Method and apparatus for managing model in wireless communication system

Abstract

According to one embodiment of the present disclosure, a method performed by a first device in a wireless communication system comprises the steps of: receiving first information related to a group; and receiving second information related to management of the group.

Description

Technical Field

[0001] The present disclosure relates to a method and apparatus for managing models in a wireless communication system. Background Art

[0002] Mobile communication systems have been developed to provide voice services while ensuring user mobility. However, the scope of mobile communication systems has expanded to include data services in addition to voice. Due to the current explosive increase in traffic, resource shortages have emerged, leading to user demands for higher-speed services. Therefore, a more advanced mobile communication system is needed.

[0003] The requirements for next-generation mobile communication systems need to be able to accommodate explosive data traffic, significantly increase the data rate per user, accommodate a significant increase in the number of connected devices, very low end-to-end latency, and high energy efficiency. To this end, various technologies have been studied, such as dual connectivity, massive multiple-input multiple-output (MIMO), in-band full-duplex, non-orthogonal multiple access (NOMA), ultra-wideband support, and device networking.

[0004] Communication functions can be implemented based on models / functions. In this regard, operations for Life Cycle Management (LCM) can be performed. As an example, multiple models / functions can be implemented based on parameters (and structures) optimized / obtained for each operating environment / scenario. As an example, multiple functions can be supported in a single device. Summary of the Invention

[0005] Technical issues

[0006] When multiple models / functions are implemented / used for the communication functions as described above, LCM-related signaling (e.g., activation / deactivation / update / switching / fallback, etc. for the model / function) should be performed due to various elements related to the management of the corresponding model / function (e.g., the environment related to the communication function, the scenario related to the specific communication function, etc.).

[0007] In this case, the overhead for LCM-related signaling may increase excessively. For example, LCM-related signaling may be frequently performed whenever the above-mentioned model / function-based LCM-related elements / attributes change. In addition, when such LCM-related signaling is performed for each of multiple models / functions, the signaling overhead may be further increased.

[0008] An object of the present disclosure is to propose a method for solving the above-mentioned problems.

[0009] The technical objectives of the present disclosure are not limited to the above-mentioned technical objectives, and other technical objectives not mentioned above will be clearly understood by those of ordinary skill in the art from the following description.

[0010] Technical Solution

[0011] A method performed by a first device in a wireless communication system according to an embodiment of the present disclosure includes receiving first information related to a group; and receiving second information related to management of the group.

[0012] The group may be associated with i) one or more models and / or ii) one or more functions.

[0013] Operations related to one or more models and / or one or more functions may be indicated based on the second information.

[0014] The operation may include at least one of: i) activation, ii) deactivation, iii) selection, iv) switching, v) updating, and / or vi) rollback.

[0015] The operation may be instructed based on an ID or unit associated with a group.

[0016] At least one configuration related to the group may be reset based on the second information.

[0017] At least one configuration may include at least one of: i) a reference signal (RS) set associated with the measurement, ii) a prediction window associated with channel state information (CSI) and / or beam, and / or iii) a granularity associated with reporting of CSI and / or beam.

[0018] Each group may be associated with a common attribute.

[0019] The common attribute may be based on at least one of: i) zone, ii) configuration, iii) data traffic, iv) mobility, and / or v) interference.

[0020] A first device operating in wireless communication according to another embodiment of the present disclosure includes one or more transceivers, one or more processors, and one or more memories connected to the one or more processors and storing instructions.

[0021] The instructions, upon execution by one or more processors, configure the one or more processors to perform all the steps of any one of the methods.

[0022] An apparatus according to another embodiment of the present disclosure includes one or more memories and one or more processors operatively connected to the one or more memories.

[0023] The one or more memories store instructions that, upon execution by the one or more processors, configure the one or more processors to perform all the steps of any one of the methods.

[0024] According to another embodiment of the present disclosure, one or more non-transitory computer-readable media stores instructions that are executable by one or more processors to configure the one or more processors to perform all the steps of any one of the methods.

[0025] A method performed by a second device in a wireless communication system according to another embodiment of the present disclosure includes: transmitting first information related to a group; and transmitting second information related to management of the group.

[0026] A second device operating in wireless communication according to another embodiment of the present disclosure includes one or more transceivers, one or more processors, and one or more memories connected to the one or more processors and storing instructions.

[0027] The instructions, upon execution by the one or more processors, configure the one or more processors to perform all the steps of the method.

[0028] Beneficial effects

[0029] According to an embodiment of the present disclosure, management of models / functions (i.e., LCMs) is performed based on predefined groups. Therefore, compared with the case where LCM-related signaling is performed for each model / function, overhead can be reduced. Multiple models / functions can be efficiently managed while minimizing signaling overhead.

[0030] Furthermore, signaling / operations for managing multiple models / functions can be further simplified, thereby reducing the complexity required to implement a device supporting management of multiple models / functions.

[0031] Effects that can be achieved with the present disclosure are not limited to those described above by way of example, and those skilled in the art to which the present disclosure pertains will more clearly understand other effects and advantages of the present disclosure from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 Illustrate the functional framework of AI / ML models.

[0033] Figure 2 A signaling process according to an embodiment of the present disclosure is illustrated.

[0034] Figure 3 is a flowchart illustrating a method performed by a user equipment according to an embodiment of the present disclosure.

[0035] Figure 4 is a flowchart illustrating a method performed by a base station according to another embodiment of the present disclosure.

[0036] Figure 5 The configurations of the first device and the second device according to the embodiment of the present disclosure are illustrated. DETAILED DESCRIPTION

[0037] The following will be Figure 1 The detailed description disclosed above will describe exemplary embodiments of the present disclosure rather than describing unique embodiments for carrying out the present disclosure. The following detailed description includes details that provide a complete understanding of the present disclosure. However, those skilled in the art will appreciate that the present disclosure can be carried out without these details.

[0038] In some cases, in order to prevent the concepts of the present disclosure from being obscure, known structures and devices may be omitted, or may be illustrated in a block diagram format based on the core functions of each structure and device.

[0039] In the following, downlink (DL) means communication from a base station to a terminal, and uplink (UL) means communication from a terminal to a 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 be represented as a first communication device, and the terminal may be represented as a second communication device. The base station (BS) may be replaced with terms including a fixed station, a node B, an evolved node B (eNB), a next-generation node B (gNB), a base transceiver system (BTS), an access point (AP), a network (5G network), an AI system, a roadside unit (RSU), a vehicle, a robot, an unmanned aerial vehicle (UAV), an AR (augmented reality) device, a VR (virtual reality) device, and the like. In addition, the terminal may be fixed or mobile and may be replaced with terms including user equipment (UE), mobile station (MS), user terminal (UT), mobile subscriber station (MSS), subscriber station (SS), advanced mobile station (AMS), wireless terminal (WT), machine type communication (MTC) device, machine-to-machine (M2M) device and device-to-device (D2D) device, vehicle, robot, AI module, unmanned aerial vehicle (UAV), AR (augmented reality) device, VR (virtual reality) device, etc.

[0040] AIML related description

[0041] With the advancement of artificial intelligence / machine learning (AI / ML) technologies, the nodes and UEs that constitute wireless communication networks are becoming increasingly intelligent / advanced.

[0042] In particular, due to the intelligence of the network / base station, it is expected that various network / base station decision parameters can be quickly optimized and derived / applied based on various environmental parameters.

[0043] Environmental parameters may include at least one of the distribution / location of base stations, the distribution / location / material of buildings / furniture, the location / movement direction / speed of the UE, or climate information. However, the above parameters are merely examples, and in addition to the listed parameters, environmental parameters may also include other environmental parameters related to network / base station decision parameters.

[0044] The network / base station decision parameters may include at least one of the transmit / receive power of each base station (BS), the transmit power of each UE, the precoder / beam of the BS / UE, the time / frequency resource allocation for each UE, or the duplex method of each BS. However, the above parameters are only examples, and in addition to the listed parameters, the network / base station decision parameters may also include other parameters determined by the network / base station.

[0045] In line with this trend, many standardization organizations (e.g., 3GPP, O-RAN) are considering the introduction of AI / ML, and related research is also actively underway.

[0046] In a narrow sense, AI / ML can be simply referred to as artificial intelligence based on deep learning, but conceptually, it can be categorized as follows.

[0047] - Artificial Intelligence: It is any automation that allows machines to do work that would otherwise be done by humans.

[0048] -Machine Learning: It refers to a technology in which machines learn patterns from data for decision making without explicit programming rules.

[0049] Deep learning: It is a model based on artificial neural networks that allows machines to simultaneously perform feature extraction and decision-making based on unstructured data. The algorithm relies on a multi-layer network of interconnected nodes for feature extraction and transformation, which is inspired by biological neural systems (i.e., neural networks). Common deep learning network architectures include deep neural networks (DNNs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs).

[0050] 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 and broader than deep learning.

[0051] Types of AI / ML based on various criteria

[0052] -Offline and online

[0053] Offline learning

[0054] Offline learning faithfully follows the sequential process of database collection, learning, and prediction. That is, collection and learning can be performed offline, and the completed program can be installed on-site and used for prediction. This offline learning approach is used in most cases.

[0055] Online Learning

[0056] Online learning refers to a method that gradually improves performance by performing incremental learning using additional data generated, taking advantage of the fact that data that can be used for recent learning is continuously generated via the Internet.

[0057] Classification based on AI / ML framework concepts

[0058] -Focused learning

[0059] In centralized learning, all data resources / storage / learning (e.g., supervised learning, unsupervised learning, reinforcement learning, etc.) are performed in one centralized node while training data collected from multiple different nodes is reported to the centralized node.

[0060] - Federated Learning

[0061] Federated learning is built on data, where a collective model exists across distributed data owners. Instead of collecting data into the model, the AI / ML model is imported into the data source, allowing local nodes / individual devices to collect data and train their own copies of the model, thus eliminating the need to report source data to a centralized node.

[0062] In federated learning, the parameters and weights of AI / ML models are retransmitted to centralized nodes to support general model training. Federated learning offers advantages in terms of improved computing speed and information security. Specifically, uploading personal data to a centralized server is unnecessary, preventing the leakage and misuse of personal information.

[0063] -Distributed learning

[0064] Distributed learning refers to the concept of scaling and distributing the machine learning process across a cluster of nodes. The trained model is shared across multiple nodes, which are split up and operated simultaneously to accelerate model training.

[0065] Classification according to learning methods

[0066] -Supervised learning

[0067] Supervised learning is a machine learning task that aims 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. An example of supervised learning is shown below.

[0068] 1) Regression: linear regression, logistic regression

[0069] 2) Instance-based algorithm: k-nearest neighbor (KNN)

[0070] 3) Decision Tree Algorithm: CART

[0071] 4) Support Vector Machine: SVM

[0072] 5) Bayesian algorithm: Naive Bayes

[0073] 6) Ensemble Algorithms: Extreme Gradient Boosting, Bagging: Random Forest

[0074] Supervised learning can be further grouped into regression and classification problems, where classification is predicting a label and regression is predicting a quantity.

[0075] -Unsupervised learning

[0076] Unsupervised learning is a machine learning task that aims to learn a function that describes the hidden structure in unlabeled data. The input data is unlabeled, and the outcome is unknown. Some examples of unsupervised learning include K-means clustering, principal component analysis (PCA), nonlinear independent component analysis (ICA), and long short-term memory (LSTM).

[0077] -Reinforcement Learning

[0078] In reinforcement learning (RL), an agent aims to optimize a long-term goal by interacting with an environment based on a trial-and-error process. It is goal-oriented learning based on interactions with the environment. Examples of RL algorithms are as follows.

[0079] 1) Q-learning

[0080] 2) Multi-arm probabilistic machine (bandit) learning

[0081] 3) Deep Q Network

[0082] 4) State-Action-Reward-State-Action (SARSA)

[0083] 5) Time difference learning

[0084] 6) Executor-Critic Reinforcement Learning

[0085] 7) Deep Deterministic Policy Gradient

[0086] 8) Monte Carlo Tree Search

[0087] Reinforcement learning can be further grouped into model-based reinforcement learning and model-free reinforcement learning.

[0088] Model-based reinforcement learning: It refers to RL algorithms that use predictive models and use a model of the various dynamic states of the environment and the rewards these states bring to the environment to derive the probabilities of transitions between states.

[0089] Model-free reinforcement learning: It refers to RL algorithms that are based on values ​​or policies that maximize future rewards. The multi-agent environment / state is less computationally complex and does not require an accurate representation of the environment.

[0090] RL algorithms can also be classified into value-based RL and policy-based RL, policy-based RL and non-policy RL, etc.

[0091] Representative models of deep learning

[0092] 1. Feedforward Neural Network (FFNN)

[0093] FFNN consists of an input layer, a hidden layer, and an output layer.

[0094] 2. Recurrent Neural Network (RNN)

[0095] RNN is a type of artificial neural network in which hidden nodes are connected to directed edges to form a directed loop. It is a model suitable for processing sequential data such as speech and text.

[0096] 3. Convolutional Neural Network (CNN)

[0097] CNN is used for two purposes: reducing model complexity and extracting good features by applying convolution operations commonly used in the fields of video processing or image processing.

[0098] - Kernel or Filter: It refers to a unit / structure that applies weights to the input of a specific range / unit.

[0099] - Stride: It refers to the range of movement of the kernel within the input.

[0100] - Feature map: It refers to the result of applying the kernel to the input.

[0101] -Padding: It refers to the value that is added to resize the feature map.

[0102] - Pooling: It refers to the operation of reducing the size of feature maps by downsampling them (e.g., max pooling, average pooling).

[0103] 4. Autoencoder

[0104] An autoencoder is a neural network that takes a feature vector x as input and outputs the same or a similar vector x'. The input nodes and output nodes of the autoencoder have the same features.

[0105] Figure 1 Illustrate the functional framework of AI / ML models.

[0106] exist Figure 1 In the functional framework shown, the definition of each term and the operation of each function can be based on Table 1 below.

[0107] [Table 1]

[0108]

[0109] Dataset

[0110] The datasets used in AI / ML are classified into training data, validation data, and test data, and their definitions are as follows.

[0111] - Training data

[0112] Dataset used to train the model

[0113] - Verify data

[0114] Dataset used to validate the trained model

[0115] Validation data is a dataset that is often used to prevent overfitting of the training dataset.

[0116] Validation data is a dataset used to select the best model among the various models trained during the training process. Therefore, validation data can be considered as a dataset related to training.

[0117] -Test data

[0118] The test data is the dataset used for final evaluation. The test data is independent of the training data.

[0119] The data set may use a training set including the above data in a predetermined proportion.

[0120] For example, you can use a training set that includes training data and validation data in a ratio of 8:2 or 7:3.

[0121] For example, a training set including training data, validation data, and test data in a ratio of 6:2:2 may be used.

[0122] Collaboration Level

[0123] Depending on whether the AI / ML function between the base station and the UE is capable, the collaboration level can be defined as shown in Table 2 below.

[0124] [Table 2]

[0125]

[0126] The collaboration levels shown in Table 2 are examples and can be modified and utilized differently from the illustrated examples based on implementation methods. For example, a collaboration level that combines two or more of the illustrated collaboration levels can be defined / utilized. For example, a collaboration level that does not include one or more of the illustrated collaboration levels can be utilized.

[0127] The present disclosure proposes a method for reducing signaling overhead for model / capability management.

[0128] Hereinafter, the embodiments described below are not limited to application to the management of AI / ML models. As an example, the embodiments described below may be applied to the management of models that implement communication functions. As an example, the embodiments described below may be applied to the management of models related to communication functions. Hereinafter, "AI / ML model" may be interpreted / replaced with "model", "model related to (specific) communication functions", "model for (specific) telecommunication functions", "model related to (specific) communication processes" or "model for (specific) telecommunication processes".

[0129] In the present disclosure, “ / ” means “and”, “or”, or “and / or”, depending on the context. In the present disclosure, from the perspective of the air interface, “terminal” and “UE” can be used interchangeably in the same / similar sense, and “base station”, “network” and “TRP” can also be used interchangeably in the same / similar sense.

[0130] In recent years, attempts to apply artificial intelligence / machine learning (AI / ML) technology to wireless communication networks have been active. In the 3GPP Rel-18 AI / ML study project, research began on applying AI / ML technology to the air interface between the UE and the network. As the main use cases for incorporating AI / ML into the air interface in the corresponding study, beam management (BM), CSI acquisition, and positioning are considered, and various related terms are defined / discussed as shown in Table 3 below. In the corresponding study, methods for managing AI / ML models are being discussed. As an example, management of AI / ML models may refer to lifecycle management (LCM). LCM may include at least one of model activation / deactivation, model switching / selection, model monitoring, model update / (fine) tuning, and / or fallback.

[0131] [Table 3]

[0132]

[0133]

[0134]

[0135]

[0136] For the UE part / side model, two approaches / methods for model management are discussed in the last protocol as shown in Table 3. Here, the UE part model refers to the UE part in the two-sided model, and the UE side model refers to the one-sided model in which AI is implemented only in the UE.

[0137] The function-based approach focuses on the functions or capabilities supported by the application of AI / ML models. The standardization goal of the function-based approach is the signaling related to activation / deactivation / switching / fallback of functions.

[0138] The standardized goal of the pattern-based approach is the signaling related to activation / deactivation / switching / fallback of AI-ML models.

[0139] The biggest differences between the two approaches mentioned above are as follows.

[0140] It can be assumed that the UE implements multiple AI / ML models according to various environments / scenarios in which the same function can be applied, relevant base station configuration values, etc.

[0141] Model-based LCM directly manages which model is activated / deactivated / selected / switched. On the other hand, function-based LCM performs activation / deactivation / monitoring, etc., in terms of the functions / capabilities for the corresponding models. Therefore, in the case of function-based LCM, information about how many models are implemented by the base station (NW) and / or UE and how the models are implemented may not be required.

[0142] The model / function monitoring entity for the UE part / side model can be the UE or / and the NW. The entity that determines / executes activation / deactivation / selection / switching / updating of the model / function can be the UE or / and the NW.

[0143] An example in which the UE and the NW perform the LCM process together is as follows: When the UE recommends / reports a determination for model selection / update to the NW, the NW may perform a final confirmation / decision on the corresponding determination.

[0144] As described above, when the NW is involved in the LCM procedure, signaling between the relevant UE and the NW inevitably occurs.

[0145] Table 4 below shows LCM signaling between UE and NW.

[0146] [Table 4]

[0147]

[0148] This LCM signaling may have to be performed every time the environment / scenario changes, especially when multiple AI / ML models are implemented by optimizing / obtaining parameters (and structures) according to each operating environment / scenario. In addition, AI / ML models for multiple functions (e.g., N1 model for CSI prediction, N2 model for CSI compression, N3 model for beam prediction, N4 model for positioning) may be implemented in one device / UE, leading to the problem of further increase in LCM signaling overhead. Hereinafter, a method for solving the above-mentioned problem will be described in detail.

[0149] Method 1

[0150] Multiple models / functions may be grouped, and model / function LCM signaling may be defined / performed based on the corresponding group (or the unit / ID corresponding to the corresponding group).

[0151] Grouping can be performed as follows. Grouping can be performed so that AI / ML models for different functions or trained models for the same or similar operating environments / scenarios are grouped together. That is, one or more groups can be determined based on multiple models / functions.

[0152] Here, the operating environment / scenario can be divided / classified in various aspects such as indoor / outdoor, urban area / suburban area, sector / site / configuration (ID), base station / TRP deployment / density, UE deployment / density, inter-cell / intra-cell interference, NW data traffic, UE mobility speed, UE form factor, etc. According to this embodiment, LCM signaling can be performed as follows.

[0153] As an example, in case of model-based LCM, model group (ID) based LCM signaling may be defined / performed.

[0154] As an example, in the case of function-based LCM, individual models may not appear in the standard. That is, individual models may not be explicitly defined. In this case, LCM signaling may be defined / performed based on specific units (corresponding to model groups). Model groups can be defined as any unit or distinguished by any ID (e.g., index or indicator).

[0155] For example, a region / configuration / scenario / environment ID may be defined. LCM based on a model group may be performed by defining / performing LCM signaling based on the corresponding ID. This approach may also be applied to model-based LCM. Specifically, the approach may be applied as follows. Multiple models may belong to the same region / configuration / scenario / environment ID (e.g., corresponding IDs are assigned / authorized to model-specific information), and LCM signaling may be defined / performed based on the corresponding ID. A specific application example is shown in Table 5 below.

[0156] [Table 5]

[0157]

[0158] When group-based LCM is performed through the proposed approach, the signaling / RS overhead can be further reduced by specifying changes to RS, channels, reporting configurations, etc. associated with the corresponding LCM signaling.

[0159] In other words, based on LCM signaling, at least one of the RS, channel, and / or reporting configuration associated with the corresponding LCM signaling may be changed / updated. As an example, the change / update of at least one of the RS, channel, and / or reporting configuration associated with the LCM signaling may be defined as being performed by the entity executing LCM (without separate signaling). As an example, the entity executing LCM may operate by assuming that at least one of the RS, channel, and / or reporting configuration associated with the corresponding LCM signaling is changed / updated when performing LCM signaling. As an example, in addition to LCM, LCM signaling may also serve as an indication of a change / update of at least one of the RS, channel, and / or reporting configuration.

[0160] Hereinafter, specific examples of changes / updates of RSs, channels, reporting configurations, etc. related to LCM signaling will be described.

[0161] For example, the measurement CSI-RS / SSB resource set / group associated with CSI compression, CSI prediction, beam prediction, positioning, etc. can be changed as a whole based on the model group change-related indication. Such an operation can reduce RS reconfiguration signaling based on changes in the operating environment (e.g., changing the measurement set based on moving from cell / TRP A to cell / TRP B).

[0162] For example, configuration values ​​associated with CSI compression, CSI prediction, beam prediction, positioning, etc. (e.g., prediction window, reporting granularity, etc.) can be changed overall based on model group-based LCM signaling. Such operations can reduce report reconfiguration signaling based on changes in the operating environment.

[0163] In this case, information about which group's RS set / group and report configuration value to change / activate / deactivate can be configured / defined in advance (for example, corresponding information is configured through RRC message and defined when implementing UE / NW (base station)).

[0164] Alternatively, application-specific specified values ​​(e.g., values ​​corresponding to fallback operations) may be specified. For example, when fallback operations are indicated via LCM signaling, specific parameters of the reporting configuration related to CSI prediction and beam prediction may be defined to be set to specified default values ​​(e.g., non-predicted CSI / beam reporting is performed by resetting prediction window-related values ​​to default values).

[0165] Method 1-1

[0166] (When method 1 is applied) RS / channel / report related configurations may be reset to preset or committed / prescribed values ​​based on LCM signaling.

[0167] The above method 1-1 can also be applied to the case where method 1 is not applied, that is, LCM based on a single model / function.

[0168] The proposed methods (e.g., Method 1 and Method 1-1)) can be applied not only to LCM signaling, but also to model group-based transfer / delivery methods in model transfer / delivery. For example, model transfer / delivery for a model group can be performed according to changes in the operating environment / scenario.

[0169] In terms of implementation, the operation of the base station / UE according to the above embodiment (for example, the operation based on at least one of the method 1 and the method 1-1)) can be performed by the following method. Figure 5 The device in (for example, Figure 5 Processed by processors 110 and 210).

[0170] In addition, the operation of the base station / UE according to the above embodiment (for example, the operation based on at least one of Method 1 and Method 1-1)) can be used to drive at least one processor (for example, Figure 5 110 and 210) in the form of instructions / programs (eg, instructions or executable code) stored in a memory (eg, Figure 5 140 and 240).

[0171] Hereinafter, a signaling process based on the above-mentioned embodiment will be described.

[0172] Figure 2 A signaling process according to an embodiment of the present disclosure is illustrated.

[0173] Figure 2 An example of signaling between a user equipment (UE) and a network (NW) based on the above-mentioned proposed method is illustrated. Here, UE / NW are merely examples and can be replaced with and applied with various devices. Figure 2 It is only for the convenience of description and does not limit the scope of the present disclosure. In addition, depending on the situation and / or configuration, the Figure 2Some steps shown.

[0174] belong Figure 2 The base station of the NW in may correspond to any entity, such as a base station (BS), a node B, a TRP, etc., and the UE may also be replaced by an entity / server responsible for UE-related AI / ML operations.

[0175] Figure 2 The model / function switching (or selection) process is illustrated as an implementation of the proposed LCM signaling, and other processes (eg, model / function selection / activation / deactivation / update / fallback / etc.) may be performed with respect to other LCM processes. Figure 2 In addition to the process shown, the model / function switching process can also be performed through another process.

[0176] The UE may perform a process S205 of reporting UE information for the AI / ML model and / or features / functions related thereto to the base station. The information may include a UE capability value.

[0177] The base station may perform configuration for related functions / parameters and / or AI / ML models based on the UE capability value reported in S205 ( S210 ).

[0178] Then, the model / function switching process between the base station and the UE can be performed. The detailed process of the model / function switching process can be diversified, and Figure 2 The embodiment of the corresponding process is shown. In order for the NW to determine the model switching, the UE may send monitoring information related to the model capability to the base station (S215). Alternatively, when the base station does not determine the model switching based on the UE's report information, such a process may be omitted.

[0179] The NW may execute an instruction for model / function switching of the UE (S220). In such a process, the methods proposed in the present disclosure (e.g., Method 1 or Method 1-1) may be applied. For example, a switching instruction based on a model group ID or based on any segment / configuration ID may be issued. In addition, RS / channel / report-related configurations may be changed based on such an instruction.

[0180] The UE receiving the instruction S220 may perform switching and related operations for the model / function, and send a related confirmation / verification message to the NW ( S225 ).

[0181] As mentioned above, the above NW / UE signaling and operations can be performed by the apparatus to be described below (in Figure 5 For example, the NW may correspond to a first wireless device, and the UE may correspond to a second wireless device, and in some cases, the opposite case may also be considered.

[0182] For example, the above NW / UE signaling and operations can be performed by Figure 5 One or more processors 110 and 210 are processed, and the above-mentioned NW / UE signaling and operations can be used to drive Figure 5 The instructions / programs (eg, instructions, executable codes) of at least one processor 110 or 210 are stored in the memories 140 and 240 .

[0183] In the following, reference will be made to Figure 3 and Figure 4 The above embodiments are described in detail in terms of the operation of the first device and the second device. The methods to be described below are distinguished only for ease of description, and it goes without saying that some components of any one method can be replaced with some components of another method, or can be applied in combination with each other. In the following, the first device and the second device can be entities that perform signaling related to model / function management (and / or model transfer / delivery). As an example, the first device can be a UE, a base station, or a first UE, and the second device can be a base station, a UE, or a second UE.

[0184] Figure 3 is a flowchart for describing a method performed by a first device according to an embodiment of the present disclosure.

[0185] Reference Figure 3 , the method performed by the first device according to an embodiment of the present disclosure includes a first information receiving step S310 and a second information receiving step S320.

[0186] In S310, the first device receives first information related to a group from the second device. As an example, the grouping can be configured based on the first information. As an example, multiple models / functions can be classified / determined into groups.

[0187] According to an embodiment, each group may be associated with a common attribute.This embodiment may be based on method 1.

[0188] As an example, the common attribute may be based on at least one of i) segment, ii) configuration, iii) data traffic, iv) mobility, and / or v) interference.

[0189] In S320, the first device receives second information related to management of the group from the second device.

[0190] Depending on the embodiment, the group may be associated with i) one or more models and / or ii) one or more functions.

[0191] As an example, operations related to one or more models and / or one or more functions may be indicated based on the second information. This embodiment may be based on method 1.

[0192] As an example, the operation may include at least one of: i) activation, ii) deactivation, iii) selection, iv) switching, v) updating, and / or vi) rollback.

[0193] As an example, the operation may be indicated based on an ID or unit associated with the group.

[0194] According to an embodiment, at least one configuration related to the group may be reset based on the second information.This embodiment may be based on Method 1 or Method 1-1.

[0195] As an example, the at least one configuration may be related to at least one of CSI compression, CSI prediction, beam prediction, and / or positioning.

[0196] As an example, at least one configuration may include at least one of: i) a set of reference signals (RS) associated with the measurement, ii) a prediction window associated with channel state information (CSI) and / or beams, and / or iii) a granularity associated with reporting of CSI and / or beams.

[0197] The above operations based on S310 and S320 can be performed by Figure 5 For example, the first device 100 / 200 may control one or more transceivers 130 / 230 and / or one or more memories 140 / 240 to perform operations based on S310 and S320.

[0198] Hereinafter, the above-mentioned embodiment will be described in detail in terms of the operation of the second device.

[0199] S410 and S440 described below correspond to Figure 3 By considering the corresponding relationship, redundant description is omitted. That is, the specific description of the operation of the second device described below can be used with the corresponding operation. Figure 3 The description / implementation method is replaced by .

[0200] Figure 4 is a flowchart for describing a method performed by a second device according to another embodiment of the present disclosure.

[0201] Reference Figure 4 According to another embodiment of the present disclosure, the method performed by the second device includes a first information sending step S410 and a second information sending step S420.

[0202] In S410 , the second device sends first information related to the group to the first device.

[0203] In S420, the second device sends second information related to management of the group to the first device.

[0204] The above operations based on S410 and S420 can be performed by Figure 5 For example, the second device 100 / 200 may control one or more transceivers 130 / 230 and / or one or more memories 140 / 240 to perform operations based on S410 and S420.

[0205] Refer to the following Figure 5 The following describes devices to which embodiments of the present disclosure are applicable (devices that implement methods / operations according to embodiments of the present disclosure).

[0206] Figure 5 The configurations of the first device and the second device according to the embodiment of the present disclosure are illustrated.

[0207] The first device 100 may include a processor 110 , an antenna unit 120 , a transceiver 130 , and a memory 140 .

[0208] The processor 110 can perform signal processing related to the baseband, and includes a high-level processing unit 111 and a physical layer processing unit 115. The high-level processing unit 111 can process operations of the MAC layer, the RRC layer, or a higher layer. The physical layer processing unit 115 can process operations of the PHY layer. For example, if the first device 100 is a base station (BS) device in BS-UE communication, the physical layer processing unit 115 can perform uplink received signal processing, downlink transmitted signal processing, etc. For example, if the first device 100 is a first UE device in inter-UE communication, the physical layer processing unit 115 can perform downlink received signal processing, uplink transmitted signal processing, sidelink transmitted signal processing, etc. In addition to performing signal processing related to the baseband, the processor 110 can also control the overall operation of the first device 100.

[0209] The antenna unit 120 may include one or more physical antennas, and if the antenna unit 120 includes multiple antennas, MIMO transmission / reception is supported. The transceiver 130 may include a radio frequency (RF) transmitter and an RF receiver. The memory 140 may store information processed by the processor 110 and software, an operating system, and applications related to the operation of the first device 100. The memory 140 may also include components such as a buffer.

[0210] In the embodiments described in the present disclosure, the processor 110 of the first device 100 may be configured to implement operations of a BS in BS-UE communication (or operations of a first UE device in inter-UE communication).

[0211] The second device 200 may include a processor 210 , an antenna unit 220 , a transceiver 230 , and a memory 240 .

[0212] The processor 210 can perform signal processing related to the baseband and includes a high-level processing unit 211 and a physical layer processing unit 215. The high-level processing unit 211 can process operations of the MAC layer, the RRC layer, or higher layers. The physical layer processing unit 215 can process operations of the PHY layer. For example, if the second device 200 is a UE device in BS-UE communication, the physical layer processing unit 215 can perform downlink received signal processing, uplink transmitted signal processing, etc. For example, if the second device 200 is a second UE device in inter-UE communication, the physical layer processing unit 215 can perform downlink received signal processing, uplink transmitted signal processing, sidelink received signal processing, etc. In addition to performing signal processing related to the baseband, the processor 210 can also control the overall operation of the second device 210.

[0213] The antenna unit 220 may include one or more physical antennas, and if the antenna unit 220 includes multiple antennas, MIMO transmission / reception is supported. 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, an operating system, and applications related to the operation of the second device 200. The memory 240 may also include components such as a buffer.

[0214] In the embodiments described in the present disclosure, the processor 210 of the second device 200 may be configured to implement operations of a UE in BS-UE communication (or operations of a second UE device in inter-UE communication).

[0215] The description of the BS and UE in BS-UE communication (or the first UE device and the second UE device in inter-UE communication) in the examples of the present disclosure can be equally applied to the operations of the first device 100 and the second device 200, and redundant description is omitted.

[0216] In addition to LTE, NR, and 6G, the wireless communication technology implemented in the apparatus 100 and the apparatus 200 according to the present disclosure may also include 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 in standards such as LTE Cat NB1 and / or LTE Cat NB2. NB-IoT technology is not limited to the above names.

[0217] Additionally or alternatively, the wireless communication technology implemented in the apparatus 100 and the apparatus 200 according to the present disclosure may perform communication based on the LTE-M technology. For example, the LTE-M technology may be an example of an LPWAN technology and may be referred to by various names, such as enhanced machine type communication (eMTC). For example, the LTE-M technology may be implemented using at least one of various standards, such as 1) LTE CAT0, 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. The LTE-M technology is not limited to the above names.

[0218] Additionally or alternatively, considering low-power communication, the wireless communication technology implemented in the apparatus 100 and the apparatus 200 according to the present disclosure may include at least one of ZigBee, Bluetooth, and a low-power wide area network (LPWAN), and is not limited to the above names. For example, ZigBee technology can create a personal area network (PAN) related to small / low-power digital communication based on various standards such as IEEE 802.15.4, and can be referred to by various names.

Claims

1. A method performed by a first device in a wireless communication system, the method comprising the following steps: receiving first information related to the group; as well as Second information related to management of the group is received.

2. The method according to claim 1, wherein The groups are associated with i) one or more models and / or ii) one or more functions.

3. The method according to claim 2, wherein: An operation related to the one or more models and / or the one or more functions is indicated based on the second information.

4. The method according to claim 3, wherein: The operation includes at least one of the following: i) activation, ii) deactivation, iii) selection, iv) switching, v) updating, and / or vi) rollback.

5. The method according to claim 3, wherein The operation is indicated based on an ID or unit associated with the group.

6. The method according to claim 1, wherein At least one configuration associated with the group is reset based on the second information.

7. The method according to claim 6, wherein: The at least one configuration includes at least one of the following: i) a reference signal RS set related to the measurement, ii) a prediction window related to the channel state information CSI and / or beam, and / or iii) a granularity related to the reporting of the CSI and / or the beam.

8. The method according to claim 1, wherein Each of the groups is associated with a common attribute.

9. The method according to claim 8, wherein The common attribute is based on at least one of: i) segment, ii) configuration, iii) data traffic, iv) mobility, and / or v) interference.

10. A first device operating in a wireless communication system, the first device comprising: one or more transceivers; one or more processors; as well as one or more memories connected to the one or more processors and storing instructions, The instructions configure the one or more processors to perform all the steps of the method according to any one of claims 1 to 9 upon execution by the one or more processors.

11. A device comprising: one or more memories, and one or more processors functionally connected to the one or more memories, The one or more memories store instructions that, upon execution 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 9.

12. One or more non-transitory computer-readable media storing instructions, in, 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 9.

13. A method performed by a second device in a wireless communication system, the method comprising the following steps: sending first information related to the group; and Second information related to management of the group is transmitted.

14. A second device operating in a wireless communication system, the second device comprising: one or more transceivers; one or more processors; as well as One or more memories connected to the one or more processors and storing instructions that, upon execution by the one or more processors, configure the one or more processors to perform all the steps of the method according to claim 13.

Images