Terminal, wireless communication method, and base station

Abstract

A terminal according to one aspect of the present disclosure comprises: a reception unit that receives a data set or a model parameter; and a control unit that uses the data set or the model parameter, derives a model to be specified, and uses the derived model to generate channel state information feedback. According to the aspect of the present disclosure, it is possible to achieve a favorable overhead reduction / channel estimation / resource utilization.

Description

Terminal, Wireless Communication Method, and Base Station

[0001] The present disclosure relates to a terminal, a wireless communication method, and a base station in a next-generation mobile communication system.

[0002] In a Universal Mobile Telecommunications System (UMTS) network, Long Term Evolution (LTE) was specified for the purpose of achieving further high data rates, low latency, etc. (Non-Patent Document 1). Also, LTE-Advanced (3GPP Rel. 10-14) was specified for the purpose of further increasing capacity and enhancing performance of LTE (Third Generation Partnership Project (3GPP (registered trademark)) Release (Rel.) 8, 9).

[0003] Successor systems to LTE (for example, also referred to as 5th generation mobile communication system (5G), 5G+ (plus), 6th generation mobile communication system (6G), New Radio (NR), 3GPP Rel. 15 and later, etc.) are also being considered.

[0004] 3GPP TS 36.300 V8.12.0, "Evolved Universal Terrestrial Radio Access (E-UTRA) and Evolved Universal Terrestrial Radio Access Network (E-UTRAN); Overall description; Stage 2 (Release 8)", April 2010

[0005] Regarding future wireless communication technologies, it is being considered to utilize artificial intelligence (AI) technologies such as machine learning (ML) for network / device control, management, etc.

[0006] For example, in future wireless communication systems (e.g., Rel. 20 and beyond), the introduction of combinations of options related to inter-vendor collaboration is being considered.

[0007] However, the specific UE behavior for such combinations of options has not been sufficiently considered. If this consideration is insufficient, it may not be possible to properly utilize AI / ML models in future wireless communication systems, potentially hindering improvements in communication throughput.

[0008] Therefore, one of the objectives of this disclosure is to provide a terminal, a wireless communication method, and a base station that can achieve suitable overhead reduction, channel estimation, and resource utilization.

[0009] A terminal according to one aspect of this disclosure includes a receiving unit that receives a dataset or model parameters, and a control unit that uses the dataset or model parameters to derive a specified model and uses the derived model to generate channel state information feedback.

[0010] According to one aspect of this disclosure, suitable overhead reduction, channel estimation, and resource utilization can be achieved.

[0011] Figure 1 shows an example of an AI model management framework. Figure 2 shows an example of specifying an AI model. Figure 3 shows an example of an ORAN architecture. Figure 4 shows an example of AI-based CSI feedback. Figure 5 shows an example of processing when the UE has a decoder. Figure 6 shows an example of CSI reconstruction using a proxy model. Figure 7A shows an example of generating an existing NR codebook. Figure 7B shows an example of signal generation related to option 1. Figure 7C shows an example of signal reconstruction related to option 1. Figure 8 shows an example of signal generation / reconstruction related to option 3a-1. Figure 9 shows an example of signal generation / reconstruction related to option 3a-2. Figure 10 shows an example of signal generation / reconstruction related to option 3a-3. Figure 11 shows an example of signal generation / reconstruction related to option 3b. Figure 12 shows an example of signal generation / reconstruction related to option 4 / option 4-1. Figure 13 shows an example of signal generation / reconstruction related to option 5a-1. Figure 14 shows an example of signal generation / signal reconstruction related to option 5a-2. Figure 15 shows an example of signal generation / signal reconstruction related to option 5a-3. Figure 16 shows an example of signal generation / signal reconstruction related to option 5b. Figure 17 shows an example of a schematic configuration of a wireless communication system according to one embodiment. Figure 18 shows an example of a base station configuration according to one embodiment. Figure 19 shows an example of a user terminal configuration according to one embodiment. Figure 20 shows an example of the hardware configuration of a base station and user terminal according to one embodiment. Figure 21 shows an example of a vehicle according to one embodiment.

[0012] (Application of Artificial Intelligence (AI) Technology to Wireless Communication) Regarding future wireless communication technologies, the use of AI technologies such as Machine Learning (ML) for network / device control and management is being considered.

[0013] For example, terminals (user terminals, User Equipment (UE)) and base stations (BS) are being considered to utilize AI technology to improve Channel State Information (CSI) feedback (e.g., overhead reduction, improved accuracy, prediction), beam management (e.g., improved accuracy, prediction in the spatiotemporal domain), and position measurement (e.g., improved position estimation / prediction).

[0014] The AI ​​model may output at least one piece of information, such as an estimated value, a predicted value, a selected action, or a classification, based on the input information. The UE / BS may input channel status information, reference signal measurements, etc., to the AI ​​model and output highly accurate channel status information / measurements / beam selection / position, future channel status information / wireless link quality, etc.

[0015] In this disclosure, AI may be interpreted as an object (also called a subject, object, data, function, program, etc.) having at least one of the following characteristics: - estimation based on observed or collected information, - selection based on observed or collected information, - prediction based on observed or collected information.

[0016] In this disclosure, estimation, prediction, and inference may be interpreted interchangeably. Furthermore, in this disclosure, estimate, predict, and infer may be interpreted interchangeably.

[0017] In this disclosure, an object may be, for example, a device or apparatus such as a UE or BS. In this disclosure, an object may also refer to a program / model / entity that operates on such apparatus.

[0018] Furthermore, in this disclosure, the AI ​​model may be reinterpreted as an object having (implementing) at least one of the following features: - generating estimates by feeding; - predicting estimates by feeding; - discovering features by feeding; - selecting actions by feeding.

[0019] Furthermore, in this disclosure, the term "AI model" may also mean a data-driven algorithm that applies AI technology to generate a set of outputs based on a set of inputs.

[0020] Furthermore, in this disclosure, AI models, models, ML models, predictive analytics, predictive analytics models, tools, autoencoders, encoders, decoders, neural network models, AI algorithms, schemes, etc., may be interpreted interchangeably. Also, AI models may be derived using at least one of the following: regression analysis (e.g., linear regression analysis, multiple regression analysis, logistic regression analysis), support vector machines, random forests, neural networks, deep learning, etc.

[0021] In this disclosure, the term "autoencoder" may be interpreted interchangeably with any autoencoder, such as a stacked autoencoder or a convolutional autoencoder. The encoder / decoder in this disclosure may employ models such as Residual Network (ResNet), DenseNet, or RefineNet.

[0022] Furthermore, in this disclosure, terms such as encoder, encoding, encoding / encoded, modification / change / control by an encoder, compression, compression / compressed, generating, and generated / generated may be interpreted interchangeably.

[0023] Furthermore, in this disclosure, terms such as decoder, decoding, decoding / decoded, modification / change / control by a decoder, decompressing, decompressing / decompressed, reconstructing, and reconstructing / reconstructed may be interpreted interchangeably.

[0024] In this disclosure, the term "layer" (referring to an AI model) may be interpreted interchangeably with the terms "input layer," "hidden layer," etc., used in an AI model. The layers in this disclosure may correspond to at least one of the following: an input layer, a hidden layer, an output layer, a batch normalization layer, a convolutional layer, an activation layer, a dense layer, a normalization layer, a pooling layer, an attention layer, a dropout layer, a fully connected layer, etc.

[0025] In this disclosure, methods for training AI models may include supervised learning, unsupervised learning, reinforcement learning, and federated learning. Supervised learning may mean the process of training a model from inputs and corresponding labels. Unsupervised learning may mean the process of training a model without labeled data. Reinforcement learning may mean the process of training a model from inputs (in other words, states) and feedback signals (in other words, rewards) resulting from the model's outputs (in other words, actions) in an environment in which the model interacts.

[0026] In this disclosure, terms such as generation, calculation, and derivation may be interpreted interchangeably. In this disclosure, terms such as implementation, operation, function, and execution may be interpreted interchangeably. In this disclosure, terms such as training, learning, updating, and retraining may be interpreted interchangeably. In this disclosure, terms such as inference, after-training, production use, and actual use may be interpreted interchangeably. In this disclosure, "signal" may be interpreted interchangeably with "signal / channel".

[0027] Figure 1 shows an example of an AI model management framework. In this example, each stage related to the AI ​​model is shown as a block. This example is also referred to as AI model lifecycle management (LCM).

[0028] The data collection stage is the phase in which data is collected for the generation / updating of an AI model. The data collection stage may also include data organization (e.g., deciding which data to transfer for model training / model inference) and data transfer (e.g., transferring data to entities (e.g., UE, gNB) that will be used for model training / model inference).

[0029] Data collection may also mean the process by which data is collected by a network node, management entity, or UE for the purpose of AI model training / data analysis / inference. In this disclosure, processing and procedures may be interpreted interchangeably. In this disclosure, collection may also mean obtaining a dataset (e.g., usable as input / output) for AI model training / inference based on measurements (e.g., channel measurements, beam measurements, radio link quality measurements, location estimation).

[0030] In this disclosure, offline field data may be data collected from the field (real world) and used for offline training of an AI model. In this disclosure, online field data may be data collected from the field (real world) and used for online training of an AI model.

[0031] In the model training stage, the model is trained based on the data (training data) transferred from the collection stage. This stage may include data preparation (e.g., data preprocessing, cleaning, formatting, transformation, etc.), model training / validation, model testing (e.g., checking whether the trained model meets performance thresholds), model exchange (e.g., transferring the model for distributed learning), and model deployment / update (deploying / updating the model to entities that perform model inference).

[0032] Furthermore, AI model training may also refer to the process of training an AI model in a data-driven manner and obtaining a trained AI model for inference.

[0033] Furthermore, AI model validation may refer to a sub-process of training that evaluates the quality of the AI ​​model using a different dataset than the one used for model training. This sub-process helps in selecting model parameters that generalize beyond the dataset used for model training.

[0034] Furthermore, AI model testing may refer to a sub-training process that evaluates the performance of the final AI model using a different dataset than the one used for model training / validation. Unlike validation, testing does not necessarily require subsequent model tuning.

[0035] In the model inference stage, model inference is performed based on the data (inference data) transferred from the collection stage. This stage may include data preparation (e.g., data preprocessing, cleaning, formatting, transformation, etc.), model inference, model monitoring (e.g., monitoring the performance of the model inference), model performance feedback (feeding back model performance to the entities being trained on the model), and output (providing the model output to the actors).

[0036] Furthermore, AI model inference may also refer to the process of using a trained AI model to produce a set of outputs from a set of inputs.

[0037] Furthermore, the UE-side model may refer to an AI model in which the inference is performed entirely within the UE. The network-side model may refer to an AI model in which the inference is performed entirely within the network (e.g., gNB).

[0038] Furthermore, a one-sided model may refer to either the UE-side model or the network-side model. A two-sided model may refer to a pair of AI models in which joint inference is performed. Here, joint inference may include AI inference in which the inference is performed jointly across the UE and the network, for example, the first part of the inference may be performed first by the UE and the rest by the gNB (or vice versa).

[0039] Furthermore, AI model monitoring may also refer to the process of monitoring the inference performance of an AI model, and may be interchangeable with model performance monitoring, performance monitoring, etc.

[0040] Model registration may also mean making a model executable (registering it) by assigning a version identifier to the model and compiling it for specific hardware used during the inference phase. Model deployment may also mean delivering (or activating) a runtime image (or execution environment image) of a fully developed and tested model to a target (e.g., UE / gNB) where inference will be performed.

[0041] The actor stage may include an action trigger (e.g., a decision on whether to trigger an action against another entity), feedback (e.g., feedback of information necessary for training data / inference data / performance feedback), etc.

[0042] Note that, for example, training of a model for mobility optimization may be performed, for example, in network (Network (NW)) operation, administration, and maintenance (OAM) / gNodeB (gNB). In the former case, interoperability, large-capacity storage, operator manageability, and model flexibility (such as feature engineering) are advantageous. In the latter case, advantages include the latency of model updates and the absence of data exchange for model deployment. The inference of the above model may be performed, for example, in gNB.

[0043] Depending on the use case (or, in other words, the functionality of the AI model), the entity that performs training / inference may be different. The functionality of the AI model may include beam management, beam prediction, autoencoder (or information compression), CSI feedback, positioning, etc.

[0044] For example, for AI-assisted beam management based on measurement reports, OAM / gNB may perform model training and gNB may perform model inference.

[0045] For AI-assisted UE-assisted positioning, Location Management Function (LMF) may perform model training and the LMF may perform model inference.

[0046] For CSI feedback / channel estimation using an autoencoder, OAM / gNB / UE may perform model training and gNB / UE may (jointly) perform model inference.

[0047] For AI-assisted beam management or AI-assisted UE-based positioning based on beam measurements, OAM / gNB / UE may perform model training and UE may perform model inference.

[0048] Model activation may also mean enabling an AI model for a specific function. Model deactivation may also mean deactivating an AI model for a specific function. Model switching may also mean deactivating the currently active AI model for a specific function and activating a different AI model.

[0049] Furthermore, model transfer may also mean distributing an AI model over the air interface. This distribution may include distributing either or both parameters of a known model structure, or a new model having those parameters, at the receiving end. This distribution may also include a complete or partial model. Model download may mean transferring a model from the network to the UE. Model upload may mean transferring a model from the UE to the network.

[0050] Figure 2 shows an example of specifying an AI model. In this example, the UE and NW (for example, the base station (BS)) can recognize models #1 and #2 (they do not need to fully understand the details of the models). The UE may report the performance of model #1 and model #2 to the NW, and the NW may instruct the UE on which AI model to use.

[0051] (Open RAN (ORAN)) The ORAN architecture will be explained below using Figure 3.

[0052] In 5G NR, the standardization of Open RAN (ORAN) is being considered to reduce the burden on operators in building and operating RANs, and to facilitate the introduction of automation utilizing AI / ML models.

[0053] In conventional closed networks, the radio units (RUs) and distributed units (DUs) / central units (CUs) that make up the base station can only connect to equipment from the same vendor.

[0054] On the other hand, ORAN enables the interconnection of equipment from multiple different vendors (e.g., RUs and CUs / DUs), allowing for a more scalable and flexible RAN configuration. This makes it possible to support new services / industries and diversifying requirements.

[0055] In the ORAN architecture, a RIC (RAN Intelligent Controller) may be defined as a logical node that automates and optimizes the parameter design, configuration, and operation of base stations in order to realize network operation utilizing AI / ML models.

[0056] As shown in the figure, RIC may include non-real-time RIC and near real-time RIC (which may simply be called real-time RIC).

[0057] Non-real-time RICs may be controlled in seconds and may be located within a Service Management and Orchestration (SMO) that monitors, maintains, and orchestrates the RAN.

[0058] A non-real-time RIC may be connected to a near-real-time RIC via an A1 interface.

[0059] The near real-time RIC may be controlled in milliseconds and may be connected to E2 nodes such as O-eNB (ORAN base station), O-CU (Open Central Unit), and O-DU (Open Distributed Unit) via the E2 interface. The SMO may be connected to the O-eNB, O-CU, and O-DU via the O1 interface.

[0060] The non-real-time RIC may work in conjunction with the function unit that provides OAM services within the SMO to collect data accumulated within the E2 node, such as Performance Management Counter, Fault Management Data, and Trace Management Data.

[0061] The near real-time RIC may collect information about the E2 node from the E2 node using the E2 interface. The near real-time RIC may also control the E2 node according to the policy notified by the non-real-time RIC.

[0062] The ORAN architecture shown in the diagram is merely one example and is not the only example.

[0063] (AI-based CSI feedback) As a typical sub-use case, spatial-frequency domain CSI compression using a two-sided AI model is being considered.

[0064] Figure 4 shows an example of AI-based CSI feedback. The UE performs preprocessing, AI / ML-based CSI generation, and postprocessing on measurement results related to CSI, and transmits the encoded bits (CSI feedback information) to the NW (base station). The NW (base station) performs preprocessing, AI / ML-based CSI reconstruction, and postprocessing on the received bits to obtain the CSI (channel / precoding matrix).

[0065] <CSI Reconstruction in UE> Figure 5 shows an example of processing when the UE has a decoder. If the UE has the same decoder as the base station, it can use the reconstructed CSI in pre-processing. For example, SVD + IDFT conversion may be used for pre-processing. As shown in Figure 5, the UE can monitor the accuracy of the model by comparing the target CSI (error-free CSI (W, H) due to CSI compression) and the reconstructed CSI (W', H'). Based on the reconstructed CSI, the UE can report rank information and channel quality indication information.

[0066] However, there are two challenges to CSI reconstruction in UE: (1) Additional UE processing is required for CSI reconstruction, necessitating the storage of the reconstruction model (decoder) in addition to the generation model (encoder); (2) Intellectual property rights issues. Base station (gNB) vendors may consider the model information to be their intellectual property and may not want to disclose generational model information to UE vendors.

[0067] The UE can use a proxy model to calculate the expected reconfigured CSI instead of the reconfiguration model actually used by the base station. The proxy model is a model that mimics the reconfiguration model used by the base station. The proxy model can be a simple model. This reduces the processing and storage problems of the UE (as described in (1) above). The proxy model may differ from the actual reconfiguration model at the base station. This avoids the issue of uniqueness (as described in (2) above).

[0068] Figure 6 shows an example of CSI reconstruction (pseudo-reconstruction) using a proxy model. The UE receives a proxy model for decoding from the NW (base station). The UE uses this proxy model to reconstruct the encoded CSI and outputs it as the estimated CSI result. The UE maps the estimated result with the actual CSI and calculates the KPI (Key Performance Indicator) (e.g., SGCS (squared generalized cosine similarity)). There is a strong correlation between the KPI (SGCS) when using an actual decoder as in the example in Figure 5 and the KPI (SGCS) when using a proxy model as in the example in Figure 6.

[0069] (Inter-vendor collaboration) In future wireless communication systems (e.g., Rel. 19 and beyond), the introduction of at least one of the following options 1 to 5 is being considered as a scheme for inter-vendor collaboration: Option 1: Fully standardized model. Option 2: Standardized dataset. Option 3: Standardized reference model structure + parameter exchange between NW-side and UE-side. Option 4: Standardized data / dataset format + dataset exchange between NW-side and UE-side. Option 5: Standardized data / dataset format + reference model exchange between NW-side and UE-side.

[0070] Of these, option 1 may mean that the structure and parameters of the model used are standardized / specified.

[0071] As in Option 1, standardizing / specifying the models used can contribute to reducing the complexity of inter-vendor collaboration.

[0072] Furthermore, these options are particularly suitable for use in the operation of a two-side model, regardless of whether they are applied in inter-vendor collaboration. In a two-side model, model pairing is performed on the NW side and UE side, and by specifying at least one of the models, the pairing operation can be made easier. Each embodiment of this disclosure can also be applied regardless of whether or not it is applied in inter-vendor collaboration.

[0073] For example, Option 1 specifies the model structure / parameters, eliminating the need for model determination / pairing procedures between the UE and NW, and also facilitating model testing.

[0074] Figure 7A shows an example of generating an existing NR codebook. As shown in Figure 7A, in existing NR, feedback content (i １ , i ２ From this, a precoding matrix is ​​generated according to the specifications.

[0075] Figure 7B shows an example of signal generation related to Option 1. As shown in Figure 7B, in Option 1, the feedback content (i) is generated from the precoding / channel matrix according to the specified model (which may also be called the Specification of a Model or Model Specification). ｘ ) may be generated.

[0076] Figure 7C shows an example of signal reconstruction related to Option 1. As shown in Figure 7C, in Option 1, the feedback content (i ｘThe precoding / channel matrix may be reconstructed according to the model specifications.

[0077] Furthermore, in option 3, for example, in order to specify the structure of the model, only the procedure for determining / pairing model parameters between the UE and NW can be performed.

[0078] Option 3 is broadly divided into Option 3a (which may include Option 3a-1 / Option 3a-2 / Option 3a-3) and Option 3b, depending on the part in which parameter exchange is performed and whether or not offline engineering is performed on the UE side.

[0079] Option 3a is an option in which offline engineering is performed on the UE side.

[0080] Option 3a-1 is an option in which parameters of the signal generation part are swapped and offline engineering is performed.

[0081] Figure 8 shows an example of signal generation / reconstruction related to option 3a-1. In the example shown in Figure 8, CSI is used as the signal for explanation, and the same applies to subsequent figures. Therefore, in this disclosure, the CSI generation / reconstruction part may be read as any signal generation / reconstruction part.

[0082] As shown in Figure 8, in option 3a-1, the model structure for the signal (CSI) generation part is specified. The UE receives information about the model required for the CSI generation part from the NW (e.g., model parameters / weights). The UE then performs offline engineering on its side and uses the derived model to generate the CSI from the precoding / channel matrix (target CSI) and provides CSI feedback to the NW. The NW reconstructs the target CSI using the CSI reconstruction part.

[0083] Option 3a-2 is an option in which parameters of the signal reconstruction part are swapped and offline engineering (with a long delay) is performed.

[0084] Figure 9 shows an example of signal generation / reconstruction related to option 3a-2. As shown in Figure 9, in option 3a-2, the model structure is specified for the signal (CSI) reconstruction part (the CSI generation part may depend on the UE implementation). The UE receives information about the model necessary for the CSI reconstruction part from the NW (e.g., model parameters / weights). The UE then performs offline engineering on its side and uses the derived model to generate the CSI from the precoding / channel matrix (target CSI) and provides CSI feedback to the NW. The NW reconstructs the target CSI using the CSI reconstruction part.

[0085] Option 3a-3 is an option in which parameters are swapped in both the signal generation part and the signal reconstruction part, and offline engineering is performed.

[0086] Figure 10 shows an example of signal generation / reconstruction related to option 3a-3. As shown in Figure 10, in option 3a-3, the model structure is specified for both the signal (CSI) generation part and the signal (CSI) reconstruction part. The UE receives from the NW information about the model required for the CSI generation part (e.g., model parameters / weights) and information about the model required for the CSI reconstruction part (e.g., model parameters / weights). The UE then performs offline engineering on its side and uses the derived model to generate a CSI from the precoding / channel matrix (target CSI) and provides CSI feedback to the NW. The NW reconstructs the target CSI using the CSI reconstruction part.

[0087] Option 3b is an option in which the parameters of the signal generation part are swapped, but offline engineering is not performed.

[0088] Figure 11 shows an example of signal generation / reconstruction related to option 3b. As shown in Figure 11, in option 3b, the model structure for the signal (CSI) generation part is specified. The UE receives information about the model necessary for the CSI generation part from the NW (Network). The UE then uses the specified model to generate a CSI from the precoding / channel matrix (target CSI) based on the received model information and provides CSI feedback to the NW. The NW reconstructs the target CSI using the CSI reconstruction part.

[0089] Furthermore, for example, option 4 may include at least one of the following: option 4-1, in which a dataset exchange is performed for the target CSI and CSI feedback; option 4-2, in which a dataset exchange is performed for the CSI feedback and the reconstructed CSI; and option 4-3, in which a dataset exchange is performed for the target CSI, the CSI feedback, and the reconstructed CSI. In options 4-1 / 4-2 / 4-3, after the NW model training, a dataset is sent that will be used to train the UE-side model.

[0090] Figure 12 shows an example of signal generation / reconstruction related to Option 4 / Option 4-1. As shown in Figure 12, in Option 4 / 4-1, dataset generation is performed by offline engineering from the CSI generation part / CSI reconstruction part on the NW side. The generated dataset may be a target CSI / CSI feedback and is sent to the UE using specific signaling for dataset transfer / delivery. The UE trains / tests a model for the CSI generation part by offline engineering based on the received dataset and derives a model for the CSI generation part. Using the derived model, the UE generates a CSI from the precoding / channel matrix (target CSI) and provides CSI feedback to the NW. The NW reconstructs the target CSI using the CSI reconstruction part.

[0091] Furthermore, for example, option 5 allows for the specification of a model format (for distribution / transfer) and enables the UE and NW to perform judgment / pairing regarding the reference model.

[0092] Option 5 is broadly divided into Option 5a-1, Option 5a-2, Option 5a-3, and Option 5b, depending on whether or not there is a part involving model (model format) exchange and whether or not there is offline engineering on the UE side.

[0093] Option 5a-1 is an option in which the signal generation part is model-swapped and offline engineering is performed.

[0094] Figure 13 shows an example of signal generation / reconstruction related to option 5a-1. As shown in Figure 13, in option 5a-1, the model for the signal (CSI) generation part may be based on the UE's implementation. The UE receives from the NW a model (model format) for the CSI generation part and information about the model (e.g., model parameters / weights). The UE then performs offline engineering on its side and uses the derived model to generate a CSI from the precoding / channel matrix (target CSI) and provides CSI feedback to the NW. The NW reconstructs the target CSI using the CSI reconstruction part.

[0095] Option 5a-2 is an option in which the signal reconstruction part is model-swapped and offline engineering (with a long delay) is performed.

[0096] Figure 14 shows an example of signal generation / reconstruction related to option 5a-2. As shown in Figure 14, in option 5a-2, the model for the signal (CSI) generation part may be based on the UE's implementation. The UE receives from the NW a model (model format) for the CSI reconstruction part and information about the model (e.g., model parameters / weights). The UE then performs offline engineering on its side and uses the derived model to generate a CSI from the precoding / channel matrix (target CSI) and provides CSI feedback to the NW. The NW reconstructs the target CSI using the CSI reconstruction part.

[0097] Option 5a-3 is an option in which both the signal generation part and the signal reconstruction part are model-swapped and offline engineering is performed.

[0098] Figure 15 shows an example of signal generation / reconstruction related to option 5a-3. As shown in Figure 15, in option 5a-3, the model for the signal (CSI) generation part may be based on the UE's implementation. The UE receives from the NW a model (model format) for the CSI generation part, a model (model format) for the CSI reconstruction part, information about the model for the CSI generation part (e.g., model parameters / weights), and information about the model for the CSI reconstruction part (e.g., model parameters / weights). The UE then performs offline engineering on its side and uses the derived model to generate a CSI from the precoding / channel matrix (target CSI) and provides CSI feedback to the NW. The NW reconstructs the target CSI using the CSI reconstruction part.

[0099] Option 5b is an option in which the signal generation part is model-swapped, but offline engineering is not performed.

[0100] Figure 16 shows an example of signal generation / reconstruction related to option 5b. As shown in Figure 16, in option 5b, the model for the signal (CSI) generation part may be based on the UE's implementation. The UE receives from the NW a model (model format) for the CSI generation part and information about the model for the CSI generation part (e.g., model parameters / weights). The UE then generates a CSI from the pre-coding / channel matrix (target CSI) based on / using the received model and information about the model, and provides CSI feedback to the NW. The NW reconstructs the target CSI using the CSI reconstruction part.

[0101] (Analysis) In future wireless communication systems (e.g., Rel. 20 and beyond), the introduction of the above-mentioned combination of vendor collaboration options is being considered.

[0102] For example, it has been considered that options 3a-1 and 4-1 (which may also be called Direction A) may be applied in combination with option 1 (which may also be called Direction B).

[0103] For example, in the combination of Option 1 and 3a-1, it is thought that the same model structure and some of the model parameters can be reused proprietary when applying Option 3a-1, thereby reducing the effort required for standardization / specification.

[0104] For example, in the combination of Option 1 and 4-1, when applying Option 4-1, the same model structure can be reused to align / align the model backbone for performance, and some of the model parameters can also be reused.

[0105] However, the specific UE behavior for such combinations of options has not been sufficiently considered. If this consideration is insufficient, it may not be possible to properly utilize AI / ML models in future wireless communication systems, potentially hindering improvements in communication throughput.

[0106] Therefore, the inventors came up with a solution to this problem.

[0107] The embodiments of this disclosure will be described in detail below with reference to the drawings. Each wireless communication method according to the embodiments may be applied individually or in combination.

[0108] (Various substitutions) In this disclosure, words enclosed in parentheses () may indicate an explanation of the preceding word (e.g., an explanation of spelling), a paraphrase, a specific example, or supplementary explanation. Also, in this disclosure, words enclosed in square brackets [] may be interpreted as part of the overall meaning of the text, or they may be interpreted as being excluded (ignored). Note that parentheses () and square brackets [] may be used for purposes / meanings other than those described above.

[0109] In this disclosure, "A / B" and "at least one of A and B" may be interpreted as mutually exclusive. In this disclosure, "A / B / C" may mean "at least one of A, B, and C".

[0110] In this disclosure, terms such as notice, activate, deactivate, indicate (or specify), select, configure, update, and determine may be interpreted interchangeably. In this disclosure, terms such as support, control, controllable, operate, and capable of operating may be interpreted interchangeably.

[0111] In this disclosure, Radio Resource Control (RRC), RRC parameters, RRC messages, higher-layer parameters, fields, Information Elements (IE), settings, etc., may be interpreted interchangeably. In this disclosure, Medium Access Control elements (MAC Control Elements (CE)), update commands, activation / deactivation commands, etc., may be interpreted interchangeably.

[0112] In this disclosure, the upper layer signaling may be any or a combination thereof, such as Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information, and other messages (e.g., messages from the core network, such as positioning protocol messages (e.g., NR Positioning Protocol A (NRPPPa) / LTE Positioning Protocol (LPP)) messages).

[0113] In this disclosure, MAC signaling may include, for example, MAC Control Elements (MAC CEs) and MAC Protocol Data Units (PDUs). Broadcast information may include, for example, Master Information Blocks (MIBs), System Information Blocks (SIBs), Remaining Minimum System Information (RMSIs), and Other System Information (OSIs).

[0114] In this disclosure, physical layer signaling may include, for example, Downlink Control Information (DCI) and Uplink Control Information (UCI).

[0115] In this disclosure, the Network Function (NF) may include, for example, at least one of the following: • Application Function (AF) (e.g., a function that provides an application server outside the 5G Core Network (5GC)). • Access and Mobility Management Function (AMF) (e.g., a function that manages UE registration, location, etc.). • Data Network (DN) (e.g., a function that provides a data network outside the 5GC). • Location Management Function (LMF) (e.g., a function that controls communication related to location information services). • Non-3GPP Inter-Working Function (N3IWF) (e.g., a function that connects an untrusted non-3GPP access network to the 5GC). • Network Exposure Function (NEF) (e.g., a function that provides an application interface for the 5GC's NF services to the outside). • Network Slice Selection Function (NSSF) (e.g., a function that selects a network slice). • Network Data Analytics Function (NWDAF) (e.g., a function that analyzes network data). - Operation, Administration and Maintenance (Management) (OAM) (e.g., a function that provides means for maintenance and operation management). - Policy Control Function (PCF) (e.g., a function that controls the quality of data transfer paths, policies, etc.). - Session Management Function (SMF) (e.g., a function that manages sessions). - Trusted Non-3GPP Gateway Function (TNGF) (e.g., a function that connects trusted non-3GPP access networks to 5GC).- Trusted WLAN Interworking Function (TWIF) (e.g., a function that connects a trusted non-3GPP access network to 5G for non-5G UEs via a wireless local area network (LAN)). - (Radio) Access Network ((R)AN) (e.g., a function that provides a wireless access network). - User Equipment (UE) (e.g., a function that allows users to access network services via a wireless interface). - Unified Data Management (UDM) (e.g., a function that stores / manages subscriber information, UE authentication information, etc.). - Unified Data Repository (UDR) (e.g., a function that manages authentication / authorization based on subscriber information). - User Plane Function (UPF) (e.g., a function that transmits user data packets). - Over The Top (OTT) (e.g., content / services / functions provided by an independent provider / vendor that bypass the telecommunications carrier's network).

[0116] Each embodiment of this disclosure can also be appropriately applied to an ORAN network (for example, a base station compliant with the ORAN specification).

[0117] In this disclosure, the terms "specified model," "specification of a model," and "model specification" may be interpreted interchangeably.

[0118] In this disclosure, an entity (e.g., a UE / NW entity) may generate an output from an input in a specific format according to a model specification.

[0119] The model specification may define at least one of the following: • Information / description of a series of layers / functions (e.g., type of computation (e.g., n-dimensional convolution, linear function, attention, sigmoid function, or ReLU function, etc.)), and information / description(s) of the parameters / weights required for the defined computation. • Information / description of a series of computations, and information / description of the parameters / weights required for the defined computation. • Information / description of the computation order across the defined layers / functions / computations. • Information / description of the data types / formats for inputs / outputs / each computation step. • Information about the specified (model) name / functionality, and the corresponding ID / version / timestamp / release number. • Information about applicable conditions / additional conditions.

[0120] In this disclosure, the specified model may mean a model / entity / module / functionality / behavior defined by the model specification.

[0121] In this disclosure, some information / descriptions of a model (e.g., layers) may be specified. In this case, the model that is partially specified may be referred to as the specified layer / parameter, the specified model part (part(s)), etc.

[0122] In this disclosure, the Signal Generation Part (SGP) may mean that a model / functionality / entity / module generates a signal to be transmitted based on an input signal.

[0123] For example, SGP may include a CSI generation part, a waveform generation part, etc.

[0124] In this disclosure, the terms SGP implemented and SGP implementation may be interpreted interchangeably. In this disclosure, the terms SGP specified, SGP specification, and SGP relating to model specification may be interpreted interchangeably.

[0125] In this disclosure, a Signal Reconstruction Part (SRP) may mean that a model / functionality / entity / module outputs (reconstructs) a signal based on a received signal.

[0126] In this disclosure, the terms reconstruct, construct, represent, display, describe, restore, process, etc., may be interpreted interchangeably.

[0127] For example, SRP may include a CSI reconstruction part, a waveform reconstruction part, etc.

[0128] In this disclosure, the terms "Implemented SRP" and "SRP implementation" may be interpreted interchangeably. In this disclosure, the terms "Specified SRP," "SRP Specification," and "SRP relating to Model Specification" may be interpreted interchangeably.

[0129] SGP / SRP may be specified by the model specification, or may be included as part of the specification by the model specification.

[0130] In this disclosure, input signals / output signals may mean at least a portion of the specified model / dataset.

[0131] In this disclosure, the CSI generation part may mean a set of operations that process an input precoding matrix / channel matrix and generate a feedback payload (or an output that can be used to further generate a feedback payload).

[0132] The CSI generation part may accept input in specific domains (e.g., spatial / frequency / angle / wavenumber / temporal / delay domains).

[0133] The CSI generation part may include input processing, such as converting input from one domain (for example, a part of the spatial / frequency / angle / wavenumber / temporal / delay domain) to another domain (another part of the spatial / frequency / angle / wavenumber / temporal / delay domain).

[0134] The CSI generation part may include output quantization, which includes scalar quantization and at least one vector quantization for each element of the output.

[0135] In this disclosure, the CSI reconstruction part may mean a set of operations that process the input feedback payload and generate the precoding matrix / channel matrix to be reconstructed.

[0136] The CSI generation part may generate outputs in specific domains (e.g., spatial / frequency / angle / wavenumber / temporal / delay domains).

[0137] The CSI generation part may include dequantization of the input based on a quantization scheme that includes at least one of scalar quantization and vector quantization for each element of the output.

[0138] In this disclosure, the names and types of model specifications / parts of model specifications / SGP / SRP / input signals / output signals / CSI generation part / CSI reconstruction part are merely examples and are not limited to those described, and may be modified as appropriate depending on the applicable use case.

[0139] In this disclosure, the terms "model information" and "model information" may be interpreted interchangeably.

[0140] In this disclosure, offline engineering, offline operation, internal operation, processing, internal processing, model, and operations for activating / using / deploying / configuring at least one of the corresponding functionality / module / option (e.g., the corresponding codebook) may be interpreted interchangeably.

[0141] In this disclosure, the terms model, model backbone, model structure, model parameters, etc., may be interpreted interchangeably.

[0142] In this disclosure, UE and UE side may be interpreted interchangeably.

[0143] (Wireless communication method) The UE may receive a dataset for model training / derivation (e.g., a dataset related to the target CSI / CSI feedback) and model parameters from the NW.

[0144] The UE may use the dataset / model parameters to train / derive a model. The UE may use the trained / derivated model to generate signals (e.g., CSI feedback).

[0145] The models that UE trains / derives may utilize a specification model (the model backbone / structure / parameters of the model being specified).

[0146] When the UE receives / uses the dataset, options 4 / 4-1 above may be applied. This case will be explained in the first embodiment below.

[0147] When the UE receives / uses the dataset, option 3a-1 above may be applied. This case will be explained in the second embodiment below.

[0148] <First Embodiment> For example, options 1 and 4 / 4-1 may be applied in combination.

[0149] For example, the UE / UE side may assume that the same model backbone / structure / parameters as those of Option 1 (i.e., the specified model backbone / structure / parameters) will be applied to Option 4 / 4-1.

[0150] <<Embodiment 1-1>> A specification model of SGP / SRP may be used.

[0151] The UE may be configured or instructed to generate / update SGP / SRP based on the dataset.

[0152] The UE may receive a dataset for generating / updating SGP / SRP.

[0153] UE may assume that it will use the same model backbone for SGP / SRP as the specified / configured / instructed specification model.

[0154] In this disclosure, the term "model backbone" may mean at least one of the following: • Model type (e.g., at least one of CNN (Convolutional Neural Network), transformer, LSTM (Long Short-Term Memory), GNN (Graph Neural Network), etc.) • Number of layers • Normalization / activation function for each layer • Number of parameters for each layer • Connections between layers • Parameters of the reference model.

[0155] The UE may use / freeze / fix at least some of the parameters (model parameters) of the specification model.

[0156] The UE may assume that at least some of the parameters of the specified model [specified / configured / instructed] will be used / fixed for the generation / update of the SGP / SRP.

[0157] At least some of the parameters used / fixed may be determined according to the specifications, based on settings / instructions to the UE, based on the UE's capabilities, or based on at least a combination of these.

[0158] Furthermore, all parameters of the specified model [specified / configured / instructed] are available, and the UE may decide to use / fix some of them.

[0159] <<Embodiment 1-2>> Embodiment 1-2 describes the application of Embodiment 1-1 to the CSI compression case.

[0160] A specification model for the CSI generation part / CSI reconstruction part may be used.

[0161] The UE may be configured / instructed to generate / update the CSI generation part / CSI reconstruction part based on the dataset.

[0162] The UE may receive datasets for generating / updating the CSI generation part / CSI reconstruction part.

[0163] The UE may assume that it uses the same model backbone for the CSI generation part / CSI reconstruction part as the specification model [specified / configured / instructed].

[0164] The UE may use / freeze / fix at least some of the parameters (model parameters) of the specification model.

[0165] The UE may assume that at least some of the parameters of the specified model [specified / configured / instructed] will be used / fixed for generating / updating the CSI generation part / CSI reconstruction part.

[0166] At least some of the parameters used / fixed may be determined according to the specifications, based on settings / instructions to the UE, based on the UE's capabilities, or based on at least a combination of these.

[0167] Furthermore, all parameters of the specified model [specified / configured / instructed] are available, and the UE may decide to use / fix some of them.

[0168] According to the first embodiment described above, the UE operation relating to the combination of option 1 and 4 / 4-1 can be appropriately defined.

[0169] <Second Embodiment> For example, options 1 and 3a-1 may be applied in combination.

[0170] For example, the UE / UE side may be configured with the same model backbone / structure as Option 1 (i.e., the specified model backbone / structure), and may reuse the model parameters of Option 1 (i.e., the specified model parameters) by default. The UE may update only some of these model parameters.

[0171] <<Embodiment 2-1>> A specification model of SGP / SRP may be used.

[0172] The UE may receive specific settings / instructions using at least one of the methods described in the supplement below.

[0173] Based on the specific settings / instructions, the UE may decide to use the same model backbone as the specification model for the SGP / SRP that is being specified / configured / instructed.

[0174] The UE may, by default, use the model parameters (which may also be called reference model parameters) of the reference model (for example, the specification model for SGP / SRP).

[0175] Based on the specific setting / instruction, the UE may decide to use the same model parameters as the specified model parameters [specified / configured / instructed] by default.

[0176] The UE may receive some of the model parameters.

[0177] The UE may assume that it uses the same model parameters as the specified / configured / instructed model by default, and may make updates to some of the received model parameters.

[0178] For example, the UE may update some of the model parameters used by default with some of the received model parameters.

[0179] <<Embodiment 2-2>> Embodiment 2-2 describes the application of Embodiment 2-1 to the CSI compression case.

[0180] A specification model for the CSI generation part / CSI reconstruction part may be used.

[0181] The UE may receive specific settings / instructions using at least one of the methods described in the supplement below.

[0182] Based on the specific settings / instructions, the UE may decide to use the same model backbone as the specification model for the CSI generation part / CSI reconstruction part that is specified / configured / instructed.

[0183] The UE may, by default, use the model parameters of the reference model (for example, the specification model for the CSI generation part / CSI reconstruction part).

[0184] Based on the specific setting / instruction, the UE may decide to use the same model parameters as the specified model parameters [specified / configured / instructed] by default.

[0185] The UE may receive some of the model parameters for updating the CSI generation part / CSI reconstruction part.

[0186] The UE may assume, by default, that it uses the same model parameters as the specified / configured / instructed specification model, and may update some of the model parameters for the received CSI generation part / CSI reconstruction part.

[0187] For example, the UE may update some of the model parameters used by default to some of the model parameters for the received CSI generation part / CSI reconstruction part.

[0188] According to the second embodiment described above, the UE operation related to the combination of option 1 and 3a-1 can be appropriately defined.

[0189] <Modification> In this disclosure, functionality may be a set of parameters supported based on conditions indicated by UE capability (e.g., a set of parameters for CSI prediction / beam prediction / CSI compression).

[0190] In this disclosure, a UE may report parameter values ​​related to a function or model as conditions to the NW using at least one of the methods described in the supplement below. For example, the UE may report such conditions using a UE capability report or a UE feature / feature group report.

[0191] The UE may report parameter values ​​related to the function or model as additional conditions using at least one of the methods described in the supplement below, or by means other than signaling via the NW's Air Interface (e.g., the radio section (e.g., between the UE and the NW)).

[0192] The UE may specify parameter values ​​related to the function or model as additional conditions using at least one of the methods described in the supplement below, or by means other than signaling via the NW's Air Interface.

[0193] The UE may report certain information in this disclosure (e.g., parameter names) as information / instructions regarding additional conditions by using at least one of the methods described in the supplement below, or by means other than signaling via the NW's Air Interface.

[0194] The UE may indicate certain information in this disclosure (e.g., parameter names) as information / instructions regarding additional conditions by using at least one of the methods described in the supplement below, or by means other than signaling via the NW's Air Interface.

[0195] For example, the UE may report the device ID / device vendor ID as an additional condition, or may specify the cell ID as an additional condition.

[0196] For example, the UE may report / instruct information about a parameter name (e.g., a cell ID / UE ID instead of an ID value) as additional condition information / instruction.

[0197] In this disclosure, methods other than signaling via the NW's Air Interface may include at least one of the following: pre-configuration of the UE (e.g., by the UE vendor) and operator configuration provided by the NW operator.

[0198] In this disclosure, a model / function for CSI may mean a CSI report associated with a model ID or a specific function (e.g., at least one of the following: predicted CSI, compressed CSI, advanced CSI, and CSI of a specific type (e.g., type x)).

[0199] In this disclosure, AI / ML function, AI / ML function for CSI, and function for CSI may mean a function directed by the NW or reported by the UE (e.g., at least one of the predicted CSI, compressed CSI, advanced CSI, and a CSI of a particular type (e.g., type x)).

[0200] In this disclosure, AI / ML models, AI / ML models for CSI, and models for CSI may be identified by an ID or function, and may mean a model / entity that performs the specific function described above.

[0201] <Supplement> <<Model Information>> In this disclosure, AI model information (or simply "model") may mean information including at least one of the following: - Input / output information of the AI ​​model. - Pre-processing / post-processing information for the input / output of the AI ​​model. - Parameter information of the AI ​​model. - Training information for the AI ​​model. - Inference information for the AI ​​model. - Performance information regarding the AI ​​model.

[0202] Here, the input / output information of the above AI model may include information about at least one of the following: • Content of the input / output data (e.g., RSRP, SINR, amplitude / phase information in the channel matrix (or precoding matrix), information about the angle of arrival (AoA), information about the angle of departure (AoD), position information). • Auxiliary data information (may be called metadata). • Type of input / output data (e.g., immutable value, floating-point number). • Bit width of the input / output data (e.g., 64 bits for each input value). • Quantization interval (quantization step size) of the input / output data (e.g., 1 dBm for L1-RSRP). • Range of possible input / output data (e.g., [0, 1]).

[0203] In this disclosure, AoA information may include information on at least one of the azimuth angle of arrival and the zenith angle of arrival (ZoA). Also, AoD information may include, for example, information on at least one of the azimuth angle of departure and the zenith angle of departure (ZoD).

[0204] In this disclosure, location information may be location information relating to a UE / NW. Location information may include at least one of the following: information obtained using a positioning system (e.g., satellite positioning system (Global Navigation Satellite System (GNSS), Global Positioning System (GPS), etc.)) (e.g., latitude, longitude, altitude); information of a BS adjacent to (or serving) the UE (e.g., BS / cell identifier (ID), distance between BS and UE, direction / angle of BS(UE) as seen from UE(BS), coordinates of BS(UE) as seen from UE(BS) (e.g., X / Y / Z axis coordinates), etc.); and a specific address of the UE (e.g., Internet Protocol (IP) address). Location information of a UE is not limited to information based on the location of a BS, but may also be information based on a specific point.

[0205] Location information may include information about its own implementation (for example, the location / position of the antenna, the location / position of the antenna panel, the number of antennas, the number of antenna panels, etc.).

[0206] Location information may include mobility information. Mobility information may include information indicating the mobility type, information indicating the movement speed of the UE, the acceleration of the UE, and the direction of movement of the UE, or at least one of these.

[0207] Here, the mobility type may be at least one of the following: fixed location UE, movable / moving UE, no mobility UE, low mobility UE, middle mobility UE, high mobility UE, cell-edge UE, not-cell-edge UE, etc.

[0208] In this disclosure, the environmental information (for the data) may also be information about the environment in which the data is acquired / used, and may include, for example, frequency information (such as a band ID), environment type information (information indicating at least one of the following: indoor, outdoor, Urban Macro (UMa), Urban Micro (Umi)), or Line of Site (LOS) / Non-Line of Site (NLOS) information.

[0209] Here, LOS may mean that the UE and BS are in a line of sight to each other (or there are no obstructions), and NLOS may mean that the UE and BS are not in a line of sight to each other (or there are obstructions). The information indicating LOS / NLOS may be a soft value (e.g., the probability of LOS / NLOS) or a hard value (e.g., either LOS or NLOS).

[0210] In this disclosure, metadata may mean, for example, information about input / output information suitable for an AI model, information about acquired / acquirable data, etc. Specifically, metadata may include information about RS (e.g., CSI-RS / SRS / SSB, etc.) beams (e.g., the angle of each beam, 3dB beamwidth, shape of the beam being directed, number of beams), gNB / UE antenna layout information, frequency information, environmental information, metadata ID, etc. The metadata may also be used as input / output for the AI ​​model.

[0211] The pre-processing / post-processing information for the input / output of the above AI model may include information on at least one of the following: • Whether or not to apply normalization (e.g., Z-score normalization (standardization), min-max normalization). • Parameters for normalization (e.g., mean / variance for Z-score normalization, minimum / maximum value for min-max normalization). • Whether or not to apply a specific numerical transformation method (e.g., one-hot encoding, label encoding, etc.). • Selection rules for whether or not to use the data as training data.

[0212] For example, Z-score normalization (x) is performed as a preprocessing step for input information x. ｎｅｗ Normalized input information x = (x - μ) / σ, where μ is the mean of x and σ is the standard deviation. ｎｅｗ You can also input this into the AI ​​model, and the output y from the AI ​​model will be... ｏｕｔ The final output y may be obtained by applying post-processing to the result.

[0213] The parameter information of the above AI model may include information on at least one of the following: • Weight information in the AI ​​model (e.g., neuron coefficients (connection coefficients)); • Structure of the AI ​​model; • Type of AI model as a model component (e.g., Residual Network (ResNet), DenseNet, RefineNet, Transformer model, CRBlock, Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU)); • Function of the AI ​​model as a model component (e.g., decoder, encoder).

[0214] The weight information in the above AI model may include information on at least one of the following: • The bit width (size) of the weight information. • The quantization interval of the weight information. • The granularity of the weight information. • The range of possible weight information. • The weight parameters in the AI ​​model. • Information on the difference from the AI ​​model before the update (if updated). • The method of weight initialization (e.g., zero initialization, random initialization (based on normal distribution / uniform distribution / truncated normal distribution), Xavier initialization (for sigmoid function), He initialization (for Rectified Linear Units (ReLU))).

[0215] Furthermore, the structure of the AI ​​model described above may include information on at least one of the following: • Number of layers; • Layer types (e.g., convolutional layer, activation layer, dense layer, normalization layer, pooling layer, attention layer); • Layer information; • Time-series specific parameters (e.g., bidirectionality, time step); • Training parameters (e.g., type of function (L2 regularization, dropout function, etc.), where to place this function (e.g., after which layer)).

[0216] The above layer information may include information on at least one of the following: • Number of neurons in each layer. • Kernel size. • Stride for pooling / convolutional layers. • Pooling method (e.g., MaxPooling, AveragePooling). • Residual block information. • Number of heads. • Normalization method (e.g., batch normalization, instance normalization, layer normalization). • Activation function (sigmoid, tanh function, ReLU, leaky ReLU information, Maxout, Softmax).

[0217] One AI model may be included as a component of another AI model. For example, one AI model may be one in which processing proceeds in the following order: Model component #1 is ResNet, Model component #2 is a transformer model, a dense layer, and a normalization layer.

[0218] The training information for the above AI model may include information on at least one of the following: • Information on the optimization algorithm (e.g., type of optimization (Stochastic Gradient Descent (SGD)), AdaGrad, Adam, etc.), optimization parameters (learning rate, momentum information, etc.). • Information on the loss function (e.g., information on metrics of the loss function (Mean Absolute Error (MAE), Mean Square Error (MSE), cross-entropy loss, NLLLoss, Kullback-Leibler (KL) divergence, etc.)). • Parameters to be frozen for training (e.g., layers, weights). • Parameters to be updated (e.g., layers, weights). • Parameters that should be initial parameters for training (to be used as initial parameters) (e.g., layers, weights). • How to train / update the AI ​​model (e.g., (recommended) number of epochs, batch size, number of data points to use for training).

[0219] The inference information for the above AI model may include information regarding decision tree branch pruning, parameter quantization, and the functionality of the AI ​​model. Here, the functionality of the AI ​​model may be at least one of the following: time-domain beam prediction, spatial-domain beam prediction, autoencoder for CSI feedback, autoencoder for beam management, etc.

[0220] Autoencoders for CSI feedback may be used as follows: • The UE inputs the CSI / channel matrix / precoding matrix to the encoder's AI model and sends the encoded bits output as CSI feedback (CSI report). • The BS inputs the received encoded bits to the decoder's AI model and reconstructs the CSI / channel matrix / precoding matrix output.

[0221] In spatial domain beam prediction, UE / BS may input measurement results (beam quality, e.g., RSRP) based on a sparse (or wide) beam into an AI model and output a dense (or narrow) beam quality.

[0222] In time-domain beam forecasting, UE / BS may input time-series (past, present, etc.) measurement results (beam quality, e.g., RSRP) into an AI model to output future beam quality.

[0223] The performance information relating to the above AI model may include information regarding the expected value of the loss function defined for the AI ​​model.

[0224] The AI ​​model information in this disclosure may include information regarding the scope of application (applicability) of the AI ​​model. This scope may be indicated by a physical cell ID, a serving cell index, or the like. Information regarding the scope may be included in the environmental information described above.

[0225] AI model information relating to a specific AI model may be predetermined in the standard, or it may be notified to the UE from the Network (NW). An AI model defined in the standard may be called a reference AI model. AI model information relating to a reference AI model may be called reference AI model information.

[0226] Furthermore, the AI ​​model information in this disclosure may include an index for identifying the AI ​​model (which may be called, for example, an AI model index, an AI model ID, or a model ID). The AI ​​model information in this disclosure may include, in addition to or instead of, the AI ​​model index, in addition to the AI ​​model input / output information described above. The association between the AI ​​model index and the AI ​​model information (for example, the AI ​​model input / output information) may be predetermined in the standard or notified from the network to the user architecture.

[0227] The AI ​​model information in this disclosure may be associated with an AI model and may be referred to as relevant information, or simply relevant information. The relevant information does not necessarily have to explicitly include information for identifying an AI model. For example, the relevant information may only include metadata.

[0228] In this disclosure, ML model file information may be at least one of the following: the format / size / encoding of the ML model file, the runtime context (e.g., runtime environment / library), and the required computational resources.

[0229] <<Notification of Information to the UE>> In the embodiments described above, notification of any information from the Network (NW) (e.g., Base Station (BS)) to the UE (in other words, reception of any information from the BS at the UE) may be performed using physical layer signaling (e.g., DCI), higher layer signaling (e.g., RRC signaling, MAC CE), specific signals / channels (e.g., PDCCH, PDSCH, reference signal), or a combination thereof.

[0230] If the above notification is made by a MAC CE, the MAC CE may be identified by the inclusion of a new Logical Channel ID (LCID) not defined in existing standards in the MAC subheader.

[0231] If the above notification is made by DCI, the notification may be made by a specific field of the DCI, a Radio Network Temporary Identifier (RNTI) used to scramble the Cyclic Redundancy Check (CRC) bits assigned to the DCI, or the format of the DCI.

[0232] Furthermore, the notification of arbitrary information to the UE in the above-described embodiment may be periodic, semi-persistent, or aperiodic.

[0233] <<Notification of Information from UE>> Notification of any information from the UE to the NW in the embodiments described above (in other words, transmission / reporting of any information from the UE to the BS) may be performed using physical layer signaling (e.g., UCI), higher layer signaling (e.g., RRC signaling, MAC CE), specific signals / channels (e.g., PUCCH, PUSCH, PRACH, reference signals), or a combination thereof.

[0234] If the above notification is made by a MAC CE, the MAC CE may be identified by the inclusion of a new LCID not specified in existing standards in the MAC subheader.

[0235] If the above notice is made by the UCI, the notice may be transmitted using PUCCH or PUSCH.

[0236] Furthermore, the notification of any information from the UE in the above-described embodiment may be periodic, semi-persistent, or aperiodic.

[0237] <<Regarding the Application of Each Embodiment>> In UE / BS, specific (one or more) processes / operations / controls / assumptions / information for at least one of the embodiments described above may be applied (or used) if any or more of the following conditions are met: - A higher-layer parameter indicating the specific process / operation / control / assumption / information is set. - The specific process / operation / control / assumption / information is determined based on the relevant higher-layer parameter. - The specific process / operation / control / assumption / information is designated / activated / triggered by MAC CE / DCI / UCI / Resource / Channel / RS. - A specific UE capability indicating (or related to) the specific process / operation / control / assumption / information is reported or supported. - The application of the specific process / operation / control / assumption / information is determined based on specific conditions.

[0238] The specific UE capabilities described above may indicate, for example, at least one of the following: which specification models are supported, and which models are updated by dataset / parameter swapping.

[0239] Furthermore, the above-mentioned specific UE capability may be a capability that applies across all frequencies (commonly regardless of frequency), a capability per frequency (e.g., one or a combination thereof, such as cell, band, band combination, BWP, component carrier, etc.), a capability per frequency range (e.g., Frequency Range 1 (FR1), FR2, FR3, FR4, FR5, FR2-1, FR2-2), a capability per subcarrier spacing (SCS), or a capability per feature set (FS) or feature set per component-carrier (FSPC).

[0240] Furthermore, the specific UE capabilities described above may be capabilities that apply across all duplexing schemes (common to all duplexing schemes regardless of the duplexing scheme), or they may be capabilities specific to each duplexing scheme (e.g., Time Division Duplex (TDD), Frequency Division Duplex (FDD)).

[0241] If the above conditions are not met, UE / BS may follow the behavior specified in existing 3GPP releases.

[0242] (Note) The following invention is added with respect to one embodiment of the present disclosure. [Note 1] A terminal having a receiving unit that receives a dataset or model parameters, and a control unit that uses the dataset or model parameters to derive a specified model and uses the derived model to generate channel state information feedback.

[0243] (Wireless Communication System) The configuration of a wireless communication system according to one embodiment of this disclosure will be described below. In this wireless communication system, communication is performed using any of the wireless communication methods according to the above embodiments of this disclosure, or a combination thereof.

[0244] Figure 17 shows an example of a schematic configuration of a wireless communication system according to one embodiment. The wireless communication system 1 (which may also be simply called system 1) may be a system that realizes communication using Long Term Evolution (LTE), 5th generation mobile communication system New Radio (5G NR), etc., as specified by the Third Generation Partnership Project (3GPP).

[0245] Furthermore, the wireless communication system 1 may support dual connectivity between multiple Radio Access Technologies (RATs) (Multi-RAT Dual Connectivity (MR-DC)). MR-DC may include dual connectivity between LTE (Evolved Universal Terrestrial Radio Access (E-UTRA)) and NR (E-UTRA-NR Dual Connectivity (EN-DC)), dual connectivity between NR and LTE (NR-E-UTRA Dual Connectivity (NE-DC)), and the like.

[0246] In EN-DC, the LTE (E-UTRA) base station (eNB) is the Master Node (MN), and the NR base station (gNB) is the Secondary Node (SN). In NE-DC, the NR base station (gNB) is the MN, and the LTE (E-UTRA) base station (eNB) is the SN.

[0247] The wireless communication system 1 may support dual connectivity between multiple base stations within the same RAT (for example, dual connectivity where both MN and SN are NR base stations (gNB) (NR-NR Dual Connectivity (NN-DC))).

[0248] The wireless communication system 1 may include a base station 11 that forms a macrocell C1 with relatively wide coverage, and base stations 12 (12a-12c) located within the macrocell C1 that form a small cell C2 that is narrower than the macrocell C1. User terminals 20 may be located within at least one cell. The arrangement, number, shape, size, etc., of each cell and user terminal 20 are not limited to the configuration shown in the figure. Hereinafter, when base stations 11 and 12 are not distinguished, they will be collectively referred to as base station 10.

[0249] The wireless communication system 1 may utilize Multi Input Multi Output (MIMO). For example, one cell may be formed by one antenna / base station 10, or by multiple antennas / base stations 10. One [virtual] cell (which may be called a supercell, for example) may be composed of multiple [virtual] cells (which may be called subcells, for example). A supercell may correspond to a cell with a fixed physical range, and a subcell may correspond to a cell whose physical range fluctuates quasi-statically / dynamically. In this case, the wireless communication system 1 may be called a cell-free system.

[0250] The user terminal 20 may be connected to at least one of the multiple base stations 10. The user terminal 20 may utilize at least one of Carrier Aggregation (CA) using multiple Component Carriers (CC) and Dual Connectivity (DC).

[0251] Each CC may be included in at least one of the first frequency band (Frequency Range 1 (FR1)) and the second frequency band (Frequency Range 2 (FR2)). A macrocell C1 may be included in FR1, and a small cell C2 may be included in FR2. For example, FR1 may be a frequency band of 6 GHz or less (sub-6 GHz), and FR2 may be a frequency band above 24 GHz. Note that the frequency bands and definitions of FR1 and FR2 are not limited to these, and for example, FR1 may be in a frequency band higher than FR2.

[0252] Furthermore, the user terminal 20 may communicate in each CC using at least one of Time Division Duplex (TDD) and Frequency Division Duplex (FDD).

[0253] Multiple base stations 10 may be connected by wire (e.g., optical fiber compliant with Common Public Radio Interface (CPRI), X2 / Xn interface, etc.) or wireless (e.g., NR communication). For example, when NR communication is used as a backhaul between base stations 11 and 12, base station 11, which is the upstream station, may be called an Integrated Access Backhaul (IAB) donor, and base station 12, which is the relay station, may be called an IAB node.

[0254] Base station 10 may be connected to the core network 30 via other base stations 10 or directly. The core network 30 may include at least one of the following: Evolved Packet Core (EPC), 5G Core Network (5GCN), Next Generation Core (NGC), etc.

[0255] The core network 30 may include network functions (NF) such as User Plane Function (UPF), Access and Mobility Management Function (AMF), Session Management Function (SMF), Unified Data Management (UDM), Application Function (AF), Data Network (DN), Location Management Function (LMF), and Operation, Administration and Maintenance (Management) (OAM). Multiple functions may be provided by a single network node. Furthermore, communication with an external network (e.g., the Internet) may occur via the DN.

[0256] The user terminal 20 may be a terminal that supports at least one of the following communication methods: LTE, LTE-A, 5G, etc.

[0257] In the wireless communication system 1, an orthogonal frequency division multiplexing (OFDM)-based wireless access scheme may be used. For example, Cyclic Prefix OFDM (CP-OFDM), Discrete Fourier Transform Spread OFDM (DFT-s-OFDM), Orthogonal Frequency Division Multiple Access (OFDMA), Single Carrier Frequency Division Multiple Access (SC-OFDM), etc., may be used in at least one of the downlink (DL) and uplink (UL).

[0258] The wireless access method may also be called a waveform. In wireless communication system 1, other wireless access methods (for example, other single-carrier transmission methods, other multi-carrier transmission methods) may be used for the UL and DL wireless access methods.

[0259] In the wireless communication system 1, a Physical Downlink Shared Channel (PDSCH), a Broadcast Channel (PBCH), or a Physical Downlink Control Channel (PDCCH) may be used as the downlink channel, which is shared by each user terminal 20.

[0260] Furthermore, in the wireless communication system 1, the uplink channel may include a Physical Uplink Shared Channel (PUSCH), a Physical Uplink Control Channel (PUCCH), a Physical Random Access Channel (PRACH), or the like, all of which are shared by each user terminal 20.

[0261] User data, higher-layer control information, and System Information Blocks (SIBs) are transmitted via PDSCH. User data and higher-layer control information may also be transmitted via PUSCH. Furthermore, Master Information Blocks (MIBs) may be transmitted via PBCH.

[0262] Lower-layer control information may be transmitted by PDCCH. The lower-layer control information may include, for example, Downlink Control Information (DCI) which includes scheduling information for at least one of PDSCH and PUSCH.

[0263] Furthermore, the DCI that schedules PDSCH may be called DL assignment, DL DCI, etc., and the DCI that schedules PUSCH may be called UL grant, UL DCI, etc. Furthermore, PDSCH may be read as DL data, and PUSCH may be read as UL data.

[0264] PDCCH detection may utilize a Control Resource Set (CORESET) and a search space. A CORESET corresponds to the resources used to search for DCIs. A search space corresponds to the search area and search method for PDCCH candidates. A single CORESET may be associated with one or more search spaces. A UE may monitor CORESETs associated with a given search space based on the search space configuration.

[0265] A single search space may correspond to one or more PDCCH candidates corresponding to aggregation levels. One or more search spaces may be referred to as a search space set. In this disclosure, "search space," "search space set," "search space configuration," "search space set configuration," "CORESET," and "CORESET configuration" may be interpreted interchangeably.

[0266] PUCCH may transmit uplink control information (UCI) including at least one of channel state information (CSI), delivery acknowledgment information (for example, Hybrid Automatic Repeat reQuest ACKnowledgement (HARQ-ACK), ACK / NACK, etc.), and scheduling request (SR). PRACH may transmit a random access preamble for establishing a connection with the cell.

[0267] In this disclosure, downlinks, uplinks, etc., may be expressed without the prefix "link." Also, the prefix "physical" may be omitted from the names of various channels.

[0268] In the wireless communication system 1, a synchronization signal (SS), a downlink reference signal (DL-RS), etc., may be transmitted. In the wireless communication system 1, the DL-RS may include a cell-specific reference signal (CRS), a channel state information reference signal (CSI-RS), a demodulation reference signal (DMRS), a positioning reference signal (PRS), a phase tracking reference signal (PTRS), etc.

[0269] The synchronization signal may be, for example, at least one of a Primary Synchronization Signal (PSS) and a Secondary Synchronization Signal (SSS). A signal block including SS (PSS, SSS) and PBCH (and DMRS for PBCH) may be called an SS / PBCH block, SS Block (SSB), etc. Note that SS, SSB, etc. may also be called reference signals.

[0270] Furthermore, in the wireless communication system 1, the uplink reference signal (UL-RS) may include a sounding reference signal (SRS), a demodulation reference signal (DMRS), etc. The DMRS may also be called a user-specific reference signal (UE-specific Reference Signal).

[0271] (Base Station) Figure 18 shows an example of the configuration of a base station according to one embodiment. The base station 10 includes a control unit 110, a transmitting / receiving unit 120, a transmitting / receiving antenna 130, and a transmission line interface 140. Note that one or more of the control unit 110, the transmitting / receiving unit 120, the transmitting / receiving antenna 130, and the transmission line interface 140 may be provided.

[0272] In this example, the functional blocks of the characteristic parts of this embodiment are mainly shown, and it may be assumed that the base station 10 also has other functional blocks necessary for wireless communication. Some of the processing of each part described below may be omitted.

[0273] The control unit 110 controls the entire base station 10. The control unit 110 can be composed of a controller, control circuit, etc., as described based on common understanding in the technical field related to this disclosure.

[0274] The control unit 110 may control signal generation, scheduling (e.g., resource allocation, mapping), etc. The control unit 110 may also control transmission and reception, measurement, etc., using the transmitting / receiving unit 120, transmitting / receiving antenna 130, and transmission path interface 140. The control unit 110 may generate data to be transmitted as signals, control information, sequences, etc., and transfer them to the transmitting / receiving unit 120. The control unit 110 may also perform call processing of communication channels (setting, releasing, etc.), status management of the base station 10, management of wireless resources, etc.

[0275] The transmitting / receiving unit 120 may include a baseband unit 121, a radio frequency (RF) unit 122, and a measurement unit 123. The baseband unit 121 may include a transmission processing unit 1211 and a reception processing unit 1212. The transmitting / receiving unit 120 can be composed of a transmitter / receiver, RF circuit, baseband circuit, filter, phase shifter, measurement circuit, transmitting / receiving circuit, etc., as described based on common understanding in the art relating to this disclosure.

[0276] The transmitting / receiving unit 120 may be configured as an integrated transmitting / receiving unit, or it may be composed of a transmitting unit and a receiving unit. The transmitting unit may consist of a transmitting processing unit 1211 and an RF unit 122. The receiving unit may consist of a receiving processing unit 1212, an RF unit 122 and a measuring unit 123.

[0277] The transmitting and receiving antenna 130 can be composed of an antenna described based on common understanding in the art relating to this disclosure, such as an array antenna.

[0278] The transmitting / receiving unit 120 may transmit the downlink channel, synchronization signal, downlink reference signal, etc. The transmitting / receiving unit 120 may also receive the uplink channel, uplink reference signal, etc.

[0279] The transmitting / receiving unit 120 may use digital beamforming (e.g., precoding), analog beamforming (e.g., phase rotation), or the like to form at least one of the transmitting beam and the receiving beam.

[0280] The transmitting / receiving unit 120 (transmission processing unit 1211) may perform processing on data and control information acquired from the control unit 110, for example, at the Packet Data Convergence Protocol (PDCP) layer, the Radio Link Control (RLC) layer (e.g., RLC retransmission control), and the Medium Access Control (MAC) layer (e.g., HARQ retransmission control), to generate a bit sequence to be transmitted.

[0281] The transmitting / receiving unit 120 (transmission processing unit 1211) may perform transmission processing on the bit sequence to be transmitted, such as channel coding (which may include error correction coding), modulation, mapping, filtering, discrete Fourier transform (DFT) processing (if necessary), inverse fast Fourier transform (IFFT) processing, precoding, and digital-to-analog conversion, and output a baseband signal.

[0282] The transmitting / receiving unit 120 (RF unit 122) may perform modulation, filtering, amplification, etc., of the baseband signal to the radio frequency band and transmit the signal in the radio frequency band via the transmitting / receiving antenna 130.

[0283] On the other hand, the transmitting / receiving unit 120 (RF unit 122) may perform amplification, filtering, demodulation to a baseband signal, etc., on the radio frequency band signal received by the transmitting / receiving antenna 130.

[0284] The transmitting / receiving unit 120 (receiving processing unit 1212) may apply reception processing such as analog-to-digital conversion, Fast Fourier Transform (FFT) processing, Inverse Discrete Fourier Transform (IDFT) processing (if necessary), filtering, demapping, demodulation, decoding (may include error correction decoding), MAC layer processing, RLC layer processing, and PDCP layer processing to the acquired baseband signal to acquire user data, etc.

[0285] The transmitting / receiving unit 120 (measurement unit 123) may perform measurements related to the received signal. For example, the measurement unit 123 may perform Radio Resource Management (RRM) measurements, Channel State Information (CSI) measurements, etc., based on the received signal. The measurement unit 123 may also measure received power (e.g., Reference Signal Received Power (RSRP)), reception quality (e.g., Reference Signal Received Quality (RSRQ), Signal to Interference plus Noise Ratio (SINR), Signal to Noise Ratio (SNR)), signal strength (e.g., Received Signal Strength Indicator (RSSI)), propagation path information (e.g., CSI), etc. The measurement results may be output to the control unit 110.

[0286] The transmission path interface 140 may send and receive signals (backhaul signaling) with devices included in the core network 30 (e.g., network nodes that provide NF), other base stations 10, etc., and may acquire and transmit user data (user plane data), control plane data, etc. for the user terminal 20.

[0287] In this disclosure, the transmitting and receiving units of the base station 10 may consist of at least one of a transmitting / receiving unit 120, a transmitting / receiving antenna 130, and a transmission path interface 140.

[0288] The base station 10 may be separated into three elements: a Radio Unit (RU), a Distributed Unit (DU), and a Central Unit (CU). For example, the RU may implement RF processing (digital beamforming, digital-to-analog conversion, analog beamforming, etc.) and lower-level physical layer functions (precoding, IFFT, FFT, etc.). The DU may implement higher-level physical layer functions (coding to resource element mapping, etc.), MAC layer functions, and RLC layer functions. The CU may implement PDCP layer, Service Data Adaptation Protocol (SDAP) layer, and RRC layer functions.

[0289] In this disclosure, base station 10 may include a single device that implements all the functions of RU, DU, and CU, or it may include multiple devices that each implement some of the functions of RU, DU, and CU and are connected to each other. In this disclosure, base station 10 may be interpreted as RU / DU / CU.

[0290] The transmitting / receiving unit 120 may transmit a dataset or model parameters. The control unit 110 may use the dataset or model parameters to derive a model to be specified, and use the derived model to generate channel state information feedback.

[0291] (User Terminal) Figure 19 shows an example of the configuration of a user terminal according to one embodiment. The user terminal 20 includes a control unit 210, a transmitting / receiving unit 220, and a transmitting / receiving antenna 230. Note that one or more of the control unit 210, the transmitting / receiving unit 220, and the transmitting / receiving antenna 230 may be provided.

[0292] In this example, the functional blocks of the characteristic parts of this embodiment are mainly shown, and it may be assumed that the user terminal 20 also has other functional blocks necessary for wireless communication. Some of the processing of each part described below may be omitted.

[0293] The control unit 210 controls the entire user terminal 20. The control unit 210 can be composed of a controller, control circuit, etc., as described based on common understanding in the technical field related to this disclosure.

[0294] The control unit 210 may control signal generation, mapping, etc. The control unit 210 may also control transmission and reception, measurement, etc., using the transmitting / receiving unit 220 and the transmitting / receiving antenna 230. The control unit 210 may generate data to be transmitted as signals, control information, sequences, etc., and transfer them to the transmitting / receiving unit 220.

[0295] The transmitting / receiving unit 220 may include a baseband unit 221, an RF unit 222, and a measurement unit 223. The baseband unit 221 may include a transmission processing unit 2211 and a reception processing unit 2212. The transmitting / receiving unit 220 can be composed of a transmitter / receiver, RF circuit, baseband circuit, filter, phase shifter, measurement circuit, transmitting / receiving circuit, etc., as described based on common understanding in the art relating to this disclosure.

[0296] The transmitting / receiving unit 220 may be configured as an integrated transmitting / receiving unit, or it may be composed of a transmitting unit and a receiving unit. The transmitting unit may consist of a transmitting processing unit 2211 and an RF unit 222. The receiving unit may consist of a receiving processing unit 2212, an RF unit 222 and a measuring unit 223.

[0297] The transmitting and receiving antenna 230 can be composed of an antenna described based on common understanding in the art relating to this disclosure, such as an array antenna.

[0298] The transmitting / receiving unit 220 may receive the downlink channel, synchronization signal, downlink reference signal, etc. The transmitting / receiving unit 220 may also transmit the uplink channel, uplink reference signal, etc.

[0299] The transmitting / receiving unit 220 may use digital beamforming (e.g., precoding), analog beamforming (e.g., phase rotation), or the like to form at least one of the transmitting beam and the receiving beam.

[0300] The transmitting / receiving unit 220 (transmission processing unit 2211) may perform PDCP layer processing, RLC layer processing (e.g., RLC retransmission control), MAC layer processing (e.g., HARQ retransmission control), etc., on data and control information acquired from the control unit 210 to generate a bit sequence to be transmitted.

[0301] The transmitting / receiving unit 220 (transmission processing unit 2211) may perform transmission processing on the bit sequence to be transmitted, such as channel coding (which may include error correction coding), modulation, mapping, filtering, DFT processing (if necessary), IFFT processing, precoding, and digital-to-analog conversion, and output a baseband signal.

[0302] Whether or not to apply DFT processing may be based on the transform precoding settings. The transmitting / receiving unit 220 (transmission processing unit 2211) may perform DFT processing as part of the transmission process to transmit a channel (for example, PUSCH) using a DFT-s-OFDM waveform if transform precoding is enabled for that channel, or it may not perform DFT processing as part of the transmission process if transform precoding is not enabled for that channel.

[0303] The transmitting / receiving unit 220 (RF unit 222) may perform modulation, filtering, amplification, etc., of the baseband signal to the radio frequency band and transmit the signal in the radio frequency band via the transmitting / receiving antenna 230.

[0304] On the other hand, the transmitting / receiving unit 220 (RF unit 222) may perform amplification, filtering, demodulation to a baseband signal, etc., on the radio frequency band signal received by the transmitting / receiving antenna 230.

[0305] The transmitting / receiving unit 220 (receiving processing unit 2212) may apply reception processing such as analog-to-digital conversion, FFT processing, IDFT processing (if necessary), filtering, demapping, demodulation, decoding (may include error correction decoding), MAC layer processing, RLC layer processing, and PDCP layer processing to the acquired baseband signal to acquire user data, etc.

[0306] The transmitting / receiving unit 220 (measuring unit 223) may perform measurements related to the received signal. For example, the measuring unit 223 may perform RRM measurement, CSI measurement, etc., based on the received signal. The measuring unit 223 may also measure received power (e.g., RSRP), received quality (e.g., RSRQ, SINR, SNR), signal strength (e.g., RSSI), propagation path information (e.g., CSI), etc. The measurement results may be output to the control unit 210.

[0307] The measurement unit 223 may derive channel measurements for CSI calculation based on channel measurement resources. Channel measurement resources may be, for example, Non Zero Power (NZP) CSI-RS resources. The measurement unit 223 may also derive interference measurements for CSI calculation based on interference measurement resources. Interference measurement resources may be at least one of the following: NZP CSI-RS resources for interference measurement, CSI-Interference Measurement (IM) resources, etc. CSI-IM may also be called CSI-Interference Management (IM), and may be interpreted interchangeably with Zero Power (ZP) CSI-RS. In this disclosure, CSI-RS, NZP CSI-RS, ZP CSI-RS, CSI-IM, CSI-SSB, etc., may be interpreted interchangeably.

[0308] In this disclosure, the transmitting unit and receiving unit of the user terminal 20 may be composed of at least one of a transmitting / receiving unit 220 and a transmitting / receiving antenna 230.

[0309] The transmitting / receiving unit 220 may receive a dataset or model parameters. The control unit 210 may use the dataset or model parameters to derive a model to be specified, and may use the derived model to generate channel state information feedback.

[0310] (Hardware Configuration) The block diagram used in the description of the above embodiment shows functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining the above one device or the above multiple devices with software.

[0311] Here, functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission may be called a transmitting unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited.

[0312] For example, a base station, user terminal, etc. in one embodiment of the present disclosure may function as a computer that processes the wireless communication method of the present disclosure. Figure 20 is a diagram showing an example of the hardware configuration of a base station and user terminal according to one embodiment. The base station 10 and user terminal 20 described above may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0313] In this disclosure, terms such as apparatus, circuit, device, section, and unit are interchangeable. The hardware configuration of the base station 10 and the user terminal 20 may include one or more of the devices shown in the figure, or it may be configured without some of the devices.

[0314] For example, although only one processor 1001 is shown in the diagram, there may be multiple processors. Furthermore, the processing may be performed by one processor, or it may be performed by two or more processors simultaneously, sequentially, or by other means. Note that the processor 1001 may be implemented using one or more chips.

[0315] Each function in the base station 10 and the user terminal 20 is realized, for example, by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations and control communication via the communication device 1004, or control at least one of reading and writing data in the memory 1002 and storage 1003.

[0316] The processor 1001 controls the entire computer, for example, by running an operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. For example, at least a part of the control unit 110 (210) and the transmitting / receiving unit 120 (220) described above may be implemented by the processor 1001.

[0317] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the control unit 110 (210) may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented similarly.

[0318] The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically EPROM (EEPROM), Random Access Memory (RAM), or other suitable storage medium. The memory 1002 may also be called a register, cache, or main memory. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out a wireless communication method according to one embodiment of the present disclosure.

[0319] The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: a flexible disk, a floppy disk, a magneto-optical disk (e.g., a Compact Disk (Compact Disc ROM (CD-ROM)), a Digital Use Disk, a Blu-ray (registered trademark) disk), a removable disk, a hard disk drive, a smart card, a flash memory device (e.g., a card, stick, key drive), a magnetic stripe, a database, a server, or other suitable storage medium. The storage 1003 may also be called an auxiliary storage device.

[0320] The communication device 1004 is hardware (transmitting / receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include, for example, a high-frequency switch, duplexer, filter, frequency synthesizer, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the above-mentioned transmitting / receiving unit 120 (220), transmitting / receiving antenna 130 (230), etc., may be implemented by the communication device 1004. The transmitting / receiving unit 120 (220) may be implemented with physically or logically separated transmitting unit 120a (220a) and receiving unit 120b (220b).

[0321] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, light-emitting diode (LED) lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0322] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0323] Furthermore, the base station 10 and the user terminal 20 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a programmable logic device (PLD), and a field programmable gate array (FPGA), and some or all of each functional block may be implemented using such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0324] Furthermore, devices included in the core network 30 (for example, network nodes that provide NF) may also be implemented using the functional block / hardware configuration described above.

[0325] (Variations) Terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, channel, symbol and signal (signal or signaling) may be used interchangeably. Also, a signal may be a message. A reference signal may be abbreviated as RS and may be called a pilot, pilot signal, etc., depending on the applicable standard. Also, a component carrier (CC) may be called a cell, frequency carrier, carrier frequency, etc.

[0326] A wireless frame may consist of one or more periods (frames) in the time domain. Each of these periods (frames) constituting a wireless frame may be called a subframe. Furthermore, a subframe may consist of one or more slots in the time domain. A subframe may have a fixed time length (e.g., 1 ms) that is independent of numerology.

[0327] Here, the neurology may be communication parameters applied to at least one of the transmission and reception of a signal or channel. The neurology may be, for example, at least one of the following: subcarrier spacing (SCS), bandwidth, symbol length, cyclic prefix length, transmission time interval (TTI), number of symbols per TTI, radio frame configuration, specific filtering processes performed by the transceiver in the frequency domain, and specific windowing processes performed by the transceiver in the time domain.

[0328] A slot may consist of one or more symbols in the time domain (such as Orthogonal Frequency Division Multiplexing (OFDM) symbols or Single Carrier Frequency Division Multiple Access (SC-FDMA) symbols). Alternatively, a slot may be a time unit based on neurology.

[0329] A slot may include multiple minislots. Each minislot may consist of one or more symbols in the time domain. Minislots may also be called subslots. Minislots may consist of fewer symbols than a slot. A PDSCH (or PUSCH) transmitted in a time unit larger than a minislot may be called a PDSCH (PUSCH) mapping type A. A PDSCH (or PUSCH) transmitted using minislots may be called a PDSCH (PUSCH) mapping type B.

[0330] Wireless frames, subframes, slots, minislots, and symbols all represent units of time when transmitting a signal. Wireless frames, subframes, slots, minislots, and symbols may each be referred to by different names. Furthermore, the units of time such as frames, subframes, slots, minislots, and symbols in this disclosure may be interpreted as interchangeable.

[0331] For example, one subframe may be called a TTI, multiple consecutive subframes may be called a TTI, and one slot or one mini-slot may be called a TTI. In other words, at least one of a subframe and a TTI may be a subframe in existing LTE (1 ms), a period shorter than 1 ms (e.g., 1-13 symbols), or a period longer than 1 ms. Note that the unit representing a TTI may be called a slot, mini-slot, etc., instead of a subframe.

[0332] Here, TTI refers to, for example, the smallest time unit for scheduling in wireless communication. For example, in an LTE system, the base station schedules each user terminal to allocate wireless resources (such as the frequency bandwidth and transmission power available to each user terminal) in TTI units. However, the definition of TTI is not limited to this.

[0333] TTI may be a transmission time unit for channel-encoded data packets (transport blocks), code blocks, code words, etc., or it may be a processing unit for scheduling, link adaptation, etc. When a TTI is given, the actual time interval (e.g., number of symbols) in which the transport block, code block, code word, etc. are mapped may be shorter than the TTI.

[0334] Furthermore, if one slot or one mini-slot is referred to as a TTI, then one or more TTIs (i.e., one or more slots or one or more mini-slots) may constitute the minimum time unit for scheduling. In addition, the number of slots (number of mini-slots) that constitute this minimum time unit for scheduling may be controlled.

[0335] A TTI with a time length of 1 ms may be called a normal TTI, long TTI, normal subframe, long subframe, slot, etc. A TTI shorter than a normal TTI may be called a shortened TTI, short TTI, partial or fractional TTI, shortened subframe, short subframe, mini slot, sub slot, slot, etc.

[0336] Furthermore, long TTIs (e.g., normal TTIs, subframes, etc.) may be interpreted as TTIs with a time length exceeding 1 ms, and short TTIs (e.g., shortened TTIs, etc.) may be interpreted as TTIs with a TTI length less than that of a long TTI but 1 ms or more.

[0337] A Resource Block (RB) is a resource allocation unit in the time domain and frequency domain, and in the frequency domain, it may contain one or more consecutive subcarriers. The number of subcarriers in an RB may be the same regardless of the neurology, for example, 12. The number of subcarriers in an RB may be determined based on the neurology.

[0338] Furthermore, an RB may contain one or more symbols in the time domain and may have the length of one slot, one minislot, one subframe, or one TTI. One TTI, one subframe, etc., may each consist of one or more resource blocks.

[0339] One or more RBs may also be called Physical RBs (PRBs), Sub-Carrier Groups (SCGs), Resource Element Groups (REGs), PRB pairs, RB pairs, etc.

[0340] Furthermore, a resource block may consist of one or more resource elements (REs). For example, one RE may be a radio resource area comprising one subcarrier and one symbol.

[0341] A Bandwidth Part (BWP), also known as a partial bandwidth, may represent a subset of consecutive common resource blocks (RBs) for a given neurology in a given carrier. These common RBs may be identified by an index of the RBs relative to a common reference point of the carrier. The PRBs may be defined and numbered within a given BWP.

[0342] A BWP may include UL BWP (BWP for UL) and DL BWP (BWP for DL). One or more BWPs may be configured within a single carrier for a UE.

[0343] At least one of the configured BWPs may be active, and the UE does not need to assume that it will transmit or receive a predetermined signal / channel outside of the active BWP. In this disclosure, terms such as "cell" and "carrier" may be read as "BWP".

[0344] The structures of wireless frames, subframes, slots, minislots, and symbols described above are merely examples. For example, the number of subframes included in a wireless frame, the number of slots per subframe or wireless frame, the number of minislots included in a slot, the number of symbols and RBs included in a slot or minislot, the number of subcarriers included in an RB, and the number of symbols, symbol length, and cyclic prefix (CP) length within a TTI can be varied in various ways.

[0345] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information. For example, wireless resources may be indicated by a predetermined index.

[0346] The names used for parameters and other elements in this disclosure are not restrictive in any way. Furthermore, mathematical formulas and other elements using these parameters may differ from those expressly disclosed in this disclosure. Various channels (PUCCH, PDCCH, etc.) and information elements can be identified by any suitable name, and therefore, the various names assigned to these various channels and information elements are not restrictive in any way.

[0347] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0348] Furthermore, information, signals, etc., can be output from upper layers to lower layers and from lower layers to upper layers, or to at least one of the two. Information, signals, etc., may also be input and output via multiple network nodes.

[0349] Input and output information and signals may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information and signals may be overwritten, updated, or appended to. Output information and signals may be deleted. Input information and signals may be transmitted to other devices.

[0350] Any information described in this disclosure (e.g., variables, constants, parameters) may be communicated from any first device (e.g., UE / base station) to any second device (e.g., base station / UE) that indicates / specifies (or relates to) the value of such any information, even if not specifically stated in the embodiments described above.

[0351] Information notification is not limited to the embodiments described herein and may be carried out by other means. For example, information notification in this disclosure may be carried out by physical layer signaling (e.g., Downlink Control Information (DCI), Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, broadcast information (Master Information Block (MIB), System Information Block (SIB)), Medium Access Control (MAC) signaling), other signals, or a combination thereof.

[0352] Physical layer signaling may also be called Layer 1 / Layer 2 (L1 / L2) control information (L1 / L2 control signals), L1 control information (L1 control signals), etc. RRC signaling may also be called RRC messages, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc. MAC signaling may also be communicated using, for example, MAC Control Elements (CEs).

[0353] Furthermore, notification of the specified information (for example, notification that "X is the case") is not limited to explicit notification, but may also be made implicitly (for example, by not notifying the specified information or by notifying other information).

[0354] The determination may be made by a value represented by one bit (0 or 1), by a boolean value represented as true or false, or by a numerical comparison (for example, a comparison with a predetermined value).

[0355] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0356] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technology (such as coaxial cable, fiber optic cable, twisted pair, or Digital Subscriber Line (DSL)) and wireless technology (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0357] The terms “system” and “network” as used in this disclosure may be used interchangeably. “Network” may also mean the equipment included in the network (e.g., base stations).

[0358] In this disclosure, terms such as “precoding,” “precoder,” “weight (precoding weight),” “quasi-co-location (QCL),” “transmission configuration indication state (TCI state),” “spatial relation,” “spatial domain filter,” “transmit power,” “phase rotation,” “antenna port,” “layer,” “number of layers,” “rank,” “resource,” “resource set,” “beam,” “beam width,” “beam angle,” “antenna,” “antenna element,” “panel,” “UE panel,” “transmitting entity,” and “receiving entity” may be used interchangeably.

[0359] In this disclosure, "antenna port" may be interpreted interchangeably with "antenna port for any signal / channel" (e.g., a Demodulation Reference Signal (DMRS) port). In this disclosure, "resource" may be interpreted interchangeably with "resource for any signal / channel" (e.g., a reference signal resource, an SRS resource, etc.). Resources may include time / frequency / code / spatial / power resources. Furthermore, a spatial domain transmit filter may include at least one of a spatial domain transmit filter and a spatial domain receive filter.

[0360] The above group may include, for example, at least one of the following: a spatial relationship group, a code division multiplexing (CDM) group, a reference signal (RS) group, a control resource set (CORESET) group, a PUCCH group, an antenna port group (e.g., a DMRS port group), a layer group, a resource group, a beam group, an antenna group, or a panel group.

[0361] Furthermore, in this disclosure, terms such as beam, SRS Resource Indicator (SRI), CORESET, CORESET pool, PDSCH, PUSCH, Codeword (CW), Transport Block (TB), and RS may be interpreted interchangeably.

[0362] Furthermore, in this disclosure, TCI state, downlink TCI state (DL TCI state), uplink TCI state (UL TCI state), unified TCI state, common TCI state, joint TCI state, etc., may be interpreted interchangeably.

[0363] Furthermore, in this disclosure, terms such as "QCL," "QCL assumption," "QCL relationship," "QCL type information," "QCL property / properties," "specific QCL type (e.g., Type A, Type D) properties," and "specific QCL type (e.g., Type A, Type D)" may be interpreted interchangeably.

[0364] In this disclosure, terms such as index, identifier (ID), indicator, indication, and resource ID may be interpreted interchangeably. In this disclosure, terms such as sequence, list, set, group, cluster, subset may be interpreted interchangeably.

[0365] Furthermore, the spatial relationship information Identifier (ID) (TCI state ID) and spatial relationship information (TCI state) may be interpreted as mutually exclusive. "Spatial relationship information (TCI state)" may be interpreted as mutually exclusive as "a set of spatial relationship information (TCI state)," "one or more pieces of spatial relationship information," etc. TCI state and TCI may be interpreted as mutually exclusive. Spatial relationship information and spatial relationship may be interpreted as mutually exclusive.

[0366] In this disclosure, terms such as “Base Station (BS),” “wireless base station,” “fixed station,” “NodeB,” “eNB (eNodeB),” “gNB (gNodeB),” “access point,” “Transmission Point (TP),” “Reception Point (RP),” “Transmission / Reception Point (TRP),” “panel,” “cell,” “sector,” “cell group,” “carrier,” and “component carrier” may be used interchangeably. Base stations may also be referred to by terms such as macrocell, small cell, femtocell, and picocell.

[0367] A base station may house one or more (e.g., three) cells. If a base station houses multiple cells, the entire coverage area of ​​the base station may be divided into several smaller areas, each of which may also be provided with communication services by a base station subsystem (e.g., a small indoor base station (Remote Radio Head (RRH))). The terms “cell” or “sector” refer to part or all of the coverage area of ​​at least one of the base station and / or base station subsystems that provide communication services in that coverage.

[0368] In this disclosure, the transmission of information by a base station to a terminal may be interpreted as the base station instructing the terminal to perform a control / operation based on said information.

[0369] In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably.

[0370] A mobile station may also be called a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other appropriate term.

[0371] At least one of the base station and the mobile station may be called a transmitting device, a receiving device, a wireless communication device, etc. At least one of the base station and the mobile station may also be a device mounted on a moving object, the moving object itself, etc.

[0372] The term "mobile object" refers to any movable object, regardless of its speed, and naturally includes cases where the mobile object is stationary. Examples of such mobile objects include, but are not limited to, vehicles, transport vehicles, automobiles, motorcycles, bicycles, connected cars, excavators, bulldozers, wheel loaders, dump trucks, forklifts, trains, buses, handcarts, rickshaws, ships and other watercraft, airplanes, rockets, satellites, drones, multicopters, quadcopters, balloons, and items carried on them. Furthermore, such mobile objects may be autonomously driven objects operating based on operational commands.

[0373] The mobile entity may be a vehicle (e.g., a car, an airplane), an unmanned mobile entity (e.g., a drone, an autonomous vehicle), or a robot (manned or unmanned). At least one of the base station and the mobile station may be a device that does not necessarily move during communication operations. For example, at least one of the base station and the mobile station may be an Internet of Things (IoT) device such as a sensor.

[0374] Figure 21 shows an example of a vehicle according to one embodiment. The vehicle 40 includes a drive unit 41, a steering unit 42, an accelerator pedal 43, a brake pedal 44, a shift lever 45, left and right front wheels 46, left and right rear wheels 47, an axle 48, an electronic control unit 49, various sensors (including a current sensor 50, a rotation speed sensor 51, a pneumatic pressure sensor 52, a vehicle speed sensor 53, an acceleration sensor 54, an accelerator pedal sensor 55, a brake pedal sensor 56, a shift lever sensor 57, and an object detection sensor 58), an information service unit 59, and a communication module 60.

[0375] The drive unit 41 consists of, for example, at least one of an engine, a motor, or an engine-motor hybrid. The steering unit 42 includes at least a steering wheel (also called a handle) and is configured to steer at least one of the front wheels 46 and the rear wheels 47 based on the operation of the steering wheel operated by the user.

[0376] The electronic control unit 49 consists of a microprocessor 61, memory (ROM, RAM) 62, and communication ports (e.g., input / output (IO) ports) 63. Signals from various sensors 50-58 installed in the vehicle are input to the electronic control unit 49. The electronic control unit 49 may also be called an Electronic Control Unit (ECU).

[0377] Signals from various sensors 50-58 include current signals from current sensor 50 for sensing motor current, rotational speed signals of front wheels 46 / rear wheels 47 acquired by rotational speed sensor 51, air pressure signals of front wheels 46 / rear wheels 47 acquired by air pressure sensor 52, vehicle speed signals acquired by vehicle speed sensor 53, acceleration signals acquired by acceleration sensor 54, accelerator pedal depression amount signals acquired by accelerator pedal sensor 55, brake pedal depression amount signals acquired by brake pedal sensor 56, operation signals of shift lever 45 acquired by shift lever sensor 57, and detection signals acquired by object detection sensor 58 for detecting obstacles, vehicles, pedestrians, etc.

[0378] The information service unit 59 consists of various devices for providing (outputting) various types of information such as driving information, traffic information, and entertainment information, including a car navigation system, audio system, speakers, display, television, and radio, and one or more ECUs that control these devices. The information service unit 59 uses information acquired from external devices via a communication module 60 or the like to provide various types of information / services (for example, multimedia information / multimedia services) to the occupants of the vehicle 40.

[0379] The information service unit 59 may include input devices that accept input from the outside (e.g., keyboard, mouse, microphone, switch, button, sensor, touch panel, etc.) or output devices that perform output to the outside (e.g., display, speaker, LED lamp, touch panel, etc.).

[0380] The driver assistance system unit 64 consists of various devices that provide functions to prevent accidents or reduce the driver's workload, such as millimeter-wave radar, Light Detection and Ranging (LiDAR), cameras, positioning locators (e.g., Global Navigation Satellite System (GNSS)), map information (e.g., High Definition (HD) maps, Autonomous Vehicle (AV) maps), gyro systems (e.g., Inertial Measurement Unit (IMU), Inertial Navigation System (INS)), artificial intelligence (AI) chips, and AI processors, as well as one or more ECUs that control these devices. The driver assistance system unit 64 also transmits and receives various information via the communication module 60 to realize driver assistance functions or autonomous driving functions.

[0381] The communication module 60 can communicate with the microprocessor 61 and components of the vehicle 40 via the communication port 63. For example, the communication module 60 sends and receives data (information) via the communication port 63 to the drive unit 41, steering unit 42, accelerator pedal 43, brake pedal 44, shift lever 45, left and right front wheels 46, left and right rear wheels 47, axle 48, the microprocessor 61 and memory (ROM, RAM) 62 in the electronic control unit 49, and various sensors 50-58 provided in the vehicle 40.

[0382] The communication module 60 is a communication device that can be controlled by the microprocessor 61 of the electronic control unit 49 and can communicate with external devices. For example, it can send and receive various types of information to and from external devices via wireless communication. The communication module 60 may be located either inside or outside the electronic control unit 49. The external device may be, for example, the base station 10 or the user terminal 20 described above. Alternatively, the communication module 60 may be, for example, at least one of the base station 10 and the user terminal 20 (it may function as at least one of the base station 10 and the user terminal 20).

[0383] The communication module 60 may transmit at least one of the following to an external device via wireless communication: signals from the various sensors 50-58 input to the electronic control unit 49, information obtained based on said signals, and information based on input from an external source (user) obtained via the information service unit 59. The electronic control unit 49, the various sensors 50-58, the information service unit 59, etc., may also be called input units that accept input. For example, the PUSCH transmitted by the communication module 60 may include the information based on the above input.

[0384] The communication module 60 receives various information (traffic information, signal information, inter-vehicle information, etc.) transmitted from an external device and displays it on the information service unit 59 installed in the vehicle. The information service unit 59 may also be called an output unit, which outputs information (for example, it outputs information to devices such as displays and speakers based on the PDSCH (or data / information decoded from the PDSCH) received by the communication module 60).

[0385] Furthermore, the communication module 60 stores various information received from external devices in a memory 62 that can be used by the microprocessor 61. Based on the information stored in the memory 62, the microprocessor 61 may control the drive unit 41, steering unit 42, accelerator pedal 43, brake pedal 44, shift lever 45, left and right front wheels 46, left and right rear wheels 47, axle 48, various sensors 50-58, etc., which are provided in the vehicle 40.

[0386] Furthermore, the term "base station" in this disclosure may be interpreted as "user terminal." For example, the various aspects / embodiments of this disclosure may be applied to a configuration in which communication between a base station and a user terminal is replaced with communication between multiple user terminals (which may be called, for example, Device-to-Device (D2D), Vehicle-to-Everything (V2X)). In this case, the user terminal 20 may have the functions of the base station 10 described above. Also, terms such as "uplink" and "downlink" may be interpreted as terms corresponding to terminal-to-terminal communication (for example, "sidelink"). For example, uplink channel, downlink channel, etc., may be interpreted as sidelink channel.

[0387] Similarly, the term "user terminal" in this disclosure may be replaced with "base station." In this case, the base station 10 may be configured to have the same functions as the user terminal 20 described above.

[0388] In this disclosure, operations performed by a base station may, in some cases, be performed by its upper node. In a network including one or more network nodes having base stations, it is clear that various operations performed for communication with terminals may be performed by the base station, one or more network nodes other than the base station (for example, a Mobility Management Entity (MME), a Serving Gateway (S-GW), etc., but not limited to these), or a combination thereof.

[0389] Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during execution. Furthermore, the processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be rearranged in order, provided they are consistent. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented.

[0390] Each aspect / embodiment described in this disclosure is Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 6th generation mobile communication system (6G), xth generation mobile communication system (xG (where x is, for example, an integer or decimal)), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM®), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi®), IEEE 802.16 (WiMAX®), IEEE 802.20, systems utilizing Ultra-WideBand (UWB), Bluetooth®, or other appropriate wireless communication methods, and next-generation systems extended, modified, created, or defined based thereon may also be applied. Furthermore, multiple systems may be applied in combination (for example, a combination of LTE or LTE-A and 5G).

[0391] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0392] Any reference to elements using the designations “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, the references to the first and second elements do not imply that only two elements may be employed or that the first element must precede the second element in any way.

[0393] The term “determining” as used in this disclosure may encompass a wide variety of actions. For example, “determining” may be considered to mean judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in tables, databases, or other data structures), ascertaining, etc.

[0394] Furthermore, "judgment (decision)" may be considered as "judging (deciding)" things like receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory).

[0395] Furthermore, “judgment (decision)” may be considered as “judgment (decision)” of resolving, selecting, choosing, establishing, comparing, etc. In other words, “judgment (decision)” may be considered as “judgment (decision)” of some action. In this disclosure, “judgment (decision)” may be interpreted as mutually interchangeable with the actions described above.

[0396] Furthermore, in this disclosure, “determine / determining” may be interpreted as “assume / assuming,” “expect / expecting,” or “consider / considering.” In addition, in this disclosure, “not expecting to do…” may be interpreted as “expecting not to do….”

[0397] In this disclosure, "expect" may be rephrased as "be expected." For example, "expect(s) ..." (where "..." may be expressed as a that clause, an infinitive, etc.) may be rephrased as "be expected ..." or "do (the verb without "to" if "..." is an infinitive)." Similarly, "does not expect ..." may be rephrased as "be not expected ..." or "do not (the verb without "to" if "..." is an infinitive)." Furthermore, "An apparatus A is not expected ..." may be rephrased as "An apparatus B other than apparatus A does not expect ... from apparatus A" (for example, if apparatus A is a UE, apparatus B may be a base station).

[0398] The term "maximum transmit power" as used in this disclosure may mean the maximum transmit power, the nominal UE maximum transmit power, or the rated UE maximum transmit power.

[0399] As used in this disclosure, the terms “connected,” “coupled,” and any variations thereof mean any direct or indirect connection or coupling between two or more elements, and may include one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be replaced with “access.”

[0400] In this disclosure, when two elements are connected, they can be considered to be "connected" or "coupled" to each other using one or more wires, cables, printed electrical connections, etc., and, in some non-exclusive and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain.

[0401] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."

[0402] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0403] In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0404] In this disclosure, "less than or equal to," "less than," "greater than or equal to," "more than," and "equal to" may be interpreted interchangeably. In addition, in this disclosure, words meaning "good," "bad," "big," "small," "high," "low," "early," "slow," "wide," and "narrow" may be interpreted interchangeably, not limited to the positive, comparative, and superlative degrees. In addition, in this disclosure, words meaning "good," "bad," "big," "small," "high," "low," "early," "slow," "wide," and "narrow" may be interpreted interchangeably, not limited to the positive, comparative, and superlative degrees, by adding "i-th" (where i is any integer) to the expression (for example, "highest" may be interpreted interchangeably with "i-th highest").

[0405] In this disclosure, "of," "for," "regarding," "related to," and "associated with" may be interpreted as being interchangeable.

[0406] In this disclosure, phrases such as "when A, B", "if A, then B", "B upon A", "B in response to A", "B based on A", "B during / while A", "B before A", "B at (the same time as) / on A", "B after A", "B since A", and "B until A" may be interchangeable. Furthermore, A, B, etc., may be replaced with appropriate expressions such as nouns, gerunds, or regular sentences depending on the context. The time difference between A and B may be approximately zero (immediately after or immediately before). Additionally, a time offset may be applied to the time when A occurs. For example, "A" may be interpreted as "before / after the time offset when A occurs". The time offset (e.g., one or more symbols / slots) may be predetermined or determined by the UE based on notified information.

[0407] In this disclosure, timing, time, duration, time instance, any unit of time (e.g., slot, subslot, symbol, subframe), period, occasion, resource, etc., may be interpreted interchangeably.

[0408] Although the invention described herein has been explained in detail above, it will be clear to those skilled in the art that the invention described herein is not limited to the embodiments described herein. The descriptions herein are illustrative and not intended to be restrictive in any way to the invention described herein.

[0409] This application is based on Japanese Patent Application No. 2024-203738, filed on November 22, 2024. All of its contents are included here.

Claims

1. A terminal comprising: a receiving unit that receives a dataset or model parameters; and a control unit that uses the dataset or model parameters to derive a specification related to a model, and uses the derived model to generate channel state information feedback.

2. A wireless communication method for a terminal, comprising the steps of: receiving a dataset or model parameters; deriving a specified model using the dataset or model parameters; and generating channel state information feedback using the derived model.

3. A base station having a transmitting unit that transmits a dataset or model parameters, and a control unit that instructs the derivation of a specified model using the dataset or model parameters, and the generation of channel state information feedback using the derived model.

Images