Terminal, radio communication method, and base station

Abstract

To improve communication throughput / communication quality.SOLUTION: A terminal according to an aspect of the present disclosure has: a receiving section that receives settings related to channel state information (CSI) compression using an artificial intelligence (AI) model; and a control section that executes the CSI compression on the basis of the settings. The control section controls, for input to the AI model, positional encoding for generation of a specific signal on the basis of the correspondence between tokens and features.SELECTED DRAWING: Figure 12

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 technology]

[0002] In Universal Mobile Telecommunications System (UMTS) networks, Long Term Evolution (LTE) has been specified with the aim of achieving higher data rates and lower latency (Non-Patent Document 1). Also, LTE-Advanced (3GPP Rel. 10-14) has been specified with the aim of achieving higher capacity and more advanced features than LTE (Third Generation Partnership Project (3GPP (registered trademark)) Release (Rel.) 8, 9).

[0003] Successor systems to LTE (e.g., 5th generation mobile communication system (5G), 5G+ (plus), 6th generation mobile communication system (6G), New Radio (NR), 3GPP Rel. 15 or later) are also being considered. [Prior art documents] [Non-patent literature]

[0004] [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 [Problem to be solved by the invention]

[0005] Regarding future wireless communication technologies, the use of artificial intelligence (AI) technologies such as machine learning (ML) for network / device control and management is being considered.

[0006] As a use case of utilizing an AI model, Channel State Information (CSI) compression using a two-sided AI model is being considered. Such a CSI compression method may be called AI-based CSI feedback.

[0007] However, there are cases where such CSI compression (AI-based CSI feedback) has not been sufficiently studied. If these studies are insufficient, it is expected that appropriate CSI compression cannot be achieved. As a result, optimal overhead reduction, channel estimation, and resource utilization cannot be achieved, which may hinder improvements in communication throughput and communication quality.

[0008] Therefore, one object of the present disclosure is to provide a terminal, a wireless communication method, and a base station that can improve communication throughput / communication quality. [Means for solving the problem]

[0009] A terminal according to one embodiment of the present disclosure includes a receiving unit that receives settings related to Channel State Information (CSI) compression using an artificial intelligence (AI) model, and a control unit that performs the CSI compression based on the settings, and the control unit controls positional encoding for generating a specific signal based on a correspondence between tokens and features for input to the AI ​​model. [Effects of the Invention]

[0010] According to one aspect of the present disclosure, communication throughput / communication quality can be improved. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of CSI feedback using an encoder / decoder. [Figure 2] FIG. 2 illustrates an example of AI-based CSI feedback. [Figure 3] FIG. 3 is a diagram illustrating an example of CSI feedback using an encoder / decoder incorporating quantization. [Figure 4] FIG. 4 is a diagram showing an example of a model structure according to option 3a-1. [Figure 5] FIG. 5 is a diagram illustrating an example of hyperparameters for each process in the model structure of the present disclosure. [Figure 6] 6A to 6C are diagrams showing an example of a dimensional design (correspondence between features and tokens). [Figure 7] FIG. 7 is a diagram showing an example of a correspondence relationship between features and tokens according to embodiment 1.3. [Figure 8] FIG. 8 is a diagram showing an example of a correspondence relationship between features and tokens according to embodiment 1.5. [Figure 9] FIG. 9 is a diagram showing an example of a correspondence relationship between features and tokens according to embodiment 1.6. [Figure 10] FIG. 10 is a diagram showing an example of the correspondence between features and tokens according to embodiment 1.7. [Figure 11] FIG. 11 is a diagram showing an example of the correspondence between features and tokens according to embodiment 1.8. [Figure 12] FIG. 12 is a diagram showing an example of signal generation according to embodiment 3.1. [Figure 13] FIG. 13 is a diagram showing an example of signal generation according to embodiment 3.1. [Figure 14] FIG. 14 is a diagram showing an example of signal generation according to embodiment 3.2. [Figure 15] FIG. 15 is a diagram showing an example of signal generation according to embodiment 3.2. [Figure 16] FIG. 16 is a diagram illustrating an example of a schematic configuration of a wireless communication system according to an embodiment of the present disclosure. [Figure 17] FIG. 17 is a diagram illustrating an example of a configuration of a base station according to an embodiment of the present disclosure. [Figure 18] FIG. 18 is a diagram illustrating an example of a configuration of a terminal according to an embodiment of the present disclosure. [Figure 19] FIG. 19 is a diagram illustrating an example of a hardware configuration of a base station and a terminal according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] (AI-based CSI feedback) Regarding future wireless communication technologies, the use of AI technologies such as machine learning (ML) for network / device control and management is being considered.

[0013] For example, there are plans for terminals (user terminals, user equipment (UE)) / base stations (BSs) to utilize AI technology to improve Channel State Information (CSI) feedback (e.g., reducing overhead, improving accuracy, prediction), improve beam management (e.g., improving accuracy, prediction in the time / space domain), and improve position measurement (e.g., improving position estimation / prediction).

[0014] As a use case of utilizing an AI model, CSI compression using a two-sided AI model is being considered. Such a CSI compression method may be called AI-based CSI feedback and may be realized using, for example, an autoencoder.

[0015] 1 is a diagram illustrating an example of CSI feedback using an encoder / decoder. A UE inputs input information (e.g., CSI) to an encoder and transmits information (CSI feedback information) including encoded bits from an antenna. A BS inputs the received CSI feedback information bits to a corresponding decoder to obtain reconstructed input information (e.g., CSI) to be output.

[0016] The input CSI may include, for example, information on channel coefficients (elements of a channel matrix) or information on precoding coefficients (elements of a precoding matrix). In other words, the CSI may correspond to information on the channel state in the space-frequency domain. Note that the input may include information other than CSI.

[0017] The CSI output from the decoder may be a reconstructed CSI corresponding to the input to the encoder, or may be a CSI different from the input to the encoder (for example, if the input information is information on channel coefficients, information on precoding coefficients, etc.).

[0018] The encoder / decoder may include pre-processing for input and post-processing for output.

[0019] The encoded bits are more compressed than the input information before encoding, which is expected to reduce the communication overhead required for CSI feedback.

[0020] Figure 2 shows an example of AI-based CSI feedback. The UE performs pre-processing, AI / ML-based CSI generation, and post-processing on CSI measurement results, etc., and transmits the encoded bits (CSI feedback information) to the NW (base station). The NW (base station) performs pre-processing, AI / ML-based CSI reconstruction, and post-processing on the received bits to obtain CSI (channel / precoding matrix).

[0021] Quantization for CSI Feedback FIG. 3 illustrates an example of CSI feedback using an encoder / decoder incorporating quantization. The UE performs specific quantization on the encoding or encoded values / bits, and transmits information (CSI feedback) including the quantized bits from an antenna. Note that in this disclosure, "AI model layer(s)" may refer to an encoder / decoder implemented using one or more layers.

[0022] The base station applies corresponding inverse quantization to the bits of the received CSI feedback, and inputs the inverse quantized values / bits to corresponding decoders to obtain the reconstructed input information that is output.

[0023] (UE behavior in CSI processing) The scalability of a specified model structure is being considered. To achieve this scalability, the UE must correctly process the CSI (e.g., precoder or channel matrix).

[0024] CSI processing may include, for example, reshaping the token / feature domain of the CSI (e.g., slot, subband, Tx port, phase / amplitude / real / imaginary dimensions), applying specific padding methods to specified token / feature dimensions, etc.

[0025] (Model structure for CSI compression) 4 is a diagram showing an example of a model structure according to Option 3a-1. For the sake of convenience, details of each step will be omitted.

[0026] In Figure 4, the number of tokens is represented by Nt (N token ), and the dimension of each token may be represented by dt (d token (It may also be expressed as

[0027] For example, in the embedding layer, each token is represented as dm(d model )-dimensional vector representation. That is, the dimension of each token after conversion is dm(d model )

[0028] In positional encoding, the encoded position information is converted into a vector.

[0029] In multi-head attention, a signal is multiplied by the weights of each head and its own weight, resulting in features abstracted by the heads.

[0030] The features abstracted by the head are processed by a multi-layer perceptron (MLP).

[0031] The steps after the positional encoding and before the output linear layer may refer to an encoding process. The encoding process may be repeated a predetermined number of times (e.g., N TF-Enc The encoding process may be repeated (times). The encoding process may be referred to as a TF block, a transform block, etc.

[0032] In the output linear layer (which may also be called the output of the linear layer), the output of the transformer (TF) is transformed into the required dimension for the task. The transformed dimension is, for example, Z dimIt may be expressed as:

[0033] Total payload size after quantization N payload is N bit *Z dim It is expressed as:

[0034] The steps from embedding to output may be called a conversion process, a transformer, etc.

[0035] The steps from the input linear layer (which may also be called the input of the linear layer) after de-quantization to the output linear layer may refer to a decoding process. The decoding process may be performed in the reverse order of the encoding process described above. The decoding process may be performed a predetermined number of times (e.g., N TF-Dec The decoding process may be referred to as a TF block, a transform block, etc.

[0036] The steps from input to output may be called a conversion process, a transformer, etc.

[0037] In the present disclosure, quantization, inverse quantization, transform [processing], encoding [processing], decoding [processing], etc. may be read interchangeably.

[0038] In this disclosure, a Transformer (TF) may refer to an entity that performs the transformation process (e.g., a model of a UE / NW). That is, a Transformer, a UE, and a NW (i.e., any entity) may be interchangeable.

[0039] ((Hyperparameters in the model structure)) The following are examples of various parameters (which may also be referred to as hyperparameters) related to the above-mentioned TF: Fig. 5 is a diagram showing an example of hyperparameters for each process in the model structure of the present disclosure.

[0040] <embedded layer> Number of tokens. ·Feature dimension of each token. Output dimension per token (d model ). <Positional Encoding> Number of token positions. The dimension of the positional encoding for each token position (d model ). <Transformer Blocks> Number of Transformer Blocks (N TF ). Transformer block dimension (d model ). Number of self-attention heads (N head ). Attention head dimension (d head ). The dimension of the latent space inside the feedforward module (d FF ). · Feature selection activation. <Output linear layer> Reshape the matrix to a vector. Output dimension (Z dim ). <Quantization> Scalar quantization: - Number of bits per latent dimension (N bit ), - Scalar quantization total payload size (N bit *Z dim ). Vector Quantization: - Number of segments / size (N seg ), - Number of bits per latent dimension (N bit ), - bits per segment (N bit *N seg ), - Number of segments (Zdim / N seg ), - Total payload size for vector quantization (number of segments * bits per segment (N seg *N bit *N seg )).

[0041] ((Example of model structure)) In natural language processing (NLP), each word may be treated as a token, i.e., words and tokens may be interchangeable. For example, TF learns the relationships between tokens based on the input text.

[0042] Each token (i.e., word) may be represented as a vector, the value of which may indicate the meaning of the word. The values ​​of the vector, i.e., word, token, and vector, may be interchangeable.

[0043] The input to a TF can be thought of as a matrix, where one dimension may be tokens and the other dimension may be features.

[0044] For CSI processing, the CSI matrix is ​​usually a high-dimensional matrix, which needs to be reformulated into a matrix with token / feature dimensions.

[0045] For example, Rel. 19 considers which dimensions of CSI are appropriate to treat as tokens / features.

[0046] More specifically, there are cases where a frequency domain unit (e.g., a subband) becomes a token and a Tx port becomes a feature (Alt1, described below), and cases where a subband becomes a feature and a Tx port becomes a characteristic (Alt2, described below).

[0047] ((Scalability Scheme)) For example, a model structure for option 3a-1 is defined, and the corresponding dimensional design for the model output is considered. Figures 6A-6C are diagrams showing an example of the dimensional design (the correspondence between features and tokens). In Figure 6, the horizontal axis corresponds to the Tx port (transmission port), and the vertical axis corresponds to the subband.

[0048] <Selection of token dimension and feature dimension> The following options can be exemplified for the correspondence between features and tokens: The present disclosure is applicable to any of the following options: In any of the following options, a common model (structure) may be used across layers (among multiple layers).

[0049] < <alt1>> Subbands may be used as the token dimension and Tx ports may be used as the feature dimension, and the number of tokens may vary depending on the number of subbands.

[0050] For example, as shown in Fig. 6A, multiple tokens may be assigned (defined) for each subband. Specifically, four tokens (tokens #0 to #3) may be defined for each of the four subbands.

[0051] < <alt2>> The Tx port may be used as the token dimension and the subband may be used as the feature dimension, and the number of tokens may vary depending on the number of Tx ports.

[0052] For example, as shown in Fig. 6B, multiple tokens may be assigned (defined) for each Tx port. Specifically, six tokens (tokens #0 to #5) may be defined, which are divided among six Tx ports.

[0053] < <alt3>> A fixed-size sub-block consisting of a matrix of sub-bands and tokens may be used as a token. The sub-block may be, for example, an N*M matrix, where N may represent the number of Tx ports and M may represent the number of sub-bands. The input may be represented as a sequence of tokens.

[0054] The number of tokens (number of sub-blocks) may vary depending on the number of Tx ports and the number of sub-bands.

[0055] For example, as shown in Figure 6C, one token may be composed of sub-blocks of a 2*2 matrix (i.e., N = 2, M = 2). Specifically, six tokens (tokens #0 to #5) divided into six sub-blocks may be defined.

[0056] <Scalability for feature dimensions> In the feature dimension, at least one of the following options may be applied:

[0057] < <alt1>> A specific embedding layer for each feature size.

[0058] < <alt2>> A common embedding layer with padding (e.g., zero padding, other methods using arbitrary padding values).

[0059] <Token dimension scalability> In the token dimension, at least one of the following options may apply:

[0060] < <alt1>> Unique positional embedding for each token [index]. N token Among the token positions, N token,active tokens may be used as input, where N token represents the number of tokens (total number), and N token,active may represent the number of active tokens.

[0061] The method of position embedding (which may also be called positional encoding) needs to be specified to ensure common understanding between the UE and the NW.

[0062] < <alt2>> Padding on input.

[0063] <Payload setting scalability> In the payload configuration, at least one of the following options may be applied:

[0064] < <alt1>> A unique output linear layer for each payload.

[0065] < <alt2>> Truncation / masking of output linear layers.

[0066] < <alt3>> Change in quantization parameters.

[0067] (analysis) A method is needed to provide a common understanding between the UE and the NW (e.g., gNB) regarding the input and output of CSI related to CSI processing for scalability.

[0068] In addition, it is necessary to clarify the details of positional embedding (positional encoding), which is one of the operations related to CSI processing.

[0069] Positional encoding can also be applied in CSI processing, where the space / frequency / time domains of the input vector containing the CSI coefficients are transferred to the TF (Transformer). Furthermore, positional encoding can be applied with or without padding schemes to achieve model scalability.

[0070] As such, it is necessary to clarify how to achieve a common understanding between the UE and the network regarding the positional encoding method and its combination with other CSI processing.

[0071] If these factors are not clearly defined, it is expected that appropriate CSI feedback (CSI compression) will not be achieved, which may result in insufficient overhead reduction, channel estimation, and resource utilization, resulting in limited improvements in communication throughput and communication quality.

[0072] Therefore, the present inventors came up with a method for solving these problems.

[0073] Hereinafter, embodiments according to the present disclosure will be described in detail with reference to the drawings. Wireless communication methods according to the respective embodiments may be applied independently or in combination. The present disclosure also provides embodiments in which part or all of one embodiment is combined with part or all of another embodiment.

[0074] (Various reading changes) In the present disclosure, words enclosed in "()" in a sentence may indicate an explanation of the immediately preceding wording (for example, an explanation of spelling), a paraphrase, a specific example, a supplementary explanation, etc. Also, in the present disclosure, words enclosed in "[ ]" in a sentence may be interpreted including the meaning of the entire sentence, or may be interpreted excluding the meaning of the entire sentence (ignoring the meaning of the entire sentence). Note that "()" and "[ ]" may also be used for purposes / meanings other than those mentioned above.

[0075] In the present disclosure, "A / B" and "at least one of A and B" may be interpreted interchangeably. Also, in the present disclosure, "A / B / C" may mean "at least one of A, B, and C."

[0076] In the present disclosure, terms such as notify, activate, deactivate, indicate (or indicate), select, configure, update, and determine may be interchangeable. In the present disclosure, terms such as support, control, controllable, operate, and operate may be interchangeable.

[0077] In the present disclosure, Radio Resource Control (RRC), RRC parameters, RRC messages, higher layer parameters, fields, information elements (IEs), settings, etc. may be interchangeable. In the present disclosure, Medium Access Control (MAC) control elements (CEs), update commands, activation / deactivation commands, etc. may be interchangeable.

[0078] In the present disclosure, signaling, message, field, parameter, information, payload, etc. may be read interchangeably.

[0079] In the present disclosure, higher layer signaling may be, for example, any one of Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information, Non-Access Stratum (NAS) signaling (of the control plane), other messages (e.g., messages communicated to and from the core network, such as positioning protocol (e.g., NR Positioning Protocol A (NRPPa) / LTE Positioning Protocol (LPP)) messages), or a combination thereof.

[0080] In the present disclosure, MAC signaling may use, for example, a MAC Control Element (MAC CE), a MAC Protocol Data Unit (PDU), etc. Broadcast information may be, for example, a Master Information Block (MIB), a System Information Block (SIB), Remaining Minimum System Information (RMSI), Other System Information (OSI), etc.

[0081] In the present disclosure, physical layer signaling may be, for example, Downlink Control Information (DCI), Uplink Control Information (UCI), and the like.

[0082] In this disclosure, the terms index, identifier (ID), indicator, resource ID, etc. may be interchangeable. In this disclosure, the terms sequence, list, set, group, cluster, subset, etc. may be interchangeable.

[0083] In this disclosure, the terms panel, UE panel, panel group, beam, beam group, precoder, Uplink (UL) transmitting entity, Transmission / Reception Point (TRP), base station, Spatial Relation Information (SRI), spatial relation, SRS Resource Indicator (SRI), Control Resource Set (CORESET), Physical Downlink Shared Channel (PDSCH), Codeword (CW), Transport Block (TB), Reference Signal (RS), antenna port (e.g., Demodulation Reference Signal (DMRS) port), antenna port group (e.g., DMRS port group), group (e.g., spatial relation group, Code Division Multiplexing (CDM) group, reference signal group, CORESET group, Physical Uplink Control Channel (PUCCH) group, PUCCH resource group), resource (e.g., reference signal resource, SRS resource), resource set (e.g., reference signal resource set), CORESET pool, downlink Transmission Configuration Indication state (TCI state) (DL TCI state), uplink TCI state (UL TCI state), unified TCI state, common TCI state, Quasi-Co-Location (QCL), QCL assumption, etc. may be read as interchangeable.

[0084] In the present disclosure, CSI-RS, non-zero power (NZP) CSI-RS, zero power (ZP) CSI-RS, and CSI interference measurement (CSI-IM) may be interchangeable. Furthermore, CSI-RS may include other reference signals.

[0085] In this disclosure, the measured / reported RS may refer to the RS measured / reported for a CSI report.

[0086] In the present disclosure, timing, time, duration, slot, subslot, symbol, subframe, etc. may be read interchangeably.

[0087] In the present disclosure, the terms direction, axis, dimension, domain, polarization, polarization component, etc. may be interpreted interchangeably.

[0088] In this disclosure, estimation, prediction, and inference may be used interchangeably. Also, in this disclosure, estimate, predict, and infer may be used interchangeably.

[0089] In the present disclosure, the terms autoencoder, encoder, decoder, etc. may be replaced with at least one of a model, an ML model, a neural network model, an AI model, an AI algorithm, etc. Furthermore, the term autoencoder may be replaced with any autoencoder, such as a stacked autoencoder or a convolutional autoencoder. The encoder / decoder of the present disclosure may employ a model such as a Residual Network (ResNet), a DenseNet, or a RefineNet.

[0090] In the present disclosure, the terms bit, bit string, bit sequence, sequence, value, information, value obtained from a bit, information obtained from a bit, etc. may be read interchangeably.

[0091] In the present disclosure, a layer (for an encoder) may be interchangeably read as a layer (such as an input layer or an intermediate layer) used in an AI model. The layer in the present disclosure may correspond to at least one of an input layer, an intermediate layer, an output layer, a batch normalization layer, a convolutional layer, an activation layer, a dense layer, a normalization layer, a pooling layer, an attention layer, a dropout layer, a fully connected layer, etc.

[0092] In the present disclosure, RSRP may be interchangeably read as any parameter related to received power / received quality, etc. (for example, RSRQ, SINR, CSI), etc.

[0093] In the present disclosure, the RS may be, for example, a CSI-RS, an SS / PBCH block (SS block (SSB)), etc. Also, the RS index may be a CSI-RS Resource Indicator (CRI), an SS / PBCH Block Indicator (SSBRI), etc.

[0094] In the present disclosure, channel measurement / estimation may be performed using at least one of, for example, a Channel State Information Reference Signal (CSI-RS), a Synchronization Signal (SS), a Synchronization Signal / Physical Broadcast Channel (SS / PBCH) block, a Demodulation Reference Signal (DMRS), a Sounding Reference Signal (SRS), etc.

[0095] In the present disclosure, the terms "receive beam assumption," "number of receive beams," "index of receive beam," "receive beam selection," "receive beam setting," and "receive beam instruction" may be interchangeable. In the present disclosure, the terms "receive beam," "transmit beam," "DL receive beam," "DL transmit beam," and "pair of transmit beam and receive beam" may be interchangeable. In the present disclosure, the terms "transmit / receive beam" may be interchangeable with the terms "transmit / receive beam for beam prediction" and "transmit / receive beam for CSI measurement / reporting for beam prediction."

[0096] In this disclosure, functionality may refer to the use of a model or the physical meaning of the model's input / output. Multiple models may have the same functionality. Monitoring (checking performance), activation, deactivation, switching, fallback, and updating may be instructed (controlled) based on the functionality (e.g., for each function).

[0097] In this disclosure, functionality may refer to features (requiring AI / ML capabilities) (e.g., reporting information based on CSI prediction / CSI compression / temporal beam prediction / spatial domain beam prediction).

[0098] A model ID may also refer to an identifier for a model (or a set of models). Multiple models may be assigned the same model ID in an actual deployment. In this case, these models may actually be different models (e.g., have different numbers of layers) but may be treated as the same model.

[0099] In the present disclosure, the model ID may be interchangeably read as a meta information (or a set of meta information) ID. The meta information (or meta information ID) may be associated with information about the applicability of the model / function, the environment, the UE / gNB configuration, etc.

[0100] In this disclosure, functionality, functionality, function ID, model, and model ID may be read interchangeably.

[0101] In the present disclosure, an ID may represent an ID corresponding to (for identifying) at least one of a dataset, a model, and a property of a channel / RS. That is, in the present disclosure, an ID, a dataset ID, a model ID, and a property ID of a channel / RS may be read as interchangeable.

[0102] In the present disclosure, the terms "report initiation" and "report trigger" may be read interchangeably.

[0103] In the present disclosure, the prediction result and the monitoring output may be interpreted as interchangeable.

[0104] In the present disclosure, measurement, measurement, and measurement may be read interchangeably.

[0105] In the present disclosure, ceil(A) may mean multiplying A by a ceiling function. Also, ceil(A) may be transformed / replaced with floor(A). Also, in the present disclosure, floor(A) may mean multiplying A by a floor function.

[0106] In the present disclosure, the terms CSI, precoder, and channel matrix may be interchangeable.

[0107] In the present disclosure, features, characteristics [quantities], and functions may be read interchangeably.

[0108] In the present disclosure, vectors, matrices, functions, and rules may be read interchangeably.

[0109] In the present disclosure, the terms token, feature, and dimension may be read interchangeably.

[0110] In this disclosure, the terms Transformer, Model (Structure), and Entity may be read interchangeably.

[0111] In this disclosure, Tx port, transmit port, port, and spatial domain may be interpreted interchangeably.

[0112] (Wireless communication method) This disclosure relates to a method for providing a common understanding between a UE and a network (e.g., a gNB) regarding the input and output of CSI related to CSI processing for scalability, and a specific method for CSI processing (e.g., a positional encoding method). Specifically, the following is proposed as the processing and basic concept for model input.

[0113] A particular model structure can accept inputs of dimensions Nt x Nf, where Nt is a [fixed] value that can be specified / set and Nf is a [flexible] value that can be specified.

[0114] Step A. The UE / NW can group consecutive CSI coefficients of 1 to 4 dimensions (e.g., slot, subband, Tx port, phase / amplitude / real / imaginary) into Nt groups. Detailed rules can be exemplified by the above-mentioned Figures 6A to 6C.

[0115] Step B. If the length of one dimension is not the specified / configured value, the UE / NW may pad the CSI coefficients. The padding may be by adding zero values, or by copying the contents, interpolation, extending, etc.

[0116] The UE / NW may perform steps A and B in any order (e.g., perform step A followed by step B, or vice versa, perform step B followed by step A).

[0117] Specifically, the present disclosure relates to CSI compression / CSI feedback and can be broadly divided into the following embodiments. First embodiment: Input / output correspondence for a specific model structure. Second embodiment: dedicated padding scheme. Third embodiment: Positional encoding method.

[0118] Each embodiment will be described below based on these. Each embodiment / option may be applied alone or in combination.

[0119] In the following embodiments, the operation of a UE will be mainly described, but is not limited to this. The following embodiments are applicable not only to the UE but also to the operation of a NW (e.g., gNB). That is, in the present disclosure, the UE and the NW may be read as interchangeable.

[0120] In this disclosure, CSI compression (AI-based CSI feedback) is mainly exemplified as a use case of utilizing an AI model. However, the present disclosure is not limited to this and can be applied to other use cases. In addition, the present disclosure can also be applied to CSI compression (CSI feedback) that does not use AI technology.

[0121] Although this disclosure illustrates CSI compression using a two-sided model, it is not limited to this example, and the present disclosure can also be applied to CSI compression using a one-sided model (UE side / gNB side model).

[0122] The UE / NW (gNB) may perform various operations related to CSI compression by applying the following embodiments.

[0123] The UE / NW may receive various settings for CSI compression.

[0124] The UE / NW may send various settings / instructions for CSI compression to the UE.

[0125] The wireless communication method disclosed herein clarifies the specifications for various measurements for CSI compression using an AI model (AI-based feedback). This enables the UE / network to provide appropriate CSI feedback. As a result, optimal overhead reduction, channel estimation, and resource utilization can be achieved, and improvements in communication throughput and communication quality are expected.

[0126] First Embodiment The first embodiment relates to the correspondence between input and output for a specific model structure.

[0127] In the present disclosure, a CSI report of any type (e.g., Type X) may refer to a novel CSI report such as Type 3 or Extended Type X. The novel CSI report may refer to a CSI report based on inference using a UE-side model, a CSI report based on inference using a two-sided model (e.g., AI-based CSI compression, etc.), or may refer to other CSI reports.

[0128] <<Embodiment 1.0>> In embodiment 1.0, model input is described.

[0129] For CSI reporting of any type (e.g., type X), the UE (NW) may assume the following:

[0130] The CSI represented by the payload / PMI reported by the UE is one or more matrices with Nt*Nf dimensions.

[0131] Here, Nf is a parameter that can be specified / configured / instructed to the UE and may be, for example, a flexible value, and Nt is a parameter that can be specified / configured / instructed to the UE and may be, for example, a fixed value.

[0132] The UE may report the value (e.g., the maximum value) of Nt (Nf) that it can support, which may be reported using a UE capability report.

[0133] Also, the value of Nt(Nf) may be specified / configured / indicated by higher layer signaling / MAC signaling / physical layer signaling, or may be predefined by a specification or determined according to UE capabilities.

[0134] The above CSI matrix (which may simply be called a matrix) is A or A k It can be expressed as (k=1,2,···).

[0135] matrix (A, or A k ) may represent elements of the precoder / channel matrix for different factors, where the factors may be at least one of a layer, an RS port, a subband, a time instance / slot, and a different part (real part / imaginary part / amplitude part / phase part).

[0136] In the present disclosure, factors may be read as dimensions.

[0137] The UE calculates the matrix (A or A) according to the specified / configured / instructed mapping rule. k ) and a mapping between precoder / channel matrices for different factors may be assumed.

[0138] The mapping rule may be expressed as follows: A(i,j)=P(v,p,f,t,r) or, A k (i,j)=P(v,p,f,t,r)

[0139] In the above equation, matrices A(i,j) and A k (i, j) means the CSI matrix described above and may be interchangeable. (i, j, k) relating to matrix A may be an output [parameter] from a certain function (F).

[0140] The matrix P(v,p,f,t,r) may represent the precoder / channel matrix for different factors. The (v,p,f,t,r) related to the matrix P are inputs (parameters) for a function (F).

[0141] The parameters in the above equation may be defined as follows: ·v means a layer index, and the maximum value of v may be represented by L. ·p means the [Tx] port index, and the maximum value of p may be represented by P. ·f denotes a frequency domain resource (e.g., subband) index, and the maximum value of f may be denoted by S. ·t denotes a time domain resource / instance (eg, slot) index, and the maximum value of t may be denoted as T. r denotes a partial (real part / imaginary part / amplitude part / phase part) index of the precoder / channel coefficient (which may also be called a signal part index), and may have a value of 0 or 1. The part may also be called a part, a portion, a block, a sub-block, etc.

[0142] Also, (i,j,k)=F(v,p,f,t,r) may denote any function / rule (group of functions) that maps any parameters (v,p,f,t,r) to (i,j,k). The function / rule may be specified / configured / instructed to the UE.

[0143] The number of parameters in the correspondence between matrix A and matrix P can be set arbitrarily. For example, which parameters are input to a function / rule (F) and which / how many parameters are output from the function may be set flexibly.

[0144] More specifically, matrix A is A k (i,j)=A(i,j,k)=P(v,p,f,t,r), or by adding / expanding parameters, A k,m (i,j)=A(i,j,k,m)=P(v,p,f,t,r),A k,m,n It may also be expressed in the form (i,j)=A(i,j,k,m,n)=P(v,p,f,t,r), etc.

[0145] where (k,m,n) in matrix A are any / optional parameters that can be output by the function / rule (F), and (v,p,f,t,r) in matrix P are any / optional parameters that can be input to the function / rule (F).

[0146] The above-mentioned values ​​of L, P, S, and T may be predefined by specifications, specified / configured / indicated by higher layer signaling / MAC signaling / physical layer signaling, or determined according to UE capabilities. The UE may report the values ​​of L, P, S, and T as capability information.

[0147] The UE receives A with optional k. k We may assume that (i,j) = P(v,p,f,t,r), where k is based on (v,p,f,t,r) = F'(i,j,k), where F'(i,j,k) is the inverse function of P(v,p,f,t,r).

[0148] This embodiment clarifies the correspondence between inputs and outputs for specific types of CSI reporting using AI models.

[0149] The following embodiments 1.1 to 1.8 are specific examples of embodiment 1.0. That is, each of the following embodiments may be based on embodiment 1.0.

[0150] <<Embodiment 1.1>> Embodiment 1.1 relates to the case where the time domain is not considered in the example of Fig. 6A described above, i.e., in embodiment 1.1, subbands may be used as the token dimension (which may be called the first dimension) and Tx ports may be used as the feature dimension (which may be called the second dimension).

[0151] The UE may assume the following rules:

[0152] k=v,(v=0,1,,L-1) In this case, there are L matrices A k (i,j) where each matrix A corresponds to a precoder / channel matrix for a layer.

[0153] i=f,(f=0,1,...,S-1) In this case, this may mean that the subbands are mapped to the first dimension (dimension #1, ie, tokens).

[0154] ·j=p+Pr,(p=0,1,···,P-1, r=0,1) In this case, it may mean that some of the Tx ports and numbers are mapped to the second dimension (dimension #2, ie, features).

[0155] The UE may assume a mapping rule (correspondence) based on the inverse function (inverse matrix) described above.

[0156] <<Embodiment 1.2>> Embodiment 1.2 relates to the case where the time domain is not considered in the example of Fig. 6B described above, i.e., in embodiment 1.2, Tx ports may be used as the token dimension (which may be called the first dimension) and subbands may be used as the feature dimension (which may be called the second dimension).

[0157] The UE may assume the following rules:

[0158] k=v,(v=0,1,,L-1) In this case, there are L matrices A k (i,j) where each matrix A corresponds to a precoder / channel matrix for a layer.

[0159] i=p,(f=0,1,...,P-1) In this case, this may mean that the Tx port is mapped to the first dimension (dimension #1, ie, token).

[0160] ·j=f+Sr,(f=0,1,···,S-1, r=0,1) In this case, it may mean that some of the subbands and numbers are mapped to the second dimension (dimension #2, ie, features).

[0161] The UE may assume a mapping rule (correspondence relationship) based on the inverse function described above.

[0162] <<Embodiment 1.3>> Embodiment 1.3 relates to a case where the time domain is not considered in the example of Fig. 6C described above, i.e., in embodiment 1.3, a fixed-size sub-block (which may be called a sub-band-Tx port block, etc.) configured by a matrix of sub-bands and tokens may be used as a token.

[0163] The UE may assume the following rules:

[0164] k=v,(v=0,1,,L-1) In this case, there are L matrices A k (i,j) where each matrix A corresponds to a precoder / channel matrix for a layer.

[0165] The UE may divide the precoder / channel coefficients into multiple blocks (sub-blocks), each containing a specified / configured / instructed number of precoder / channel coefficients.

[0166] For example, each block may include precoder / channel coefficients consisting of S' frequency domain resources and P' ports.

[0167] UE is Nt=M s *M p where M s =ceil(S / S'), M p =ceil(P / P').

[0168] The UE may map the precoder / channel coefficients of each block according to a specified / configured / instructed rule. Specifically, the UE may assume the following rules:

[0169] i=m s +M s m p ,(m s =0,1,···,M s -1, m p =0,1,···,M p -1) ·j=s+S'p+P'S'r,(s=m s S'+s', p=m p P'+p'),(p'=0,1,...,P'-1,s'=0,1,...,S'-1,r=0,1)

[0170] FIG. 7 is a diagram showing an example of a correspondence relationship between features and tokens according to embodiment 1.3.

[0171] In Figure 7, M s =2,S'=2,M p =3, P'=2. That is, Nt=M s *M p = 6. In this case, six tokens (tokens #0 to #5) are input to the TF.

[0172] <<Embodiment 1.4>> Embodiment 1.4 relates to a case in which embodiment 1.3 is extended to multiple time instances (time domain resources), that is, in embodiment 1.3, the time domain may be taken into consideration.

[0173] The UE may assume the following rules:

[0174] k=v,(v=0,1,,L-1) In this case, there are L matrices A k (i,j) where each matrix A corresponds to a precoder / channel matrix for a layer.

[0175] The UE may divide the precoder / channel coefficients into multiple blocks (sub-blocks), each containing a specified / configured / instructed number of precoder / channel coefficients.

[0176] For example, each block may include precoder / channel coefficients consisting of T' time domain resources, S' frequency domain resources, and P' ports.

[0177] UE is Nt=M s *M p *M t where M s =ceil(S / S'), M p =ceil(P / P'), M t =ceil(T / T').

[0178] The UE may map the precoder / channel coefficients of each block according to a specified / configured / instructed rule. Specifically, the UE may assume the following rules:

[0179] i=m s +M s m p +M s M p m t ,(m s =0,1,···,M s -1, m p =0,1,···,M p -1, m t =0,1,···,M t -1) ·j=s+S'p+S'P't+P'S'T'r,(s=m s S'+s', p=m p P'+p', t=m t T'+t'),(p'=0,1,···,P'-1, s'=0,1,···,S'-1, t'=0,1,···,T'-1, r=0,1)

[0180] Thus, in embodiment 1.4, time domain resources are further considered in addition to embodiment 1.3.

[0181] <<Embodiment 1.5>> Embodiment 1.5 relates to a case in which embodiment 1.1 is extended to multiple time instances (time domain resources), that is, in embodiment 1.1, the time domain may be taken into consideration.

[0182] The UE may assume the following rules:

[0183] k=v,(v=0,1,,L-1) In this case, there are L matrices A k (i,j) where each matrix A corresponds to a precoder / channel matrix for a layer.

[0184] ·i=f+St,(f=0,1,···,S-1, t=0,1,···,T-1) In this case, this may mean that the subbands and time instances are mapped to the first dimension (dimension #1, ie, tokens).

[0185] ·j=p+Pr,(p=0,1,···,P-1, r=0,1) In this case, it may mean that some of the Tx ports and numbers are mapped to the second dimension (dimension #2, ie, features).

[0186] FIG. 8 is a diagram showing an example of a correspondence relationship between features and tokens according to embodiment 1.5.

[0187] Figure 8 shows the case where S = 4 and T = 2. As shown in Figure 8, tokens #0 to #3 correspond to t = 0, and tokens #4 to #7 correspond to T = 1. That is, different mappings (tokens) are applied for each value of T.

[0188] <<Embodiment 1.6>> Embodiment 1.6 relates to another case in which embodiment 1.1 is extended to multiple time instances (time domain resources).

[0189] The UE may assume the following rules:

[0190] k=v,(v=0,1,,L-1) In this case, there are L matrices A k (i,j) where each matrix A corresponds to a precoder / channel matrix for a layer.

[0191] i=f,(f=0,1,...,S-1) In this case, this may mean that the subbands are mapped to the first dimension (dimension #1, ie, tokens).

[0192] ·j=p+P(t+Tr),(p=0,1,···,P-1, t=0,1,···,T-1, r=0,1) In this case, it may mean that the Tx port, time instance and some of the numbers are mapped to the second dimension (dimension #2, ie, features).

[0193] FIG. 9 is a diagram showing an example of a correspondence relationship between features and tokens according to embodiment 1.6.

[0194] Figure 9 shows the case where S = 4 and T = 2. As shown in Figure 9, tokens #0 to #3 correspond to t = 0, 1, and t = 0, 1 correspond to different Tx ports and time instances. In other words, a common mapping (token) is applied for the value of T.

[0195] <<Embodiment 1.7>> Embodiment 1.7 relates to a case in which embodiment 1.2 is extended to multiple time instances (time domain resources), that is, in embodiment 1.2, the time domain may be taken into consideration.

[0196] The UE may assume the following rules:

[0197] k=v,(v=0,1,,L-1) In this case, there are L matrices A k (i,j) where each matrix A corresponds to a precoder / channel matrix for a layer.

[0198] ·i=p+Pt,(f=0,1,···,P-1, t=0,1,···,T-1) In this case, this may mean that the Tx port and time instance are mapped to the first dimension (dimension #1, i.e., token).

[0199] ·j=f+Sr,(f=0,1,···,S-1, r=0,1) In this case, it may mean that some of the subbands and numbers are mapped to the second dimension (dimension #2, ie, features).

[0200] FIG. 10 is a diagram showing an example of the correspondence between features and tokens according to embodiment 1.7.

[0201] Figure 10 shows the case where S = 4, T = 2, and P = 6. As shown in Figure 10, tokens #0 to #5 correspond to t = 0, and tokens #6 to #11 correspond to T = 1. That is, different mappings (tokens) are applied for each value of T.

[0202] <<Embodiment 1.8>> Embodiment 1.8 relates to another case in which embodiment 1.2 is extended to multiple time instances (time domain resources).

[0203] The UE may assume the following rules:

[0204] k=v,(v=0,1,,L-1) In this case, there are L matrices A k (i,j) where each matrix A corresponds to a precoder / channel matrix for a layer.

[0205] i=p,(f=0,1,...,P-1) In this case, this may mean that the Tx port is mapped to the first dimension (dimension #1, ie, token).

[0206] ·j=f+S(t+Tr),(f=0,1,···,S-1, t=0,1,···,T-1, r=0,1) In this case, it may mean that some of the subbands, time instances and numbers are mapped to the second dimension (dimension #2, ie, features).

[0207] FIG. 11 is a diagram showing an example of the correspondence between features and tokens according to embodiment 1.8.

[0208] 11 shows the case where S=4, T=2, and P=6. As shown in FIG. 11, tokens #0 to #5 correspond to t=0, 1, and t=0, 1 correspond to different subbands. That is, a common mapping (token) is applied for the value of T.

[0209] <<Others>> In embodiments 1.1 to 1.3, the frequency domain (subbands) / Tx ports are considered for the token dimension / feature dimension. In embodiments 1.4 to 1.8, the time domain (e.g., slots) is considered in addition to the frequency domain (subbands) / Tx ports for the token dimension / feature dimension. In addition to these, for example, the time domain may be considered instead of the frequency domain. That is, the time domain / Tx ports may be considered for the token dimension / feature dimension (the frequency domain may not be considered). That is, in the present disclosure, the frequency domain and the time domain may be interpreted as interchangeable.

[0210] According to the first embodiment described above, the correspondence between input and output in a specific type of CSI report using an AI model becomes clear.

[0211] <Second embodiment> The second embodiment relates to a padding scheme for (dedicated to) the first embodiment, that is, the second embodiment may be based on the first embodiment.

[0212] <<The case where the token dimension consists of a single dimension>> If the token dimension contains only one dimension for the precoder / channel coefficients (eg, the case in embodiments 1.1, 1.2), the following may apply.

[0213] The UE may expand the dimension of the precoder / channel coefficients to L layers / P ports / S subbands / T time instances.

[0214] Specifically, the UE may pad the CSI coefficients (precoder / channel). The padding may be performed by adding zero values, or may be performed by padding with existing coefficients, copying content, interpolation, extending, extrapolation, etc.

[0215] These extension methods may be specified / configured / instructed to the UE.

[0216] <<The case where the token dimension consists of multiple dimensions>> If the token dimension includes multiple (eg, two or more) dimensions for the precoder / channel coefficients (eg, the case in embodiments 1.3, 1.4), the following may apply.

[0217] The UE increases the dimension of the precoder / channel coefficients by K L L' layers / K P P' ports / K S S' subbands / K T It may be extended to T' time instances.

[0218] Specifically, the UE may pad the CSI coefficients (precoder / channel). The padding may be performed by adding zero values, or may be performed by padding with existing coefficients, copying content, interpolation, extending, extrapolation, etc.

[0219] Here, L' may represent the number of layers contained within a block (sub-block) of precoder / channel coefficients.

[0220] K L is K L It may represent the smallest integer that makes the value of L' greater than the layer number of the precoder / channel coefficients.

[0221] K P is K P It may represent the smallest integer that makes the value of P' greater than the port number (number) of the precoder / channel coefficients.

[0222] K S is K S It may represent the smallest integer that makes the value of S' greater than the subband number of the precoder / channel coefficients.

[0223] K T is K T The value of T' may represent the smallest integer greater than the time instance number of the precoder / channel coefficients.

[0224] According to this embodiment, a dedicated padding method is made clear.

[0225] <Third embodiment> The third embodiment relates to a positional encoding method.

[0226] The positional encoding method of the present disclosure can be exemplified as follows. Opt1: Token-based positional encoding with padding (corresponding to embodiment 3.1). Opt2: Signal position-based positional encoding with / without padding (corresponding to embodiment 3.2).

[0227] In the third embodiment, Alt2 (FIG. 6B) is used as an example of the correspondence between features and tokens, but the correspondence between features and tokens is not limited to this example. Other options may be used for the correspondence between features and tokens.

[0228] <<Embodiment 3.1>> Embodiment 3.1 relates to token-based positional encoding.

[0229] 12 and 13 are diagrams showing an example of signal generation according to embodiment 3.1.

[0230] For any type (eg, type X) of CSI reporting, the UE (NW) may generate a specific signal (eg, vector).

[0231] The specific signal may be referred to as signal #A, positional encoding [signal], vector, etc. That is, the specific signal, signal #A, positional encoding [signal], and vector may be read interchangeably.

[0232] Signal #A may be generated based on a signal index (ie, a token index) along with a signal dimension (ie, a token dimension) representing the CSI (see FIG. 12).

[0233] For example, the dimension representing the CSI may correspond to the first dimension (token dimension) of a matrix (CSI matrix) having Nt*Nf dimensions, where the token index may be represented by 0, , Nt-1 (see FIG. 12).

[0234] The UE may add / multiply (multiplex) the signal #A to the signal representing the CSI according to the corresponding index, or may combine (combine) these signals (the signal representing the CSI and the signal #A) using a specified / configured / instructed function.

[0235] The UE may control the addition of zero signals to a signal representing CSI (i.e., a token) based on whether padding is applied to the signal representing CSI.

[0236] For example, if the signal representing the CSI is padded (copy-based padding or zero-padded) (i.e., the token is a padded token), the UE may add (append) / multiply (multiplex) a zero signal to the signal representing the CSI [according to the corresponding index].

[0237] More specifically, as shown in FIG. 13, for signals that the UE does not report (signals not to be reported), the UE may add zero padding (zero signals or other signals) to the corresponding positions before positional encoding.

[0238] Alternatively, in this case, the UE may not add (add) / multiply (multiplex) a zero signal to the signal representing the CSI.

[0239] Adding a zero signal etc. may mean generating a zero vector / positional encoding [signal].

[0240] Token-based positional encoding allows for easy scaling of the model structure.

[0241] The UE may use the resulting signal to generate a CSI payload.

[0242] That is, the UE may use the resulting signal as input to the TF block (subsequent encoding process).

[0243] <<<Modifications>>> Given a given index (i), the signal (eg, signal #A) generated based on that index (i) may follow the formula: p(i,2k)=sin(i / n 2k / d ), p(i,2k+1)=cos(i / n 2k / d ), 0≦k <Nf / 2、 Here, n and d may be specified / set / instructed values.

[0244] According to embodiment 3.1, a token-based positional encoding scheme is clarified.

[0245] <<Embodiment 3.2>> Embodiment 3.2 relates to signal position-based positional encoding.

[0246] 14 and 15 are diagrams showing an example of signal generation according to embodiment 3.1.

[0247] For any type (eg, type X) of CSI reporting, the UE (NW) may generate a specific signal (eg, vector).

[0248] The specific signal may be referred to as signal #A, positional encoding [signal], vector, etc. That is, the specific signal, signal #A, positional encoding [signal], and vector may be read interchangeably.

[0249] The UE may generate signal #A based on the signal position in the space / frequency / time domain index, with or without padding.

[0250] For example, the UE may generate the signal #A based on an index (i) generated based on at least one of the following parameters: The parameter may be a parameter related to the above-mentioned matrix P. Specific examples are listed below.

[0251] Layer index v. The maximum value of v may be denoted by L. [Tx] port index p. The maximum value of p may be denoted by P. A frequency domain resource (e.g., subband) index f. The maximum value of f may be denoted by S. A time domain resource / instance (e.g., slot) index t. The maximum value of t may be denoted by T. Precoder / channel coefficient part (real part / imaginary part / amplitude part / phase part) index r (may also be called signal part index r). r can have a value of either 0 or 1. Signal block index, where each block may correspond to a specified / configured / indicated number of layers / ports / frequency domain resources / time domain resources / signal portions.

[0252] Examples of parameter combinations include the following:

[0253] <<<Example 1>>> When including all of the above parameters (factors), the index (i) may be derived / mapped as follows:

[0254] i=v+L(p+P(s+S(t+Tr))),(v=0,1,···,L-1, p=0,1,···,P-1, s=0,1,···,S-1, t=0,1,···,T-1, r=0,1)

[0255] <<<Example 2>>> When the parameters include port, frequency domain resource, time domain resource, real part / imaginary part, the index (i) may be derived / mapped as follows:

[0256] i=p+P(s+S(t+Tr)),(v=0,1,···,L-1, p=0,1,···,P-1, s=0,1,···,S-1, t=0,1,···,T-1, r=0,1)

[0257] <<<Example 3>>> When the parameters include frequency domain resources, time domain resources, and real / imaginary parts, the index (i) may be derived / mapped as follows:

[0258] i=s+S(t+Tr),(s=0,1,...,S-1, t=0,1,...,T-1, r=0,1)

[0259] In this case, the Tx port (spatial domain) may be applied as the feature dimension.

[0260] <<<Example 4>>> The UE may derive the index (i) based on the above-described embodiments 1.1 to 1.8.

[0261] <<<Others>>> The UE may generate a signal representing the signal #A / CSI using the formula described in the variant of embodiment 3.1.

[0262] To generate a signal representing signal #A / CSI, the UE may omit indexes corresponding to layers / ports / frequency domain resources / time domain resources / signal portions that the UE does not report (see FIG. 14). That is, the UE may delete / omit indexes that are not to be reported from the signal.

[0263] As shown in FIG. 14, by omitting the portion that the UE does not report (portion not to be reported), the UE can use a signal with a smaller size.

[0264] For the signal #A in FIG. 14, positional encoding based on layer / sub-band / port / other index can transmit the correct position of the signal to the TF when part of the signal is omitted (not reported from the UE).

[0265] FIG. 15 shows the case of S = 6, T = 2, r = 0, 1) in the above-described Example 3 (the case of i = s + S(t + Tr)).

[0266] As shown in FIG. 15, at t = 0 of the real part (r = 0), i = 0 to 5 correspond, and then at t = 1 of the real part, i = 6 to 11 correspond. Further, at t = 0 of the imaginary part (r = 1), i = 12 to 17 correspond, and then at t = 1 of the imaginary part, i = 18 to 23 correspond.

[0267] Thus, in the example of FIG. 15, the index (i) may be assigned / determined in ascending order of real part / time domain resource / imaginary part / time domain resource.

[0268] According to Embodiment 3.2, the signal position-based positional encoding method becomes clear. In particular, since the UE can generate a specific signal without using padding, it is possible to reduce the complexity of the model.

[0269] <Supplementary> <<Notification of Information to UE / BS>> Notification of any information from [Network (NW) (e.g., Base Station (BS)) / NW node] to UE / BS in the above-described embodiment (in other words, reception of any information from BS / NW node in UE / BS) may be performed using physical layer signaling (e.g., DCI), upper layer signaling (e.g., RRC signaling, MAC CE, NAS signaling, LPP message, NRPPa message), a specific signal / channel (e.g., PDCCH, PDSCH, reference signal), or a combination thereof.

[0270] When the above notification is performed by a MAC CE, the MAC CE may be identified by including a new logical channel ID (LCID) not defined in the existing standard in the MAC sub-header.

[0271] When the above notification is performed by DCI, the above notification may be performed by a specific field of the DCI, a radio network temporary identifier (RNTI) used for scrambling cyclic redundancy check (CRC) bits assigned to the DCI, the format of the DCI, etc.

[0272] Also, the notification of any information to the UE / BS in the above-described embodiment may be performed periodically, semi-persistently, or aperiodically. The notification of semi-persistent or aperiodic information may be triggered by an instruction from the UE / BS / NW.

[0273] In the above-described embodiment, the information from the NW may be set / instructed by any one or a combination of the following methods: · Common to multiple UEs or UE-specific (for each UE), · Common to multiple BSs or BS-specific (for each BS), · Common to a plurality of frequencies (e.g., one or a combination of a cell, a band, a band combination, a bandwidth part (BWP), a component carrier, etc.) (e.g., cell-common) or frequency-specific (for each frequency, e.g., for each cell).

[0274] <<Notification of Information from UE / BS>> In the above-described embodiments, notification of any information from the UE / BS [to the NW] (in other words, transmission / reporting of any information from the UE / BS to the BS / NW node) may be performed using physical layer signaling (e.g., UCI), higher layer signaling (e.g., RRC signaling, MAC CE, NAS signaling, LPP message, NRPPa message), specific signals / channels (e.g., PUCCH, PUSCH, PRACH, reference signal), or a combination thereof.

[0275] When the notification is performed by a MAC CE, the MAC CE may be identified by including a new LCID in the MAC subheader that is not defined in existing standards.

[0276] If the notification is performed by UCI, the notification may be transmitted using PUCCH or PUSCH.

[0277] In addition, any information notification from the UE / BS in the above-mentioned embodiments may be performed periodically, semi-persistently, or aperiodically. Notification of semi-persistent or aperiodic information may be triggered by an instruction from the UE / BS / NW.

[0278] <<Application of each embodiment>> In a UE / BS, a specific (e.g., one or more, or part of) process / operation / control / assumption / information of at least one of the above-described embodiments may be applied (used) when one or more of the following conditions are met: Upper layer parameters indicating the above specific processing / operation / control / assumment / information are set in the UE / BS; The specific processing / operation / control / assumption / information is determined in the UE / BS based on relevant higher layer parameters; The above specific process / operation / control / assumption / information is specified / activated / triggered to the UE / BS by the MAC CE / DCI / UCI / resource / channel / RS, The UE / BS reports or supports specific capabilities (e.g., UE capabilities) that indicate (or relate to) the specific processing / action / control / assumptions / information. The application of the above specific processing / operation / control / assumption / information is determined in the UE / BS based on specific conditions.

[0279] The specified capabilities may indicate at least one of the following: Supporting the above specific processes / actions / controls / assumptions / information; Supporting AI-based feedback, -Parameter values ​​for supporting matrices.

[0280] In the present disclosure, "supporting" and "whether to support" may be read interchangeably.

[0281] Furthermore, the above-mentioned specific capabilities may be capabilities that are applied across all frequencies (commonly regardless of frequency), capabilities for each frequency (e.g., one or a combination of a cell, band, band combination, BWP, component carrier, etc.), capabilities for each frequency range (e.g., Frequency Range 1 (FR1), FR2, FR3, FR4, FR5, FR2-1, FR2-2), capabilities for each subcarrier spacing (SubCarrier Spacing (SCS)), or capabilities for each Feature Set (FS) or Feature Set Per Component-carrier (FSPC).

[0282] Furthermore, the above-mentioned specific capabilities may be capabilities that are applied across all duplexing methods (commonly regardless of the duplexing method), or may be capabilities for each duplexing method (for example, Time Division Duplex (TDD) or Frequency Division Duplex (FDD)).

[0283] If the above conditions are not met, the UE / BS may follow the behavior specified in existing 3GPP releases.

[0284] (Addendum) The following inventions are added regarding one embodiment of the present disclosure. [Appendix 1] a receiver for receiving a configuration for Channel State Information (CSI) compression using an artificial intelligence (AI) model; a control unit that performs the CSI compression based on the setting; The control unit controls positional encoding for generating specific signals based on the correspondence between tokens and features for input to the AI ​​model. [Appendix 2] 2. The terminal of claim 1, wherein the positional encoding is token-based positional encoding or signal position-based positional encoding. [Appendix 3] 3. The terminal according to claim 1, wherein the control unit controls addition of zero signals to signals representing CSI based on whether padding is applied to the signals representing CSI. [Appendix 4] 4. The terminal of claim 1, wherein the controller generates the particular signal based on an index generated based on at least one parameter of a layer, a transmission port, a frequency domain resource, a time domain resource, a signal portion, and a signal block. [Appendix 5] receiving a configuration for Channel State Information (CSI) compression using an artificial intelligence (AI) model; performing the CSI compression based on the setting; A wireless communication method for a terminal, in which the terminal controls positional encoding for generating a specific signal based on the correspondence between tokens and features for the input to the AI ​​model. [Appendix 6] a transmitter that transmits configuration for Channel State Information (CSI) compression using an artificial intelligence (AI) model; a control unit that performs the CSI compression based on the setting; The control unit controls positional encoding for generating a specific signal based on the correspondence between tokens and features for the input to the AI ​​model.

[0285] (wireless communication system) The configuration of a wireless communication system according to an embodiment of the present disclosure will be described below. In this wireless communication system, communication is performed using any one of the wireless communication methods according to the above embodiments of the present disclosure or a combination thereof.

[0286] 16 is a diagram illustrating an example of a schematic configuration of a wireless communication system according to an embodiment of the present disclosure. The wireless communication system 1 (which may be simply referred to as system 1) may be a system that realizes communication using Long Term Evolution (LTE), 5th generation mobile communication system New Radio (5G NR), or the like, which are specified by the Third Generation Partnership Project (3GPP).

[0287] The wireless communication system 1 may also support dual connectivity between multiple Radio Access Technologies (RATs) (Multi-RAT Dual Connectivity (MR-DC)). MR-DC may include dual connectivity between LTE (Evolved Universal Terrestrial Radio Access (E-UTRA)) and NR (E-UTRA-NR Dual Connectivity (EN-DC)), dual connectivity between NR and LTE (NR-E-UTRA Dual Connectivity (NE-DC)), etc.

[0288] In EN-DC, the LTE (E-UTRA) base station (eNB) is the master node (MN), and the NR base station (gNB) is the secondary node (SN). In NE-DC, the NR base station (gNB) is the MN, and the LTE (E-UTRA) base station (eNB) is the SN.

[0289] The wireless communication system 1 may support dual connectivity between multiple base stations within the same RAT (for example, dual connectivity in which both the MN and the SN are NR base stations (gNBs) (NR-NR Dual Connectivity (NN-DC))).

[0290] The wireless communication system 1 may include a base station 11 that forms a macrocell C1 with a relatively wide coverage, and base stations 12 (12a-12c) that are arranged within the macrocell C1 and form small cells C2 that are smaller than the macrocell C1. A terminal 20 may be located within at least one of the cells. The arrangement, number, shape, size, etc. of each cell and terminal 20 are not limited to the embodiment shown in the figure. Hereinafter, when there is no need to distinguish between the base stations 11 and 12, they will be collectively referred to as base station 10.

[0291] The wireless communication system 1 may utilize Multi Input Multi Output (MIMO). For example, one cell may be formed by one antenna / base station 10, or may be formed by multiple antennas / base stations 10. One [virtual] cell (which may be called, for example, a super cell) may be composed of multiple [virtual] cells (which may be called, for example, sub-cells). A super cell may correspond to a cell whose physical range is fixed, and a sub-cell may correspond to a cell whose physical range varies semi-statically / dynamically. In this case, the wireless communication system 1 may be called a cell-free system.

[0292] The terminal 20 may be connected to at least one of the multiple base stations 10. The terminal 20 may use at least one of carrier aggregation (CA) using multiple component carriers (CC) and dual connectivity (DC).

[0293] Each CC may be included in at least one of a first frequency band (Frequency Range 1 (FR1)) and a second frequency band (Frequency Range 2 (FR2)). The macro cell C1 may be included in FR1, and the small cell C2 may be included in FR2. For example, FR1 may be a frequency band of 6 GHz or less (sub-6 GHz), and FR2 may be a frequency band above 24 GHz (above-24 GHz). Note that the frequency bands and definitions of FR1 and FR2 are not limited to these, and for example, FR1 may be a frequency band higher than FR2.

[0294] Furthermore, the terminal 20 may perform communication using at least one of Time Division Duplex (TDD) and Frequency Division Duplex (FDD) in each CC.

[0295] The multiple base stations 10 may be connected by wire (for example, optical fiber conforming to the Common Public Radio Interface (CPRI), an X2 / Xn interface, etc.) or wirelessly (for example, NR communication). For example, when NR communication is used as a backhaul between the base stations 11 and 12, the base station 11 corresponding to the upper station may be called an Integrated Access Backhaul (IAB) donor, and the base station 12 corresponding to the relay station (relay) may be called an IAB node.

[0296] The base station 10 may be connected to the core network 30 directly or via another base station 10. The core network 30 may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN, 5GC), a Next Generation Core (NGC), and the like.

[0297] The core network 30 may include network functions (Network Functions (NFs)) such as a User Plane Function (UPF), an Access and Mobility management Function (AMF), a Session Management Function (SMF), a Unified Data Management (UDM), an Application Function (AF), a Data Network (DN), a Location Management Function (LMF), and Operation, Administration and Maintenance (Management) (OAM). Note that a single network node (which may simply be referred to as a node) may provide multiple functions. Furthermore, communication with an external network (e.g., the Internet) may be performed via the DN.

[0298] The terminal 20 may be a terminal compatible with at least one of communication methods such as LTE, LTE-A, and 5G.

[0299] An Orthogonal Frequency Division Multiplexing (OFDM)-based radio access scheme may be used in the radio communication system 1. For example, Cyclic Prefix OFDM (CP-OFDM), Discrete Fourier Transform Spread OFDM (DFT-s-OFDM), Orthogonal Frequency Division Multiple Access (OFDMA), Single Carrier Frequency Division Multiple Access (SC-FDMA), or the like may be used in at least one of the downlink (DL) and uplink (UL).

[0300] The radio access scheme may also be called a waveform. Note that 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 UL and DL radio access schemes.

[0301] In the wireless communication system 1, a downlink shared channel (Physical Downlink Shared Channel (PDSCH)) shared by each terminal 20, a broadcast channel (Physical Broadcast Channel (PBCH)), a downlink control channel (Physical Downlink Control Channel (PDCCH)), etc. may be used as the downlink channel.

[0302] In addition, in the wireless communication system 1, an uplink shared channel (Physical Uplink Shared Channel (PUSCH)) shared by each terminal 20, an uplink control channel (Physical Uplink Control Channel (PUCCH)), a random access channel (Physical Random Access Channel (PRACH)), etc. may be used as an uplink channel.

[0303] The PDSCH transmits user data, higher layer control information, System Information Block (SIB), etc. The PUSCH may transmit user data, higher layer control information, etc. Furthermore, the PBCH may transmit Master Information Block (MIB).

[0304] Lower layer control information may be transmitted by the PDCCH. The lower layer control information may include, for example, Downlink Control Information (DCI) including scheduling information for at least one of the PDSCH and the PUSCH.

[0305] Note that the DCI for scheduling the PDSCH may be referred to as a DL assignment, a DL DCI, etc., and the DCI for scheduling the PUSCH may be referred to as an UL grant, a UL DCI, etc. Note that the PDSCH may be interpreted as DL data, and the PUSCH may be interpreted as UL data.

[0306] A control resource set (CORESET) and a search space may be used to detect the PDCCH. The CORESET corresponds to resources to search for DCI. The search space corresponds to a search region and a search method for PDCCH candidates. One CORESET may be associated with one or more search spaces. The UE may monitor a CORESET associated with a certain search space based on the search space configuration.

[0307] One search space may correspond to PDCCH candidates corresponding to one or more aggregation levels. One or more search spaces may be called a search space set. Note that the terms "search space," "search space set," "search space setting," "search space set setting," "CORESET," "CORESET setting," etc. in the present disclosure may be read interchangeably.

[0308] The PUCCH may transmit uplink control information (UCI) including at least one of channel state information (CSI), acknowledgement information (which may be called, for example, Hybrid Automatic Repeat reQuest ACKnowledgement (HARQ-ACK), ACK / NACK, etc.), and scheduling request (SR). The PRACH may transmit a random access preamble for establishing a connection with a cell.

[0309] In the present disclosure, downlink, uplink, etc. may be expressed without adding "link." Also, various channels may be expressed without adding "Physical" to the beginning.

[0310] In the wireless communication system 1, a synchronization signal (SS), a downlink reference signal (DL-RS), etc. may be transmitted. In the wireless communication system 1, a cell-specific reference signal (CRS), a channel state information reference signal (CSI-RS), a demodulation reference signal (DMRS), a positioning reference signal (PRS), a phase tracking reference signal (PTRS), etc. may be transmitted as DL-RS.

[0311] 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 the SS (PSS, SSS) and the PBCH (and DMRS for the PBCH) may be referred to as an SS / PBCH block, an SS Block (SSB), or the like. Note that the SS, SSB, and the like may also be referred to as reference signals.

[0312] Furthermore, in the wireless communication system 1, a sounding reference signal (SRS), a demodulation reference signal (DMRS), etc. may be transmitted as an uplink reference signal (UL-RS). Note that the DMRS may also be called a user equipment-specific reference signal (UE-specific reference signal).

[0313] (base station) 17 is a diagram illustrating an example of the configuration of a base station according to an embodiment of the present disclosure. The base station 10 includes a control unit 110, a transceiver unit 120, a transceiver antenna 130, and a transmission line interface 140. Note that the base station may include one or more of each of the control unit 110, the transceiver unit 120, the transceiver antenna 130, and the transmission line interface 140.

[0314] In this example, the functional blocks of the characteristic parts of the present embodiment are mainly shown, and it may be assumed that the base station 10 also has other functional blocks necessary for wireless communication. Some of the processing of each unit described below may be omitted.

[0315] The control unit 110 performs overall control of the base station 10. The control unit 110 can be configured from a controller, a control circuit, and the like that are explained based on common understanding in the technical field to which the present disclosure relates.

[0316] The control unit 110 may control signal generation, scheduling (e.g., resource allocation, mapping), etc. The control unit 110 may control transmission and reception using the transceiver unit 120, the transceiver antenna 130, and the transmission path interface 140, measurement, etc. The control unit 110 may generate data to be transmitted as signals, control information, sequences, etc., and transfer them to the transceiver unit 120. The control unit 110 may perform call processing (setting up, releasing, etc.) of communication channels, status management of the base station 10, management of radio resources, etc.

[0317] The transceiver unit 120 may include a baseband unit 121, a radio frequency (RF) unit 122, and a measurement unit 123. The baseband unit 121 may include a transmission processing unit 1211 and a reception processing unit 1212. The transceiver unit 120 may be configured with a transmitter / receiver, an RF circuit, a baseband circuit, a filter, a phase shifter, a measurement circuit, a transceiver circuit, etc., which are described based on common understanding in the technical field related to the present disclosure.

[0318] The transmitting / receiving unit 120 may be configured as an integrated transmitting / receiving unit, or may be composed of a transmitting unit and a receiving unit. The transmitting unit may be composed of a transmission processing unit 1211 and an RF unit 122. The receiving unit may be composed of a reception processing unit 1212, an RF unit 122, and a measurement unit 123.

[0319] The transmitting and receiving antenna 130 can be configured from an antenna described based on common understanding in the technical field to which the present disclosure pertains, such as an array antenna.

[0320] The transceiver 120 may transmit the above-mentioned downlink channel, synchronization signal, downlink reference signal, etc. The transceiver 120 may receive the above-mentioned uplink channel, uplink reference signal, etc.

[0321] The transceiver 120 may form at least one of a transmission beam and a reception beam using digital beamforming (for example, precoding), analog beamforming (for example, phase rotation), or the like.

[0322] The transceiver 120 (transmission processing unit 1211) may 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 data, control information, etc. obtained from the control unit 110, and generate a bit string to be transmitted.

[0323] The transceiver 120 (transmission processor 1211) may perform transmission processing such as channel coding (which may include error correction coding), modulation, mapping, filtering, Discrete Fourier Transform (DFT) processing (if necessary), Inverse Fast Fourier Transform (IFFT) processing, precoding, and digital-to-analog conversion on the bit string to be transmitted, and output a baseband signal.

[0324] The transmitting / receiving unit 120 (RF unit 122) may perform modulation to a radio frequency band, filtering, amplification, etc. on the baseband signal, and transmit the radio frequency band signal via the transmitting / receiving antenna .

[0325] On the other hand, the transmitting / receiving unit 120 (RF unit 122) may perform amplification, filtering, demodulation to a baseband signal, etc. on the radio frequency band signal received by the transmitting / receiving antenna .

[0326] The transceiver 120 (reception processing unit 1212) may apply reception processing such as analog-to-digital conversion, Fast Fourier Transform (FFT) processing, Inverse Discrete Fourier Transform (IDFT) processing (if necessary), filtering, demapping, demodulation, decoding (which may include error correction decoding), MAC layer processing, RLC layer processing, and PDCP layer processing to the acquired baseband signal, thereby acquiring user data, etc.

[0327] The transceiver 120 (measurement unit 123) may perform measurements on the received signal. For example, the measurement unit 123 may perform Radio Resource Management (RRM) measurements, Channel State Information (CSI) measurements, etc. based on the received signal. The measurement unit 123 may 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 be output to the control unit 110.

[0328] The transmission path interface 140 may transmit and receive signals (backhaul signaling) between devices included in the core network 30 (e.g., network nodes providing NFs), other base stations 10, etc., and may acquire and transmit user data (user plane data), control plane data, etc. for the terminal 20.

[0329] The transmitting section and receiving section of the base station 10 in the present disclosure may be configured by at least one of the transmitting / receiving section 120, the transmitting / receiving antenna 130, and the transmission path interface 140.

[0330] The base station 10 may be separated into three elements: a radio unit (RU), a distributed unit (DU), and a central unit (CU). For example, the RU may perform RF processing (digital beamforming, digital-to-analog conversion, analog beamforming, etc.) and lower-level functions of the physical layer (precoding, IFFT, FFT, etc.). The DU may perform higher-level functions of the physical layer (coding to resource element mapping, etc.), MAC layer functions, and RLC layer functions. The CU may perform PDCP layer, Service Data Adaptation Protocol (SDAP) layer, and RRC layer functions.

[0331] In the present disclosure, the base station 10 may include a single device that implements all of the functions of the RU, DU, and CU, or may include multiple devices that each implement some of the functions of the RU, DU, and CU and are connected to each other. In the present disclosure, the base station 10 may be interchangeably read as RU / DU / CU.

[0332] The control unit 110 may perform at least part of the processing of the control unit in the above appendix.

[0333] The transceiver unit 120 may perform at least part of the processing of the transmitter / receiver unit in the above appendix.

[0334] (Terminal) 18 is a diagram illustrating an example of the configuration of a terminal according to an embodiment of the present disclosure. The terminal 20 includes a control unit 210, a transceiver unit 220, and a transceiver antenna 230. Note that the terminal may include one or more of each of the control unit 210, the transceiver unit 220, and the transceiver antenna 230.

[0335] In this example, functional blocks of the characteristic parts of the present embodiment are mainly shown, and it may be assumed that the terminal 20 also has other functional blocks necessary for wireless communication. Some of the processing of each unit described below may be omitted.

[0336] The control unit 210 performs overall control of the terminal 20. The control unit 210 can be configured from a controller, a control circuit, and the like that are explained based on common understanding in the technical field to which the present disclosure relates.

[0337] The control unit 210 may control signal generation, mapping, etc. The control unit 210 may also control transmission and reception, measurement, etc. using the transceiver unit 220 and the transceiver antenna 230. The control unit 210 may generate data, control information, sequences, etc. to be transmitted as signals, and transfer them to the transceiver unit 220.

[0338] The transceiver unit 220 may include a baseband unit 221, an RF unit 222, and a measurement unit 223. The baseband unit 221 may include a transmission processing unit 2211 and a reception processing unit 2212. The transceiver unit 220 may be configured from a transmitter / receiver, an RF circuit, a baseband circuit, a filter, a phase shifter, a measurement circuit, a transceiver circuit, etc., which are described based on common understanding in the technical field related to the present disclosure.

[0339] The transmitting / receiving unit 220 may be configured as an integrated transmitting / receiving unit, or may be composed of a transmitting unit and a receiving unit. The transmitting unit may be composed of a transmission processing unit 2211 and an RF unit 222. The receiving unit may be composed of a reception processing unit 2212, an RF unit 222, and a measurement unit 223.

[0340] The transmitting / receiving antenna 230 can be configured as an antenna described based on common understanding in the technical field to which the present disclosure pertains, such as an array antenna.

[0341] The transceiver 220 may receive the above-mentioned downlink channel, synchronization signal, downlink reference signal, etc. The transceiver 220 may transmit the above-mentioned uplink channel, uplink reference signal, etc.

[0342] The transceiver 220 may form at least one of a transmission beam and a reception beam using digital beamforming (for example, precoding), analog beamforming (for example, phase rotation), or the like.

[0343] The transceiver 220 (transmission processing unit 2211) may perform PDCP layer processing, RLC layer processing (e.g., RLC retransmission control), MAC layer processing (e.g., HARQ retransmission control), etc. on data, control information, etc. obtained from the control unit 210, and generate a bit string to be transmitted.

[0344] The transceiver 220 (transmission processor 2211) may perform transmission processing such as channel coding (which may include error correction coding), modulation, mapping, filtering, DFT processing (if necessary), IFFT processing, precoding, and digital-to-analog conversion on the bit string to be transmitted, and output a baseband signal.

[0345] Whether or not to apply DFT processing may be based on the setting of transform precoding. When transform precoding is enabled for a certain channel (e.g., PUSCH), the transceiver unit 220 (transmission processing unit 2211) may perform DFT processing as the transmission processing to transmit the channel using a DFT-s-OFDM waveform, and when transform precoding is not enabled, the transceiver unit 220 may not perform DFT processing as the transmission processing.

[0346] The transmitting / receiving unit 220 (RF unit 222) may perform modulation to a radio frequency band, filtering, amplification, etc. on the baseband signal, and transmit the radio frequency band signal via the transmitting / receiving antenna 230.

[0347] On the other hand, the transmitting / receiving unit 220 (RF unit 222) may perform amplification, filtering, demodulation to a baseband signal, etc. on the radio frequency band signal received by the transmitting / receiving antenna 230.

[0348] The transceiver 220 (reception processing unit 2212) may apply reception processing such as analog-to-digital conversion, FFT processing, IDFT processing (if necessary), filtering, demapping, demodulation, decoding (which may include error correction decoding), MAC layer processing, RLC layer processing, and PDCP layer processing to the acquired baseband signal to acquire user data, etc.

[0349] The transceiver 220 (measurement unit 223) may perform measurements on the received signal. For example, the measurement unit 223 may perform RRM measurement, CSI measurement, etc. based on the received signal. The measurement unit 223 may measure received power (e.g., RSRP), received quality (e.g., RSRQ, SINR, SNR), signal strength (e.g., RSSI), propagation path information (e.g., CSI), etc. The measurement results may be output to the control unit 210.

[0350] The measurement unit 223 may derive channel measurements for CSI calculation based on the channel measurement resources. The channel measurement resources may be, for example, non-zero power (NZP) CSI-RS resources. The measurement unit 223 may also derive interference measurements for CSI calculation based on the interference measurement resources. The interference measurement resources may be at least one of an NZP CSI-RS resource for interference measurement, a CSI-Interference Measurement (IM) resource, etc. Note that CSI-IM may be referred to as CSI-Interference Management (IM) or may be interchangeably read as Zero Power (ZP) CSI-RS. Note that in the present disclosure, CSI-RS, NZP CSI-RS, ZP CSI-RS, CSI-IM, CSI-SSB, etc. may be interchangeably read as interchangeable.

[0351] The transmitting section and receiving section of the terminal 20 in the present disclosure may be configured by at least one of the transmitting / receiving section 220 and the transmitting / receiving antenna 230.

[0352] The control unit 210 may perform at least part of the processing of the control unit in the above appendix.

[0353] The transceiver unit 220 may perform at least part of the processing of the transmitter / receiver unit in the above appendix.

[0354] The tokens correspond to subbands and the features correspond to transmitting ports, or the tokens correspond to transmitting ports and the features correspond to subbands, or a subblock consisting of a matrix of subbands and tokens is applied as the tokens.

[0355] The input-related parameters include at least one of a layer index, a port index, a frequency domain resource index, a time domain resource index, and a precoder sub-index.

[0356] (Hardware configuration) The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by hardware, software, or a combination of these. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized by using a single device that is physically or logically coupled, or may be realized by using two or more physically or logically separated devices that are connected directly or indirectly (for example, by wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or the multiple devices with software.

[0357] For example, a base station, a terminal, a network node, etc. according to an embodiment of the present disclosure may function as a computer that performs processing of the wireless communication method of the present disclosure. Fig. 19 is a diagram illustrating an example of the hardware configuration of a base station and a terminal according to an embodiment of the present disclosure. The above-described base station 10 and terminal 20 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0358] In the present disclosure, any two terms selected from a set of terms such as apparatus, circuit, device, section, unit, module, chip, means, etc. may be read as interchangeable. The hardware configurations of the base station 10 and the terminal 20 may be configured to include one or more of the devices shown in the drawings, or may be configured to exclude some of the devices.

[0359] Each function in the base station 10 and the terminal 20 is realized, for example, by loading predetermined software (programs) onto hardware such as the processor 1001 and the memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control the reading, writing, or both reading and writing of data in the memory 1002 and the storage 1003.

[0360] The processor 1001, for example, runs an operating system to control the entire computer. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, at least a part of the above-mentioned control unit 110 (210), transceiver unit 120 (220), etc. may be realized by the processor 1001. Although only one processor 1001 is shown in the figure, there may be multiple processors.

[0361] The processor 1001 also reads programs (program codes), software modules, data, etc. from the storage 1003, the communication device 1004, or both the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the control unit 110 (210) may be realized by a control program stored in the memory 1002 and running on the processor 1001, and the other functional blocks may be realized in a similar manner.

[0362] The various processes described above may be performed by one processor 1001, or may be performed by two or more processors 1001 simultaneously, sequentially, or using other techniques. The processor 1001 may be implemented by one or more chips. The program may be transmitted from a network via a telecommunications line, or may be provided to the computer device via, for example, the communication device 1004.

[0363] The present disclosure also provides a computer program product including a computer program, which may implement the steps of the methods described in the above embodiments when the computer program is executed by a computer (e.g., the processor 1001).

[0364] The memory 1002 is a non-transitory computer-readable recording medium and may be configured, for example, by a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically EEPROM (EEPROM), a random access memory (RAM), or a combination of at least two of these. The memory 1002 may also be referred to as a register, a cache, a main memory, or the like. The memory 1002 may store executable programs (program codes), software modules, and the like for implementing a wireless communication method according to one embodiment of the present disclosure.

[0365] Storage 1003 is a non-transitory computer-readable recording medium, and may be, for example, a flexible disk, a floppy disk, an optical disk (e.g., a compact disc (e.g., a Compact Disc ROM (CD-ROM)), a digital versatile disc, a Blu-ray disc), a magneto-optical disk, a removable disk, a hard disk drive, a smart card, a flash memory (e.g., a card, stick, key drive), a magnetic stripe, or the like, or a combination of at least two of these. Storage 1003 may also be referred to as a secondary storage device.

[0366] The above-mentioned recording medium may be, for example, the memory 1002, the storage 1003, or a database including both the memory 1002 and the storage 1003, a server, or other suitable medium.

[0367] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via a wired network, a wireless network, or both 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. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc., or a combination of at least two of these. For example, the above-mentioned transmission / reception unit 120 (220), transmission / reception antenna 130 (230), etc. may be realized by the communication device 1004. The transmission / reception unit 120 (220) may be implemented as a transmission unit 120a (220a) and a reception unit 120b (220b) that are physically or logically separated.

[0368] The input device 1005 is an input device that accepts input from the outside (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc., or a combination of at least two of these). The output device 1006 is an output device that performs output to the outside (for example, a display, a speaker, a Light Emitting Diode (LED) lamp, etc., or a combination of at least two of these). Note that the input device 1005 and the output device 1006 may be integrated into one device (for example, a touch panel).

[0369] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0370] Furthermore, base station 10 and terminal 20 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), a graphics processing unit (GPU), a neural processing unit (NPU), or a combination of at least two of these, and some or all of the functional blocks may be realized using such hardware. For example, processor 1001 may be implemented using at least one of these hardware elements.

[0371] In this disclosure, the term "processor" may encompass a single processor or a group of multiple processors, including, for example, a single-core processor, a multi-core processor, multiple processors in a single device, multiple processors in wired or wireless communication with each other, etc. Similarly, the term "(non-transitory) computer-readable storage medium" may encompass a single storage medium or a group of multiple storage media, including multiple storage media in wired or wireless communication with each other.

[0372] Devices such as processors and storage media in the present disclosure may be distributed locally or remotely, and may perform the processing of the devices by operating cooperatively or independently using a bus, network, the Internet, the cloud, etc.

[0373] Note that the devices included in the core network 30 (for example, network nodes that provide NFs) may also be realized by the above-described functional block / hardware configuration.

[0374] (Variation) Each aspect / embodiment described in the present disclosure may be a mobile communication system other than Long Term Evolution (LTE), LTE-Advanced (LTE-A), International Mobile Telecommunications-Advanced (IMT-Advanced), 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G-Advanced (5G-A), 6th generation mobile communication system (6G), xth generation mobile communication system (xG (x is, for example, an integer or a decimal number)), Future Radio Access (FRA), New Radio (NR), New radio access (NX), Future generation radio access (FX), Open Radio Access Network (Open RAN (O-RAN)), Wideband Code Division Multiple Access (W-CDMA (registered trademark)), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), Institute of Electrical and Electronics Engineers (IEEE) 802.11, IEEE 802.11x (where x is any character string such as b, a, g, n, ac, ax, be, or bn, and when x = n, it is called Wi-Fi 4, when x = ac, it is called Wi-Fi 5, when x = ax, it is called Wi-Fi 6 or Wi-Fi 6E, when x = be, it is called Wi-Fi 7, and when x = bn, it is called Wi-Fi 8.Note that the present disclosure may be applied to systems based on technologies such as Wi-Fi (a registered trademark), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), network virtualization technologies (e.g., Network Function Virtualization (NFV), Service Function Chaining (SFC), Software Defined Networking (SDN)), or Low Power Wide Area (LPWA). Furthermore, each aspect / embodiment described in the present disclosure may be applied to a system based on a combination of at least two of these technologies. Here, "based on" naturally refers not only to a system that uses the technology in question, but also to a system that uses an extension or modification of the technology.

[0375] In the present disclosure, any two terms selected from a set of terms such as "Base Station (BS)", "Radio Base Station", "Fixed Station", "NodeB", "eNodeB (eNB)", "gNodeB (gNB)", "Access Point (AP)", "Transmission Point (TP)", "Reception Point (RP)", "Transmission / Reception Point (TRP)", "Radio Unit (RU)", "Remote Unit (RU)", "Control Unit (CU)", "Distributed Unit (DU)", "Remote Radio Head (RRH)", "node", "gateway", "terrestrial base station", "stratospheric base station", "unmanned aerial vehicle", "High Altitude Platform Station (HAPS)", "airborne platform", "panel", "cell", "Radio Access Network (RAN)", "network", etc. may be used interchangeably. Each cell accommodated by a base station may be referred to by terms such as a macro cell, a small cell, a femto cell, a pico cell, a serving cell, a super cell, etc. In the present disclosure, any two terms selected from a set of terms such as "cell," "sector," "cell group," "carrier," "component carrier," "cluster," "bandwidth part (BWP)," and "carrier bandwidth" may be used interchangeably.

[0376] In the present disclosure, any two terms selected from the set of terms such as "Mobile Station (MS)", "user terminal", "User Equipment (UE)", "Device", "Module", "Terminal", etc. may be used interchangeably.

[0377] A terminal may 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, handset, user agent, mobile client, client, router (e.g., home router, mobile router, etc.), Telematics Control Unit (TCU), or some other suitable terminology.

[0378] The base station and the terminal may each be composed of one or more devices. The devices constituting at least a part of the base station and the terminal may be called a transmitting device, a receiving device, a [wireless] communication device, etc. In addition, the devices constituting at least a portion of each of the base stations and terminals may be objects themselves, such as vehicles, transport vehicles, automobiles, motorcycles, bicycles, connected cars, excavators, bulldozers, wheel loaders, dump trucks, forklifts, trains, buses, handcars, rickshaws, ships and other watercraft, airplanes, rockets, unmanned aerial vehicles, stratospheric base stations (e.g., High Altitude Platform Stations (HAPS)), artificial satellites (e.g., Low Earth Orbit (LEO) satellites, Middle Earth Orbit (MEO) satellites, Geostationary Earth Orbit (GEO) satellites), drones (registered trademark), multicopters, quadcopters, balloons, Internet of Things (IoT) equipment (e.g., smart meters, sensors), etc., or may include, but are not limited to, objects or devices mounted on such objects. Furthermore, the object may be a moving object (hereinafter referred to as a "moving object"; this does not exclude the case where the moving object is stationary and not moving), or may be a fixedly positioned object (hereinafter referred to as a "non-moving object").

[0379] Furthermore, a base station in the present disclosure may be read as a terminal. For example, the aspects / embodiments of the present disclosure may be applied to a configuration in which communication between a base station and a terminal is replaced with communication between multiple terminals (which may be called, for example, Device-to-Device (D2D) or Vehicle-to-Everything (V2X)) or communication in a non-terrestrial network (Non-Terrestrial Network (NTN)). In this case, the terminal 20 may be configured to have the functions of the base station 10 described above. Furthermore, terms such as "uplink" and "downlink" may be read as terms corresponding to communication between terminals (for example, "sidelink") or terms corresponding to NTN (for example, feeder link, service link). For example, terms such as uplink channel and downlink channel may be read as sidelink channel.

[0380] The present disclosure is also applicable to cases where at least some of the devices constituting the base station and the terminal operate outside the earth (for example, in the atmosphere or outer space).

[0381] Similarly, the term "terminal" in the present disclosure may be read as "base station." In this case, the base station 10 may be configured to have the functions of the terminal 20 described above.

[0382] In the present disclosure, an operation described as being performed by a base station may be performed by its upper node or by some of its upper nodes (e.g., CU, RU, DU, etc.) in some cases. It is clear that various operations performed for communication with a terminal in a RAN or core network may be performed by at least some of the base station and other network nodes other than the base station. The other network node may be one node or a combination of multiple nodes. The network node is, for example, a node provided in various core networks such as an Evolved Packet Core (EPC) or a 5G Core Network (5GCN, 5GC), and provides one or more network functions (Network Functions (NFs)), but is not limited to these.

[0383] Furthermore, in the present disclosure, the operation of "a terminal receives information from a base station" accompanies the operation of "the base station transmits the information to the terminal," "the base station generates the information," or both. Similarly, the operation of "a terminal transmits information to a base station" accompanies the operation of "the base station receives the information from the terminal." Furthermore, operations such as "a terminal is configured to ..." or "configure UE to ..." may include the operation of "a base station transmits configuration information regarding the configuration of the terminal" or "a terminal configures a predetermined operation based on the configuration information."

[0384] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information in the present disclosure may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB)), Medium Access Control (MAC) signaling), other signals, or a combination of at least two of them.

[0385] The physical layer signaling may be referred to as Layer 1 (L1) control information. The MAC signaling may be referred to as, for example, a MAC Control Element (CE) or a MAC Protocol Data Unit (PDU). The RRC signaling may be referred to as an RRC message or an information element (IE) in the RRC message. The RRC signaling may be, for example, a message used for controlling an RRC connection (e.g., setup, reconfiguration, establishment, reestablishment, release, or resume), mobility, a measurement report, notification of terminal capabilities, or an information element in the message.

[0386] Furthermore, notification of information may be either explicit or implicit. Note that an explicit notification of certain information means notification of the certain information itself, and an implicit notification of certain information may mean notification of information other than the certain information, or the certain information being deemed to have been notified when a certain condition is met.

[0387] Furthermore, notification of information may include not only notification between the same layers of different devices (for example, between a lower layer or an upper layer of the base station 10 and the terminal 20) but also notification between different layers in the same or different devices (for example, between a lower layer and an upper layer in the base station 10 or the terminal 20). Furthermore, notification of information from one device to another device may be performed via one or more devices.

[0388] With respect to any information (e.g., variables, constants, parameters, settings) described in the present disclosure, even if not specifically stated in the above embodiments, any first device (e.g., terminal / base station) may notify any second device (e.g., base station / terminal) of information indicating / identifying (or relating to) the value of the any information.

[0389] Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched depending on the implementation. Furthermore, the order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed as long as it is consistent. For example, the methods described in this disclosure present various step elements using an exemplary order and are not limited to the particular order presented. Furthermore, at least one step may be omitted in the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure.

[0390] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0391] In the present disclosure, a radio resource may be defined by a combination of resource units in one or more domains, such as the time domain, the frequency domain, the spatial domain, the code domain, and the power domain.

[0392] For example, a resource in the time domain (which may be referred to as a time resource) may be defined by one or more time units. The one or more time units may include, but are not limited to, a radio frame, a subframe, a slot, a symbol, a transmission time interval (TTI), or a combination of at least two of these. Furthermore, the time unit may be a fixed-length time unit that is independent of numerology, a variable-length time unit that is dependent on numerology, or both.

[0393] Examples of fixed-length time units include, but are not limited to, subframes each consisting of one or more slots and radio frames each including multiple subframes. Examples of variable-length time units include, but are not limited to, symbols and slots each including a fixed number of symbols. A certain time unit may be divided into time units shorter than the certain time unit. Examples of such shorter time units include, but are not limited to, minislots each consisting of fewer symbols than the number of symbols that make up a slot. The above-described time units may include time units used as units for scheduling, link adaptation, and the like. Any time unit in the present disclosure may be interchangeable with another time unit.

[0394] Numerology is a parameter that defines the physical layer structure, and may be a parameter based on at least one of the subcarrier spacing (SCS), the symbol length, the cyclic prefix length, and the sampling time, for example.

[0395] A resource in the frequency domain (which may also be referred to as a frequency domain resource) may be defined by, for example, one or more frequency units. The one or more frequency units may include, for example, a subcarrier, a resource block (RB), a bandwidth part (BWP), a carrier bandwidth, or a combination of at least two of these, but the name of the frequency unit is not limited to these. Furthermore, the number of subcarriers included in a certain frequency unit may be a fixed number regardless of numerology, or may be a variable number that changes depending on numerology.

[0396] For example, an RB is composed of a predetermined number of consecutive subcarriers in the frequency domain, and the number of subcarriers included in the RB may be the same regardless of numerology, for example, 12, but is not limited to this. Also, a BWP may be composed of, for example, one or more consecutive RBs within a certain carrier bandwidth, but is not limited to this. One or more BWPs may be configured within one carrier for terminal 20, and at least one of the BWPs may be activated. Also, any frequency unit in the present disclosure may be interpreted as another frequency unit.

[0397] Furthermore, resources in both the time domain and the frequency domain may be defined by one or more time / frequency units each consisting of a time unit and a frequency unit, such as, but not limited to, a resource element (RE) consisting of one symbol and one subcarrier, a resource element group (REG) consisting of a predetermined number of REs, or a control resource set (CORESET) consisting of a predetermined number of symbols and a predetermined number of RBs.

[0398] The resources in the spatial domain (which may also be referred to as spatial resources) may be defined, for example, by one or more spatial units, including, but not limited to, beams, layers of Multi-Input Multi-Output (MIMO), antenna ports, etc., or a combination of at least two of them.

[0399] The resource in the code domain (which may also be referred to as a code resource) may be defined by, for example, one or more code units, including, but not limited to, a Cyclic Shift (CS), an Orthogonal Cover Code (OCC), or a combination thereof.

[0400] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0401] In the present disclosure, terms such as "decide," "determine," "judge," "select," "specify," "compute," "calculate," "process," "derive," "look up / search / inquiry," "confirm," "assume," "expect," and "consider" may be read interchangeably. Also, in the present disclosure, performing a certain process (e.g., sending, receiving) may be read interchangeably as deciding to perform that process. Also, in the present disclosure, "not expected to do..." may be read interchangeably as "assumed not to do...."

[0402] In the present disclosure, "expect" may be interchangeably read as "be expected." For example, "expect(s) ..." ("..." may be expressed, for example, as a that clause, a to-infinitive, etc.) may be interchangeably read as "be expected ...," "do ... (if the above "..." is a to-infinitive, a verb with "to")," etc. "does not expect ..." may be interchangeably read as "be not expected ...," "does not ... (if the above "..." is a to-infinitive, a verb with "to")," etc. Furthermore, "An apparatus A is not expected ..." may be interchangeably read as "an apparatus B other than apparatus A does not expect ... from apparatus A" (for example, if apparatus A is a UE, apparatus B may be a base station).

[0403] In the present disclosure, terms such as "less than or equal to," "less than," "greater than," "more than," "equal to," etc. may be interchangeable. Furthermore, in the present disclosure, terms meaning "good," "bad," "big," "small," "high," "low," "fast," "slow," "wide," "narrow," etc. may be interchangeable, not limited to the positive, comparative, and superlative. Furthermore, in the present disclosure, terms meaning "good," "bad," "big," "small," "high," "low," "fast," "slow," "wide," "narrow," etc. may be interchangeable, not limited to the positive, comparative, and superlative, as expressions with the prefix "i-th" (i is any integer) (for example, "highest" may be interchangeable as "i-th highest").

[0404] In this disclosure, the terms "of," "for," "regarding," "related to," "associated with," etc. may be read interchangeably.

[0405] In the present disclosure, terms such as "when A, B," "if A, (then) B," "B upon A," "B in response to A," "B based on A," "B during / while A," "B before A," "B at (the same time as) / on A," "B after A," "B since A," and "B until A" may be interchangeable. Note that A, B, and the like herein may be replaced with appropriate expressions, such as nouns, gerunds, and regular sentences, depending on the context. Note that the time difference between A and B may be nearly zero (immediately after or immediately before). A time offset may be applied to the time at which A occurs. For example, "A" may be interchangeable with "before / after the time offset at which A occurs." The time offset (eg, one or more symbols / slots) may be predefined or may be specified by the UE based on signaled information.

[0406] In the present disclosure, timing, time, duration, time instance, any time unit (e.g., slot, subslot, symbol, subframe), period, occasion, resource, etc. may be read interchangeably.

[0407] 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 relation information," "spatial domain filter," "transmit power," "phase rotation," "antenna port," "port," "layer," "number of layers," "rank," "resource," "resource set," "beam," "beam width," "beam angle," "antenna," "antenna element," "panel," "UE panel," "transmitting entity," "receiving entity," etc. may be used interchangeably.

[0408] In the present disclosure, an antenna port may be interchangeably read as an antenna port for any signal / channel (e.g., a Demodulation Reference Signal (DMRS) port). In the present disclosure, a resource may be interchangeably read as a resource for any signal / channel (e.g., a reference signal resource). Furthermore, the spatial domain filter may include at least one of a spatial domain transmission filter and a spatial domain reception filter.

[0409] In the present disclosure, beam, sounding reference signal (SRS) resource indicator (SRS Resource Indicator (SRI)), control resource set (CONTROLLER RESOLUTION SET (CORESET)), CORESET pool, uplink shared channel (Physical Downlink Shared Channel (PDSCH)), uplink shared channel (Physical Uplink Shared Channel (PUSCH)), codeword (CW), transport block (TB), reference signal (RS), etc. may be interpreted as interchangeable.

[0410] In the present disclosure, the terms TCI state, TCI, downlink TCI state (Downlink (DL) TCI state), uplink TCI state (Uplink (UL) TCI state), unified TCI state, common TCI state, joint TCI state, etc. may be read interchangeably.

[0411] Furthermore, in this disclosure, terms such as "QCL," "QCL assumptions," "QCL relationships," "QCL type information," "QCL properties," "specific QCL type (e.g., Type A, Type D) properties," and "specific QCL type (e.g., Type A, Type D)" may be interchangeable.

[0412] In this disclosure, terms such as index, identifier (ID), identity (ID), indicator, indication, resource ID, etc. may be interchangeable. In this disclosure, terms such as sequence, list, set, group, cluster, subset, etc. may be interchangeable.

[0413] In the present disclosure, a group may include, for example, at least one of a spatial relationship group, a Code Division Multiplexing (CDM) group, an RS group, a CORESET group, a Physical Uplink Control Channel (PUCCH) group, an antenna port group (e.g., a DMRS port group), a layer group, a resource group, a beam group, an antenna group, a panel group, and the like.

[0414] Information in this disclosure (e.g., variables, constants, parameters, settings) may be interchangeably read as the ID of the information. For example, TCI state and TCI state ID may be interchangeably read as the ID of the information. Also, information in this disclosure may be interchangeably read as "a set of the information," "one or more pieces of the information," etc.

[0415] Any signal / channel (e.g., PUCCH) in the present disclosure may be interchangeably read as another signal / channel (e.g., PUSCH, PDSCH, any RS). A signal / channel may be interchangeably read as a signal / channel for the same direction (e.g., UL if the certain signal / channel is in the UL direction, and DL if in the DL direction), or as a signal / channel for another direction (e.g., DL if the certain signal / channel is in the UL direction, and UL if in the DL direction). Also, in the present disclosure, descriptions related to DL communication and descriptions related to UL communication may be interchangeably read. In this case, DL (UL) operation may be interchangeably read as the corresponding UL (DL) operation. For example, reception of a PDSCH in a terminal may be interchangeably read as transmission of a PUSCH in the terminal.

[0416] In the present disclosure, terms such as "X's number," "X number," "the number of X(s)," and "a number of X(s)" may be interchangeable. Note that X here may be replaced with an appropriate expression such as a noun, a gerund, or an ordinary sentence, depending on the context. In the present disclosure, "number" may be interchangeable with terms such as maximum number, minimum number, average number, and total number. In addition, in the present disclosure, terms such as "value," "index," "number," and "quantity" may be interchangeable with each other.

[0417] Values / ranges in this disclosure may be interpreted as approximations, as if the words "about" or "approximately" were preceding the value / range. In this disclosure, "A and B are the same" (A and B are any words) may mean "A and B are identical," "A and B are almost the same," "A and B are partly the same (or partially overlapped)," "There is an error within a certain range between A and B," etc. (i.e., these words may be read interchangeably). Furthermore, in the present disclosure, A and B being the same may mean that at least part of A and at least part of B are the same (or overlapped).

[0418] In this disclosure, the terms "one embodiment," "some embodiments," "another embodiment," etc. may be used interchangeably. The appearances of phrases such as "one embodiment," "some embodiments," "another embodiment," etc. in this disclosure do not necessarily all refer to the same embodiment, nor are they necessarily meant to be mutually exclusive.

[0419] In the present disclosure, expressions such as "at least one of A and B," "at least one of A or B," "A and / or B," and "A / B" may be read interchangeably and may be understood to include "only A," "only B," or "both A and B." Furthermore, in the present disclosure, expressions such as "at least one of A, B, and C," "at least one of A, B, or C," "A, B and / or C," and "A / B / C" may be read interchangeably and may be understood to include "only A," "only B," "only C," "A and B," "B and C," "C and A," or "all of A, B, and C." Note that similar interpretations / readings can be applied to any expression in this disclosure such as "at least X of ..." (where the number of elements in "..." and X are each any number).

[0420] In the present disclosure, expressions such as "A, [and] B, and the like" / "such as A and B"," "A, [or] B, or the like" / "such as A or B"," "A, B, etc." / "A, B, and so on" / "A, B, and so forth"," and "A, B, [and / or] the others" may be read interchangeably.

[0421] In the present disclosure, expressions representing one / single X (e.g., "a X," "one X," "a single X"), expressions representing one or more Xs (e.g., "one or more X(s)," "at least one of X(s)"), and expressions representing a plurality of Xs (e.g., "Xs," "more than one X(s)," "multiple X(s)," "a plurarity of X(s)") may be read interchangeably. Note that these expressions may also be read interchangeably with expressions that include specific wording (e.g., when X is an uncountable noun, "pieces of," "amount of," etc.). For example, "a plurality of pieces of spatial relation information" may be read interchangeably as "a plurality of spatial relation information."

[0422] The present disclosure has been described above, but it is for illustrative purposes only, and the present invention is not limited to the aspects / embodiments described in the present disclosure. The present disclosure can be implemented in modified and altered forms without departing from the spirit of the invention. The present disclosure and its modifications and alterations are included in the scope of the present invention and its equivalents.

Claims

1. a receiver for receiving a configuration for Channel State Information (CSI) compression using an artificial intelligence (AI) model; a control unit that performs the CSI compression based on the setting, The control unit controls positional encoding for generating a specific signal based on the correspondence between tokens and features for the input to the AI ​​model.

2. The terminal of claim 1 , wherein the positional encoding is token-based positional encoding or signal position-based positional encoding.

3. The terminal according to claim 1 , wherein the control unit controls addition of a zero signal to the signal representing CSI based on whether padding is applied to the signal representing CSI.

4. The terminal of claim 1 , wherein the controller generates the specific signal based on an index generated based on at least one parameter of a layer, a transmission port, a frequency domain resource, a time domain resource, a signal portion, and a signal block.

5. receiving a configuration for Channel State Information (CSI) compression using an artificial intelligence (AI) model; performing the CSI compression based on the setting; A wireless communication method for a terminal, in which the terminal controls positional encoding for generating a specific signal based on the correspondence between tokens and features for the input to the AI ​​model.

6. a transmitter for transmitting configuration for Channel State Information (CSI) compression using an Artificial Intelligence (AI) model; a control unit that performs the CSI compression based on the setting, The control unit controls positional encoding for generating a specific signal based on the correspondence between tokens and features for the input to the AI ​​model.

Images