Terminal, wireless communication method, and base station

Abstract

A terminal according to one embodiment of the present disclosure is provided with: a receiving unit for receiving information for determining an application of an AI model with respect to a location based on artificial intelligence (AI); and a control unit that determines the application of the AI model on the basis of the information. According to one mode of the present disclosure, appropriate overhead reduction / channel estimation / resource utilization can be realized.

Description

Technical Field

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

[0002] In the Universal Mobile Telecommunications System (UMTS) network, Long Term Evolution (LTE) has been standardized to achieve even higher data rates and lower latency (Non-Patent Document 1). Furthermore, LTE-Advanced (3GPP Rel. 10-14) has been standardized to further enhance the capacity and sophistication of LTE (Release (Rel.) 8 and 9) (Third Generation Partnership Project (3GPP (registered trademark))).

[0003] Successor systems to LTE (e.g., also referred to as 5th generation mobile communication system (5G), 5G+ (plus), 6th generation mobile communication system (6G), New Radio (NR), 3GPP Rel. 15 and later) are also under study.

[0004] Prior art literature

[0005] Non-patent literature

[0006] Non-Patent Document 1: 3GPP TS 36.300 V8.12.0 “Evolved Universal Terrestrial Radio Access (E-UTRA) and Evolved Universal Terrestrial Radio Access Network (E-UTRAN); Overall description; Stage 2 (Release 8)”, April 2010 Summary of the Invention

[0007] Problems to be solved by the invention

[0008] Future wireless communication technologies are being researched, including the use of artificial intelligence (AI) technologies such as machine learning (ML) for network and device control and management. For example, research is underway to use AI to determine (estimate) the location (positioning) of user terminals (user devices, user equipment (UE)).

[0009] Regarding positioning, research is underway on inference and monitoring of AI models. This can be performed in both terminals (user terminals, user equipment (UE)) and base stations (BS). However, inference and monitoring within UEs and BSs using AI models for positioning has not yet been fully explored.

[0010] If the implementation method of inference / monitoring of the AI ​​model used for positioning is not properly specified, there is a concern that appropriate overhead reduction / high-precision channel estimation / efficient resource utilization cannot be achieved, which may inhibit the improvement of communication throughput / communication quality.

[0011] Therefore, one of the objects of the present disclosure is to provide a terminal, a wireless communication method, and a base station that can achieve appropriate overhead reduction / channel estimation / resource utilization.

[0012] Means for solving problems

[0013] A terminal according to one embodiment of the present disclosure includes: a receiving unit that receives information for determining application of an artificial intelligence (AI) model regarding positioning based on artificial intelligence (AI); and a control unit that determines application of the AI ​​model based on the information.

[0014] Effects of the Invention

[0015] According to one aspect of the present disclosure, appropriate overhead reduction / channel estimation / resource utilization can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a diagram showing an example of a framework for managing AI models.

[0017] Figure 2 This is a diagram showing an example of specifying an AI model.

[0018] Figure 3 This is a diagram showing an example of a UE positioning method.

[0019] Figure 4 This is a diagram showing an example of a UE positioning method.

[0020] Figure 5 This is a diagram showing an example of a UE positioning method.

[0021] Figure 6 This is a diagram showing an example of a UE positioning method.

[0022] Figure 7 This is a diagram showing an example of DL positioning based on UE.

[0023] Figure 8 This is a diagram showing an example of positioning service support based on NG-RAN.

[0024] Figure 9 This is a diagram showing an example of the positioning measurement indication process between UE / gNB.

[0025] Figure 10 This is a diagram showing an example of the start time and end time of delay in the physical layer.

[0026] Figure 11 This is a diagram showing an example of a schematic configuration of a wireless communication system according to one embodiment.

[0027] Figure 12 This is a diagram showing an example of the configuration of a base station according to one embodiment.

[0028] Figure 13 This is a diagram showing an example of the configuration of a user terminal according to one embodiment.

[0029] Figure 14 This is a diagram showing an example of the hardware configuration of a base station and a user terminal according to one embodiment.

[0030] Figure 15 This is a diagram showing an example of a vehicle according to an embodiment. DETAILED DESCRIPTION

[0031] (Application of Artificial Intelligence (AI) Technology to Wireless Communications)

[0032] Regarding future wireless communication technologies, research is underway into utilizing AI technologies such as machine learning (ML) for network and device control and management.

[0033] For example, research is underway into the use of AI technology in terminals (user terminals, user equipment (UE)) and base stations (Base Station (BS)) to improve channel state information (Channel State Information Reference Signal (CSI)) feedback (e.g., overhead reduction, improved accuracy, prediction), improve beam management (e.g., improved accuracy, prediction in the time / spatial domain), and improve position measurement (e.g., improved position estimation / prediction).

[0034] The AI ​​model may also output at least one of an estimated value, a predicted value, a selected operation, a classification, etc. based on the input information. The UE / BS may also input channel state information, reference signal measurement values, etc. into the AI ​​model, and output high-precision channel state information / measurement values / beam selection / position, future channel state information / radio link quality, etc.

[0035] In addition, in the present disclosure, AI can also be rewritten as an object (also referred to as an object, object, data, function, program, etc.) having (implementing) at least one of the following characteristics:

[0036] estimates based on observations or collected information,

[0037] Selection based on observed or collected information,

[0038] Predictions based on observations or collected information.

[0039] In this disclosure, estimation, prediction, and inference can be replaced with each other. In addition, in this disclosure, estimation, prediction, and inference can be replaced with each other.

[0040] In the present disclosure, an object may also be, for example, a device or apparatus such as a UE or a BS. In addition, in the present disclosure, an object may also be equivalent to a program, a model, or an entity that operates in the apparatus.

[0041] In addition, in the present disclosure, the AI ​​model may also be rewritten as an object having (implementing) at least one of the following features:

[0042] Producing estimates by feeding information,

[0043] Predicting estimated values ​​by giving information,

[0044] Discovering features by giving information,

[0045] ·Selecting an action by giving information.

[0046] Furthermore, in the present disclosure, an AI model may also refer to a data-driven algorithm that applies AI technology to generate an output set based on an input set.

[0047] Furthermore, in the present disclosure, AI models, models, ML models, predictive analytics, predictive analytics models, tools, autoencoders, encoders, decoders, neural network models, AI algorithms, and schemes may be interchangeable. Furthermore, AI models may be derived using at least one of regression analysis (e.g., linear regression analysis, multiple regression analysis, logistic regression analysis), support vector machines, random forests, neural networks, and deep learning.

[0048] In this disclosure, the autoencoder can be interchanged with any other autoencoder, such as a stacked autoencoder or a convolutional autoencoder. The encoder / decoder of this disclosure can also use models such as Residual Network (ResNet), DenseNet, and RefineNet.

[0049] In addition, in the present disclosure, encoder, encoding, encoding / encoded, correction / change / control based on encoder, compression, compressing / compressed, generating, generating / generated, etc. can also be rewritten.

[0050] In addition, in the present disclosure, decoder, decoding, decoding / decoding, correction / change / control based on the decoder, decompressing, decompressing / decompressed, reconstructing, reconstructing / reconstructed, etc. can also be rewritten.

[0051] In this disclosure, layers (for AI models) can also be rewritten with layers used in AI models (input layer, intermediate layer, etc.). Layers in this disclosure can also correspond to at least one of the following: input layer, intermediate layer, output layer, batch normalization layer, convolution layer, activation layer, dense layer, normalization layer, pooling layer, attention layer, dropout layer, fully connected layer, etc.

[0052] In the present disclosure, AI model training methods may also include supervised learning, unsupervised learning, reinforcement learning, and federated learning. Supervised learning may also refer to the process of training a model based on input and corresponding labels. Unsupervised learning may also refer to the process of training a model without labeled data. Reinforcement learning may also refer to the process of training a model based on input (in other words, state) and feedback signals (in other words, rewards) generated by the model's output (in other words, action) in an environment where the model interacts.

[0053] In this disclosure, the terms "generate," "calculate," and "derive" may be used interchangeably. In this disclosure, the terms "implement," "apply," "operate," and "execute" may be used interchangeably. In this disclosure, the terms "train," "learn," "update," and "retrain" may be used interchangeably. In this disclosure, the terms "infer," "post-training," "formal utilization," and "actual utilization" may be used interchangeably. In this disclosure, the terms "signal" and "signal / channel" may be used interchangeably.

[0054] Figure 1 This diagram shows an example of a framework for managing AI models. In this example, each stage associated with an AI model is represented by a box. This example also represents the life cycle management of an AI model.

[0055] The data collection phase corresponds to the collection of data used to generate / update AI models. This phase may also include data organization (e.g., determining which data to forward for model training / inference) and data forwarding (e.g., forwarding data to entities performing model training / inference (e.g., UEs, gNBs)).

[0056] Additionally, data collection can also refer to the process of collecting data through network nodes, management entities, or UEs for the purpose of AI model training / data analysis / inference. In this disclosure, processing and process can be interchangeable. Furthermore, in this disclosure, collection can also refer to obtaining a dataset (e.g., usable as input / output) for AI model training / inference based on measurements (e.g., channel measurements, beam measurements, radio link quality measurements, position estimation, etc.).

[0057] In this disclosure, offline field data may also refer to data collected from the field (displayed world) and used for offline training of AI models. In addition, in this disclosure, online field data may also refer to data collected from the field (displayed world) and used for online training of AI models.

[0058] During the model training phase, the model is trained based on the data (training data) forwarded from the collection phase. This phase may also include data preparation (e.g., data preprocessing, cleaning, formatting, and transformation), model training / validation, model testing (e.g., confirming that the trained model meets performance thresholds), model exchange (e.g., forwarding models for distributed learning), and model deployment / updates (deploying / updating models to entities performing model inference).

[0059] In addition, AI model training can also refer to the process of training an AI model using a data-driven approach to obtain a trained AI model for inference.

[0060] AI model validation can also refer to a sub-process of training that uses a dataset different from the one used in model training to evaluate the quality of an AI model. This sub-process is useful for selecting model parameters that are generalizable beyond the dataset used in model training.

[0061] Furthermore, AI model testing can also refer to a sub-process of training that uses a different dataset from the one used in model training / validation to evaluate the performance of the final AI model. Furthermore, testing, unlike validation, does not necessarily require subsequent model tuning.

[0062] In the model inference phase, model inference is performed based on the data forwarded from the collection phase (inference data). This phase may also include data preparation (e.g., data preprocessing, cleaning, formatting, and transformation), model inference, model monitoring (e.g., monitoring model inference performance), model performance feedback (feedback on model performance to the entities performing model training), and output (providing model output to the actors).

[0063] In addition, AI model inference may also refer to a process for using a trained AI model to generate a set of outputs based on a set of inputs.

[0064] Furthermore, a UE-side model may also refer to an AI model whose reasoning is fully implemented in the UE. A network-side model may also refer to an AI model whose reasoning is fully implemented in the network (e.g., gNB).

[0065] Furthermore, a one-sided model can also refer to a UE-side model or a network-side model. A two-sided model can also refer to a paired AI model that performs joint inference. Joint inference can also include AI inference performed jointly across the UE and the network. For example, the first part of the inference can be initially performed by the UE, and the remaining part can be performed by the gNB (or vice versa).

[0066] In addition, AI model monitoring can also refer to the processing used to monitor the inference performance of the AI ​​model, and can also be interchanged with model performance monitoring, performance monitoring, model monitoring, etc.

[0067] Additionally, model registration can also mean attaching a version identifier to the model and compiling it on the specific hardware used during inference to enable execution (registering the model). Furthermore, model deployment can also mean distributing the runtime image (or execution environment image) of a fully developed and tested model to (or activating (validating) in) the target (e.g., UE / gNB) where inference is performed.

[0068] The participant stage may also include action triggering (e.g., deciding whether to trigger an action on other entities), feedback (e.g., feeding back information necessary for training data / inference data / performance feedback), etc.

[0069] Furthermore, for example, training models for mobility optimization can also be performed within the network (network)'s operations, administration, and maintenance (OAM) / gNodeB (gNB). The former offers advantages such as interoperability, large storage capacity, operator manageability, and model flexibility (feature engineering). The latter offers advantages such as reduced model update latency and the elimination of data exchange for model deployment. Inference of these models can also be performed within the gNB, for example.

[0070] Depending on the use case (in other words, the AI ​​model's functionality), the entity performing training / inference can also vary. AI model functionality can include beam management, beam prediction, autoencoders (or information compression), CSI feedback, and location positioning.

[0071] For example, for AI-supported beam management based on measurement reports, OAM / gNB can also perform model training and gNB can perform model inference.

[0072] Regarding AI support for UE-assisted positioning, it can also be the Location Management Function (LMF) that performs model training, and the LMF performs model inference.

[0073] Regarding CSI feedback / channel estimation using autoencoders, OAM / gNB / UE can also perform model training, and gNB / UE can (jointly) perform model inference.

[0074] Regarding AI-supported beam management based on beam measurement or AI-supported UE positioning, OAM / gNB / UE can also perform model training and UE can perform model inference.

[0075] Additionally, model activation can also mean activating (validating) an AI model used for a specific function. Model deactivation can also mean deactivating (invalidating) an AI model used for a specific function. Model switching can also mean deactivating the currently active AI model used for a specific function and activating a different AI model.

[0076] Furthermore, model transfer can also refer to the distribution of an AI model over the air interface. This distribution can also include distributing parameters of a model structure known to the receiving side, or a new model with these parameters, or both. Furthermore, this distribution can include a complete model or a partial model. Model download can also refer to the forwarding of a model from the network to the UE. Model upload can also refer to the forwarding of a model from the UE to the network.

[0077] Figure 2 This diagram illustrates an example of AI model designation. In this example, the UE and the network network (e.g., a base station (BS)) can identify models #1 and #2 (though they may not fully understand the details of the models). Alternatively, the UE may report the performance of, for example, model #1 and model #2 to the network network, and the network network may instruct the UE which AI model to utilize.

[0078] (UE positioning using AI technology)

[0079] Fingerprinting localization, which estimates the position of a wireless device using the transmission characteristics of wireless signals, can also be widely used in both line-of-site (LOS) and non-line-of-site (NLOS) scenarios.

[0080] In the present disclosure, LOS may also mean that the UE and the base station are in an environment where they can see each other (or there is no obstruction), and NLOS may also mean that the UE and the base station are not in an environment where they can see each other (or there is an obstruction).

[0081] In fingerprint positioning, the UE's position is estimated based on the fingerprints of multiple propagation paths (multipath) of the UE based on a database / AI model.

[0082] The multipath information may be, for example, information on the angle of arrival (Angle of Arrival (AoA)) / angle of departure (Angle of Departure (AoD)) of the signal in the optimal / candidate propagation path.

[0083] In the present disclosure, information related to AoA may include, for example, information related to at least one of arrival azimuthangles and arrival zenith angles. Furthermore, information related to AoD may include, for example, information related to at least one of departure azimuthangles and departure zenith angles.

[0084] 3GPP Rel.16 NR supports the following positioning technologies.

[0085] Positioning based on DL / UL Time Difference Of Arrival (TDOA),

[0086] Angle-based (DL AoD / UL AoA) positioning,

[0087] Positioning based on multiple round trip times (RTT),

[0088] Enhanced Cell ID (E-CID)-based positioning.

[0089] Figure 3 This figure shows an example of positioning based on DL / UL TDOA. For example, assume that multiple base stations (TRP#0-#2) are configured around the UE. In this positioning method, the UE's position is estimated (measured) using the measured value of the reference signal reception time difference (RSTD). For example, the RSTD (T i -T j ) takes a certain value (k i，j ) can be connected to draw a hyperbola H i，j The intersection of multiple such hyperbolas (in this case H 0，1、 H 1，2、 H 2，0 The intersection of the reference signal and the UE position can also be estimated as the UE position. In addition, the RSRP of the reference signal can also be used to estimate the UE position.

[0090] Figure 4This figure shows an example of positioning based on DL AoD / UL AoA. In this positioning method, the UE's position is estimated using measured values ​​of DL AoD (e.g., θ or φ) or UL AoA (e.g., θ or φ). RSRP can also be used to estimate the UE's position.

[0091] Figure 5 This figure illustrates an example of multi-RTT-based positioning. This positioning method estimates the UE's position using multiple RTTs calculated from the Tx / Rx time difference of reference signals (and additionally from RSRP, RSRQ, and other factors). For example, geometric circles based on RTTs are drawn around each base station. The intersection of these multiple circles can also be used to estimate the UE's position.

[0092] Figure 6 This figure shows an example of E-CID-based positioning. In this positioning method, the UE's position is estimated based on the geometric positions of the serving cell and neighboring cells and additional measurement results (Tx-Rx time difference, RSRP, RSRQ, etc.).

[0093] The aforementioned DL positioning (DL TDOA, DL AoD) can also be performed on the UE or LMF side. For example, in UE-based positioning, the UE can calculate its position based on various UE measurement results and assistance information from the LMF. Furthermore, in UE-assisted positioning, the UE can report various measurement results to the LMF, which then calculates the UE's position. The assistance information can also be used to assist in estimating the UE's position.

[0094] The above-mentioned UL positioning (UL TDOA, UL AoA) can also be implemented on the LMF side. In this case, the base station can also report various measurement results to the LMF, and the LMF can calculate the UE's position.

[0095] The aforementioned positioning in DL and UL (multi-RTT, E-CID) can also be implemented on the LMF side. In this case, the UE / base station can report various measurement results to the LMF, and the LMF can calculate the UE's position.

[0096] Furthermore, 3GPP Release 17 proposes a positioning method that uses assistance information to further improve positioning accuracy. Assistance information can also be used as measurement information for DL / UL-TDOA, DL-AoD / UL-AoA, multi-RTT, and E-CID, and is transmitted between the UE, base station, and LMF.

[0097] The auxiliary information may also include information related to at least one of the following:

[0098] Timing Error Group (TEG),

[0099] RSRPP (path-specific RSRP),

[0100] Expected angle (Expected angle),

[0101] Adjacent beam information,

[0102] TRP antenna / beam information,

[0103] LOS / NLOS indicator,

[0104] Additional route reporting.

[0105] The TEG may also indicate one or more PRS (Positioning Reference Signal) resources whose transmit / receive timing errors (Rx / Tx timing errors) are within a certain tolerance range (margin).

[0106] RSRPP may also show the measurement result of RSRP in the initial path.

[0107] In UL positioning, the assistance information related to the expected angle can also represent the expected UL AoA / ZoA. This assistance information can be sent from the LMF to the base station. Furthermore, this assistance information can support at least one of UL TDOA, UL AoA, and multi-RTT positioning.

[0108] In DL positioning, the assistance information related to the expected angle may also include information related to the expected DL-AoA / ZoA (expected DL-AoA / ZoA) or DL-AoD / ZoD (expected DL-AoD / ZoD). This assistance information may also be sent from the LMF to the UE. Furthermore, this assistance information may support at least one of DL TDOA, DL AoA, and multi-RTT positioning. This improves the accuracy of angle-based UE positioning and enables optimization of UE or base station Rx beamforming.

[0109] Furthermore, the auxiliary information related to the predicted angle may include information indicating the uncertainty range of these values ​​in addition to the information on the values ​​of AoA / ZoA / AoD / ZoD as described above.

[0110] As additional beam information, adjacent beam information can also include information about a subset of DL-PRS resources for prioritizing DL-AoD reporting (Option 1) or the boresight direction of each DL-PRS resource (Option 2). This allows for optimization of UE Rx beam scanning and DL-AoD measurements.

[0111] Furthermore, the auxiliary information may include PRS beam pattern information as additional beam information. The PRS beam pattern information may include information on the relative power between DL-PRS resources at each angle for each TRP.

[0112] The LOS / NLOS indicator may also include information related to Line Of Site (LOS) / Non-Line Of Site (NLOS).

[0113] In addition, for the purpose of improving the positioning delay of the UE, pre-set measurement gaps (MG), activation of the MG via the lower layer, MG-less location, PRS Rx / Tx in the RRC_INACTIVE state, or on-demand PRS may be set for the UE (and may be used by the UE).

[0114] 3GPP Release 17 NR has agreed that to improve the accuracy of UE position estimation, the UE measures and reports the RSRP of adjacent beams. For example, in the UE-assisted DL-AoD positioning method, the LMF can include at least one of the following options 1 and 2 in the auxiliary information.

[0115] Option 1: Subsets of PRS resources for DL-AoD reporting prioritization. This subset can also be set for each PRS resource based on UE capabilities. When reporting requested PRS measurements for associated PRSs, the UE can also include the requested PRS measurements for the subset of PRSs in the additional DL-AoD measurements. The requested PRS measurements can also be DL PRS RSRP / path PRS RSRP. The UE can also report PRS measurements only for a subset of PRS resources. Furthermore, the subset associated with a PRS resource can exist in the same or different PRS resource set as the PRS resource.

[0116] Option 2: Information on the boresight direction set for each PRS resource according to UE capabilities.

[0117] In 3GPP Rel.16 NR, it was agreed that the LMF should indicate the expected RSTD and its uncertainty range to the UE. Furthermore, in Rel.17, it was agreed that the LMF should indicate the expected angle and its uncertainty range to the UE to mitigate errors and complexity in AoA / AoD measurements.

[0118] In 3GPP Release 17 NR, the introduction of a Positioning Reference Unit (PRU) is under consideration for positioning. The PRU is a device with a known location, designed to mitigate transmission and reception timing errors in the UE / gNB. The PRU can also be rewritten as UE / gNB / TRP (transmission reception point) / TP (transmission point). Furthermore, the NW (gNB / LMF) should preferably recognize the PRU's location information.

[0119] For example, the PRU may also support at least one of the following:

[0120] Measure DL PRS and report associated measurement values ​​(e.g. RSTD / transmit / receive time difference / RSRP) to the LMF,

[0121] Sending SRS to enable the TRP to measure measurements relative to the reference device (e.g., Relative Time of Arrival (RTOA) / Time Difference Between Transmitter and Receiver, AOA) and report them to the LMF,

[0122] Operation, measurement, various parameters (parameters related to transmit / receive timing delay, enhancement of AoD and AOA, and correction of measurement values),

[0123] · LMF reports the location coordinate information of the reference device to LMF when it does not have the location coordinate information.

[0124] The reference device whose location is known is the UE / gNB,

[0125] The accuracy of the position of the reference device can be known.

[0126] For example, there are two use cases for positioning using AI models:

[0127] Direct AI / ML targeting,

[0128] AI / ML-assisted positioning.

[0129] Direct AI / ML positioning, for example, outputs UE positioning (UE location). AI / ML-assisted positioning, for example, outputs intermediate features. These intermediate features can also be fed back into the AI / ML model.

[0130] Examples of outputs of the aforementioned AI / ML-assisted positioning may include at least one of the following:

[0131] LOS / NLOS identification (LOS / NLOS probability),

[0132] ToA (time of arrival of PRS / SRS),

[0133] Rx-Tx (send and receive) time difference,

[0134] AoA / AoD,

[0135] Number of waves, Rx-Tx (transmit and receive) phase difference (Rel.18 phase measurement),

[0136] DL RSTD / UL TDOA,

[0137] ·DL-PRS / UL-SRS, RSRPs / RSRPPs,

[0138] The likelihood of the above value (e.g., the probability of ToA).

[0139] (Beam information used for UE positioning)

[0140] As mentioned above, antenna (configuration) setting / beam information is considered useful for AI / Ml models.

[0141] As scenarios in which antenna (configuration) settings / beam information are utilized, consider the following scenarios A and B.

[0142] [Scenario A]

[0143] Select a more appropriate AI model based on antenna settings / frequency / region (erea).

[0144] [Scenario B]

[0145] To provide better performance, AI models require metadata (antenna setting information / beam information) as input.

[0146] In existing specifications, auxiliary information supporting beam information of a base station (gNB) from the network (NW) to the UE is only used for positioning.

[0147] The following wireless communication methods are being studied for the future:

[0148] • Using beam information for beam management.

[0149] Interfaces other than positioning protocols (eg, LTE Positioning Protocol (LPP)) also use beam information in the same manner.

[0150] Beam information of RSs other than the Positioning Reference Signal (PRS) is used for positioning.

[0151] • Using the beam information in the UE.

[0152] Rel. 17 supports beam information indicating the beam direction (boresight direction) for each PRS as beam information from the LMF to the UE (beam information used for UE-based positioning, information related to the base station's transmit beam). This beam information may also indicate the boresight direction for each PRS.

[0153] The beam information indicating the direction of the beam of each PRS is "DL-PRS-BeamInfoElement" included in "NR-DL-PRS-BeamInfo" of the common NR positioning information element.

[0154] The "DL-PRS-BeamInfoElement" includes information on the azimuth angle and the elevation angle of the beam transmitted from the base station (TRP).

[0155] Information related to the azimuth angle is "dl-PRS-Azimuth" and "dl-PRS-Azimuth-fine." "dl-PRS-Azimuth" is information expressed as values ​​from 0° to 359° in units of 1°, and "dl-PRS-Azimuth-fine" is information expressed as values ​​from 0° to 0.9° in units of 0.1°.

[0156] Information related to the elevation angle is "dl-PRS-Elevation" and "dl-PRS-Elevation-fine." "dl-PRS-Elevation" is information showing values ​​from 0° to 180° in granularity of 1°, and "dl-PRS-Elevation-fine" is information showing values ​​from 0° to 0.9° in granularity of 0.1°.

[0157] In addition, Rel.17 supports beam information representing the relative power of DL PRS in each angle (azimuth / elevation) as beam information from LMF to UE (beam information used for UE positioning, information related to the base station's transmission beam).

[0158] This beam information indicating relative power is included in the TRP's beam antenna information ("NR-TRP-BeamAntennaInfo") within the common NR positioning information element.

[0159] "NR-TRP-BeamAntennaInfo" contains information "NR-TRP-BeamAntennaInfoAzimuthElevation" related to beam antenna information of TRP for azimuth and elevation.

[0160] “NR-TRP-BeamAntennaInfoAzimuthElevation” includes “azimuth” indicating the azimuth angle with a granularity of 1° unit, “azimuth-fine” indicating the azimuth angle with a granularity of 0.1° unit, and a list of elevation angles “elevationList”.

[0161] The elevation angle list "elevationList" includes "elevation" indicating elevation angles with a granularity of 1° unit, "elevation-fine" indicating elevation angles with a granularity of 0.1° unit, and a beam power list "beamPowerList".

[0162] The beam power list "beamPowerList" includes "nr-dl-prs-ResourceSetID" representing the resource set ID of DL PRS, "nr-dl-prs-ResourceID" representing the resource ID of DL PRS, "nr-dl-prs-RelativePower" representing the relative power of the resource given by "nr-dl-prs-ResourceID" with a granularity of 1dB unit, and "nr-dl-prs-RelativePowerFine" representing the relative power of the resource given by "nr-dl-prs-ResourceID" with a granularity of 0.1dB unit.

[0163] Furthermore, Rel. 17 supports information indicating an antenna reference point (ARP) as beam (antenna) information (information on a base station's transmission beam) from the LMF to the UE.

[0164] This information is shown through the TRP location information of the public NR positioning information element, namely the "referencePoint" in the "NR-TRP-LocationInfo".

[0165] The location information of TRP "NR-TRP-LocationInfo" is expressed by the relative position of the reference point and the reference point.

[0166] The ARP location of a PRS resource is represented by a relative position associated with the ARP location of a PRS resource set.

[0167] The antenna reference point is shown by altitude, latitude and longitude.

[0168] In addition, in Rel.17, information related to the spatial direction of DL PRS is supported as information (information related to the base station's transmission beam) from the base station (e.g., gNB, NG-RAN (Next Generation-Radio Access Network) node) to the LMF.

[0169] This information includes information indicating the boresight direction of the azimuth and elevation angles of the PRS resource.

[0170] In addition, the information contains the transition information from the local coordinate system (LCS) to the global coordinate system (GCS).

[0171] The GCS can also be defined for a system containing multiple base stations and multiple UEs. In addition, in the LCS, an array antenna for a base station or a UE can also be defined.

[0172] The LCS is used as a reference to define the vector far-field of each antenna element in the array. This vector far-field is the pattern and polarization. The array configuration within the GCS can also be defined by transforming the GCS and LCS. The GCS / LCS can also be derived based on definitions and transformations (specified in standards) that are recognizable to those skilled in the art.

[0173] In addition, in Rel.17, as information from a base station (e.g., gNB) to LMF (information related to the transmission beam of the base station), information representing the beam / antenna of TRP is supported.

[0174] This information includes information indicating the relative power of the DL PRS at each angle (azimuth / elevation).

[0175] In addition, in Rel.17, as information from a base station (e.g., gNB) to the LMF (information related to the receiving beam of the base station), information related to the receiving beam during UL signal measurement is supported.

[0176] The information includes at least one of a PRS resource ID, a PRS resource set ID, and an SSB index.

[0177] Furthermore, Rel. 17 supports information related to spatial relationships as information transmitted from the UE to the NW (information related to the transmission beam of the UE).

[0178] This information indicates the ID / index of a specific RS (eg, SSB / CSI-RS / SRS / DL PRS).

[0179] Furthermore, Rel. 17 specifies the number of UE receive beams used in beam scanning for positioning. The UE may also report its support of UE capabilities to the LMF.

[0180] For example, in FR1, the UE uses one receive beam.

[0181] In FR2, if the UE supports certain UE capabilities, the number of beams indicated by "numberOfRxBeamSweepingFactor" information indicating the number of Rx beam sweeping factors for FR2 is used. Otherwise, the UE uses 8 receive beams.

[0182] In addition, information about the receive beam used by the UE in the measurement is supported (e.g., "nr-DL-PRS-RxBeamIndex").

[0183] Regarding this information, when different beams are used within a DL PRS resource set, the UE may also report measurement values ​​received through the same receive beam.

[0184] In other words, the beam information sent by the UE indicates whether the same beam is used between resource sets.

[0185] (UE-based DL positioning)

[0186] The situation where UE implements positioning in the AI ​​model on the UE side is explained. Figure 7 This figure shows an example of UE-based DL positioning. The UE can also use the AI ​​model to infer the UE positioning (UE position location, position). The UE can also report the inferred positioning results to the LMF.

[0187] The AI ​​model in the UE can also perform inference based on the UE's own dataset. The input information for the AI ​​model (input information) can also include raw data (information related to features) and auxiliary information measured by the UE. The UE can also receive auxiliary information from the base station or LMF.

[0188] The original measurement results (also referred to as measured characteristics) measured by the UE may also include data (information) related to at least one of the following (information listed in commas does not necessarily need to be included. The same applies to the subsequent content of this disclosure):

[0189] UE DL-PRS-RSRP (or DL-PRS-RSSI / RSRQ) measurement results for multiple reference TRPs,

[0190] DL-RSTD measurement results of multiple reference TRPs,

[0191] Refer to the TRP's Time of Arrival (ToA) measurement results.

[0192] Refer to the AoD measurement results of TRP,

[0193] the quality of various measurements,

[0194] The timestamp (moment) of the measurement result,

[0195] Physical Cell ID (PCI), Global Cell ID (GCI), Absolute Radio Frequency Channel Number (ARFCN), PRS Resource ID, PRS Resource Set ID, and PRS ID for each measurement.

[0196] UE Rx TEG ID, TRP Tx TEG ID, UE Tx TEG ID, UE RxTxTEG ID, TRP Rx TEG ID, TRP RxTx TEG ID for DL ​​RSTD measurement,

[0197] DL-PRS receive beam index,

[0198] DL-PRS-RSRP measurement results for the first path,

[0199] Channel impulse response / channel frequency response, coded channel impulse response / coded channel frequency response,

[0200] The phase difference between different antennas in the antenna array,

[0201] Receive multipath characteristics with reference to TRP (e.g., DL-PRS-RSRP measurements for each path, amplitude / average / cumulative distribution function (CDF) of the estimated multipath amplitude, path loss, root-mean-square (rms) delay spread, and sharpness of the channel impulse response).

[0202] In addition, GCI and NR Cell Global Identity (NCGI) can also rewrite each other.

[0203] The assistance information notified from the base station / LMF may also include information related to at least one of the following:

[0204] The noise of the Grand Truth dataset (such as the expected dispersion of the noise),

[0205] The physical cell ID (PCI), global cell ID (GCI), ARFCN, and PRSID of the NR TRP candidate to be measured,

[0206] Timing relative to the NR TRP candidate and the serving (reference) TRP,

[0207] TRP SSB information (SSB time / frequency occupancy),

[0208] DL-PRS settings for candidate NR TRPs,

[0209] The spatial direction information (azimuth, elevation, etc.) of the DL-PRS resource of the TRP provided by the base station,

[0210] The geographical coordinates of the TRP provided by the base station (the reference position of each DL-PRS resource ID, the reference position of the transmit antenna of the reference TRP, and the reference position of the transmit antennas of other TRPs),

[0211] Fine Timing relative of the candidate NR TRP to the serving (baseline) TRP,

[0212] PRS-specific transmission point indication (TP indication),

[0213] TRP Tx TEG ID and DL-PRS resource association information,

[0214] DL-PRS-RSRP / DL-PRS-RSSI / DL-RSTD / ToA / AoD / Phase Difference Each measured information related to LOS / NLOS,

[0215] On-Demand DL-PRS settings,

[0216] TRP beam / antenna information (including azimuth angle, zenith angle, and relative power between PRS resources at each angle in each TRP),

[0217] Auxiliary information of expected angles,

[0218] PRS priority table.

[0219] The aforementioned correct answer (ground truth) dataset can also be rewritten as a dataset representing position information used in AI training / validation / testing.

[0220] The UE may also output its location based on the AI ​​model. The UE-side AI model, which outputs the UE location, may also be applied to UL-based positioning, DL-based UL-based positioning, and so on. These inputs may include, for example, UE / gNB measurement results and extracted features, features extracted on the gNB side, and features extracted on the LMF side.

[0221] (Classification of positioning)

[0222] Positioning using AI models can also be categorized as follows:

[0223] (1) UE-based positioning,

[0224] (2) AI / ML-assisted positioning,

[0225] (3) NG-RAN (Next Generation Radio Access Network) node assisted positioning.

[0226] (1) UE-based positioning can be further categorized as follows:

[0227] (1-1) Direct AI / ML positioning in the UE-side model,

[0228] (1-2) AI / ML-assisted positioning in the UE-side model, and non-AI-based positioning in the UE-side algorithm.

[0229] (2) AI / ML-assisted positioning can be further categorized as follows:

[0230] (2-1) AI / ML-assisted positioning in the UE-side model and non-AI-based positioning in the LMF-side algorithm.

[0231] (2-2) Direct AI / ML positioning in the LMF side model.

[0232] (3) NG-RAN node-assisted positioning can be further categorized as follows:

[0233] (3-1) AI / ML-assisted positioning in the gNB-side model, and non-AI-based positioning in the LMF-side algorithm,

[0234] (3-2) Direct AI / ML positioning in the LMF side model.

[0235] Regarding each of the above positioning, the following contents are studied:

[0236] The type of measurement used as input to model inference (new measurement / existing measurement),

[0237] In the positioning of (1) and (2) above, the UE is assumed to perform measurements as input to the model inference.

[0238] In the positioning of (3) above, TRP (gNB / LMF) is assumed to be measured as input to model inference.

[0239] Report the measurement results as input to the LMF side model (2-2, 3-2) for model inference on the LMF,

[0240] In AI / ML assisted positioning, as the model output to LMF for UE assisted (2-1) and NG-RAN node assisted positioning (3-1), it is possible to extend new measurement reports / existing measurement reports,

[0241] • Extensions to auxiliary signaling / procedures to facilitate model inference for both UE-side and NW-side models.

[0242] The positioning methods described in (1) to (3) above can also be collectively referred to as AI / ML-based positioning. In other words, positioning using an AI model, the aforementioned positioning methods, and AI / ML-based positioning (AI-based positioning) can be interchanged.

[0243] (Positioning process)

[0244] Figure 8 This is a diagram showing an example of positioning service support based on NG-RAN.

[0245] like Figure 8 As shown, in each of steps 1a-1c, the entity within the 5GC / AMF / UE requests a positioning service. The positioning service may also be, for example, the distribution of positioning / assistance information.

[0246] In step 2, AMF forwards the request for location service to LMF.

[0247] In steps 3a-3b, the LMF starts the positioning process with the UE / gNB (NG-RAN Node) to obtain positioning estimation / positioning measurement / assistance information, etc.

[0248] In step 4, the LMF provides the AMF with a response to the positioning service (Positioning Service Response). The response may also include necessary results (indication of success / failure, and the UE's positioning estimate in the case of request / acquisition, etc.).

[0249] In step 5a, the AMF returns (provides) a response to the request for the positioning service in step 1a (positioning service response) to the 5GC entity. This response may also include necessary results (such as the UE's positioning estimate).

[0250] In step 5b, the AMF may also support the location service triggered in step 1b using the location service response received in step 4. Specifically, the AMF may provide a location estimate associated with the emergency call to the GMLC.

[0251] In step 5c, the AMF returns a response to the location service request in step 1c (location service response) to the UE. This response may also include necessary results (such as the UE's location estimate).

[0252] (Positioning measurement indication process)

[0253] Figure 9 This is a diagram showing an example of the positioning measurement indication process between UE / gNB.

[0254] When the MG (Measurement Gap) is not configured / the MG is insufficient, the UE sends an RRC message related to the positioning measurement indication to the serving gNB in ​​order to request the MG for performing the requested positioning measurement (step 1).

[0255] This message may also indicate that the UE has started positioning measurements / acquiring the subframe and slot timing of the targeted E-UTRA system. Furthermore, this message may include information necessary for the gNB to configure the appropriate MG. If the gNB configures the necessary MG, the UE performs the positioning measurement / timing acquisition process.

[0256] Once the UE completes the positioning measurement / timing acquisition process requiring the MG, it sends another RRC message related to the positioning measurement instruction to the serving gNB (step 2). This message may also indicate that the UE has completed the positioning measurement / acquisition of the target E-UTRA system subframe and slot timing.

[0257] (Measurement / Measurement Report)

[0258] To reduce latency, Rel. 17 positioning supports UEs receiving DL-PRS and measuring RSTD independently of the mobile group (MG). Alternatively, the UE can be instructed with a measurement window via a higher-layer parameter (DL-PRS-ProcessingWindowPreConfig). This measurement window can also indicate the period within the specified window during which the UE can receive data (PDCCH / PDSCH), CSI-RS, and DL-PRS.

[0259] In addition, in NR positioning, the following measurements are reported regarding the requested location information (CommonIEsRequestLocationInformation):

[0260] TriggeredReporting

[0261] Periodical Reporting

[0262] TriggeredReporting can also contain at least one of the following fields:

[0263] cellChange: If this field is set to TRUE, the target device provides the requested positioning information whenever the primary cell changes.

[0264] reportingDuration: Indicates the maximum duration (in seconds) of TriggeredReporting. A value of zero also means an unlimited (i.e., "infinite") duration. The target device must continue TriggeredReporting for the duration of reportingDuration or before receiving an LPP Abort / Error message.

[0265] PeriodicalReporting can also contain at least one of the following fields:

[0266] reportingAmount: Indicates the number of periodic location information reports requested. The listed values ​​correspond to 1, 2, 4, 8, 16, 32, 64, or infinite / indefinite reports. When reportingAmount is "infinite / indefinite," the target device must continue PeriodicReporting until it receives an LPP Abort message. On the sending side, the value "ra1" cannot be used.

[0267] reportingInterval: Indicates the interval for reporting location information and the response time requirement for the initial location information report. The listed values ​​ri0-25, ri0-5, ri1, ri2, ri4, ri8, ri16, ri32, and ri64 correspond to reporting intervals of 1, 2, 4, 8, 10, 16, 20, 32, and 64 seconds, respectively. If the reportingInterval expires before the target device obtains a new measurement or can obtain a new position estimate, a measurement report that does not contain a measurement or position estimate is requested. The value "noPeriodicalReporting" cannot be used by the sending side.

[0268] The report may also include information related to NR E-CID positioning and DL-TDOA positioning.

[0269] (KPI)

[0270] Regarding the performance monitoring of AI models, research is underway on public and important performance indicators (Key Performance Indicators (KPIs)).

[0271] The following is an initial table of common KPIs used to evaluate the performance of AI / ML models:

[0272] Performance

[0273] Intermediate KPIs,

[0274] Link-level and system-level performance,

[0275] Generalization performance,

[0276] Over-the-air expenses,

[0277] The overhead of auxiliary information,

[0278] Data collection overhead,

[0279] Model delivery / transfer overhead,

[0280] The overhead of signaling associated with other AI / ML models,

[0281] Inference complexity,

[0282] The computational complexity of model inference: floating point operations (FLOPs (also, s is lowercase)) (this refers to the number of floating point operations),

[0283] The computational complexity of pre- and post-processing,

[0284] The complexity of the model (number of parameters / data size (e.g., Mbyte), etc.),

[0285] The complexity of the training,

[0286] LCM related complexity and storage overhead,

[0287] Latency (e.g., inference latency).

[0288] In addition, the above KPIs are only examples, and other KPIs (such as KPIs related to model training, KPIs specific to a given use case, etc.) can also be added to the table.

[0289] (Performance metrics related to positioning)

[0290] In Rel.17, the following metrics are specified for performance evaluation of positioning (TR38.857). Furthermore, positioning error percentages of 50%, 67%, 80%, and 90% can be used for analysis.

[0291] Horizontal accuracy

[0292] The horizontal accuracy may also represent the difference between the calculated horizontal position of the UE and the actual horizontal position of the UE. For example, the horizontal accuracy may also be less than 0.2 meters in 90% of the UEs.

[0293] Vertical accuracy

[0294] The vertical accuracy may also represent the difference between the calculated vertical position of the UE and the actual vertical position of the UE. For example, the vertical accuracy may also be less than 1 meter in 90% of the UEs.

[0295] ·Delay

[0296] For example, the delay may be the end-to-end delay used for UE position estimation. This delay may be less than 100 milliseconds (more preferably, on the order of 10 milliseconds). This delay may also include processing delays in various nodes (such as the UE, gNB, AMF, and LMF) and signaling delays between nodes. Other delays may include physical layer delays used for UE position estimation. This delay may also be less than 10 milliseconds, for example.

[0297] Performance metrics used for model monitoring can use at least one of the following:

[0298] Performance

[0299] Latency

[0300] Complexity

[0301] Performance can also include at least one of the following:

[0302] Horizontal accuracy of AI / ML-based positioning (meters),

[0303] Vertical accuracy of AI / ML-based positioning (meters),

[0304] Accuracy of intermediate features for AI / ML-based positioning.

[0305] The horizontal accuracy may also represent the difference between the calculated horizontal position of the UE and the actual horizontal position of the UE. For example, the horizontal accuracy may be less than 0.2 m for 90% of the UEs.

[0306] The vertical accuracy may also represent the difference between the calculated vertical position of the UE and the actual vertical position of the UE. For example, the vertical accuracy may also be less than 1 m in 90% of the UEs.

[0307] The intermediate feature accuracy may also represent the difference between an inferenced intermediate value and an intermediate value derived based on the actual UE location. The intermediate feature accuracy may also be represented by, for example, at least one of the following: accuracy of the LOS / NLOS indicator (error rate %), ToA (milliseconds), AoA (degrees), RSTD (milliseconds), RSRP (dBm), etc.

[0308] Latency can also include at least one of the following:

[0309] Physical layer latency (milliseconds),

[0310] End-to-end latency (milliseconds).

[0311] The delay in the positioning process can also be determined based on e.g. Figure 10 is defined by the diagram shown. Figure 10 This is a diagram showing an example of the start time / end time of the delay in the physical layer. Figure 10 As shown, the physical layer delay can also be defined separately according to the positioning method.

[0312] For example, in the case of UE-based positioning, the start time can be any of the following: the UE sends a PUSCH containing an MG request (Alt1), the gNB sends an LPP message containing assistance data using the PDSCH (Alt2), or the UE starts receiving the DL PRS (Alt3). Furthermore, the end time in this case can be the time when the gNB successfully decodes the PUSCH containing the LPPP Provide Location Information message, or when the gNB performs a position estimate for the UE if decoding is unsuccessful.

[0313] In the case of UE-assisted positioning / LMF-based positioning, the start time can also be the timing when the gNB sends the PDSCH containing the LPP Request Location Information message. Alternatively, the end time in this case can also be the timing when the gNB successfully decodes the PUSCH containing the LPP Provide Location Information message.

[0314] In the case of NG-RAN node-assisted positioning, the start time may also be the timing when the gNB receives the NRPPa measurement request message. In addition, the end time in this case may also be the timing when the gNB sends the NRPPa measurement response message.

[0315] In addition, the delay of AI models is not limited to Figure 10 For example, the timing when UE / NW receives the input of model inference can be used as the start time, and the timing when NW / UE receives the output of the AI ​​model can be used as the end time.

[0316] The end-to-end delay may also be the delay used for UE position estimation.

[0317] Furthermore, latency may include higher-layer latency as another type of delay. This latency may also include processing delays within various nodes (such as the UE, gNB, AMF, and LMF) and signaling delays between nodes. The definitions of these delays may also conform to those in Rel. 17.

[0318] Complexity can also be defined by the computational complexity of model inference (floating point operations (FLOPs)). Furthermore, the complexity of an AI model can be defined by, for example, the model's data size (in Mbytes) and the number of parameters associated with the AI ​​model.

[0319] (Performance monitoring for positioning (model monitoring))

[0320] Calculating Performance Metrics

[0321] In UE-based positioning, model monitoring for direct AI / ML positioning based on UE-side models may also be performed based on at least one of the following:

[0322] <1> Performance indicator calculation in UE,

[0323] <2> Performance indicator calculation in LMF.

[0324] In UE-based positioning, model monitoring for AI / ML-assisted positioning based on UE-side models may also be performed based on at least one of the following:

[0325] <3> Performance indicator calculation in UE,

[0326] <4> Performance indicator calculation in LMF.

[0327] In UE-assisted positioning, model monitoring for AI / ML-assisted positioning based on UE-side models can also be performed according to the following:

[0328] <5> Performance indicator calculation in LMF.

[0329] In NG-RAN node-assisted positioning, model monitoring for AI / ML-assisted positioning based on the gNB-side model may also be performed based on at least one of the following:

[0330] <6> Performance indicator calculation in gNB,

[0331] <7> Performance indicator calculation in LMF.

[0332] Performance Indicator Calculation in Direct AI / ML Positioning Based on UE-Side Models

[0333] The above <1> The performance index calculation (model monitoring) can also be performed according to the following steps.

[0334] Step 1: The UE obtains a noisy ground truth UE position (a true value related to the UE position).

[0335] Step 1´: UE obtains estimated UE position from model inference.

[0336] Step 2: The UE calculates the performance indicators monitored by the model.

[0337] Step 3: The UE reports the performance indicators monitored by the model.

[0338] Step 3´: The UE requests the LMF to activate / deactivate / switch the model.

[0339] Step 4: The UE receives an indication of activation / deactivation / switching of the model from the LMF.

[0340] Step 5: The UE activates / deactivates / switches the model.

[0341] The above <2> The performance index calculation (model monitoring) can also be performed according to the following steps.

[0342] Step 1: The UE infers the UE position from the model and reports it.

[0343] Step 1´: LMF obtains the noisy ground truth UE position (the actual value related to the UE position).

[0344] Step 2: LMF calculates the performance indicators monitored by the model.

[0345] Step 3: The UE receives an indication of activation / deactivation / switching of the model from the LMF.

[0346] Step 4: The UE activates / deactivates / switches the model.

[0347] Calculation of Performance Indicators in AI / ML-Assisted Positioning Based on UE-Side Models

[0348] The above <3> The performance index calculation (model monitoring) can also be performed according to the following steps.

[0349] Step 1: The UE obtains noisy ground truth data (real values ​​related to certain data (such as UE location)).

[0350] Step 1´: UE obtains estimated data from model inference.

[0351] Step 2: The UE calculates the performance indicators monitored by the model.

[0352] Step 3: The UE reports the performance indicators monitored by the model.

[0353] Step 3´: The UE requests the LMF to activate / deactivate / switch the model.

[0354] Step 4: The UE receives an indication of activation / deactivation / switching of the model from the LMF.

[0355] Step 5: The UE activates / deactivates / switches the model.

[0356] The above <4> 、 <5> The performance index calculation (model monitoring) can also be performed according to the following steps.

[0357] Step 1: UE obtains and reports estimated data from model inference.

[0358] Step 2: The LMF obtains the ground truth data (the actual value related to a certain data (e.g., UE location)).

[0359] Step 3: LMF calculates the performance indicators monitored by the model.

[0360] Step 4: The UE receives an indication of activation / deactivation / switching of the model from the LMF.

[0361] Step 5: The UE activates / deactivates / switches the model.

[0362] Calculation of Performance Indicators in AI / ML-Assisted Positioning Based on gNB-Side Models

[0363] The above <6> The performance index calculation (model monitoring) can also be performed according to the following steps.

[0364] Step 1: The gNB obtains and reports the estimated data from model inference.

[0365] Step 1´: The gNB obtains the ground truth data (the actual value related to a certain data (e.g. UE location)).

[0366] Step 2: The gNB calculates the performance metrics monitored by the model.

[0367] Step 3: The gNB reports the performance metrics monitored by the model.

[0368] Step 3´: The gNB requests the LMF to activate / deactivate / switch the model.

[0369] Step 4: The gNB receives the activation / deactivation / switching indication of the model from the LMF.

[0370] Step 5: The gNB activates / deactivates / switches the model.

[0371] The above <7> The performance index calculation (model monitoring) can also be performed according to the following steps.

[0372] Step 1: The gNB obtains and reports the estimated data from model inference.

[0373] Step 2: The LMF obtains the ground truth data (the actual value related to a certain data (e.g., UE location)).

[0374] Step 3: LMF calculates the performance indicators monitored by the model.

[0375] Step 4: The gNB receives the activation / deactivation / switching indication of the model from the LMF.

[0376] Step 5: The gNB activates / deactivates / switches the model.

[0377] Application of performance indicators on the UE side

[0378] When model inference is performed on the NW / UE side, the UE can also determine whether the performance indicator requirements are met.

[0379] The UE may also report at least one of the following monitoring information to the NW via higher layer signaling / physical layer signaling such as LPP / MAC CE / DCI / RRC / NRPPa:

[0380] Monitor the accuracy of the AI ​​model’s output information,

[0381] The difference between the inferred horizontal position / vertical position and the actual horizontal position / vertical position,

[0382] The difference between the inferred output (ToA, AoA, RSTD, RSRP, etc.) and the actual position (ToA, AoA, RSTD, RSRP, etc.)

[0383] Delay difference,

[0384] The complexity of AI models and latency, and the complexity of requirements),

[0385] A binary indicator indicating whether the performance indicator requirements are met.

[0386] The estimated accuracy of the calculation (horizontal accuracy / vertical accuracy / intermediate feature accuracy),

[0387] Information about the reliability of the estimated accuracy.

[0388] In addition, the monitoring information may also be reported based on at least one of the following:

[0389] <Select 1>

[0390] When some of the existing conditions are met (for example, when a performance indicator does not meet a specific requirement),

[0391] <Select 2>

[0392] Always report after monitoring (report unconditionally),

[0393] <Select 3>

[0394] Reporting based on settings / NW instructions (e.g., periodic, semi-permanent, non-periodic).

[0395] Application of Performance Indicators on the gNB Side

[0396] When model inference is performed on the UE / gNB / LMF side, the gNB can also determine whether the performance indicator requirements are met.

[0397] The UE / LMF may also report at least one of the following AI model output information to the gNB / LMF via higher layer signaling / physical layer signaling such as LPP / MAC CE / DCI / RRC / NRPPa. In this case, the UE may also report to the gNB via the LMF:

[0398] Inferred UE coordinates,

[0399] ToA for reasoning,

[0400] Inferred LOS / NLOS indicators,

[0401] Inferred AoA, RSTD, RSRP,

[0402] The complexity of the AI ​​model,

[0403] ·Delay.

[0404] After comparing the information reported from the UE / information indicated from the LMF with the actual information, the gNB may also indicate at least one of the above-mentioned monitoring information (UE-side information) to the UE / LMF via higher-layer signaling / physical layer signaling such as LPP / MAC CE / DCI / RRC / NRPPa.

[0405] Application of performance indicators in LMF side

[0406] When model inference is performed on the UE / gNB / LMF side, LMF can also determine whether the performance indicator requirements are met.

[0407] The UE / gNB may also report at least one of the following AI model output information to the NW via higher layer signaling / physical layer signaling such as LPP / MAC CE / DCI / RRC / NRPPa:

[0408] Inferred UE coordinates,

[0409] ToA for reasoning,

[0410] Inferred LOS / NLOS indicators,

[0411] Inferred AoA, RSTD, RSRP,

[0412] The complexity of the AI ​​model,

[0413] ·Delay.

[0414] After comparing the information reported from the UE / gNB with the actual information, the LMF can also indicate at least one of the above-mentioned monitoring information (UE-side information) to the UE / gNB via high-layer signaling / physical layer signaling such as LPP / MAC CE / DCI / RRC / NRPPa.

[0415] Regarding the above-mentioned performance indicator targets on the UE / gNB / LMF side, model monitoring and model reasoning are preferably performed in the same entity (UE / gNB / LMF).

[0416] Issues in Model Monitoring

[0417] Regarding model monitoring of AI / ML-based positioning, research is underway to determine which entity should be responsible for calculating / applying the aforementioned performance indicators.

[0418] (analyze)

[0419] Problem Analysis 1

[0420] For example, regarding positioning using AI models, it is unclear which AI / ML model the UE applies for model inference, or how the UE determines the AI / ML model (Analysis 1-1). Specifically, the application and determination methods of AI / ML models are listed as research topics.

[0421] In addition, in the AI / ML model on the UE side, the input information source used for model inference is not clear (Analysis 1-2).

[0422] In addition, it is unclear what information the UE can report / feed back after model inference (Analysis 1-3).

[0423] Problem Analysis 2

[0424] As mentioned above, research is underway into performance monitoring (model monitoring) of AI models. However, specific lifecycle management related to performance monitoring in locations where AI models are used has not yet been studied.

[0425] For example, the definition of model monitoring is not clear (Analysis 2-0).

[0426] Furthermore, when to perform model monitoring (timing), that is, the situations / conditions under which model monitoring is applied, is not clear (Analysis 2-1).

[0427] Furthermore, it is unclear how the UE requests information for model monitoring (e.g., from the NW), or what information the NW provides (Analysis 2-2). More specifically, it is unclear which entities are used to calculate indicators for model monitoring (e.g., the aforementioned performance indicators), which signaling is used to provide data to the entity performing model monitoring, and how to request / report to the entity that provides the data.

[0428] Thus, regarding positioning using AI models, sufficient research has not yet been conducted on reasoning / monitoring of AI models.

[0429] In view of the above-mentioned problems, the inventors of the present invention have conceived a method of inferring and monitoring an AI model related to positioning.

[0430] (various rewrites, etc.)

[0431] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. The wireless communication methods according to the respective embodiments may be applied individually or in combination.

[0432] In future implementations, the angle of arrival of the signal at the UE, the AoA at the UE, and the AoA at the base station may be overwritten. In the present disclosure, the angle of radiated signal at the UE, the AoD at the UE, and the AoD at the base station may be overwritten. In the present disclosure, the AoA and AoD may be overwritten. In the present disclosure, the UE and the base station may be overwritten.

[0433] In one embodiment of the present disclosure, a terminal (user terminal, user equipment (UE)) / base station (BS) trains an ML model in training mode and implements the ML model in inference mode (also known as inference mode). In inference mode, the accuracy of the ML model trained in training mode can also be verified.

[0434] In the present disclosure, an object may also be, for example, a device or apparatus such as a terminal or a base station. In addition, in the present disclosure, an object may also be equivalent to a program / model / entity operating in the apparatus.

[0435] In the present disclosure, "A / B" and "at least one of A and B" may be replaced with each other. In addition, in the present disclosure, "A / B / C" may also mean "at least one of A, B, and C."

[0436] In the present disclosure, activation, deactivation, indication (or designation), selection, configuration, update, and determination may also be replaced with each other. In the present disclosure, support, control, controllable, operation, and operability may also be replaced with each other.

[0437] In this disclosure, Radio Resource Control (RRC), RRC parameters, RRC messages, higher-layer parameters, fields, Information Elements (IEs), and settings may also be overwritten. In this disclosure, Medium Access Control (MAC) Control Elements (CEs), update commands, and activation / deactivation commands may also be overwritten.

[0438] In the present disclosure, high-layer signaling may be, for example, Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information, positioning protocol (e.g., NR Positioning Protocol A (NRPPa)) / LTE Positioning Protocol (LTE Positioning Protocol (LPP))) messages, or any one or a combination thereof.

[0439] In the present disclosure, MAC signaling may include, for example, a MAC Control Element (MACCE) and a MAC Protocol Data Unit (PDU). Broadcast information may include, for example, a Master Information Block (MIB), a System Information Block (SIB), minimum system information (Remaining Minimum System Information (RMSI)), and other system information (Other System Information (OSI)).

[0440] In the present disclosure, the physical layer signaling may also be, for example, downlink control information (Downlink Control Information (DCI)), uplink control information (Uplink Control Information (UCI)), etc.

[0441] In the present disclosure, an index, an identifier (ID), a pointer, a resource ID, etc. may also be replaced by one another. In the present disclosure, a sequence, a list, a set, a group, a group, a cluster, a subset, etc. may also be replaced by one another.

[0442] In the present disclosure, panel, UE panel, panel group, beam, beam group, precoding, 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 (PDSCH)), Channel (PUCCH)) group, PUCCH resource group), resources (e.g., reference signal resources, SRS resources), resource sets (e.g., reference signal resource sets), CORESET pool, downlink transmission configuration indication state (Transmission Configuration Indication state (TCI state)) (DL TCI state), uplink TCI state (UL TCI state), unified TCI state (unified TCI state), common TCI state (common TCI state), Quasi-Co-Location (QCL)), QCL assumptions, etc. can also be rewritten with each other.

[0443] In this disclosure, CSI-RS, non-zero power (NZP) CSI-RS, zero power (ZP) CSI-RS, and CSI interference measurement (CSI-IM) can be interchanged. Furthermore, CSI-RS can also include other reference signals.

[0444] In the present disclosure, the measured / reported RS may also mean the RS measured / reported for CSI reporting.

[0445] In the present disclosure, timing, moment, time, time slot, sub-time slot, code element, sub-frame, etc. can also be rewritten.

[0446] In the present disclosure, directions, axes, dimensions, domains, polarizations, polarization components, etc. may be replaced with each other.

[0447] In this disclosure, estimation, prediction, and inference can be replaced with each other. In addition, in this disclosure, estimation, prediction, and inference can be replaced with each other.

[0448] In the present disclosure, autoencoders, encoders, decoders, etc. can also be rewritten as at least one of a model, an ML model, a neural network model, an AI model, an AI algorithm, etc. Furthermore, autoencoders can be rewritten with any other autoencoders, such as stacked autoencoders and convolutional autoencoders. The encoder / decoder of the present disclosure can also employ models such as Residual Network (ResNet), Densely Connected Network (DenseNet), and RefineNet.

[0449] In the present disclosure, bits, bit strings, bit series, series, values, information, values ​​obtained from bits, information obtained from bits, etc. can also be replaced with each other.

[0450] In the present disclosure, layers (for encoders) can also be rewritten with layers used in AI models (input layers, intermediate layers, etc.). The layers (layers) of the present disclosure can also correspond to at least one of the input layer, intermediate layer, output layer, batch normalization layer, convolution layer, activation layer, dense layer, normalization layer, pooling layer, attention layer, dropout layer, fully connected layer, etc.

[0451] In the present disclosure, RSRP may be interchangeably with any parameters related to received power and received quality (eg, RSRQ, SINR, CSI).

[0452] In the present disclosure, RS may also be, for example, CSI-RS, SS / PBCH block (SS block (SSB)), etc. Furthermore, RS index may also be CSI-RS Resource Indicator (CSI-RS Resource Indicator (CRI)), SS / PBCH Block Resource Indicator (SSBRI), etc.

[0453] In the present disclosure, channel measurement / estimation may be performed, for example, using at least one of a Channel State Information Reference Signal (CSI-RS), a Synchronization Signal (SS), a Synchronization Signal / Broadcast Channel (SS / PBCH)) block, a DeModulation Reference Signal (DMRS), and a Sounding Reference Signal (SRS).

[0454] In the present disclosure, CSI may also include at least one of a channel quality indicator (CQI), a precoding matrix indicator (PMI), a CSI-RS resource indicator (CRI), an SS / PBCH block resource indicator (SSBRI), a layer indicator (LI), a rank indicator (RI), L1-RSRP (Layer 1 Reference Signal Received Power), L1-RSRQ (Layer 1 Reference Signal Received Quality), L1-SINR (Layer 1 Signal to Interference plus Noise Ratio), L1-SNR (Layer 1 Signal to Noise Ratio), information related to a channel matrix (or channel coefficient), information related to a precoding matrix (or precoding coefficient), and the like.

[0455] In the present disclosure, UCI, CSI report, CSI feedback, feedback information, feedback bit, CSI feedback method, CSI feedback scheme, etc. may be interchangeable. Furthermore, in the present disclosure, bit, bit sequence, bit series, series, value, information, value derived from a bit, information derived from a bit, etc. may be interchangeable.

[0456] In this disclosure, "model / non-AI-based CSI feedback" can also be interchanged with model, CSI feedback method, CSI feedback scheme, etc. In addition, in this disclosure, model can also be interchanged with functionality.

[0457] In this disclosure, positioning (location measurement) can be interchanged with position determination, position estimation, and position prediction. In this disclosure, KPIs (key performance indicators) and performance metrics can be interchanged. Performance metric calculation, model monitoring, and performance monitoring can also be interchanged.

[0458] In this disclosure, functionality can refer to both the purpose of a model (such as UE positioning) and the physical nature of its inputs and outputs. Multiple models can have the same functionality. Monitoring (performance verification), activation, deactivation, switching, feedback, and updates can also be instructed (controlled) on a functionality-by-function basis (e.g., per function).

[0459] Furthermore, a model ID can also refer to the identifier of a model (or set of models). In actual deployments, multiple models may be assigned the same model ID. In this case, these models can be treated as the same model, even though they are actually different models (e.g., with different numbers of layers).

[0460] In this disclosure, model IDs and metadata (or metadata sets) IDs can be interchangeable. Metadata (or metadata IDs) can also be associated with information related to positioning, environment, UE / gNB settings, and so on.

[0461] Based on the model ID, it is also possible to instruct (control) monitoring (confirmation of performance) / selection of the model / activation / deactivation / switching / feedback / update.

[0462] In the following embodiments, to illustrate the AI ​​model related to communication between UEs, gNBs, and LMFs, the associated entities are UEs, gNBs, and LMFs. However, the application of the embodiments of this disclosure is not limited to this. For example, for communication between other entities (e.g., UE-UE communication), the UEs, gNBs, and LMFs in the following embodiments can be rewritten as first UEs, second UEs, third UEs, and so on. In other words, the UEs, gNBs, and LMFs in this disclosure can be rewritten as any UE, gNB, or LMF. Furthermore, NWs, BSs, gNBs, and LMFs can also be rewritten as each other.

[0463] (Wireless Communication Method)

[0464] <First embodiment>

[0465] The first embodiment relates to enhancement of model inference for localization.

[0466] [Implementation 1.1]

[0467] Implementation 1.1 Regarding the above-mentioned analysis 1-1, the judgment / determination of model application will be described.

[0468] Method 1.1.1

[0469] For model inference, the UE decides based on at least one of the following options:

[0470] Whether AI / ML models are applied,

[0471] If an AI / ML model is applied, which AI / ML model is applied.

[0472] (Opt1): Based on instructions from the NW (gNB / LMF) via higher layer signaling / physical layer signaling such as LPP / MAC CE / DCI / RRC / NRPPa.

[0473] (Opt2): Based on a request from the UE via higher layer signaling / physical layer signaling such as LPP / MAC CE / DCI / RRC / NRPPa.

[0474] (Opt3): Based on the UE's own decision.

[0475] In the case of Opt 2, the NW (gNB / LMF) may also send a response to the UE confirming the request (Opt 2-1). Furthermore, the NW (gNB / LMF) may also send a response to the UE indicating information related to the application of the model (Opt 2-2). This response may include the same information as the request described above or other information. Furthermore, if the gNB / LMF sends an instruction that differs from the UE's request, the UE may either follow the gNB / LMF's instruction or resend a new request to the gNB / LMF.

[0476] In addition, in the case of Opt 2, the gNB / LMF may also send a response to reject the request (Opt 2-3). In this case, after receiving the response, the UE can either resend the previous request or send a new request.

[0477] Regarding Opt2, before the UE sends the request, if model identification / model activation is performed, the NW needs to indicate to the UE the information of the available models (model ID, model functions, etc.). In addition, the model identification and model ID can also be overwritten.

[0478] In the case of Opt3, the UE can either report the application of the AI ​​model to the gNB / LMF (the UE itself determines the model application) or not report it.

[0479] Method 1.1.2

[0480] The above-mentioned instruction / request for model application may also be executed based on at least one of the following conditions (timing).

[0481] (Alt1): After the executable AI / ML model is identified / activated.

[0482] (Alt2): After collecting data for model inference.

[0483] (Alt3): When output information related to inference is requested.

[0484] (Alt4): Follow the actual installation procedures of NW / UE.

[0485] Method 1.1.3

[0486] The above-mentioned instruction / request for model application may also include at least one of the following information (Alt1-Alt3).

[0487] (Alt1): Information / table of information related to one / multiple model IDs / model functionality.

[0488] The model ID / model function can also be associated with the ID / function of the identified / activated AI / ML model. The model function can also include different information that the AI / ML model can output (for example, UE location, LOS / NLOS indicator, ToA, AoA / AoD, etc.).

[0489] Furthermore, when a model function is indicated / requested, other auxiliary information associated with the AI / ML model (which may also include tables) may also be indicated / requested. As described above, this auxiliary information may also include information related to the required data volume, model complexity, and so on.

[0490] In addition, when a model function is indicated / requested and multiple models in the UE are capable of implementing the function, the UE can also decide which model among the multiple models to apply.

[0491] (Alt2): Information related to the effectiveness and validity of the AI / ML models used in model inference.

[0492] The validity of an AI / ML model can also be defined by the following information: information regarding the operational time (x seconds / minutes / hours) or number of times (x times) for the AI / ML model when applied on the UE side. This time / number of times can also refer to input / output. Furthermore, this time / number of times can also be the "maximum" operational limit for the AI / ML model. Furthermore, the value x can also be set or indicated by the NW based on the power, complexity, or usage of the AI / ML model.

[0493] (Alt3): Auxiliary information used to facilitate model inference on the UE side.

[0494] The auxiliary information can also reuse the auxiliary information notified from the gNB / LMF mentioned above. In addition, the auxiliary information can also include parameters / IDs associated with the scenario / environment.

[0495] In this disclosure, model identification can also refer to the process of establishing a common identification of AI / ML models between the UE and the NW. In other words, it can also refer to the process of ensuring that the model identified on the UE and the NW are consistent. This process can be specified by a specification or based on the actual NW / UE installation.

[0496] In the present disclosure, model identification (model is identified), model configuration (model is configured), and model registration (model is registered) may also overwrite each other.

[0497] Furthermore, in the above-described approach, the UE may also use the model ID to determine (select) a specific, appropriate model. Alternatively, the model function may be used instead of the model ID. When the UE uses the model function to determine a model, it is also provided with the aforementioned auxiliary information, and the UE may determine a model based on this auxiliary information. By utilizing multiple pieces of information (information related to the model ID / model function, and the auxiliary information), the UE can determine a more appropriate AI / ML model.

[0498] [Implementation Method 1.2]

[0499] Implementation 1.2 Regarding the above-mentioned analysis 1-2, the input information source corresponding to the model reasoning is explained.

[0500] The input information used for model inference may include at least one of the following information (Alt1-Alt2).

[0501] (Alt1): Information related to UE measurements.

[0502] This information may also include UE-measured channel information (e.g., Channel Impulse Response (CIR), Channel Feedback Report (CFR), Power Delay Profile (PDP), etc.). In addition, this information may also include UE measurements of the PRS. This UE-measured information may also be sent from the UE to the LMF via higher-layer signaling.

[0503] (Alt2): Information related to NW (gNB / LMF) indication.

[0504] The UE can also receive this information from the NW via higher-layer signaling / physical layer signaling. Furthermore, for virtual location prediction based on AI / ML models, a large amount of information related to UE measurements (e.g., RSTD / Rx-Tx time difference / ToA) can be used as model input. This input information can also be generated / indicated by the NW, separately from UE measurements. This allows information generated / indicated by the NW to be used as model input (e.g., for training) instead of UE measurements. This reduces UE measurements and reduces UE load.

[0505] [Implementation Method 1.3]

[0506] Implementation 1.3 Regarding the above analysis 1-3, the UE operation (report / feedback) after model inference is described.

[0507] After model inference, the UE may also report or provide feedback on at least one of the following information (Alt1-Alt8). The UE may also use higher-layer signaling or physical layer signaling to report or provide feedback to the network. This information may also be referred to as information related to the result (judgment / decision) of the model application.

[0508] (Alt1): Output of model inference (e.g., UE position, median value).

[0509] (Alt2): GNSS information / intermediate value derived from GNSS information.

[0510] (Alt3): Input for applied model inference.

[0511] (Alt4): Quality of measurement.

[0512] (Alt5): Timestamps of the model's input / output during inference.

[0513] (Alt6): Domain (zone) ID / context ID where the AI / ML model is applied (e.g., information associated with the environment / location around the UE / gNB).

[0514] (Alt7): A table of information associated with a specific ID (e.g., model ID, domain ID, scenario ID).

[0515] (Alt8): Instructions regarding which information to report.

[0516] The UE may also perform the above-mentioned reporting / feedback based on at least one of the following conditions.

[0517] Based on pre-defined rules (e.g., after obtaining model inference / output information).

[0518] After obtaining the model's inference and output information

[0519] Based on settings / instructions from NW (gNB / LMF).

[0520] · Follow the actual installation of UE.

[0521] Regarding the settings / instructions from the NW described above, existing information related to the UE location can also be reused. The UE can report this information based on periodic, semi-persistent or aperiodic settings / instructions.

[0522] According to the first embodiment described above, the UE can appropriately control the decision of applying a model for positioning, the determination of the model to be applied, and the UE operation after model inference, thereby further enhancing model inference.

[0523] <Second embodiment>

[0524] The second embodiment relates to an enhancement of model monitoring for positioning.

[0525] [Implementation Method 2.0]

[0526] Regarding Implementation 2.0, regarding the above-mentioned Analysis 2-0, the definition of model monitoring is explained.

[0527] In this disclosure, model monitoring may also refer to a series of processes for monitoring the inference performance of AI / ML models. Specifically, model monitoring may also include at least one of the following operations:

[0528] Calculation of performance indicators (performance evaluation indicators),

[0529] Evaluation of performance indicators (including comparison with a threshold),

[0530] · Report of calculated performance indicators / performance indicator evaluation (comparison results),

[0531] · Decisions based on the operation of model functions (e.g., monitoring (confirmation of performance) / activation / deactivation / switching / feedback / update).

[0532] The details of each of the above operations are the same as those described above and are therefore omitted.

[0533] [Implementation Method 2.1]

[0534] Implementation 2.1 Regarding the above-mentioned Analysis 2-1, the execution timing and conditions of model monitoring are described.

[0535] The UE may also determine whether to perform model monitoring based on at least one of the following conditions (timing).

[0536] (Alt1): After the NW (gNB / LMF) configures / instructs the UE via higher layer signaling / physical layer signaling.

[0537] (Alt2): After the UE sends a request to the NW via high-layer signaling / physical layer signaling.

[0538] (Alt3): Based on pre-defined rules, the UE makes its own judgment.

[0539] The condition (Alt2) may be further combined with at least one of the following conditions.

[0540] (Alt2-1): The NW sends a response to the request to the UE via higher layer signaling / physical layer signaling.

[0541] (Alt2-2): The NW sends a response to the UE, indicating information related to the model monitoring application. This response may contain the same information as the request or other information. Furthermore, if the NW sends instructions that differ from the UE's request, the UE may either follow the NW's instructions or resend a new request to the NW.

[0542] (Alt2-3): The NW sends a response rejecting the request. In this case, after receiving the response, the UE can either resend the previous request or send a new request.

[0543] In addition, in the condition (Alt2), before the UE sends a request, the UE needs to be shown information about the achievable models (model ID, model functions, etc.), performance indicators, and information about the evaluation.

[0544] The condition (Alt3) may be further combined with at least one of the following conditions.

[0545] (Alt3-1): After the UE obtains the inference output (such as performance indicators).

[0546] (Alt3-2): After the UE obtains the necessary data for comparison with model inference (e.g., performance indicators).

[0547] (Alt3-3): Combined with any conditions.

[0548] (Alt3-4): The validity of the AI / ML model used for model inference expires.

[0549] (Alt3-5): The quality measured by the UE is lower than the threshold.

[0550] (Alt3-6): When the UE applies an AI / ML model in model inference, the number of times the input and output reaches x times or every x seconds / minutes / hours.

[0551] (Alt3-7): During the validity period of the AI / ML model used for model inference.

[0552] In the condition of (Alt3), the UE may also decide not to report the UE operation and the above-mentioned associated information to the NW after making its own judgment.

[0553] [Implementation Method 2.2]

[0554] Regarding Embodiment 2.2, regarding the above-mentioned Analysis 2-2, the request / report of information for model monitoring will be described.

[0555] Method 2.2.1

[0556] The information related to the indication of model monitoring based on NW (gNB / LMF) and the information related to the request for model monitoring based on UE may also include at least one of the information (Alt1-Alt8) shown below.

[0557] (Alt1): A binary indicator indicating whether model monitoring is performed.

[0558] (Alt2): Model ID (multiple model IDs are possible).

[0559] (Alt3): Type of model monitoring (e.g., input-based, output-based, model parameter-based, etc.).

[0560] (Alt4): Information used for model monitoring (e.g., the aforementioned UE location, ToA / RSTD / AoA / AoD, LOS / NLOS indicators, power / complexity / processing time of the AI / ML model, etc.).

[0561] (Alt5): Threshold value to use for performance indicator / comparison.

[0562] (Alt6): Information about the entity that provides the data used to calculate the performance indicator.

[0563] (Alt7): Information related to the entity that makes the judgment / decision after model monitoring.

[0564] (Alt8): Information indicating the model's capabilities.

[0565] Furthermore, the information in (Alt6) may include signaling for sending data to an entity that monitors the model, and requests / reports to an entity that provides data.

[0566] Method 2.2.2

[0567] Regarding model monitoring, information used to calculate the performance index may be obtained based on at least one of the entities (Alt1 to Alt4) shown below.

[0568] (Alt1):PRU.

[0569] As described above, the location of the PRU is known (identified) by the NW (gNB / LMF). The PRU can also calculate intermediate values ​​based on its (own) location. Furthermore, the NW can derive other intermediate values ​​based on the PRU's location. Furthermore, the NW can report or indicate the PRU's location and the aforementioned intermediate values ​​to the UE. Furthermore, in NR positioning, information related to PRUs can be used only by the NW. The UE can also request information related to these PRUs from the NW for model monitoring purposes.

[0570] (Alt2):UE.

[0571] The UE may also use GNSS / AI / ML-based positioning (such as the UE-based positioning described above) to obtain its own position. The UE may also measure PRS for multiple intermediate values. The UE may also report the UE position / measured intermediate values ​​to the NW. Furthermore, in NR positioning, the UE's measurement results (UE position / measured intermediate values) may not be communicated to the NW. The UE's measurement results may be used as input for model inference only during model monitoring. The NW may also request this information (UE measurement results) from the UE for model monitoring purposes.

[0572] (Alt3):LMF.

[0573] The LMF may also use AI / ML-based positioning (such as the NG-RAN node-assisted positioning described above) to derive the UE location. The LMF may also obtain measurement / assistance information from the UE / gNB. The LMF may also send the UE location, gNB measurements, and gNB-side assistance information to the UE. The gNB / UE may also request this information (UE location, measurements, assistance information) from the LMF for model monitoring. Furthermore, in NR positioning, the LMF may not transmit UE-gNB measurements. Regarding UE measurement results, UE-side / gNB-side measurements may be used only as input for model inference during model monitoring.

[0574] (Alt4): gNB / TRP.

[0575] The gNB / TRP can also measure the SRS for multiple intermediate values. The gNB / TRP can also send the measured intermediate values ​​to the UE / LMF. The UE / LMF can also request this information (SRS, intermediate values) from the gNB for model monitoring. Furthermore, in NR positioning, the gNB's measurement results may not be sent to the UE. The gNB's measurement results can be used as input for model inference or only for model monitoring.

[0576] The reporting (sending) / requesting of the information in Alt1-Alt4 of the above-mentioned method 2.2.2 may also use high-layer signaling / physical layer signaling.

[0577] According to the second embodiment described above, the UE can appropriately control the model monitoring for positioning, thereby further strengthening the model monitoring.

[0578] <Supplement>

[0579] [Supplement 1: AI model information]

[0580] In this disclosure, AI model information may also mean information including at least one of the following:

[0581] AI model input / output information,

[0582] Information on pre-processing and post-processing of AI model input and output,

[0583] Information about the parameters of the AI ​​model,

[0584] Training information for AI models (training information),

[0585] Reasoning information for AI models,

[0586] Performance information related to AI models.

[0587] Here, the input / output information of the AI ​​model may also include information related to at least one of the following:

[0588] Contents of input / output data (e.g., RSRP, SINR, amplitude / phase information in the channel matrix (or precoding matrix), information related to the angle of arrival (AoA), information related to the angle of departure (AoD), and location information),

[0589] Auxiliary information about the data (also called meta information),

[0590] The type of input / output data (e.g., immutable value, floating point number),

[0591] The bit width of input / output data (e.g., 64 bits for each input value),

[0592] Quantization interval (quantization step size) of input / output data (for example, 1 dBm for L1-RSRP),

[0593] The range of possible input / output data (e.g., [0, 1]).

[0594] In the present disclosure, information related to AoA may include information related to at least one of the azimuth angle of arrival and the zenith angle of arrival (ZoA). Furthermore, information related to AoD may include information related to at least one of the azimuth angle of departure and the zenith angle of depature (ZoD).

[0595] In the present disclosure, location information may also refer to location information related to the UE / NW. The location information may also include at least one of information obtained using a positioning system (e.g., satellite positioning systems (Global Navigation Satellite System (GNSS)), Global Positioning System (GPS)), etc.) (e.g., latitude, longitude, altitude), information about a base station (BS) adjacent to (or serving) the UE (e.g., BS / cell identifier (ID), BS-UE distance, direction / angle of the BS (UE) as seen from the UE (BS), coordinates of the BS (UE) as seen from the UE (BS) (e.g., X / Y / Z coordinates), etc.), and a specific address of the UE (e.g., Internet Protocol (IP) address). The UE's location information is not limited to information based on the location of the BS and may also be information based on a specific point.

[0596] The location information may also include information related to the installation of the antenna itself (eg, the location / position / orientation of the antenna, the location / orientation of the antenna panel, the number of antennas, the number of antenna panels, etc.).

[0597] The location information may also include mobility information. The mobility information may also include at least one of information indicating mobility type, UE's moving speed, UE's acceleration, and UE's moving direction.

[0598] Here, the mobility type may also be equivalent to at least one of fixed location UE, movable / moving UE, no mobility UE, low mobility UE, middle mobility UE, high mobility UE, cell-edge UE, not-cell-edge UE, etc.

[0599] In the present disclosure, environmental information (used for data) may also be information related to the environment in which the data is obtained / used, for example, it may also be equivalent to information representing frequency information (frequency band ID, etc.), environment type information (at least one of indoor, outdoor, Urban Macro (UMa), Urban Micro (Urban Micro (Umi)), etc.), line of site (LOS) / non-line of site (NLOS) information, etc.

[0600] Here, LOS may also mean that the UE and BS are in an environment where they can see each other (or there are no obstructions), and NLOS may also mean that the UE and BS are not in an environment where they can see each other (or there are obstructions). The information indicating LOS / NLOS may indicate either a soft value (e.g., the probability of LOS / NLOS) or a hard value (e.g., either LOS / NLOS).

[0601] In this disclosure, meta-information may also refer to, for example, information related to input / output information suitable for AI models, information related to available / retrievable data, and so on. Meta-information may specifically include information related to RS (e.g., CSI-RS / SRS / SSB) beams (e.g., the angle of each beam, 3dB beamwidth, beam shape, and number of beams), gNB / UE antenna layout information, frequency information, environmental information, and meta-information IDs. Meta-information can also be used as input / output for AI models.

[0602] The information used for pre-processing / post-processing of the input / output of the AI ​​model may also include information related to at least one of the following:

[0603] whether to apply normalization (e.g., z-score normalization, min-max normalization),

[0604] Parameters used for normalization (e.g., mean / dispersion for Z-score normalization, min / max for min-max normalization),

[0605] Whether to apply specific numerical transformation methods (e.g., one hot encoding, label encoding, etc.),

[0606] · Selection rules for whether to use as training data.

[0607] For example, for the input information x, the normalized input information xnew that has been Z-score normalized (xnew = (x-μ) / σ. Here μ is the average of x and σ is the standard deviation) can be input into the AI ​​model as a pre-processing, or the output yout from the AI ​​model can be post-processed to obtain the final output y.

[0608] The information about the parameters of the AI ​​model may also include information related to at least one of the following:

[0609] Information about weights in the AI ​​model (e.g., coefficients (binding coefficients) of neurons),

[0610] The structure of the AI ​​model,

[0611] The type of AI model used as a component of the model (e.g., Residual Network (ResNet), DenseNet, RefineNet, Transformer model, CRBlock, Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU)),

[0612] The AI ​​model’s capabilities as components (e.g., decoder, encoder).

[0613] In addition, the weight information in the above AI model may also include information related to at least one of the following:

[0614] The bit width (size) of the weight information,

[0615] ·The quantization interval of the weight information,

[0616] The granularity of the weight information,

[0617] The acceptable range of weight information,

[0618] ·The parameters of the weights in the AI ​​model,

[0619] Differential information from the AI ​​model before the update (in the case of an update),

[0620] Weight initialization methods (e.g., zero initialization, random initialization (based on normal distribution / uniform distribution / truncated normal distribution), Xavier initialization (for sigmoid function), He initialization (for Rectified Linear Units (ReLU))).

[0621] In addition, the structure of the AI ​​model may also include information related to at least one of the following:

[0622] Number of layers,

[0623] The type of layer (e.g., convolutional layer, activation layer, fully connected (dense) layer, normalization layer, pooling layer, attention layer),

[0624] Layer information,

[0625] Time series-specific parameters (e.g., bidirectionality, temporal phase),

[0626] Parameters used for training (e.g., type of feature (L2 regularization, dropout feature, etc.), where (e.g., after which layer) to set the feature).

[0627] The layer information may also include information related to at least one of the following:

[0628] the number of neurons in each layer,

[0629] Convolution kernel size,

[0630] The stride used for pooling / convolutional layers,

[0631] Pooling method (MaxPooling, AveragePooling, etc.),

[0632] Information about the residual block,

[0633] Number of heads,

[0634] Normalization methods (batch normalization, instance normalization, layer normalization, etc.),

[0635] Activation functions (Sigmoid, tanh function, ReLU, Leaky ReLU information, Maxout, Softmax).

[0636] An AI model can also be included as a component of another AI model. For example, an AI model can be an AI model that is processed in the order of ResNet as model component #1, Transformer model as model component #2, fully connected layer, and normalization layer.

[0637] The training information for the AI ​​model may also include information related to at least one of the following:

[0638] Information about the optimization algorithm used (e.g., the type of optimization (Stochastic Gradient Descent (SGD)), AdaGrad, Adam, etc.), and the parameters used for optimization (learning rate, momentum, etc.).

[0639] Information about the loss function (e.g., information about the metrics of the loss function (Mean Absolute Error (MAE)), Mean Square Error (MSE), cross entropy loss, NLLLoss, Kullback-Leibler (KL) divergence, etc.)),

[0640] Parameters that should be frozen for training (e.g., layers, weights),

[0641] Parameters that should be updated (e.g., layers, weights),

[0642] Parameters (e.g., layers, weights) that should be used as initial parameters for training,

[0643] The AI ​​model’s training / update method (e.g., the (recommended) number of training epochs, batch size, and the amount of data used in training).

[0644] The inference information used for the AI ​​model may also include information related to decision tree branch pruning, parameter quantization, and AI model functions. Here, the AI ​​model function may also correspond to at least one of time-domain beam prediction, spatial-domain beam prediction, an autoencoder for CSI feedback, and an autoencoder for beam management.

[0645] The autoencoder for CSI feedback can also be used as follows:

[0646] The UE can also send the coded bits as CSI feedback (CSI report) to the AI ​​model of the encoder, which takes CSI / channel matrix / precoding matrix as input and outputs the coded bits.

[0647] The BS may also reconstruct the CSI / channel matrix / precoding matrix in the AI ​​model of the decoder, taking the received coded bits as input and outputting the CSI / channel matrix / precoding matrix.

[0648] In spatial domain beam prediction, the UE / BS can also input sparse (or coarse) beam-based measurement results (beam quality, for example, RSRP) into the AI ​​model and output dense (or fine) beam quality.

[0649] In time-domain beam prediction, the UE / BS can also input time-series (past, current, etc.) measurement results (beam quality, for example, RSRP) into the AI ​​model and output future beam quality.

[0650] The performance information related to the above-mentioned AI model may also include information related to the expected value of the loss function defined for the AI ​​model.

[0651] The AI ​​model information in this disclosure may also include information related to the application scope (possible application scope) of the AI ​​model. This application scope may also be indicated by a physical cell ID, serving cell index, etc. Information related to the application scope may also be included in the aforementioned environmental information.

[0652] AI model information related to a specific AI model can be pre-specified in a specification or notified to the UE from the network (NW). The AI ​​model specified in the specification is also referred to as the reference AI model. AI model information related to the reference AI model is also referred to as reference AI model information.

[0653] Furthermore, the AI ​​model information in this disclosure may also include an index for identifying the AI ​​model (e.g., also referred to as an AI model index, AI model ID, model ID, etc.). The AI ​​model information in this disclosure may include an AI model index in addition to or in place of the aforementioned AI model input / output information. The association between the AI ​​model index and AI model information (e.g., AI model input / output information) may be pre-specified in the specification or notified to the UE from the NW.

[0654] In this disclosure, AI model information may also be associated with an AI model. AI model-related information (relevant information) may also be referred to as relevant information. AI model-related information may not explicitly include information used to identify the AI ​​model. For example, AI model-related information may include only metadata.

[0655] In the present disclosure, the model ID may be interchangeable with the ID corresponding to the set of AI models (model set ID). Furthermore, in the present disclosure, the model ID may be interchangeable with the meta-information ID. Meta-information (or meta-information ID) may also be associated with information related to beams (beam settings) as described above. For example, meta-information (or meta-information ID) may be used by the UE to select an AI model based on which beam the BS uses, or may be used to notify the BS of which beam to use in order to apply the AI ​​model deployed by the UE. Furthermore, in the present disclosure, the meta-information ID may be interchangeable with the ID corresponding to the set of meta-information (meta-information set ID).

[0656] [Supplement 2: Information Notification to UE]

[0657] The notification of arbitrary information (from the NW) to the UE in the above-mentioned embodiment (in other words, the reception of arbitrary information from the BS in the UE) can also be carried out using physical layer signaling (e.g., DCI), high-layer signaling (e.g., RRC signaling, MACCE), specific signals / channels (e.g., PDCCH, PDSCH, reference signals), or a combination thereof.

[0658] When the notification is performed through a MAC CE, the MAC CE may be identified by including a new logical channel ID (LCID) not specified in existing specifications in the MAC subheader.

[0659] When the above notification is performed through DCI, the above notification may be performed through a specific field of the DCI, a Radio Network Temporary Identifier (RNTI) used in scrambling cyclic redundancy check (CRC) bits assigned to the DCI, the format of the DCI, and the like.

[0660] In addition, notification of any information in the above-mentioned embodiments to the UE may be performed periodically, semi-continuously, or aperiodically.

[0661] [Supplement 3: Notification of information from UE]

[0662] The notification of arbitrary information from the UE (to the NW) in the above-mentioned embodiment (in other words, the sending / reporting of arbitrary information from the UE to the BS) can also be performed using physical layer signaling (e.g., UCI), high-layer signaling (e.g., RRC signaling, MAC CE), specific signals / channels (e.g., PUCCH, PUSCH, PRACH, reference signals), or a combination thereof.

[0663] When the above notification is performed through MAC CE, the MAC CE can also be identified by including a new LCID that is not specified in the existing specifications in the MAC subheader.

[0664] When the notification is performed through UCI, the notification may be transmitted using PUCCH or PUSCH.

[0665] Furthermore, the notification of arbitrary information from the UE in the above-mentioned embodiments may be performed periodically, semi-continuously, or aperiodically.

[0666] [Regarding the application of each embodiment]

[0667] At least one of the above embodiments may also be applied when a specific condition is met, which may be specified in the specification or notified to the UE / BS using higher layer signaling / physical layer signaling.

[0668] At least one of the above-mentioned embodiments may also be applied only to a UE that reports a specific UE capability (UE capability) or supports the specific UE capability.

[0669] Support AI / ML-based positioning.

[0670] Support for AI models used to obtain UE location.

[0671] Supports model reasoning / model monitoring (performance monitoring).

[0672] The specific UE capability may also indicate support for specific processing / operation / control / information for at least one of the above-mentioned implementations / options / selections.

[0673] In addition, the above-mentioned specific UE capabilities can be capabilities that are applied across all frequencies (commonly regardless of frequency), or capabilities for each frequency (for example, one or a combination of cells, bands, band combinations, BWPs, component carriers, etc.), or capabilities for each frequency range (for example, Frequency Range 1 (FR1), FR2, FR3, FR4, FR5, FR2-1, FR2-2), or capabilities for each subcarrier spacing (SubCarrier Spacing (SCS)), or capabilities for each feature set (Feature Set (FS)) or each feature set (Feature Set Per Component-carrier (FSPC)) of each component carrier.

[0674] Furthermore, the specific UE capability may be a capability applied across all full-duplex modes (commonly regardless of the duplex mode) or a capability for each duplex mode (eg, time division duplex (TDD) or frequency division duplex (FDD)).

[0675] Furthermore, at least one of the aforementioned embodiments may also be applied when specific information associated with the aforementioned embodiment is configured / activated / triggered by the UE via higher layer signaling / physical layer signaling (or actions related to the aforementioned embodiment are performed). For example, the specific information may include information indicating activation of AI model utilization, information indicating activation of CSI prediction, information indicating activation of dataset-based data collection / model monitoring, or arbitrary RRC parameters for a specific release (e.g., Rel. 18 / 19).

[0676] Even if the UE does not support at least one of the above-mentioned specific UE capabilities or is not configured with the above-mentioned specific information, the UE may apply operations such as Rel.15 / 16.

[0677] (Note)

[0678] The following inventions are added to one embodiment (first embodiment) of the present disclosure.

[0679] [Note 1]

[0680] A terminal having:

[0681] a receiving unit for receiving information for determining application of an AI model for positioning based on artificial intelligence (AI); and

[0682] A control unit determines the application of the AI ​​model based on the information.

[0683] [Note 2]

[0684] The terminal as described in Supplement 1, wherein:

[0685] The information includes at least one of information related to the location of the terminal, model ID, model function, and model validity.

[0686] [Note 3]

[0687] The terminal as described in Supplement 1 or Supplement 2, wherein:

[0688] After determining the applied AI model, the control unit controls reporting of information related to the output of model inference.

[0689] [Note 4]

[0690] The terminal according to any one of Supplement 1 to Supplement 3, wherein:

[0691] It also includes a sending unit that sends information related to the judgment of the application of the AI ​​model,

[0692] The information related to the determination of application of the AI ​​model includes at least one of information related to a location of the terminal, a measured intermediate value, and a specific ID of the AI ​​model.

[0693] (Note)

[0694] The following inventions are additionally described with respect to one embodiment (second embodiment) of the present disclosure.

[0695] [Note 1]

[0696] A terminal having:

[0697] a receiving unit for receiving information for performance monitoring regarding positioning based on artificial intelligence (AI); and

[0698] A control unit controls the performance monitoring based on the information,

[0699] The control unit calculates or evaluates a performance evaluation index used for the performance monitoring.

[0700] [Note 2]

[0701] The terminal as described in Supplement 1, wherein:

[0702] The control unit determines whether to perform the performance monitoring based on a specific condition.

[0703] [Note 3]

[0704] The terminal as described in Supplement 1 or Supplement 2, wherein:

[0705] The specific condition is at least one of acquisition of the performance evaluation index, request for information related to the application of the performance monitoring, and a validity period of an applied AI model.

[0706] [Note 4]

[0707] The terminal according to any one of Supplement 1 to Supplement 3, wherein:

[0708] The control unit controls acquisition of information related to calculation of the performance indicator index from a specific entity.

[0709] (Wireless Communication System)

[0710] The following describes a configuration of a wireless communication system according to an embodiment of the present disclosure. In this wireless communication system, communication is performed using any one of the wireless communication methods according to the above-described embodiments of the present disclosure or a combination thereof.

[0711] Figure 11 This figure shows an example of a schematic configuration of a wireless communication system according to one embodiment. Wireless communication system 1 (may also be simply referred to as system 1) may be a system that implements communication using Long Term Evolution (LTE) standardized by the Third Generation Partnership Project (3GPP) or the fifth-generation mobile communication system New Radio (5G NR).

[0712] In addition, the wireless communication system 1 may also support dual connectivity between multiple radio access technologies (Radio Access Technologies (RATs)) (Multi-RAT Dual Connectivity (MR-DC)). MR-DC may also include dual connectivity between LTE (Evolved Universal Terrestrial Radio Access (E-UTRA)) and NR (E-UTRA-NR Dual Connectivity (EN-DC)), dual connectivity between NR and LTE (NR-E-UTRA Dual Connectivity (NE-DC)), and the like.

[0713] 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.

[0714] The wireless communication system 1 may also support dual connectivity between multiple base stations within the same RAT (for example, dual connectivity (NR-NR Dual Connectivity (NN-DC)) in which both the MN and the SN are NR base stations (gNB)).

[0715] The wireless communication system 1 may also include a base station 11 that forms a macrocell C1 with relatively wide coverage, and base stations 12 (12a-12c) that are deployed within the macrocell C1 and form small cells C2 that are narrower than the macrocell C1. User terminals 20 may also be located within at least one of the cells. The arrangement and number of cells and user terminals 20 are not limited to those shown in the figure. Hereinafter, when not distinguishing between base stations 11 and 12, they are collectively referred to as base stations 10.

[0716] The user terminal 20 may be connected to at least one of the multiple base stations 10. The user terminal 20 may utilize at least one of carrier aggregation (CA) using multiple component carriers (CCs) and dual connectivity (DC).

[0717] 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)). Macrocell C1 may be included in FR1, and small cell C2 may be included in FR2. For example, FR1 may be a frequency band below 6 GHz (sub-6 GHz), and FR2 may be a frequency band higher than 24 GHz (above-24 GHz). The frequency bands and definitions of FR1 and FR2 are not limited to these. For example, FR1 may correspond to a frequency band higher than FR2.

[0718] Furthermore, the user terminal 20 may perform communication using at least one of time division duplex (TDD) and frequency division duplex (FDD) in each CC.

[0719] Multiple base stations 10 may be connected via wired (e.g., optical fiber based on the Common Public Radio Interface (CPRI), an X2 interface, etc.) or wireless (e.g., NR communication). For example, when NR communication is used as a backhaul between base stations 11 and 12, base station 11, which functions as a host station, may be referred to as an Integrated Access Backhaul (IAB) donor, and base station 12, which functions as a relay station (relay), may be referred to as an IAB node.

[0720] The base station 10 may be connected to the core network 30 via other base stations 10 or directly. The core network 30 may include, for example, at least one of an evolved packet core (EPC), a 5G core network (5GCN), and a next generation core (NGC).

[0721] The core network 30 may also include network functions (NFs), such as the User Plane Function (UPF), Access and Mobility Management Function (AMF), Session Management Function (SMF), Unified Data Management (UDM), Application Function (AF), Data Network (DN), Location Management Function (LMF), and Operation, Administration, and Maintenance (Management) (OAM). Furthermore, a single network node may provide multiple functions. Furthermore, communication with external networks (e.g., the Internet) may also be conducted via the DN.

[0722] The user terminal 20 may also be a terminal that supports at least one of communication methods such as LTE, LTE-A, and 5G.

[0723] In the wireless communication system 1 , a radio access scheme based on orthogonal frequency division multiplexing (OFDM) may be used. For example, in at least one of the downlink (DL) and uplink (UL), cyclic prefix OFDM (CP-OFDM), discrete Fourier transform spread OFDM (DFT-s-OFDM), orthogonal frequency division multiple access (OFDMA), or single carrier frequency division multiple access (SC-FDMA) may be used.

[0724] The radio access scheme may also be referred to as a waveform. In addition, in the wireless communication system 1 , other radio access schemes (eg, other single-carrier transmission schemes, other multi-carrier transmission schemes) may be used as the UL and DL radio access schemes.

[0725] As downlink channels, the wireless communication system 1 may use a downlink shared channel (Physical Downlink Shared Channel (PDSCH)) shared by each user terminal 20 , a broadcast channel (Physical Broadcast Channel (PBCH)), a downlink control channel (Physical Downlink Control Channel (PDCCH)), etc.

[0726] In addition, as uplink channels, the wireless communication system 1 can also use an uplink shared channel (Physical Uplink Shared Channel (PUSCH)) shared by each user terminal 20, an uplink control channel (Physical Uplink Control Channel (PUCCH)), a random access channel (Physical Random Access Channel (PRACH)), etc.

[0727] User data, higher-layer control information, and system information blocks (SIBs) are transmitted via the PDSCH. User data and higher-layer control information can also be transmitted via the PUSCH. Furthermore, the Master Information Block (MIB) can also be transmitted via the PBCH.

[0728] The lower layer control information may also be transmitted via the PDCCH. The lower layer control information may include, for example, downlink control information (Downlink Control Information (DCI)) including scheduling information for at least one of the PDSCH and the PUSCH.

[0729] In addition, the DCI that schedules the PDSCH may also be referred to as DL allocation, DL DCI, etc., and the DCI that schedules the PUSCH may also be referred to as UL grant, UL DCI, etc. In addition, the PDSCH may also be rewritten as DL data, and the PUSCH may also be rewritten as UL data.

[0730] PDCCH detection also utilizes control resource sets (CORESETs) and search spaces. A CORESET corresponds to the resources used to search for DCI. A search space corresponds to the search area and search method for PDCCH candidates. A CORESET can be associated with one or more search spaces. Based on the search space configuration, the UE can monitor the CORESETs associated with a particular search space.

[0731] A search space may also correspond to PDCCH candidates corresponding to one or more aggregation levels. One or more search spaces may also be referred to as a search space set. Furthermore, the terms "search space," "search space set," "search space configuration," "search space set configuration," "CORESET," and "CORESET configuration" in this disclosure may be interchangeable.

[0732] The PUCCH can also transmit uplink control information (uplink control information (UCI)) including at least one of channel state information (CSI), delivery confirmation information (e.g., also known as hybrid automatic repeat request ACKnowledgement (HARQ-ACK), ACK / NACK, etc.), and scheduling request (SR). The PRACH can also transmit the random access preamble used to establish a connection with a cell.

[0733] In the present disclosure, downlink, uplink, etc. may be expressed without the word “link.” Furthermore, various channels may be expressed without the word “physical” at the beginning.

[0734] In the wireless communication system 1, a synchronization signal (SS), a downlink reference signal (DL-RS), and the like may also be transmitted. As DL-RSs, 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), and a phase tracking reference signal (PTRS) may also be transmitted.

[0735] For example, a synchronization signal may be at least one of a primary synchronization signal (PSS) and a secondary synchronization signal (SSS). A signal block containing SSs (PSS, SSS) and PBCHs (and DMRS for the PBCH) may also be referred to as an SS / PBCH block or an SS block (SSB). Furthermore, SSs and SSBs may also be referred to as reference signals.

[0736] In addition, wireless communication system 1 may also transmit a sounding reference signal (SRS) or a demodulation reference signal (DMRS) as an uplink reference signal (UL-RS). DMRS is also called a user terminal-specific reference signal (UE-specific Reference Signal).

[0737] (Base Station)

[0738] Figure 12 This figure shows an example of the configuration of a base station according to one embodiment. The base station 10 includes a control unit 110, a transceiver unit 120, a transceiver antenna 130, and a transmission path interface (transmission line interface) 140. Furthermore, one or more of each of the control unit 110, the transceiver unit 120, the transceiver antenna 130, and the transmission path interface 140 may be provided.

[0739] In addition, in this example, the functional blocks of the characteristic parts of this embodiment are mainly shown, and it is also conceivable that the base station 10 also has other functional blocks required for wireless communication. Part of the processing of each unit described below may also be omitted.

[0740] The control unit 110 controls the entire base station 10. The control unit 110 can be composed of a controller, a control circuit, and the like that are described based on common knowledge in the technical field to which this disclosure relates.

[0741] The control unit 110 may also control signal generation, scheduling (e.g., resource allocation, mapping), etc. It may also control transmission, reception, and measurement using the transceiver unit 120, the transceiver antenna 130, and the transmission path interface 140. The control unit 110 may also generate data, control information, sequences, etc. to be transmitted as signals and forward them to the transceiver unit 120. The control unit 110 may also perform call processing (e.g., setup and release) of communication channels, manage the status of the base station 10, and manage radio resources.

[0742] Transmitter / receiver unit 120 may also include a baseband unit 121, a radio frequency (RF) unit 122, and a measurement unit 123. Baseband unit 121 may also include a transmit processing unit 1211 and a receive processing unit 1212. Transmitter / receiver unit 120 may include a transmitter / receiver, RF circuits, baseband circuits, filters, phase shifters, measurement circuits, transmit / receive circuits, and the like, as described based on common knowledge in the technical fields involved in this disclosure.

[0743] The transmitting and receiving unit 120 may be configured as an integrated transmitting and receiving unit or may be configured as a transmitting unit and a receiving unit. The transmitting unit may also be configured as a transmitting processing unit 1211 and an RF unit 122. The receiving unit may also be configured as a receiving processing unit 1212, an RF unit 122, and a measuring unit 123.

[0744] The transmitting and receiving antenna 130 can be formed of an antenna described based on common knowledge in the technical field to which this disclosure relates, such as an array antenna.

[0745] The transmitting and receiving unit 120 may also transmit the aforementioned downlink channel, synchronization signal, downlink reference signal, etc. The transmitting and receiving unit 120 may also receive the aforementioned uplink channel, uplink reference signal, etc.

[0746] The transmitting and receiving unit 120 may also use digital beamforming (eg, precoding), analog beamforming (eg, phase rotation), etc. to form at least one of a transmitting beam and a receiving beam.

[0747] The transmitting and receiving unit 120 (transmitting processing unit 1211) may perform processing at the Packet Data Convergence Protocol (PDCP) layer, processing at the Radio Link Control (RLC) layer (e.g., RLC retransmission control), processing at the Medium Access Control (MAC) layer (e.g., HARQ retransmission control), etc. on the data and control information obtained from the control unit 110, to generate a bit string to be transmitted.

[0748] The transmitting and receiving unit 120 (transmitting processing unit 1211) may also perform transmission processing such as channel coding (which may also include error correction coding), modulation, mapping, filter processing (filtering processing), discrete Fourier transform (DFT) processing (as needed), inverse fast Fourier transform (IFFT) processing), precoding, digital-to-analog conversion, etc. on the bit sequence to be transmitted, and output a baseband signal.

[0749] The transmitting and receiving unit 120 (RF unit 122 ) may also perform modulation, filter processing, amplification, etc. on the baseband signal to a radio frequency band, and transmit the signal in the radio frequency band via the transmitting and receiving antenna 130 .

[0750] Meanwhile, the transmitting and receiving unit 120 (RF unit 122 ) may also perform amplification, filter processing (filtering), and demodulation into baseband signals on the radio frequency band signals received via the transmitting and receiving antenna 130 .

[0751] The transmitting and receiving unit 120 (receiving processing unit 1212) may also apply receiving processing such as analog-to-digital conversion, fast Fourier transform (FFT) processing, inverse discrete Fourier transform (IDFT) processing (as needed), filter processing (filtering processing), demapping, demodulation, decoding (which may also include error correction decoding), MAC layer processing, RLC layer processing, and PDCP layer processing to the obtained baseband signal to obtain user data, etc.

[0752] The transmitting / receiving unit 120 (measuring unit 123) may also perform measurements related to received signals. For example, the measuring unit 123 may also perform radio resource management (RRM) measurements and channel state information (CSI) measurements based on the received signals. The measuring unit 123 may also measure received power (e.g., Reference Signal Received Power (RSRP)), received quality (e.g., Reference Signal Received Quality (RSRQ), Signal to Interference plus Noise Ratio (SINR), Signal to Noise Ratio (SNR)), signal strength (e.g., Received Signal Strength Indicator (RSSI)), and propagation path information (e.g., CSI). The measurement results may also be output to the control unit 110.

[0753] The transmission path interface 140 can also send and receive signals (return signaling) between the devices included in the core network 30 (for example, the network node providing NF), other base stations 10, etc., and obtain and transmit user data (user plane data), control plane data, etc. for the user terminal 20.

[0754] In addition, the transmitting unit and the receiving unit of the base station 10 in the present disclosure may also be composed of at least one of the transmitting and receiving unit 120 , the transmitting and receiving antenna 130 , and the transmission path interface 140 .

[0755] Furthermore, the transmitting and receiving unit 120 may receive information for determining the application of an AI model for positioning based on artificial intelligence (AI). The transmitting and receiving unit 120 may also transmit information related to the determination of the application of the AI ​​model.

[0756] The control unit 110 may also determine the application of the AI ​​model based on the information. After determining the applied AI model, the control unit 110 may also control the reporting of information related to the output of the model inference.

[0757] The information may also include at least one of information related to the terminal's location, a model ID, a model function, and model validity. The information related to the determination of application of the AI ​​model may also include at least one of information related to the terminal's location, a measured intermediate value, and a specific ID of the AI ​​model.

[0758] The transmitting and receiving unit 120 may receive information for performance monitoring in addition to positioning based on artificial intelligence (AI).

[0759] The control unit 110 may also control the performance monitoring based on the information and calculate or evaluate the performance evaluation index used for the performance monitoring. The control unit 110 may also determine whether to perform the performance monitoring based on specific conditions. The control unit 110 may also control the acquisition of information related to the calculation of the performance index from a specific entity.

[0760] The specific condition may be at least one of acquisition of the performance evaluation index, request for information related to the application of the performance monitoring, and a validity period of an applied AI model.

[0761] (User Terminal)

[0762] Figure 13 This figure shows an example of the configuration of a user terminal according to one embodiment. The user terminal 20 includes a control unit 210, a transmitting / receiving unit 220, and a transmitting / receiving antenna 230. Furthermore, the control unit 210, the transmitting / receiving unit 220, and the transmitting / receiving antenna 230 may each be provided in one or more units.

[0763] In addition, in this example, the functional blocks of the characteristic parts of this embodiment are mainly shown, and it is also assumed that the user terminal 20 also has other functional blocks required for wireless communication. Part of the processing of each unit described below may also be omitted.

[0764] The control unit 210 controls the entire user terminal 20. The control unit 210 can be composed of a controller, a control circuit, and the like that are described based on common knowledge in the technical field to which this disclosure relates.

[0765] The control unit 210 may also control signal generation, mapping, etc. The control unit 210 may also control transmission, reception, measurement, etc. using the transmission and reception unit 220 and the transmission and reception antenna 230. The control unit 210 may also generate data, control information, sequences, etc. to be transmitted as signals and forward them to the transmission and reception unit 220.

[0766] The transceiver unit 220 may also include a baseband unit 221, an RF unit 222, and a measurement unit 223. The baseband unit 221 may also include a transmission processing unit 2211 and a reception processing unit 2212. The transceiver unit 220 may include a transmitter / receiver, an RF circuit, a baseband circuit, a filter, a phase shifter, a measurement circuit, a transceiver circuit, and the like, which are described based on common knowledge in the technical fields involved in this disclosure.

[0767] The transmitting and receiving unit 220 may be configured as an integrated transmitting and receiving unit or may be composed of a transmitting unit and a receiving unit. The transmitting unit may also be composed of a transmitting processing unit 2211 and an RF unit 222. The receiving unit may also be composed of a receiving processing unit 2212, an RF unit 222, and a measuring unit 223.

[0768] The transmitting and receiving antenna 230 can be formed of an antenna described based on common knowledge in the technical field involved in the present disclosure, such as an array antenna.

[0769] The transmitting and receiving unit 220 may also receive the aforementioned downlink channel, synchronization signal, downlink reference signal, etc. The transmitting and receiving unit 220 may also transmit the aforementioned uplink channel, uplink reference signal, etc.

[0770] The transmitting and receiving unit 220 may also use digital beamforming (eg, precoding), analog beamforming (eg, phase rotation), etc. to form at least one of a transmitting beam and a receiving beam.

[0771] The transmitting and receiving unit 220 (transmitting processing unit 2211) may also perform PDCP layer processing, RLC layer processing (e.g., RLC retransmission control), MAC layer processing (e.g., HARQ retransmission control), etc. on the data and control information obtained from the control unit 210, and generate a bit string to be transmitted.

[0772] The transmitting and receiving unit 220 (transmitting processing unit 2211) can also perform channel coding (which may also include error correction coding), modulation, mapping, filter processing (filtering processing), DFT processing (as needed), IFFT processing, precoding, digital-to-analog conversion and other transmission processing on the bit string to be transmitted, and output a baseband signal.

[0773] Furthermore, whether DFT processing is applied may also be determined based on the transform precoding configuration. For a particular channel (e.g., PUSCH), if transform precoding is enabled, the transceiver unit 220 (transmit processing unit 2211) may perform DFT processing as part of the aforementioned transmit processing in order to transmit the channel using a DFT-s-OFDM waveform. Otherwise, the transceiver unit 220 (transmit processing unit 2211) may perform DFT processing as part of the aforementioned transmit processing.

[0774] The transmitting and receiving unit 220 (RF unit 222 ) may also perform modulation, filter processing (filtering), amplification, etc. on the baseband signal to a radio frequency band, and transmit the signal in the radio frequency band via the transmitting and receiving antenna 230 .

[0775] Meanwhile, the transmitting and receiving unit 220 (RF unit 222 ) may also perform amplification, filter processing (filtering processing), and demodulation into a baseband signal on the radio frequency band signal received via the transmitting and receiving antenna 230 .

[0776] The transmitting and receiving unit 220 (receiving processing unit 2212) may also apply receiving processing such as analog-to-digital conversion, FFT processing, IDFT processing (as needed), filter processing (filtering processing), demapping, demodulation, decoding (which may also include error correction decoding), MAC layer processing, RLC layer processing, and PDCP layer processing to the obtained baseband signal, and obtain user data, etc.

[0777] The transmitting / receiving unit 220 (measuring unit 223) may also perform measurements related to received signals. For example, the measuring unit 223 may also perform RRM measurements and CSI measurements based on the received signals. The measuring unit 223 may also measure received power (e.g., RSRP), received quality (e.g., RSRQ, SINR, SNR), signal strength (e.g., RSSI), propagation path information (e.g., CSI), etc. The measurement results may also be output to the control unit 210.

[0778] In addition, the measurement unit 223 may also derive channel measurements for CSI calculation based on channel measurement resources. Channel measurement resources may also be, for example, non-zero power (NZP) CSI-RS resources. In addition, the measurement unit 223 may also derive interference measurements for CSI calculation based on interference measurement resources. Interference measurement resources may also be at least one of NZP CSI-RS resources for interference measurement, CSI-Interference Measurement (IM) resources, etc. In addition, CSI-IM may be referred to as CSI-Interference Management (IM) and may be interchangeable with Zero Power (ZP) CSI-RS. In addition, in the present disclosure, CSI-RS, NZP CSI-RS, ZP CSI-RS, CSI-IM, CSI-SSB, etc. may be interchangeable.

[0779] In addition, the transmitting unit and the receiving unit of the user terminal 20 in the present disclosure may also be composed of at least one of the transmitting and receiving unit 220 and the transmitting and receiving antenna 230 .

[0780] Furthermore, the transmitting and receiving unit 220 may receive information for determining the application of an AI model for positioning based on artificial intelligence (AI). The transmitting and receiving unit 220 may also transmit information related to the determination of the application of the AI ​​model.

[0781] The control unit 210 may also determine the application of the AI ​​model based on the information. After determining the applied AI model, the control unit 210 may also control the reporting of information related to the output of the model inference.

[0782] The information may also include at least one of information related to the terminal's location, a model ID, a model function, and model validity. The information related to the determination of application of the AI ​​model may also include at least one of information related to the terminal's location, a measured intermediate value, and a specific ID of the AI ​​model.

[0783] The transmitting and receiving unit 220 may also receive information for performance monitoring regarding positioning based on artificial intelligence (AI).

[0784] The control unit 210 may also control the performance monitoring based on the information, and calculate or evaluate the performance evaluation index used for the performance monitoring. The control unit 210 may also determine whether to perform the performance monitoring based on specific conditions. The control unit 210 may also control the acquisition of information related to the calculation of the performance index from a specific entity.

[0785] The specific condition may be at least one of acquisition of the performance evaluation index, request for information related to the application of the performance monitoring, and a validity period of an applied AI model.

[0786] (Hardware structure)

[0787] Furthermore, the block diagrams used in the description of the above embodiments illustrate blocks of functional units. These functional blocks (structural units) are implemented by any combination of at least one of hardware and software. Furthermore, the implementation method of each functional block is not particularly limited. Specifically, each functional block can be implemented using a single device that is physically or logically combined, or by connecting two or more physically or logically separate devices directly or indirectly (e.g., by wired or wireless connections) to implement these multiple devices. A functional block can also be implemented by combining one or more of these devices with software.

[0788] Functions include, but are not limited to, judging, determining, calculating, calculating, processing, deriving, investigating, searching, confirming, receiving, sending, outputting, accessing, resolving, selecting, choosing, establishing, comparing, assuming, expecting, regarding, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assigning. For example, a functional block (structural unit) that implements a transmitting function may also be referred to as a transmitting unit, a transmitter, or the like. Any of these functions are as described above, and their implementation methods are not particularly limited.

[0789] For example, a base station, a user terminal, etc. in one embodiment of the present disclosure may also function as a computer that performs processing of the wireless communication method of the present disclosure. Figure 14This figure shows an example of the hardware configuration of a base station and a user terminal according to one embodiment. The base station 10 and the user terminal 20 described above can also 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, and the like.

[0790] In this disclosure, the terms "device," "circuit," "equipment," "section," and "unit" are interchangeable. The hardware configuration of the base station 10 and the user terminal 20 may include one or more of the devices shown in the figures, or may exclude some of the devices.

[0791] For example, although only one processor 1001 is shown, multiple processors may be provided. Furthermore, processing may be performed by a single processor, or by two or more processors simultaneously, sequentially, or using other methods. Furthermore, processor 1001 may be implemented using more than one chip.

[0792] The functions of the base station 10 and the user terminal 20 are realized, for example, by reading specific software (program) into hardware such as the processor 1001 and the memory 1002, so that the processor 1001 performs calculations and controls communication via the communication device 1004, or controls at least one of reading and writing data in the memory 1002 and the storage 1003.

[0793] Processor 1001 controls the entire computer by, for example, operating an operating system. Processor 1001 may also be comprised of a central processing unit (CPU) including interfaces with peripheral devices, a control device, a computing device, registers, and the like. For example, at least a portion of the aforementioned control unit 110 (210) and transceiver unit 120 (220) may also be implemented by processor 1001.

[0794] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes based on them. As a program, a program that causes a computer to execute at least a portion of the operations described in the above-described embodiments can be used. For example, the control unit 110 (210) can also be implemented by a control program stored in the memory 1002 and executed by the processor 1001, and the other functional blocks can also be implemented similarly.

[0795] Memory 1002 may also be a computer-readable recording medium, such as at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), or other suitable storage medium. Memory 1002 may also be referred to as a register, a cache, a main memory (main storage device), or the like. Memory 1002 can store executable programs (program code), software modules, and the like for implementing the wireless communication method according to an embodiment of the present disclosure.

[0796] Storage 1003 may also be a computer-readable recording medium, such as at least one of a flexible disk, a floppy disk, an optical disk (such as a compact disk (Compact Disc Read-Only Memory (CD-ROM)), a digital versatile disk, a Blu-ray disk), a removable disk, a hard disk drive, a smart card, a flash memory device (such as a card, a stick, or a key drive), a magnetic stripe, a database, a server, or other suitable storage medium. Storage 1003 may also be referred to as an auxiliary storage device.

[0797] The communication device 1004 is hardware (a transmitting and receiving device) for communicating between computers via at least one of a wired network and a wireless network. For example, it is also referred to as a network device, a network controller, a network card, a communication module, etc. In order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD), the communication device 1004 may also be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. For example, the aforementioned transmitting and receiving unit 120 (220) and the transmitting and receiving antenna 130 (230) may also be implemented by the communication device 1004. The transmitting and receiving unit 120 (220) may also be physically or logically separated by a transmitting unit 120a (220a) and a receiving unit 120b (220b).

[0798] The input device 1005 is an input device that receives input from the outside (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to the outside (e.g., a display, speaker, light-emitting diode (LED) lamp, etc.). Alternatively, the input device 1005 and output device 1006 may be integrated (e.g., a touch panel).

[0799] Furthermore, the processor 1001, memory 1002, and other devices are connected via a bus 1007 for communicating information. The bus 1007 may be configured as a single bus or may be configured as different buses between the devices.

[0800] Furthermore, the base station 10 and user terminal 20 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and may use this hardware to implement part or all of each functional block. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0801] (Variation)

[0802] In addition, the terms described in this disclosure and the terms required for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, channel, symbol, and signal (signal or signaling) may be replaced with each other. In addition, a signal may also be a message. A reference signal may also be referred to as RS, or as a pilot, pilot signal, etc. depending on the applied standard. In addition, a component carrier (CC) may also be referred to as a cell, frequency carrier, carrier frequency, etc.

[0803] A radio frame can also be composed of one or more time periods (frames) in the time domain. Each of these one or more time periods (frames) that make up a radio frame can also be called a subframe. Furthermore, a subframe can also be composed of one or more time slots in the time domain. A subframe can also be a fixed time length (for example, 1ms) that is independent of the numerology.

[0804] Here, a parameter set may also refer to communication parameters applied to at least one of the transmission and reception of a signal or channel. For example, the parameter set may also represent at least one of subcarrier spacing (SCS), bandwidth, symbol length, cyclic prefix length, transmission time interval (TTI), the number of symbols per TTI, radio frame structure, specific filtering processing performed by the transmitter and receiver in the frequency domain, and specific windowing processing performed by the transmitter and receiver in the time domain.

[0805] In the time domain, a slot can also be composed of one or more symbols (Orthogonal Frequency Division Multiplexing (OFDM) symbols, Single Carrier Frequency Division Multiple Access (SC-FDMA) symbols, etc.) Furthermore, a slot can also be a time unit based on a parameter set.

[0806] A time slot may also contain multiple mini-slots. Each mini-slot may also consist of one or more symbols in the time domain. Furthermore, a mini-slot may also be referred to as a sub-slot. A mini-slot may also consist of fewer symbols than a time slot. A PDSCH (or PUSCH) transmitted in a time unit larger than a mini-slot may also be referred to as PDSCH (PUSCH) mapping type A. A PDSCH (or PUSCH) transmitted using mini-slots may also be referred to as PDSCH (PUSCH) mapping type B.

[0807] Radio frames, subframes, time slots, mini-slots, and symbols all represent time units used for signal transmission. Radio frames, subframes, time slots, mini-slots, and symbols may also be referred to by their respective equivalents. Furthermore, the time units of frame, subframe, time slot, mini-slot, and symbol in this disclosure may be interchangeable.

[0808] For example, a subframe can be called a TTI, multiple consecutive subframes can be called a TTI, and a slot or a mini-slot can be called a TTI. That is, at least one of a subframe and a TTI can be a subframe (1 ms) in existing LTE, a period shorter than 1 ms (for example, 1-13 symbols), or a period longer than 1 ms. Furthermore, the unit representing a TTI can be called a slot, a mini-slot, or the like, rather than a subframe.

[0809] Here, TTI refers to, for example, the minimum time unit used for scheduling in wireless communications. For example, in the LTE system, a base station schedules each user terminal by allocating radio resources (such as the frequency bandwidth and transmit power available to each user terminal) in TTI units. The definition of TTI is not limited to this.

[0810] A TTI can also be a unit of time for transmitting channel-coded data packets (transport blocks), code blocks, code words, etc., and can also be a unit of processing for scheduling, link adaptation, etc. Furthermore, when a TTI is given, the time interval (e.g., the number of symbols) to which a transport block, code block, code word, etc. is actually mapped can be shorter than the TTI.

[0811] Furthermore, while a time slot or mini-slot is referred to as a TTI, one or more TTIs (i.e., one or more time slots or one or more mini-slots) can also be the minimum time unit for scheduling. Furthermore, the number of time slots (mini-slots) that constitute this minimum time unit for scheduling can also be controlled.

[0812] A TTI with a time length of 1 ms may also be referred to as a normal TTI (TTI in 3GPP Rel. 8-12), a standard TTI, a long TTI, a normal subframe, a standard subframe, a long subframe, a time slot, etc. A TTI shorter than a normal TTI may also be referred to as a shortened TTI, a short TTI, a partial TTI (partial or fractional TTI), a shortened subframe, a short subframe, a minislot, a subslot, a time slot, etc.

[0813] In addition, a long TTI (e.g., normal TTI, subframe, etc.) can also be rewritten as a TTI with a time length exceeding 1ms, and a short TTI (e.g., shortened TTI, etc.) can also be rewritten as a TTI with a TTI length shorter than the long TTI and longer than 1ms.

[0814] A resource block (RB) is a unit of resource allocation in the time and frequency domains. In the frequency domain, it may also include one or more consecutive subcarriers (subcarriers). The number of subcarriers contained in an RB can be the same regardless of the parameter set, for example, it can be 12. The number of subcarriers contained in an RB can also be determined based on the parameter set.

[0815] In addition, an RB may also include one or more symbols in the time domain, and may also be the length of a slot, a mini-slot, a subframe, or a TTI. A TTI, a subframe, etc. may also be composed of one or more resource blocks.

[0816] In addition, one or more RBs may also be referred to as a physical resource block (Physical RB (PRB)), a sub-carrier group (SCG), a resource element group (REG), a PRB pair, an RB pair, etc.

[0817] Furthermore, a resource block may be composed of one or more resource elements (REs). For example, one RE may be a radio resource region of one subcarrier and one symbol.

[0818] A Bandwidth Part (BWP) (also known as a fractional bandwidth) can also represent a subset of contiguous common resource blocks (RBs) used for a particular parameter set within a carrier. Common RBs can also be identified by their index relative to the common reference point for that carrier. PRBs can also be defined within a BWP and numbered within that BWP.

[0819] The BWP may include a UL BWP (BWP for UL) and a DL BWP (BWP for DL). For a UE, one or more BWPs may be configured within one carrier.

[0820] At least one of the configured BWPs may be activated, and the UE may not assume that it will transmit or receive specific signals / channels other than the activated BWP.

[0821] The above-mentioned structures of radio frames, subframes, slots, mini-slots, and symbols are merely examples. For example, the number of subframes in a radio frame, the number of slots per subframe or radio frame, the number of mini-slots within a slot, the number of symbols and RBs within a slot or mini-slot, the number of subcarriers within an RB, the number of symbols within a TTI, the symbol length, and the cyclic prefix (CP) length can be modified in various ways.

[0822] Furthermore, the information and parameters described in this disclosure may be expressed as absolute values, relative values ​​relative to a specific value, or other corresponding information. For example, wireless resources may be indicated by specific indexes.

[0823] The names used for parameters, etc. in this disclosure are not intended to be limiting in any respect. Furthermore, the mathematical formulas used for these parameters may differ from those explicitly disclosed in this disclosure. Various channels (PUCCH, PDCCH, etc.) and information elements can be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any respect.

[0824] Information, signals, and the like described in this disclosure may also be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, and the like that may be referred to throughout the foregoing description may also be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or photons, or any combination thereof.

[0825] Furthermore, information, signals, etc. can be output in at least one of the following directions: from a higher layer (upper layer) to a lower layer (lower layer), and from a lower layer to a higher layer. Information, signals, etc. can also be input and output via multiple network nodes.

[0826] Input and output information, signals, etc. can be stored in a specific location (e.g., memory) or managed using a management table. Input and output information, signals, etc. can be overwritten, updated, or appended. Output information, signals, etc. can also be deleted. Input information, signals, etc. can also be sent to other devices.

[0827] The notification of information is not limited to the methods / implementations described in this disclosure and may also be performed using other methods. For example, the notification of information in this disclosure may also be implemented through physical layer signaling (e.g., downlink control information (Downlink Control Information (DCI)), uplink control information (Uplink Control Information (UCI))), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, broadcast information (Master Information Block (MIB)), System Information Block (SIB), etc.), Medium Access Control (MAC) signaling), other signals, or a combination thereof.

[0828] Physical layer signaling may also be referred to as Layer 1 / Layer 2 (L1 / L2) control information (L1 / L2 control signal), Layer 1 control information (L1 control signal), etc. Furthermore, RRC signaling may also be referred to as an RRC message, such as an RRC Connection Setup message or an RRC Connection Reconfiguration message. Furthermore, MAC signaling may also be notified using, for example, a MAC Control Element (CE).

[0829] Furthermore, notification of specific information (eg, notification of “it is X”) is not limited to explicit notification, but may be performed implicitly (eg, by not notifying the specific information or by notifying other information).

[0830] The determination can be made using a value represented by a bit (0 or 1), a true or false value represented by true (true) or false (false) (Boolean value), or by comparing numerical values ​​(for example, comparing with a specific value).

[0831] The term “software” or “firmware” shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, sub-programs, software modules, applications, software applications, software packages, routines, sub-routines, objects, executable files, execution threads, procedures, functions, etc.

[0832] Furthermore, software, instructions, information, and the like may also be transmitted and received via a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using at least one of a wired technology (coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), etc.) and a wireless technology (infrared, microwave, etc.), at least one of the wired technology and the wireless technology is included within the definition of a transmission medium.

[0833] The terms "system" and "network" used in this disclosure are interchangeable. "Network" may also refer to devices included in the network (eg, base stations).

[0834] In the present disclosure, terms such as "precoding", "precoder", "weight (precoding weight)", "Quasi-Co-Location (QCL))", "Transmission Configuration Indication state (TCI state)", "spatial relation", "spatial domain filter", "transmit power", "phase rotation", "antenna port", "layer", "number of layers", "rank", "resource", "resource set", "beam", "beam width", "beam angle", "antenna", "antenna element", "panel", "UE panel", "transmitting entity", and "receiving entity" can be used interchangeably.

[0835] Furthermore, in the present disclosure, antenna ports can be interchanged with antenna ports used for any signal / channel (e.g., Demodulation Reference Signal (DMRS) ports). In the present disclosure, resources can be interchanged with resources used for any signal / channel (e.g., reference signal resources, SRS resources, etc.). Furthermore, resources can include time / frequency / code / space / power resources. Furthermore, spatial domain transmit filters can include at least one of spatial domain transmission filters and spatial domain reception filters.

[0836] The above-mentioned group may also include, for example, at least one of a spatial relationship group, a code division multiplexing (CDM) group, a reference signal (RS) group, a control resource set (CORESET) group, a PUCCH group, an antenna port group (for example, a DMRS port group), a layer group, a resource group, a beam group, an antenna group, a panel group, etc.

[0837] In addition, in the present disclosure, beam, SRS Resource Indicator (SRI), CORESET, CORESET pool, PDSCH, PUSCH, codeword (CW), transport block (TB), RS, etc. can also be rewritten.

[0838] In addition, in the present disclosure, TCI state, downlink TCI state (DL TCI state), uplink TCI state (UL TCI state), unified TCI state (unified TCI state), common TCI state (common TCI state), joint TCI state, etc. can also be rewritten with each other.

[0839] In addition, in the present disclosure, "QCL", "QCL concept", "QCL relationship", "QCL type information", "QCL characteristics (QCLproperty / properties)", "specific QCL type (e.g., type A, type D) characteristics", "specific QCL type (e.g., type A, type D)", etc. can also be rewritten with each other.

[0840] In the present disclosure, index, identifier (ID), indicator, indication, resource ID, etc. may also be replaced by each other. In the present disclosure, sequence, list, set, group, group, cluster, subset, etc. may also be replaced by each other.

[0841] Furthermore, the spatial relationship information identifier (ID) (TCI state ID) and spatial relationship information (TCI state) can also be overwritten. "Spatial relationship information (TCI state)" can also be overwritten with "a set of spatial relationship information (TCI state)," "one or more spatial relationship information," and so on. TCI states and TCIs can also be overwritten. Spatial relationship information and spatial relationships can also be overwritten.

[0842] In this disclosure, terms such as "base station (BS)", "wireless base station", "fixed station", "NodeB", "eNB (eNodeB)", "gNB (gNodeB)", "access point", "transmission point (TP)", "reception point (RP)", "transmission / reception point (TRP))", "panel", "cell", "sector", "cell group", "carrier", and "component carrier" are used interchangeably. In some cases, a base station may be referred to as a macrocell, small cell, femtocell, or picocell.

[0843] A base station can accommodate one or more (for example, three) cells. When a base station accommodates multiple cells, the base station's overall coverage area can be divided into multiple smaller areas, each of which can be provided with communications services by a base station subsystem (for example, a small indoor base station (Remote Radio Head (RRH))). Terms such as "cell" or "sector" refer to a portion or the entire coverage area of ​​at least one of a base station and a base station subsystem providing communications services within that coverage area.

[0844] In the present disclosure, the base station sends information to the terminal, and this situation can also be rewritten as the base station instructing the terminal to control / operate based on the information.

[0845] In the present disclosure, terms such as “mobile station (MS)”, “user terminal”, “user device (UE)”, and “terminal” can be used interchangeably.

[0846] A mobile station may also be referred to as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, hand set, user agent, mobile client, client, or several other appropriate terms.

[0847] At least one of the base station and the mobile station may also be referred to as a transmitting device, a receiving device, a wireless communication device, etc. In addition, at least one of the base station and the mobile station may also be a device mounted on a moving object, a moving object body, etc.

[0848] The mobile body refers to a movable object, and the moving speed is arbitrary, including the case where the mobile body is stopped. The mobile body includes, for example, vehicles, transport vehicles, cars, automatic two-wheeled vehicles (motorcycles), bicycles, connected cars, loading shovels, bulldozers, wheel loaders, dump trucks, forklifts, trains, buses, trolleys, rickshaws, ships (ships and other watercraft), airplanes, rockets, artificial satellites, drones, multicopters, quadcopters, hot air balloons, and objects carried on them, but is not limited to these. In addition, the mobile body can also be a mobile body that moves autonomously based on operating instructions.

[0849] The mobile object may be a vehicle (e.g., a car, an aircraft, etc.), an unmanned mobile object (e.g., a drone, an autonomous vehicle, etc.), or a robot (manned or unmanned). Furthermore, at least one of the base station and the mobile station may include a device that does not necessarily move during communication operations. For example, at least one of the base station and the mobile station may be an Internet of Things (IoT) device such as a sensor.

[0850] Figure 15 This diagram shows an example of a vehicle according to one embodiment. Vehicle 40 includes a drive unit 41, a steering unit 42, an accelerator pedal 43, a brake pedal 44, a shift lever 45, left and right front wheels 46, left and right rear wheels 47, an axle 48, an electronic control unit 49, various sensors (including a current sensor 50, a rotation speed sensor 51, an air pressure sensor 52, a vehicle speed sensor 53, an acceleration sensor 54, an accelerator pedal sensor 55, a brake pedal sensor 56, a shift lever sensor 57, and an object detection sensor 58), an information service unit 59, and a communication module 60.

[0851] The drive unit 41 is composed of, for example, at least one of an engine, a motor, or a combination of an engine and a motor. The steering unit 42 is configured to include at least a steering wheel (also referred to as a handle), and steers at least one of the front wheels 46 and the rear wheels 47 based on the user's operation of the steering wheel.

[0852] The electronic control unit 49 is composed of a microprocessor 61, memory (ROM, RAM) 62, and communication ports (e.g., input / output (IO) ports) 63. Signals from various sensors 50-58 included in the vehicle are input to the electronic control unit 49. The electronic control unit 49 may also be referred to as an electronic control unit (ECU).

[0853] As signals from various sensors 50-58, there are current signals from the current sensor 50 that senses the current of the motor, speed signals of the front wheels 46 / rear wheels 47 obtained by the speed sensor 51, air pressure signals of the front wheels 46 / rear wheels 47 obtained by the air pressure sensor 52, vehicle speed signals obtained by the vehicle speed sensor 53, acceleration signals obtained by the acceleration sensor 54, depression amount signals of the accelerator pedal 43 obtained by the accelerator pedal sensor 55, depression amount signals of the brake pedal 44 obtained by the brake pedal sensor 56, operation signals of the shift lever 45 obtained by the shift lever sensor 57, detection signals for detecting obstacles, vehicles, pedestrians, etc. obtained by the object detection sensor 58, etc.

[0854] Information service unit 59 is comprised of various devices, such as a navigation system, audio system, speakers, display, television, and radio, that provide (output) various types of information, including driving information, traffic information, and entertainment information, and one or more ECUs that control these devices. Information service unit 59 uses information acquired from external devices via communication module 60 and the like to provide various information and services (e.g., multimedia information and multimedia services) to vehicle 40 occupants.

[0855] The information service unit 59 may include an input device for accepting input from the outside (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, a touch panel, etc.), or an output device for outputting to the outside (e.g., a display, a speaker, an LED light, a touch panel, etc.).

[0856] The driving assistance system unit 64 is composed of various devices that provide functions for preventing accidents or reducing the driver's driving burden, such as millimeter-wave radar, light detection and ranging (LiDAR), cameras, positioners (e.g., Global Navigation Satellite System (GNSS)), map information (e.g., High Definition (HD) maps, Autonomous Vehicle (AV) maps), gyroscope systems (e.g., inertial measurement units (IMUs)), inertial navigation systems (INS), artificial intelligence (AI) chips, and AI processors, as well as one or more ECUs that control these devices. Furthermore, the driving assistance system unit 64 transmits and receives various information via the communication module 60 to implement driving assistance functions or autonomous driving functions.

[0857] The communication module 60 can communicate with the microprocessor 61 and components of the vehicle 40 via the communication port 63. For example, the communication module 60 transmits and receives data (information) via the communication port 63 with the drive unit 41, steering unit 42, accelerator pedal 43, brake pedal 44, shift lever 45, left and right front wheels 46, left and right rear wheels 47, axle 48, the microprocessor 61 in the electronic control unit 49, the memory (ROM, RAM) 62, and various sensors 50-58 included in the vehicle 40.

[0858] The communication module 60 is controlled by the microprocessor 61 of the electronic control unit 49 and is a communication device capable of communicating with external devices. For example, various information can be transmitted and received with the external device via wireless communication. The communication module 60 can be located either inside or outside the electronic control unit 49. Examples of external devices include the aforementioned base station 10 and user terminal 20. Furthermore, the communication module 60 can also be, for example, at least one of the aforementioned base station 10 and user terminal 20 (or function as at least one of the base station 10 and user terminal 20).

[0859] The communication module 60 may also transmit at least one of the following to an external device via wireless communication: signals input to the electronic control unit 49 from the various sensors 50-58, information obtained based on these signals, and information based on external (user) input received via the information service unit 59. The electronic control unit 49, the various sensors 50-58, the information service unit 59, etc. may also be referred to as input units that receive input. For example, the PUSCH transmitted via the communication module 60 may also include information based on these inputs.

[0860] The communication module 60 receives various information (such as traffic information, traffic light information, and vehicle information) transmitted from external devices and displays it on the vehicle's information service unit 59. The information service unit 59 can also be referred to as an output unit that outputs information (for example, information output to a display, speaker, or other device based on the PDSCH received by the communication module 60 (or data / information decoded from the PDSCH)).

[0861] Furthermore, the communication module 60 stores various information received from external devices in a memory 62 that can be used by the microprocessor 61. Based on the information stored in the memory 62, the microprocessor 61 can also control the drive unit 41, steering unit 42, accelerator pedal 43, brake pedal 44, shift lever 45, left and right front wheels 46, left and right rear wheels 47, axles 48, various sensors 50-58, and the like included in the vehicle 40.

[0862] Furthermore, the base station in this disclosure can also be rewritten as a user terminal. For example, the various methods / implementations of this disclosure can also be applied to a structure in which communication between a base station and a user terminal is replaced by communication between multiple user terminals (e.g., device-to-device (D2D) or vehicle-to-everything (V2X)). In this case, the user terminal 20 can also have the functions of the base station 10 described above. Furthermore, terms such as "uplink" and "downlink" can also be rewritten with terms corresponding to inter-terminal communication (e.g., "sidelink"). For example, uplink channels, downlink channels, etc. can also be rewritten as sidelink channels.

[0863] Likewise, the user terminal in the present disclosure may be rewritten as a base station. In this case, the base station 10 may have the functions of the user terminal 20 described above.

[0864] In this disclosure, actions performed by a base station may also be performed by its upper node depending on the situation. Obviously, in a network including one or more network nodes including a base station, various operations performed for communication with a terminal may be performed by the base station, one or more network nodes other than the base station (for example, but not limited to, a Mobility Management Entity (MME) and a Serving-Gateway (S-GW)), or a combination thereof.

[0865] The various methods / implementations described in this disclosure may be used individually or in combination, and may be switched between them during execution. Furthermore, the processing procedures, timings, flow charts, and the like of the various methods / implementations described in this disclosure may be reversed as long as they do not conflict. For example, the methods described in this disclosure use an illustrative order to present elements of various steps, but are not limited to the specific order presented.

[0866] The various modes and embodiments described in the present disclosure may also be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 6th generation mobile communication system (6G), xth generation mobile communication system (xG (x is, for example, an integer or a decimal)), Future Radio Access (FRA), New Radio Access Technology (RAT), New Radio (NR), New Radio Access (NX), Future Generation Radio Access (FX), Global System for Mobile Communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), systems utilizing other appropriate wireless communication methods, and next-generation systems based on these that are extended, modified, generated, or specified. Furthermore, multiple systems may be combined for application (for example, LTE or LTE-A combined with 5G).

[0867] The phrase “based on” used in this disclosure does not mean “based only on” unless otherwise specified. In other words, the phrase “based on” means both “based only on” and “based at least on.”

[0868] Any reference to an element using the designations "first," "second," etc., as used in this disclosure, does not necessarily define the quantity or order of these elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Therefore, reference to a first and a second element does not imply that only two elements may be used or that the first element must in some way take precedence over the second element.

[0869] The term "determining" as used in this disclosure may encompass a wide variety of actions. For example, "determining" may also encompass situations where judging, calculating, computing, processing, deriving, investigating, looking up (e.g., searching a table, database, or other data structure), ascertaining, and the like are considered "determining."

[0870] In addition, “judgment (decision)” may also refer to situations where receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in a memory), etc. are regarded as “judgment (decision)”.

[0871] Furthermore, "judgment (decision)" can also refer to situations where resolving, selecting, choosing, establishing, comparing, and the like are considered "judgment (decision)." In other words, "judgment (decision)" can also refer to situations where certain actions are considered "judgment (decision)." In this disclosure, "judgment (decision)" can be interchanged with the aforementioned actions.

[0872] Furthermore, in this disclosure, "determine / determining" can be rephrased as "assume / assuming," "expect / expecting," "consider / considering," etc. Furthermore, in this disclosure, "do not assume..." can be rephrased as "do not assume...".

[0873] In this disclosure, "expect" and "be expected" can be interchanged. For example, "expect(s)..." ("..." can also be expressed as a that-clause, a to-infinitive, etc.) and "be expected..." can be interchanged. "Does not expect..." and "Does not expect..." can be interchanged. Furthermore, "An apparatus A is not expected..." and "An apparatus B other than apparatus A does not expect..." can be interchanged (for example, if apparatus A is a UE, apparatus B can also be a base station).

[0874] The “maximum transmit power” described in the present disclosure may refer to the maximum value of the transmit power, the nominal UE maximum transmit power, or the rated UE maximum transmit power.

[0875] As used in this disclosure, the terms "connected," "coupled," or all variations thereof, refer to any direct or indirect connection or coupling between two or more elements, including the presence of one or more intermediate elements between the two elements being "connected" or "coupled." The coupling or connection between elements can be physical, logical, or a combination thereof. For example, "connected" can also be rephrased as "accessed."

[0876] In the present disclosure, when two elements are connected, it is possible to consider being "connected" or "combined" to each other using one or more wires, cables, printed electrical connections, etc., as well as using electromagnetic energy with wavelengths in the wireless frequency domain, microwave region, light (both visible and invisible) region, etc. as several non-limiting and non-inclusive examples to be "connected" or "combined" to each other.

[0877] In the present disclosure, the term "A is different from B" may also mean "A and B are different from each other." Alternatively, the term may also mean "A and B are each different from C." Terms such as "separate" and "bound" may also be interpreted in the same manner as "different."

[0878] When used in this disclosure, "include," "including," and variations thereof have the same inclusive meaning as the term "comprising." Furthermore, the term "or" used in this disclosure does not mean an exclusive OR.

[0879] In the present disclosure, when an article is added by translation, such as a, an, and the in English, the present disclosure may also include a case where the noun following the article is in a plural form.

[0880] In the present disclosure, "below," "less than," "above," "more than," "equal to," and the like may be replaced with one another. Furthermore, in the present disclosure, expressions meaning "good," "bad," "big," "small," "high," "low," "early," "late," "wide," and "narrow," etc., are not limited to the positive, comparative, and superlative forms, but may be replaced with one another. Furthermore, in the present disclosure, expressions meaning "good," "bad," "big," "small," "high," "low," "early," "late," "wide," and "narrow," etc., with "i" (where i is an arbitrary integer) are not limited to the positive, comparative, and superlative forms, but may be replaced with one another (for example, "highest" and "i-th highest" may be replaced with one another).

[0881] In the present disclosure, “of,” “for,” “regarding,” “related to,” “associated with,” etc. may also be replaced with each other.

[0882] In this disclosure, expressions 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 / on A," "B after A," "B since A," and "B until A" can be interchanged. Furthermore, A, B, and the like herein can be interchanged with nouns, verbs, or other expressions appropriate to the context. Furthermore, the time difference between A and B can be substantially zero (immediately after or immediately before). Furthermore, a time offset can be applied to the time at which A occurs. For example, "A" can be interchanged with "before / after the time offset at which A occurs." This time offset (for example, one or more symbols / time slots) may be predetermined or determined by the UE based on notified information.

[0883] In the present disclosure, timing, moment, time, time instance, arbitrary time unit (eg, time slot, sub-time slot, symbol, sub-frame), period, occasion, resource, etc. may also be interchangeable.

[0884] While the inventions disclosed herein have been described in detail above, it will be apparent to those skilled in the art that the inventions disclosed herein are not limited to the embodiments described herein. The disclosure herein is presented for illustrative purposes only and is not intended to limit the inventions disclosed herein.

Claims

1. A terminal comprising: a receiving unit for receiving information for determining application of an AI model for positioning based on artificial intelligence (AI); and A control unit determines the application of the AI ​​model based on the information.

2. The terminal according to claim 1, wherein: The information includes at least one of information related to a location of the terminal, a model ID, a model function, and a validity of the model.

3. The terminal according to claim 1, wherein: After determining the applied AI model, the control unit controls reporting of information related to the output of model inference.

4. The terminal according to claim 1, further comprising: a sending unit for sending information related to the determination of the application of the AI ​​model, The information related to the determination of application of the AI ​​model includes at least one of information related to a location of the terminal, a measured intermediate value, and a specific ID of the AI ​​model.

5. A wireless communication method, which is a wireless communication method of a terminal, comprising: Regarding positioning based on artificial intelligence (AI), the step of receiving information for determining application of an AI model; and The step of determining the application of the AI ​​model based on the information.

6. A base station comprising: a receiving unit for receiving information for determining application of an AI model for positioning based on artificial intelligence (AI); and A control unit determines the application of the AI ​​model based on the information.

Images