Terminal, wireless communication method, and base station

Abstract

A terminal according to an embodiment of the present disclosure includes a reception unit that receives setting information for data collection in positioning based on artificial intelligence (AI), and a control unit that controls at least one of execution of at least one of inference, learning, and training of a model, and reporting related to the at least one of inference, learning, and training, based on a parameter indicating a use or a state of a model process included in the setting information. According to an embodiment of the present disclosure, appropriate overhead reduction / channel estimation / resource utilization can be achieved.

Description

Technical Field

[0001] This disclosure relates to terminals, wireless communication methods, and base stations in next-generation mobile communication systems. Background Technology

[0002] In Universal Mobile Telecommunications System (UMTS) networks, Long Term Evolution (LTE) was standardized with the aim of achieving higher data rates and lower latency (Non-Patent Document 1). Furthermore, LTE-Advanced (3GPP Rel. 10-14) was standardized with the aim of further increasing capacity and improving upon LTE (Third Generation Partnership Project (3GPP) Release (Rel.) 8, 9).

[0003] The development of successor systems to LTE is also underway (e.g., also known as the 5th generation mobile communication system (5G), 5G+, the 6th generation mobile communication system (6G), New Radio (NR), 3GPP Rel.15 and later, etc.).

[0004] Existing technical documents

[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] The problem that the invention aims to solve

[0008] Regarding future wireless communication technologies, research is underway on the flexible application of artificial intelligence (AI) technologies such as machine learning (ML) for the control and management of networks / devices.

[0009] As a use case for the flexible application of AI models, research is underway on spatial domain downlink (DL) beam prediction, temporal DL beam prediction, and localization. Such beam prediction methods can also be referred to as AI-based beam prediction (beam reporting), AI-based localization, and AI-based beam management (BM). Temporal DL beam prediction can also be referred to as temporal channel state information (CSI) prediction.

[0010] In such flexible applications of AI, there are instances of insufficient research. This lack of research hinders appropriate overhead reduction, channel estimation, and resource utilization, raising concerns that improvements in communication throughput and quality may be suppressed.

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

[0012] Methods for solving problems

[0013] One aspect of this disclosure relates to a terminal comprising: a receiving unit for receiving setting information for data collection in location based on artificial intelligence (AI); and a control unit for controlling the execution of at least one of the following: inference, learning, and training of a model, and at least one of a report related to at least one of the inference, learning, and training, based on parameters indicating the purpose or the state of a model process contained in the setting information.

[0014] Invention Effects

[0015] According to one method of this disclosure, appropriate overhead reduction / channel estimation / resource utilization can be achieved. Attached Figure Description

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

[0017] Figure 2 This is a diagram illustrating a specific example of an AI model.

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

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

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

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

[0022] Figure 7 This is a diagram illustrating an example of information forwarded from the UE to the LMF during GNSS / A-GNSS positioning.

[0023] Figure 8 This is a diagram illustrating an example of information forwarded from the UE to the LMF during barometric pressure sensor positioning.

[0024] Figure 9 This is a diagram illustrating an example of forwarding information from the UE to the LMF during TBS positioning.

[0025] Figure 10 This is a diagram illustrating an example of information forwarded from the UE to the LMF during motion sensor positioning.

[0026] Figure 11 This is a diagram illustrating an example of information forwarded from the UE to the LMF during WLAN positioning.

[0027] Figure 12 This is a diagram illustrating an example of information forwarded from the UE to the LMF during Bluetooth (registered trademark) positioning.

[0028] Figure 13 This is a diagram illustrating an example of a request related to location information in DL TDOA positioning.

[0029] Figure 14 This is a diagram illustrating other examples of requests related to location information in DL TDOA positioning.

[0030] Figure 15 This is a diagram illustrating an example of a response related to location information in DL TDOA positioning.

[0031] Figure 16 This is a diagram illustrating an example of the accuracy requirements for RSTD measurements.

[0032] Figure 17 This is a diagram illustrating an example of the setup for data collection according to the first embodiment.

[0033] Figure 18This is a diagram illustrating an example of the schematic structure of a wireless communication system according to one embodiment.

[0034] Figure 19 This is a diagram illustrating an example of the structure of a base station according to one embodiment.

[0035] Figure 20 This is a diagram illustrating an example of the structure of a user terminal according to one embodiment.

[0036] Figure 21 This is a diagram illustrating an example of the hardware structure of a base station and a user terminal according to one embodiment.

[0037] Figure 22 This is a diagram illustrating an example of a vehicle according to one embodiment. Detailed Implementation

[0038] (Application of Artificial Intelligence (AI) Technology in Wireless Communication)

[0039] Regarding future wireless communication technologies, research is underway on the flexible application of AI technologies such as Machine Learning (ML) in the control and management of networks / devices.

[0040] For example, research is underway to improve Channel State Information (CSI) feedback (e.g., reduced overhead, improved accuracy, prediction), beam management (e.g., improved accuracy, prediction in the time / space domain), and location measurement (e.g., improved location estimation / prediction), and to flexibly apply AI technologies to terminals (terminals, user terminals, user equipment (UE)) / base stations (BS).

[0041] AI models can also output at least one of the following information based on the input: estimated value, predicted value, selected operation, classification, etc. UE / BS can also input channel state information, reference signal measurements, etc., into the AI ​​model and output high-precision channel state information / measurements / beam selection / location, future channel state information / wireless link quality, etc.

[0042] Additionally, in this disclosure, AI can also be rewritten as an object (also referred to as an object, subject, data, function, program, etc.) having at least one of the following characteristics: Estimates based on observed or collected information, Based on the selection of the observed or collected information Prediction based on observed or collected information.

[0043] In this disclosure, estimation, prediction, and inference can be rewritten interchangeably. Furthermore, in this disclosure, making an estimate, making a prediction, and inferring can also be rewritten interchangeably.

[0044] In this disclosure, the object may be, for example, a device or equipment such as a UE or BS. Furthermore, in this disclosure, the object may also be equivalent to a program / model / entity operating within that device.

[0045] Furthermore, in this disclosure, the AI ​​model can also be rewritten as an object having at least one of the following characteristics: By providing information (feeding), estimates are generated. By providing information, we can predict and estimate values. By providing information, we can discover characteristics. By providing information, you can choose an action.

[0046] Furthermore, in this disclosure, AI model can also refer to a data-driven algorithm that applies AI technology and generates a set of outputs based on a set of inputs.

[0047] Furthermore, in this disclosure, AI models, models, ML models, predictive analytics, predictive analytics models, tools, autoencoders, encoders, decoders, neural network models, AI algorithms, schemes, etc., can be rewritten interchangeably. Additionally, AI models can 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, deep learning, etc.

[0048] In this disclosure, the autoencoder can also be rewritten with any autoencoder such as a stacked autoencoder or a convolutional autoencoder. The encoder / decoder of this disclosure can also adopt models such as residual networks (ResNet), dense networks (DenseNet), and multi-path reinforcement networks (RefineNet).

[0049] Furthermore, in this disclosure, encoder, encoding, encoding / encoded, encoder-based modification / change / control, compression, compression / compressed, generating, and generating / generated can also be rewritten in different ways.

[0050] Furthermore, in this disclosure, decoder, decoding, decoding / being decoded, modification / change / control based on decoder, decompressing, decompressing / being decompressed, reconstructing, reconstructing / being reconstructed, etc., can also be rewritten in relation to each other.

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

[0052] In this disclosure, the training methods for AI models can also include supervised learning, unsupervised learning, reinforcement learning, federated learning, etc. Supervised learning can also refer to training the model's processing based on inputs and corresponding labels. Unsupervised learning can also refer to training the model's processing without labeled data. Reinforcement learning can also refer to training the model's processing based on feedback signals (in other words, rewards) generated from the model's output (in other words, actions) in an interactive environment.

[0053] In this disclosure, the terms "generation," "computation," and "derivation" can be rewritten interchangeably. In this disclosure, the terms "implementation," "running," "operation," and "execution" can also be rewritten interchangeably. In this disclosure, the terms "training," "learning," "updating," and "retraining" can also be rewritten interchangeably. In this disclosure, the terms "inference," "after-training," "formal utilization," and "actual utilization" can also be rewritten interchangeably. In this disclosure, "signal" can also be rewritten interchangeably with "signal / channel."

[0054] Figure 1 This is a diagram illustrating an example of a framework for managing an AI model. In this example, the stages associated with the AI ​​model are shown as blocks. This example is also described as AI model lifecycle management (LCM).

[0055] The data collection phase is equivalent to the phase of collecting data for the generation / updating of AI models. The data collection phase may also include data preparation (e.g., deciding which data to transmit for model training / inference), data transmission (e.g., transmitting data to entities performing model training / inference (e.g., UE, gNB), etc.).

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

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

[0058] In the model training phase, the model is trained based on the data transferred from the collection phase (training data). This phase may also include data preparation (e.g., implementation of data preprocessing, cleaning, formatting, transformation, etc.), model training / validation, model testing (e.g., confirming whether the trained model meets performance thresholds), model exchange (e.g., transfer of models for distributed learning), and model deployment / update (deploying / updating the model for the entity performing model inference), etc.

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

[0060] Furthermore, AI model validation can also refer to a training subprocess used to evaluate the quality of an AI model using a dataset different from the dataset used in model training. This subprocess helps to generalize the selection of model parameters beyond the dataset used in model training.

[0061] In addition, AI model testing can also refer to the training subprocess used to evaluate the performance of the final AI model using a different dataset than that used in model training / validation. Furthermore, testing can differ from validation in that it is not contingent upon subsequent model adjustments.

[0062] In the Model Inference phase, model inference is performed based on the data (inference data) transmitted from the collection phase. This phase may also include data preparation (e.g., implementation of data preprocessing, cleaning, formatting, transformation, etc.), model inference, model monitoring (e.g., monitoring the performance of model inference), model performance feedback (providing model performance feedback to the entities used for model training), and output (providing the model's output to the actors).

[0063] Additionally, AI model inference can also refer to the process of using a trained AI model to generate a set of outputs from a set of inputs.

[0064] Furthermore, a UE-side model can also refer to an AI model where the inference is implemented entirely within the UE. Similarly, a network-side model can refer to an AI model where the inference is implemented entirely within 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 an AI model that performs joint inference. Here, joint inference can also include AI inference performed jointly by the UE and the network; for example, the first part of the inference is performed by the UE, and the remaining part is 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 AI models, and can be interchanged with model performance monitoring, performance monitoring, etc.

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

[0068] The Actor phase can also include action triggering (e.g., deciding whether to trigger an action on other entities), feedback (e.g., providing feedback on training data / inference data / performance feedback, etc.).

[0069] Furthermore, training models for mobility optimization, for example, can also be performed within the Network (NW)'s Operation, Administration and Maintenance (OAM) / gNodeB (gNB). In the former case, there are advantages in interoperability, large-capacity storage, operator manageability, and model flexibility (feature engineering, etc.). In the latter case, there are advantages in terms of latency (no need for model updates) and data exchange for model deployment. Inference for the aforementioned models can also be performed within the gNB, for example.

[0070] The entities used for training / inference can also vary depending on the use case (in other words, the function of the AI ​​model). The functions of an AI model can also include beam management, beam prediction, autoencoders (or information compression), CSI feedback, position measurement, etc.

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

[0072] For AI-assisted UE-assisted positioning, the location management function (LMF) can be used to train the model, and the LMF can be used for model inference.

[0073] For CSI feedback / channel estimation using an autoencoder, it is also possible to perform model training on OAM / gNB / UE and model inference (jointly) on gNB / UE.

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

[0075] Additionally, model activation can also refer to activating an AI model used for a specific function. Model deactivation can also refer to deactivating an AI model used for a specific function. Model switching can also refer to deactivating the currently activated 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 may include distributing parameters of a known model structure, or a new model with parameters, to the receiving side, or both. Additionally, this distribution may include a complete model or a portion of the model. Model download can also refer to model migration from the network to the UE. Model upload can also refer to model migration from the UE to the network.

[0077] Figure 2 This diagram illustrates an example of an AI model specification. In this example, the UE and the NW (e.g., the base station (BS)) are able to identify models #1 and #2 (the details of the models may not be fully understood). The UE can, for example, report the performance of model #1 and model #2 to the NW, and the NW can also give instructions to the UE regarding the AI ​​model used.

[0078] (UE positioning using AI technology)

[0079] Fingerprinting localization, which uses the propagation characteristics of wireless signals to estimate the location of wireless devices, is widely used in both line-of-sight (LOS) and non-line-of-sight (NLOS) scenarios.

[0080] In this disclosure, LOS may also mean that the UE and the base station are in an environment where they are mutually visible (or without obstructions), and NLOS may also mean that the UE and the base station are not in an environment where they are mutually visible (or with obstructions).

[0081] In fingerprint localization, the location of the UE is estimated based on the fingerprints from multiple transmission paths (multipath) of the UE, using a database / AI model.

[0082] Multipath information can also include information related to the angle of arrival (AoA) and angle of departure (AoD) of signals in the optimal / candidate transmission paths.

[0083] Additionally, in this disclosure, information related to AoA may include, for example, information related to at least one of the azimuth angles of arrival and the zenith angles of arrival. Similarly, information related to AoD may include, for example, information related to at least one of the azimuth angles of depature and the zenith angles of departure.

[0084] In 3GPP Rel.16 NR, the following positioning techniques are supported.

[0085] Positioning based on DL / UL time difference of arrival (TDOA) Angle-based positioning (DL AoD / UL AoA) Based on Round Trip Time (RTT) positioning, Location based on Enhanced Cell ID (E-CID)

[0086] Figure 3This diagram illustrates an example of positioning based on DL / UL TDOA. For instance, consider a scenario where multiple base stations (TRP#0-#2) are configured around the UE. In this positioning method, the UE's location is estimated (measured) using the measurement of the reference signal time difference (RSTD). For example, the RSTD (T...) for two specific base stations (TRP#i, #j (i, j are integers)) is... i -T j Take a certain value (k) i，j Connect the points to draw the hyperbola H. i，j The intersection point of multiple such hyperbolas (H in this example). 0，1、 H 1，2、 H 2，0 The intersection of the reference signal and the reference signal (RSRP) can also be used to estimate the UE's location. Additionally, the RSRP of the reference signal can also be used to estimate the UE's location.

[0087] Figure 4 This diagram illustrates an example of positioning based on DL AoD / UL AoA. In this positioning method, measurements of DL AoD (e.g., θ or 0) are used. ), or UL AoA measurements (e.g., θ or Alternatively, RSRP can also be used to estimate the UE's location.

[0088] Figure 5 This diagram illustrates an example of multi-RTT-based positioning. In this positioning method, the UE's location is estimated using multiple RTTs calculated from the Tx / Rx time difference of a reference signal (and additionally RSRP, RSRQ, etc.). For example, geometric circles based on RTTs are drawn centered on each base station. The intersection of these multiple circles can also be estimated as the UE's location.

[0089] Figure 6 This diagram illustrates an example of E-CID-based positioning. In this positioning method, the UE's location is estimated based on the geometric location of the serving cell / neighbor cells and additional measurements (Tx-Rx time difference, RSRP, RSRQ, etc.).

[0090] The positioning measurements in the aforementioned DL (DL TDOA, DL AoD) can also be implemented on the UE side or the LMF side. For example, in UE-based positioning, the UE can calculate its position based on various measurement results from the UE and assistance information from the LMF. Furthermore, in UE-assisted positioning, the UE can report various measurement results to the LMF, and the LMF can calculate the UE's position. The assistance information can also be information used to assist the UE in position estimation.

[0091] The location measurements described above in UL (UL TDOA, UL AoA) can also be performed 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 location.

[0092] The location measurements mentioned above in DL and UL (Multi-RTT, E-CID) can also be performed on the LMF side. In this case, the UE / base station can also report various measurement results to the LMF, and the LMF can calculate the UE's location.

[0093] Furthermore, in 3GPP Rel.17, a positioning method using auxiliary information was proposed to further improve positioning accuracy. This auxiliary information can also be used as measurement information for the aforementioned DL / UL-TDOA, DL-AoD / UL-AoA, multiple RTTs, and E-CIDs, and transmitted between the UE, base station, and LMF.

[0094] The auxiliary information may also include information related to at least one of the following: Timing Error Group (TEG) RSRPP (Path-Specific RSRP) Expected angle Adjacent beam information. TRP antenna / beam information LOS / NLOS indicator Additional route report.

[0095] TEG can also represent one or more PRS (Positioning Reference Signal) resources where the transmit / receive timing errors (Rx / Tx) are within a certain margin.

[0096] RSRPP can also represent the measurement results of RSRP in the initial path.

[0097] In UL positioning, auxiliary information related to the expected angle can also represent the expected UL-AoA / ZoA. This auxiliary information can also be sent from the LMF to the base station. Furthermore, this auxiliary information can also support positioning for at least one of UL TDOA, UL AoA, and multiple RTTs.

[0098] In DL positioning, auxiliary information related to the expected angle can also include information related to the expected DL-AoA / ZoA or DL-AoD / ZoD. This auxiliary information can also be sent from the LMF to the UE. Furthermore, this auxiliary information can also support positioning for at least one of DL TDOA, DL AoA, and multiple RTTs. This improves the accuracy of angle-based UE positioning and enables optimization of Rx beamforming for the UE or base station.

[0099] In addition, the auxiliary information related to the expected angle may include not only the values ​​of AoA / ZoA / AoD / ZoD themselves, as mentioned above, but also information representing the uncertainty range of these values.

[0100] As additional beam information, adjacent beam information may also include a subset of DL-PRS resources for the purpose of prioritizing DL-AoD reports (Option 1), or information related to the boresight direction of each DL-PRS resource (Option 2). This enables optimization of UE Rx beam sweeping and DL-AoD measurements.

[0101] In addition, as supplementary beam information, auxiliary information may also include PRS beam pattern information. This PRS beam pattern information may also include information related to the relative power between DL-PRS resources at each angle of each TRP.

[0102] The LOS / NLOS indicator can also represent information related to line of sight (LOS) / non-line of sight (NLOS).

[0103] In addition, with the aim of improving the UE's position delay, preset measurement gaps (MG), activation of MG via lower layer, MG-less position, PRS Rx / Tx in RRC_INACTIVE state, or on-demand PRS can also be set for the UE (and can also be used by the UE).

[0104] In 3GPP Rel.17 NR, an agreement was reached on having the UE measure / report the RSRP of adjacent beams in order to improve the location estimation accuracy of the UE. For example, in the UE-assisted DL-AoD positioning method, the LMF can include at least one of the following options 1 to 2 in the auxiliary information.

[0105] Option 1: A subset of PRS resources for the purpose of prioritizing DL-AOD reports. This subset can also be configured for each PRS resource based on UE capabilities. When reporting requested PRS measurements for an associated PRS, the UE can also include requested PRS measurements for a subset of the PRS in the additional measurements of DL-AoD. The requested PRS measurement can also be a 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 within the same / different PRS resource set as that PRS resource.

[0106] Option 2: Information related to the line-of-sight direction set for each PRS resource, based on UE capabilities.

[0107] In 3GPP Rel.16 NR, an agreement was reached to indicate the expected RSTD and its uncertainty range to the UE from the LMF. Furthermore, in Rel.17, an agreement was reached to indicate the expected angle and its uncertainty range to the UE from the LMF in order to reduce the error and complexity in AoA / AoD measurement.

[0108] In 3GPP Rel.17 NR, the introduction of a Positioning Reference Unit (PRU) is being studied regarding positioning. The PRU is discussed as a reference device with a known location, designed to mitigate timing errors in the UE / gNB's transmission and reception. The PRU can also be rewritten as UE / gNB / TRP (transmission reception point) / TP (transmission point).

[0109] For example, PRU can also support at least one of the following: Measure DL PRS and report the associated measurements (e.g., RSTD / transmit / receive time difference / RSRP) to LMF. It can transmit SRS and report measurements (e.g., Relative Time of Arrival: RTOA / Transmit / Receive Time Difference, AOA) associated with the TRP measurement and reference equipment to the LMF. Operation, measurement, and various parameters (parameters associated with transmit / receive timing delays, AoD and AOA enhancements, and measurement corrections). When the LMF does not have position coordinate information, the position coordinate information of the reference device should be provided to the LMF report. The reference device with a known location is the UE / gNB. It is possible to determine the accuracy of the position of the reference device.

[0110] In localization using AI models, there are, for example, the following two use cases: Direct AI / ML localization AI / ML-assisted localization.

[0111] Based on direct AI / ML localization, such as outputting UE location (UE position). Based on AI / ML assisted localization, such as outputting intermediate features. These intermediate features can also be fed back into the AI / ML model.

[0112] As an example of the AI / ML-assisted localization output described above, it may also include at least one of the following: LOS / NLOS identification (probability of LOS / NLOS) ToA (Arrival Time of PRS / SRS). Rx-Tx (transmit / receive) time difference, AoA / AoD, Wave number, Rx-Tx (transmit / receive) phase difference (Rel.18 phase measurement). DL RSTD / UL TDOA, DL-PRS / UL-SRS, RSRPs / RSRPPs, The likelihood of the above values ​​(e.g., the probability of ToA).

[0113] (UE-based DL positioning)

[0114] This section explains the scenario where the UE performs positioning using an AI model on the UE side. The UE can also use the AI ​​model to infer UE positioning (UE location measurement, position). The UE can also report the inferred positioning results to the LMF.

[0115] Inference for the AI ​​model in the UE can also be performed based on the dataset possessed by the UE. The information input for the AI ​​model (input information) can also include raw data (feature-related information) / auxiliary information measured by the UE. The UE can also receive auxiliary information from the base station or LMF.

[0116] The raw measurement results (also referred to as the measured feature) measured by the UE may also include data (information) related to at least one of the following (in addition, the information listed in commas does not need to be included in all of them. This is also true below in this disclosure): UE DL-PRS-RSRP (or DL-PRS-RSSI / RSRQ) measurement results from multiple reference TRPs. DL-RSTD measurement results from multiple reference TRPs Referring to the Time of Arrival (ToA) measurement results of the TRP, Referring to the AoD measurement results of TRP, The quality of various measurements, Timestamp (moment) of the measurement results. The physical cell ID (PCI) and global cell ID (GCI) of each measurement include the absolute radio frequency channel number (ARFCN), PRS resource ID, PRS resource set ID, and PRS ID. UE Rx TEG ID, TRP Tx TEG ID, UE Tx TEG ID, UE RxTx TEGID, TRP Rx TEG ID, TRP RxTx TEG ID for DL ​​RSTD measurement, DL-PRS receiver beam index First path DL-PRS-RSRP measurement results Channel pulse response / channel frequency response, coded channel pulse response / coded channel frequency response Phase difference among different antennas within an antenna array The received multipath characteristics of the TRP are referenced (e.g., DL-PRS-RSRP measurements for each path), the amplitude / average / cumulative distribution function (CDF) of the multipath amplitude is estimated, path loss, root-mean-square (rms) delay spread, and kurtosis of the channel impulse response are estimated.

[0117] In addition, GCI can be rewritten with NR Cell Global Identity (NCGI).

[0118] The auxiliary information notified from the base station / LMF may also include information related to at least one of the following: The noise in the dataset (the expected variance of the noise, etc.) is the ground truth (the ground truth). The physical cell ID (PCI), global cell ID (GCI), ARFCN, and PRSID of the NR TRP candidate for the measurement object. NR TRP Candidates and Service (Reference) TRP Timing Relative. TRP's SSB information (SSB time / frequency occupancy rate). DL-PRS settings for candidate NR TRP The spatial orientation information (azimuth, elevation, etc.) of the DL-PRS resources of the TRP provided by the base station. The geographical coordinates of the TRP provided by the base station (including the transmission reference location of each DL-PRS resource ID, the reference location of the transmission antenna of the reference TRP, and the reference location of the transmission antenna of other TRPs). The fine timing relative to the candidate NR TRP and the service (baseline) TRP. PRS-specific transmit point indication (TP indication). Association information between TRP, Tx, TEG ID and DL-PRS resources. Information related to LOS / NLOS for each DL-PRS-RSRP / DL-PRS-RSSI / DL-RSTD / ToA / AoD / phase difference measurement. DL-PRS settings as needed TRP beam / antenna information (including azimuth angle, zenith angle, and relative electrical properties between PRS resources at each angle in each TRP). Auxiliary information for the expected angle, PRS Priority List.

[0119] The aforementioned dataset of correct answers (basic truth values) can also be rewritten as a dataset representing location information used for AI training / validation / testing.

[0120] The UE can also output its location from the AI ​​model. The aforementioned AI model on the UE side, which outputs the UE location, can also be applied to UL-based location measurement, DL UL-based location measurement, etc. These inputs may include, for example, the measurement results of the UE / gNB, extracted features, etc., or features extracted on the gNB side, or features extracted on the LMF side, etc.

[0121] (Categorization of positioning)

[0122] Locations using AI models can also be categorized as follows: (1) UE-based positioning (2) AI / ML-assisted localization (3) NG-RAN (Next Generation-Radio Access Network) node-assisted positioning.

[0123] (1) Based on UE positioning, it can be classified as follows: (1-1) Direct AI / ML localization in the UE-side model, (1-2) AI / ML-assisted localization in the UE-side model and non-AI-based localization in the UE-side algorithm.

[0124] (2) AI / ML-assisted localization can then be classified as follows: (2-1) AI / ML-assisted localization in the UE-side model and non-AI-based localization in the LMF-side algorithm. (2-2) Direct AI / ML localization in LMF side model.

[0125] (3) NG-RAN node-assisted localization can then be classified as follows: (3-1) AI / ML-assisted localization in the gNB-side model and non-AI-based localization in the LMF-side algorithm. (3-2) Direct AI / ML localization in LMF side model.

[0126] Regarding the aforementioned positioning, the following aspects are currently under study: The types of measurements used as input to the model inference (new measurements / existing measurements). In the positioning described in (1) and (2) above, it is assumed that the UE performs measurements as input for model inference. In the positioning described in (3) above, it is assumed that TRP (gNB / LMF) is measured and used as input for model inference. The reported measurement results serve as the input for model inference into the LMF side model (2-2, 3-2). In AI / ML-assisted localization, as part of UE-assisted (2-1) and NG-RAN node-assisted localization (3-1) model outputs to the LMF, new / existing measurement reports may be enhanced. Enhancements to the auxiliary signaling / procedures used to facilitate model inference for both the UE-side model and the NW-side model.

[0127] The localization methods shown in (1)-(3) above can also be collectively referred to as AI / ML-based localization. That is, localization using AI models, the localization methods mentioned above, and AI / ML-based localization (AI-based localization) can also be rewritten in relation to each other.

[0128] In addition, the following classifications are being researched regarding AI / ML-based positioning: Scenario 1: UE-based localization using UE-side models (direct AI / ML localization). Scenario 2a: UE-assisted / LMF-based localization using UE-side model (AI / ML-assisted localization). Scenario 2b: UE-assisted / LMF-based localization using LMF side model (direct AI / ML localization) Scenario 3a: NG-RAN node-assisted localization using gNB-side model (AI / ML-assisted localization). Scenario 3b: NG-RAN node-assisted localization using LMF-side model (direct AI / ML localization).

[0129] (Performance metrics related to positioning)

[0130] In Rel.17, the following metrics (TR38.857) are specified for performance evaluation. Additionally, the percentiles of the positioning error can be analyzed at 50%, 67%, 80%, and 90%.

[0131] Horizontal accuracy

[0132] Horizontal accuracy can also represent the difference between the calculated horizontal position of the UE and the actual horizontal position of the UE. For example, horizontal accuracy can be less than 0.2 meters in 90% of UEs.

[0133] Vertical accuracy

[0134] Vertical accuracy can also represent the difference between the calculated vertical position of the UE and the actual vertical position of the UE. For example, vertical accuracy can be less than 1 meter in 90% of UEs.

[0135] Latency

[0136] The latency can also be, for example, the end-to-end latency used for UE location estimation. This latency can also be less than 100 milliseconds (more preferably in the order of 10 milliseconds). This latency may also include processing delays of various associated nodes (UE, gNB, AMF, LMF, etc.) and signaling delays between nodes. As another type of latency, it may also include physical layer latency used for UE location estimation. This latency can also be less than 10 milliseconds.

[0137] At least one of the following can be used as a performance metric for model monitoring: Performance Latency. Complexity.

[0138] Performance can also include at least one of the following: Horizontal accuracy (in meters) of AI / ML-based positioning. Vertical accuracy (meters) for AI / ML-based positioning. Accuracy of intermediate features in AI / ML-based localization.

[0139] Horizontal accuracy can also represent the difference between the calculated horizontal position of the UE and the actual horizontal position of the UE. For example, horizontal accuracy can be less than 0.2m in 90% of UEs.

[0140] Vertical accuracy can also represent the difference between the calculated vertical position of the UE and the actual vertical position of the UE. For example, vertical accuracy can be less than 1m in 90% of UEs.

[0141] Intermediate feature precision can also represent the difference between the inferred intermediate value and the intermediate value derived based on the actual UE location. For example, intermediate feature precision can also represent at least one of the following: LOS / NLOS indicator precision (error rate %), ToA (milliseconds), AoA (degrees), RSTD (milliseconds), RSRP (dBm).

[0142] Latency can also include at least one of the following: Physical layer latency (milliseconds) End-to-end latency (milliseconds).

[0143] The latency during the positioning process can also be defined according to specific rules. The physical layer latency (start time / end time) can also be defined separately depending on the positioning method.

[0144] For example, in the case of UE-based positioning, the start time can be any of the following: the timing when the UE sends a PUSCH containing an MG request (Alt1), the timing when the gNB uses a PDSCH to send an LPP message containing auxiliary data (Alt2), or the timing when the UE begins receiving DL PRS (Alt3). Furthermore, the end time in this case can be the timing when the gNB successfully decodes the PUSCH containing an LPP-provide Location Information message, or, if unsuccessful, the timing when the UE performs location estimation calculations.

[0145] In the case of UE-assisted positioning / LMF-based positioning, the start time can also be the time when the gNB sends the PDSCH containing the LPP Request Location Information message. Furthermore, in this case, the end time can also be the time when the gNB successfully decodes the PUSCH containing the LPP Provide Location Information message.

[0146] In the case of NG-RAN node-assisted localization, the start time can also be the time when the gNB receives the NRPPa measurement request message. Furthermore, in this case, the end time can also be the time when the gNB sends the NRPPa measurement response message.

[0147] In addition, regarding the latency of the AI ​​model, for example, the timing when the UE / NW receives the input for model inference can be set as the start time, and the timing when the NW / UE receives the output of the AI ​​model can be set as the end time.

[0148] End-to-end latency can also be the latency used for UE location estimation.

[0149] Furthermore, the delay can also include higher-level delays as other delays. This delay can also include processing delays of various related nodes (UE, gNB, AMF, LMF, etc.) and signaling delays between nodes. Moreover, the definitions of the above delays can also follow the definitions in Rel. 17.

[0150] Complexity can also be defined by the computational complexity of model inference (floating-point operations (FLOPs)). Furthermore, the complexity of an AI model can also be defined by factors such as the model's data size (Mbytes) and the number of parameters associated with the AI ​​model.

[0151] (Performance monitoring for positioning (model monitoring))

[0152] Calculation of Performance Metrics

[0153] In UE-based localization, model monitoring for direct AI / ML localization based on the UE-side model can also be performed through at least one of the following: <1> Calculation of performance metrics in UE, <2> Calculation of performance indicators in LMF.

[0154] In UE-based localization, model monitoring for AI / ML-assisted localization based on the UE-side model can also be performed through at least one of the following: <3> Calculation of performance metrics in UE <4> Calculation of performance indicators in LMF.

[0155] In UE-assisted localization, model monitoring for AI / ML-assisted localization based on the UE-side model can also be performed in the following ways: <5> Calculation of performance indicators in LMF.

[0156] In NG-RAN node-assisted localization, model monitoring for AI / ML-assisted localization based on the gNB side model can also be performed through at least one of the following: <6> Performance index calculation in gNB, <7> Calculation of performance indicators in LMF.

[0157] Performance Metric Calculation in Direct AI / ML Localization Based on UE-Side Model

[0158] The performance index calculation (model monitoring) of <1> above can also be carried out by following the steps below.

[0159] Step 1: The UE obtains the basic true value of the UE location (the true value related to the UE location) in the noisy environment.

[0160] Step 1': The UE obtains the estimated UE position from model inference.

[0161] Step 2: Performance metrics monitored by the UE calculation model.

[0162] Step 3: Performance metrics monitored by the UE reporting model.

[0163] Step 3': The UE requests the LMF to activate / deactivate / switch the model.

[0164] Step 4: The UE receives the activation / deactivation / switching indication of the model from the LMF.

[0165] Step 5: The UE performs model activation / deactivation / switching.

[0166] The performance index calculation (model monitoring) of <2> above can also be carried out by following the steps below.

[0167] Step 1: The UE obtains its location from the model inference and reports it.

[0168] Step 1': LMF obtains the basic true UE location with more noise (the true value related to the UE location).

[0169] Step 2: Performance metrics monitored by the LMF calculation model.

[0170] Step 3: The UE receives the activation / deactivation / switching indication of the model from the LMF.

[0171] Step 4: The UE performs model activation / deactivation / switching.

[0172] Performance Metric Calculation in AI / ML-Assisted Localization Based on UE-Side Model

[0173] The performance index calculation (model monitoring) of <3> above can also be carried out by following the steps below.

[0174] Step 1: The UE obtains basic ground truth data with high noise levels (the true value related to a certain data (e.g., the UE's location)).

[0175] Step 1': The UE obtains estimated data from model inference.

[0176] Step 2: Performance metrics monitored by the UE calculation model.

[0177] Step 3: Performance metrics monitored by the UE reporting model.

[0178] Step 3': The UE requests the LMF to activate / deactivate / switch the model.

[0179] Step 4: The UE receives the activation / deactivation / switching indication of the model from the LMF.

[0180] Step 5: The UE performs model activation / deactivation / switching.

[0181] The performance index calculations (model monitoring) for <4> and <5> mentioned above can also be performed following these steps.

[0182] Step 1: The UE obtains estimated data from model inference and reports it.

[0183] Step 2: LMF obtains basic truth data (the true value related to a certain data (e.g., UE location)).

[0184] Step 3: Performance metrics monitored by the LMF calculation model.

[0185] Step 4: The UE receives the activation / deactivation / switching indication of the model from the LMF.

[0186] Step 5: The UE performs model activation / deactivation / switching.

[0187] Performance Metric Calculation in AI / ML-Assisted Localization Based on gNB Side Model

[0188] The performance index calculation (model monitoring) of <6> above can also be carried out by following the steps below.

[0189] Step 1: gNB obtains estimated data from model inference and reports it.

[0190] Step 1': gNB obtains basic truth data (the true value related to a certain data (e.g., UE location)).

[0191] Step 2: Performance metrics monitored by the gNB calculation model.

[0192] Step 3: gNB reports the performance metrics monitored by the model.

[0193] Step 3': gNB requests the LMF to activate / deactivate / switch the model.

[0194] Step 4: gNB receives activation / deactivation / switching instructions for the model from LMF.

[0195] Step 5: gNB performs model activation / deactivation / switching.

[0196] The performance index calculation (model monitoring) of <7> above can also be carried out by following the steps below.

[0197] Step 1: gNB obtains estimated data from model inference and reports it.

[0198] Step 2: LMF obtains basic truth data (the true value related to a certain data (e.g., UE location)).

[0199] Step 3: Performance metrics monitored by the LMF calculation model.

[0200] Step 4: gNB receives activation / deactivation / switching instructions for the model from LMF.

[0201] Step 5: gNB performs model activation / deactivation / switching.

[0202] Application of performance metrics on the UE side

[0203] When model inference is performed on the NW / UE side, the UE can also determine whether the performance index requirements are met.

[0204] The UE can 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: The accuracy of the output information of the monitored AI model. The difference between the inferred horizontal / vertical position and the actual horizontal / vertical position. The difference between the inferred output (ToA, AoA, RSTD, RSRP, etc.) and the output obtained from the actual location (ToA, AoA, RSTD, RSRP, etc.). The difference in latency The complexity of AI models and latency, and the required complexity. A binary indicator that indicates whether the performance requirements are met. The calculated estimation accuracy (horizontal accuracy / vertical accuracy / intermediate feature accuracy). Information related to the reliability (value) of the estimation accuracy.

[0205] In addition, the aforementioned monitoring information can also be reported based on at least one of the following selected branches: <Choose Branch 1> The situation where several of the multiple conditions are met (for example, the performance index does not meet a specific requirement). <Choose Branch 2> Report immediately after monitoring (unconditionally). <Choose Branch 3> Reports are based on settings / NW instructions (e.g., periodic, semi-permanent, non-permanent).

[0206] Application of performance indicators on the gNB side

[0207] When model inference is performed on the UE / gNB / LMF side, the gNB can also determine whether the performance index requirements are met.

[0208] The UE / LMF can 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 can also report to the gNB via the LMF: The inferred UE coordinates The deduced ToA, The inferred LOS / NLOS indicator, The inferred AoA, RSTD, and RSRP The complexity of AI models Time delay.

[0209] After comparing the information reported by the UE / information indicated by the LMF with the actual information, the gNB can also indicate at least one of the aforementioned monitoring information (UE-side information) to the UE / LMF via higher-layer signaling / physical layer signaling such as LPP / MAC CE / DCI / RRC / NRPPa.

[0210] Application of performance metrics on the LMF side

[0211] When model inference is performed on the UE / gNB / LMF side, the LMF can also determine whether the performance index requirements are met.

[0212] The UE / gNB can 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: The inferred UE coordinates The deduced ToA, The inferred LOS / NLOS indicator, The inferred AoA, RSTD, and RSRP The complexity of AI models Time delay.

[0213] After comparing the information reported by the UE / gNB with the actual information, the LMF can also indicate at least one of the aforementioned monitoring information (UE-side information) to the UE / gNB via higher-layer signaling / physical layer signaling such as LPP / MACCE / DCI / RRC / NRPPa.

[0214] Regarding the application of the aforementioned performance metrics on the UE / gNB / LMF side, model monitoring and model inference are preferably performed within the same entity (UE / gNB / LMF).

[0215] The topic of model monitoring

[0216] Regarding AI / ML-based localization model monitoring, research is underway on which entity should be specified for the calculation / application of the aforementioned performance metrics.

[0217] Regarding the monitoring of AI / ML models in lifecycle management, at least the following metrics / methods are being investigated for each use case: Monitoring based on inference accuracy (including metrics associated with intermediate KPIs). System performance monitoring (including metrics related to system performance KPIs). Other monitoring <Option 1> Monitoring based on data distribution (a) Input-based: For example, monitoring the validity of AI / ML inputs (out-of-distribution detection, input data drift detection, SNR, latency expansion, etc.). (b) Output-based: e.g., drift detection of output data, <Option 2> Monitoring based on application conditions The calculation of indicators for model monitoring can also be performed by UE / NW.

[0218] As mentioned above, regarding the monitoring of AI / ML models used for positioning, research is underway on the calculation subjects, calculation methods, and reporting methods of various indicators.

[0219] The main body (entity) for exporting performance indicators (monitoring indicators)

[0220] In addition to the above, the following can be cited as entities for deriving monitoring metrics regarding the performance monitoring of AI / ML-based positioning.

[0221] For UEs in scenarios 1 / 2a that are accompanied by (utilizing) the UE-side model.

[0222] For gNB in ​​case 3a, which is accompanied by (utilizing) the gNB side model.

[0223] For LMF in cases 2b and 3b, which are accompanied by (utilizing) the LMF side model.

[0224] Furthermore, the following entities are also studied.

[0225] LMF for scenario 2a (using the UE-side model) and scenario 3a (using the gNB-side model) when monitoring is performed at least based on the provided basic truth label (or its approximation).

[0226] For example, in scenarios 2a and 3a, the UE-side / gNB-side model can be monitored via the UE / gNB or LMF.

[0227] This disclosure is not limited to the above-described situation, and can also be applied to situations where the model of situation 1 can be monitored through the LMF side model.

[0228] (Lifecycle Management (LCM))

[0229] The introduction of multiple LCMs is being studied in future wireless communication systems (e.g., after Rel.18).

[0230] These multiple LCMs can also be function-based LCMs or model ID-based LCMs. Function-based LCMs can also be called function-based LCMs, and model ID-based LCMs can also be called model-ID-based LCMs.

[0231] In a functionality-based LCM, the NW (e.g., base station / NW node) can also indicate the operations involved in the functionality of AI / ML (e.g., activation, deactivation, fallback operation, handover at least one).

[0232] The UE may also perform model-level LCM (e.g., at least one of model switching and model selection) within the indicated functionality.

[0233] In terms of functionality, which model is activated / deactivated can also be transparent.

[0234] The UE Capability Information report can also be used in the notification of supported functionality.

[0235] In model-ID-based LCM, NW (e.g., base station / NW node) can also indicate the operation involved by an individual AI / ML model (e.g., activation, deactivation, rollback, handover, at least one of the following) via model ID.

[0236] The UE can also perform model-level LCM (e.g., model switching and model selection at least one) based on NW instructions.

[0237] Models can also be defined in NW using a model identifier (ID).

[0238] (Scenarios involved in model delivery / transfer)

[0239] Regarding model distribution / forwarding, three scenarios are defined in the existing context when the model is learned through NW.

[0240] [Scenario y]

[0241] First, the NW learns the model and distributes it to the UE outside of the 3GPP network based on offline engineering from multiple vendors.

[0242] Next, the UE reports on the support for the distributed models (this step can also be called model identification).

[0243] [Scenario z2]

[0244] First, NW learns models through offline engineering from multiple vendors and saves them in a proprietary format. A proprietary format can also mean a format defined by each vendor.

[0245] Next, the UE reports the utilization of the stored model in the 3GPP network (this step can also be called model identification).

[0246] Next, the model is transferred.

[0247] Next, the UE reports support for the forwarded model (this step can also be called model identification).

[0248] [Scenario z4]

[0249] First, the UE reports the supported model structure (this step can also be called model identification).

[0250] Next, NW forwards the model parameters of the supported model structures.

[0251] Next, the UE reports support for the forwarded model (this step can also be called model identification).

[0252] (Meta information)

[0253] The UE may also receive at least one of the following as metadata.

[0254] Furthermore, the term "meta-information" in this disclosure is merely one example; meta-information can also refer to at least one of specific setting information, scene information, environmental information, auxiliary information, and model information. In this disclosure, meta-information, setting information, scene information, environmental information, auxiliary information, and model information can also be interchanged.

[0255] The metadata used by the UE / NW may also include at least one of the following: information related to NW deployment, environment-related information, information related to the AL / ML model on the NW side, and information related to the model requested by the NW.

[0256] Information related to NW settings / configuration may also include information related to antenna settings.

[0257] Information related to antenna settings may include, for example, at least one of the following: number of horizontal / vertical antenna elements / panels, number of ports, antenna spacing, antenna position, panel position, transceiver unit (TxRU) mapping.

[0258] Information related to NW settings / configurations may also include information related to beam settings.

[0259] Information related to beam settings may include, for example, at least one of beamwidth, number of beams, beam direction, etc.

[0260] Information related to NW settings / configuration may also include information related to TRP.

[0261] Information related to beam setting may include, for example, the height of the TRP, the relative positions of multiple TRPs, and at least one of them.

[0262] Environment-related information may also include information related to the configuration scenario.

[0263] Information related to the configuration scenario can also represent at least one of the following: Urban Macro (UMa), Urban Micro (Umi), and Indoor Hotspot (InH).

[0264] Information related to the environment may include information related to indoor or outdoor environments.

[0265] Information related to indoor or outdoor conditions can also represent indoor / outdoor probabilities.

[0266] Information related to the environment can also be information related to objects around the UE / base station.

[0267] Information related to objects surrounding the UE / base station can also represent the configuration of objects surrounding the UE / base station.

[0268] Information related to the environment may also include, for example, the scene setting format (meta-information) described below.

[0269] Use cases that utilize AI models can also be associated with scenario setting formats consisting of long-tern features.

[0270] Furthermore, long-term features can be interchanged with short-term / medium-term / long-term features, or simply with other features. Additionally, scenario setting formats can be interchanged with metadata, metadata formats, scenario and configuration formats, scenario structure formats, scenario formats, configuration formats, use case formats, environment formats, and metaformats. Moreover, formats can be interchanged with types, patterns, data, and settings.

[0271] The above features may also include one or more combinations of the following elements: Scenes / models (Urban Macro (UMa)), Urban Micro (Umi)), Indoor, Outdoor, Indoor Hotspot (InH), etc.).

[0272] Frequency / frequency range.

[0273] Parameter set (or subcarrier spacing).

[0274] The distribution / set of general channel parameters (e.g., inter-site distances (ISD)), gNB height, delay spread, angular spread, Doppler spread, etc.) in a single scenario / model.

[0275] UE distribution.

[0276] UE speed.

[0277] UE trajectory.

[0278] Number of transmit beams / receive beams.

[0279] UE rotation mode.

[0280] gNB / UE antenna structure (e.g., transmit / receive antenna vectors).

[0281] Number of cells / Number of sectors.

[0282] bandwidth.

[0283] UE payload.

[0284] Channel quality (e.g., RSRP, SINR).

[0285] Beam configuration ID.

[0286] Physical Cell ID (PCI)

[0287] Global Cell ID (GCI)

[0288] Absolute Radio Frequency Channel Number (ARFCN)

[0289] The probability of line of sight (LOS) / non-line of sight (NLOS).

[0290] UEs can also expect that the scene setting format associated with the setting / registration (registration) is consistent with the UE's settings / state.

[0291] In addition, UEs can also expect that the activated scene setting format is consistent with the UE's settings / state.

[0292] The correspondence between use cases and scenario setting formats can also be specified in the standard, and information related to this correspondence can be communicated to the UE. Furthermore, the features included in the scenario setting format corresponding to the use case can also be specified in the standard, and information related to these features can also be communicated to the UE.

[0293] Information related to the AL / ML model on the NW side can also be included, for example, information related to the paired model available on the NW side.

[0294] Information related to the paired models available on the NW side can also represent, for example, the paired decoder used for CSI compression.

[0295] Information related to the AL / ML model on the NW side can also be included, for example, information related to preprocessing / postprocessing available on the NW side.

[0296] The preprocessing / postprocessing information available on the NW side may include, for example, at least one of quantization / dequantization, DFT transform, IDFT transform, FFT transform, IFFT transform, etc.

[0297] (UE assistance information)

[0298] UE can also report auxiliary information / metadata (meta-information) of AI / ML models.

[0299] Auxiliary information may also include at least one of the following: user status.

[0300] Overheating auxiliary information, DRX parameter preferences Priority order related to maximum aggregate bandwidth Preference for the maximum number of MIMO layers.

[0301] The AI / ML model can also be an AI / ML model that is registered, configured, compiled, or activated in the UE.

[0302] Auxiliary information / metadata of the AI / ML model can also be transmitted along with or in place of beam information. This beam information can, for example, be information related to the UE's antenna / beam.

[0303] The auxiliary information / metadata of the AI / ML model may also be at least one of the following.

[0304] The auxiliary information / metadata of an AI / ML model can also be the ID of the AI / ML model.

[0305] The ID of an AI / ML model can also be a global / local AI / ML model ID.

[0306] The auxiliary information / metadata of AI / ML models can also be information related to the applicable bandwidth corresponding to the AI / ML model ID.

[0307] This bandwidth can also be represented as the minimum / maximum bandwidth that can be applied.

[0308] Information related to the bandwidth may include, for example, information representing a band field indicator (e.g., "freqBandIndicatorNR"). The information representing the band field indicator may also be represented in a specific number of bits (e.g., 10 bits).

[0309] Information related to this bandwidth may include, for example, information indicating the bandwidth of the RS associated with the corresponding AI / ML model (e.g., “supportedBandwidth”).

[0310] Information indicating the bandwidth of the RS associated with the corresponding AI / ML model can also represent the frequency of each frequency range (e.g., FR1 / FR2 (FR2-1 / FR2-2) / FR3 / FR4 / FR5).

[0311] The auxiliary information / metadata of AI / ML models can also be information related to the applicable regions corresponding to the AI / ML model ID.

[0312] Information related to the applicable region corresponding to the AI / ML model may also include at least one of the following (a list of information): Region ID.

[0313] The global ID of the (NR) cell.

[0314] (NR) Physical cell ID (Identifier).

[0315] ARFCN (Absolute Radio Frequency Channel Number).

[0316] Global ID (ECGI) of Evolved Cell.

[0317] The region ID may also include the global ID of the NR cell, the physical cell ID of the NR, and at least one of the ARFCNs.

[0318] The auxiliary information / metadata of AI / ML models can also be antenna settings / beam information corresponding to the AI / ML model ID.

[0319] (KPI)

[0320] Regarding the performance monitoring of AI models, we are currently researching public key performance indicators (KPIs).

[0321] Below is an initial list of common KPIs used to evaluate the performance of AI / ML-based models: Performance Intermediate KPIs Link-level and system-level performance Generalization performance Over-the-air expenses, The cost of auxiliary information, The overhead of data collection, The overhead of model delivery / transfer. The overhead of signaling associated with other AI / ML models. Inference complexity. Computational complexity of model inference: floating point operations (FLOPs, where 's' is lowercase) (this refers to the amount of floating-point operations). The computational complexity of pre- and post-processing. Model complexity (number of parameters / data size (e.g., Mbytes) etc.) Training complexity, LCM-related complexity and memory overhead. Time delay (e.g., inference delay).

[0322] In addition, the KPIs mentioned above are just one example, and other KPIs (such as KPIs related to model training, KPIs specific to the use cases considered for the provided use cases, etc.) can be added to the list.

[0323] The performance-related KPIs mentioned above can also be called performance KPIs.

[0324] (Functional related information)

[0325] The UE can also report on the supported (or supported) functionalities.

[0326] Functionality can also be associated with specific information. Furthermore, functionality can also contain specific information. Additionally, functionality can belong to specific information.

[0327] In this disclosure, the terms "be associated with", "include", "belong to", and "correspond to" can be used interchangeably.

[0328] This specific information may also be at least one of the following. Furthermore, specific information and functionally related information may be modified from each other.

[0329] This specific information can also be related to applicable conditions / settings.

[0330] This specific information could be, for example, an applicable NW setting. For instance, the applicable parameters involved in this NW setting could be at least one of system information parameters and auxiliary information parameters.

[0331] This specific information could also be, for example, an applicable UE setting. For instance, the applicable parameters involved in this UE setting could also be higher-layer (e.g., RRC) parameters.

[0332] This specific information may also be information related to the applicable scenario. This information may also be information representing at least one of NLOS / LOS, UE distribution, SINR, RSRP, bandwidth, frequency, indoor / outdoor, and deployment scenario (e.g., at least one of Urban Macro (UMa), Urban Micro (Umi), and Indoor Hotspot (InH)).

[0333] This specific information may also be information related to the applicable configuration. This information may also be information indicating at least one of the following: applicable antenna settings (e.g., the number of antenna elements / panels in the horizontal / vertical direction, the number of ports, the antenna spacing, the antenna position, the panel position, the transceiver unit (TxRU) mapping), beam settings (e.g., at least one of the beamwidth, the number of beams, and the beam direction), and TRP information (e.g., the height of the TRP, the relative position of multiple TRPs, and at least one of the following).

[0334] This specific information could be, for example, information related to an applicable site. This information could also be, for example, information representing at least one of the following: area ID, NR cell global ID, NR physical cell ID, a specific frequency (e.g., ARFCN), or ECGI.

[0335] This specific information could, for example, be information related to the applicable paired models. The paired models could, for example, be two (or more) NW-side models (a combination of models). This information could also, for example, be information representing paired models used for CSI compression.

[0336] This specific information could be, for example, information related to the applicable time. This information could also be, for example, information representing the applicable period (period / interval / duration). This period could also be represented using a specific time unit (e.g., slot / symbol / subslot / millisecond / second).

[0337] Applicable conditions / settings can be predefined in the specification or determined / identified using a specific ID / token. For example, applicable settings / scenarios / conditions can be specified as specific parameters (e.g., test parameters) or represented using a specific ID / token.

[0338] Functional performance (e.g., prediction accuracy, location error) can also be conceived as being better than (e.g., higher than) a specific threshold under applicable conditions / settings. These specific conditions / settings could, for example, be conditions / settings in a specific test.

[0339] This threshold / performance requirement can be specified in advance in the specification, or it can be determined / identified using a specific ID / token.

[0340] With the threshold / performance requirement based on a specific ID / token, each vendor / operator can define the desired threshold / performance and can utilize it.

[0341] (Measurement settings for positioning)

[0342] As for the measurement settings [related information] used for positioning, the following examples can be cited.

[0343] As information related to the frequency layer, it may also include at least one of the following.

[0344] dl-PRS-SubcarrierSpacing, dl-PRS-CyclicPrefix dl-PRS-PointA (lowest subcarrier) , dl-PRS-StartPRB (start PRB index from reference point A) dl-PRS-ResourceBandwidth (24 PRBs~272 PRBs, 4 PRBs step) As information related to a resource set, it may also include at least one of the following.

[0345] nr-DL-PRS-ResourceSetID dl-PRS-Periodicity-and-ResourceSetSlotOffset dl-PRS-ResourceRepetitionFactor dl-PRS-ResourceTimeGap dl-PRS-MutingOption1 and dl-PRS-MutingOption2 The offset of SFN0 slot 0 of cell with respect to SFN0 slot 0 of reference cell in NR-DL-PRS-SFN0-Offset. dl-PRS-CombSizeN dl-PRS-NumSymbol: Size of the downlink PRS resource in the time domain {2,4,6,12}. As information related to resources, it may also include at least one of the following.

[0346] nr-DL-PRS-ResourceID, dl-PRS-SequenceID Starting RE offset, starting slot offset, starting symbol offset QCL information (QCL info) (analyze) In future wireless communication systems (e.g., after Rel.19), research is underway on data collection related to AI / ML-based positioning.

[0347] As a prerequisite for this data collection, in the case of the UE-side model (e.g., scenario 1 / 2a above), the ground truth (GRT) label may be provided from a non-PRU UE along with the estimated location. During this process, the estimated location or intermediate value of the UE may not be reported in the LMF.

[0348] In UE-based positioning, the estimated location of the UE can also be reported to the LMF as a forward retrieval label. Furthermore, in UE-assisted positioning, intermediate values ​​of the UE's measurements (e.g., timing information and at least one LOS / NLOS indicator) can also be reported to the LMF as forward retrieval labels.

[0349] For non-PRU UEs, the following are examples of positioning methods used to generate positive solution labels for the estimated location: GNSS / Assisted-(A-)GNSS positioning.

[0350] Positioning using a barometric pressure sensor.

[0351] Terrestrial Beacon Systems (TBS) positioning.

[0352] Motion sensor positioning.

[0353] Wireless Local Area Network (WLAN) location.

[0354] Bluetooth (registered trademark) positioning.

[0355] In GNSS / A-GNSS positioning, LMF can also be transmitted / forwarded from the UE. Figure 7 The information shown. In Figure 7 The diagram shows the information sent / forwarded in UE-assisted positioning and UE-based (or independent) positioning, respectively ("Yes" can also mean that it was sent, and "No" can also mean that it was not sent, as is the case in the following diagrams).

[0356] In barometric pressure sensor positioning, data can also be sent / forwarded from the UE to the LMF. Figure 8 The information shown. In Figure 8The diagram shows the information transmitted / forwarded in both UE-assisted positioning and UE-based positioning.

[0357] In TBS positioning, LMF can also be sent / forwarded from the UE. Figure 9 The information shown. In Figure 9 The diagram shows the information transmitted / forwarded in both UE-assisted positioning and UE-based positioning.

[0358] In motion sensor positioning, data can also be sent / forwarded from the UE to the LMF. Figure 10 The information shown. In Figure 10 The diagram shows the information transmitted / forwarded in both UE-assisted positioning and UE-based positioning.

[0359] In WLAN positioning, LMF can also be sent / forwarded from the UE. Figure 11 The information shown. In Figure 11 The diagram shows the information transmitted / forwarded in both UE-assisted positioning and UE-based positioning.

[0360] In Bluetooth (registered trademark) positioning, data can also be sent / forwarded from the UE to the LMF. Figure 12 The information shown. In Figure 12 The diagram shows the information transmitted / forwarded in both UE-assisted positioning and UE-based positioning.

[0361] In addition, in DL TDOA positioning, the UE ( / NW) can also receive requests related to location information (e.g., RequestLocationInformation) and [perform measurements] and report the corresponding information (response information, e.g., ProvideLocationInformation).

[0362] In addition, such as Figure 13 as well as Figure 14 As shown, requests related to this location information (e.g., NR-DL-TDOA-RequestLocationInformation-r16 / NR-DL-TDOA-ReportConfig-r16) can also contain various information.

[0363] In addition, such as Figure 15 As shown, the response information (e.g., NR-DL-TDOA-ProvideLocationInformation-r16) can also contain various information.

[0364] Furthermore, existing NR standards (up to Rel. 18) specify requirements for measurement accuracy. For example, the accuracy requirements for RSTD measurements in FR1 for AWGN (additive white Gaussian noise) channels are defined by… Figure 16 The table shown specifies this. In this table, "Precision" corresponds to the precision value X.

[0365] However, there are cases where research is insufficient in the various scenarios of AI / ML-based localization (e.g., at least one of scenarios 1 to 3b above).

[0366] <Question 1>

[0367] Regarding AI / ML-based positioning, in each case on the UE / gNB / LMF side (e.g., at least one of cases 1 to 3b above), the existing NR framework is considered as the baseline. Generally, in all LCM processes, the existing NR location request process is considered in all cases.

[0368] However, in the UE-side model, during differential LCM, UE-side measurements are not necessarily reported to the LMF. When the UE estimates location / intermediate values ​​for learning data collection, this information does not need to be reported to the LMF.

[0369] In this scenario, using the same settings as the existing ones raises concerns about signaling / process redundancy. Therefore, there is a need to investigate methods for specifying / supporting different UE operations within different LCM processes, but such research is insufficient.

[0370] <Question 2>

[0371] The investigation is focusing on data collection for AI / ML-based positioning, specifically measurements reported by the UE, including combinations of multiple measurements / reports and at least one of post-processing of the measurement reports. In this case, the NW needs to identify whether the data collected at the UE side is a processed measurement result.

[0372] In cases where post-processing result reporting is supported, it is necessary to study whether the definition of post-processing in the specification, the relevant instructions for post-processing result reporting, and the accuracy requirements are the same, but this study is insufficient.

[0373] <Question 3>

[0374] In the absence of NW identification of the UE-side model / functionality, it is considered beneficial to introduce a process to indicate whether the position information reported from the UE is generated by the AI / ML model, but the implementation method has not been sufficiently studied.

[0375] If research on these issues is unclear, it will be impossible to make appropriate overhead reductions, channel estimations, and resource utilization, and there are concerns that improvements in communication throughput and communication quality will be suppressed.

[0376] Therefore, the inventors of this application have devised a method to solve these problems.

[0377] (Various rewrites)

[0378] In this disclosure, terms enclosed in parentheses "()" may also indicate explanations of the preceding term (e.g., spelling instructions), in other words, specific examples, supplementary explanations, etc. Furthermore, in this disclosure, terms enclosed in square brackets "[]" may be included in the interpretation of the entire article, or may be excluded (ignored) while still interpreting the overall meaning of the article. Additionally, "()" and "[]" may also be used for purposes / meanings other than these.

[0379] In this disclosure, "A / B" and "at least one of A and B" may be rewritten as each other. In addition, in this disclosure, "A / B / C" may also mean "at least one of A, B and C".

[0380] In this disclosure, terms such as notification, activation, deactivation, indication (or indication), selection, configuration, update, and determination can be overridden. Similarly, terms such as support, control, ability to control, operation, and ability to operate can also be overridden.

[0381] In this disclosure, Radio Resource Control (RRC), RRC parameters, RRC messages, higher-level parameters, fields, Information Elements (IE), settings, etc., can also be modified interchangeably. In this disclosure, Medium Access Control (MAC) elements (MAC ControlElement (CE)), update commands, activation / deactivation commands, etc., can also be modified interchangeably.

[0382] In this disclosure, higher-layer signaling may be, for example, any one of Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information, other messages (e.g., messages from the core network, such as positioning protocol messages, such as NR Positioning Protocol A (NRPPa) / LTE Positioning Protocol (LPP) messages), or combinations thereof.

[0383] In this disclosure, MAC signaling may also use, for example, a MAC Control Element (MACCE) or a MAC Protocol Data Unit (PDU). Broadcast information may also be, for example, a Master Information Block (MIB), a System Information Block (SIB), a Minimum System Information (Remaining Minimum System Information (RMSI)), or Other System Information (OSI).

[0384] In this disclosure, physical layer signaling may also be, for example, downlink control information (DCI), uplink control information (UCI), etc.

[0385] In this disclosure, indexes, identifiers (IDs), indicators, resource IDs, etc., can also be overridden with each other. In this disclosure, time series, lists, sets, groups, clusters, subsets, etc., can also be overridden with each other.

[0386] In this disclosure, the following terms are used: panel, UE panel, panel group, beam, beam group, precoder, uplink (UL) transmitting entity, transmission / reception point (TRP)), base station, spatial relation information (SRI), spatial relation, SRS resource indicator (SRI), control resource set (CORESET), physical downlink shared channel (PDSCH), codeword (CW), transport block (TB), reference signal (RS), antenna port (e.g., demodulation reference signal (DMRS)) port, antenna port group (e.g., DMRS port group), group (e.g., spatial relation group, code division multiplexing (CDM) group, reference signal group, CORESET group, physical uplink control channel (PDSCH)). The Uplink Control 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 (TCI state) (DL TCI state), uplink TCI state (UL TCI state), unified TCI state, common TCI state, Quasi-Co-Location (QCL) and QCL concept can also be rewritten.

[0387] In this disclosure, CSI-RS, Non-Zero Power (NZP) CSI-RS, Zero Power (ZP) CSI-RS, and CSI Interference Measurement (CSI-IM) can be rewritten interchangeably. Furthermore, CSI-RS can also include other reference signals.

[0388] In this disclosure, the RS being measured / reported may also mean the RS being measured / reported for the purpose of CSI reporting.

[0389] In this disclosure, timing, moment, time, time slot, sub-time slot, code element, subframe, etc., can also be rewritten to each other.

[0390] In this disclosure, direction, axis, dimension, domain, polarization, polarization components, etc., can also be rewritten in relation to each other.

[0391] In this disclosure, estimation, prediction, and inference can be rewritten interchangeably. Furthermore, in this disclosure, making an estimate, making a prediction, and making an inference can also be rewritten interchangeably.

[0392] In this disclosure, the autoencoder, encoder, decoder, etc., can also be rewritten as at least one of a model, ML model, neural network model, AI model, AI algorithm, etc. Furthermore, the autoencoder can be rewritten with any autoencoder such as a stacked autoencoder or a convolutional autoencoder. The encoder / decoder of this disclosure can also employ models such as Residual Network (ResNet), DenseNet, and RefineNet.

[0393] In this disclosure, bits, bit strings, bit sequences, sequences, values, information, values ​​derived from bits, and information derived from bits can also be rewritten in relation to each other.

[0394] In this disclosure, the layers (for the encoder) can also be rewritten with layers (input layers, intermediate layers, etc.) used in the AI ​​model. The layers in this disclosure can also be equivalent to at least one of the following: input layer, intermediate layer, output layer, batch normalization layer, convolutional layer, activation layer, dense layer, normalization layer, pooling layer, attention layer, dropout layer, fully connected layer, etc.

[0395] In this disclosure, RSRP can also be rewritten with any parameters related to receive power / receive quality (e.g., RSRQ, SINR, CSI).

[0396] In this disclosure, RS can also be, for example, CSI-RS, SS / PBCH block (SS block (SSB)), etc. Furthermore, RS index can also be CSI-RS resource indicator (CSI-RS Resource Indicator (CRI)), SS / PBCH block indicator (SS / PBCH Block Indicator (SSBRI)), etc.

[0397] In this disclosure, channel measurement / estimation may also be performed using at least one of the following: Channel State Information Reference Signal (CSI-RS), Synchronization Signal (SS), Synchronization Signal / Physical Broadcast Channel (SS / PBCH) block, DeModulation Reference Signal (DMRS), Measurement Reference Signal (Sounding Reference Signal (SRS)).

[0398] In this disclosure, the receiving beam design, the number of receiving beams, the index of the receiving beams, the selection of the receiving beams, the setting of the receiving beams, and the indication of the receiving beams can be mutually modified. In this disclosure, the receiving beam, the transmitting beam, the DL receiving beam, the DL transmitting beam, the transmitting beam, and the pair of receiving beams can also be mutually modified. In this disclosure, the transmitting / receiving beams can also be mutually modified with the transmitting / receiving beams used for beam prediction and the transmitting / receiving beams used for CSI measurement / reporting for beam prediction.

[0399] In this disclosure, "functionality" can refer to the purpose of a model or the physical meaning of its inputs / outputs. Multiple models can also have the same functionality. Based on functionality (e.g., per function), monitoring (performance verification) / activation / deactivation / switching / rollback / update can also be indicated (controlled).

[0400] In this disclosure, functionality may also refer to features (requiring AI / ML capabilities) such as reporting information based on CSI prediction / CSI compression / temporal beam prediction / spatial domain beam prediction.

[0401] Furthermore, a model ID can also refer to an identifier for a model (or a collection of models). Multiple models can also be assigned the same model ID in an actual deployment. In this case, although these models are actually different models (e.g., different numbers of layers, etc.), they can be treated as the same model.

[0402] Additionally, in this disclosure, the model ID can also be associated with metadata (or a set of metadata) IDs. Metadata (or metadata IDs) can also be associated with information related to the application possibilities of the model / function, the environment, UE / gNB settings, etc.

[0403] In this disclosure, functionality can also be simply rewritten as "function".

[0404] In this disclosure, functionality, function, functional ID, model, and model ID can also be overridden.

[0405] In this disclosure, the applicable update, the update of the applicable model / functionality, the update of the applicability of the model / functionality, and the applicable update can also be rewritten in relation to each other.

[0406] In this disclosure, updates, reports, and sending can also be overridden.

[0407] In this disclosure, reports on the possibility of application and reports on applicability can be rewritten from each other.

[0408] In this disclosure, metadata, auxiliary information, sensing information, KPIs, performance KPIs, UE status, and status can also be interchanged.

[0409] In this disclosure, functions such as discard, abort, delete, truncate, rate match, postpone (postpone), and do not send can be rewritten interchangeably.

[0410] In this disclosure, ID may also represent an ID corresponding to at least one attribute (used to determine) a dataset, model, or channel / RS. That is, in this disclosure, ID, dataset ID, model ID, and channel / RS attribute ID may be interchanged.

[0411] In this disclosure, entities, specific entities, UE, NW, gNB, and LMF can also be rewritten.

[0412] In this disclosure, NW, LMF, gNB, BS, and NG-RAN can also be rewritten.

[0413] In this disclosure, performance metrics and monitoring metrics can also be rewritten.

[0414] In the following embodiments, the associated subject is UE / gNB / LMF to illustrate the AI ​​model related to communication between UE / gNB (NG-RAN) / LMF, but the application of the embodiments of this disclosure is not limited to this. For example, for communication between other subjects (e.g., UE-UE communication), the UE / gNB / LMF in the following embodiments can also be rewritten as a first UE, a second UE, a third UE, etc. In other words, the UE / gNB / LMF disclosed herein can all be rewritten as any UE / gNB / LMF. Furthermore, NW / BS / gNB / LMF can also be rewritten interchangeably.

[0415] (Wireless communication method)

[0416] The UE / NW (gNB / LMF) can also perform positioning using the various implementation methods shown below.

[0417] The UE can also receive various settings for positioning / reporting. Furthermore, the UE can also report / send the corresponding prediction (positioning) results to the NW.

[0418] The NW can also send various settings for positioning / reporting to the UE. Furthermore, the NW can also receive corresponding prediction results (reports) from the UE.

[0419] <First Implementation>

[0420] The first embodiment relates to a solution to problem 1 described above.

[0421] <<Implementation Method 1-1>>

[0422] For UE, settings for learning / monitoring / inference of AI / ML models and AI / ML functions (e.g., location information requests) can also be specified / set separately.

[0423] The UE can also perform learning / monitoring / inference operations on the model / function based on this setting.

[0424] For example, a parameter indicating usage can also be included in settings for AI / ML-based location data collection (e.g., location information requests).

[0425] This parameter can also indicate, for example, that the data is used for learning / reasoning / monitoring, or that the data is used for measurement / labeling.

[0426] Different parameters / information elements can also be specified / set in settings for different purposes (e.g., data collection for learning / monitoring, or data collection for inference).

[0427] For example, when data collection is initiated by the UE, the UE may send a data collection configuration request together with the data collection request or separately from the data collection request.

[0428] In addition, this implementation can be applied in specific situations (e.g., situation 1 / 2a) or in any situation where the (AI / ML) model / function is used on the UE side.

[0429] For example, the settings used in the data collection settings (e.g., a request for location information) can be determined by following the parameters indicating the purpose.

[0430] For example, for data collection aimed at a specific purpose (e.g., model inference), the same settings as existing location information requests can be reused.

[0431] For example, new settings can also be used for data collection intended for other purposes (e.g., model learning / monitoring). These new settings can also be settings that remove specific (unwanted) parameters from existing settings.

[0432] For example, when performing model inference in the UE-side model, it can also include (use) in such... Figure 17 The settings shown (NR-DL-TDOA-RequestLocationInformation-r16) include all parameters. Furthermore, when performing model learning / monitoring on the UE side, parameters such as those shown in the configuration can be omitted (not used). Figure 17 The specific parameters included in the settings shown (NR-DL-TDOA-RequestLocationInformation-r16).

[0433] In addition, in such Figure 17 The information elements shown may also contain parameters indicating the purpose (e.g., usage-r19).

[0434] For example, the base station can also control the inclusion or exclusion of a specific parameter in the setting (NR-DL-TDOA-RequestLocationInformation) that indicates a specific value for a parameter representing the purpose (e.g., for model learning / monitoring / inference).

[0435] For example, the UE may also envision that the specific parameter is included or not included in the setting (NR-DL-TDOA-RequestLocationInformation) of the parameter indicating the purpose (e.g., for model learning / monitoring / inference).

[0436] This specific parameter may be, for example, a parameter indicating the presence or absence of assistance (e.g., nr-AssistanceAvailability-r16), a parameter related to report settings (e.g., nr-DL-TDOA-ReportConfig-r16), a parameter related to a first additional path (e.g., additionalPaths-r16), a parameter related to a request to receive a TEG (e.g., nr-UE-RxTEG-Request-r17), a parameter related to a second additional path (e.g., additionalPathsExt-r17), a parameter related to a request for an additional path to the RSRP of the DL PRS (e.g., additionalPathsDL-PRS-RSRP-Request-r17), and a parameter related to multiple measurements in the same report (e.g., multiMeasInSameReport-r17).

[0437] In the case of a UE-side model, existing settings can also be reused when the UE collects data for a primary purpose (e.g., model inference). Furthermore, when the UE collects data for a secondary purpose (e.g., model learning / monitoring), new settings that do not include specific parameters can also be used.

[0438] According to implementation method 1-1, signaling overhead can be reduced according to the purpose specified in the settings for data collection (e.g., location information request).

[0439] <<Implementation Methods 1-2>>

[0440] The location information request in the existing NR can also be specified / set publicly for model reasoning / learning / monitoring.

[0441] The UE can also determine the positioning operation based on the state of the model process (model process state). For example, the UE can also determine, based on the state of the model process, at least one of the following: the execution of model / function learning / monitoring / inference operations, and the execution of corresponding reporting operations.

[0442] For example, the UE can also decide whether to report the measurement results based on the status of the model process.

[0443] In this disclosure, "phase X" can also be rewritten as "the period during which the results of measurement / inference for X are reported".

[0444] For example, during the learning phase, if the model learning is performed on the UE side, the UE may not report the measurement results to the LMF.

[0445] For example, during the learning phase, when model learning is performed on the LMF side, the UE can also report the measurement results as existing NR positioning.

[0446] For example, during the inference phase, the UE can also report the inference output to the LMF.

[0447] For example, during the monitoring phase, if the metric calculation for monitoring is performed on the UE side, the UE may not report the measurement results to the LMF.

[0448] For example, during the monitoring phase, if the measurement calculations for monitoring are performed on the LMF side, the UE can also report the measurement results as existing NR positioning.

[0449] The information / parameters that are ignored can vary depending on the purpose of the data collection.

[0450] The state of the model process can also be identified in the UE / NW through the LCM process, for example. For example, the structure included in the settings can also be determined based on predefined rules.

[0451] Additionally, this implementation can be applied to the UE or a third party communicating with the UE (e.g., an OTT (Over The Top, for example, bypassing the network of a communication service provider to provide independent content / services / functions provided by the provider / vendor) server / SUPL (Secure User Plane Location, for example, a secure interaction using location data) server) to perform model learning / inference / monitoring (performance metric calculation).

[0452] According to implementation methods 1-2, signaling overhead can be reduced based on the state of the model process.

[0453] The first embodiment described above can help solve the problem 1 mentioned above.

[0454] <Second Implementation>

[0455] The second implementation relates to a solution to problem 2 described above.

[0456] For AI / ML-based localization performed by the UE-side model, the processed measurement results can also be used as collected data and as input for model inference.

[0457] Post-processing of measurement results for AI / ML-based localization can also be specified.

[0458] The input for post-processing can also be, for example, a [typical] measurement / forward mapping label used in AI / ML-based localization. The input for post-processing can also include, for example, at least one of the following: UE location.

[0459] Rx-Tx time difference.

[0460] DL RSTD.

[0461] UL RTOA.

[0462] RSRP / RSRPP.

[0463] RSCP.

[0464] LOS / NLOS indicator.

[0465] The output of post-processing can also be, for example, a measurement that has been processed from the input (e.g., measurement / positive label). The output of post-processing can also be constructed with higher precision / a larger dataset size (compared to positive labels).

[0466] The UE can also decide whether to report physical measurements (without post-processing) or post-processed measurement results based on the NW's settings / instructions and predefined rules / conditions.

[0467] For example, the UE can also be instructed / set to perform post-processing via DCI / MAC CE / RRC / LPP from the NW.

[0468] This instruction / setting may also include at least one of the following: Instructions related to the reporting of post-processed measurement results or raw physical data.

[0469] Information (expected) related to the output of the post-processed dataset (e.g., information type, which entity technology was used to generate it, the required dataset size, the processing unit, and the required level of accuracy / reliability, at least one of the following).

[0470] The UE can also report capabilities related to at least one of the following: Does it support post-processing?

[0471] Does it support post-processed measurement reports?

[0472] UEs can also follow predefined rules / conditions.

[0473] For example, if at least one of the following conditions is met (i.e., the accuracy requirement is higher than a specific threshold) or (ii., the dataset size is smaller than a specific threshold), the UE may determine that post-processing is applied in the data collection on the UE side for AI / ML-based positioning.

[0474] For example, the UE can also report indicators related to whether the reported results are accompanied by post-processing.

[0475] If the UE determines that it needs to report data that has undergone post-processing, the UE can also report the post-processed measurement results.

[0476] In this case, for example, the UE may also report the original physical dataset before post-processing.

[0477] In this case, for example, the UE may also report differences in dataset size / processing units / accuracy / reliability level of post-processed measurement results compared with physical data.

[0478] In this case, for example, the UE may also report the dataset size / processing unit / accuracy / reliability level of the post-processed measurement results.

[0479] In the case of post-processing, corresponding (new) accuracy requirements can also be applied. These accuracy requirements can, for example, be defined at least for RSTD measurements / PRS-RSRP measurements / UE receive-transmit time difference measurements.

[0480] This accuracy requirement can also be higher / more stringent / more granular compared to the existing accuracy requirements (up to Rel.18) for each measurement.

[0481] For example, in RSTD measurements, a new correspondence (table) can also be specified based on a smaller precision value (e.g., X).

[0482] For example, the reference sensitivity conditions specified in the specification are met, and the corresponding bands of the associated PRS resources set for measurement purposes meet the RSTD measurement conditions. In addition, the UE can reduce the number of samples to avoid performing positioning measurements.

[0483] In this case, [when the absolute value of the accuracy requirement is higher than the threshold] the UE can also perform post-processing of positioning measurements [through specific technologies / (AI / ML) models / functions].

[0484] According to the second embodiment above, the post-processing can be properly specified / instructed, which can help solve the above-mentioned problem 2.

[0485] <Third Implementation Method>

[0486] The third implementation involves a solution to problem 3 described above.

[0487] The UE-side model / function related to AI / ML-based positioning described in the following embodiments 3-1 / 3-2 can also be applied / utilized.

[0488] <<Implementation Method 3-1>>

[0489] The UE can also report to the LMF side whether the reported positioning information was generated by the AI / ML model.

[0490] The UE may also include information related to at least one of the following in the report: An indicator that indicates whether the reported information was generated by an AI / ML model.

[0491] Valid timer / duration for UE-side model / function.

[0492] The effective area of ​​the UE-side model / function.

[0493] The local ID / associated ID of the UE-side model / function of the application.

[0494] Regarding the effective timer / period, the report can also be executed / applied for each measurement. For example, the report can also be executed / applied for at least one of X measurements and multiple (e.g., all) measurements within a specific period. For example, at least one of the value of X and the length of the specific period can also be reported by the UE.

[0495] The report for the LMF side can be reported together with the UE side location information or separately from the UE side location information.

[0496] <<Implementation Method 3-2>>

[0497] The UE can also send specific configuration requests to the NW.

[0498] This specific configuration request could also be, for example, a configuration request for facilitating (AI / ML) models / functions on the UE side.

[0499] For example, the UE can also send information to inform the NW about the UE-side (AI / ML) model / function.

[0500] In addition, for example, the UE can also request specific parameters inherent to the UE-side (AI / ML) model / function based on the positioning settings.

[0501] The settings involved in this particular parameter may also differ from those associated with existing (up to Rel.18) position measurements.

[0502] This specific parameter can also be, for example, a parameter related to at least one of the following: New measurements (e.g., new channel measurements such as channel impulse response (CIR) / power delay profile (PDP) / delay profile (DP)).

[0503] Higher precision than existing measurements.

[0504] New parameters (e.g., number of samples or a larger number of paths).

[0505] (Compared to the existing format) New report format.

[0506] The third embodiment described above can help solve the problem 3 mentioned above.

[0507] <Supplement>

[0508] <<AI Model Information>>

[0509] In this disclosure, AI model information may also refer to information that includes at least one of the following: The input / output information of the AI ​​model.

[0510] Information used for preprocessing / postprocessing of inputs / outputs in AI models.

[0511] Information about the parameters of the AI ​​model.

[0512] Training information (learning information) used for AI models.

[0513] Information used for reasoning in AI models.

[0514] Performance information related to the AI ​​model.

[0515] Here, the input / output information of the above AI model may also include at least one of the following related information: The content of input / output data (e.g., RSRP, SINR, amplitude / phase information in the channel matrix (or precoding matrix), information related to the Angle of Arrival (AoA), information related to the Angle of Departure (AoD), and location information).

[0516] Auxiliary information of the data (also known as meta-information).

[0517] The type of input / output data (e.g., immutable values ​​(constant values), floating-point numbers).

[0518] Bit width of input / output data (e.g., 64 bits for each input value).

[0519] The quantization interval (step size) of the input / output data (e.g., 1 dBm for L1-RSRP).

[0520] The range of input / output data that can be taken (e.g., [0, 1]).

[0521] Additionally, in this disclosure, information related to AoA may also 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, for example, include information related to at least one of the azimuth angle of departure and the zenith angle of depature (ZoD).

[0522] In this disclosure, location information can also be location information related to the UE / NW. Location information may also include at least one of the following: information obtained using a positioning system (e.g., satellite positioning systems such as Global Navigation Satellite System (GNSS), Global Positioning System (GPS), etc.) (e.g., latitude, longitude, altitude); information of the BS (Block Grid) adjacent to (or serving) the UE (e.g., BS / cell identifier (ID)), distance between BS and UE, direction / angle of the BS (UE) as observed from the UE (BS), coordinates of the BS (UE) as observed from the UE (BS) (e.g., X / Y / Z axis coordinates), 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, but can also be information based on a specific point.

[0523] Location information can also include implementation-related information (e.g., antenna location / position / orientation, antenna panel location / orientation, number of antennas, number of antenna panels, etc.).

[0524] Location information may also include mobility information. Mobility information may also include at least one of the following: information indicating the type of mobility, the UE's moving speed, the UE's acceleration, and the UE's moving direction.

[0525] Here, the mobility type can also be equivalent to at least one of the following: fixed location UE, movable / moving UE, no mobility UE, low mobility UE, middle mobility UE, high mobility UE, cell-edge UE, and not-cell-edge UE.

[0526] In this disclosure, the environmental information (used for the data) may also be information related to the environment in which the data is acquired / utilized, such as frequency information (band ID, etc.), environmental type information (information indicating at least one of indoor, outdoor, urban macro (UMa) or urban micro (Umi)), information indicating line of sight (LOS) or non-line of sight (NLOS)), etc.

[0527] Here, LOS can also mean that the UE and BS are in an environment where they are mutually visible (or without obstructions), and NLOS can also mean that the UE and BS are not in an environment where they are mutually visible (or with obstructions). Information representing LOS / NLOS can represent either soft values ​​(e.g., the probability of LOS / NLOS) or hard values ​​(e.g., either LOS or NLOS).

[0528] In this disclosure, metadata can also refer to information related to input / output information suitable for AI models, information related to acquired / available data, etc. Specifically, metadata can also include beam-related information of RS (e.g., CSI-RS / SRS / SSB, etc.) (e.g., pointing angle of each beam, 3dB beamwidth, shape of the pointing beam, number of beams), antenna layout information of gNB / UE, frequency information, environmental information, metadata ID, etc. Furthermore, metadata can also be used as input / output of AI models.

[0529] The preprocessing / postprocessing information used for the input / output of the aforementioned AI model may also include at least one of the following related information: Whether to apply normalization (e.g., Z-score normalization, min-max normalization).

[0530] The parameters used for normalization (e.g., normalizing to mean / variance for Z-scores, and normalizing to minimum / maximum for min-maximum).

[0531] Whether to apply specific numerical transformation methods (e.g., one-hot encoding, label encoding, etc.).

[0532] The selection rules for whether to use it as training data.

[0533] For example, the input information x can also be preprocessed and Z-score normalized (x new = (x - μ) / σ. Here, μ is the mean of x, and σ is the standard deviation. The input information x after normalization is... new Input to an AI model can also be used to process the output y from the AI ​​model. out After applying post-processing, the final output y is obtained.

[0534] The parameters of the aforementioned AI model may also include information related to at least one of the following: Weight information (e.g., the coefficients of neurons (association coefficients)) in AI models.

[0535] The structure of AI models.

[0536] Types of AI models that serve as model components (e.g., Residual Network (ResNet), Dense Network (DenseNet), RefineNet, Transformer model, Convolutional Residual Block (CRBlock), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU))).

[0537] The functionality of an AI model as a model component (e.g., decoder, encoder).

[0538] In addition, the weight information in the aforementioned AI model may also include at least one of the following related information: The bit width (size) of the weight information.

[0539] Quantization interval of weight information.

[0540] Granularity of weight information.

[0541] The range of acceptable weight information.

[0542] The parameters of weights in an AI model.

[0543] Information from the difference between the AI ​​model before the update (update case).

[0544] Methods of weight initialization (e.g., zero initialization, random initialization (based on normal / uniform / truncated normal distribution), Xavier initialization (for sigmoid function), He initialization (for rectified linear units (ReLU))).

[0545] In addition, the structure of the aforementioned AI model may also include information related to at least one of the following: Number of floors.

[0546] Layer type (e.g., convolutional layer, activation layer, dense layer, normalization layer, pooling layer, attention layer).

[0547] Layer information.

[0548] Parameters specific to time series (e.g., bidirectionality, time steps).

[0549] The parameters used for training (e.g., the type of feature (L2 regularization, dropout feature, etc.) and where to place that feature (e.g., after which layer).

[0550] The aforementioned layer information may also include information related to at least one of the following: The number of neurons in each layer.

[0551] Kernel size.

[0552] The stride used for pooling / convolutional layers.

[0553] Pooling methods (Max Pooling, Average Pooling, etc.).

[0554] Information about the residual block.

[0555] Head count.

[0556] Normalization methods (batch normalization, instance normalization, layer normalization, etc.).

[0557] Activation functions (sigmoid, tanh function, ReLU, information from Leaky ReLU, Maxout, Softmax).

[0558] An AI model can also be included as a component of other AI models. For example, an AI model can be processed in the following order: ResNet as model component #1, Transformer model as model component #2, dense layers, and normalization layers.

[0559] The training information used for the AI ​​model described above may also include information related to at least one of the following: Information used for optimization algorithms (e.g., the type of optimization (Stochastic Gradient Descent (SGD)), AdaGrad, Adam, etc.), and optimization parameters (learning rate, momentum information, etc.).

[0560] Information about the loss function (e.g., information related to the metrics of the loss function (Mean Absolute Error (MAE)), Mean Square Error (MSE)), Cross-Entropy Loss, NLLLoss, Kullback-Leibler (KL) divergence, etc.)).

[0561] Parameters that should be frozen for training purposes (e.g., layers, weights).

[0562] Parameters that should be updated (e.g., layer, weight).

[0563] These should be the parameters (e.g., layers, weights) used for initial training (applied as initial parameters).

[0564] AI model training / update methods (e.g., (recommended) number of epochs, batch size, number of data used in training).

[0565] The inference information used for the aforementioned AI model may also include information related to decision tree branch pruning, parameter quantization, and the functionality of the AI ​​model. Here, the functionality of the AI ​​model may be equivalent to at least one of the following: temporal beam prediction, spatial beam prediction, CSI-feedback-oriented autoencoder, or beam management-oriented autoencoder.

[0566] Automatic encoders oriented towards CSI feedback can also be used as follows: The UE can also send the encoded bits output from the AI ​​model of the encoder as CSI feedback (CSI report).

[0567] BS can also reconstruct the CSI / channel matrix / precoding matrix output from the received encoded bits as input to the AI ​​model of the decoder.

[0568] In spatial domain beam prediction, UE / BS can also take measurements (beam quality, e.g., RSRP) based on sparse (or wide) beams as input to the AI ​​model and output dense (or narrow) beam quality.

[0569] In time-domain beam prediction, the UE / BS can also take time-series (past, present, etc.) measurement results (beam quality, e.g., RSRP) as input to the AI ​​model and output the future beam quality.

[0570] The performance information related to the aforementioned AI model may also include information related to the expected value of the loss function defined for the AI ​​model.

[0571] The AI ​​model information in this disclosure may also include information related to the application scope (applicable scope) of the AI ​​model. This application scope may also be represented by physical cell ID, serving cell index, etc. Information related to the application scope may also be included in the environmental information mentioned above.

[0572] AI model information associated with a specific AI model can be predetermined in the standard or notified to the UE from the network (NW). The AI ​​model specified in the standard can also be referred to as a reference AI model. AI model information associated with the reference AI model can also be referred to as reference AI model information.

[0573] Furthermore, the AI ​​model information in this disclosure may also include an index for identifying the AI ​​model (e.g., it may also be referred to as the AI ​​model index, AI model ID, model ID, etc.). The AI ​​model information in this disclosure may also be based on / replace the aforementioned input / output information of the AI ​​model, and include an AI model index. The association between the AI ​​model index and the AI ​​model information (e.g., the input / output information of the AI ​​model) can be predetermined in the standard or notified to the UE from the NW.

[0574] The AI ​​model information in this disclosure can also be associated with an AI model and can be referred to as AI model-related information, or simply as related information. The AI ​​model-related information may not explicitly include information used to identify the AI ​​model. For example, AI model-related information may only contain metadata.

[0575] In this disclosure, the model ID can also be interchanged with the ID of the set corresponding to the AI ​​model (model set ID). Furthermore, in this disclosure, the model ID can also be interchanged with the metadata ID. As mentioned above, metadata (or metadata ID) can also be associated with beam-related information (beam settings). For example, metadata (or metadata ID) can also be used by the UE to consider which beam the BS uses to select the AI ​​model, or to notify the BS which beam should be used to apply the AI ​​model deployed by the UE. Additionally, in this disclosure, the metadata ID can also be interchanged with the ID of the set corresponding to the metadata (metadata set ID).

[0576] In this disclosure, functionality may also mean the set of parameters that can be supported based on the conditions indicated by the UE capability (e.g., the set of parameters for CSI prediction / beam prediction / CSI compression).

[0577] The UE can also report parameter values ​​associated with functionality / model as conditions to the NW via higher-layer signaling (e.g., RRC, MAC CE) / physical-layer signaling (e.g., DCI). For example, the UE can also report conditions using reports of UE capabilities / features / feature groups.

[0578] The UE can also report parameter values ​​associated with functionality / model as additional conditions to the NW using methods other than higher-layer signaling / physical layer signaling or signaling via the NW's air interface (such as operator's configurations, pre-set messages, etc.), or can be instructed to do so.

[0579] The UE can also use higher-layer signaling / physical layer signaling, or other methods such as signaling via the NW's air interface (e.g., operator's configurations, pre-set messages, etc.) as information / indications related to additional conditions, and report information / indications (e.g., parameter names) for the corresponding parameters, which can also be indicated.

[0580] For example, the UE can also report device ID, vendor ID, etc., as supplementary information. Furthermore, the UE can also be notified of the cell ID as an additional condition. Additionally, the UE can report cell ID / UE ID, etc., instead of parameter names, and can also be instructed to do so.

[0581] Other methods besides signaling via the NW's air interface can be methods related to UE pre-configuration (e.g., based on UE vendor settings) or service provider settings provided by the NW service provider.

[0582] <<Information Notification to UE>>

[0583] In the above embodiments, any information [notification from the network (NW) (e.g., base station (BS))] to the UE (in other words, the reception of any information from the BS in the UE) can also be delivered using physical layer signaling (e.g., DCI), higher layer signaling (e.g., RRC signaling, MAC CE), specific signals / channels (e.g., PDCCH, PDSCH, reference signals), or combinations thereof.

[0584] In the case where the above notification is made via MAC CE, the MAC CE can also be identified by including a new Logical Channel ID (LCID) that is not specified in the existing standard in the MAC subheader.

[0585] When the above notification is made through a DCI, the notification can also be made through specific fields of the DCI, the Radio Network Temporary Identifier (RNTI) used in the scrambling of the Cyclic Redundancy Check (CRC) bits assigned to the DCI, the format of the DCI, etc.

[0586] Furthermore, the notification of any information to the UE in the above embodiments can also be carried out periodically, semi-persistently, or non-periodically.

[0587] <<Notification of Information from UE>>

[0588] The notification of arbitrary information from the UE to the NW (in other words, the transmission / reporting of arbitrary information from the UE to the BS) in the above embodiments can also be performed using physical layer signaling (e.g., UCI), higher layer signaling (e.g., RRC signaling, MAC CE), specific signals / channels (e.g., PUCCH, PUSCH, PRACH, reference signals), or combinations thereof.

[0589] In the case where the above notification is made via MAC CE, the MAC CE can also be identified by including a new LCID in the MAC subheader that is not specified in the existing standard.

[0590] In cases where the above notification is sent via UCI, the above notification may also be sent using PUCCH or PUSCH.

[0591] Furthermore, the notification of any information from the UE in the above embodiments can also be carried out periodically, semi-persistently, or non-periodically.

[0592] <<Application of Each Implementation Method>>

[0593] In the UE / BS, a specific processing / operation / control / conception / information for at least one of the above-described implementations may also be applied (used) if any one or more of the following conditions are met: These are high-level parameters that are set to represent the specific processing / operation / control / concept / information described above. The specific processing / operation / control / concept / information mentioned above is determined based on associated high-level parameters. The aforementioned specific processing / operation / control / conception / information is specified / activated / triggered via MAC CE / DCI / UCI / resource / channel / RS. The report or support indicates the specific UE capability mentioned above, which refers to the specific processing / operation / control / conception / information (or associated information). The application of the aforementioned specific processing / operation / control / conception / information is judged based on specific conditions.

[0594] The aforementioned specific UE capabilities can also indicate support for the aforementioned specific processing / operation / control / concept / information.

[0595] Furthermore, the aforementioned specific UE capabilities can be capabilities that apply across all frequencies (frequency-independent and common), capabilities that apply to each frequency (e.g., one or a combination of cells, bands, band combinations, BWPs, component carriers, etc.), capabilities that apply to each frequency range (e.g., Frequency Range 1 (FR1)), FR2, FR3, FR4, FR5, FR2-1, FR2-2), capabilities that apply to each subcarrier spacing (SCS) or capabilities that apply to each feature set (FS) or each feature set per component carrier (FSPC).

[0596] Furthermore, the aforementioned specific UE capabilities can be either capabilities that apply to all duplex modes (commonly regardless of the duplex mode) or capabilities that apply to each duplex mode (e.g., Time Division Duplex (TDD) and Frequency Division Duplex (FDD)).

[0597] If the above conditions are not met, the UE / BS may also follow the operations specified in the existing 3GPP version.

[0598] (Postscript)

[0599] With respect to one embodiment of this disclosure, the following invention is noted.

[0600] [Postscript 1]

[0601] A terminal includes: a receiving unit for receiving setting information for data collection in location based on artificial intelligence (AI); and a control unit for controlling the execution of at least one of the following: inference, learning, and training of a model, and at least one of the following: a report related to at least one of the inference, learning, and training, based on parameters indicating the purpose or the state of a model process contained in the setting information.

[0602] [Postscript 2]

[0603] As described in Appendix 1, the control unit is designed so that the setting information does not contain the specific parameter when the parameter represents a specific value.

[0604] [Postscript 3]

[0605] As described in Appendix 1 or Appendix 2, the receiving unit receives instructions related to the execution of post-processing for the measurement results.

[0606] [Postscript 4]

[0607] The terminal as described in any one of Annexes 1 to 3, wherein the control unit performs control to determine whether the reported position information is generated by an AI model.

[0608] (Wireless communication system)

[0609] The structure of a wireless communication system according to one embodiment of this disclosure will now be described. In this wireless communication system, communication is performed using any one or a combination of the wireless communication methods according to the above embodiments of this disclosure.

[0610] Figure 18 This is a diagram illustrating an example of the schematic structure of a wireless communication system according to one embodiment. The wireless communication system 1 (also referred to simply as System 1) may also be a system that uses Long Term Evolution (LTE) or 5th generation mobile communication system New Radio (5G NR) as standardized by the Third Generation Partnership Project (3GPP) to achieve communication.

[0611] Furthermore, the wireless communication system 1 can also support dual connectivity between multiple radio access technologies (RATs) (Multi-RAT Dual Connectivity (MR-DC)). MR-DC can 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)), etc.

[0612] 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.

[0613] Wireless communication system 1 can also support dual connectivity between multiple base stations within the same RAT (e.g., MN and SN are dual connectivity between NR base stations (gNB) (NR-NR Dual Connectivity (NN-DC))).

[0614] The wireless communication system 1 may also include a base station 11 forming a macro cell C1 with a relatively wide coverage area, and a base station 12 (12a-12c) configured within the macro cell C1 and forming a small cell C2 narrower than the macro cell C1. The user terminal 20 may also be located within at least one cell. The configuration, number, shape, size, etc., of each cell and the user terminal 20 are not limited to the manner shown in the figure. Hereinafter, without distinguishing between base stations 11 and 12, they will be collectively referred to as base station 10.

[0615] Alternatively, the wireless communication system 1 can also utilize Multiple Input Multiple Output (MIMO). For example, a cell can be formed by one antenna / base station 10 or by multiple antennas / base stations 10. A [virtual] cell (e.g., also called a super cell) can also be composed of multiple [virtual] cells (e.g., also called sub-cells). A super cell can also be equivalent to a cell with a fixed physical range, and a sub-cell can also be equivalent to a cell with a semi-static / dynamically varying physical range. In this case, the wireless communication system 1 can also be called a cell-free system.

[0616] User terminal 20 may also connect to at least one of multiple base stations 10. User terminal 20 may also utilize at least one of carrier aggregation (CA) using multiple component carriers (CC) and dual connectivity (DC).

[0617] Each CC can also be included in at least one of the first frequency band (Frequency Range 1 (FR1)) and the second frequency band (Frequency Range 2 (FR2)). Macro cell C1 can also be included in FR1, and small cell C2 can also be included in FR2. For example, FR1 can also be a frequency band below 6 GHz (sub-6 GHz), and FR2 can also be a frequency band above 24 GHz (above-24 GHz). In addition, the frequency bands, definitions, etc. of FR1 and FR2 are not limited to these; for example, FR1 can also be equivalent to a frequency band higher than FR2.

[0618] In addition, in each CC, the user terminal 20 may also use at least one of Time Division Duplex (TDD) and Frequency Division Duplex (FDD) for communication.

[0619] Multiple base stations 10 can also be connected via wired (e.g., fiber optic cable based on the Common Public Radio Interface (CPRI), X2 / Xn interface, etc.) or wireless (e.g., NR communication). For example, when NR communication is used as a backhaul between base stations 11 and 12, base station 11, which is equivalent to a host station, can also be referred to as an Integrated Access Backhaul (IAB) donor, and base station 12, which is equivalent to a relay station, can also be referred to as an IAB node.

[0620] Base station 10 may also be connected to core network 30 via other base stations 10 or directly. Core network 30 may include, for example, at least one of Evolved Packet Core (EPC), 5G Core Network (5GCN), Next Generation Core (NGC), etc.

[0621] The core network 30 may also include, for example, user plane functions (UPF), access and mobility management functions (AMF), session management functions (SMF), unified data management (UDM), application functions (AF), data network (DN), location management functions (LMF), and network functions (NF) such as operation, administration and maintenance (OAM). Alternatively, multiple functions can be provided through a single network node. Furthermore, communication with external networks (e.g., the Internet) can also be achieved via the DN.

[0622] User terminal 20 can also be a terminal that supports at least one of the following communication methods: LTE, LTE-A, 5G, etc.

[0623] In wireless communication system 1, wireless access methods based on Orthogonal Frequency Division Multiplexing (OFDM) can also be used. For example, in at least one of the downlink (DL) and uplink (UL) links, Cyclic Prefix OFDM (CP-OFDM), Discrete Fourier Transform Spread OFDM (DFT-s-OFDM), Orthogonal Frequency Division Multiple Access (OFDMA), and Single Carrier Frequency Division Multiple Access (SC-FDMA) can also be used.

[0624] The wireless access method can also be referred to as a waveform. In addition, in the wireless communication system 1, other wireless access methods (e.g., other single-carrier transmission methods, other multi-carrier transmission methods) can also be used in the wireless access methods of UL and DL.

[0625] In the wireless communication system 1, the downlink channel can also be a shared downlink channel (Physical Downlink Shared Channel (PDSCH)), a broadcast channel (Physical Broadcast Channel (PBCH)), or a downlink control channel (Physical Downlink Control Channel (PDCCH)) shared by each user terminal 20.

[0626] In addition, in the wireless communication system 1, the uplink channel can also be the shared uplink channel (Physical Uplink Shared Channel (PUSCH)), the uplink control channel (Physical Uplink Control Channel (PUCCH)), the random access channel (Physical Random Access Channel (PRACH)) shared by each user terminal 20, etc.

[0627] Additionally, base station 10 can be separated into three elements: Radio Unit (RU), Distributed Unit (DU), and Central Unit (CU). For example, the RU can implement RF processing (digital beamforming, digital-to-analog conversion, analog beamforming, etc.) and lower-level physical layer functions (precoding, IFFT, FFT, etc.). The DU can implement higher-level physical layer functions (from coding to resource element mapping, etc.), MAC layer functions, and RLC layer functions. The CU can also implement PDCP layer, Service Data Adaptation Protocol (SDAP) layer, and RRC layer functions.

[0628] In this disclosure, base station 10 may include a device that implements all the functions of RU, DU, and CU, or it may include multiple devices that implement a portion of the functions of RU, DU, and CU respectively and are interconnected. In this disclosure, base station 10 may also be rewritten in relation to RU / DU / CU.

[0629] User data, high-level control information, and System Information Blocks (SIBs) are transmitted via the PDSCH. User data and high-level control information can also be transmitted via the PUSCH. In addition, Master Information Blocks (MIBs) can also be transmitted via the PBCH.

[0630] Lower-layer control information can also be transmitted via PDCCH. This lower-layer control information may include, for example, downlink control information (DCI), which includes scheduling information for at least one of PDSCH and PUSCH.

[0631] Additionally, the DCI that schedules PDSCH can also be called DL allocation, DL DCI, etc., and the DCI that schedules PUSCH can also be called UL authorization, UL DCI, etc. Furthermore, PDSCH can be rewritten as DL data, and PUSCH can be rewritten as UL data.

[0632] In PDCCH detection, a Control Resource Set (CORESET) and a search space can be utilized. A CORESET corresponds to the resources used to search for DCIs. The search space corresponds to the search area and search method for PDCCH candidates. A CORESET can also be associated with one or more search spaces. The UE can also monitor CORESETs associated with a specific search space based on search space settings.

[0633] A search space can also correspond to one or more PDCCH candidates equivalent to one or more aggregation levels. One or more search spaces can also be referred to as a search space set. In addition, the terms "search space", "search space set", "search space setting", "search space set setting", "CORESET", and "CORESET setting" in this disclosure can be rewritten interchangeably.

[0634] The PUCCH can also transmit uplink control information (uplink control information (UCI)) that includes at least one of the following: Channel State Information (CSI), delivery confirmation information (e.g., also known as Hybrid Automatic Repeat Request ACK Knowledge (HARQ-ACK), ACK / NACK, etc.), and Scheduling Request (SR). The PRACH can also transmit random access preambles used for establishing connections with the cell.

[0635] In addition, in this disclosure, downlink, uplink, etc., may be described without the word "link". Furthermore, various channels may be described without the word "physical".

[0636] In wireless communication system 1, synchronization signals (SS) and downlink reference signals (DL-RS) can also be transmitted. In wireless communication system 1, DL-RS can also transmit cell-specific reference signals (CRS), channel state information reference signals (CSI-RS), demodulation reference signals (DMRS), positioning reference signals (PRS), and phase tracking reference signals (PTRS).

[0637] Synchronization signals can be, for example, at least one of a primary synchronization signal (PSS) and a secondary synchronization signal (SSS). A signal block containing SS (PSS, SSS) and PBCH (and DMRS for PBCH) can also be called an SS / PBCH block, SS block (SSB), etc. In addition, SS, SSB, etc. can also be called reference signals.

[0638] Furthermore, in wireless communication system 1, the uplink reference signal (UL-RS) can also transmit measurement reference signals (sounding reference signals (SRS)) and demodulation reference signals (DMRS). Additionally, DMRS can also be referred to as user terminal-specific reference signals (UE-specific reference signals).

[0639] (Base station)

[0640] Figure 19 This diagram illustrates an example of the structure of a base station according to one embodiment. The base station 10 includes a control unit 110, a transmit / receive unit 120, a transmit / receive antenna 130, and a transmission path interface (transmission line interface) 140. Alternatively, the control unit 110, the transmit / receive unit 120, the transmit / receive antenna 130, and the transmission path interface 140 may each be provided in more than one manner.

[0641] Furthermore, while this example primarily illustrates the functional blocks of the characteristic portions of this embodiment, it is also conceivable that the base station 10 may also possess other functional blocks required for wireless communication. A portion of the processing of each unit described below may also be omitted.

[0642] The control unit 110 performs overall control of the base station 10. The control unit 110 can be composed of a controller, control circuit, etc., which are described based on common knowledge in the art to which this disclosure pertains.

[0643] The control unit 110 can also control signal generation and scheduling (e.g., resource allocation, mapping). The control unit 110 can also control transmission, reception, and measurement using the transmit / receive unit 120, transmit / receive antenna 130, and transmission path interface 140. The control unit 110 can also generate data, control information, sequences, etc., to be transmitted as signals and forward them to the transmit / receive unit 120. The control unit 110 can also perform call processing (setting, releasing, etc.) of the communication channel, status management of the base station 10, and management of wireless resources.

[0644] The transmitting / receiving unit 120 may also include a baseband unit 121, a radio frequency (RF) unit 122, and a measurement unit 123. The baseband unit 121 may also include a transmitting processing unit 1211 and a receiving processing unit 1212. The transmitting / receiving unit 120 may be composed of transmitters / receivers, RF circuits, baseband circuits, filters, phase shifters, measurement circuits, transmitting / receiving circuits, etc., as described based on common knowledge in the art to which this disclosure pertains.

[0645] The transmitting and receiving unit 120 can be configured as a single integrated transmitting and receiving unit, or it can be composed of a transmitting unit and a receiving unit. The transmitting unit can also be composed of a transmitting processing unit 1211 and an RF unit 122. The receiving unit can also be composed of a receiving processing unit 1212, an RF unit 122, and a measurement unit 123.

[0646] The transmitting and receiving antenna 130 can be constructed from an antenna, such as an array antenna, as described based on common knowledge in the art to which this disclosure pertains.

[0647] The transmitting / receiving unit 120 can also transmit the aforementioned downlink channel, synchronization signal, downlink reference signal, etc. The transmitting / receiving unit 120 can also receive the aforementioned uplink channel, uplink reference signal, etc.

[0648] The transmitting and receiving unit 120 may also use digital beamforming (e.g., precoding), analog beamforming (e.g., phase rotation), etc., to form at least one of the transmitting beam and the receiving beam.

[0649] The transmitting and receiving unit 120 (transmitting processing unit 1211) may, for example, perform processing at the Packet Data Convergence Protocol (PDCP) layer, Radio Link Control (RLC) layer (e.g., RLC retransmission control), and Medium Access Control (MAC) layer (e.g., HARQ retransmission control) on the data and control information obtained from the control unit 110, and generate a bit string to be transmitted.

[0650] The transmitting and receiving unit 120 (transmitting processing unit 1211) can 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, and digital-to-analog conversion on the bit string to be transmitted, and output the baseband signal.

[0651] The transmitting and receiving unit 120 (RF unit 122) can also perform modulation, filtering, amplification, etc. on the baseband signal to the wireless frequency band, and transmit the wireless frequency band signal through the transmitting and receiving antenna 130.

[0652] On the other hand, the transmitting and receiving unit 120 (RF unit 122) can also amplify, filter, and demodulate the signals of the wireless frequency band received through the transmitting and receiving antenna 130 into the baseband signal.

[0653] The transmitting and receiving unit 120 (receiving and processing unit 1212) can also perform receiving and processing on the acquired baseband signal, including analog-to-digital conversion, Fast Fourier Transform (FFT) processing, Inverse Discrete Fourier Transform (IDFT) processing (as needed), filter processing, demapping, demodulation, decoding (which may also include error correction decoding), MAC layer processing, RLC layer processing, and PDCP layer processing, to acquire user data, etc.

[0654] The transmitting / receiving unit 120 (measurement unit 123) can also perform measurements related to the received signal. For example, the measurement unit 123 can also perform radio resource management (RRM) measurements, channel state information (CSI) measurements, etc., based on the received signal. The measurement unit 123 can also measure received power (e.g., Reference Signal Received Power (RSRP)), received quality (e.g., Reference Signal Received Quality (RSRQ), Signal to Interference plus Noise Ratio (SINR), Signal to Noise Ratio (SNR)), signal strength (e.g., Received Signal Strength Indicator (RSSI)), propagation path information (e.g., CSI), etc. The measurement results can also be output to the control unit 110.

[0655] The transmission path interface 140 can also transmit and receive signals (backhaul signaling) between the device included in the core network 30 (e.g., the network node providing the NF), other base stations 10, etc., and can also acquire and transmit user data (user plane data), control plane data, etc. for the user terminal 20.

[0656] In addition, the transmitting unit and receiving unit of the base station 10 in this disclosure may also be composed of at least one of a transmitting / receiving unit 120, a transmitting / receiving antenna 130, and a transmission path interface 140.

[0657] Additionally, base station 10 can be separated into three elements: Radio Unit (RU), Distributed Unit (DU), and Central Unit (CU). For example, the RU can implement RF processing (digital beamforming, digital-to-analog conversion, analog beamforming, etc.) and lower-level physical layer functions (precoding, IFFT, FFT, etc.). The DU can implement higher-level physical layer functions (from coding to resource element mapping, etc.), MAC layer functions, and RLC layer functions. The CU can also implement PDCP layer, Service Data Adaptation Protocol (SDAP) layer, and RRC layer functions.

[0658] In this disclosure, base station 10 may include a device that implements all the functions of RU, DU, and CU, or it may include multiple devices that implement a portion of the functions of RU, DU, and CU respectively and are interconnected. In this disclosure, base station 10 may also be rewritten in relation to RU / DU / CU.

[0659] The transmitting and receiving unit 120 can also transmit setting information for data collection in location based on artificial intelligence (AI). The control unit 110 can also use the parameters indicating the purpose or the state of the model process contained in the setting information to instruct at least one of the following (first embodiment): the execution of at least one of the model's inference, learning, and training, and a report related to at least one of the inference, learning, and training.

[0660] (User terminal)

[0661] Figure 20 This diagram illustrates an example of the structure 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. Alternatively, more than one of each of the control unit 210, the transmitting / receiving unit 220, and the transmitting / receiving antenna 230 may be included.

[0662] Furthermore, while this example primarily illustrates the functional blocks of the characteristic portions of this embodiment, it is also conceivable that the user terminal 20 may also have other functional blocks required for wireless communication. Some of the processing of each unit described below may also be omitted.

[0663] The control unit 210 performs overall control of the user terminal 20. The control unit 210 can be composed of a controller, control circuit, etc., which are described based on common knowledge in the technical field to which this disclosure pertains.

[0664] The control unit 210 can also control signal generation, mapping, etc. The control unit 210 can also control transmission, reception, measurement, etc., using the transmission / reception unit 220 and the transmission / reception antenna 230. The control unit 210 can also generate data, control information, sequences, etc., to be transmitted as signals and forward them to the transmission / reception unit 220.

[0665] The transmitting / receiving 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 transmitting processing unit 2211 and a receiving processing unit 2212. The transmitting / receiving unit 220 may be composed of transmitters / receivers, RF circuits, baseband circuits, filters, phase shifters, measurement circuits, transmitting / receiving circuits, etc., as described based on common knowledge in the art to which this disclosure pertains.

[0666] The transmitting and receiving unit 220 can be configured as a single integrated transmitting and receiving unit, or it can be composed of a transmitting unit and a receiving unit. The transmitting unit can also be composed of a transmitting processing unit 2211 and an RF unit 222. The receiving unit can also be composed of a receiving processing unit 2212, an RF unit 222, and a measurement unit 223.

[0667] The transmitting and receiving antenna 230 can be constructed from an antenna, such as an array antenna, as described based on common knowledge in the art to which this disclosure pertains.

[0668] The transmitting / receiving unit 220 can also receive the downlink channel, synchronization signal, downlink reference signal, etc., mentioned above. The transmitting / receiving unit 220 can also transmit the uplink channel, uplink reference signal, etc., mentioned above.

[0669] The transmitting and receiving unit 220 may also use digital beamforming (e.g., precoding), analog beamforming (e.g., phase rotation), etc., to form at least one of the transmitting beam and the receiving beam.

[0670] The transmitting and receiving unit 220 (transmitting processing unit 2211) may, for example, perform PDCP layer processing, RLC layer processing (e.g., RLC retransmission control), MAC layer processing (e.g., HARQ retransmission control) on the data and control information obtained from the control unit 210, and generate the bit string to be transmitted.

[0671] The transmitting and receiving unit 220 (transmitting processing unit 2211) can also perform channel coding (which may include error correction coding), modulation, mapping, filter processing, DFT processing (as needed), IFFT processing, precoding, digital-to-analog conversion and other transmission processing on the bit string to be transmitted, and output the baseband signal.

[0672] Furthermore, the decision to apply DFT processing can be based on the transform precoding settings. For a specific channel (e.g., PUSCH), if transform precoding is enabled, the transmit / receive unit 220 (transmit processing unit 2211) can perform DFT processing as described above for transmitting the channel using the DFT-s-OFDM waveform; otherwise, the transmit / receive unit 220 (transmit processing unit 2211) can perform DFT processing as described above for transmitting the channel without performing DFT processing.

[0673] The transmitting and receiving unit 220 (RF unit 222) can also perform modulation, filtering, amplification, etc. on the baseband signal to the wireless frequency band, and transmit the wireless frequency band signal through the transmitting and receiving antenna 230.

[0674] On the other hand, the transmitting and receiving unit 220 (RF unit 222) can also amplify, filter, demodulate, etc., the signals of the wireless frequency band received by the transmitting and receiving antenna 230.

[0675] The transmitting and receiving unit 220 (receiving and processing unit 2212) can also perform receiving and processing on the acquired baseband signal, such as analog-to-digital conversion, FFT processing, IDFT processing (as needed), filter processing, demapping, demodulation, decoding (which may also include error correction decoding), MAC layer processing, RLC layer processing, and PDCP layer processing, to obtain user data.

[0676] The transmitting / receiving unit 220 (measurement unit 223) can also perform measurements related to the received signal. For example, the measurement unit 223 can also perform RRM measurements, CSI measurements, etc., based on the received signal. The measurement unit 223 can 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 can also be output to the control unit 210.

[0677] Additionally, the measurement unit 223 can also derive channel measurements for CSI calculation based on channel measurement resources. Channel measurement resources can be, for example, non-zero power (NZP) CSI-RS resources. Furthermore, the measurement unit 223 can also derive interference measurements for CSI calculation based on interference measurement resources. Interference measurement resources can be at least one of NZP CSI-RS resources for interference measurement, CSI-Interference Measurement (IM) resources, etc. Additionally, CSI-IM can also be referred to as CSI-Interference Management (IM), and can be interchanged with zero power (ZP) CSI-RS. Furthermore, in this disclosure, CSI-RS, NZP CSI-RS, ZP CSI-RS, CSI-IM, CSI-SSB, etc., can also be interchanged.

[0678] Alternatively, the transmitting and receiving units of the user terminal 20 in this disclosure may also be composed of at least one transmitting / receiving unit 220 and transmitting / receiving antenna 230.

[0679] The transmitting and receiving unit 220 can also receive setting information for data collection in location based on artificial intelligence (AI). The control unit 210 can also control the execution of at least one of the following (first embodiment): the inference, learning, and training of the model, and reports related to at least one of the inference, learning, and training, based on parameters indicating the purpose or the state of the model process contained in the setting information.

[0680] When the parameter represents a specific value, the control unit 210 may also be conceived as not including the specific parameter in the setting information (first embodiment).

[0681] The transmitting and receiving unit 220 can also receive instructions related to the execution of post-processing for the measurement results (second embodiment).

[0682] The control unit 210 can also control whether the reported measurement information is generated by the AI ​​model (third embodiment).

[0683] (Hardware structure)

[0684] Furthermore, the block diagrams used in the description of the above embodiments illustrate functional units. These functional blocks (structural units) are implemented through any combination of at least one of hardware and software. Moreover, the implementation method of each functional block is not particularly limited. That is, each functional block can be implemented using a single device that is physically or logically combined, or it can be implemented by directly or indirectly (e.g., using wired, wireless, etc.) connecting two or more physically or logically separate devices. A functional block can also be implemented by combining the aforementioned single device or multiple devices with software.

[0685] Here, the functions include judgment, decision, determination, calculation, calculation, processing, export, investigation, search, confirmation, receiving, sending, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, regard as, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assigning, but are not limited to these. For example, a functional block (structural unit) that implements the sending function can also be called a transmitting unit, transmitter, etc. As described above, the implementation method of any of them is not particularly limited.

[0686] For example, in one embodiment of this disclosure, the base station, user terminal, etc., can also function as a computer for processing the wireless communication method of this disclosure. Figure 21 This is a diagram illustrating an example of the hardware structure 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 device 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0687] Furthermore, in this disclosure, terms such as apparatus, circuit, device, section, and unit can be interchanged. The hardware structure of base station 10 and user terminal 20 can be configured to include one or more of the apparatuses shown in the figures, or it can be configured not to include any of the apparatuses.

[0688] For example, only one processor 1001 is shown, but there can be multiple processors. Furthermore, processing can be performed by one processor, or simultaneously, sequentially, or by two or more processors using other methods. Additionally, processor 1001 can be implemented using more than one chip.

[0689] The functions of the base station 10 and the user terminal 20 are implemented, for example, by reading specific software (programs) 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 device 1003.

[0690] The processor 1001, for example, enables the operating system to operate and control the computer as a whole. The processor 1001 may also be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic devices, registers, etc. For example, at least a portion of the control unit 110 (210), the transmit / receive unit 120 (220), etc., described above may also be implemented by the processor 1001.

[0691] 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 performs various processes accordingly. As a program, a program that causes the computer to perform at least a portion of the operations described in the above embodiments can be used. For example, the control unit 110 (210) can also be implemented by a control program stored in the memory 1002 and operated in the processor 1001; similar implementations can be made for other functional blocks.

[0692] The memory 1002 may also be a computer-readable recording medium, such as being composed of at least one of a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a random access memory (RAM), or other suitable storage media. The memory 1002 may also be referred to as a register, cache, main memory (main storage device), etc. The memory 1002 is capable of storing executable programs (program code), software modules, etc., for implementing the wireless communication method according to an embodiment of this disclosure.

[0693] Storage device 1003 may also be a computer-readable recording medium, such as a flexible disc, floppy disk, optical disk (e.g., compact disc ROM, CD-ROM), digital multifunction disk, Blu-ray disc, removable disk, hard disk, smart card, flash memory device (e.g., card, stick, key drive), stripe, database, server, or at least one other suitable storage medium. Storage device 1003 may also be referred to as an auxiliary storage device.

[0694] The communication device 1004 is hardware (transmitting and receiving device) used for communication between computers via at least one of a wired network and a wireless network. It is also referred to as a network device, network controller, network interface card (NIC), communication module, etc. To implement at least one of, for example, Frequency Division Duplex (FDD) and Time Division Duplex (TDD), the communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. For example, the aforementioned transmit / receive unit 120 (220) and transmit / receive antenna 130 (230) may also be implemented by the communication device 1004. The transmit / receive unit 120 (220) may also be implemented by physically or logically separating the transmit unit 120a (220a) and the receive unit 120b (220b).

[0695] Input device 1005 is an input device that receives input from external sources (e.g., keyboard, mouse, microphone, switch, button, sensor, etc.). Output device 1006 is an output device that performs output to external sources (e.g., display, speaker, light-emitting diode (LED) lamp, etc.). Alternatively, input device 1005 and output device 1006 can also be an integrated structure (e.g., a touch panel).

[0696] Furthermore, the processor 1001, memory 1002, and other devices are connected via a bus 1007 for communicating information. The bus 1007 can be configured as a single bus or as different buses between the devices.

[0697] Furthermore, the base station 10 and the user terminal 20 can 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 can also use this hardware to implement part or all of the functional blocks. For example, the processor 1001 can also be implemented using at least one of these hardware components.

[0698] In addition, the devices included in the core network 30 (e.g., network nodes that provide NF) can also be implemented through the functional block / hardware structure described above.

[0699] (Variation example)

[0700] Furthermore, the terms described in this disclosure, as well as those necessary for understanding this disclosure, may be replaced with terms that have the same or similar meanings. For example, channel, symbol, and signal (signal or signaling) may be interchanged. Additionally, a signal may also be a message. A reference signal can also be abbreviated as RS, and may be referred to as pilot, pilot signal, etc., depending on the applied standard. Furthermore, a component carrier (CC) may also be referred to as cell, frequency carrier, carrier frequency, etc.

[0701] A radio frame can also be composed of one or more periods (frames) in the time domain. Each of these periods (frames) that constitute 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 (e.g., 1 ms) independent of the parameter set (numerology).

[0702] Here, the parameter set can also be communication parameters applied in at least one of the transmission and reception of a signal or channel. For example, the parameter set can also represent at least one of the following: subcarrier spacing (SCS), bandwidth, symbol length, cyclic prefix length, transmission time interval (TTI), number of symbols per TTI, radio frame 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.

[0703] In the time domain, a time 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.). In addition, a time slot can also be a time unit based on a set of parameters.

[0704] A time slot can also contain multiple mini-time slots. Each mini-time slot can also consist of one or more symbols in the time domain. Furthermore, a mini-time slot can also be called a sub-time slot. A mini-time slot can also consist of fewer symbols than a time slot. PDSCH (or PUSCH) transmitted in a time unit larger than a mini-time slot can also be called PDSCH (PUSCH) mapping type A. PDSCH (or PUSCH) transmitted using mini-time slots can also be called PDSCH (PUSCH) mapping type B.

[0705] Radio frames, subframes, time slots, mini-time slots, and symbols all represent time units for transmitting signals. Radio frames, subframes, time slots, mini-time slots, and symbols can also use their respective other names. Furthermore, the time units such as frames, subframes, time slots, mini-time slots, and symbols in this disclosure can be interchanged.

[0706] For example, a subframe can also be called a TTI, multiple consecutive subframes can also be called a TTI, and a time slot or a mini-time slot can also be called a TTI. That is, at least one of a subframe and a TTI can be a subframe in existing LTE (1ms), a period shorter than 1ms (e.g., 1-13 symbols), or a period longer than 1ms. In addition, the unit representing TTI may not be called a subframe, but rather a time slot, mini-time slot, etc.

[0707] Here, TTI refers, for example, to the smallest unit of time for scheduling in wireless communication. For instance, in an LTE system, the base station schedules radio resources (frequency bandwidth, transmit power, etc., available to each user terminal) in TTI units. However, the definition of TTI is not limited to this.

[0708] TTI can also be a unit of time for transmitting channel-coded data packets (transmission blocks), code blocks, codewords, etc., and can also be a unit of processing such as scheduling and link adaptation. In addition, when a TTI is given, the actual time interval (e.g., the number of symbols) mapped to transmission blocks, code blocks, codewords, etc. can be shorter than the TTI.

[0709] Additionally, where a time slot or a mini-time slot is referred to as a TTI, more than one TTI (i.e., more than one time slot or more than one mini-time slot) can also be the minimum time unit for scheduling. Furthermore, the number of time slots (mini-time slots) constituting the minimum time unit of the schedule can also be controlled.

[0710] A TTI with a duration of 1 ms can 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 can also be referred to as a shortened TTI, a short TTI, a partial TTI (partial or fractional TTI), a shortened subframe, a short subframe, a mini time slot, a sub-time slot, a time slot, etc.

[0711] In addition, a long TTI (e.g., a normal TTI, a subframe, etc.) can also be rewritten as a TTI with a duration of more than 1 ms, and a short TTI (e.g., a shortened TTI, etc.) can also be rewritten as a TTI with a duration of less than a long TTI but more than 1 ms.

[0712] A resource block (RB) is a unit of resource allocation in both the time and frequency domains. In the frequency domain, it can also contain one or more consecutive subcarriers. The number of subcarriers in an RB can be the same regardless of the parameter set, for example, it can be 12. The number of subcarriers in an RB can also be determined based on the parameter set.

[0713] Furthermore, an RB can contain one or more symbols in the time domain, and can also be a time slot, a mini-time slot, a subframe, or the length of a TTI. A TTI, a subframe, etc., can also be composed of one or more resource blocks.

[0714] In addition, one or more RBs can also be referred to as Physical Resource Blocks (PRBs), Sub-Carrier Groups (SCGs), Resource Element Groups (REGs), PRB pairs, RB pairs, etc.

[0715] Furthermore, a resource block can also consist of one or more resource elements (REs). For example, an RE can also be a radio resource area consisting of a subcarrier and a symbol.

[0716] The Bandwidth Part (BWP) (also referred to as partial bandwidth, etc.) can also represent a subset of consecutive common resource blocks (RBs) used for a certain parameter set in a carrier. Here, common RBs can also be determined by the index of RBs based on the common reference point of the carrier. PRBs can also be defined in a BWP and appended with numbers within that BWP.

[0717] A BWP can also include a UL BWP (the BWP used by UL) and a DL BWP (the BWP used by DL). For a UE, one or more BWPs can also be set within a single carrier.

[0718] At least one of the configured BWPs can be active, and the UE may not intend to transmit or receive specific signals / channels outside of the active BWPs. Furthermore, the terms "cell," "carrier," etc., in this disclosure can be rewritten as "BWP."

[0719] Furthermore, the structures described above, such as radio frames, subframes, time slots, mini-time slots, and symbols, are merely illustrative. For example, the number of subframes contained in a radio frame, the number of time slots in each subframe or radio frame, the number of mini-time slots contained within a time slot, the number of symbols and RBs contained in a time slot or mini-time slot, the number of subcarriers contained in an RB, and the number of symbols in a TTI, symbol length, and cyclic prefix (CP) length can be varied in many ways.

[0720] Furthermore, the information, parameters, etc., described in this disclosure can be represented by absolute values, relative values ​​with respect to a specific value, or other corresponding information. For example, wireless resources can also be indicated by a specific index.

[0721] In this disclosure, the names used for parameters, etc., are not limiting names in any respect. Furthermore, the mathematical expressions, etc., using 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 name; therefore, the various names assigned to these various channels and information elements are not limiting names in any respect.

[0722] The information, signals, etc., described in this disclosure can also be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc., which may be mentioned throughout the above description, can also be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any combination thereof.

[0723] Furthermore, information, signals, etc., can be output in at least one of the following directions: from higher level (upper layer) to lower level (lower layer), and from lower layer to higher level. Information, signals, etc., can also be input and output via multiple network nodes.

[0724] 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.

[0725] Regarding any information (e.g., variables, constants, parameters) recorded in this disclosure, even if not specifically explicitly stated in the above embodiments, information representing / determining the value of such arbitrary information (or information associated with such arbitrary information) can be notified from any first device (e.g., UE / base station) to any second device (e.g., base station / UE).

[0726] The notification of information is not limited to the methods / implementations described in this disclosure, and may also be carried out by other methods. For example, the notification of information in this disclosure may also be implemented by physical layer signaling (e.g., downlink control information (DCI), uplink control information (UCI), etc.), 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 combinations thereof.

[0727] In addition, physical layer signaling can also be referred to as Layer 1 / Layer 2 (L1 / L2) control information (L1 / L2 control signals), L1 control information (L1 control signals), etc. Furthermore, RRC signaling can also be referred to as RRC messages, such as RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc. Additionally, MAC signaling can also be notified using, for example, a MAC Control Element (CE).

[0728] Furthermore, notification of specific information (e.g., a notification of “is X”) is not limited to explicit notification, but can also be implicit (e.g., by not providing that specific information, or by providing other information).

[0729] The determination can be made by a value represented by a single bit (0 or 1), by a true or false value (boolean), or by a numerical comparison (e.g., a comparison with a specific value).

[0730] Whether software is called software, firmware, middleware, microcode, hardware description language, or any other name, it should be broadly interpreted to refer to instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc.

[0731] Furthermore, software, instructions, and information can also be sent and received via a transmission medium. For example, when software is sent from a website, server, or other remote source using at least one of wired technologies (coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL) etc.) and wireless technologies (infrared, microwave, etc.), at least one of these wired and wireless technologies is included within the definition of a transmission medium.

[0732] The terms “system” and “network” as used in this disclosure are interchangeable. “Network” may also mean devices included in a network (e.g., base stations).

[0733] In this disclosure, the terms “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”, “beamwidth”, “beam angle”, “antenna”, “antenna element”, “panel”, “UE panel”, “transmitting entity”, and “receiving entity” are used interchangeably.

[0734] Furthermore, in this disclosure, the antenna port can also be rewritten with an antenna port used for any signal / channel (e.g., a DeModulation Reference Signal (DMRS) port). In this disclosure, resources can also be rewritten with resources used for any signal / channel (e.g., reference signal resources, SRS resources, etc.). Additionally, resources can also include time / frequency / code / spatial / power resources. Moreover, the spatial domain transmission filter can also include at least one of a spatial domain transmission filter and a spatial domain reception filter.

[0735] The aforementioned groups may include, for example, at least one of the following: spatial relation group, code division multiplexing (CDM) group, reference signal (RS) group, control resource set (CORESET) group, PUCCH group, antenna port group (e.g., DMRS port group), layer group, resource group, beam group, antenna group, panel group, etc.

[0736] Furthermore, in this disclosure, beam, SRS Resource Indicator (SRI), CORESET, CORESET pool, PDSCH, PUSCH, Codeword (CW), Transport Block (TB), RS, etc., can also be rewritten to each other.

[0737] Furthermore, in this disclosure, the TCI state, downlink TCI state (DL TCI state), uplink TCI state (UL TCI state), unified TCI state, common TCI state, and joint TCI state can also be rewritten to each other.

[0738] Furthermore, in this disclosure, terms such as "QCL", "QCL concept", "QCL relationship", "QCL type information", "QCL property (QCLproperty / properties)", "specific QCL type (e.g., type A, type D) property", and "specific QCL type (e.g., type A, type D)" can be rewritten interchangeably.

[0739] In this disclosure, indexes, identifiers (IDs), indicators, indications, resource IDs, etc., can also be interchanged. In this disclosure, sequences, lists, sets, groups, clusters, subsets, etc., can also be interchanged.

[0740] Furthermore, the spatial relationship information identifier (ID) (TCI state ID) and the spatial relationship information (TCI state) can be interchanged. "Spatial relationship information (TCI state)" can also be interchanged with "a set of spatial relationship information (TCI states)," "one or more spatial relationship information," etc. TCI state and TCI can also be interchanged. Spatial relationship information and spatial relationship can also be interchanged.

[0741] In this disclosure, the terms "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. There are also instances where the terms macro cell, small cell, femtocell, and picocell are used to refer to a base station.

[0742] A base station can accommodate one or more (e.g., three) cells. When a base station accommodates multiple cells, the overall coverage area of ​​the base station can be divided into multiple smaller areas, each of which can also provide communication services through a base station subsystem (e.g., a small indoor base station (Remote Radio Head (RRH))). Terms such as "cell" or "sector" refer to a portion or all of the coverage area of ​​at least one of the base station and base station subsystem providing communication services within that coverage area.

[0743] In this disclosure, the information sent by the base station to the terminal can also be rewritten with the control / operation instructed by the base station to the terminal based on that information.

[0744] In this disclosure, the terms “Mobile Station (MS)”, “user terminal”, “user equipment (UE)”, and “terminal” are used interchangeably.

[0745] There are also instances where mobile stations are referred to as subscriber stations, mobile units, subscriber units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile subscriber stations, access terminals, mobile terminals, wireless terminals, remote terminals, handsets, user agents, mobile clients, clients, or several other appropriate terms.

[0746] At least one of the base station and the mobile station can also be referred to as a transmitting device, a receiving device, a wireless communication device, etc. Additionally, at least one of the base station and the mobile station can also be a device mounted on a moving object, the moving object itself, etc.

[0747] The term "mobile body" refers to a movable object whose speed is arbitrary, including situations where the body is stationary. Examples of such mobile bodies include vehicles, transport vehicles, automobiles, motorcycles, bicycles, connected cars, loading shovels, bulldozers, wheel loaders, dump trucks, forklifts, trains, buses, trolleys, rickshaws, ships (including vessels and other watercraft), airplanes, rockets, satellites, drones, multi-rotor aircraft, quadcopters, balloons, and objects carried on them, but are not limited to these. Furthermore, the mobile body can also be a mobile body that moves autonomously based on operational commands.

[0748] The mobile entity can be a means of transportation (e.g., a vehicle, an airplane, etc.), a mobile entity moving in an unmanned manner (e.g., a drone, an autonomous vehicle, etc.), or a robot (humanized or unmanned). Additionally, 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 also be an Internet of Things (IoT) device such as a sensor.

[0749] Figure 22This figure illustrates an example of a vehicle according to one embodiment. The vehicle 40 includes a drive unit 41, a steering unit 42, an accelerator pedal 43, a brake pedal 44, a gear 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 speed sensor 51, a pressure sensor 52, a vehicle speed sensor 53, an acceleration sensor 54, an accelerator pedal sensor 55, a brake pedal sensor 56, a gear shift lever sensor 57, and an object detection sensor 58), an information service unit 59, and a communication module 60.

[0750] The drive unit 41 is comprised of 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 called a handlebar) and to perform directional control on at least one of the front wheel 46 and the rear wheel 47 based on the operation of the steering wheel by the user.

[0751] The electronic control unit 49 consists of a microprocessor 61, a memory (ROM, RAM) 62, and a communication port (e.g., an input / output (IO) port) 63). Signals from various sensors 50-58 present in the vehicle are input into the electronic control unit 49. The electronic control unit 49 can also be referred to as an ECU (Electronic Control Unit).

[0752] The signals from various sensors 50-58 include current signals from current sensor 50 that senses the current of the motor, speed signals from front wheel 46 / rear wheel 47 obtained by speed sensor 51, air pressure signals from front wheel 46 / rear wheel 47 obtained by air pressure sensor 52, vehicle speed signals obtained by vehicle speed sensor 53, acceleration signals obtained by acceleration sensor 54, accelerator pedal 43 depress amount signals obtained by accelerator pedal sensor 55, brake pedal 44 depress amount signals obtained by brake pedal sensor 56, shift lever 45 operation signals obtained by shift lever sensor 57, and detection signals obtained by object detection sensor 58 for detecting obstacles, vehicles, pedestrians, etc.

[0753] The information service unit 59 comprises various devices such as a vehicle navigation system, audio system, speakers, display, television, and radio, used to provide (output) various information such as driving information, traffic information, and entertainment information, as well as one or more ECUs that control these devices. The information service unit 59 uses information obtained from external devices via the communication module 60, etc., to provide various information / services (e.g., multimedia information / multimedia services) to the occupants of the vehicle 40.

[0754] The information service unit 59 may include input devices that accept input from the outside (e.g., keyboard, mouse, microphone, switch, button, sensor, touch panel, etc.) or output devices that implement output to the outside (e.g., display, speaker, LED light, touch panel, etc.).

[0755] The driver assistance system unit 64 comprises various devices used to provide functions for preventing accidents and reducing the driver's workload, such as millimeter-wave radar, light detection and ranging (LiDAR), cameras, positioning devices (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 Unit (IMU)), Inertial Navigation System (INS)), artificial intelligence (AI) chips, and AI processors, as well as one or more ECUs that control these devices. Furthermore, the driver assistance system unit 64 sends and receives various information via a communication module 60 and implements driver assistance or autonomous driving functions.

[0756] The communication module 60 can communicate with the microprocessor 61 and the structural elements of the vehicle 40 via the communication port 63. For example, the communication module 60 sends and receives data (information) between the microprocessor 61 and the memory (ROM, RAM) 62, and various sensors 50-58 in the drive unit 41, steering control unit 42, accelerator pedal 43, brake pedal 44, gear shift lever 45, left and right front wheels 46, left and right rear wheels 47, axle 48, and electronic control unit 49 of the vehicle 40 via the communication port 63.

[0757] 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, it can transmit and receive various types of information between external devices via wireless communication. The communication module 60 can be located either inside or outside the electronic control unit 49. The external device can be, for example, the aforementioned base station 10, user terminal 20, etc. Furthermore, the communication module 60 can be, for example, at least one of the aforementioned base station 10 and user terminal 20 (or it can function as at least one of the base station 10 and user terminal 20).

[0758] The communication module 60 can also wirelessly transmit at least one of the following to an external device: signals from the various sensors 50-58 described above that are input to the electronic control unit 49, information obtained based on these signals, and information based on input from an external source (user) obtained via the information service unit 59. The electronic control unit 49, the various sensors 50-58, the information service unit 59, etc., can also be referred to as input units that receive input. For example, the PUSCH transmitted via the communication module 60 can also contain information based on the aforementioned input.

[0759] The communication module 60 receives various information (traffic information, traffic light information, vehicle-to-vehicle information, etc.) sent from external devices and displays it to the information service unit 59 provided by the vehicle. The information service unit 59 can also be referred to as an output unit that outputs information (for example, outputs information to devices such as displays and speakers based on the PDSCH received through the communication module 60 (or data / information decoded from the PDSCH).

[0760] Furthermore, the communication module 60 stores various information received from external devices in a memory 62 that can be used by the microprocessor 61. The microprocessor 61 can also control the drive unit 41, steering unit 42, accelerator pedal 43, brake pedal 44, gear shift lever 45, left and right front wheels 46, left and right rear wheels 47, axle 48, and various sensors 50-58 of the vehicle 40 based on the information stored in the memory 62.

[0761] Furthermore, the base station in this disclosure can also be rewritten as a user terminal. For example, various methods / implementations of this disclosure can be applied to structures where communication between the base station and the user terminal is replaced by communication between multiple user terminals (e.g., also referred to as device-to-device (D2D) or vehicle-to-everything (V2X)). In this case, it can also be configured such that the user terminal 20 has the functions of the base station 10 described above. In addition, terms such as "uplink" and "downlink" can be rewritten as terms corresponding to inter-terminal communication (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can also be rewritten as sidelink channel.

[0762] Similarly, the user terminal in this disclosure can also be rewritten as a base station. In this case, it can also be configured such that the base station 10 has the functions of the user terminal 20 described above.

[0763] In this disclosure, operations are assumed to be performed by the base station, and sometimes, depending on the circumstances, by its upper node. Clearly, in a network containing one or more network nodes having a base station, various operations for communication with a terminal can be performed by the base station, one or more network nodes other than the base station (e.g., considering a Mobility Management Entity (MME), a Serving-Gateway (S-GW), etc., but not limited to these), or combinations thereof.

[0764] The various methods / implementations described in this disclosure can be used individually or in combination, and can be switched as needed during execution. Furthermore, the processing procedures, timing sequences, flowcharts, etc., of the various methods / implementations described in this disclosure can be rearranged as long as they do not contradict each other. For example, for the method described in this disclosure, the illustrated order is used to indicate various steps, but the order in which they are indicated is not limited.

[0765] The various methods / implementations described in this disclosure can 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), Futuregeneration radio access (FX), Global System for Mobile Communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE This includes 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-Wideband (UWB)), Bluetooth (registered trademark), systems utilizing other suitable wireless communication methods, and next-generation systems derived from enhancements, modifications, creations, or specifications based on them. Furthermore, multiple systems can be combined (e.g., LTE or LTE-A, combinations with 5G, etc.) for application.

[0766] As used in this disclosure, the term "based on" does not mean "based on only" unless otherwise specified. In other words, the term "based on" means both "based on only" and "based on at least".

[0767] Any reference to an element using the designations "first," "second," etc., as used in this disclosure does not comprehensively limit 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 the first and second elements does not imply that only two elements may be used, or that the first element must take precedence over the second element in some form.

[0768] The term "determining" as used in this disclosure can encompass a wide variety of operations. For example, "determining" can also refer to judging, calculating, computing, processing, deriving, investigating, looking up (search, inquiry) (e.g., searching in a table, database or other data structure), and ascertaining.

[0769] In addition, "judgment (decision)" can also refer to receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, accessing (e.g., accessing data in memory), etc., as situations where "judgment (decision)" is performed.

[0770] Furthermore, "judgment (decision)" can also refer to situations where resolving, selecting, choosing, establishing, or comparing are considered as making a "judgment (decision)". That is, "judgment (decision)" can also refer to certain operations as making a "judgment (decision)". In this disclosure, "judgment (decision)" can also be rewritten in relation to the operations described above.

[0771] Furthermore, in this disclosure, "determine / determining" can also be interchanged with "assume / assuming," "expect / expecting," "consider / considering," etc. Additionally, in this disclosure, "not assuming..." can also be interchanged with "assuming not...".

[0772] In this disclosure, "expect" can also be interchanged with "be expected." For example, "expect(s)..." (where "..." can also be expressed as a that clause, an infinitive to, etc.) can also be interchanged with "be expected..." or "perform..." (in the case of "..." being an infinitive to "to," the verb with "to" removed). "Does not expect..." can also be interchanged with "be not expected..." or "does not perform..." (in the case of "..." being an infinitive to "to," the verb with "to" removed). Furthermore, "An apparatus A is not expected..." can also be interchanged with "Apparatus B other than apparatus A does not expect apparatus A to perform..." (for example, if apparatus A is a UE, apparatus B can also be a base station).

[0773] The term "maximum transmit power" as used in this disclosure may refer to the maximum value of the transmit power, the nominal maximum transmit power (the nominal UE maximum transmit power), or the rated maximum transmit power (the rated UE maximum transmit power).

[0774] As used in this disclosure, the terms “connected,” “coupled,” or all variations thereof, refer to all direct or indirect connections or combinations between two or more elements, and can include cases where there is one or more intermediate elements between two mutually “connected” or “coupled” elements. The connections or combinations between elements can be physical, logical, or a combination thereof. For example, “connection” can also be rewritten as “access.”

[0775] In this disclosure, when two elements are connected, it is possible to consider using more than one wire, cable, printed electrical connection, etc. to be "connected" or "combined" with each other, and as several non-limiting and non-exclusive examples, to use electromagnetic energy with wavelengths having wireless frequency domain, microwave region, light (both visible and invisible) region to be "connected" or "combined" with each other.

[0776] In this disclosure, the term "A is different from B" can also mean "A and B are different from each other." Additionally, the term can also mean "A and B are each different from C." Terms such as "separate" and "combined" can also be interpreted in the same way as "different."

[0777] When the terms "include," "including," and variations thereof are used in this disclosure, these terms, like the term "comprising," mean inclusive. Furthermore, the term "or" as used in this disclosure does not mean XOR.

[0778] In this disclosure, for example, in cases where articles are added through translation, such as a, an, and the in English, the disclosure may also include cases where the noun following these articles is in a plural form.

[0779] In this disclosure, terms such as "below," "less than," "above," "more than," and "equal to" can be interchanged. Furthermore, in this disclosure, statements meaning "good," "bad," "large," "small," "high," "low," "early," "late," "wide," and "narrow" can be interchanged, not limited to the positive, comparative, and superlative degrees. Additionally, in this disclosure, statements meaning "good," "bad," "large," "small," "high," "low," "early," "late," "wide," and "narrow" can also be interchanged as expressions accompanied by "i" (where i is any integer), not limited to the positive, comparative, and superlative degrees (e.g., "highest" can also be interchanged with "i-th highest").

[0780] In this disclosure, "of", "for", "regarding", "related to", "associated with", etc., can also be rewritten interchangeably.

[0781] In this disclosure, phrases such as "when A, B", "if A, then B", "B upon A", "B in response to A", "B based on A", "B during / while A", "B before A", "B at (the same time as) / on A", "B after A", "B since A", and "B until A" can be rewritten interchangeably. Furthermore, A and B can be appropriately replaced with nouns, gerunds, or other suitable expressions depending on the context. Additionally, the time difference between A and B can be approximately 0 (immediately following or immediately preceding). Moreover, a time offset can be applied to the time A occurs. For example, "A" can also be rewritten interchangeably with "before / after the time offset of A". This time offset (e.g., more than one symbol / slot) can be predetermined or determined by the UE based on the information it is notified of.

[0782] In this disclosure, timing, moment, time, time instance, arbitrary time unit (e.g., time slot, sub-time slot, symbol, subframe), period, opportunity, resource, etc., can also be overridden.

[0783] The inventions disclosed herein have been described in detail above. However, it will be apparent to those skilled in the art that the inventions disclosed herein are not limited to the embodiments described herein. The description herein is for illustrative purposes only and is not intended to limit the inventions disclosed herein in any way.

[0784] This application is based on Japanese Special Application 2024-084237, filed on May 23, 2024. The entire contents of that application are contained herein.

Claims

1. A terminal, comprising: The receiving unit receives setting information for data collection in AI-based positioning; and The control unit controls the execution of at least one of the following: the inference, learning, and training of the model, and at least one of the reports associated with at least one of the inference, learning, and training, based on parameters indicating the purpose or the state of the model process contained in the setting information.

2. The terminal as described in claim 1, wherein, When the parameter represents a specific value, the control unit assumes that the specific parameter is not included in the setting information.

3. The terminal as described in claim 1, wherein, The receiving unit receives instructions related to the execution of post-processing for the measurement results.

4. The terminal as described in claim 1, wherein, The control unit controls whether the reported positioning information is generated by the AI ​​model.

5. A wireless communication method for a terminal, comprising: The steps for receiving data collection settings information in location services based on artificial intelligence (AI); and Based on the parameters representing the purpose contained in the setting information, or the state of the model process, the steps of controlling the execution of at least one of the model's inference, learning, and training, and at least one of the reports related to the inference, learning, and training.

6. A base station, comprising: The transmitting unit transmits setting information for data collection in AI-based positioning; and The control unit, using parameters representing the purpose or the state of the model process contained in the setting information, instructs at least one of the following: the execution of at least one of the model's inference, learning, and training; and at least one of the reports associated with the inference, learning, and training.

Images