where the reporting of the corresponding CSI report setting ends. This is during the period when the terminal performs inference based on the results of the measurements O APU It may be an assumption that APU(s) are occupied.

[0536] For example, O APUThe occupancy time of the APU(s) can be defined as follows. The said occupancy time can be defined as the time from the start of the last measurement prior to the slot corresponding to the CSI reference resource of the inference-related CSI report settings, or from X slot(s) or X ms or X symbol(s) (X value can be based on capability and / or configured by NW) after that time until the completion of the inference report.

[0537] For example, O APU The occupancy time of the APU(s) can be defined as from the time the last measurement prior to the slot corresponding to the CSI reference resource ended, or from X slot(s) or X ms or X symbol(s) (X value can be based on capability and / or configured by NW) after that time until the inference report is completed.

[0538] Occupying (legacy) O in the CSI report settings for inference related to inference BM-case2 CPU The timeline is discussed as shown in candidates 1 to 3 of Fig. 8. Candidate 1 continuously O from the time the observation is performed until the time the reporting of the setting ends. CPU It is a method of occupying. Candidate 2 is the O mentioned above. APU O that has the same timeline as the value occupancy CPUThis is the occupancy method. Candidate 3 is O only for terminal reporting, base station setup, and / or for a certain period of time defined by the specification, starting from each Set B measurement time point corresponding to the observation instance. CPU Possessing O APU O even while the value is occupied CPU This is the method by which the value is occupied.

[0539] In this case, for the above candidate 1 and candidate 3, the following problem (Problem 1) may occur. When measuring for one or more specific Set B occasions, O CPU When the value is occupied, a CSI report with a higher priority than the CSI report setting for inference related to the corresponding BM-case2 may be executed. Accordingly, N based on the terminal capability report CPU Exceeding the value may prevent measurements for one or more Set B transmission occasions from being performed, and a higher-priority CSI report may be executed instead. The report is O CPU value (i.e., O CPU When occupying multiple CPUs, a shortage of Set B measurement samples for inference input may occur, leading to problems where the smooth inference operation of the AI / ML model is not performed or the reliability of the inference result is reduced. This specification proposes a method to solve this problem. The following proposal relates to O CPU In the occupancy timeline, not only is the omission of measurements for specific Set B transmission occasions due to a situation similar to Problem 1 above, but also O related to the inference report APUIt is also applicable when a situation like the above problem 1 occurs in the occupancy timeline.

[0540] Below, we propose a method for reporting an inference result when a terminal performs DL Tx beam prediction for BM-case1 / BM-case2 using UE-sided AI / ML, and propose a subsequent terminal operation.

[0541] Proposal 2

[0542] When a situation such as the above problem 1 occurs, the terminal can perform an inference result report related to BM-case2 based on at least one of the following embodiments.

[0543] Example 1)

[0544] The terminal does not expect that measurements for one or more Set B transmission occasions (corresponding to observation instances / windows) will be missed as described above. Or / and the base station may perform such settings / instructions.

[0545] Example 2)

[0546] The terminal may not update the CSI report for which a measurement for one or more Set B transmission occasions (corresponding to the observation instance / window) is missing (i.e., UE is not required to update the CSI for the n-th triggered CSI report). Specifically, the terminal may report the reported value of the relevant report (in the case of AP / SP CSI reports) as the n-1th CSI report value, which is earlier than the activation / triggering time.

[0547] Example 3)

[0548] The terminal can ignore / drop CSI reports for which measurements for one or more Set B transmission occasions (corresponding to the observation instance / window) are missing.

[0549] Example 4)

[0550] In the case of a CSI report where a measurement for one or more Set B transmission occasions (corresponding to the observation instance / window) is missing, the terminal may ignore the scheduling DCI that triggered the aperiodic( / SP on PUSCH) CSI (in the case of an AP / SP CSI report).

[0551] Example 5)

[0552] In the case of a CSI report in which a measurement for one or more Set B transmission occasions (corresponding to the observation instance / window) is missing, the terminal may notify the base station through the CSI report that the confidence, probability, or / and accuracy of the inference result is poor or that a Set B measurement is missing (indicating whether the above problem has occurred). To perform this operation, a 1-bit field indicating the situation may be added relative to the contents of the CSI report of BM-case2. For example, the terminal's inference report is implemented by the terminal (e.g., interpolation / extrapolation for the missing part, copy from the nearest measurement occasion, based on model scalability), but the terminal may notify the base station of the situation regarding the degradation of prediction performance due to the omission through the above 1-bit field.

[0553] Example 6)

[0554] In the case of a CSI report in which a measurement for one or more Set B transmission occasions (corresponding to the observation instance / window) is missing, the terminal may report a dummy value or dummy bit agreed upon between the base station and the terminal regarding the inference result of a specific future instance for prediction (e.g., k-th beam information or / and the corresponding (k-th) predicted RSRP value) to notify the base station of the occurrence of the problem through the CSI report.

[0555] In the above embodiments, the operation of the above embodiments (e.g., Embodiment 1) to Embodiment 6)) can be performed between the base station and the terminal for a CSI report in which a measurement for a Set B transmission occasion (corresponding to an observation instance / window) greater than or equal to an X value set / instructed by the base station, an X value reported by the terminal, or / and an X value defined by the specification is omitted instead of one or more Set B transmission occasions (corresponding to an observation instance / window).

[0556] For example, the terminal may report to the base station as a UE capability i) the number of measurements that can be omitted (number of (consecutive) measurements) among the Set B transmission occasions (corresponding to an observation instance / window) or ii) the minimum number of (consecutive) measurements required for prediction (e.g., the minimum number of transmission occasions for Set B). If the number of omitted measurements is exceeded or the minimum number is not met, the terminal may perform an operation based on at least one of the embodiments 1 to 6 above.

[0557] As an additional embodiment, the aforementioned problems can be resolved through the following operations regarding the operation between the base station and the terminal itself concerning CPU or APU occupancy rules / timelines. For example, a CPU / APU occupancy rule can be defined to drop the CPU / APU for a specific CSI report if any part of its CPU / APU occupancy time overlaps with the CPU / APU occupancy time for a higher priority CSI report. In this case, the terminal's subsequent operation may follow previously defined actions (e.g., reporting a non-updated CSI and dropping the CSI report).

[0558] Unlike the previous case where a CSI report related to the existing occupied CPU was calculated preferentially, the above additional embodiment (in the case of candidate 1 / 3 for the CPU occupation timeline in the background above) proposes an action to drop the existing occupied CPU if a CSI corresponding to another higher priority CSI report is configured / activated / triggered during the period of occupation, even if a specific CSI report is occupying the CPU / APU preferentially.

[0559] The above operation may be extended to CSI reports in which measurements for one or more Set B transmission occasions (corresponding to observation instances / windows) are missing due to causes other than CPU-related causes.

[0560] The above operation may be extended to CSI reports related to inference results where a (single) Set B measurement of BM-case 1 is missing.

[0561] Additionally, the above operation may be extended to CSI reports in which one or more CSI-RS measurement instances (corresponding to observation instances / windows) for inference input in CSI prediction are missing.

[0562] The above embodiments may be operated by a combination of one or more embodiments.

[0563] According to Proposal 2, the following effects are derived.

[0564] According to Proposal 2 above, the CPU / APU occupancy rule / timeline of CSI reports related to AI / ML inference can be clarified. This can have the effect of clarifying the terminal's inference result reporting behavior in the event that an observation instance of a CSI report related to inference is omitted due to CPU / APU conflicts, etc.

[0565] 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 Proposed 2) is as follows.

[0566] 1) The terminal (base station) receives (transmits) settings related to beam measurement / reporting. The settings may include reporting settings related to Set A and Set B. The reporting settings may include inference result reporting settings related to BM-case1 / 2.

[0567] 2) The terminal (base station) receives (transmits) a message scheduling the transmission of a beam measurement report.

[0568] The transmission of reports scheduled by a base station can have periodic, semi-persistent, or dynamic time domain behavior.

[0569] The above report may be an inference result report utilizing UE-sided AI / ML.

[0570] 3) The terminal transmits (receives) a beam measurement report based on the above message.

[0571] The above report may be performed based on an embodiment of Proposal 2.

[0572] The above terminal / base station operation is merely an example, and each operation (or step) is not necessarily essential; depending on the terminal / base station implementation method, the beam measurement / reporting operation of the terminal according to the aforementioned embodiments may be omitted or added.

[0573] The above embodiments may be operated by a combination of specific embodiments.

[0574] In terms of implementation, operations of a base station / terminal according to the embodiments described above (e.g., operations based on at least one of Proposal 1 and / or Proposal 2) can be processed by the device of FIG. 11 (e.g., the processor (110, 210) of FIG. 11).

[0575] In addition, the operations of the base station / terminal according to the above-described embodiment (e.g., operations based on at least one of Proposal 1 and / or Proposal 2) 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).

[0576] 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.

[0577] FIG. 9 is a flowchart illustrating a method according to one embodiment of the present specification.

[0578] Referring to FIG. 9, a method according to one embodiment of the present specification includes a terminal performance information transmission step (S910), a setting information reception step (S920), and a CSI report transmission step (S930).

[0579] In S910, the terminal transmits a terminal capability information (UECapabilityInformation) message to the base station.

[0580] In S920, the terminal receives configuration information related to Channel State Information (CSI) from the base station.

[0581] 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 2. 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 / or ii) one or more resource settings (e.g., M≥1 CSI-ResourceConfig resource setting).

[0582] 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.

[0583] For example, the above setting information may include at least one of i) a first reporting setting related to prediction and / or ii) a second reporting setting related to prediction accuracy. Specifically, the one or more reporting settings may include at least one of i) a first reporting setting related to prediction and / or ii) a second reporting setting related to prediction accuracy.

[0584] As a specific example, the above-mentioned configuration information may include a reporting configuration related to a prediction (e.g., the first reporting configuration). The above-mentioned reporting configuration (e.g., the first reporting configuration) may include at least one of i) information related to a first resource configuration for measurement (e.g., an ID representing the first resource configuration, more specifically, a higher-level parameter resourcesForChannelMeasurement representing CSI-ResourceConfigId), ii) information related to a second resource configuration for prediction (e.g., an ID representing the second resource configuration (CSI-ResourceConfigId), more specifically, a higher-level parameter resourcesForChannelPrediction-r19 representing CSI-ResourceConfigId), and / or iii) information regarding the number of one or more time instances (e.g., a higher-level parameter nrofTimeInstance-r19).

[0585] More specifically, the above reporting setting (e.g., the above first reporting setting) may be related to BM-case1. Specifically, the above reporting setting (e.g., the above first reporting setting) may include i) information related to a first resource setting for measurement and ii) information related to a second resource setting for prediction.

[0586] More specifically, the above reporting setting (e.g., the above first reporting setting) may be related to BM-case2. Specifically, the above reporting setting (e.g., the above first reporting setting) may include i) information related to a first resource setting for measurement, ii) information related to a second resource setting for prediction, and iii) information regarding the number of one or more time instances.

[0587] 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).

[0588] 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.

[0589] 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.

[0590] 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 CSI report described below may be based on the best CRI(s) or best SSBRI(s).

[0591] For example, the report quantity of the second report setting above can be set to pai (or rs-pai).

[0592] 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.

[0593] 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).

[0594] 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.

[0595] 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.

[0596] For example, the third resource setting may include information regarding a third resource set(s) for measurement (e.g., the resource set(s) described above for monitoring). As a specific example, the third resource setting may include a list of SSB resources or CSI-RS resources for measurement.

[0597] In S930, the terminal may transmit a CSI report to the base station containing predicted information based on the second resource setting. For example, the CSI report may be associated with BM-case1 or BM-case2. Each case is described below.

[0598] As a specific example of BM-case1, the terminal can transmit a CSI report containing predicted information based on the second resource setting to the base station.

[0599] As a specific example of BM-case2, the terminal may transmit to the base station a CSI report containing predicted information based on the second resource setting for each of the one or more time instances.

[0600] For example, the predicted information may include predicted CSI parameter(s) per time instance (e.g., P-CRI(s) / P-SSBRI(s) / P-L1-RSRP(s) per time instance). Specifically, the predicted CSI parameter(s) may include predicted CSI parameter(s) based on the report quantity of the first reporting setting (e.g., P-CRI(s), P-SSBRI(s), and / or P-L1-RSRP(s)). To explain in more detail, the predicted information 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).

[0601] According to one embodiment, the CSI report may be transmitted only when at least X latest consecutive transmission occasions are received for each of the resources in the resource set for measurement based on the first resource setting, and otherwise, the CSI report may be dropped. This embodiment may be based on Embodiment 3) of Proposal 2. For example, the value of X may be indicated based on the UECapabilityInformation message.

[0602] For example, the above at least X latest consecutive transmission opportunities mean the latest transmission opportunities that are not later than the CSI reference resource associated with the CSI report, as defined in the Agreement described above.

[0603] Specifically, the above at least X recent consecutive transmission opportunities can be received no later than the CSI reference resource.

[0604] To explain the above-described CSI report transmission / drop operation in more detail, the CSI report may be transmitted only when at least X latest consecutive transmission occasions are received for each of the resources in the resource set for measurement based on the first resource setting, no later than the CSI reference resource, and otherwise, the CSI report may be dropped.

[0605] According to one embodiment, the UECapabilityInformation message may include information related to BM-case1 (e.g., a case where predicted information is reported) and / or BM-case2 (e.g., a case where predicted information is reported when one or more time instances are set) for inference based on a UE-side model. This embodiment may be based on Embodiment 5 of Proposal 1 and Proposal 2. The information for each case included in the UECapabilityInformation message will be described in detail below.

[0606] For example, the UECapabilityInformation message may include information related to BM-case2 for inference based on a UE-side model. The information related to BM-case2 may include i) information indicating the minimum number of received transmission opportunities (e.g., the minimum number of received transmission opportunities related to Set B) and ii) information regarding the number of CPUs (CSI Processing Units) occupied for processing the CSI report. X may be the minimum number of received transmission opportunities.

[0607] For example, the first uplink symbol carrying the above CSI report is i) the number of symbols related to the CSI calculation (e.g., or ) and ii) can be determined based on an offset (e.g., d) related to the number of symbols.

[0608] To explain in more detail with reference to the operation defined for the aforementioned CSI processing time, the first uplink symbol carrying the CSI report is a defined uplink symbol (e.g., Z ref , Z' refIt is determined by an uplink symbol that does not start earlier than (n). This operation takes into account the following technical considerations. In the case of an uplink symbol that starts earlier than the uplink symbol defined above, time for CSI calculation cannot be secured. Therefore, (to ensure minimum time for CSI calculation) the first uplink symbol carrying the CSI report is determined as an uplink symbol that does not start earlier than the uplink symbol defined above. The number of symbols (e.g., Z / Z') for determining the uplink symbol defined above is i) the number of symbols related to the CSI calculation (e.g., / ) and ii) it can be determined based on an offset (e.g., d / d') related to the number of symbols.

[0609] For example, the information related to the above BM-case2 may further include information indicating the value of the offset. The offset related to the number of symbols may mean an additional timing offset for the processing time required in addition to the processing time based on the number of symbols. In other words, the value of the offset is the number of symbols (e.g., and / or It may mean the value of an offset (e.g., d and / or d') for the relaxation of a timeline based on ).

[0610] For example, the UECapabilityInformation message may include information related to BM-case 1 for inference based on a UE-side model. The information related to BM-case 1 includes i) information regarding the number of CPUs (CSI Processing Units) occupied for processing the CSI report and ii) the number of symbols related to the CSI calculation (e.g., and / or It may include information indicating the value of the offset (e.g., d and / or d') for ).

[0611] For example, the above UECapabilityInformation message may include information related to BM-case1 and information related to BM-case2 for inference based on the UE-side model.

[0612] The information related to the above BM-case1 may include i) information regarding the number of CPUs (CSI Processing Units) occupied for the CSI report related to the above BM-case1 and ii) information indicating the value of a first offset regarding the number of symbols for CSI calculation. In this case, the CSI report related to the above BM-case1 is associated with a report setting that does not have information regarding one or more time instances.

[0613] The information related to the above BM-case2 may include i) information indicating the minimum number of received transmission opportunities (e.g., the minimum number of received transmission opportunities related to Set B), ii) information regarding the number of CPUs (CSI Processing Units) occupied for the CSI report related to the above BM-case2, and iii) information indicating the value of a second offset for the number of symbols for CSI calculation. In this case, the CSI report related to the above BM-case2 is associated with a reporting setting that includes information on one or more time instances.

[0614] According to one embodiment, the method may further include a step of receiving a terminal capability request (UECapabilityEnquiry) message. Specifically, the terminal may receive a terminal capability request (UECapabilityEnquiry) message from a base station. The step of receiving the terminal capability request (UECapabilityEnquiry) message may be performed prior to S910. The UECapabilityInformation message may include information related to supported AI / ML functionalities. This embodiment may be based on at least one of the embodiments related to step 2 of FIG. 7.

[0615] According to one embodiment, the method may further include a message transmission step related to applicable AI / ML functions. Specifically, the terminal may transmit a message containing information related to applicable AI / ML functions to a base station. This embodiment may be based on at least one of the embodiments related to step 4 / applicable functionality reporting of FIG. 7. The message transmission step related to applicable AI / ML functions may be performed before S920, after S920, or before S930.

[0616] For example, the information related to the applicable AI / ML functions may include information indicating the reporting configuration (e.g., CSI-ReportConfigId). As a specific example, based on the information related to the applicable AI / ML functions, one or more reporting configurations included in the configuration information may be indicated as applicable. As a specific example, the information related to the applicable AI / ML functions may include information indicating applicable reporting configuration(s) among one or more reporting configurations included in the configuration information.

[0617] For example, the above message may be an RRC ReconfigurationComplete message or a UEAssistanceInformation message.

[0618] For example, the information related to the above-mentioned applicable AI / ML functionalities includes i) the number of CPUs (CSI Processing Units) associated with at least one AI / ML function, ii) the number of additional CPUs occupied for said CPUs, and iii) the number of symbols associated with CSI calculation (e.g., and / or ) and / or iv) may include information on at least one of an offset related to the number of symbols (e.g., the additional timing offset described above). The present embodiment may be based on at least one of embodiments 1) to 5) of Proposal 1.

[0619] As a specific example, the at least one AI / ML function may include at least one of i) an AI / ML function related to the reporting setting related to the prediction and / or ii) an AI / ML function related to the reporting setting for performance monitoring. The present embodiment may be based on at least one of embodiment 3) and / or embodiment 4) of Proposal 1.

[0620] For example, the information related to the applicable AI / ML capabilities may include additional information regarding the information reported based on the UECapabilityInformation message. This embodiment may be based on Embodiment 5) of Proposal 1.

[0621] As a specific example, the above additional information may include an additional value for at least one of i) the minimum number of received transmission opportunities, ii) the number of CPUs occupied for processing the CSI report, and / or iii) an offset for the number of symbols associated with the CSI calculation.

[0622] As a specific example, the additional information may include information indicating one of the candidate values ​​reported based on the UECapabilityInformation message. The candidate values ​​may include candidate values ​​for at least one of i) the minimum number of received transmission opportunities, ii) the number of CPUs occupied for processing the CSI report, and / or iii) an offset for the number of symbols associated with the CSI calculation.

[0623] The method described above was described assuming BM-case 2 in relation to the CSI report transmission / drop operation. However, this is merely one example of a combination based on the embodiments described above. The method may also be configured around the transmission of capability information and the resulting operation for BM-case 1 and BM-case 2, respectively. This will be explained in detail below.

[0624] For example, the above method may include the steps of transmitting a terminal performance information (UECapabilityInformation) message, receiving configuration information related to channel state information (CSI), and transmitting a CSI report. The configuration information may include reporting settings related to prediction. The reporting settings may include at least one of i) information related to a first resource setting for measurement, ii) information related to a second resource setting for prediction, and / or iii) information regarding the number of one or more time instances. The CSI report may include predicted information based on the second resource setting. The predicted information may be related to one of BM-case1 and BM-case2. The UECapabilityInformation message may include information related to BM-case1 and BM-case2 for inference based on a UE-side model.

[0625] The above information related to the BM-case1 includes i) information regarding the number of CPUs (CSI Processing Units) occupied for the CSI report related to the BM-case1 and ii) the number of symbols for CSI calculation (e.g., and / or It may include information indicating the value of the first offset for ).

[0626] The above information related to the BM-case2 includes i) information indicating the minimum number of received transmission opportunities (e.g., the minimum number of received transmission opportunities related to Set B), ii) information regarding the number of CPUs (CSI Processing Units) occupied for the CSI report related to the BM-case2, and iii) the number of symbols for CSI calculation (e.g., and / or It may include information indicating the value of the second offset for ).

[0627] For example, based on the above reporting settings, and based on the fact that information regarding one or more time instances is not set, the first uplink symbol carrying the CSI report is i) the number of symbols associated with the CSI calculation (e.g., or ) and ii) can be determined based on the first offset (e.g., d1 or d1').

[0628] For example, based on the information regarding the one or more time instances set based on the above reporting settings, the first uplink symbol carrying the CSI report is i) the number of symbols associated with the CSI calculation (e.g., or ) and ii) may be determined based on the second offset (e.g., d2 or d2') which is different from the first offset.

[0629] Operations based on the above-described steps S910 to S930, the step of receiving a terminal capability request (UECapabilityEnquiry) message, and the step of transmitting messages related to applicable AI / ML functions 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 operations based on steps S910 to S930, the step of receiving a terminal capability request (UECapabilityEnquiry) message, and the step of transmitting messages related to applicable AI / ML functions.

[0630] The embodiments described above will be explained in detail below in terms of base station operation.

[0631] The steps described below—S1010 to S1030, the step of transmitting a terminal performance request (UECapabilityEnquiry) message, and the step of receiving messages related to applicable AI / ML functions—correspond to operations based on the steps described in FIG. 9—S910 to S930, the step of receiving a terminal performance request (UECapabilityEnquiry) message, and the step of transmitting messages related to applicable AI / ML functions. 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.

[0632] FIG. 10 is a flowchart illustrating a method according to another embodiment of the present specification.

[0633] Referring to FIG. 10, a method according to another embodiment of the present specification includes a terminal performance information receiving step (S1010), a setting information transmission step (S1020), and a CSI report receiving step (S1030).

[0634] In S1010, the base station receives a terminal capability information (UECapabilityInformation) message from the terminal.

[0635] In S1020, the base station transmits configuration information related to Channel State Information (CSI) to the terminal.

[0636] For example, the above setting information may include reporting settings related to a prediction. The reporting settings may include i) information related to a first resource setting for measurement, ii) information related to a second resource setting for prediction, and / or iii) information regarding the number of one or more time instances.

[0637] In S1030, the base station can receive a CSI report from the terminal containing predicted information based on the second resource setting.

[0638] For example, the CSI report may be received only when at least X recent consecutive transmission opportunities for each of the resources in the resource set for measurement based on the first resource setting are received by the terminal, and otherwise, the CSI report may be dropped. The value of X may be indicated based on the UECapabilityInformation message.

[0639] According to one embodiment, the method may further include a step of transmitting a terminal capability request (UECapabilityEnquiry) message. Specifically, a base station may transmit a terminal capability request (UECapabilityEnquiry) message to a terminal. The step of transmitting the terminal capability request (UECapabilityEnquiry) message may be performed prior to S1010.

[0640] According to one embodiment, the method may further include a step of receiving a message related to applicable AI / ML functions. Specifically, a base station may receive a message from a terminal containing information related to applicable AI / ML functions. The step of receiving a message related to applicable AI / ML functions may be performed before S1020, after S1020, or before S1030.

[0641] The method described above was described assuming BM-case 2 in relation to the CSI report reception / drop operation. However, this is merely one example of a combination based on the embodiments described above. The method may also be configured around the reception of capability information and the subsequent operation for BM-case 1 and BM-case 2, respectively. This will be explained in detail below.

[0642] For example, the above method may include the steps of receiving a terminal performance information (UECapabilityInformation) message, transmitting configuration information related to Channel State Information (CSI), and receiving a CSI report. The configuration information may include reporting settings related to prediction. The reporting settings may include at least one of i) information related to a first resource setting for measurement, ii) information related to a second resource setting for prediction, and / or iii) information regarding the number of one or more time instances. The CSI report may include predicted information based on the second resource setting. The predicted information may be related to one of BM-case1 and BM-case2. The UECapabilityInformation message may include information related to BM-case1 and BM-case2 for inference based on a UE-side model.

[0643] The above information related to the BM-case1 includes i) information regarding the number of CPUs (CSI Processing Units) occupied for the CSI report related to the BM-case1 and ii) the number of symbols for CSI calculation (e.g., and / or It may include information indicating the value of the first offset for ).

[0644] The above information related to the BM-case2 includes i) information indicating the minimum number of received transmission opportunities (e.g., the minimum number of received transmission opportunities related to Set B), ii) information regarding the number of CPUs (CSI Processing Units) occupied for the CSI report related to the BM-case2, and iii) the number of symbols for CSI calculation (e.g., and / or It may include information indicating the value of the second offset for ).

[0645] For example, based on the above reporting settings, and based on the fact that information regarding one or more time instances is not set, the first uplink symbol carrying the CSI report is i) the number of symbols associated with the CSI calculation (e.g., or ) and ii) can be determined based on the first offset (e.g., d1 or d1').

[0646] For example, based on the information regarding the one or more time instances set based on the above reporting settings, the first uplink symbol carrying the CSI report is i) the number of symbols associated with the CSI calculation (e.g., or ) and ii) may be determined based on the second offset (e.g., d2 or d2') which is different from the first offset.

[0647] Operations based on the above-described S1010 to S1030, the step of transmitting a terminal capability request (UECapabilityEnquiry) message, and the step of receiving a message related to applicable AI / ML functions can be implemented by the device of FIG. 11. For example, referring to FIG. 11, a base station (100) can control one or more transceivers (130) and / or one or more memories (140) to perform operations based on S1010 to S1030, the step of transmitting a terminal capability request (UECapabilityEnquiry) message, and the step of receiving a message related to applicable AI / ML functions.

[0648] 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 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).

[0649] 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.

[0650] FIG. 11 is a drawing showing the configuration of a first device and a second device according to an embodiment of the present specification.

[0651] The first device (100) may include a processor (110), an antenna unit (120), a transceiver (130), and a memory (140).

[0652] 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).

[0653] 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.

[0654] 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.

[0655] The second device (200) may include a processor (210), an antenna unit (220), a transceiver (230), and a memory (240).

[0656] 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).

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] 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.

[0662] 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 transmitting a terminal performance information (UECapabilityInformation) message to a base station by the terminal; The step of receiving configuration information related to Channel State Information (CSI) from the base station by the terminal, wherein the configuration information includes reporting settings related to prediction, and The above reporting setting includes i) information related to a first resource setting for measurement, ii) information related to a second resource setting for prediction and / or iii) information regarding the number of one or more time instances; and The method includes the step of transmitting a CSI report containing predicted information based on the second resource setting to the base station by the terminal; For each of the resources in the resource set for measurement based on the first resource setting above, the CSI report is transmitted only when at least X latest consecutive transmission occasions are received, and otherwise, the CSI report is dropped. A method characterized in that the value of X is indicated based on the UECapabilityInformation message. In Article 1, A method characterized in that at least X recent consecutive transmission opportunities are received no later than the CSI reference resource. In Article 1, The above UECapabilityInformation message includes information related to BM-case2 for inference based on the UE-side model, and The above information includes i) information indicating the minimum number of received transmission opportunities and ii) information regarding the number of CPUs (CSI Processing Units) occupied for the processing of the CSI report, and A method characterized in that X is the minimum number of the received transmission opportunities. In Paragraph 3, The first uplink symbol carrying the above CSI report is determined based on i) the number of symbols associated with the CSI computation and ii) an offset associated with the number of symbols, and A method characterized by further including information indicating the value of the offset in the above information. In Article 1, The method further includes the step of receiving a terminal performance request (UECapabilityEnquiry) message, and A method characterized in that the above UECapabilityInformation message includes information related to supported AI / ML functions (supported Artificial Intelligence / Machine Learning, AI / ML, functionalities). In Article 5, A method characterized by further including the step of transmitting a message containing information related to applicable AI / ML functionalities. In Article 6, A method characterized by the information related to the applicable AI / ML functions including information indicating the reporting settings. In Article 6, A method characterized in that the above message is an RRC Reconfiguration Complete message or a UE Assistance Information message. In Article 6, A method characterized in that the information related to the applicable AI / ML functionalities includes information regarding at least one of i) the number of CPUs (CSI Processing Units) related to at least one AI / ML functional, ii) the number of additional CPUs occupied for said CPUs, iii) the number of symbols related to CSI calculation, and / or iv) an offset related to said number of symbols. In Article 9, A method characterized in that the above-mentioned at least one AI / ML function comprises at least one of i) an AI / ML function related to the reporting setting related to the prediction and / or ii) an AI / ML function related to the reporting setting for performance monitoring. In Article 6, A method characterized in that the information related to the above-mentioned applicable AI / ML functionalities includes additional information regarding the information reported based on the UECapabilityInformation message. In Article 11, A method characterized by including at least one additional value for the above additional information, i) a minimum number of received transmission opportunities, ii) a number of CPUs (CSI Processing Units) occupied for processing the CSI report, and / or iii) an offset for the number of symbols related to CSI computation. In Article 11, A method characterized by the above additional information including information indicating one of the candidate values ​​reported based on the above UECapabilityInformation message. 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 13, 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 13, 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 such that the terminal performs all steps of the method according to any one of claims 1 to 13. In terms of method, A step of receiving a terminal performance information (UECapabilityInformation) message from a terminal via a base station; A step of transmitting configuration information related to Channel State Information (CSI) to a terminal by the base station, wherein the configuration information includes reporting settings related to prediction, and The above reporting setting includes i) information related to a first resource setting for measurement, ii) information related to a second resource setting for prediction and / or iii) information regarding the number of one or more time instances; and The method includes the step of receiving a CSI report containing predicted information based on the second resource setting from the terminal by the base station; For each of the resources in the resource set for measurement based on the first resource setting above, the CSI report is received only when at least X latest consecutive transmission occasions are received by the terminal, and otherwise, the CSI report is dropped. A method characterized in that the value of X is indicated based on the UECapabilityInformation message. 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 17.

Images