Terminal, wireless communication method and base station

Abstract

A terminal according to one embodiment of the present disclosure is characterized in that it comprises: a receiving unit that receives a first setting related to a payload of channel state information (CSI) and a second setting related to CSI feedback; and a control unit that controls CSI compression based on artificial intelligence (AI) based on the first setting and the second setting. According to one embodiment of the present disclosure, appropriate CSI feedback using AI can be achieved.

Description

Technical Field

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

[0002] In the Universal Mobile Telecommunications System (UMTS) network, Long Term Evolution (LTE) is standardized for the purpose of further high-speed data rate, low latency, etc. (Non-Patent Document 1). In addition, LTE-Advanced (3GPP Rel. 10-14) is standardized for the purpose of further increasing the capacity and sophistication of LTE (Release (Rel.) 8, 9 of the Third Generation Partnership Project (3GPP (registered trademark))).

[0003] Successor systems of LTE (also called, for example, fifth generation mobile communication system (5G), 5G+(plus), sixth generation mobile communication system (6G), New Radio (NR), 3GPP Rel.15 and later, etc.) are also being studied.

[0004] Prior art literature

[0005] Non-patent literature

[0006] Non-patent document 1: 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 Summary of the invention

[0007] Problems to be solved by the invention

[0008] Regarding future wireless communication technologies, research is underway to flexibly apply artificial intelligence (AI) technologies such as machine learning (ML) in the control and management of networks / devices. For example, regarding future wireless communication technologies, research is underway to flexibly apply AI technologies to improve feedback of channel state information (Channel State Information Reference Signal (CSI)) based on terminals (user terminals, user equipment (UE)), such as reducing overhead, improving accuracy, and predicting. CSI feedback based on AI technology can also be called AI-aided CSI feedback.

[0009] However, there has been no progress in the research on the specific content of AI-assisted CSI feedback. If these are not properly regulated, it will be impossible to achieve appropriate overhead reduction / high-precision channel estimation / efficient resource utilization, and there is a concern that the improvement of communication throughput / communication quality will be suppressed.

[0010] Therefore, one of the objects of the present disclosure is to provide a terminal, a wireless communication method, and a base station that can implement appropriate CSI feedback using AI.

[0011] Means for solving problems

[0012] A terminal according to one embodiment of the present disclosure is characterized in that it comprises: a receiving unit that receives a first setting related to a payload of channel state information (CSI) and a second setting related to CSI feedback; and a control unit that controls CSI compression based on artificial intelligence (AI) based on the first setting and the second setting.

[0013] Effects of the Invention

[0014] According to one aspect of the present disclosure, appropriate CSI feedback using AI can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a diagram showing an example of a framework for managing AI models.

[0016] Figure 2 This is a diagram showing an example of specifying an AI model.

[0017] Figure 3 This is a diagram showing an example of an AI model.

[0018] Figure 4 This is a diagram showing the codebook configuration (CodebookConfig) of Rel.16.

[0019] Figure 5 An example of a 16-level quantization table is shown.

[0020] Figure 6 An example of an 8-level quantization table is shown.

[0021] Figure 7 : is a diagram showing the relationship between the number of antenna ports and the port number of the type 2 codebook.

[0022] Figure 8 It is a diagram showing each parameter corresponding to paramCombination-r16.

[0023] Fig. 9 is a diagram showing an example of AI-based CSI feedback.

[0024] Fig. 10A as well as Fig. 10B This is a diagram showing an example of input information for option 1.

[0025] Fig.11A as well as Fig. 11B This is a diagram showing an example of input information for option 2.

[0026] Fig. 12A as well as Fig. 12B This is a diagram showing an example of extraction of input information based on the DFT basis involved in Option 3.

[0027] Fig.13A as well as Fig. 13B This is a diagram showing an example of a method for determining a DFT basis.

[0028] Figures 14A-14D This is a diagram showing an example of a matrix that can serve as input information.

[0029] Fig.15A as well as Fig. 15B This is a diagram showing a first example of RRC parameters of the first embodiment.

[0030] Fig.16 This is a diagram showing a second example of the RRC parameters of the first embodiment.

[0031] Fig.17 This is a diagram showing an example of AIML parameters of the first embodiment.

[0032] Fig.18 This is a diagram showing an example of CSI feedback according to implementation mode 3-1.

[0033] Fig.19 This is a diagram showing an example of CSI feedback according to implementation mode 3-2.

[0034] Fig. 20 This is a diagram showing an example of CSI feedback according to implementation mode 3-3.

[0035] Fig.21 This is a diagram showing an example of CSI feedback according to implementation mode 3-4.

[0036] Fig. 22 It is a diagram showing an example of CSI feedback according to the fourth embodiment.

[0037] Fig.23 This is a diagram showing an example of a schematic configuration of a wireless communication system according to an embodiment.

[0038] Fig.24 This is a diagram showing an example of the configuration of a base station according to an embodiment.

[0039] Fig.25 This is a diagram showing an example of a configuration of a user terminal according to an embodiment.

[0040] Fig.26 This is a diagram showing an example of the hardware configuration of a base station and a user terminal according to an embodiment.

[0041] Fig. 27 This is a diagram showing an example of a vehicle according to an embodiment. DETAILED DESCRIPTION

[0042] (Application of Artificial Intelligence (AI) technology to wireless communications)

[0043] For example, regarding future wireless communication technologies, research is underway into the flexible use of AI technology to improve channel state information (Channel State Information Reference Signal (CSI)) feedback (e.g., overhead reduction, improved accuracy, prediction), beam management (e.g., improved accuracy, prediction in the time / spatial domain), and position measurement (e.g., improved position estimation / prediction).

[0044] Figure 1 This is a diagram showing an example of a framework for managing an AI model. In this example, each stage associated with an AI model is shown as a block. This example is also described as lifecycle management of an AI model.

[0045] The data collection phase corresponds to the phase of collecting data for the generation / update of AI models. The data collection phase may also include data organization (e.g., deciding which data to migrate for model training / model inference), data migration (e.g., migrating data to entities that perform model training / model inference (e.g., UE, gNB)), etc.

[0046] In the model training phase, model training is performed based on the data (training data) migrated from the collection phase. This phase may also include data preparation (e.g., implementation of data preprocessing, cleaning, formatting, transformation, etc.), model training / validation, model testing (e.g., confirming whether the trained model meets the performance threshold), model exchange (e.g., migration of models for distributed learning), model deployment / update (deployment / update of models for entities that perform model inference), etc.

[0047] In the Model Inference phase, model inference is performed based on the data (inference data) migrated from the Collection phase. This phase may also include data preparation (e.g., implementation of data preprocessing, cleaning, formatting, transformation, etc.), model inference, model monitoring (e.g., monitoring the performance of model inference), model performance feedback (feedback on model performance to entities performing model training), output (providing model output to actors), etc.

[0048] The actor stage can also include action triggering (e.g., deciding whether to trigger an action on other entities), feedback (e.g., feeding back training data / inference data / information required for performance feedback), etc.

[0049] In addition, for example, the training of models for mobility optimization can also be performed in the network (Network (NW)) in the operation, administration and maintenance (OAM) / gNodeB (gNB). In the former case, it is beneficial to interoperability, large-capacity storage, operator manageability, model flexibility (feature engineering, etc.). In the latter case, it is beneficial in that latency for model updates and data exchange for model decompression are not required. The reasoning of the above model can also be performed in the gNB, for example.

[0050] Furthermore, the entity doing the training / inference can also vary depending on the use case.

[0051] For example, for AI-assisted beam management based on measurement reports, OAM / gNB can also perform model training and gNB can perform model inference.

[0052] For AI-assisted UE assisted positioning (Assisted Positioning), the location management function (LMF) can also perform model training, and the LMF performs model reasoning.

[0053] For CSI feedback / channel estimation using an autoencoder, it is also possible for OAM / gNB / UE to perform model training and gNB / UE (jointly) to perform model inference.

[0054] For AI-assisted beam management based on beam measurement or AI-assisted UE-based positioning, OAM / gNB / UE can also perform model training and UE can perform model inference.

[0055] However, it is expected that data / AI models will be treated as proprietary assets. For example, since it takes a lot of money and time to create a high-precision AI model, it will be a big disadvantage if the content of the AI ​​model created by a certain company is known to other companies. Therefore, research is being conducted to make part of the information related to the AI ​​model unusable (or impossible to infer) for UE / gNB provided by different vendors.

[0056] The model approach based on identifier (ID) can be one of the management methods of AI models in such scenarios. For example, although NW / gNB does not know the details of the AI ​​model, it can know only part of the information of the AI ​​model for AI model management (for example, which ML model is used for what in the UE).

[0057] Figure 2 This is a diagram showing an example of specifying an AI model. In this example, the UE and NW (e.g., the base station (BS)) can identify model #1 and #2 (the details of the model may not be fully understood). For example, the UE can also report the performance of model #1 and the performance of model #2 to the NW, and the NW can also instruct the UE on the AI ​​model to be used.

[0058] In the present disclosure, UE / BS can also input channel state information, reference signal measurement values, etc. into the ML model, and output high-precision channel state information / measurement values / beam selection / position, future channel state information / radio link quality, etc.

[0059] In addition, in the present disclosure, AI can also be rewritten as an object (also referred to as an object, object, data, function, program, etc.) having (implementing) at least one of the following characteristics:

[0060] Estimates based on observed or collected information,

[0061] · Selection based on observed or collected information,

[0062] Predictions based on observed or collected information.

[0063] In the present disclosure, an object may also be, for example, a device, such as a terminal or a base station, etc. In addition, in the present disclosure, an object may also correspond to a program / model / entity operating in the device.

[0064] In addition, in the present disclosure, the ML model may also be rewritten as an object having (implementing) at least one of the following features:

[0065] Generate estimates by feeding information,

[0066] By providing information, forecasting estimates,

[0067] ·Discover features by providing information,

[0068] · Select an action by providing information.

[0069] In addition, in the present disclosure, AI, AI / ML, AI / ML model, ML model, model, AI model, predictive analytics, predictive analytics model, etc. can also be rewritten to each other. In addition, ML model can also be derived using at least one of regression analysis (e.g., linear regression analysis, multiple regression analysis, logistic regression analysis), support vector machine, random forest, neural network, deep learning, etc. In the present disclosure, model can also be rewritten as at least one of encoder, decoder, tool, etc.

[0070] The ML model outputs at least one piece of information such as an estimated value, a predicted value, a selected operation, a classification, etc. based on the input information.

[0071] ML models can also include supervised learning, unsupervised learning, reinforcement learning, etc. Supervised learning can also be used to learn general rules for mapping inputs to outputs. Unsupervised learning can also be used to learn the features of data. Reinforcement learning can also be used to learn operations for maximizing the goal.

[0072] In the present disclosure, generation, calculation, and export may be mutually replaced. In the present disclosure, implementation, operation, operation, and execution may be mutually replaced. In the present disclosure, training, learning, updating, and retraining may be mutually replaced. In the present disclosure, reasoning, after-training, formal utilization, and actual utilization may be mutually replaced. Signal may be mutually replaced with signal / channel.

[0073] (CSI report or reporting)

[0074] In Rel.15 NR, a terminal (also referred to as a user terminal, user equipment (UE), etc.) generates (also referred to as determining, calculating, estimating, measuring, etc.) channel state information (CSI) based on a reference signal (RS) (or resources used for the RS), and sends (also referred to as reporting, feedback, etc.) the generated CSI to a network (e.g., a base station). The CSI may be sent to a base station using, for example, an uplink control channel (e.g., a physical uplink control channel (PUCCH)) or an uplink shared channel (e.g., a physical uplink shared channel (PUSCH)).

[0075] The RS used in the generation of CSI may be, for example, at least one of a Channel State Information Reference Signal (CSI-RS), a Synchronization Signal / Broadcast Channel (SS / PBCH) block, a Synchronization Signal (SS), a demodulation reference signal (DeModulation Reference Signal (DMRS)), etc.

[0076] CSI-RS may also include at least one of Non Zero Power (NZP) CSI-RS and CSI-Interference Management (CSI-IM). SS / PBCH block is a block including SS and PBCH (and corresponding DMRS), and may also be referred to as SS block (SSB), etc. In addition, SS may also include at least one of Primary Synchronization Signal (PSS) and Secondary Synchronization Signal (SSS).

[0077] In addition, CSI may also include at least one of a channel quality indicator (Channel Quality Indicator (CQI)), a precoding matrix indicator (Precoding Matrix Indicator (PMI)), a CSI-RS resource indicator (CSI-RSResource Indicator (CRI)), a SS / PBCH block resource indicator (SS / PBCH Block Resource Indicator (SSBRI)), a layer indicator (Layer Indicator (LI)), a rank indicator (Rank Indicator (RI)), L1-RSRP (reference signal received power in layer 1 (Layer 1 Reference Signal Received Power)), L1-RSRQ (reference signal received quality (Reference Signal ReceivedQuality)), L1-SINR (signal to interference plus noise ratio (Signal to Interference plus NoiseRatio)), L1-SNR (signal to noise ratio (Signal to Noise Ratio)), etc.

[0078] The UE may also receive information related to CSI reporting (report configuration information) and control CSI reporting based on the report configuration information. The report configuration information may also be, for example, "CSI-ReportConfig" of the information element (IE) of the Radio Resource Control (RRC). In addition, in the present disclosure, the RRC IE may also be mutually rewritten with RRC parameters, high-layer parameters, etc.

[0079] The report configuration information (eg, “CSI-ReportConfig” of RRC IE) may include, for example, at least one of the following.

[0080] Information related to the type of CSI report (report type information, such as "reportConfigType" of RRC IE)

[0081] Information related to one or more quantities (quantities) of CSI to be reported (one or more CSI parameters) (report quantity information, for example, RRC IE "reportQuantity")

[0082] Information related to the RS resource used to generate the quantity (the CSI parameter) (resource information, for example, "CSI-ResourceConfigId" of RRCIE)

[0083] Information related to the frequency domain that is the subject of CSI reporting (frequency domain information, for example, "reportFreqConfiguration" of RRC IE)

[0084] For example, the reporting type information may also represent (indicate) periodic CSI (P-CSI) reporting, aperiodic CSI (A-CSI) reporting, or semi-persistent CSI (Semi-Persistent CSI (SP-CSI)) reporting.

[0085] In addition, the reporting amount information may also specify a combination of at least one of the above-mentioned CSI parameters (for example, CRI, RI, PMI, CQI, LI, L1-RSRP, etc.).

[0086] In addition, the resource information may be an ID of a resource for RS. The resource for RS may include, for example, a non-zero-power CSI-RS resource or SSB, and a CSI-IM resource (for example, a zero-power CSI-RS resource).

[0087] In addition, frequency domain information can also indicate the frequency granularity of the CSI report. The frequency granularity may also include, for example, a wideband and a subband. The wideband is the entire CSI reporting band. For example, the wideband may be the entirety of a certain carrier (component carrier (CC), cell, service cell), or the entirety of the bandwidth part (Bandwidth part (BWP)) within a certain carrier. The wideband may also be renamed as the CSI reporting band, the entire CSI reporting band, etc.

[0088] In addition, a subband is a part of a wideband and may be composed of one or more resource blocks (Resource Block (RB) or Physical Resource Block (PRB)). The size of a subband may also be determined by the size of a BWP (the number of PRBs).

[0089] The frequency domain information may also indicate which wideband or subband PMI is reported (the frequency domain information may also include, for example, the "pmi-FormatIndicator" of the RRC IE used to determine whether to report wideband PMI or subband PMI). The UE may also determine the frequency granularity of the CSI report (i.e., whether to report wideband PMI or subband PMI) based on at least one of the above-mentioned reporting amount information and the frequency domain information.

[0090] When wideband PMI reporting is configured (determined), one wideband PMI may be reported for the entire CSI reporting band. On the other hand, when subband PMI reporting is configured, a single wideband indication i1 may be reported for the entire CSI reporting band, and one subband indication i2 (e.g., a subband indication for each subband) may be reported for each of one or more subbands within the entire CSI report.

[0091] The UE performs channel estimation using the received RS and estimates a channel matrix H. The UE feeds back an index (PMI) determined based on the estimated channel matrix.

[0092] The PMI may also represent a precoder matrix (also referred to as a precoder for short) that the UE considers suitable for downlink (downlink (DL)) transmission to the UE. Each value of the PMI may also correspond to a precoder matrix. The set of PMI values ​​may also correspond to a set of different precoder matrices called a precoder codebook (also referred to as a codebook for short).

[0093] In the space domain, the CSI report may also include more than one type of CSI. For example, the CSI may also include at least one of a first type (type 1 CSI) for single beam selection and a second type (type 2 CSI) for multi-beam selection. A single beam may also be referred to as a single layer, and multi-beams may also be referred to as multiple beams. In addition, type 1 CSI may not assume multi-user multiple input multiple output (MIMO), and type 2 CSI may assume multi-user MIMO.

[0094] The above codebook may also include a codebook for type 1 CSI (also referred to as type 1 codebook, etc.) and a codebook for type 2 CSI (also referred to as type 2 codebook, etc.). In addition, type 1 CSI may also include type 1 single-panel CSI and type 1 multi-panel CSI, and different codebooks (type 1 single-panel codebook, type 1 multi-panel codebook) may be specified for each.

[0095] In the present disclosure, type 1 and type I may be replaced by each other. In the present disclosure, type 2 and type II may be replaced by each other.

[0096] The uplink control information (UCI) type may also include at least one of a hybrid automatic repeat request acknowledgment (HARQ-ACK), a scheduling request (SR), and CSI. UCI may be carried by either PUCCH or PUSCH.

[0097] In Rel.15 NR, UCI can include a CSI part for wideband PMI feedback. CSI report #n contains PMI wideband information when reported.

[0098] In Rel.15 NR, UCI can include two CSI parts for subband PMI feedback. CSI part 1 includes wideband PMI information. CSI part 2 includes one wideband PMI information and several subband PMI information. CSI part 1 and CSI part 2 are coded separately.

[0099] (AI model information)

[0100] In the present disclosure, AI model information may also mean information including at least one of the following:

[0101] AI model input / output information,

[0102] Information for pre-processing / post-processing of AI model input / output,

[0103] Information about the parameters of the AI ​​model,

[0104] Training information for AI models (training information),

[0105] Reasoning information for AI models,

[0106] Performance information related to the AI ​​model.

[0107] Here, the input / output information of the above AI model may also include information related to at least one of the following:

[0108] Content of input / output data (e.g., RSRP, SINR, amplitude / phase information in the channel matrix (or precoding matrix), information related to the angle of arrival (AoA), information related to the angle of departure (AoD), location information),

[0109] Auxiliary information of the data (also called meta information),

[0110] The type of input / output data (e.g., immutable value, floating point number),

[0111] Quantization interval (step size) of input / output data (e.g. 1 dBm for L1-RSRP),

[0112] The range that the input / output data can take (e.g., [0, 1]).

[0113] In addition, in the present disclosure, information related to AoA may also include information related to at least one of an azimuth angle of arrival and a zenith angle of arrival (ZoA). In addition, information related to AoD may also include information related to at least one of an azimuth angle of departure and a zenith angle of departure (ZoD).

[0114] In the present disclosure, location information may also be location information related to UE / NW. Location information may also include information (e.g., latitude, longitude, altitude) obtained using a positioning system (e.g., a satellite positioning system (Global Navigation Satellite System (GNSS)), a Global Positioning System (GPS), etc.)), information of a base station adjacent to (or in service of) the UE (e.g., an identifier (ID) of a base station / cell, the distance between BS and UE, the direction / angle of the BS (UE) observed from the UE (BS), the coordinates of the BS (UE) observed from the UE (BS) (e.g., coordinates of the X / Y / Z axes), etc.), a specific address of the UE (e.g., an Internet Protocol (IP) address), etc. At least one of the above. The location information of the UE is not limited to information based on the location of the BS, but may also be information based on a specific point.

[0115] The location information may also include information related to its own implementation (eg, the location / position / orientation of the antenna, the location / orientation of the antenna panel, the number of antennas, the number of antenna panels, etc.).

[0116] The location information may also include mobility information. The mobility information may also include information indicating a mobility type, information indicating at least one of a moving speed of the UE, an acceleration of the UE, and a moving direction of the UE.

[0117] Here, the mobility type may also correspond to at least one of a fixed location UE, a movable / moving UE, a no mobility UE, a low mobility UE, a middle mobility UE, a high mobility UE, a cell-edge UE, a non-cell-edge UE, etc.

[0118] In the present disclosure, environmental information (used for data) may also be information related to the environment in which the data is obtained / utilized, and may include, for example, frequency information (band ID, etc.), environment type information (indicating at least one of indoor, outdoor, Urban Macro (UMa), Urban Micro (Urban Micro (Umi)), etc.).

[0119] In the present disclosure, meta information may also mean, for example, information related to input / output information suitable for an AI model, information related to acquired / capable data, etc. Specifically, meta information may also include information related to beams of RS (e.g., CSI-RS / SRS / SSB, etc.) (e.g., the angle at which each beam points, 3dB beam width, the shape of the beam pointed, the number of beams), layout information of antennas of gNB / UE, frequency information, environmental information, meta information ID, etc. In addition, meta information may also be used as input / output of an AI model.

[0120] The pre-processing / post-processing information for the input / output of the above-mentioned AI model may also include information related to at least one of the following:

[0121] Whether to apply normalization (e.g., Z-score normalization, min-max normalization),

[0122] Parameters used for normalization (e.g. mean / variance for Z-score normalization, min / max for min-max normalization),

[0123] Whether to apply specific numerical transformation methods (e.g., one hot encoding, label encoding, etc.),

[0124] Whether to use it as a selection rule for training data.

[0125] For example, the input information x can also be normalized by Z score (x new = (x-μ) / σ. Here, μ is the mean of x and σ is the standard deviation) as the normalized input information x obtained by preprocessing. new Input to the AI ​​model, output y from the AI ​​model out Post-processing is applied to obtain the final output y.

[0126] The information of the parameters of the above AI model may also include information related to at least one of the following:

[0127] Information about weights in the AI ​​model (e.g., coefficients of neurons (combination coefficients)),

[0128] The structure of the AI ​​model

[0129] The types of AI models used as model components (e.g., Residual Network (ResNet), DenseNet, RefineNet, Transformer model, CRBlock, Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU)),

[0130] The functionality of the AI ​​model as a model component (e.g., decoder, encoder).

[0131] In addition, the weight information in the above AI model may also include information related to at least one of the following:

[0132] The bit width (size) of the weight information,

[0133] ·Quantization interval of weight information,

[0134] The granularity of the weight information,

[0135] The range of weight information that can be taken,

[0136] ·The weight parameters in the AI ​​model,

[0137] Information on the difference between the AI ​​model before the update (when updating),

[0138] Weight initialization methods (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))).

[0139] In addition, the structure of the above AI model may also include information related to at least one of the following:

[0140] Number of layers,

[0141] The type of layer (e.g., convolutional layer, activation layer, dense layer, normalization layer, pooling layer, attention layer),

[0142] Layer information,

[0143] Time series-specific parameters (e.g., bidirectionality, time step),

[0144] Parameters used for training (e.g., type of function (L2 regularization, dropout function, etc.), where (e.g., after which layer) to set the function).

[0145] The above layer information may also include information related to at least one of the following:

[0146] The number of neurons in each layer,

[0147] kernel size,

[0148] Stride used for pooling / convolutional layers,

[0149] Pooling methods (MaxPooling, AveragePooling, etc.),

[0150] Information of residual blocks,

[0151] Number of heads,

[0152] Normalization methods (batch normalization, instance normalization, layer normalization, etc.),

[0153] Activation functions (sigmoid, tanh, ReLU, leaky ReLU, Maxout, Softmax).

[0154] Figure 3 This is a diagram showing an example of an AI model. This example shows an AI model that includes ResNet as model component #1, a Transformer model as model component #2, a dense layer, and a normalization layer. In this way, an AI model can also be included as a component of another AI model. In addition, Figure 3 It can also be an AI model that processes from left to right.

[0155] The training information for the AI ​​model may also include information related to at least one of the following:

[0156] Information used for the optimization algorithm (e.g., the type of optimization (Stochastic Gradient Descent (SGD)), AdaGrad, Adam, etc.), the parameters optimized (learning rate, momentum information, etc.),

[0157] Information about the loss function (e.g., information about the metrics of the loss function (Mean Absolute Error (MAE)), Mean Square Error (MSE), Cross-Entropy Loss, NLLLoss (Negative Log Likelihood Loss), Kullback-Leibler (KL) divergence, etc.)),

[0158] Parameters that should be frozen for training (e.g., layers, weights),

[0159] the parameters that should be updated (e.g., layers, weights),

[0160] Parameters (e.g., layers, weights) that should be used as initial parameters for training,

[0161] The training / updating method of the AI ​​model (e.g., (recommended) number of epochs, batch size, amount of data used in training).

[0162] The above-mentioned reasoning information for the AI ​​model may also include information related to decision tree branch pruning, parameter quantization, AI model functions, etc. Here, the AI ​​model function may also correspond to at least one of time domain beam prediction, space domain beam prediction, CSI feedback-oriented autoencoder, beam management-oriented autoencoder, etc.

[0163] The autoencoder for CSI feedback can also be used as follows:

[0164] UE inputs CSI / channel matrix / precoding matrix into the AI ​​model of the encoder and outputs the encoded bits as CSI feedback (CSI report).

[0165] The BS reconstructs the CSI / channel matrix / precoding matrix output by inputting the received coded bits to the decoder's AI model.

[0166] In spatial domain beam prediction, the UE / BS can also input the measurement results (beam quality, for example, RSRP) based on sparse (or coarse) beams into the AI ​​model and output dense (or fine) beam quality.

[0167] In time domain beam prediction, UE / BS can also input time series (past, current, etc.) measurement results (beam quality, for example, RSRP) into the AI ​​model and output future beam quality.

[0168] The above-mentioned performance information related to the AI ​​model may also include information related to the expected value of the loss function defined for the AI ​​model.

[0169] The AI ​​model information in the present disclosure may also include information related to the application scope (applicable scope) of the AI ​​model. The application scope may also be represented by a physical cell ID, a serving cell index, etc. Information related to the application scope may also be included in the above-mentioned environmental information.

[0170] The AI ​​model information related to a specific AI model can be predetermined in the standard or notified to the UE from the network (NW). The AI ​​model specified in the standard can also be called a reference AI model. The AI ​​model information related to the reference AI model can also be called reference AI model information.

[0171] In addition, the AI ​​model information in the present disclosure may also include an index for determining the AI ​​model (for example, it may also be referred to as an AI model index, an AI model ID, a model ID, etc.). The AI ​​model information in the present disclosure may also include an AI model index on the basis of / instead of the above-mentioned AI model input / output information, etc. 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 to the UE from the NW.

[0172] The AI ​​model information in the present disclosure may also be referred to as AI model relevant information, or simply referred to as relevant information, etc. In the AI ​​model relevant information, information used to determine the AI ​​model may not be explicitly included. The AI ​​model relevant information may also be information that only includes meta information.

[0173] (Codebook setting)

[0174] The UE is configured with codebook-related parameters (CodebookConfig) through high-level signaling (RRC signaling) ( Figure 4 ). The codebook setting is included in the CSI report setting (CSI-ReportConfig) of the higher layer (RRC) parameters.

[0175] In the codebook setting, at least one codebook of type 1 single panel (typeI-SinglePanel), type 1 multi-panel (typeI-MultiPanel), type 2 (typeII), and type 2 port selection (typeII-PortSelection) is selected.

[0176] The codebook parameters include parameters related to codebook subset restriction (CBSR) (…Restriction). The CBSR setting is a bit that indicates which PMI reports are allowed (“1”) and which PMI reports are not allowed (“0”) for the precoder associated with the CBSR bit. One bit of the CBSR bitmap corresponds to one codebook index / antenna port.

[0177] (Type 1 codebook)

[0178] Type 1 single-panel codebook and type 1 multi-panel codebook are defined for base station panels. In type 1 single-panel, the number of CSI-RS antenna ports P CSI-RS and (N1, N2) define the antenna model of the CSI antenna port array (logical setting). In the type 1 multi-panel, the number of CSI-RS antenna ports P CSI-RS and (N g ,N1,N2), specifies the antenna model of the CSI antenna port array (logical setting).

[0179] For Rel.15 type 1 single panel CSI, the higher layer parameter of the UE's codebook type (subType in type1 in codebookType in CodebookConfig) is set to type 1 single panel ('typeI-SinglePanel'). In the case where the number of layers v∈{2,3,4} is not 1,1 , i 1,2 , i2. In the case of layer number v∈{2,3,4}, the PMI value corresponds to four codebook indexes i 1,1 , i 1,2 , i 1,3 , i2. In the case where the number of layers v∈{2,3,4} is not the same, the composite codebook index i1=[i 1,1 , i 1,2 In the case of the number of layers v∈{2,3,4}, the composite codebook index i1=[i 1,1 , i 1,2 , i 1,3 ].

[0180] The number of CSI antenna ports P is specified in the specification. CSI-RSThe supported settings (combinations of values) of (N1, N2) and (O1, O2) are specified. (N1, N2) represents the number of antenna elements in two dimensions and is set by n1-n2 in moreThanTwo in nrOfAntennaPorts in typeI-SinglePanel. (O1, O2) is the two-dimensional oversampling factor. i corresponding to the horizontal beam 1,1 is {0,1,...,N1O1-1}. i corresponding to the vertical beam 1,2 is {0,1,...,N2O2-1}. i2 is {0,1,2,3}. For codebookMode = 1, use antenna ports 3000 to 2999+P CSI-RS The matrix used in the 1-layer CSI report codebook is W_i 1,1 ,i 1,2 ,i2^(1). Here, W l,m,n (1) It is provided by the following formula (1).

[0181] [Mathematical formula 1]

[0182]

[0183] For Rel.15 Type 1 multi-panel CSI, in addition to N1 and N2, the number of panels N is also set compared to Type 1 single panel. g As inter-panel co-phasing, phase compensation between panels, phase adjustment / phase difference between panels, add i, 1,4 Select the same SD beam for each panel (precoding matrix W l ), only the inter-panel phase matching is reported.

[0184] The number of CSI antenna ports P is specified in the specification. CSI-RS Specifies the supported (N g ,N1,N2) and (O1,O2) settings (combination of values). (N1,N2) are set by ng-n1-n2 in typeI-MultiPanel. 1,1 is {0,1,...,N1O1-1}. 1,2 is {0,1,...,N2O2-1}. For q=1,...,N g -1,i 1,4,qis {0,1,2,3}. i2 is {0,1,2,3}. For codebookMode = 1, use antenna ports 3000 to 2999+P CSI-RS The matrix used in the 1-layer CSI report codebook is W_i 1,1 ,i 1,2 ,i 1,4 ,i2^(1). Here, W l,m,p,n (1) =W l,m,p,n ^1,N g ,1.

[0185] For N g =W_l,m,p,n^1,N of {2,4} g ,1 and W_l,m,p,n^2,N g ,1 (for the first layer, N g =2, codeBookMode = 1 l,m,p,n 1,2,1 , for the second layer, N g =2, codeBookMode = 1 l,m,p,n 2,2,1 , for the first layer, N g =4, codeBookMode = 1 l,m,p,n 1,4,1 , and for the second layer, N g =4, codeBookMode = 1 l,m,p,n 2,4,1 ) is provided by the following formula (2).

[0186] [Mathematical formula 2]

[0187]

[0188] Here, φ n =e jπn / 2 . For N g =2, p=p1, for N g =4, p = [p1, p2, p3]. φ_p1, φ_p2, φ_p3 represent inter-panel co-phasing. The same beam is selected for panels 0, 1, 2, and 3 (SD beam matrix, precoding matrix W l ), φ_p1 represents the phase compensation of panel 1 relative to panel 0, φ_p2 represents the phase compensation of panel 2 relative to panel 0, and φ_p3 represents the phase compensation of panel 3 relative to panel 0.

[0189] (Type 2 codebook)

[0190] We are studying CSI acquisition for coherent joint transmission (CJT) for FR1 and up to four TRPs, assuming ideal backhaul, synchronization, and the same number of antenna ports across multiple TRPs. We are studying improvements to the type 2 codebook of Rel.16 / 17 for CJT multi-TRPs for FDD.

[0191] In the present disclosure, a matrix Z having X rows and Y columns is sometimes expressed as Z(X×Y).

[0192] For the provided layer k, the generation of the precoding vector per subband (SB-wise) of the type 2 CSI of Rel.15 is based on the following equation.

[0193] W k (N t ×N3) = W1W 2,k (Y1)

[0194] N t is the number of ports. N3 is the total number of precoding matrices (precoders) (number of subbands) represented by PMI. W1 (N t ×2L) is a matrix (SD beam matrix) composed of L∈{2,4} (oversampled) spatial domain (SD) two-dimensional (2D) discrete Fourier transform (DFT) vectors (SD beams, 2D-DFT vectors). L is the number of beams. For example, L=2 SD 2D-DFT vectors are b i ,b j .W 2,k (2L×N3) is the subband complex linear combination (LC) coefficient matrix (combination coefficients) for layer k. 2,k represents beam selection and co-phasing between two polarizations. 2,k They are c i ,c j For example, the channel matrix h is obtained by linear combination of L = 2 SD 2D-DFT vectors c i b i ,+c j b j The feedback overhead is mainly due to the LC coefficient matrix W 2,k In addition, the type 2 CSI of Rel.15 only supports ranks 1 and 2.

[0195] Rel.16 Type 2 CSI uses frequency domain (FD) compression to reduce the W 2,k The associated overhead. In addition to rank 1 and 2, the type 2 CSI of Rel.16 also supports rank 3 and 4.

[0196] For the provided layer k, Rel.16 type 2 CSI may also be reported by the UE based on the following information.

[0197] W k = W1W ~ k W f,k H (Y2)

[0198] W 2,k By W ~ k W f,k H To approximate. The matrix W ~ It can also be represented by a ~ (wavy line) on W. f,k H It is W f,k The adjoint matrix of .

[0199] For CSI reporting, the UE can also be configured with one of two subband sizes. This subband (CQI subband) can also be defined as N PRB SB The number of consecutive PRBs depends on the total number of PRBs in the BWP. The number of PMI subbands R per CQI subband is set by RRCIE (numberOfPMI-SubbandsPerCQI-Subband). For R, the total number of precoding matrices N3 represented by PMI is controlled as a function of the number of subbands set in csi-ReportingBand, the subband size set by subbandSize, and the total number of PRBs in the BWP.

[0200] W1(N t ×2L) is a matrix composed of multiple (oversampled) spatial domain (SD) 2D-DFT (vectors, beams). For this matrix, multiple indices of the two-dimensional discrete Fourier transform (2D-DFT) vector and the two-dimensional oversampling factor are reported. The spatial domain response / distribution represented by the SD 2D-DFT vector can also be called an SD beam.

[0201] W ~ k(2L×M v ) is a matrix of combination coefficients, subband complex linear combination (LC) coefficients. For this matrix, up to K0 non-zero coefficients (NZCs) are reported. The report consists of two parts: a bitmap that captures the NZC positions and the quantized NZCs.

[0202] W f,k (N3×M v ) is a matrix consisting of multiple frequency domain (FD) bases (vectors) for layer k. Each layer has M v FD basis (FD DFT basis). In the case of N3>19, select M from the intermediate subset (InS) of size N3' (<N3) v DFT. In the case of N3≤19, log2(C(N3-1,M v -1)) bits. Here, C(N3-1,M v -1) is to select M from N3-1 v -1 combinations are also called binomial coefficients. The frequency domain response / distribution (frequency response) represented by the linear combination of the FD basis vectors and the combination coefficients can also be called an FD beam. An FD beam can also correspond to a delay distribution (time response).

[0203] A subset of the FD basis is provided as {f1,...,f Mv Here, f i is the i-th FD basis for the k-th layer, i∈{1,...,M v}. The PMI subband size is provided by the CQI subband size R, R∈{1,2}. The number of FD bases M for the provided rank v v By ceil (p v ×N3 / R) is provided. The number of FD bases is the same for all layers k∈{1,2,3,4}. v Set by high level.

[0204] Matrix W 2,kEach row of represents the channel frequency response of a specific SD beam. In the case where the SD beam has high directivity, the channel tap of each beam is limited (in the time domain, the power delay profile becomes sparse). As a result, the channel frequency response of each SD beam has a high correlation (close to flat in the frequency domain). In this case, the channel frequency response can be approximated by a linear combination of a small number of FD bases. For example, in M v = 2, use the FD basis f2, f q and linear combination coefficient d1 0 ,d2 0 , the frequency response associated with SD beam b0 is through d1 0 f2+,d2 0 f q To approximate.

[0205] M v The FD basis selects the highest gain. By setting M v ≪N3, W ~ k The cost and W 2,k The overhead is quite small compared to M v All or part of the FD basis is used for the approximation of the frequency response of each SD beam. In order to report only the selected FD basis for each SD beam, a bitmap is used. In case the bitmap is not reported, all FD basis are selected for each SD beam. In this case, the nonzero coefficients (NZC) of all FD basis are reported for each SD beam. The maximum number of NZCs in one layer is K. k NZ ≤K0=ceil(β×2LM v ), the maximum number of NZCs across all layers K NZ ≤2K0=ceil(β×2LM v ). β is set by the higher level.

[0206] W ~ k The complex coefficients reported in are the quantized amplitude and phase, respectively.

[0207] [Amplitude Quantization]

[0208] The polarization-specific reference amplitude is obtained using Figure 5 Table (amplitude coefficient indicator i 2,3,l Mapping of multiple elements: From element k l,p (1) Amplitude coefficient p l,p (1) All other coefficients are quantized using Figure 6 Table (amplitude coefficient indicator i 2,4,l Mapping of multiple elements: From element k l,i,f (2) Amplitude coefficient p l,i,f (2) 8-level quantization of the mapping).

[0209] [Phase Quantization]

[0210] All coefficients are quantized using 16-PSK. l,i = exp(j2πc l,i / 16), c l,i ∈{0,...,15}. Here, c l,i is the phase value φ associated with l,i Phase coefficient reported by the UE (using 4 bits).

[0211] Type 2 CSI feedback on PUSCH in Rel.16 consists of two parts. CSI Part 1 has a fixed payload size and is used to identify the number of information bits in CSI Part 2. Part 2 is of variable size (UCI size depends on the number of non-zero amplitude coefficients (NZCs), which is unknown to the base station). The UE reports the number of NZCs in CSI Part 1, which determines the size of CSI Part 2. After receiving CSI Part 1, the base station identifies the size of CSI Part 2.

[0212] In enhanced type 2 CSI feedback, CSI part 1 contains RI, CQI, and an indication of the total number of non-zero amplitudes across multiple layers for enhanced type 2 CSI. The fields of part 1 are coded separately. CSI part 2 contains the PMI for enhanced type 2 CSI. Parts 1 and 2 are coded separately. CSI part 2 (PMI) contains at least one of the following: oversampling factor, index of 2D-DFT basis, index of initial DFT basis (starting offset) of the selected DFT window M initial , the DFT basis selected for each layer, the non-zero LC coefficients (NZC, amplitude and phase) of each layer, the strongest (strongest, maximum intensity) coefficient indicator (strongest coefficientint indicator (SCI)) of each layer, and the amplitude of the strongest coefficient for each layer / each polarization.

[0213] For the k-th layer, multiple PMI indexes (PMI values, codebook indexes) associated with different CSI part 2 information may also follow as follows.

[0214] ·i 1,1 : Oversampling factor

[0215] ·i 1,2 : Multiple indices of a 2D-DFT basis

[0216] ·i 1,5 : Index of the initial DFT basis (starting offset) of the selected DFT window M initial

[0217] ·i 1,6,k : The DFT basis selected for the kth layer

[0218] ·i 1,7,k : Bitmap for the kth layer

[0219] ·i 1,8,k : The strongest (strongest, maximum intensity) coefficient indicator (SCI) for the kth layer

[0220] ·i 2,3,k : The amplitude of the strongest coefficient (for both polarizations) of the kth layer

[0221] ·i 2,4,k : The amplitude of the reported coefficients of the kth layer

[0222] ·i 2,5,k : The phase of the reported coefficients of the kth layer

[0223] i 1,5 and 1,6,k is the PMI index for DFT basis reporting. Only when N3>19, report i 1,5 .

[0224] As a grouping of CSI Part 2, the PMI information is aggregated into 3 groups (Groups 0 to 2) for the provided CSI report. This is important in case of CSI omission. Index i 2,4,l 、i 2,5,l 、i 1,7,l Each element reported is associated with a specific precedence rule. Groups 0 to 2 follow the following.

[0225] Group 0: index i 1,1 、i 1,2 、i 1,8,l (l=1,...,v)

[0226] Group 1: Index i (when reported) 1,5 , index i (when reported) 1,6,l 、i 1,7,l The highest (upper) v2LM within v -floor(K NZ / 2) priority elements, i 2,3,l 、i 2,4,l The highest (upper) ceil (K NZ / 2)-v priority elements, i 2,5,l The highest (upper) ceil (K NZ / 2)-v priority elements (l=1,...,v)

[0227] ·Group 2:i 1,7,l The lowest (lower) floor (K NZ / 2) priority elements, i 2,4,l The lowest (lower) floor (K NZ / 2) priority elements, i 2,5,l The lowest (lower) floor (K NZ / 2) priority elements (l=1,...,v)

[0228] In Type 1 CSI, an SD beam represented by an SD DFT vector is transmitted to the UE. In Type 2 CSI, L SD beams are linearly combined and transmitted to the UE. Each SD beam can be associated with multiple FD beams. For the corresponding SD beam, a channel frequency response can be obtained by linearly combining these FD basis vectors. The channel frequency response corresponds to the power delay profile.

[0229] Figure 7 is a diagram showing the relationship between the number of antenna ports and the port number of the type 2 codebook. When 'typeII' is set in the high-level parameter codebookType, Figure 7 The number of antenna ports and port numbers are set.

[0230] Figure 8 It is a diagram showing each parameter corresponding to paramCombination-r16. Figure 8 Shown with Figure 4 The parameters L, P corresponding to paramCombination-r16 in CodebookConfig-r16 are shown v ,β value. In the type 2 codebook of Rel.16, (N1,N2,O1,O2,L,p v ,β),(Nsb,R) determines the payload size.

[0231] (Accuracy performance of CSI reconstruction)

[0232] In the previous Rel.16 CSI feedback, in order to reconstruct the channel information, the index of the discrete Fourier transform (DFT) vector in the spatial domain (SD) and the frequency domain (FD) and the channel coefficient as the quantized non-zero coefficient (NZC) are reported. The accuracy performance of CSI reconstruction is related to the following (1) to (3).

[0233] (1) The number of DFT vector indices, the number of NZCs, and the quantization level of SD and FD. These values ​​are set by the base station (gNB) through RRC parameters (CodebookConfig-r16) to determine the total payload.

[0234] (2) The selection of DFT vector and NZC set by RRC. These are selected by UE implementation.

[0235] (3) Construction of basis vectors. Basis vectors are model-based and can be fixed in all scenarios. The so-called model-based basis vectors can also be generated by conventional methods other than AI / ML models in the database. The UE and the base station (gNB) can also have a common identification of the basis vectors.

[0236] (AI-based CSI feedback)

[0237] As a representative sub-use case, spatial-frequency domain CSI compression based on a two-sided AI model is being studied. For example, the preprocessed and compressed beam delay domain CSI matrix is ​​compressed using a type II codebook through an autoencoder (AE).

[0238] Specifically, the UE connects the (K×2L×M) CSI matrix generated by 2D-DFT to the AE for compression. In addition, K is the number of antenna ports of the UE, L is the number of beams (number of layers), and M is the number of delayed extensions. The overall payload consists of the same L and M information as the Type II codebook and the stream bits of the coefficients. The advantage (scalability) is that even if the number of transmission ports and the number of subbands change, the input and output to the AE become the same matrix size (K×2L×M), so the processing can be simplified. For example, when L=8, M=16, and N3=104, the payload is calculated as shown in the following formula (3).

[0239] [Mathematical formula 3]

[0240]

[0241] Fig. 9This is a diagram showing an example of AI-based CSI feedback. The UE performs preprocessing, AI / ML-based CSI generation, and post-processing on CSI-related measurement results, and sends the coded bits (CSI feedback information) to the NW (base station). In this AI / ML-based CSI generation, CSI compression is performed. The NW (base station) performs preprocessing, AI / ML-based CSI reconstruction, and post-processing on the received bits to obtain CSI (channel / precoding matrix).

[0242] In this case, it is desirable to select and adjust AI / ML so that the CSI obtained by the NW (base station) is close to the target CSI. The target CSI may also refer to the CSI calculated based on UE measurement, the ideal CSI (based on simulation, fixed value), or the actual CSI.

[0243] <Example of using encoder CSI feedback>

[0244] The information provided (supplied) by the UE to the encoder for CSI feedback is described below. This information may also be referred to as input information to the encoder, or simply referred to as input information.

[0245] The UE transmits information (CSI feedback) including coded bits outputted by inputting input information to an encoder from an antenna. The base station receives reconstructed input information outputted by inputting the received CSI feedback bits to a corresponding decoder.

[0246] [Option 1]

[0247] The input information may also be information related to the channel (or channel matrix). The channel matrix may include information on the channel coefficients for each subband / antenna port (for simplicity, referred to as the matrix of Option 1.1), or information obtained from the Inverse Discrete Fourier Transform (IDFT) of the channel coefficients (for simplicity, referred to as the matrix of Option 1.2). The latter information can make the matrix sparser than the former information by transforming the channel matrix into the angle / delay domain, and thus can be expected to contribute to the speed-up of the encoder operation, etc.

[0248] When the output from the decoder is information subjected to IDFT, the base station can obtain the original channel coefficients by applying DFT thereto.

[0249] In addition, in the present disclosure, the antenna port may also be rewritten as at least one of a transmitter (BS) antenna port, a receiver (UE) antenna port, a transmission antenna port, a reception antenna port, etc. In the present disclosure, a subband, a subcarrier, a CSI subband, and a CSI subcarrier may also be rewritten mutually.

[0250] When Option 1 is adopted, the UE can obtain input information by obtaining the channel coefficient based on the reference signal, etc., and there is no need to calculate the precoding matrix, thereby reducing the UE load.

[0251] Fig. 10A as well as Fig. 10B : is a diagram showing an example of input information of option 1. In this example, a single-antenna UE is assumed. Fig. 10A The matrix of option 1.1 is shown, for example, a channel matrix corresponding to the number of antenna ports x the number of subbands. Each element may also represent a channel coefficient. Fig. 10B Shown with Fig. 10A Here, the matrix sandwiched by the two-dimensional DFT (2D-DFT) matrix represents the matrix of Option 1.2, which corresponds to, for example, a channel matrix of the number of antenna ports×the number of subbands.

[0252] [Option 2]

[0253] The input information may also be information related to the precoding matrix. The precoding matrix may include information about the precoding coefficients (elements of the precoding matrix) for each subband / each antenna port / each MIMO layer (for simplicity, referred to as the matrix of Option 2.1), or information obtained from the IDFT of the precoding coefficients (for simplicity, referred to as the matrix of Option 2.2). The latter information can make the matrix sparser than the former information by transforming the precoding matrix into the angle / delay domain, and thus can be expected to contribute to the speed-up of the encoder operation, etc.

[0254] When the output from the decoder is information subjected to IDFT, the base station can obtain the original channel coefficients by applying DFT thereto.

[0255] When Option 2 is adopted, the UE calculates the precoding matrix, thereby improving compatibility with existing standards that perform control based on the precoding matrix.

[0256] Fig.11A as well as Fig. 11B : is a diagram showing an example of input information of option 2. In this example, a precoding matrix for each MIMO layer is shown. Fig.11A The matrix of Option 2.1 is shown, for example, a precoding matrix corresponding to the number of antenna ports × the number of subbands. Each element may also represent a precoding weight (coefficient). Fig. 11B Shown with Fig.11AHere, the matrix sandwiched by the two-dimensional DFT (2D-DFT) matrix represents the matrix of Option 2.2, which corresponds to the precoding matrix of the number of antenna ports×the number of subbands, for example.

[0257] In addition, the UE can decide which information of options 1 and 2 to use as input information based on specific rules / UE capabilities, or it can be notified using physical layer signaling (e.g., DCI), higher layer signaling (e.g., RRC signaling, MAC CE), specific signals / channels, or a combination thereof.

[0258] [Option 3]

[0259] Option 3 involves how the UE obtains (extracts) input information. The extraction can also be performed for each DFT basis. For example, only information corresponding to a specific DFT basis can be extracted as input information. In this case, the DFT basis can correspond to a vector that can be calculated based on the same DFT component (or the same DFT coefficient / DFT index) and at least one of the oversampling factors, or it can correspond to the row / column of the above-mentioned channel matrix / precoding matrix. For example, a DFT basis can also correspond to a vector (a row vector or a column vector) in a 2D DFT matrix.

[0260] In addition, a DFT basis can also contain components corresponding to parameters such as DFT index / oversampling factor (e.g., e j(2π*(DFT索引)*(采样点) / ((样本数)*(过采样因子))) ).

[0261] Here, the DFT index may also be an index for identifying the DFT basis, the sampling point may also be an index representing a specific sample, and the sampling point may also take a value of 0, 1, ..., (number of samples) * (oversampling factor) - 1. The DFT index may also be called the DFT basis index, etc. The DFT index may also correspond to the row number / column number of the channel matrix / precoding matrix.

[0262] Fig. 12A as well as Fig. 12B : is a diagram showing an example of extraction of input information based on the DFT basis according to Option 3. In this example, an example of extraction of input information of the precoding matrix from Option 2.2 is shown. Fig. 12A is a diagram showing the selected DFT basis. Fig. 12A It shows the case where two DFT bases are selected for the rows (angle domain, antenna port domain) and one DFT base is selected for the columns (delay domain, subband domain).

[0263] The input information may also correspond to the elements of the intersection of the row-wise DFT basis and the column-wise DFT basis. Fig. 12A , Fig. 12BElements in the hatched portion shown are determined as input information.

[0264] The UE may also send information related to the DFT basis to the network. The UE may include the information in the CSI report or send it separately from the CSI report. The information related to the DFT basis may be information related to several DFT basis selected (reported) in a specific CSI report / CSI part 1 / CSI part 2 / CSI part X, or information related to which DFT basis is selected (reported) in a specific CSI report / CSI part 1 / CSI part 2 / CSI part X (information for identifying the DFT basis).

[0265] In the present disclosure, CSI part X may also mean a newly defined CSI part other than CSI part 1 / 2. Information corresponding to the output from the encoder described in the present disclosure may also be included in CSI part 1 / 2 / X.

[0266] The UE may also send information about how many DFT bases are selected (reported) in a specific CSI part (e.g., CSI part 1) to the network. The UE may also use other CSI parts (e.g., CSI part 1) to send information about how many DFT bases are selected (reported) in a CSI report (a certain CSI part (e.g., CSI part 2) in the CSI report).

[0267] The UE may determine the number of extracted elements (eg, corresponding to the DFT basis of the extracted elements) / extracted elements (eg, corresponding to the DFT basis of the extracted elements) based on a specific rule or based on received information related to the DFT basis.

[0268] The information related to the DFT basis sent / received by the UE can be notified to the UE using physical layer signaling (e.g., DCI, UCI), high-layer signaling (e.g., RRC signaling, MAC CE), specific signals / channels, or a combination thereof, or it can be UE capabilities.

[0269] The information related to the DFT basis may also indicate the starting position of the selected DFT basis and the number of the selected DFT basis. This information can be implemented in a smaller capacity.

[0270] The information related to the DFT basis may also indicate the index of each selected DFT basis. Based on this information, a more flexible DFT basis can be used.

[0271] These information related to the DFT basis can also be used in combination. In addition, the UE can decide which information related to the DFT basis to use based on specific rules / UE capabilities, or use physical layer signaling (e.g., DCI), high-layer signaling (e.g., RRC signaling, MAC CE), specific signals / channels, or a combination thereof to notify the UE. For example, which information related to the DFT basis to use can also be selected based on at least one of the number of candidate DFT bases, other parameters, etc.

[0272] Fig.13A as well as Fig. 13B This is a diagram showing an example of a method for determining a DFT basis. Fig.13A In the case where the information on the DFT basis indicates the start position of the selected DFT basis and the number of the selected DFT basis, an example of the DFT basis indicated by the information is shown. Fig. 13B FIG. 8 shows an example of a DFT basis represented by the information when the information related to the DFT basis represents the index of each selected DFT basis. Fig. 13B In the case of the determination method, as shown in the figure, the selected DFT basis may also be discontinuous.

[0273] Figures 14A-14D is a diagram showing an example of a matrix that can be used as input information. In this example, the precoding matrix of option 2 is assumed for explanation, but those skilled in the art will understand that the same is true for option 1. In this example, W 1-1 It can also mean a matrix obtained without additional processing (preprocessing) other than obtaining the existing precoding matrix, W 1-2-1 , W 1-2-2 , W 1-2-3 It may also mean a matrix obtained by performing additional processing (preprocessing) in addition to obtaining an existing precoding matrix.

[0274] Fig.14A The left side of W 1-1 Corresponding to the matrix of option 2.1, the W on the right is 1-2-1 The matrices corresponding to option 2.1. The size of these matrices is the number of subbands × the number of antenna ports. These matrices can also be obtained for each layer.

[0275] Fig. 14C W 1-2-2 Corresponding to W 1-2-1 The angular domain is extracted with respect to several DFT bases (in this case, Fig. 14B The two DFT bases shown on the left side of the DFT matrix correspond to the information (in other words, the matrix obtained by beam selection) (close to the type II codebook). 1-2-2The size of is the number of subbands × the number of selected beams (number of angles), and this matrix can also be obtained for each layer.

[0276] Fig.14D W 1-2-3 Corresponds to: From W 1-2-2 We further extract the delay domain with respect to several DFT bases (in this case, Fig. 14C The two DFT bases shown on the right side of the DFT matrix correspond to the information (in other words, the delay extracted) matrix (close to the enhanced type II codebook). 1-2-3 The size of is the selected delay number × the selected beam number (number of angles), and this matrix can also be obtained for each layer.

[0277] As mentioned above, AI-assisted CSI feedback has been studied. However, there are still some areas where research has not yet progressed on the specific content of AI-assisted CSI feedback. If these are not properly regulated, appropriate overhead reduction / high-precision channel estimation / efficient resource utilization cannot be achieved, and there is a concern that the improvement of communication throughput / communication quality will be suppressed.

[0278] For example, there is a trade-off between scalability and CSI compression performance. For example, the greater the constraints in the angle domain and beam domain, the higher the scalability in the spatial domain and frequency domain, but the CSI compression performance becomes lower.

[0279] However, how to adjust the balance between compression performance and scalability has not been fully studied. For example, in some cases, scalability in the spatial domain and frequency domain is not required, and the potential of channel compression based on AE should be fully utilized. In addition, for example, when AE is used in CSI compression, how to set the size and form of the coding bits, whether the Type II 2D-DFT basis is reused in AE, whether the structure of the Type II codebook is reused, and how to reuse it, etc., have not been fully studied. If these are not properly specified, appropriate overhead reduction / high-precision channel estimation / efficient resource utilization cannot be achieved, and there is a concern that the improvement of communication throughput / communication quality will be suppressed.

[0280] Therefore, the inventors of the present invention have conceived of a terminal that can implement appropriate CSI feedback using AI.

[0281] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. The wireless communication methods according to the embodiments may be applied individually or in combination.

[0282] In the present disclosure, "A / B" and "at least one of A and B" may be replaced with each other. In addition, in the present disclosure, "A / B / C" may also mean "at least one of A, B, and C".

[0283] In the present disclosure, notification, activation, deactivation, indication (or indication), selection, configuration, update, determination, etc. may also be mutually rewritten. In the present disclosure, support, control, controllable, operation, and operation may also be mutually rewritten.

[0284] In the present disclosure, Radio Resource Control (RRC), RRC parameters, RRC messages, high-layer parameters, fields, Information Element (IE), settings, etc. may also be overwritten with each other. In the present disclosure, Medium Access Control (MAC) control elements (MAC Control Element (CE)), update commands, activation / deactivation commands, etc. may also be overwritten with each other.

[0285] In the present disclosure, the higher layer signaling may be, for example, any one of Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information, etc., or a combination thereof.

[0286] In the present disclosure, MAC signaling may also use, for example, MAC Control Element (MACCE), MAC Protocol Data Unit (MAC Protocol Data Unit (PDU)), etc. Broadcast information may also be, for example, Master Information Block (MIB), System Information Block (SIB), minimum system information (Remaining Minimum System Information (RMSI)), Other System Information (Other System Information (OSI)), etc.

[0287] In the present disclosure, the physical layer signaling may be, for example, downlink control information (Downlink Control Information (DCI)), uplink control information (Uplink Control Information (UCI)), etc.

[0288] In the present disclosure, index, identifier (ID), indicator, resource ID, etc. may also be mutually replaced. In the present disclosure, sequence, list, set (set), group, group, cluster, subset, etc. may also be mutually replaced.

[0289] In the present disclosure, panel, UE panel, panel group, beam, beam group, precoder, uplink (UL) transmission entity, transmission / reception point (Transmission / Reception Point (TRP)), base station, spatial relationship information (Spatial Relation Information (SRI)), spatial relationship, SRS resource indicator (SRSResource Indicator (SRI)), control resource set (COntrol REsource SET (CORESET)), physical downlink shared channel (Physical Downlink Shared Channel (PDSCH)), codeword (Codeword (CW)), transport block (Transport Block (TB)), reference signal (Reference Signal (RS)), antenna port (e.g., demodulation reference signal (DeModulation Reference Signal (DMRS)) port), antenna port group (e.g., DMRS port group), group (e.g., spatial relationship group, code division multiplexing (Code Division Multiplexing (CDM)) group, reference signal group, CORESET group, physical uplink control channel (Physical Uplink Control Channel (PUCCH)) group, PUCCH resource group), resources (for example, reference signal resources, SRS resources), resource sets (for example, reference signal resource sets), CORESET pool, downlink transmission configuration indication state (Transmission Configuration Indicationstate (TCI state)) (DL TCI state), uplink TCI state (UL TCI state), unified TCI state, common TCI state, Quasi-Co-Location (QCL)), QCL assumptions, etc. can also be rewritten with each other.

[0290] In the present disclosure, CSI-RS, Non Zero Power (NZP) CSI-RS, Zero Power (ZeroPower (ZP)) CSI-RS, and CSI Interference Measurement (CSI-IM) may also be replaced with each other. In addition, CSI-RS may also include other reference signals.

[0291] In the present disclosure, the autoencoder, encoder, decoder, etc. can also be rewritten as at least one of a model, an ML model, a neural network model, an AI model, an AI algorithm, etc. In addition, the autoencoder can also be rewritten with any autoencoder such as a stacked autoencoder (StackedAutoencoder) and a convolutional autoencoder. The encoder / decoder of the present disclosure can also adopt models such as a residual network (Residual Network (ResNet)), a densely connected network (DenseNet), and a multi-path reinforcement network (RefineNet).

[0292] In addition, in the present disclosure, encoder, encoding (Encoding), encoding operation (Encode), correction / change / control based on encoder, etc. can also be rewritten mutually. In addition, in the present disclosure, decoder, decoding (Decoding), decoding operation (Decode), correction / change / control based on decoder, etc. can also be rewritten mutually.

[0293] In the present disclosure, UCI, CSI report, CSI feedback, feedback information, feedback bit, etc. may also be replaced by each other. In addition, in the present disclosure, bit, bit string, bit sequence, sequence, value, information, value obtained according to bit, information obtained according to bit, etc. may also be replaced by each other.

[0294] In the present disclosure, matrices, channel matrices, coefficients, channel coefficients, and precoding matrices may also be rewritten mutually.

[0295] In the present disclosure, beam, SD beam, SD vector, and SD 2D-DFT vector may be replaced with each other. L, 2L, the number of SD beams, the number of beams, and the number of SD 2D-DFT vectors may be replaced with each other.

[0296] In the present disclosure, FD substrate, FD DFT substrate, DFT substrate, f i In the present disclosure, FD beam, FD vector, FD basis vector, FD DFT basis vector, and DFT basis vector may be replaced with each other.

[0297] In the following embodiments, since the AI ​​model related to the communication between UE and BS is described, the associated subjects are UE and BS, but the application of the embodiments of the present disclosure is not limited to this. For example, for communication between other subjects (for example, communication between UE and UE), the UE and BS in the following embodiments can also be rewritten as the first UE and the second UE. In other words, the UE, BS, etc. of the present disclosure can also be rewritten as any UE / BS. The network (NW), base station (BS), and gNB can also be rewritten with each other.

[0298] In the present disclosure, models and AI / ML models may also be mutually rewritten. Compression, encoding, and application of AI / ML models may also be mutually rewritten. In the present disclosure, expectations, assumptions, and predictions may also be mutually rewritten.

[0299] In the present disclosure, payload, payload size, CSI payload size, and compressed CSI payload (payload size) may also be replaced with each other. CSI compression may also refer to AI-based CSI compression.

[0300] (Wireless Communication Method)

[0301] <First embodiment>

[0302] [First method]

[0303] The UE may also receive a setting (first setting) related to the payload of the compressed CSI (e.g., the total payload size (P) or P2) from the NW (base station). P2 is the payload size of the encoded bits. When the payload size of the codebook part is set to P1, P2=P-P1.

[0304] The UE may also receive RRC parameters for AI-based codebook configuration. The AI-based codebook configuration may also be included in the type I or type II field in the codebook configuration ( Fig.15A , Fig. 15B Alternatively, this setting can also be independent of the previous (e.g. Rel.16) Type I / Type II settings ( Fig.16 ).

[0305] exist Fig.15A In the codebook setting, the type I setting and the type II setting respectively include the AI-based codebook setting "AIML". Fig. 15B In the codebook configuration for Rel. 16, the type II configuration includes the AI-based codebook configuration "AIML". This allows for appropriate configuration corresponding to other codebook types.

[0306] exist Fig.16 In the codebook setting, a specific codebook type "AIML" is set, which is independent of the setting of other codebook types (Type I / Type II). This allows flexible setting regardless of other codebook types.

[0307] The UE may also receive RRC parameters related to the payload for the AI-based codebook setting. The UE may not directly receive the payload, but may be implicitly set. For example, the UE may also calculate the payload based on the Type I / Type II setting in the codebook setting. The payload may also be independent of other settings in the AI-based codebook setting.

[0308] Fig.17 This is a diagram showing an example of parameters of AIML. Fig.17 The "AIML" is Fig.15A , Fig. 15B , Fig.16 The details of the "AIML" of the message. The "AIML" contains the value of the payload. The value of the payload can also be at least one of the total payload size (P) or P2.

[0309] [Modification 1]

[0310] The UE may also determine the total payload size (P) or P2 based on information related to the model. The UE may also receive the model through high-layer signaling / physical layer signaling. In the present disclosure, the model and information related to the model may also be overwritten.

[0311] Alternatively, the UE may also calculate the total payload size (P) or P2 based on the number of layers / rank number / RI. For example, the UE may also determine the total payload size (P) or P2 as a value obtained by multiplying the set specific value by the number of layers / rank number / RI. The specific value may also be sent to the UE via high-layer signaling / physical layer signaling.

[0312] The model may also be a model for activated CSI feedback.

[0313] Alternatively, the model may be a set / registered model for CSI feedback. In this case, model activation / model switching may not be supported, and only model setting may be supported.

[0314] [Modification 2]

[0315] The UE may also receive information associated with the model (information of variant example 1) and other information (settings in the first embodiment), and determine the total payload size (P) based on the information associated with the model and other information. The information associated with the model may also be the compression rate of the CSI.

[0316] The model may be a model for activated CSI feedback or a model for set / registered CSI feedback.

[0317] Other information may also be RRC parameters for AI-based codebook settings. For example, other information (settings) may also be included in the Type I / Type II field. Alternatively, other information (settings) may also be independent of the previous (e.g., Rel. 16) Type I / Type II settings.

[0318] Other information may also be RRC parameters related to the payload for the AI-based codebook setting. The UE may not directly receive the payload, but may be implicitly set. For example, the UE may also calculate the payload based on the type I / type II setting in the codebook setting. The payload may also be independent of other settings in the AI-based codebook setting.

[0319] <Second embodiment>

[0320] The UE may also receive an intermediate configuration (second configuration) related to CSI feedback from the NW (base station). The intermediate configuration may also be at least one of the parameters shown in the following embodiments 2-0 to 2-4 and supplements.

[0321] [Implementation Method 2-0]

[0322] The UE receives parameters (N1, N2, O1, O2) indicating the number of ports and the oversampling coefficient (factor). This parameter can also be set independently of other settings for use in AI / ML settings. Alternatively, this parameter can also be set implicitly based on the settings of the previous (e.g., Rel.16) codebook. The UE can also determine this parameter based on the codebook subset restriction (n1-n2-CodebookSubsetRestriction-r16), for example.

[0323] [Implementation Method 2-1]

[0324] The UE may also receive a parameter indicating the number of layers (number of beams) (L) in the beam domain. This allows the degree of freedom in the frequency domain to be maintained and allows scalability in response to different transmission ports. For use in AI / ML settings, this parameter may also be set independently of other settings. Alternatively, this parameter may also be set implicitly based on the settings of a previous (e.g., Rel.16) codebook. The UE may also determine the parameter (L), for example, based on paramCombination-r16. paramCombination-r16 is a parameter representing a group of L, Pv, and β.

[0325] [Implementation Method 2-2]

[0326] The UE may also receive a parameter indicating the number of extensions (M) in the delay domain. In this way, the degree of freedom in the spatial domain can be maintained, and different numbers of subbands can also be handled. For use in AI / ML settings, this parameter may also be set independently of other settings. Alternatively, this parameter may also be implicitly set based on the settings of the previous (e.g., Rel.16) codebook. The UE may also determine the parameter (M), for example, based on at least one of the values ​​of L and Pv of paramCombination-r16, the number of PMI bands per CQI subband (numberOfPMI-SubbandsPerCQI-Subband), and the size of the subband (subbandSize).

[0327] [Implementation Method 2-3]

[0328] The UE may also receive a parameter indicating the number of layers (L) in the beam domain and a parameter indicating the number of extensions (M) in the delay domain. In this way, the degree of freedom of coefficient compression can be maintained, and the same model can be used to deal with different transmission ports and different numbers of subbands. For AI / ML settings, this parameter may also be set independently of other settings. Alternatively, this parameter may also be implicitly set based on the settings of the previous (e.g., Rel.16) codebook. The UE may also determine the parameters (L and M) based on, for example, the values ​​of L and Pv of paramCombination-r16, the number of PMI bands per CQI subband (numberOfPMI-SubbandsPerCQI-Subband), and at least one of the size of the subband (subbandSize).

[0329] [Implementation Method 2-4]

[0330] The UE may also receive a parameter indicating the number of layers (L) in the beam domain, a parameter indicating the number of extensions (M) in the delay domain, and a parameter indicating the number of NZCs (K0). This allows the previous (e.g., Rel.16) codebook settings to be reused, and the freedom of compression of the amplitude and phase of the NZC to be ensured. For use in AI / ML settings, this parameter may also be set independently of other settings. Alternatively, this parameter may also be implicitly set based on the previous (e.g., Rel.16) codebook settings. The UE may also determine the parameters (L, M, and K0) based on, for example, the values ​​of L and Pv of paramCombination-r16, the number of PMI bands per CQI subband (numberOfPMI-SubbandsPerCQI-Subband), and at least one of the size of the subband (subbandSize).

[0331] [Replenish]

[0332] The UE may also receive intermediate settings related to CSI feedback, precoding vector P v , parameter β used to control the maximum number of NZCs, and subband size R.

[0333] <Third Embodiment>

[0334] The UE may also receive a setting (first setting) related to the CSI payload (refer to the first embodiment) and an intermediate setting (second setting) related to the CSI feedback (refer to the second embodiment), and control the AI-based CSI compression based on the received setting and the intermediate setting related to the payload size. For example, the UE calculates the payload of the compressed CSI based on the first setting, and determines the matrix applied to the CSI compression based on the second setting.

[0335] The intermediate setting (second setting) can also be related to the number of beams L, the number of delayed spreads (M), the number of antenna elements (number of ports) (N1, N2), the oversampling coefficient (factor) (O1, O2), the precoding vector P v , subband number N sb , the number of non-zero coefficients (NZC) K0, a parameter β for controlling the maximum number of NZCs, and at least one related setting of the subband size R.

[0336] [Implementation Method 3-1]

[0337] The UE follows the following steps to perform DFT in the spatial domain, followed by AI-based CSI compression (encoding), and sends the compressed CSI to the base station (gNB) ( Fig.18 ). H is the channel matrix and W is the precoding matrix. L ', W L ' is the channel matrix and precoding matrix corresponding to the L beams. The UE may also receive the payload (P), L, N1, N2, O1, O2 in advance.

[0338] Step 1: The UE calculates the payload size (P1) of the codebook part and the payload size (P2) of the AI ​​part (encoded bits) respectively. The payload size (P1) of the codebook part is calculated in the same way as the type II codebook in the beam domain. Specifically, it is calculated as shown in the following equation (4). In addition, the payload size (P2) of the AI ​​part is P-P1. P represents the total payload size of the CSI.

[0339] [Formula 4]

[0340]

[0341] Step 2: UE performs DFT and selects L beams. In this case, the basis of 2D-DFT can also be the same as Type I / Type II / Enhanced Type II. Alternatively, the 2D-DFT basis can also be a basis set by the NW (base station) or a new basis specified in the specification.

[0342] Step 3: The UE uses the encoder to generate the matrix (H L ' / W L ') for compression.

[0343] Step 4: The UE sends the beam domain codebook with payload size (P1) and the coded bits with payload size (P2) to the base station (gNB).

[0344] [Implementation Method 3-2]

[0345] The UE follows the following steps to perform DFT in the frequency domain, followed by AI-based CSI compression (encoding), and sends the compressed CSI to the base station (gNB) ( Fig.19 ). H is the channel matrix and W is the precoding matrix. M ', W M ' is the channel matrix and precoding matrix corresponding to the extension number M of the delay domain. The UE may also receive the payload (P), Pv, Nsb, and R in advance.

[0346] Step 1: The UE calculates the payload size (P1) of the codebook part and the payload size (P2) of the AI ​​part (encoded bits) respectively. The payload size (P1) of the codebook part is calculated in the same way as the type II codebook in the beam domain. Specifically, it is calculated as shown in the following equation (5). In addition, the payload size (P2) of the AI ​​part is P-P1. P represents the total payload size of the CSI.

[0347] [Mathematical formula 5]

[0348]

[0349] Step 2: UE performs DFT and selects M extensions. In this case, the basis of 2D-DFT can also be the same as that of enhanced type II. Alternatively, the 2D-DFT basis can also be a basis set by the NW (base station) or a new basis specified in the specification.

[0350] Step 3: The UE uses the encoder to encode the matrix (H M ' / W M ') for compression.

[0351] Step 4: The UE sends the beam domain codebook with payload size (P1) and the coded bits with payload size (P2) to the base station (gNB).

[0352] [Implementation Method 3-3]

[0353] The UE follows the following steps to perform DFT in the spatial domain and frequency domain, followed by AI-based CSI compression (encoding), and sends the compressed CSI to the base station (gNB) ( Fig. 20 ). H is the channel matrix and W is the precoding matrix. LM ', W LM ' is the channel matrix and precoding matrix corresponding to the number of beams L and the number of extensions in the delay domain M. The UE can also receive the payload (P) in advance, L, N1, N2, O1, O2, P v 、N sb , R.

[0354] Step 1: The UE calculates the payload size (P1) of the codebook part and the payload size (P2) of the AI ​​part (encoded bits) respectively. The payload size (P1) of the codebook part is calculated in the same way as the beam domain type II codebook. Specifically, it is calculated as shown in the following equation (6). In addition, the payload size (P2) of the AI ​​part is P-P1. P represents the total payload size of the CSI.

[0355] [Mathematical formula 6]

[0356]

[0357] Step 2: UE performs DFT, selects L beams, and M extensions. In this case, the basis of 2D-DFT can also be the same as Type I / Type II / Enhanced Type II. Alternatively, the 2D-DFT basis can also be a basis set by the NW (base station) or a new basis specified in the specification.

[0358] Step 3: The UE uses the encoder to generate the matrix (H LM ' / W LM ') for compression.

[0359] Step 4: The UE sends the beam domain codebook with payload size (P1) and the coded bits with payload size (P2) to the base station (gNB).

[0360] [Implementation Method 3-4]

[0361] The UE follows the following steps to perform DFT in the spatial domain and frequency domain, select NZC (K0), and then AI-based CSI compression (encoding), and send the compressed CSI to the base station (gNB) ( Fig.21 ). H is the channel matrix and W is the precoding matrix. LMK0 ', W LMK0 ' is the channel matrix and precoding matrix corresponding to the number of beams L, the number of extensions in the delay domain M, and the number of NZCs K0. The UE may also receive the payload (P) in advance, L, N1, N2, O1, O2, Pv, β, Nsb, R.

[0362] Step 1: The UE calculates the payload size (P1) of the codebook part and the payload size (P2) of the AI ​​part (encoded bits) respectively. The payload size (P1) of the codebook part is calculated in the same way as the type II codebook in the beam domain. Specifically, it is calculated as shown in the following equation (7). In addition, the payload size (P2) of the AI ​​part is P-P1. P represents the total payload size of the CSI.

[0363] [Mathematical formula 7]

[0364]

[0365] Step 2: UE performs DFT, selects L beams, M extensions, and K0 NZCs. In this case, the basis of 2D-DFT can also be the same as Type I / Type II / Enhanced Type II. Alternatively, the 2D-DFT basis can also be a basis set by the NW (base station) or a new basis specified in the specification.

[0366] Step 3: The UE uses the encoder to generate the matrix (H LMK0 ' / W LMK0 ') for compression.

[0367] Step 4: The UE sends the beam domain codebook with payload size (P1) and the coded bits with payload size (P2) to the base station (gNB).

[0368] As the 2D-DFT basis and DFT basis of this embodiment, the same formula as any one of the following formula (8) (basis of type I single-panel codebook), the following formula (9) (basis of type I multi-panel codebook), and the following formula (10) (basis of type II codebook) can also be used.

[0369] [Mathematical formula 8]

[0370]

[0371] [Mathematical formula 9]

[0372]

[0373] [Formula 10]

[0374]

[0375] According to the third embodiment, it is possible to appropriately perform AI-based CSI compression using the settings and intermediate settings related to the payload of the received CSI.

[0376] <Fourth embodiment>

[0377] The UE receives the intermediate setting (second setting) and uses the AI / ML model to generate a codebook index ( Fig. 22 ). This enables the use of AI / ML search capabilities and reuse of current settings and feedback in the specification. The UE can also receive payload (P), L, N1, N2, O1, O2, P in advance. v , β, N sb , R is used as the intermediate setting.

[0378] Step 1: UE implements DFT. In this case, the basis of 2D-DFT can be the same as Type I / Type II / Enhanced Type II. Alternatively, the 2D-DFT basis can also be a basis set by the NW (base station) or a new basis specified in the specification.

[0379] Step 2: The UE selects L beams, M extensions, and K0 NZCs, and uses the AI / ML model to generate the corresponding codebook index.

[0380] Step 3: The UE sends the generated codebook index (type II / enhanced type II codebook index) to the base station (gNB).

[0381] According to the fourth embodiment, by transmitting the codebook index, the performance of the AI / ML model can be visualized.

[0382] <Supplement>

[0383] [Notification of information to UE]

[0384] The notification of arbitrary information (from the network (NW)) (e.g., base station (BS))) to the UE (in other words, the reception of arbitrary information from the BS in the UE) in the above-mentioned embodiments may also 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 signals), or a combination thereof.

[0385] When the notification is performed through MAC CE, the MAC CE may be identified by including a new logical channel ID (Logical Channel ID (LCID)) not specified in the existing standard in a MAC subheader.

[0386] In the case where the above notification is performed through DCI, the above notification may be performed through a specific field of the DCI, a Radio Network Temporary Identifier (RNTI) used in scrambling of a cyclic redundancy check (CRC) bit assigned to the DCI, the format of the DCI, etc.

[0387] In addition, the notification of arbitrary information to the UE in the above-mentioned embodiments may be performed periodically, semi-continuously, or aperiodically.

[0388] [Notification of information from UE]

[0389] The notification of arbitrary information from the UE (to the NW) in the above-mentioned implementation manner (in other words, the sending / reporting of arbitrary information from the UE to the BS) may also be performed using physical layer signaling (e.g., UCI), high-layer signaling (e.g., RRC signaling, MAC CE), specific signals / channels (e.g., PUCCH, PUSCH, PRACH, reference signals), or a combination thereof.

[0390] In the case where the above notification is performed through MAC CE, the MAC CE can also be identified by including a new LCID that is not specified in the existing standard in the MAC subheader.

[0391] When the notification is performed through UCI, the notification may be sent using PUCCH or PUSCH.

[0392] In addition, the notification of arbitrary information from the UE in the above-mentioned embodiments may be performed periodically, semi-continuously, or aperiodically.

[0393] [About application of each embodiment]

[0394] At least one of the above-mentioned embodiments may also be applied when a specific condition is met. The specific condition may be specified in the standard or notified to the UE / BS using high-layer signaling / physical layer signaling.

[0395] At least one of the above-mentioned implementation modes may also be applied only to UEs that report a specific UE capability (UE capability) or support the specific UE capability.

[0396] The specific UE capability may also represent specific processing / operation / control / information for at least one of the above-mentioned embodiments.

[0397] In addition, the above-mentioned specific UE capabilities can be capabilities that are applied throughout all frequencies (commonly regardless of frequency), or capabilities for each frequency (for example, one or a combination of cells, bands, band combinations, BWPs, component carriers, etc.), or capabilities for each frequency range (for example, frequency range 1 (Frequency Range 1 (FR1)), FR2, FR3, FR4, FR5, FR2-1, FR2-2), or capabilities for each subcarrier spacing (SubCarrier Spacing (SCS)), or capabilities for each feature set (Feature Set (FS)) or each component carrier feature set (Feature Set Per Component-carrier (FSPC)).

[0398] Furthermore, the specific UE capability may be a capability applicable to all duplex modes (commonly regardless of the duplex mode) or a capability applicable to each duplex mode (eg, time division duplex (TDD) or frequency division duplex (FDD)).

[0399] In addition, at least one of the above-mentioned embodiments may also be applied when the UE is configured / activated / triggered with specific information associated with the above-mentioned embodiments (or the operation of implementing the above-mentioned embodiments) through high-layer signaling / physical layer signaling. For example, the specific information may also be any RRC parameter for a specific version (e.g., Rel.18 / 19).

[0400] The UE may also apply operations such as Rel.15 / 16 when it does not support at least one of the above-mentioned specific UE capabilities or is not configured with the above-mentioned specific information.

[0401] (Note)

[0402] The following inventions are added to one embodiment of the present disclosure.

[0403] [Note 1]

[0404] A terminal having:

[0405] a receiving unit, receiving a first setting related to a payload of channel state information (CSI) and a second setting related to CSI feedback; and

[0406] The control unit controls CSI compression based on artificial intelligence (AI) based on the first setting and the second setting.

[0407] [Note 2]

[0408] A terminal as described in Appendix 1, wherein:

[0409] The first setting is included in a setting of a specific codebook type within the codebook setting, and is independent of settings of other codebook types.

[0410] [Note 3]

[0411] A terminal as described in Supplement 1 or Supplement 2, wherein:

[0412] The control unit calculates the payload of the compressed CSI based on the first setting, and determines a matrix applied to the CSI compression based on the second setting.

[0413] [Note 4]

[0414] A terminal as described in any one of Notes 1 to 3, wherein:

[0415] The second setting is a setting related to at least one of the number of beams, the number of delayed extensions, the number of antenna elements, the oversampling coefficient, the precoding vector, the subband number, the number of non-zero coefficients, the parameter for controlling the maximum number of non-zero coefficients, and the subband size.

[0416] (Wireless Communication System)

[0417] Hereinafter, a configuration of a wireless communication system according to an embodiment of the present disclosure will be described. In the wireless communication system, communication is performed using any one of the wireless communication methods according to the above-mentioned embodiments of the present disclosure or a combination thereof.

[0418] Fig.231 is a diagram showing an example of a schematic structure of a wireless communication system according to an embodiment. The wireless communication system 1 (may also be simply referred to as the system 1) may also be a system that implements communication using Long Term Evolution (LTE) standardized by the Third Generation Partnership Project (3GPP), the fifth generation mobile communication system New Radio (5GNR), or the like.

[0419] In addition, the wireless communication system 1 may also support dual connectivity (Multi-RAT Dual Connectivity (MR-DC)) between multiple radio access technologies (Radio Access Technology (RAT)). MR-DC may also include dual connectivity between LTE (Evolved Universal Terrestrial Radio Access (E-UTRA)) and NR (E-UTRA-NR Dual Connectivity (E-UTRA-NR Dual Connectivity (EN-DC))), dual connectivity between NR and LTE (NR-E-UTRA Dual Connectivity (NR-E-UTRA Dual Connectivity (NE-DC))), etc.

[0420] In EN-DC, the base station (eNB) of LTE (E-UTRA) is the master node (Master Node (MN)), and the base station (gNB) of NR is the secondary node (Secondary Node (SN)). In NE-DC, the base station (gNB) of NR is the MN, and the base station (eNB) of LTE (E-UTRA) is the SN.

[0421] The wireless communication system 1 may also support dual connectivity between multiple base stations within the same RAT (for example, dual connectivity (NR-NR Dual Connectivity (NN-DC)) where both MN and SN are NR base stations (gNB)).

[0422] The wireless communication system 1 may also include a base station 11 that forms a macro cell C1 with a relatively wide coverage, and a base station 12 (12a-12c) that is configured in the macro cell C1 and forms a small cell C2 that is narrower than the macro cell C1. The user terminal 20 may also be located in at least one cell. The configuration and number of each cell and user terminal 20 are not limited to the method shown in the figure. Hereinafter, when the base stations 11 and 12 are not distinguished, they are collectively referred to as base stations 10.

[0423] The user terminal 20 may be connected to at least one of the plurality of base stations 10. The user terminal 20 may use at least one of carrier aggregation (CA) using a plurality of component carriers (CC) and dual connectivity (DC).

[0424] Each CC may also be included in at least one of the first frequency band (Frequency Range 1 (FR1)) and the second frequency band (Frequency Range 2 (FR2)). The macro cell C1 may also be included in FR1, and the small cell C2 may also be included in FR2. For example, FR1 may be a frequency band below 6 GHz (below 6 GHz (sub-6 GHz)), and FR2 may be a frequency band higher than 24 GHz (above-24 GHz). In addition, the frequency bands and definitions of FR1 and FR2 are not limited to these. For example, FR1 may also correspond to a frequency band higher than FR2.

[0425] Furthermore, the user terminal 20 may perform communication using at least one of time division duplex (TDD) and frequency division duplex (FDD) in each CC.

[0426] Multiple base stations 10 may also be connected by wire (e.g., optical fiber based on Common Public Radio Interface (CPRI), X2 interface, etc.) or wireless (e.g., NR communication). For example, when NR communication between base stations 11 and 12 is used as a backhaul, the base station 11 corresponding to the upper station may also be referred to as an Integrated Access Backhaul (IAB) donor, and the base station 12 corresponding to the relay station (relay) may also be referred to as an IAB node.

[0427] The base station 10 may be connected to the core network 30 via other base stations 10 or directly. The core network 30 may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC).

[0428] The core network 30 may also include, for example, user plane functions (User Plane Function (UPF)), access and mobility management function (Access and Mobility management Function (AMF)), session management function (Session Management Function (SMF)), unified data management (Unified Data Management (UDM)), application function (Application Function (AF)), data network (Data Network (DN)), location management function (Location Management Function (LMF)), maintenance and operation management (Operation, Administration and Maintenance (Management) (OAM)) and other network functions (Network Functions (NF)). In addition, multiple functions may be provided by one network node. In addition, communication with an external network (e.g., the Internet) may also be carried out via the DN.

[0429] The user terminal 20 may also be a terminal that supports at least one of communication modes such as LTE, LTE-A, and 5G.

[0430] In the wireless communication system 1, a wireless access method based on orthogonal frequency division multiplexing (OFDM) may be used. For example, in at least one of the downlink (DL) and the uplink (UL), 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-FDMA), etc. may be used.

[0431] The radio access scheme may also be referred to as a waveform. In addition, in the wireless communication system 1, other radio access schemes (for example, other single-carrier transmission schemes, other multi-carrier transmission schemes) may be used as the radio access schemes for UL and DL.

[0432] In the wireless communication system 1, a downlink shared channel (Physical Downlink Shared Channel (PDSCH)), a broadcast channel (Physical Broadcast Channel (PBCH)), a downlink control channel (Physical Downlink Control Channel (PDCCH)), etc. shared by each user terminal 20 can also be used as a downlink channel.

[0433] In addition, in the wireless communication system 1, an uplink shared channel (Physical Uplink Shared Channel (PUSCH)), an uplink control channel (Physical Uplink Control Channel (PUCCH)), a random access channel (Physical Random Access Channel (PRACH)), etc. shared by each user terminal 20 can also be used as an uplink channel.

[0434] The PDSCH transmits user data, high-layer control information, and system information blocks (SIB). The PUSCH also transmits user data, high-layer control information, and the like. In addition, the PBCH also transmits the master information block (MIB).

[0435] The PDCCH may also transmit lower layer control information. The lower layer control information may include, for example, downlink control information (Downlink Control Information (DCI)) including scheduling information of at least one of the PDSCH and the PUSCH.

[0436] In addition, the DCI for scheduling the PDSCH may also be referred to as DL allocation, DL DCI, etc., and the DCI for scheduling the PUSCH may also be referred to as UL grant, UL DCI, etc. In addition, the PDSCH may also be rewritten as DL data, and the PUSCH may also be rewritten as UL data.

[0437] In the detection of PDCCH, the control resource set (CORESET) and the search space can also be used. CORESET corresponds to the resources for searching DCI. The search space corresponds to the search area and search method of PDCCH candidates. A CORESET can also be associated with one or more search spaces. The UE can also monitor the CORESET associated with a search space based on the search space setting.

[0438] A search space may also correspond to a PDCCH candidate corresponding to one or more aggregation levels. One or more search spaces may also be referred to as a search space set. In addition, the "search space", "search space set", "search space setting", "search space set setting", "CORESET", "CORESET setting" and the like in the present disclosure may also be rewritten mutually.

[0439] Through PUCCH, uplink control information (uplink control information (UCI)) including at least one of channel state information (CSI), delivery confirmation information (e.g., also called hybrid automatic repeat request confirmation (HARQ-ACK), ACK / NACK, etc.), and scheduling request (SR) can also be transmitted. Through PRACH, random access preambles for establishing a connection with a cell can also be transmitted.

[0440] In the present disclosure, downlink, uplink, etc. may be expressed without “link.” In addition, various channels may be expressed without “Physical” at the beginning.

[0441] In the wireless communication system 1, a synchronization signal (Synchronization Signal (SS)), a downlink reference signal (Downlink Reference Signal (DL-RS)), etc. may also be transmitted. In the wireless communication system 1, a cell-specific reference signal (Cell-specific Reference Signal (CRS)), a channel state information reference signal (CSI-RS), a demodulation reference signal (DeModulation Reference Signal (DMRS)), a positioning reference signal (Positioning Reference Signal (PRS)), a phase tracking reference signal (Phase Tracking Reference Signal (PTRS)), etc. may also be transmitted as DL-RS.

[0442] 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 also be referred to as SS / PBCH block, SS block (SS Block (SSB)), etc. In addition, SS, SSB, etc. may also be referred to as reference signals.

[0443] In addition, in the wireless communication system 1, as an uplink reference signal (Uplink Reference Signal (UL-RS)), a measurement reference signal (Sounding Reference Signal (SRS)), a demodulation reference signal (DMRS), etc. may also be transmitted. In addition, DMRS may also be called a user terminal specific reference signal (UE-specific Reference Signal).

[0444] (Base Station)

[0445] Fig.24 1 is a diagram showing an example of a structure of a base station involved in one embodiment. The base station 10 includes a control unit 110, a transmitting and receiving unit 120, a transmitting and receiving antenna 130, and a transmission path interface (transmission line interface) 140. In addition, the control unit 110, the transmitting and receiving unit 120, the transmitting and receiving antenna 130, and the transmission path interface 140 may each be provided with more than one.

[0446] In addition, in this example, the functional blocks of the characteristic parts in this embodiment are mainly shown, and it is also assumed that the base station 10 also has other functional blocks required for wireless communication. Part of the processing of each unit described below may also be omitted.

[0447] The control unit 110 controls the entire base station 10. The control unit 110 can be composed of a controller, a control circuit, and the like that are described based on common knowledge in the technical field to which the present disclosure relates.

[0448] The control unit 110 may also control signal generation, scheduling (e.g., resource allocation, mapping), etc. The control unit 110 may also control transmission and reception, measurement, etc. using the transmission and reception unit 120, the transmission and reception antenna 130, and the transmission path interface 140. The control unit 110 may also generate data, control information, sequences, etc. to be sent as signals, and forward them to the transmission and reception unit 120. The control unit 110 may also perform call processing (setting, release, etc.) of communication channels, state management of the base station 10, management of wireless resources, etc.

[0449] The transmitting and receiving unit 120 may also include a baseband unit 121, a radio frequency (RF) unit 122, and a measuring unit 123. The baseband unit 121 may also include a transmitting processing unit 1211 and a receiving processing unit 1212. The transmitting and receiving unit 120 may be composed of a transmitter / receiver, an RF circuit, a baseband circuit, a filter, a phase shifter (phase shifter), a measuring circuit, a transmitting and receiving circuit, etc., which are described based on the common knowledge in the technical field involved in the present disclosure.

[0450] The transmitting and receiving unit 120 may be configured as an integrated transmitting and receiving unit, or may be configured as a transmitting unit and a receiving unit. The transmitting unit may also be configured as a transmitting processing unit 1211 and an RF unit 122. The receiving unit may also be configured as a receiving processing unit 1212, an RF unit 122, and a measuring unit 123.

[0451] The transmitting / receiving antenna 130 can be constituted by an antenna described based on common knowledge in the technical field involved in the present disclosure, such as an array antenna.

[0452] The transmitting and receiving unit 120 may also transmit the above-mentioned downlink channel, synchronization signal, downlink reference signal, etc. The transmitting and receiving unit 120 may also receive the above-mentioned uplink channel, uplink reference signal, etc.

[0453] The transmitting and receiving unit 120 may also use digital beamforming (eg, precoding), analog beamforming (eg, phase rotation), etc. to form at least one of a transmitting beam and a receiving beam.

[0454] The sending and receiving unit 120 (sending processing unit 1211), for example, may also perform Packet Data Convergence Protocol (PDCP) layer processing, Radio Link Control (RLC) layer processing (e.g., RLC retransmission control), Medium Access Control (MAC) layer processing (e.g., HARQ retransmission control), etc. on the data, control information, etc. obtained from the control unit 110, to generate a bit string to be sent.

[0455] The transmitting and receiving unit 120 (transmitting processing unit 1211) may also perform channel coding (which may also include error correction coding), modulation, mapping, filter processing (filtering processing), discrete Fourier transform (DFT) processing (as needed), inverse fast Fourier transform (IFFT) processing), precoding, digital-to-analog conversion and other transmission processing on the bit string to be transmitted, and output a baseband signal.

[0456] The transmitting and receiving unit 120 (RF unit 122 ) may also perform modulation, filter processing, amplification, etc. on the baseband signal to a radio frequency band, and transmit the signal in the radio frequency band via the transmitting and receiving antenna 130 .

[0457] On the other hand, the transmission and reception unit 120 (RF unit 122 ) may also perform amplification, filter processing, demodulation into a baseband signal, etc. on the signal in the radio frequency band received by the transmission and reception antenna 130 .

[0458] The transmitting and receiving unit 120 (receiving processing unit 1212) may also apply receiving processing such as analog-to-digital conversion, Fast Fourier Transform (FFT) processing, Inverse Discrete Fourier Transform (IDFT) processing (as needed), filter processing, demapping, demodulation, decoding (which may also include error correction decoding), MAC layer processing, RLC layer processing, and PDCP layer processing to the acquired baseband signal to obtain user data, etc.

[0459] The transmitting and receiving unit 120 (the measuring unit 123) may also implement measurements related to the received signal. For example, the measuring unit 123 may also perform radio resource management (RRM) measurements, channel state information (CSI) measurements, etc. based on the received signal. The measuring unit 123 may also measure received power (e.g., reference signal received power (RSRP)), received 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 also be output to the control unit 110.

[0460] The transmission path interface 140 can also send and receive signals (return signaling) between devices included in the core network 30 (for example, a network node providing NF), other base stations 10, etc., and can also obtain and transmit user data (user plane data) and control plane data for the user terminal 20.

[0461] In addition, the transmission unit and the reception unit of the base station 10 in the present disclosure may also be constituted by at least one of the transmission and reception unit 120 , the transmission and reception antenna 130 , and the transmission path interface 140 .

[0462] In addition, the transmitting and receiving unit 120 may also transmit a first configuration related to a payload of channel state information (CSI) and a second configuration related to CSI feedback.

[0463] The control unit 110 may also control reception of the compressed CSI when CSI compression based on artificial intelligence (AI) is controlled based on the first setting and the second setting.

[0464] (User terminal)

[0465] Fig.252 is a diagram showing an example of a configuration of a user terminal according to an embodiment. The user terminal 20 includes a control unit 210, a transmitting / receiving unit 220, and a transmitting / receiving antenna 230. In addition, the control unit 210, the transmitting / receiving unit 220, and the transmitting / receiving antenna 230 may each be provided with one or more.

[0466] In addition, in this example, the functional blocks of the characteristic parts in this embodiment are mainly shown, and it is also conceivable that the user terminal 20 also has other functional blocks required for wireless communication. Part of the processing of each unit described below may be omitted.

[0467] The control unit 210 controls the entire user terminal 20. The control unit 210 can be composed of a controller, a control circuit, and the like that are described based on common knowledge in the technical field to which the present disclosure relates.

[0468] The control unit 210 may also control signal generation, mapping, etc. The control unit 210 may also control transmission and reception, measurement, etc. using the transmission and reception unit 220 and the transmission and reception antenna 230. The control unit 210 may also generate data, control information, sequences, etc. to be transmitted as signals, and forward them to the transmission and reception unit 220.

[0469] The transmitting and receiving unit 220 may also include a baseband unit 221, an RF unit 222, and a measuring unit 223. The baseband unit 221 may also include a transmitting processing unit 2211 and a receiving processing unit 2212. The transmitting and receiving unit 220 may be composed of a transmitter / receiver, an RF circuit, a baseband circuit, a filter, a phase shifter, a measuring circuit, a transmitting and receiving circuit, etc., which are described based on the common knowledge in the technical field involved in the present disclosure.

[0470] The transmitting and receiving unit 220 may be configured as an integrated transmitting and receiving unit, or may be configured as a transmitting unit and a receiving unit. The transmitting unit may also be configured as a transmitting processing unit 2211 and an RF unit 222. The receiving unit may also be configured as a receiving processing unit 2212, an RF unit 222, and a measuring unit 223.

[0471] The transmitting / receiving antenna 230 can be constituted by an antenna described based on common knowledge in the technical field involved in the present disclosure, such as an array antenna.

[0472] The transmitting and receiving unit 220 may also receive the above-mentioned downlink channel, synchronization signal, downlink reference signal, etc. The transmitting and receiving unit 220 may also transmit the above-mentioned uplink channel, uplink reference signal, etc.

[0473] The transmitting and receiving unit 220 may also use digital beamforming (eg, precoding), analog beamforming (eg, phase rotation), etc. to form at least one of a transmitting beam and a receiving beam.

[0474] The sending and receiving unit 220 (sending processing unit 2211) may also perform PDCP layer processing, RLC layer processing (e.g., RLC retransmission control), MAC layer processing (e.g., HARQ retransmission control), etc. on the data, control information, etc. obtained from the control unit 210 to generate a bit string to be sent.

[0475] The transmitting and receiving unit 220 (transmitting processing unit 2211) may also perform channel coding (which may also include error correction coding), modulation, mapping, filter processing, DFT processing (as needed), IFFT processing, precoding, digital-to-analog conversion and other transmission processing on the bit string to be transmitted, and output a baseband signal.

[0476] In addition, whether to apply DFT processing may also be based on the setting of transform precoding. For a certain channel (e.g., PUSCH), when transform precoding is valid (enabled), the transmitting and receiving unit 220 (transmitting processing unit 2211) may also perform DFT processing as the above-mentioned transmission processing in order to transmit the channel using a DFT-s-OFDM waveform. Otherwise, the transmitting and receiving unit 220 (transmitting processing unit 2211) may also perform DFT processing as the above-mentioned transmission processing without performing DFT processing.

[0477] The transmitting and receiving unit 220 (RF unit 222 ) may also perform modulation, filter processing, amplification, etc. on the baseband signal to a radio frequency band, and transmit the signal in the radio frequency band via the transmitting and receiving antenna 230 .

[0478] On the other hand, the transmission and reception unit 220 (RF unit 222 ) may perform amplification, filter processing, demodulation into a baseband signal, etc. on the signal in the radio frequency band received by the transmission and reception antenna 230 .

[0479] The sending and receiving unit 220 (receiving processing unit 2212) can also apply receiving processing such as analog-to-digital conversion, FFT processing, IDFT processing (as needed), filter processing, demapping, demodulation, decoding (which may also include error correction decoding), MAC layer processing, RLC layer processing, and PDCP layer processing to the obtained baseband signal to obtain user data, etc.

[0480] The transmitting and receiving unit 220 (measuring unit 223) may also perform measurements related to the received signal. For example, the measuring unit 223 may also perform RRM measurement, CSI measurement, etc. based on the received signal. The measuring unit 223 may also measure the received power (e.g., RSRP), the received quality (e.g., RSRQ, SINR, SNR), the signal strength (e.g., RSSI), the propagation path information (e.g., CSI), etc. The measurement results may also be output to the control unit 210.

[0481] In addition, the transmitting unit and the receiving unit of the user terminal 20 in the present disclosure may also be composed of at least one of the transmitting and receiving unit 220 and the transmitting and receiving antenna 230 .

[0482] In addition, the transmitting and receiving unit 220 may also receive a first configuration related to a payload of channel state information (CSI) and a second configuration related to CSI feedback.

[0483] The control unit 210 may also control CSI compression based on artificial intelligence (AI) based on the first setting and the second setting. The control unit 210 may also calculate the payload of the compressed CSI based on the first setting and determine the matrix applied to the CSI compression based on the second setting.

[0484] The first setting may also be included in a setting of a specific codebook type within the codebook setting, independent of settings of other codebook types.

[0485] The second setting may also be a setting related to at least one of the number of beams, the number of delayed extensions, the number of antenna elements, the oversampling coefficient, the precoding vector, the subband number, the number of non-zero coefficients, the control parameter for the maximum number of non-zero coefficients, and the subband size.

[0486] (Hardware structure)

[0487] In addition, the block diagram used in the description of the above-mentioned embodiment shows a block of a functional unit. These functional blocks (structural units) are implemented by any combination of at least one of hardware and software. In addition, the implementation method of each functional block is not particularly limited. That is, each functional block can be implemented by a device that is physically or logically combined, or two or more physically or logically separated devices can be directly or indirectly connected (for example, by wire, wireless, etc.) and implemented by these multiple devices. The functional block can also be implemented by combining the above-mentioned one device or the above-mentioned multiple devices with software.

[0488] Here, the functions include judging, deciding, determining, calculating, calculating, processing, deriving, investigating, searching, confirming, receiving, sending, outputting, accessing, solving, selecting, selecting, establishing, comparing, assuming, expecting, regarding, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, assigning, etc., but are not limited to these. For example, a functional block (structural unit) that implements a sending function may also be referred to as a transmitting unit, a transmitter, etc. Any one of them is as described above, and the implementation method is not particularly limited.

[0489] For example, a base station, a user terminal, etc. in one embodiment of the present disclosure may also function as a computer that performs processing of the wireless communication method of the present disclosure. Fig.26 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0490] In addition, in the present disclosure, the terms such as device, circuit, equipment, section, and unit can be interchanged. 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 may exclude some of the devices.

[0491] For example, only one processor 1001 is shown, but there may be multiple processors. In addition, the processing may be performed by one processor, or may be performed by two or more processors simultaneously, sequentially, or in other ways. In addition, the processor 1001 may also be implemented by one or more chips.

[0492] The functions of the base station 10 and the user terminal 20 are realized, for example, by reading specific software (program) into hardware such as the processor 1001 and the memory 1002, so that the processor 1001 performs calculations and controls communication via the communication device 1004, or controls at least one of the reading and writing of data in the memory 1002 and the storage 1003.

[0493] The processor 1001 controls the entire computer by, for example, operating an operating system. The processor 1001 may also be composed of a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, a register, etc. For example, at least a part of the control unit 110 (210), the transmission and reception unit 120 (220), etc. described above may also be implemented by the processor 1001.

[0494] In addition, the processor 1001 reads a program (program code), a software module, data, etc. from at least one of the storage 1003 and the communication device 1004 to the memory 1002, and performs various processes based on them. As a program, a program that causes a computer to perform at least a part of the operations described in the above-mentioned embodiments can be used. For example, the control unit 110 (210) can also be implemented by a control program stored in the memory 1002 and operated in the processor 1001, and the other functional blocks can also be implemented in the same way.

[0495] The memory 1002 may also be a computer-readable recording medium, for example, composed of at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), or other appropriate storage media. The memory 1002 may also be referred to as a register, a cache, a main memory (main storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing the wireless communication method involved in one embodiment of the present disclosure.

[0496] The storage 1003 may also be a computer-readable recording medium, such as a flexible disk, a floppy disk, an optical disk (such as a compact disk (Compact Disc ROM (CD-ROM)), a digital versatile disk, a Blu-ray (Blu-ray) (registered trademark) disk), a removable disk, a hard disk drive, a smart card, a flash memory device (such as a card, a stick, a key drive), a magnetic stripe, a database, a server, or at least one of other appropriate storage media. The storage 1003 may also be referred to as an auxiliary storage device.

[0497] The communication device 1004 is hardware (transmitting and 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, a network controller, a network card, a communication module, etc. In order to realize at least one of frequency division duplex (Frequency Division Duplex (FDD)) and time division duplex (Time Division Duplex (TDD)), the communication device 1004 may also be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. For example, the above-mentioned transmitting and receiving unit 120 (220), the transmitting and receiving antenna 130 (230), etc. may also be realized by the communication device 1004. The transmitting and receiving unit 120 (220) may also be realized by physically or logically separating the transmitting unit 120a (220a) and the receiving unit 120b (220b).

[0498] The input device 1005 is an input device that receives input from the outside (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.). The output device 1006 is an output device that performs output to the outside (e.g., a display, a speaker, a light emitting diode (LED) lamp, etc.). In addition, the input device 1005 and the output device 1006 may also be an integrated structure (e.g., a touch panel).

[0499] In addition, the processor 1001, the memory 1002 and other devices are connected via a bus 1007 for communicating information. The bus 1007 may be configured as a single bus or may be configured as different buses between the devices.

[0500] In addition, the base station 10 and the user terminal 20 may also 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 the hardware may be used to implement a part or all of each functional block. For example, the processor 1001 may also be implemented using at least one of these hardware.

[0501] (Variation)

[0502] In addition, the terms described in the present disclosure and the terms required for understanding the present disclosure may also be rewritten as terms having the same or similar meanings. For example, channels, code elements, and signals (signals or signaling) may also be rewritten with each other. In addition, a signal may also be a message. A reference signal may also be referred to as RS, and may also be referred to as a pilot, a pilot signal, etc. depending on the applied standard. In addition, a component carrier (CC) may also be referred to as a cell, a frequency carrier, a carrier frequency, etc.

[0503] A radio frame may also be composed of one or more periods (frames) in the time domain. Each period (frame) of the one or more periods (frames) constituting a radio frame may also be referred to as a subframe. Further, a subframe may also be composed of one or more time slots in the time domain. A subframe may also be a fixed time length (e.g., 1 ms) that is not dependent on a parameter set (numerology).

[0504] Here, the parameter set may also be a communication parameter applied in at least one of the transmission and reception of a certain signal or channel. For example, the parameter set may also represent at least one of the subcarrier spacing (SCS), bandwidth, symbol length, cyclic prefix length, transmission time interval (TTI), the number of symbols per TTI, wireless frame structure, specific filtering processing performed by the transmitter and receiver in the frequency domain, specific windowing processing performed by the transmitter and receiver in the time domain, etc.

[0505] A time slot may also be composed of one or more symbols (Orthogonal Frequency Division Multiplexing (OFDM) symbols, Single Carrier Frequency Division Multiple Access (SC-FDMA) symbols, etc.) in the time domain. In addition, a time slot may also be a time unit based on a parameter set.

[0506] A time slot may also contain multiple mini-slots. Each mini-slot may also be composed of one or more symbols in the time domain. In addition, a mini-slot may also be referred to as a sub-slot. A mini-slot may also be composed of a smaller number of symbols than a time slot. A PDSCH (or PUSCH) transmitted in a time unit larger than a mini-slot may also be referred to as a PDSCH (PUSCH) mapping type A. A PDSCH (or PUSCH) transmitted using a mini-slot may also be referred to as a PDSCH (PUSCH) mapping type B.

[0507] Radio frames, subframes, time slots, mini-time slots, and symbols all represent time units for transmitting signals. Radio frames, subframes, time slots, mini-time slots, and symbols may also be referred to by their respective names. In addition, time units such as frames, subframes, time slots, mini-time slots, and symbols in the present disclosure may also be replaced with each other.

[0508] For example, a subframe may be referred to as a TTI, a plurality of consecutive subframes may be referred to as a TTI, and a time slot or a mini time slot may be referred to as a TTI. That is, at least one of a subframe and a TTI may be a subframe (1 ms) in existing LTE, a period shorter than 1 ms (for example, 1-13 symbols), or a period longer than 1 ms. In addition, the unit representing a TTI may be referred to as a time slot, a mini time slot, etc. instead of a subframe.

[0509] Here, TTI refers to, for example, the minimum time unit for scheduling in wireless communication. For example, in the LTE system, the base station schedules each user terminal to allocate wireless resources (frequency bandwidth, transmission power, etc. that can be used in each user terminal) in TTI units. In addition, the definition of TTI is not limited to this.

[0510] TTI can also be a transmission time unit for a data packet (transport block), code block, code word, etc. that has been channel-coded, and can also be a processing unit for scheduling, link adaptation, etc. In addition, when TTI is given, the time interval (for example, the number of symbols) to which a transport block, code block, code word, etc. is actually mapped can also be shorter than the TTI.

[0511] In addition, when a time slot or a mini time slot is called a TTI, one or more TTIs (i.e., one or more time slots or one or more mini time slots) may also be the minimum time unit of scheduling. In addition, the number of time slots (mini time slots) constituting the minimum time unit of scheduling may also be controlled.

[0512] A TTI having a time length of 1 ms may also be referred to as a normal TTI (TTI in 3GPP Rel.8-12), a standard TTI, a long TTI, a normal subframe, a standard subframe, a long subframe, a time slot, etc. A TTI shorter than a normal TTI may also be referred to as a shortened TTI, a short TTI, a partial TTI (partial or fractional TTI), a shortened subframe, a short subframe, a mini time slot, a sub time slot, a time slot, etc.

[0513] In addition, a long TTI (eg, normal TTI, subframe, etc.) may be rewritten as a TTI having a time length exceeding 1 ms, and a short TTI (eg, shortened TTI, etc.) may be rewritten as a TTI having a TTI length shorter than that of a long TTI and longer than 1 ms.

[0514] Resource Block (RB) is a resource allocation unit in the time domain and frequency domain, and may also include one or more consecutive subcarriers (subcarriers) in the frequency domain. The number of subcarriers included in an RB may also be the same regardless of the parameter set, for example, it may be 12. The number of subcarriers included in an RB may also be determined based on the parameter set.

[0515] In addition, an RB may also include one or more symbols in the time domain, and may also be the length of a slot, a mini-slot, a subframe, or a TTI. A TTI, a subframe, etc. may also be composed of one or more resource blocks, respectively.

[0516] In addition, one or more RBs may also be referred to as a physical resource block (Physical RB (PRB)), a sub-carrier group (Sub-Carrier Group (SCG)), a resource element group (Resource Element Group (REG)), a PRB pair, an RB pair, etc.

[0517] In addition, a resource block may be composed of one or more resource elements (RE). For example, one RE may be a radio resource region of one subcarrier and one symbol.

[0518] Bandwidth Part (BWP) (also referred to as partial bandwidth, etc.) can also represent a subset of contiguous common RBs (common resource blocks) for a parameter set in a carrier. Here, common RBs can also be identified by the index of the RB based on the common reference point of the carrier. PRBs can also be defined in a BWP and numbered within the BWP.

[0519] The BWP may include a UL BWP (BWP for UL) and a DL BWP (BWP for DL). For a UE, one or more BWPs may be configured in one carrier.

[0520] At least one of the set BWPs may be activated, and the UE may not assume that it will transmit or receive a specific signal / channel other than the activated BWP. In addition, "cell", "carrier", etc. in the present disclosure may also be rewritten as "BWP".

[0521] In addition, the above-mentioned structures such as radio frames, subframes, time slots, mini-time slots and symbols are only examples. For example, the number of subframes included in a radio frame, the number of time slots per subframe or radio frame, the number of mini-time slots included in a time slot, the number of symbols and RBs included in a time slot or mini-time slot, the number of subcarriers included in an RB, the number of symbols in a TTI, the symbol length, and the cyclic prefix (CP) length can be changed in various ways.

[0522] In addition, the information, parameters, etc. described in the present disclosure may be represented by absolute values, relative values ​​relative to a specific value, or other corresponding information. For example, wireless resources may also be indicated by a specific index.

[0523] In the present disclosure, the names used for parameters, etc. are not limiting in all respects. Furthermore, the mathematical formulas, etc. using these parameters may be different from those explicitly disclosed in the present disclosure. Various channels (PUCCH, PDCCH, etc.) and information elements can be identified by any suitable names, and therefore, the various names assigned to these various channels and information elements are not limiting in all respects.

[0524] Information, signals, etc. described in the present disclosure may also be represented using any of a variety of different techniques. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be mentioned throughout the above description may also be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any combination thereof.

[0525] In addition, information, signals, etc. can be output in at least one of the following directions: from a higher layer (upper layer) to a lower layer (lower layer), and from a lower layer to a higher layer. Information, signals, etc. can also be input and output via multiple network nodes.

[0526] The input and output information, signals, etc. may be stored in a specific location (e.g., a memory), or may be managed using a management table. The input and output information, signals, etc. may be overwritten, updated, or added. The output information, signals, etc. may also be deleted. The input information, signals, etc. may also be sent to other devices.

[0527] The notification of information is not limited to the methods / implementations described in the present disclosure, and may also be performed by other methods. For example, the notification of information in the present disclosure may also be implemented through physical layer signaling (e.g., downlink control information (Downlink Control Information (DCI)), uplink control information (Uplink Control Information (UCI))), high-layer signaling (e.g., Radio Resource Control (RRC) signaling, broadcast information (Master Information Block (MIB)), System Information Block (SIB), etc.), Medium Access Control (MAC) signaling), other signals, or a combination thereof.

[0528] In addition, physical layer signaling may also be referred to as layer 1 / layer 2 (Layer 1 / Layer 2 (L1 / L2)) control information (L1 / L2 control signal), L1 control information (L1 control signal), etc. In addition, RRC signaling may also be referred to as an RRC message, such as an RRC connection establishment (RRC Connection Setup) message, an RRC connection reconstruction (RRC Connection Reconfiguration) message, etc. In addition, MAC signaling may also be notified using, for example, a MAC control element (MACControl Element (CE)).

[0529] Furthermore, notification of specific information (eg, notification of “it is X”) is not limited to explicit notification, but may be performed implicitly (eg, by not notifying the specific information or by notifying other information).

[0530] The determination may be made using a value represented by one bit (0 or 1), a true or false value (Boolean value) represented by true or false, or by comparison of numerical values ​​(eg, comparison with a specific value).

[0531] Whether software is called software, firmware, middle-ware, microcode, hardware description language, or other names, it should be broadly interpreted as meaning instructions, instruction sets, code, code segments, program code, program, sub-program, software module, application, software application, software package, routine, sub-routine, object, executable files, execution thread, procedure, function, etc.

[0532] In addition, software, instructions, information, etc. may also be sent and received via a transmission medium. For example, when the software is sent from a website, server, or other remote source using at least one of wired technology (coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), etc.) and wireless technology (infrared, microwave, etc.), at least one of these wired technology and wireless technology is included in the definition of transmission medium.

[0533] The terms "system" and "network" used in the present disclosure can be used interchangeably. "Network" may also refer to a device (eg, a base station) included in the network.

[0534] In the present 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", "antenna port group", "layer", "number of layers", "rank", "resource", "resource set", "resource group", "beam", "beam width", "beam angle", "antenna", "antenna element", and "panel" can be used interchangeably.

[0535] In the present 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" can be used interchangeably. There are also cases where base stations are referred to by terms such as macro cell, small cell, micro cell, and pico cell.

[0536] A base station can accommodate one or more (for example, three) cells. When a base station accommodates multiple cells, the overall coverage area of ​​the base station can be divided into multiple smaller areas, and each smaller area can also provide communication services through a base station subsystem (for example, a small base station for indoor use (Remote Radio Head (RRH))). Terms such as "cell" or "sector" refer to a part or the entirety of the coverage area of ​​at least one of a base station and a base station subsystem that provides communication services within the coverage area.

[0537] In the present disclosure, the base station sending information to the terminal may also be rewritten with the base station instructing the terminal to control / operate based on the information.

[0538] In the present disclosure, terms such as “mobile station (MS)”, “user terminal”, “user device (User Equipment (UE))”, and “terminal” can be used interchangeably.

[0539] A mobile station may also be referred to as 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, hand set, user agent, mobile client, client or several other appropriate terms.

[0540] At least one of the base station and the mobile station may also be referred to as a transmission device, a reception device, a wireless communication device, etc. In addition, at least one of the base station and the mobile station may be a device mounted on a moving object, a moving object body, etc.

[0541] The mobile body refers to a movable object, and the moving speed is arbitrary, and of course it also includes the situation where the mobile body stops. The mobile body includes, for example, vehicles, transport vehicles, cars, automatic two-wheeled vehicles (motorcycles), bicycles, connected cars, loading shovels, bulldozers, wheel loaders, dump trucks, forklifts, trains, buses, trolleys, rickshaws, ships (ships and other watercrafts), airplanes, rockets, artificial satellites, drones, multi-rotor aircraft, quadcopters, balloons and objects carried on them, but are not limited to these. In addition, the mobile body can also be a mobile body that drives autonomously based on operating instructions.

[0542] The mobile object may be a means of transportation (e.g., a vehicle, an airplane, etc.), a mobile object that moves unmanned (e.g., a drone, an autonomous vehicle, etc.), or a robot (manned or unmanned). In addition, at least one of the base station and the mobile station may include a device that does not necessarily move when performing communication operations. For example, at least one of the base station and the mobile station may also be an Internet of Things (IoT) device such as a sensor.

[0543] Fig. 27 1 is a diagram showing an example of a vehicle according to an 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, an air 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.

[0544] The driving unit 41 is composed of at least one of an engine, a motor, or a combination of an engine and a motor. The steering unit 42 is composed of at least a steering wheel (also called a handlebar), and steers 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.

[0545] The electronic control unit 49 is composed of a microprocessor 61, a memory (ROM, RAM) 62, and a communication port (for example, an input / output (IO) port) 63. Signals from various sensors 50-58 provided in the vehicle are input to the electronic control unit 49. The electronic control unit 49 may also be referred to as an electronic control unit (ECU).

[0546] The signals from the various sensors 50-58 include a current signal from a current sensor 50 for sensing the current of the motor, a rotation speed signal of the front wheels 46 / rear wheels 47 obtained by a rotation speed sensor 51, an air pressure signal of the front wheels 46 / rear wheels 47 obtained by an air pressure sensor 52, a vehicle speed signal obtained by a vehicle speed sensor 53, an acceleration signal obtained by an acceleration sensor 54, a depression amount signal of the accelerator pedal 43 obtained by an accelerator pedal sensor 55, a depression amount signal of the brake pedal 44 obtained by a brake pedal sensor 56, an operation signal of the shift lever 45 obtained by a shift lever sensor 57, a detection signal for detecting obstacles, vehicles, pedestrians, etc. obtained by an object detection sensor 58, and the like.

[0547] The information service unit 59 is composed of various devices such as a vehicle navigation system, an audio system, a speaker, a display, a television, and a radio for providing (outputting) various information such as driving information, traffic information, and entertainment information, and one or more ECUs for controlling these devices. The information service unit 59 uses information obtained from an external device via the communication module 60, etc. to provide various information / services (for example, multimedia information / multimedia services) to the occupants of the vehicle 40.

[0548] The information service unit 59 may include input devices for accepting input from the outside (e.g., keyboard, mouse, microphone, switch, button, sensor, touch panel, etc.), and may also include output devices for implementing output to the outside (e.g., display, speaker, LED light, touch panel, etc.).

[0549] The driving assistance system unit 64 is composed of various devices for providing functions for preventing accidents or reducing the driving load of the driver, such as millimeter wave radar, light detection and ranging (LiDAR), camera, positioning device (for example, Global Navigation Satellite System (GNSS)), map information (for example, high-precision (High Definition (HD)) map, autonomous vehicle (AV) map, etc.), gyroscope system (for example, inertial measurement unit (Inertial Measurement Unit (IMU))), inertial navigation unit (Inertial Navigation System (INS)), etc.), artificial intelligence (Artificial Intelligence (AI)) chip, AI processor, and one or more ECUs that control these devices. In addition, the driving assistance system unit 64 sends and receives various information via the communication module 60 and realizes the driving assistance function or the autonomous driving function.

[0550] The communication module 60 can communicate with the microprocessor 61 and the structural elements of the vehicle 40 via the communication port 63. For example, the communication module 60 transmits and receives data (information) between the drive unit 41, the steering unit 42, the accelerator pedal 43, the brake pedal 44, the shift lever 45, the left and right front wheels 46, the left and right rear wheels 47, the axle 48, the microprocessor 61 and the memory (ROM, RAM) 62 in the electronic control unit 49, and the various sensors 50-58 provided in the vehicle 40 via the communication port 63.

[0551] The communication module 60 can be controlled by the microprocessor 61 of the electronic control unit 49, and is a communication device that can communicate with an external device. For example, various information is sent and received with the external device via wireless communication. The communication module 60 can also be located either inside or outside the electronic control unit 49. The external device can also be, for example, the above-mentioned base station 10, user terminal 20, etc. In addition, the communication module 60 can also be, for example, at least one of the above-mentioned base station 10 and user terminal 20 (it can also function as at least one of the base station 10 and user terminal 20).

[0552] The communication module 60 may also transmit at least one of the signals from the various sensors 50-58 input to the electronic control unit 49, information obtained based on the signals, and information based on input from the outside (user) obtained via the information service unit 59 to an external device via wireless communication. The electronic control unit 49, the various sensors 50-58, the information service unit 59, etc. may also be referred to as an input unit that receives input. For example, the PUSCH transmitted through the communication module 60 may also include information based on the above input.

[0553] The communication module 60 receives various information (traffic information, signal information, vehicle-to-vehicle information, etc.) transmitted from an external device, and displays it to the information service unit 59 provided in the vehicle. The information service unit 59 may also be referred to as an output unit for outputting information (for example, outputting information to a display, a speaker, etc. based on the PDSCH received by the communication module 60 (or data / information decoded from the PDSCH)).

[0554] In addition, the communication module 60 stores various information received from the external device in the memory 62 that can be used by the microprocessor 61. The microprocessor 61 can also control the drive unit 41, the steering unit 42, the accelerator pedal 43, the brake pedal 44, the shift lever 45, the left and right front wheels 46, the left and right rear wheels 47, the axle 48, the various sensors 50-58, etc., which are provided in the vehicle 40, based on the information stored in the memory 62.

[0555] In addition, the base station in the present disclosure may also be rewritten as a user terminal. For example, the various methods / implementations of the present disclosure may also be applied to a structure in which the communication between a base station and a user terminal is rewritten as communication between multiple user terminals (for example, it may also be referred to as device-to-device (D2D)), vehicle-to-everything (V2X), etc.). In this case, it may also be set as a structure in which the user terminal 20 has the functions of the above-mentioned base station 10. In addition, terms such as "uplink" and "downlink" may also be rewritten as terms corresponding to inter-terminal communication (for example, "sidelink"). For example, uplink channels, downlink channels, etc. may also be rewritten as sidelink channels.

[0556] Likewise, the user terminal in the present disclosure may be rewritten as a base station. In this case, the base station 10 may have the functions of the user terminal 20 described above.

[0557] In the present disclosure, operations are assumed to be performed by a base station, and sometimes by its upper node depending on the situation. Obviously, in a network including one or more network nodes having a base station, various operations performed for communication with a terminal can be performed by a base station, one or more network nodes other than the base station (for example, Mobility Management Entity (MME)), Serving-Gateway (S-GW), etc., but not limited to these), or a combination thereof.

[0558] The various methods / implementations described in this disclosure may be used individually or in combination, and may be used in a switched manner as the method is executed. In addition, the processing procedures, sequences, flow charts, etc. of the various methods / implementations described in this disclosure may be reversed in order as long as they are not contradictory. For example, for the methods described in this disclosure, the elements of various steps are presented in an illustrative order, but are not limited to the specific order presented.

[0559] The various modes / implementations described in the present disclosure may be applied to 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 (x is, for example, an integer or a 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 (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), systems using other appropriate wireless communication methods, and next-generation systems based on these enhancements, revisions, productions, or regulations. In addition, multiple systems may be combined (for example, LTE or LTE-A, combination with 5G, etc.) for application.

[0560] The phrase “based on” used in the present disclosure does not mean “based only on” unless otherwise specified. In other words, the phrase “based on” means both “based only on” and “based at least on”.

[0561] Any reference to an element using the terms "first", "second", etc. used in this disclosure does not fully define the amount or order of these elements. These terms can be used in this disclosure as a convenient method to distinguish between two or more elements. Therefore, reference to the first and second elements does not mean that only two elements can be used or that the first element must take precedence over the second element in some form.

[0562] The term "determining" used in this disclosure may include a variety of operations. For example, "determining" may also refer to situations where judging, calculating, computing, processing, deriving, investigating, looking up (e.g., searching in a table, database or other data structure), ascertaining, etc. are regarded as performing "determining".

[0563] In addition, “judgment (decision)” may also refer to situations where receiving (e.g., receiving information), transmitting (e.g., sending information), input (input), output (output), accessing (e.g., accessing data in a memory), etc. are regarded as making a “judgment (decision)”.

[0564] In addition, "judgment (decision)" can also be regarded as a situation where resolving, selecting, choosing, establishing, comparing, etc. are regarded as "judgment (decision)". That is, "judgment (decision)" can also be regarded as a situation where some actions are regarded as "judgment (decision)".

[0565] In addition, "judge (decide)" can also be rewritten as "assuming (assuming)", "expecting (expecting)", "considering (considering)" and so on.

[0566] The “maximum transmit power” described in the present disclosure may refer to the maximum value of the transmit power, the nominal maximum transmit power (the nominal UE maximum transmit power), or the rated maximum transmit power (the rated UE maximum transmit power).

[0567] The terms "connected", "coupled", or all their variations used in this disclosure refer to all direct or indirect connections or combinations between two or more elements, and may include the situation where one or more intermediate elements exist between two elements that are "connected" or "coupled" to each other. The combination or connection between elements may be physical, logical, or a combination thereof. For example, "connection" may also be rewritten as "access".

[0568] In the present disclosure, when two elements are connected, it is possible to consider being "connected" or "combined" to each other using one or more wires, cables, printed electrical connections, etc., and as several non-limiting and non-inclusive examples, being "connected" or "combined" to each other using electromagnetic energy with a wavelength in the wireless frequency domain, microwave region, light (both visible and invisible) region, etc.

[0569] In the present disclosure, the term "A is different from B" may also mean "A and B are different from each other". In addition, the term may also mean "A and B are different from C, respectively". The terms "separate" and "combined" may also be interpreted in the same manner as "different".

[0570] When the terms “include,” “including,” and variations thereof are used in the present disclosure, these terms have an inclusive meaning, similar to the term “comprising.” Furthermore, the term “or” used in the present disclosure does not have an exclusive OR meaning.

[0571] In the present disclosure, when an article is added by translation like a, an, and the in English, for example, the present disclosure may also include a case where the noun following the article is in plural form.

[0572] In the present disclosure, "below", "less than", "above", "more than", "equal to", etc. can also be rewritten with each other. In addition, in the present disclosure, sentences meaning "good", "bad", "big", "small", "high", "low", "early", "late", "wide", "narrow", etc. can also be rewritten with each other without being limited to the original degree, comparative degree and superlative degree. In addition, in the present disclosure, sentences meaning "good", "bad", "big", "small", "high", "low", "early", "late", "wide", "narrow", etc. can also be rewritten with each other as expressions attached with "ith" (i is an arbitrary integer) without being limited to the original degree, comparative degree and superlative degree (for example, "highest" can also be rewritten with "i-th highest").

[0573] In the present disclosure, “of”, “for”, “regarding”, “related to”, “associated with”, etc. may also be replaced by each other.

[0574] The invention involved in the present disclosure has been described in detail above, but it is obvious to those skilled in the art that the invention involved in the present disclosure is not limited to the embodiments described in the present disclosure. The invention involved in the present disclosure can be implemented as a modified and altered mode without departing from the gist and scope of the invention determined based on the description of the claims. Therefore, the description of the present disclosure is for the purpose of illustrative description and does not have any limiting meaning on the invention involved in the present disclosure.

Claims

1. A terminal having: A receiving unit, receiving a first setting related to a payload of channel state information (CSI) and a second setting related to CSI feedback; and The control unit controls CSI compression based on artificial intelligence (AI) based on the first setting and the second setting.

2. The terminal according to claim 1, wherein: The first setting is included in a setting of a specific codebook type within the codebook setting, and is independent of settings of other codebook types.

3. The terminal according to claim 1, wherein: The control unit calculates the payload of the compressed CSI based on the first setting, and determines a matrix applied to the CSI compression based on the second setting.

4. The terminal according to claim 1, wherein: The second setting is a setting related to at least one of the number of beams, the number of delayed extensions, the number of antenna elements, the oversampling coefficient, the precoding vector, the subband number, the number of non-zero coefficients, the parameter for controlling the maximum number of non-zero coefficients, and the subband size.

5. A wireless communication method of a terminal, comprising: The step of receiving a first setting related to a payload of channel state information (CSI) and a second setting related to CSI feedback; and Based on the first setting and the second setting, the step of CSI compression based on artificial intelligence (AI) is controlled.

6. A base station, comprising: A sending unit, sending a first setting related to a payload of channel state information (CSI) and a second setting related to CSI feedback; and The control unit controls reception of the compressed CSI when CSI compression based on artificial intelligence (AI) is controlled based on the first setting and the second setting.

Images