Method and apparatus for transmitting and receiving performance information in a wireless communication system

Abstract

According to an embodiment of the present disclosure, a method for a wireless communication system, which is executed by a terminal, includes transmitting capability information and transmitting information related to one or more capability values ​​based on range information, the capability information including the range information related to at least one capability value, the at least one capability value being associated with at least one feature supported by the terminal.

Description

[Technical Field]

[0001] SUMMARY The present disclosure relates to methods and apparatus for transmitting and receiving performance information in a wireless communication system. [Background technology]

[0002] Mobile communication systems were developed to provide voice services while ensuring user activity. However, the scope of mobile communication systems has expanded beyond voice to include data services, and currently, explosive traffic growth is causing resource shortages and users are demanding faster services, so more advanced mobile communication systems are required.

[0003] The requirements for next-generation mobile communication systems are significant: they must be able to accommodate explosive data traffic, dramatically increase the transmission rate per user, accommodate a significantly increased number of connected devices, achieve extremely low end-to-end latency, and be energy efficient. To achieve this, various technologies are being researched, including dual connectivity, massive multiple input multiple output (MIMO), in-band full duplex, non-orthogonal multiple access (NOMA), super wideband support, and device networking.

[0004] A cellular communication system can implement different capabilities / features for each terminal, and the terminal reports the corresponding capabilities / features to the base station / network. Such capabilities / features are determined when the terminal is implemented, and the procedure for reporting the capabilities is performed only once.

[0005] When a communication function is implemented based on a model, the function can be implemented using a single model or multiple models. For example, a specific model can be implemented for a scenario / setting / environment depending on the environment in which the function operates. When a specific communication function is implemented using multiple models, the performance / capability may differ for each model. Therefore, the capability of a terminal for the same communication function may change depending on the model. Summary of the Invention [Problem to be solved by the invention]

[0006] As mentioned above, when communication capabilities are implemented based on multiple models, the dynamically changing capabilities of the terminal cannot be reported through the existing UE capability reporting procedure (which is performed only once).

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

[0008] The technical problems to be achieved in this specification are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those having ordinary skill in the art to which the present invention pertains from the following description. [Means for solving the problem]

[0009] According to an embodiment of the present disclosure, a method performed by a terminal in a wireless communication system includes transmitting capability information and transmitting information related to one or more capability values ​​based on range information. The capability information includes range information related to at least one capability value. The at least one capability value is associated with at least one feature supported by the terminal.

[0010] The at least one capability value may include a value related to at least one of i) channel state information (CSI), ii) a prediction related to CSI and / or a beam, iii) positioning, and / or iv) a model.

[0011] The CSI-related value may include at least one of: i) a maximum CSI compression ratio; ii) a maximum payload size for CSI compression; iii) a supported pre / post processing mode; and / or iv) a compression quality indicator.

[0012] The prediction may be related to the time domain or the spatial domain.

[0013] The value associated with the prediction in the time domain may include at least one of i) a predictable maximum time instance and / or ii) a prediction accuracy.

[0014] The value associated with the prediction in the spatial domain may include at least one of: i) a maximum supportable ratio between a first set associated with Reference Signal (RS) measurements and a second set associated with the prediction; and / or ii) a size of the second set.

[0015] The positioning related capability value may include a positioning accuracy related metric.

[0016] The values ​​associated with the model may include at least one of: i) a value related to whether fine-tuning associated with the model is supported; ii) a minimum time required for training, updating, fine-tuning, switching, or selection of the model; and / or iii) a value related to fallback of communication functionality based on the model.

[0017] The range information may include at least one of: i) candidate values ​​for each capability value; ii) a minimum value for each capability value; and / or iii) a maximum value for each capability value.

[0018] The one or more capability values ​​based on the range information may include a capability value based on each of one or more time instances.

[0019] The one or more time instances may be associated with at least one of i) a first point in time associated with the transmission of information and / or ii) a second point in time a certain time period after the first point in time.

[0020] The method may further include receiving a configuration based on the capability information.

[0021] The configuration based on the Capability Information may include at least one of i) a configuration related to reporting one or more capability values ​​and / or ii) an initial configuration related to at least one function.

[0022] The method may further include receiving a configuration based on the one or more capability values.

[0023] The configuration based on the one or more capability values ​​may include information for setting or resetting related to the at least one function.

[0024] Prior to transmission of the information relating to the one or more capability values, the lowest capability value among the capability values ​​based on the range information may be applied.

[0025] Prior to transmission of the information associated with the one or more capability values, a fallback mode associated with the capability value may be applied.

[0026] The capability information may further include information related to an initial capability value, which may be associated with a fallback mode.

[0027] A terminal operating in a wireless communication system according to another embodiment of the present specification includes one or more transceivers, one or more processors, and one or more memories coupled to the one or more processors and configured to store instructions.

[0028] The instructions, when executed by the one or more processors, configure the one or more processors to perform all steps of any one of the methods.

[0029] According to still another embodiment of the present disclosure, an apparatus includes one or more memories and one or more processors operatively coupled to the one or more memories.

[0030] The one or more memories store instructions that, when executed by the one or more processors, cause the one or more processors to perform all steps of any one of the methods.

[0031] According to yet another embodiment of the present disclosure, one or more non-transitory computer-readable media store instructions executable by one or more processors to configure the one or more processors to perform all steps of any one of the methods.

[0032] According to yet another embodiment of the present disclosure, a method performed by a base station in a wireless communication system includes receiving capability information and receiving information associated with one or more capability values ​​based on range information, the capability information including range information associated with at least one capability value, the at least one capability value associated with at least one function supported by a terminal.

[0033] A base station operating in a wireless communication system according to another embodiment of the present specification includes one or more transceivers, one or more processors, and one or more memories coupled to the one or more processors and configured to store instructions. The instructions, when executed by the one or more processors, configure the one or more processors to perform all of the steps of the method. [Effects of the Invention]

[0034] According to embodiments herein, one or more capability values ​​based on range information are reported.

[0035] Therefore, information about (dynamic) fluctuations in communication functions due to factors such as model changes, model re-training, and model updates can be notified to the network.

[0036] In addition, terminal settings related to communication functions (e.g., CSI compression, CSI / beam prediction, positioning, etc.) may be changed / updated to settings that match the current terminal capabilities.

[0037] Furthermore, the performance of model-based communication functions can be optimized to dynamically change terminal capabilities.

[0038] The effects obtained in this specification are not limited to those mentioned above, and other effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention pertains from the following description. [Brief explanation of the drawings]

[0039] [Figure 1] Illustrate a functional framework for an AI / ML model. [Figure 2] 1 illustrates operations related to UE capability transfer. [Figure 3] 1 illustrates a signaling procedure according to an embodiment of the present disclosure; [Figure 4]1 is a flowchart illustrating a method performed by a terminal according to an embodiment of the present specification. [Figure 5] 10 is a flowchart illustrating a method performed by a base station according to another embodiment of the present disclosure. [Figure 6] 1 is a diagram illustrating the configuration of a first device and a second device according to an embodiment of the present specification. DETAILED DESCRIPTION OF THE INVENTION

[0040] Preferred embodiments of the present invention will now 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 invention and is not intended to represent the only embodiments in which the present invention can be practiced. The following detailed description includes specific details to provide a thorough understanding of the present invention. However, those skilled in the art will recognize that the present invention can be practiced without such specific details.

[0041] In some cases, well-known structures and devices may be omitted or shown in block diagram form, focusing on the core functions of each structure and device, in order to avoid obscuring the concepts of the present invention.

[0042] Hereinafter, downlink (DL) refers to communication from a base station to a terminal, and uplink (UL) refers to communication from the terminal to the base station. In the downlink, the transmitter may be part of the base station, and the receiver may be part of the terminal. In the uplink, the transmitter may be part of the terminal, and the receiver may be part of the base station. The base station may also be expressed as a first communication device, and the terminal may also be expressed as a second communication device. A base station (BS) may also be replaced with terms such as a fixed station, NodeB, evolved-NodeB (eNB), Next Generation NodeB (gNB), base transceiver system (BTS), access point (AP), network (5G network), AI system, road side unit (RSU), vehicle, robot, unmanned aerial vehicle (UAV), augmented reality (AR) device, and virtual reality (VR) device. Furthermore, a terminal may be fixed or mobile, and may be replaced with terms such as UE (User Equipment), MS (Mobile Station), UT (user terminal), MSS (Mobile Subscriber Station), SS (Subscriber Station), AMS (Advance Mobile Station), WT (Wireless terminal), MTC (Machine-Type Communication) device, M2M (Machine-to-Machine) device, D2D (Device-to-Device) device, vehicle, robot, AI module, drone (Unmanned Aerial Vehicle, UAV), AR (Augmented Reality) device, VR (Virtual Reality) device, etc.

[0043] AIML related explanation

[0044] Advances in AI / ML (artificial intelligence / machine learning) technology are making the nodes and terminals that make up wireless communication networks more intelligent and sophisticated.

[0045] In particular, the intelligence of networks / base stations is expected to enable the rapid optimization, derivation, and application of various network / base station decision parameter values ​​according to various environmental parameters.

[0046] The environmental parameters may include at least one of the distribution / location of base stations, the distribution / location / material of buildings / furniture, etc., the location / movement direction / speed of the terminal, and weather information. However, the above parameters are merely examples, and the environmental parameters may further include other environmental parameters associated with the network / base station determination parameters in addition to the listed parameters.

[0047] The network / base station determined parameter values ​​may include at least one of the transmit / receive power of each base station, the transmit power of each terminal, the precoder / beam of the base station / terminal, the time / frequency resource allocation for each terminal, and the duplex mode of each base station, although the above parameters are only examples, and the network / base station determined parameter values ​​may further include other parameters determined by the network / base station in addition to the listed parameters.

[0048] In line with this trend, many standardization organizations (e.g., 3GPP (registered trademark: the same below), O-RAN) are considering the introduction of AI / ML, and active studies on this are also underway.

[0049] Although AI / ML can easily be referred to as deep learning-based artificial intelligence in a narrow sense, conceptually it can be divided as follows:

[0050] - Artificial Intelligence: This refers to any automation that allows machines to replace the work that humans should do.

[0051] - Machine Learning: Machines learn patterns for decision-making from data without being explicitly programmed with rules.

[0052] - Deep Learning: An artificial neural network-based model that allows machines to perform feature extraction and judgment from unstructured data in one go. The algorithm relies on a multi-layer network of interconnected nodes for feature extraction and transformation inspired by the biological nervous system, i.e., the neural network. Common deep learning network architectures include deep neural networks (DNNs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs).

[0053] As mentioned above, artificial intelligence (AI) is the broadest concept of AI / ML, and deep learning is the narrowest concept of AI / ML. Machine learning (ML) can be interpreted as a concept narrower than artificial intelligence but broader than deep learning.

[0054] AI / ML typologies based on various criteria

[0055] - Offline vs Online

[0056] Offline Learning

[0057] - Offline learning strictly follows the sequential steps of database collection, learning, and prediction. In other words, collection and learning are performed offline, and the completed program can be installed in the field and used for prediction work. This offline learning method is used in most situations.

[0058] Online Learning

[0059] - Recently, data that can be used for learning is continuously generated via the Internet. This method of incrementally improving performance through intensive additional learning using additional data is called online learning.

[0060] Classification by AI / ML Framework Concept

[0061] -Centralized Learning

[0062] In centralized learning, training data collected from multiple different nodes is reported to a centralized node, and all data resources, storage, learning (e.g., supervised, unsupervised, reinforcement learning), etc. are executed on a single centralized node.

[0063] - Federated Learning

[0064] Federated learning is where a collective model is built on data spread across distributed data owners. Instead of bringing the data to the model, the AI / ML model is brought to the data source, allowing local nodes / individual devices to collect data and train their own copies of the model, without the need to report source data back to a central node.

[0065] In federated learning, the parameters / weights of an AI / ML model are returned to a centralized node to support general model training. The advantages of federated learning include increased computational speed and superior information security. This means that there is no need to upload personal data to a central server, preventing the leakage and misuse of personal information.

[0066] - Distributed Learning

[0067] Distributed learning describes the concept of machine learning processes being scaled and distributed across a cluster of nodes: training models are split and shared across multiple nodes working simultaneously to speed up model training.

[0068] Classification by learning method

[0069] - Supervised Learning

[0070] Supervised learning is a machine learning task whose goal is to learn a mapping function from input to output given a labeled dataset. The input data is called training data, and has known labels or outcomes. Examples of supervised learning are:

[0071] 1) Regression: Linear Regression, Logistic Regression

[0072] 2) Instance-based Algorithms: k-Nearest Neighbor(KNN)

[0073] 3)Decision Tree Algorithms:CART

[0074] 4) Support Vector Machines (SVM)

[0075] 5) Bayesian Algorithms: Naive Bayes

[0076] 6) Ensemble Algorithms: Extreme Gradient Boosting, Bagging: Random Forest

[0077] Supervised learning can be further grouped into regression and classification problems, where classification is about predicting a label and regression is about predicting a quantity.

[0078] Unsupervised Learning

[0079] Unsupervised learning is a machine learning task that aims to learn functions that explain hidden structure from unlabeled data. The input data is unlabeled and there is no known outcome. Some examples of unsupervised learning include K-means clustering, principal component analysis (PCA), nonlinear independent component analysis (ICA), and LSTM.

[0080] - Reinforcement Learning

[0081] In reinforcement learning (RL), an agent interacts with the environment based on a trial-and-error process with the aim of optimizing a long-term goal through goal-directed learning. Below are some example RL algorithms:

[0082] 1) Q-learning

[0083] 2) Multi-armed bandit learning

[0084] 3) Deep Q Network

[0085] 4)State-Action-Reward-State-Action (SARSA)

[0086] 5)Temporal Difference Learning

[0087] 6)Actor-critic reinforcement learning

[0088] 7) Deep deterministic policy gradient

[0089] 8) Monte-Carlo tree search

[0090] Reinforcement learning can be further grouped into model-based reinforcement learning and model-free reinforcement learning.

[0091] Model-based reinforcement learning: RL algorithms that use predictive models, different dynamic states of the environment, and models that lead to compensation to obtain transition probabilities between states.

[0092] Model-free reinforcement learning: RL algorithms based on values ​​or policies that achieve maximum future rewards, in multi-agent environments / states, are computationally less complex, and do not require an accurate representation of the environment.

[0093] RL algorithms can also be classified as value-based RL vs. policy-based RL, policy-based RL vs. policy-free RL, etc.

[0094] Representative model of deep learning

[0095] 1. FFNN (Feed-Forward Neural Network)

[0096] An FFNN consists of an input layer, a hidden layer, and an output layer.

[0097] 2. RNN (Recurrent Neural Network)

[0098] RNN is a type of artificial neural network in which hidden nodes are connected by directional edges to form a cyclic structure (directed cycle). It is a model suitable for processing sequential data such as voice and text.

[0099] 3. CNN(Convolution Neural Network)

[0100] CNNs are used for two purposes: to reduce model complexity and to extract good features by applying convolution operations, which are commonly used in the fields of video processing and image processing.

[0101] - Kernel or filter: a unit / structure that applies weights to inputs of a specific range / unit

[0102] - Stride: The range of movement of the kernel within the input.

[0103] - feature map: the result of applying a kernel to the input

[0104] - padding: Value added to adjust the size of the feature map

[0105] - Pooling: Operations to downsample feature maps to reduce their size (e.g., max pooling, average pooling)

[0106] 4. Auto encoder

[0107] An autoencoder is a neural network that receives a feature vector x and outputs the same or similar vector x'. In an autoencoder, the input and output nodes have the same features.

[0108] Figure 1 illustrates the functional framework of an AI / ML model.

[0109] The definitions of each term and the operations by function in the framework shown in FIG. 1 are based on Table 1 below.

[0110] [Table 1] JPEG2026504916000003.jpg121139

[0111] Data Set

[0112] Data sets used in AI / ML are divided into training data, validation data, and test data, which are defined as follows:

[0113] - Training data

[0114] Data set for training the model

[0115] - Validation data

[0116] A data set for validating a model that has already been trained

[0117] Validation data is a data set that is typically used to prevent overfitting of the training data set.

[0118] Validation data is a dataset used to select the best model from various models trained during the training process. Therefore, validation data can be considered a dataset related to training.

[0119] - Test data

[0120] Dataset for final evaluation. Test data is unrelated to training.

[0121] For the data set, a full training set containing a certain percentage of the aforementioned data may be used.

[0122] As an example, a training set containing training data and validation data in a ratio of 8:2 or 7:3 may be used.

[0123] As an example, a training set containing training data, validation data, and test data in a ratio of 6:2:2 may be used.

[0124] Collaboration level

[0125] Depending on whether or not the AI ​​ / ML function is capable between the base station and the terminal, the cooperation level can be defined as shown in Table 2 below.

[0126] [Table 2]

[0127] The cooperation levels in Table 2 are merely examples and may be modified and utilized differently depending on the implementation. For example, a cooperation level that combines two or more of the cooperation levels illustrated may be defined / utilized.

[0128] UE capability transfer

[0129] FIG. 2 illustrates operations associated with UE capability transfer.

[0130] 2, when the UE Capability Transfer procedure is initiated, the UE receives a UECapabilityEnquiry from a network (e.g., a base station), and transmits UECapabilityInformation to the network.

[0131] When receiving a UECapabilityEnquiry from the network, the specific operation of the UE compiling and transmitting UE capability information may be based on Table 3 below.

[0132] [Table 3] JPEG2026504916000006.jpg23138

[0133] JPEG2026504916000007.jpg190140JPEG2026504916000008.jpg77138

[0134] JPEG2026504916000009.jpg190140JPEG2026504916000010.jpg131139

[0135] JPEG2026504916000011.jpg190139JPEG2026504916000012.jpg57138

[0136] JPEG2026504916000013.jpg190140JPEG2026504916000014.jpg77139

[0137] The operations based on FIG. 2 and Table 3 can be implemented in combination with the embodiments described below (at least one of Method 1, Method 1-1, Method 1-2 and / or Method 1-3, and an extended embodiment of Method 1).

[0138] Recently, there has been active effort to apply AI / ML (artificial intelligence / machine learning) technology to wireless communication networks. In particular, 3GPP Rel-18 has begun a study on applying AI / ML technology to the air interface between terminals and networks. In this study, beam management (BM), CSI acquisition, and positioning are considered as the main use cases for grafting AI / ML to the air interface. This specification proposes a more efficient method for reporting terminal capabilities / functions in accordance with the grafting of AI / ML technology.

[0139] In this document, ' / ' means 'and', 'or', or 'and / or' depending on the context. In this specification, 'terminal' and 'UE' can be used interchangeably with the same / similar meaning, and 'base station', 'network', and 'TRP' can also be used interchangeably with the same / similar meaning from the perspective of air-interface.

[0140] In a cellular communication system, different capabilities / functions can be implemented for each UE, and therefore, a procedure is included in which the UE reports the corresponding capabilities / functions to the base station / network. In the 3GPP system, this procedure is called the UE capability reporting procedure (see Figure 2 and Table 3).

[0141] When implementing an AI / ML-based communication function (e.g., CSI, beam management, positioning, mobility, etc.), the function can be implemented using a single or multiple AI / ML models. For example, scenario / configuration / environment-specific AI / ML models can be implemented depending on the environment in which the function operates (e.g., macro cell or indoor cell, base station / terminal density, terminal movement speed, etc.). Here, each model has the same structure (e.g., AI / ML algorithm (e.g., CNN, RNN), number of nodes, number of (hidden) layers, input / output parameter configuration, etc.), but the parameter sets trained for the environment may differ. Alternatively, each model may differ not only in its parameter set but also in part in its structure.

[0142] Generally, the UE capability reporting procedure (see, for example, Figure 2 and Table 3) is performed once immediately after network connection. This is because the terminal functionality is determined at the terminal implementation stage and does not change during implementation. When a specific communication function is implemented using multiple AI / ML models, the performance / capability of each model may differ. Therefore, the terminal's capability / functionality / performance for the same communication function can be changed according to changes in the AI / ML model.

[0143] Even when a specific communication function is realized by a single AI / ML model, the performance of the AI / ML model can change due to changes in the environment (e.g., cell movement, moving from the city center to the outskirts, changes in device density, etc.). In particular, if performance drops below a certain level and the model needs to be retrained, the device's capability / functionality / performance may change during the retraining.

[0144] In this specification, we propose a method for a terminal to quickly report information to the network when terminal capability / functionality / performance changes due to factors such as AI / ML model changes, re-training, model updates, etc.

[0145] By applying the methods described herein, the network can improve network performance by quickly performing relevant settings / instructions (e.g., CSI / beam report reset, beam change, positioning-related settings, etc.) based on the relevant reporting information.

[0146] Method 1

[0147] The terminal can report to the network (as a UE capability report) information about the range of capability values ​​supported by the terminal for specific communication functions (e.g., CSI / beam time / spatial domain prediction, CSI compression, positioning, mobility, etc.). The terminal separately / together reports capability value information for a specific point in time of the terminal within the capability value range (depending on the AI ​​ / ML model status (e.g., model re-training / update, model selection / switching, etc.)).

[0148] The capability values ​​may be the same as or similar to information reported through an existing UE capability report. For example, the capability values ​​may be reported based on an existing UE capability message (e.g., Table 3). For example, the capability values ​​may be reported based on Uplink Control Information (UCI). For example, the capability values ​​may be reported based on Medium Access Control Element (MAC CE).

[0149] The capability value may include information about the performance of the communication function realized through AI / ML. For example, the capability value may include the following information:

[0150] - CSI compression: maximum CSI compression ratio, maximum payload size for CSI compression, supported pre / post processing technique / mode, CQI (compression quality indicator), etc.

[0151] - CSI / beam TD (time domain) prediction: predictable maximum future time instance (per given channel environment (e.g. Doppler shift / spread)), prediction accuracy (per time instance / duration) (per given channel environment), etc.

[0152] - Beam SD (spatial domain) / TD prediction: actual maximum supportable ratio of Set A / Set B and / or size of Set A (for a given size of Set B), etc. The information in this example assumes that estimation / prediction is made for beam RSs in Set A based on measurement results of beam RSs included in Set B.

[0153] - Positioning: Positioning accuracy related metrics, etc.

[0154] - i) whether to support fine-tuning, ii) required minimum time for model (re-)training / update / fine-tuning / switching / selection, iii) scalability (e.g., the range of number of antenna ports, the maximum frequency bandwidth), etc.

[0155] If the base station does not know (or does not need to know) the AI / ML model configuration of the terminal, the minimum time, whether fine-tuning is performed, etc., can be replaced with information about an operation that will interrupt the corresponding (AI / ML-related) communication function (e.g., operation in fallback mode) or an operation that will degrade performance (e.g., interruption time / behavior or time / behavior related to fallback mode according to NW indication / configuration and / or UE report).

[0156] In existing systems, the above-listed terminal capability values ​​and similar terminal capability information are determined at the time of terminal hardware / software implementation, and therefore the terminal reports fixed values ​​related to terminal capabilities.

[0157] According to the proposed method, the terminal (priority) reports to the network information on the range of capability values ​​that can change due to the AI / ML model training status, model change, etc. For example, for the capability values ​​according to the above example, range information such as information on candidate values ​​of the corresponding value or information on maximum / minimum values ​​may be reported as UE capabilities. The following provides examples of information on the capability value ranges for the above example capability values.

[0158] - CSI compression: i) Maximum CSI compression ratio Candidate values ​​or min / max values (candidate values ​​or min / max value(s) of maximum CSI compression ratio), ii) candidate values ​​or min / max value(s) of maximum payload size for CSI compression, iii) supported pre / post processing technology / mode (supported pre / post processing techniques / modes), iv) CQI Candidate values ​​or min / max values (candidate values ​​or min / max value(s) of CQI) etc.

[0159] - CSI / beam TD (time domain) prediction: i) The maximum future time instance that can be predicted (per given channel environment) Candidate values ​​or min / max values (candidate values ​​or min / max value(s) of predictable maximum future time instance (per given channel environment))ii) Prediction accuracy (per time instance / period) (per given channel environment) Candidate values ​​or min / max values (candidate values ​​or min / max value(s) of prediction accuracy (per time instance / duration) (per given channel environment))).

[0160] - Beam SD (spatial domain) / TD prediction: The maximum support ratio of Set A / Set B Candidate values ​​or min / max values(candidate values ​​or min / max value(s) of maximum supportable ratio of Set A / Set B) and / or (candidate values ​​or min / max value(s) of size of Set A (for given size of Set B)).

[0161] - Positioning: Positioning accuracy related metrics Candidate values ​​or min / max values (candidate values ​​or min / max value(s) of positioning accuracy related metric), etc.

[0162] -General or use-case specific functionality:

[0163] i) whether always or occasionally or not to support fine-tuning, ii) The minimum time required to (re)train / update / fine-tune / switch / select a model Candidate values ​​or min / max values (candidate values ​​or min / max value(s) of required minimum time for model (re-)training / update / fine-tuning / switching / selection), iii) Supported Scalability Range (e.g. the range of number of antenna ports, the maximum frequency bandwidth), etc.

[0164] Along with or after the range information of the device capability values ​​as described above, (actual) device capability value information (relating to the status of the AI / ML model) at the current time and / or a specific future time is reported.

[0165] The UE capability value range information is information determined by the implementation of the UE and can be reported based on the RRC layer. For example, the UE capability value range information can be reported through the UE capability reporting procedure defined in FIG. 2 and Table 3.

[0166] The (actual) UE capability information may change in real time and therefore may be configured as separate report information (not a UE capability report). For example, the (actual) UE capability information may be reported based on a separate RRC message, MAC-CE, and / or UCI.

[0167] It may be assumed that the (actual) UE capability information is configured with UCI report information. For example, the corresponding UCI may be transmitted with a higher priority than other predefined UCIs (e.g., HARQ-ACK, scheduling request, CSI). For example, the corresponding UCI may be transmitted with a higher priority than at least CSI.

[0168] The reporting can be periodic / aperiodic / semi-persistent reporting, or can be event-driven / based reporting.

[0169] In the former case, the report can be made by setting / instructing the base station. For example, the report can be made when the base station instructs the terminal to change / (re)train / update the AI / ML model. The model change can also be made by instructing the model ID.

[0170] In the latter case, it can be defined as information that a device reports when a change in the device's AI / ML status occurs (e.g., model change, model (re)-training / update, etc.).

[0171] The following is an example of (actual) terminal capability value information relating to the example of the information regarding the capability value range.

[0172] - CSI compression: i) actual maximum CSI compression ratio at certain time instance(s) / duration(s), etc., among the reported candidate values ​​or min / max value(s); ii) actual maximum payload size for CSI compression at certain time instance(s) / duration(s), iii) actually supported pre / post processing technique / mode at certain time instance(s) / duration(s), iv) actual CQI at certain time instance(s) / duration(s)

[0173] - CSI / beam TD (time domain) prediction: i) actual predictable maximum future time instance (per given instance(s) / duration(s) among the reported candidate values ​​or min / max value(s); ii) actual prediction accuracy (per time instance / duration) (per given channel environment) at certain time instance(s) / duration(s) among the reported candidate values ​​or min / max value(s);

[0174] - Beam SD (spatial domain) / TD prediction: actual maximum supportable ratio of Set A / Set B and / or actual size of Set A (for a given size of Set B) at certain time instance(s) / duration(s) among the reported candidate values ​​or min / max value(s);

[0175] - Positioning (actual positioning accuracy related metric at certain time instance(s) / duration(s) among the reported candidate values ​​or min / max value(s);

[0176] -General or use-case specific functionality: i) whether to support fine-tuning at certain time instance(s) / duration(s) (if occasionally support fine-tuning), ii) the actually required minimum time for model (re-)training / update / fine-tuning / switching / selection at certain time instance(s) / duration(s) within the reported range, iii) Actual scalability (e.g., the range of number of antenna ports, the maximum frequency bandwidth) at certain time instance(s) / duration(s) within the reported range).

[0177] The following is an embodiment in which the proposed method is applied.

[0178] Exemplary procedure 1

[0179] [Step 1] UE → NW: The UE reports the candidate value range to the NW through a UE capability report.

[0180] [Step 2] NW → UE: The NW transmits information to the UE based on the report in Step 1 (i.e., the report of the candidate value range). The NW can transmit information based on at least one of the examples listed below.

[0181] i) UE reporting configuration / indication for Step 3 (e.g. PUSCH / PUCCH configuration / allocation for the report in Step 3),

[0182] ii) (initial) configuration / indication of related feature(s) / parameter(s) (e.g., CSI / beam report configuration (TD prediction window, CSI compression ratio, etc.) for CSI compression or CSI / beam prediction, set A / set B beam configuration, etc.);

[0183] Note: Step 3 Depending on the UE reporting method, the Step 3 UE reporting configuration / instruction may be performed before procedure 1 (e.g., configuration for periodic reporting), before, after, or after procedure 1 (e.g., report activation / trigger in MAC-CE / DCI after configuration in RRC). Alternatively, the Step 3 UE reporting configuration / instruction may be omitted (e.g., when Step 3 reporting is a MAC-CE-based event-based reporting method).

[0184] Therefore, the setting / instruction of the functions / parameters related to the UE capability report and the setting / instruction of the Step 3 UE report may be separate or may be simultaneous / combined.

[0185] [Step3] UE → NW (event-based or periodic / semi-persistent / aperiodic report): The UE reports its current capability to the NW. For example, the reporting may be performed on an event basis. For example, the reporting may be performed periodically / semi-statically / aperiodically.

[0186] For example, the reported capability may be a capability for a specific future perspective (e.g., a point in time after the reporting time + X ms / slot, where X value may be a specified value, a value set / instructed by the base station, or a value selected by the terminal) rather than a current perspective. For example, the reported capability may include all capability information for multiple perspectives (e.g., reporting all of the capability value at the reporting time and the capability value at the reporting time + X ms / slot).

[0187] [Step 4] NW → UE: Based on the report in Step 3, the NW transmits (re-)configuration / indication of related feature(s) / parameter(s) to the UE.

[0188] The process of setting / instructing the function / parameter in Step 2 and the process of setting / instructing the function / parameter in Step 4 may be transmitted via the same or different signaling structures and / or messages (formats). For example, an adjustment / offset value for the parameter value instructed in Step 2 may be instructed in Step 4 (e.g., an adjustment value for the prediction window start timing / duration, a variation value for the CSI compression ration, addition / deletion information for the set B beam). Step 4 may be performed based on the same layer message as Step 2 or a lower layer message (e.g., Step 2 via RRC, Step 4 via MAC-CE).

[0189] In the above embodiment, if there is a time interval between the terminal capability value range information report (Step 1) and the terminal's (actual) terminal capability value information report (Step 3), the base station may need to (initially) configure related communication functions depending on the reported terminal capability value range information. In such a case, the following methods 1-1 to 1-3 may be considered.

[0190] Method 1-1

[0191] According to this embodiment, the terminal may apply / use the lowest capability value within the range of the reported capability values, where the lowest capability value may be a capability value of a fallback / non-AI / ML mode used when AI / ML is not applied.

[0192] Method 1-2

[0193] According to this embodiment, the terminal can apply / use a specific capability value (e.g., basic / mandatory / default capability value), where the specific capability value may be a capability value of a fallback / non-AI / ML mode used when AI / ML is not applied.

[0194] Method 1-3

[0195] The terminal may report the initial / currently applicable (actual) terminal capability information (e.g., current / initial / default capability) together with the capability range information as the network. For example, the report may be included in the existing UE capability report and / or information reported based on Step 1.

[0196] The 'initial / currently applicable (actual) device capability value' may be a capability value related to the performance of the AI / ML model applied at that time, or a capability value for a fallback / non-AI / ML mode.

[0197] Method 1-1 is also applicable to the exemplary procedure 1. The NW can set / instruct functions / parameters related to the UE capability report in Step 2 based on the lowest capability value in the UE report in Step 1.

[0198] Step 2 of the exemplary procedure 1 is performed based on the UE report in Step 1. When methods 1-2 are applied, the (initial) configuration / indication of related feature(s) / parameter(s) procedure can be performed based on the specified / defined capability value in Step 2. Therefore, when methods 1-2 are applied, the corresponding procedure can be performed regardless of the time of the UE report in Step 1.

[0199] The following is an embodiment in which methods 1 to 3 are applied based on exemplary procedure 1.

[0200] Exemplary procedure 2

[0201] [Step 1] UE→NW: The UE reports a candidate value range including current / initial / default values ​​to the NW through a UE capability report. Information based on the following example 1 or 2 can be transmitted from the UE to the NW.

[0202] Example 1) candidate values ​​+ current / initial / default value among the candidate values

[0203] Example 2) value range + current / initial / default value within the value range

[0204] [Step 2] NW → UE: The NW transmits information to the UE based on the report in Step 1 (i.e., the report of the candidate value range including the current / initial / default value). The NW can transmit information based on at least one of the examples listed below.

[0205] i) UE reporting configuration / indication for step 3 (e.g., PUSCH / PUCCH configuration / allocation for the report in step 3),

[0206] ii) (Initial) configuration / indication of related feature(s) / parameter(s) (e.g., CSI / beam report configuration for CSI compression or CSI / beam prediction (TD prediction window, CSI compression ratio, etc.), set A / set B beam configuration, etc.)

[0207] The information based on i) and ii) above can be based on reported current / initial / default values.

[0208] [Step 3] UE→ NW(event-based or periodic / semi-persistent / aperiodic report): The UE reports its current capability to the NW. In one example, the reporting may be performed on an event basis. In another example, the reporting may be performed periodically / statically / aperiodically.

[0209] [Step 4] NW → UE: Based on the report in Step 3, the NW transmits (re-)configuration / indication of related feature(s) / parameter(s) to the UE.

[0210] In the proposed method, it is assumed that the (actual) terminal capability value is reported as one value at a time. By expanding this method, the following method can be considered.

[0211] Extending Method 1

[0212] The terminal reports (as a UE capability report) information about the capability value range that the terminal supports to the network in relation to a particular communication function.

[0213] The terminal reports capability information for a specific point in time separately / together within the capability range (depending on the AI / ML model status (e.g., model re-training / update, model selection / switching, etc.)). In this case, multiple capability values ​​can be reported for the same point in time. When multiple capability values ​​are reported, the base station that receives them can set / indicate the capability value to actually apply.

[0214] The following is an embodiment in which the extension method is applied based on exemplary procedure 1.

[0215] Exemplary procedure 3

[0216] [Step 1] UE → NW: The UE reports the candidate value range to the NW through a UE capability report.

[0217] [Step 2] NW → UE: The NW transmits information based on the report in Step 1 (i.e., the report of the candidate value range) to the UE. Based on the report in Step 1, the NW transmits to the UE a UE reporting configuration / indication for Step 3 and / or an (initial) configuration / indication of related feature(s) / parameter(s).

[0218] [Step3] UE → NW (event-based or periodic / semi-persistent / aperiodic report): The UE reports its current capability to the NW. For example, the reporting may be performed on an event basis. For example, the reporting may be performed periodically / statically / aperiodically.

[0219] Here, multiple capability values ​​or a range of capability values ​​can be reported, taking into account the capability / relevant capability range of the AI / ML model applicable to a specific current / future point in time. The value reported in this step may correspond to some of the candidate values ​​reported in Step 1, or to some range within the range reported in Step 1.

[0220] [Step 4] NW → UE: Based on the report in Step 3, the NW transmits to the UE (re-)configuration / indication of (actual capability to be applied) and related feature(s) / parameter(s). In this step, the base station can set / indicate the capability value to be actually applied within the multiple capability values ​​or capability value range reported in Step 3. Alternatively, the relevant information (the capability value to be actually applied) can be implicitly set / indicated through the setting / indication of the related parameter / function.

[0221] In this specification, "beam" can mean a "spatial filter" or a "spatial relation" source RS, and can be interpreted as a QCL (type-D) RS, a TCI state, or (in the case of uplink) a spatial relation RS.

[0222] Although the proposed technology in this specification will be described based on UE AI / ML, this does not mean that the technology in this specification can be applied only to an AI / ML-enabled environment of a UE. The proposed technology in this specification can also be applied to an AI / ML-enabled environment of an entity / device other than a UE, or a non-AI / ML-enabled environment. Furthermore, the proposed technology in this specification may be applied to sidelink communication by applying another UE instead of a base station / network. Furthermore, the proposed technology in this specification can be utilized / applied in other environments or use cases where UE capability value fluctuations may occur due to factors other than AI / ML.

[0223] In an implementation aspect, the operations of the base station / terminal according to the above-described embodiments (e.g., operations based on at least one of Method 1, Method 1-1, Method 1-2, Method 1-3, and / or extended embodiments of Method 1) may be processed by the apparatus of FIG. 6 (e.g., the processors (110, 210) of FIG. 6) described below.

[0224] In addition, the operation of the base station / terminal according to the above-mentioned embodiments (e.g., operation based on at least one of Method 1, Method 1-1, Method 1-2, Method 1-3 and / or an extended embodiment of Method 1) may be stored in a memory (e.g., 140, 240 in FIG. 6) in the form of instructions / programs (e.g., instructions, executable code) for driving at least one processor (e.g., 110, 210 in FIG. 6).

[0225] In the following we take a closer look at the signaling procedures according to the above mentioned embodiments.

[0226] FIG. 3 illustrates a signaling procedure according to an embodiment of the present disclosure.

[0227] Specifically, Figure 3 shows an example of signaling between a user equipment (UE) and a network (NW) based on the proposed method. Here, the UE and network are merely an example, and various devices can be substituted. Figure 3 is provided for convenience of explanation only and does not limit the scope of this specification. Furthermore, some steps shown in Figure 3 may be omitted depending on the situation and / or settings.

[0228] It can correspond to any entity such as a base station, BS (Base Station), Node B, or TRP belonging to the NW in FIG.

[0229] The UE performs a reporting procedure (S305) related to the terminal capability value based on a proposed method (e.g., at least one of Method 1, Method 1-1, Method 1-2, Method 1-3, and / or an extended embodiment of Method 1). In this procedure, the range information of the terminal capability value may be included in the report to the base station.

[0230] Based on the proposed method (e.g., at least one of Method 1, Method 1-1, Method 1-2, Method 1-3 and / or an extended embodiment of Method 1), the base station performs (S310) the configuration of functions / parameters related to the terminal capability value reported in S305 and / or the configuration / instruction related to the subsequent S315 terminal report.

[0231] Based on the report in S305, the UE reports the terminal capability value for the reporting time or a specific past / future time based on a proposed method (e.g., at least one of Method 1, Method 1-1, Method 1-2, Method 1-3 and / or an extended embodiment of Method 1) (S315).

[0232] Based on the terminal's reported information (S315), the base station can (re)configure or instruct functions / parameters related to the terminal capability values ​​(S320).

[0233] In applying the above operation, step S310 (or a part thereof) may be executed before / after / simultaneously with step S305.

[0234] As mentioned above, the above-mentioned NW / UE signaling and operation can be realized by the devices described below (FIG. 6). For example, the NW (or base station) can be the first wireless device and the UE can be the second wireless device, and vice versa in some cases.

[0235] For example, the above-mentioned NW / UE signaling and operations may be processed by one or more processors 110, 210 of FIG. 6, and the above-mentioned NW / UE signaling and operations may also be stored in memory 140, 240 in the form of instructions / programs (e.g., instructions, executable code) for driving at least one processor 110, 210 of FIG. 6.

[0236] Hereinafter, the above-described embodiment will be described in detail from the viewpoint of the operation of a terminal and a base station with reference to Figures 4 and 5. The methods described below are only divided for the convenience of explanation, and it goes without saying that some components of one method may be replaced with some components of another method or may be combined with each other and applied.

[0237] FIG. 4 is a flowchart illustrating a method performed by a terminal according to an embodiment of the present specification.

[0238] Referring to FIG. 4, a method performed by a terminal according to an embodiment of the present specification includes a performance information transmitting step S410 and an information transmitting step S420 related to one or more performance values.

[0239] At S410, the terminal transmits capability information to the base station.

[0240] The capability information includes range information associated with at least one capability value.

[0241] The at least one capability value relates to at least one feature supported by the terminal.

[0242] As an example, this step may correspond to Step 1 in at least one of the above-mentioned Exemplary procedures 1 to 3.

[0243] The at least one capability value may be based on Method 1. According to one embodiment, the at least one capability value may include a value related to at least one of i) Channel State Information (CSI), ii) a prediction related to CSI and / or a beam, iii) positioning, and / or iv) a model.

[0244] As an example, the CSI-related value is

[0245] It may include at least one of: i) maximum CSI compression ratio; ii) maximum payload size for CSI compression; iii) supported pre / post processing modes; and / or iv) Compression Quality indicator.

[0246] As an example, the prediction may relate to the time domain or the spatial domain.

[0247] The value associated with the prediction in the time domain may include at least one of i) a predictable maximum time instance and / or ii) a prediction accuracy.

[0248] The values ​​associated with the prediction in the spatial domain may include at least one of i) a maximum supportable ratio of a first set associated with measurements of a Reference Signal (RS) and a second set associated with the prediction, and / or ii) a size of the second set.

[0249] As an example, the positioning-related capability value may include a positioning accuracy related metric.

[0250] As an example, the values ​​associated with the model may include at least one of: i) a value related to whether fine-tuning associated with the model is supported; ii) a minimum time required for training, updating, fine-tuning, switching, or selection of the model; and / or iii) a value related to fallback of communication functions based on the model.

[0251] According to one embodiment, the range information may include candidate values, minimum values, and / or maximum values ​​of the capabilities defined in Method 1. Specifically, the range information may include at least one of i) candidate values ​​of each capability value, ii) minimum values ​​of each capability value, and / or iii) maximum values ​​of each capability value.

[0252] The method may further include receiving a configuration based on the capability information. Specifically, the terminal receives the configuration based on the capability information from a base station. This step may correspond to Step 2 in at least one of the above-mentioned Exemplary Procedures 1 to 3. The configuration based on the capability value may include at least one of i) a configuration related to reporting the one or more capability values ​​and / or ii) an initial setting related to the at least one feature.

[0253] At S420, the terminal transmits, to the base station, information related to one or more capability values ​​based on the range information.

[0254] As an example, this step may correspond to step 3 in at least one of the above-described Exemplary procedures 1 to 3.

[0255] Based on the range information, a capability value (actually applied / currently applied / applied at a specific time) can be reported. This will be explained in detail below.

[0256] According to one embodiment, the one or more capability values ​​based on range information may include capability values ​​based on one or more time instances. This embodiment may be based on Method 1 and / or an extension of Method 1.

[0257] The one or more time instances may be associated with at least one of i) a first point in time related to the transmission of the information (e.g., the reporting time of the capability value) and / or ii) a second point in time a certain time after the first point in time (e.g., a point X ms / slot after the reporting time of the capability value).

[0258] The method may further include receiving a configuration based on the one or more capability values. Specifically, the terminal receives the configuration based on the one or more capability values ​​from a base station. This step may correspond to Step 4 of at least one of Exemplary Procedures 1 to 3 described above. The configuration based on the one or more capability values ​​may include information for setting or resetting the at least one function.

[0259] The (initial) setting of the capability value applied / used for the communication function of the terminal may be required. In this regard, the above-described methods 1-1 to 1-3 may be applied.

[0260] According to one embodiment, the lowest capability value among the capability values ​​based on the range information may be applied before the information related to the one or more capability values ​​is transmitted. This embodiment may be based on Method 1-1.

[0261] According to an embodiment, a capability value associated with a fallback mode may be applied before the information associated with the one or more capability values ​​is transmitted. This embodiment may be based on methods 1 and 2.

[0262] According to an embodiment, the capability information may further include information related to an initial capability value. The initial capability value may be associated with a fallback mode. This embodiment may be based on methods 1 to 3.

[0263] The operations based on S410, S420, the step of receiving a configuration based on capability information, and the step of receiving a configuration based on the one or more capability values ​​described above may be implemented by the apparatus of Figure 6. For example, terminal 200 may control one or more transceivers 230 and / or one or more memories 240 to perform the operations based on S410, S420, the step of receiving a configuration based on capability information, and the step of receiving a configuration based on the one or more capability values.

[0264] The above-described embodiment will now be described in detail from the perspective of the operation of the base station.

[0265] S510 to S520, which will be described later, correspond to S410, S420, the step of receiving a configuration based on capability information, and the step of receiving a configuration based on one or more capability values, which will be described later. Taking into consideration the correspondence, redundant descriptions will be omitted. That is, specific descriptions of base station operations, which will be described later, can be replaced with the descriptions / embodiments of FIG. 5 corresponding to the operations.

[0266] For example, the description / embodiment of S410 to S420 in FIG. 4 may also be applied to the base station operations of S510 to S520 described below.

[0267] As an example, the description / embodiments of the steps of receiving a configuration based on Capability Information and receiving a configuration based on the one or more Capability Values ​​may further be applied to the base station operation of the steps of transmitting a configuration based on Capability Information and transmitting a configuration based on the one or more Capability Values ​​described below.

[0268] FIG. 5 is a flowchart illustrating a method performed by a base station according to another embodiment of the present disclosure.

[0269] Referring to FIG. 5, a method performed by a base station in a wireless communication system according to another embodiment of the present specification includes receiving performance information S510 and receiving information related to one or more performance values ​​S520.

[0270] At S510, the base station receives capability information () from the terminal, the capability information including range information associated with at least one capability value, the at least one capability value associated with at least one feature supported by the terminal.

[0271] The method may further include transmitting a configuration based on the capability information, wherein the base station transmits the configuration based on the capability information to the terminal.

[0272] At S520, the base station receives information related to one or more capability values ​​based on the range information from the terminal.

[0273] The method may further include transmitting a configuration based on the one or more capability values. Specifically, the base station transmits the configuration based on the one or more capability values ​​to the terminal.

[0274] The operations based on the above-described S510 to S520, the step of transmitting a configuration based on Capability Information, and the step of transmitting a configuration based on the one or more capability values, can be realized by the apparatus of Fig. 6. For example, the base station 100 can control one or more transceivers 130 and / or one or more memories 140 to perform operations based on S510 to S520, the step of transmitting a configuration based on Capability Information, and the step of transmitting a configuration based on the one or more capability values.

[0275] An apparatus to which the embodiments of the present specification can be applied (an apparatus that implements the methods / operations according to the embodiments of the present specification) will be described below with reference to FIG.

[0276] FIG. 6 is a diagram showing the configurations of the first device and the second device according to the embodiment of the present specification.

[0277] The first device 100 may include a processor 110 , an antenna unit 120 , a transceiver 130 , and a memory 140 .

[0278] 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, the RRC layer, or higher layers. The physical layer processing unit 115 may process operations of the PHY layer. For example, when the first device 100 is a base station device in base station-terminal communication, the physical layer processing unit 115 may perform uplink reception signal processing, downlink transmission signal processing, etc. For example, when the first device 100 is a first terminal device in terminal-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.

[0279] The antenna unit 120 may include one or more physical antennas, and when multiple antennas are included, MIMO transmission and reception may be supported. 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, as well as software, an operating system, applications, etc. related to the operation of the first device 100, and may also include components such as buffers.

[0280] The processor 110 of the first device 100 can be configured to implement the operation of a base station in base station-terminal communication (or the operation of a first terminal device in terminal-terminal communication) in the embodiments described in this disclosure.

[0281] The second device 200 may include a processor 210 , an antenna unit 220 , a transceiver 230 , and a memory 240 .

[0282] 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, the RRC layer, or higher layers. The physical layer processing unit 215 may process operations of the PHY layer. For example, when the second device 200 is a terminal device in base station-terminal communication, the physical layer processing unit 215 may perform downlink reception signal processing, uplink transmission signal processing, etc. For example, when the second device 200 is a second terminal device in terminal-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 200.

[0283] The antenna unit 220 may include one or more physical antennas, and if multiple antennas are included, MIMO transmission and reception may be supported. The transceiver 230 may include an RF transmitter and an RF receiver. The memory 240 may store information processed by the processor 210, as well as software, an operating system, applications, etc. related to the operation of the second device 200, and may also include components such as buffers.

[0284] The processor 210 of the second device 200 may be configured to implement the operation of a terminal in base station-terminal communication (or the operation of a second terminal device in terminal-terminal communication) in the embodiments described in this disclosure.

[0285] In the operation of the first device 100 and the second device 200, the matters described in the examples of the present disclosure regarding the base station and the terminal in base station-terminal communication (or the first terminal and the second terminal in terminal-terminal communication) can be equally applied, and duplicate explanations will be omitted.

[0286] Here, the wireless communication technology implemented by the devices 100 and 200 of the present disclosure may include not only LTE, NR, and 6G, but also Narrowband Internet of Things (NB-IoT) for low-power communication. For example, the NB-IoT technology is an example of a Low Power Wide Area Network (LPWAN) technology, and can be implemented by standards such as LTE Cat NB1 and / or LTE Cat NB2, and is not limited to the aforementioned names.

[0287] Additionally or alternatively, the wireless communication technology implemented in the devices 100 and 200 of the present disclosure may perform communication based on LTE-M technology. For example, LTE-M technology is an example of LPWAN technology and is referred to by various names such as enhanced Machine Type Communication (eMTC). For example, LTE-M technology may be implemented by at least one of various standards such as 1) LTE CAT 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-Bandwidth Limited), 5) LTE-MTC, 6) LTE Machine Type Communication, and / or 7) LTE M, and is not limited to the above names.

[0288] Additionally or alternatively, the wireless communication technology implemented in the devices 100 and 200 of the present disclosure may include at least one of ZigBee, Bluetooth, and a Low Power Wide Area Network (LPWAN), which consider low-power communication, but are not limited to the aforementioned names. For example, ZigBee technology can create personal area networks (PANs) related to small / low-power digital communication based on various standards such as IEEE 802.15.4, and may be called by various names.

[0289] [Claims at the time of international application] [Claim 1] 1. A method performed by a terminal (User Equipment: UE) in a wireless communication system, comprising: transmitting capability information; the capability information includes range information associated with at least one capability value; the at least one capability value relates to at least one feature supported by the terminal; transmitting information relating to one or more capability values ​​based on said range information. [Claim 2] The at least one capability value is: i) Channel State Information (CSI), ii) CSI and / or beam-related predictions; iii) positioning, and / or iv) a value associated with at least one of the models. [Claim 3] The CSI-related value is i) maximum CSI compression ratio; ii) maximum payload size for CSI compression; iii) supported pre / post processing modes, and / or 3. The method of claim 2, further comprising at least one of the following: iv) a compression quality indicator. [Claim 4] 3. The method according to claim 2, characterized in that the prediction relates to the time domain or the spatial domain. [Claim 5] The value associated with the prediction in the time domain is i) the predictable maximum time instance, and / or ii) prediction accuracy. [Claim 6] The value associated with the prediction in the spatial domain is i) the maximum supportable ratio of a first set of measurements of a Reference Signal (RS) and a second set of predictions; and / or ii) including at least one of the sizes of the second set. [Claim 7] 3. The method of claim 2, wherein the positioning related capability value comprises a positioning accuracy related metric. [Claim 8] The values ​​associated with the model are: i) a value relating to the presence or absence of support for fine-tuning associated with said model; ii) the minimum time required to train, update, fine-tune, switch, or select the model; and / or 3) at least one value associated with a fallback of the model-based communication function. [Claim 9] The range information is i) candidate values ​​for each capability value; ii) the minimum value of each capability value, and / or iii) at least one of the maximum values ​​of each capability value. [Claim 10] 2. The method of claim 1, wherein the one or more capability values ​​based on the range information include a capability value based on each of one or more time instances. [Claim 11] The one or more time instances are: i) a first point in time relative to the transmission of said information; and / or ii) a second time point a certain time later than the first time point. [Claim 12] 10. The method of claim 1, further comprising: receiving a configuration based on the capability information. [Claim 13] The setting based on the capability information is i) settings related to reporting of said one or more capability values; and / or 13. The method of claim 12, further comprising: ii) at least one of an initial setting associated with said at least one feature. [Claim 14] receiving a configuration based on the one or more capability values; 2. The method of claim 1, wherein the configuration based on the one or more capability values ​​includes information for setting or resetting related to the at least one function. [Claim 15] 2. The method of claim 1, wherein the lowest capability value among the capability values ​​based on the range information is applied before transmitting the information related to the one or more capability values. [Claim 16] 2. The method of claim 1, wherein a capability value associated with a fallback mode is applied prior to transmission of the information associated with the one or more capability values. [Claim 17] The capability information further includes information regarding an initial capability value; 2. The method of claim 1, wherein the initial capability value is associated with a fallback mode. [Claim 18] A terminal (User Equipment: UE) operating in a wireless communication system, one or more transceivers; one or more processors; one or more memories coupled to the one or more processors and configured to store instructions; 18. A terminal, characterized in that the instructions, when executed by the one or more processors, configure the one or more processors to perform all steps of the method according to any one of claims 1 to 17. [Claim 19] 1. An apparatus comprising: one or more memories; one or more processors operatively connected to the one or more memories; The one or more memories store instructions that, when executed by the one or more processors, cause the one or more processors to perform all steps of the method according to any one of claims 1 to 17. [Claim 20] one or more non-transitory computer-readable media storing instructions, 18. One or more non-transitory computer-readable media, wherein the instructions executable by one or more processors configure the one or more processors to perform all steps of the method of any one of claims 1 to 17. [Claim 21] 1. A method performed by a base station in a wireless communication system, comprising: receiving capability information; the capability information includes range information associated with at least one capability value; the at least one capability value relates to at least one feature supported by a terminal (User Equipment: UE); receiving information relating to one or more capability values ​​based on the range information. [Claim 22] 1. A base station operating in a wireless communication system, comprising: one or more transceivers; one or more processors; one or more memories coupled to the one or more processors and configured to store instructions; 22. A base station, wherein the instructions, when executed by the one or more processors, configure the one or more processors to perform all steps of the method of claim 21.

Claims

1. 1. A method performed by a terminal (User Equipment: UE) in a wireless communication system, comprising: transmitting capability information; the capability information includes range information associated with at least one capability value; the at least one capability value is related to at least one feature supported by the terminal; transmitting information related to one or more capability values ​​based on said range information.

2. The at least one capability value is: i) Channel State Information (CSI); ii) CSI and / or beam related predictions; iii) positioning, and / or iv) a value associated with at least one of the models.

3. The CSI-related value is i) maximum CSI compression ratio; ii) maximum payload size for CSI compression; iii) supported pre / post processing modes, and / or 4. The method of claim 2, further comprising at least one of: iv) a compression quality indicator.

4. 3. The method according to claim 2, characterized in that the prediction relates to the time domain or the spatial domain.

5. The value associated with the prediction in the time domain is i) a predictable maximum time instance; and / or 5. The method of claim 4, wherein the method further comprises at least one of: ii) prediction accuracy.

6. The value associated with the prediction in the spatial domain is i) a maximum supportable ratio of a first set of measurement-related and a second set of prediction-related Reference Signals (RSs); and / or 5. The method of claim 4, wherein ii) at least one of the sizes of said second set is included.

7. 3. The method of claim 2, wherein the positioning related capability value comprises a positioning accuracy related metric.

8. The values ​​associated with the model are: i) a value relating to the presence or absence of support for fine-tuning associated with said model; ii) the minimum time required for training, updating, fine-tuning, switching, or selection of the model; and / or 3. The method of claim 2, further comprising: iii) at least one value associated with a fallback of the model-based communication function.

9. The range information is i) candidate values ​​for each capability value; ii) the minimum value of each capability value; and / or iii) a maximum value of each capability value.

10. 2. The method of claim 1, wherein the one or more capability values ​​based on the range information include a capability value based on each of one or more time instances.

11. The one or more time instances are: i) a first point in time relative to the transmission of said information, and / or ii) a second time point a certain time later than the first time point.

12. 10. The method of claim 1, further comprising: receiving a configuration based on the capability information.

13. The setting based on the capability information is i) settings related to reporting of said one or more capability values; and / or 13. The method of claim 12, further comprising: ii) at least one of a default setting associated with said at least one feature.

14. receiving a configuration based on the one or more capability values; 2. The method of claim 1, wherein the configuration based on the one or more capability values ​​includes information for setting or resetting related to the at least one function.

15. 2. The method of claim 1, wherein the lowest capability value among the capability values ​​based on the range information is applied before the information related to the one or more capability values ​​is transmitted.

16. 10. The method of claim 1, wherein a capability value associated with a fallback mode is applied prior to transmitting the information associated with the one or more capability values.

17. the performance information further includes information regarding an initial capability value; 2. The method of claim 1, wherein the initial capability value is associated with a fallback mode.

18. A terminal (User Equipment: UE) operating in a wireless communication system, one or more transceivers; one or more processors; one or more memories coupled to the one or more processors and configured to store instructions; 18. A terminal, characterized in that the instructions, when executed by the one or more processors, configure the one or more processors to perform all the steps of the method according to any one of claims 1 to 17.

19. 1. An apparatus comprising: one or more memories; one or more processors operatively connected to the one or more memories; 18. The apparatus, wherein the one or more memories store instructions that, when executed by the one or more processors, configure the one or more processors to perform all steps of the method according to any one of claims 1 to 17.

20. one or more non-transitory computer-readable media storing instructions, 18. One or more non-transitory computer-readable media, wherein the instructions executable by one or more processors configure the one or more processors to perform all the steps of the method according to any one of claims 1 to 17.

21. 1. A method performed by a base station in a wireless communication system, comprising: receiving capability information; the capability information includes range information associated with at least one capability value; the at least one capability value is related to at least one feature supported by a User Equipment (UE); receiving information relating to one or more capability values ​​based on the range information.

22. 1. A base station operating in a wireless communication system, comprising: one or more transceivers; one or more processors; one or more memories coupled to the one or more processors and configured to store instructions; 22. A base station, wherein the instructions, when executed by the one or more processors, configure the one or more processors to perform all steps of the method according to claim 21.

Images