WO2022208673A1

WO2022208673A1 - Terminal, wireless communication method, and base station

Info

Publication number: WO2022208673A1
Application number: PCT/JP2021/013613
Authority: WO
Inventors: 春陽越後; 浩樹原田; 大輔栗田; 祐輝松村; 尚哉芝池; 聡永田
Original assignee: 株式会社Ｎｔｔドコモ
Priority date: 2021-03-30
Filing date: 2021-03-30
Publication date: 2022-10-06
Also published as: JPWO2022208673A1

Abstract

A terminal according to one embodiment of the present disclosure comprises: a reception unit for receiving a reference signal; and a control unit for exercising control to perform a prediction based on a second setting of the reference signal, using a machine learning model having been trained on the basis of a first setting of the reference signal. One embodiment of the present disclosure makes it possible to realize highly accurate channel estimation, highly efficient resource utilization, etc.

Description

Terminal, wireless communication method and base station

The present disclosure relates to terminals, wireless communication methods, and base stations in next-generation mobile communication systems.

In the Universal Mobile Telecommunications System (UMTS) network, Long Term Evolution (LTE) has been specified for the purpose of further high data rate, low delay, etc. (Non-Patent Document 1). In addition, LTE-Advanced (3GPP Rel. 10-14) has been specified for the purpose of further increasing the capacity and sophistication of LTE (Third Generation Partnership Project (3GPP) Release (Rel.) 8, 9).

LTE successor systems (for example, 5th generation mobile communication system (5G), 5G+ (plus), 6th generation mobile communication system (6G), New Radio (NR), 3GPP Rel. 15 and later) are also being considered. .

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

However, in using the ML model for wireless communication, consideration has not yet progressed regarding which entity will implement the ML model and which entity will train the ML model. If these are not defined appropriately, highly accurate channel estimation/highly efficient use of resources cannot be achieved, and there is a risk that improvements in communication throughput or communication quality will be suppressed.

Therefore, one of the purposes of the present disclosure is to provide a terminal, a wireless communication method, and a base station that can realize highly accurate channel estimation, highly efficient use of resources, and the like.

A terminal according to an aspect of the present disclosure uses a receiving unit that receives a reference signal, and a machine learning model trained based on the first setting of the reference signal, based on the second setting of the reference signal and a control unit that controls the prediction.

According to one aspect of the present disclosure, highly accurate channel estimation, highly efficient use of resources, and the like can be realized.

FIG. 1 is a diagram illustrating an example of estimation resources. FIG. 2 is a diagram showing an example of a sequence for training an ML model according to embodiment A1. FIG. 3 is a diagram showing an example of a sequence for testing an ML model according to embodiment A1. FIG. 4 is a diagram showing an example of a sequence for training an ML model according to embodiment A2. FIG. 5 is a diagram showing an example of a sequence for training an ML model according to embodiment B1. FIG. 6 is a diagram showing an example of a sequence for testing an ML model according to embodiment B1. FIG. 7 is a diagram showing an example of a sequence for training an ML model according to embodiment B2. FIG. 8 is a diagram showing an example of a sequence for testing the ML model according to the embodiment C1. 9A and 9B are diagrams showing an example of mode switching control. FIG. 10 is a diagram illustrating an example of information transmission/reception according to the third embodiment. FIG. 11 is a diagram showing an example of what techniques are utilized for each embodiment of the present disclosure. FIG. 12 is a diagram illustrating an example of a schematic configuration of a wireless communication system according to an embodiment; FIG. 13 is a diagram illustrating an example of the configuration of a base station according to one embodiment. FIG. 14 is a diagram illustrating an example of the configuration of a user terminal according to an embodiment; FIG. 15 is a diagram illustrating an example of hardware configurations of a base station and user terminals according to an embodiment.

(Application of artificial intelligence (AI) technology to wireless communication)
As for future wireless communication technology, utilization of AI technology for control and management of networks/devices is under consideration.

For example, for future wireless communication technologies, especially in communications using beams, it is desired to improve the accuracy of channel estimation (also referred to as channel measurement) for beam management, decoding of received signals, and the like. .

Channel estimation, for example, 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 (SRS), or the like.

Conventional wireless communication technology requires a large amount of estimation resources (for example, resources for transmitting reference signals) in order to perform highly accurate channel estimation. was necessary.

FIG. 1 is a diagram showing an example of estimation resources. In this example, a resource configuration for 3 slots of NR communication is illustrated. For example, in the first slot, a terminal (also called a user terminal, User Equipment (UE), etc.) uses a physical downlink shared channel (PDSCH), a physical uplink shared channel (PUSCH) Receive downlink control information (DCI) for scheduling etc., PDSCH, DMRS for the PDSCH, and CSI-RS. In the second and third slots, the UE transmits PUSCH and DMRS for the PUSCH.

If resources such as DMRS and CSI-RS are increased to achieve highly accurate channel estimation, resources for data transmission/reception (eg PDSCH resources, PUSCH resources) will decrease.

In the future, it will be considered to use AI technology such as machine learning (ML) to achieve high-precision channel estimation with fewer resources. Such channel estimation may be called AI-aided estimation.

Therefore, the inventors came up with a method of using the ML model, especially for the physical layer (Physical (PHY) layer).

In one embodiment of the present disclosure, the UE/Base Station (BS) trains the ML model in training mode and the ML model in test mode (also called test mode, testing mode, etc.) to implement. In the test mode, validation of the accuracy of the trained ML model in the training mode may be performed.

In the present disclosure, the UE / BS inputs channel state information, reference signal measurements, etc. to the ML model, and outputs highly accurate channel state information / measurements / beam selection / positions, etc. good.

It should be noted that in the present disclosure, AI may be read as an object (also called object, object, data, function, program, etc.) having (implementing) at least one of the following characteristics:
Estimates based on observed or collected information;
- Choices based on information observed or collected;
• Predictions based on observed or collected information.

In the present disclosure, the object may be, for example, a terminal, a device such as a base station, or a device. Also, the object may correspond to a program included in the device.

Also, in this disclosure, an ML model may be read as an object that has (enforces) at least one of the following characteristics:
Generating an estimate by feeding,
Informed to predict estimates;
・Discover characteristics by giving information,
• Selecting actions by giving information.

Also, in the present disclosure, the ML model may be read as at least one of AI model, predictive analytics, predictive analysis model, and the like. Also, the ML model may be derived using at least one of regression analysis (e.g., linear regression analysis, multiple regression analysis, logistic regression analysis), support vector machines, random forests, neural networks, deep learning, and the like. In this disclosure, model may be translated as at least one of encoder, decoder, tool, and the like.

　The ML model outputs at least one information such as estimated value, predicted value, selected action, classification, etc., based on the input information.

The ML model may include supervised learning, unsupervised learning, reinforcement learning, etc. Supervised learning may be used to learn general rules that map inputs to outputs. Unsupervised learning may be used to learn features of data. Reinforcement learning may be used to learn actions to maximize a goal.

Each embodiment described later will be mainly described assuming that supervised learning is used in the ML model, but it is not limited to this.

In the present disclosure, "A/B" and "at least one of A and B" may be read interchangeably.

In the present disclosure, activate, deactivate, indicate (or indicate), select, configure, update, determine, etc. may be read interchangeably. In the present disclosure, supporting, controlling, controllable, operating, and capable of operating may be read interchangeably.

In the present disclosure, Radio Resource Control (RRC), RRC parameters, RRC messages, higher layer parameters, information elements (IEs), and settings may be read interchangeably. In the present disclosure, Medium Access Control Control Element (MAC Control Element (CE)), update command, and activation/deactivation command may be read interchangeably.

In the present disclosure, indexes, IDs, indicators, and resource IDs may be read interchangeably. In the present disclosure, sequences, lists, sets, groups, groups, clusters, subsets, etc. may be read interchangeably.

In the present disclosure, implementation, operation, operation, execution, etc. may be read interchangeably. Also, in the present disclosure, testing, after-training, production use, actual use, etc. may be read interchangeably. A signal may be interchanged with signal/channel.

In the present disclosure, the training mode may correspond to the mode in which the UE/BS transmits/receives signals for the ML model (in other words, the mode of operation during training). In the present disclosure, the test mode corresponds to the mode in which the UE/BS implements the ML model (e.g., implements the trained ML model to predict the output) (in other words, the operating mode during the test). good.

In the present disclosure, training mode may refer to a mode in which a specific signal transmitted in test mode has a large overhead (eg, a large amount of resources) is transmitted.

In the present disclosure, training mode may refer to a mode that refers to a first configuration (eg, first DMRS configuration, first CSI-RS configuration). In the present disclosure, test mode may refer to a mode that refers to a second configuration (eg, second DMRS configuration, second CSI-RS configuration) different from the first configuration. At least one of time resources, frequency resources, code resources, and ports (antenna ports) related to measurement may be set more in the first setting than in the second setting.

Hereinafter, embodiments according to the present disclosure will be described in detail with reference to the drawings. The wireless communication method according to each embodiment may be applied independently, or may be applied in combination.

In the following embodiments, the UE and the BS are the relevant subjects in order to explain the ML model for communication between the UE and the BS, but the application of each embodiment of the present disclosure is not limited to this. For example, for communication between different entities (eg, UE-UE communication), UE and BS in the following embodiments may be read as first UE and second UE. In other words, any UE, BS, etc. in this disclosure may be read as any UE/BS.

(Wireless communication method)
<First Embodiment>
In a first embodiment, we describe which subject implements the ML model and which subject trains the ML model. For the former, there are three embodiments A to C, for the latter there are three embodiments 1 to 3, and by combining these, there are nine embodiments A1 to C3.

A specific example of using the ML model will be described at the end of the first embodiment.

[Embodiment A1]
In embodiment A1, the BS implements the ML model trained by the BS.

FIG. 2 is a diagram showing an example of a sequence for training an ML model according to Embodiment A1. The UE computes information for training the ML model (step S101). The UE sends the information calculated in step S101 and/or signals for training the ML model to the BS (step S102). The BS performs training of the ML model based on the information/signals received in step S102 (step S103). Note that if a signal for training the ML model is transmitted in step S102, step S101 may be omitted.

In the present disclosure, the information for training the ML model may be the ML model report described later in the third embodiment, or may be information used as input for the ML model.

In step S101, the UE may calculate information for training the ML model based on information/signals received from the BS.

FIG. 3 is a diagram showing an example of a sequence for testing an ML model according to Embodiment A1. The UE calculates information for input of the ML model (step S201). The UE sends the information calculated in step S201 and/or the signal for testing the ML model to the BS (step S202). The BS implements a trained ML model (step S203) based on the information/signals received in step S202 (eg, with the above information as input). Note that if the signal for testing the ML model is transmitted in step S202, step S201 may be omitted.

In addition, in the present disclosure, testing the ML model may mean testing the trained ML model.

[Embodiment A2]
In embodiment A2, the ML model trained by the UE is implemented by the BS.

FIG. 4 is a diagram showing an example of a sequence for training an ML model according to Embodiment A2. The UE performs ML model training (step S111). The UE sends the information of the ML model trained in step S111 to the BS (step S112).

In step S111, the UE may perform ML model training based on information/signals received from the BS. For example, the UE may perform ML model training based on at least one of the information for ML model training and the signal for ML model training.

Information about the ML model trained in step S112 will be described later in the third embodiment.

The sequence for testing the ML model according to embodiment A2 may be the same as that of embodiment A1. However, the trained ML model is based on the information of the trained ML model in step S112.

[Embodiment A3]
In embodiment A3, the BS implements the ML model trained by both the UE and the BS.

The training of the ML model according to embodiment A3 corresponds to the case where both the training of the ML models according to embodiments A1 and A2 are performed (for example, in parallel, at the same time, at different times). That is, the BS carries out the training of the ML model as shown in Figure 2 and obtains the trained ML model. Meanwhile, the UE performs ML model training, obtains a trained ML model, and sends information of the trained ML model to the BS, as shown in FIG.

The BS may update (eg, fine-tune) the ML model trained by itself based on the information received from the UE about the ML model trained by the UE. Also, the BS may perform transfer learning of the ML model based on the information received from the UE about the ML model trained by the UE. The BS may also combine the ML model it has trained with the ML model received from the UE (e.g., use the output of the ML model received from the UE as input for the ML model it has trained. may be used). Note that the BS may perform the updating, transfer learning, etc. based on the information of a plurality of trained ML models received from a plurality of communicating UEs.

The sequence for testing the ML model according to embodiment A3 may be the same as that of embodiment A1. However, the trained ML model corresponds to the ML model to which the update/transfer learning described above has been applied.

[Embodiment B1]
In embodiment B1, the UE implements the ML model trained by the BS.

FIG. 5 is a diagram showing an example of a sequence for training an ML model according to embodiment B1. Steps S301, S302, and S303 may be the same as steps S101, S102, and S103 of FIG. 2, respectively, and therefore description thereof will not be repeated.

The UE receives from the BS the information of the ML model trained by the BS in step S303 (step S304). Information about the ML model trained in step S304 will be described later in the third embodiment.

FIG. 6 is a diagram showing an example of a sequence for testing an ML model according to embodiment B1. The UE receives information for inputting the ML model and/or signals for testing the ML model from the BS (step S401). The UE implements a trained ML model (step S402) based on the information/signals received in step S401 (eg, with the above information as input).

[Embodiment B2]
In embodiment B2, the UE implements the ML model trained by the UE.

FIG. 7 is a diagram showing an example of a sequence for training an ML model according to embodiment B2. The UE receives information for ML model training and/or signals for ML model training from the BS (step S311). The BS performs training of the ML model based on the information/signals received in step S311 (step S312).

The sequence for testing the ML model according to embodiment B2 may be the same as that of embodiment B1.

[Embodiment B3]
In embodiment B3, the UE implements the ML model trained by both the UE and the BS.

The training of the ML model according to embodiment B3 corresponds to the case where both the training of the ML models according to embodiments B1 and B2 are performed (for example, in parallel, at the same time, at different times). That is, the BS performs ML model training, obtains a trained ML model, and sends the trained ML model information to the UE, as shown in FIG. Meanwhile, the UE performs ML model training as in Fig. 7 and obtains a trained ML model.

The UE may update (eg, fine-tune) the ML model trained by itself based on the information received from the BS about the ML model trained by the BS. The UE may also perform transfer learning of the ML model based on the information received from the BS about the ML model trained by the BS. The UE may also implement a combination of the ML model it has trained with the ML model received from the BS (e.g., the output of the ML model received from the BS is used as the input for the ML model it has trained. may be used). It should be noted that the UE may perform such updating, transfer learning, etc. based on information of multiple trained ML models received from one or more BSs/one or more other UEs with which it communicates.

The sequence for testing the ML model according to embodiment B3 may be the same as that of embodiment B1. However, the trained ML model corresponds to the ML model to which the update/transfer learning described above has been applied.

[Embodiment C1]
In embodiment C1, both the UE and the BS implement the ML model trained by the BS. Note that in embodiments C1-C3, the trained ML model may consist of multiple ML models, and may include a UE-implemented ML model and a BS-implemented ML model.

The sequence for training the ML model according to embodiment C1 may be the same as that of embodiment B1. However, the information of the trained ML model notified to the UE may be the information of the ML model that the UE implements among the ML models trained by the BS.

FIG. 8 is a diagram showing an example of a sequence for testing an ML model according to Embodiment C1. The UE receives information for inputting the ML model and/or signals for testing the ML model from the BS (step S601). The UE implements a trained ML model based on the information/signals received in step S401 (eg, with the above information as input) (step S602).

The UE transmits the output of the ML model in step S602 to the BS (step S603). The BS takes as input the output of the UE's ML model sent in step S603 and implements the trained ML model (step S604).

[Embodiment C2]
In embodiment C2, both the UE and the BS implement the ML model trained by the UE.

The sequence for training the ML model according to embodiment C1 may be the same as that of embodiment A2. However, the information of the trained ML model notified to the BS may be the information of the ML model that the BS implements among the ML models trained by the UE.

The sequence for testing the ML model according to embodiment C2 may be the same as that of embodiment C1.

[Embodiment C3]
In embodiment C3, both the UE and the BS implement the ML model trained by the UE and the BS.

The training of the ML model according to embodiment C3 corresponds to the case of both training the ML models according to embodiments C1 and C2 (for example, in parallel, at the same time, at different times). That is, the BS performs ML model training as in embodiment C1, obtains a trained ML model, and sends the information of the trained ML model to the UE. Meanwhile, the UE performs ML model training as in embodiment C2, obtains a trained ML model, and sends the information of the trained ML model to the BS.

　In addition, the information of the trained ML model does not necessarily have to be transmitted to each other.

The BS may update (eg, fine-tune) the ML model trained by itself based on the information received from the UE about the ML model trained by the UE. The BS may also perform transfer learning of the ML model based on the information received from the UE about the ML model trained by the UE. The BS may also combine the ML model it has trained with the ML model received from the UE (e.g., use the output of the ML model received from the UE as input for the ML model it has trained. may be used). Note that the BS may perform the updating, transfer learning, etc. based on the information of a plurality of trained ML models received from a plurality of communicating UEs.

The sequence for testing the ML model according to embodiment C3 may be the same as that of embodiment C1. However, the trained ML model corresponds to the ML model to which the update/transfer learning described above has been applied.

[Examples of using specific ML models]
[[AI-assisted DMRS estimation]]
The ML model in the first embodiment may be used for AI-aided DMRS estimation. The input of the ML model may be the low-density DMRS (or measurements based thereon) and the output may be the high-density DMRS (or measurements based thereon). By using this ML model, dense DMRS measurements can be estimated while reducing DMRS communication overhead.

In the present disclosure, "density" may mean the density or number of at least one of time resources, frequency resources, code resources, and ports (antenna ports).

It is preferable that the period of high-density DMRS as a training signal be set in the UE. The UE/BS may use dense DMRS (training DMRS) measurements to train an ML model for learning correlations between DMRS resource elements. The UE/BS may use the trained ML model to perform channel estimation based on sparse DMRS (test DMRS).

Measurement results based on high-density DMRS, estimation results based on low-density DMRS extracted from the high-density DMRS, density/resource information of the high-density DMRS, and density/resource of the low-density DMRS Information, or any combination of these, corresponds to the training data for the ML model.

For example, at least one of embodiments A1, A3, B2, B3, etc. is preferably used for modeling the ML model for AI-assisted DMRS estimation.

[[AI-assisted CSI-RS estimation]]
The ML model in the first embodiment may be utilized for AI-assisted CSI-RS estimation. The input of the ML model may be low-density CSI-RS (or measurements based thereon) and the output may be high-density CSI-RS (or measurements based thereon). By using this ML model, high-density CSI-RS measurements can be estimated while reducing CSI-RS communication overhead.

CSI resource indicators for high density DMRS (training DMRS) and low density DMRS (test DMRS) and CSI reporting quality are preferably configured in the UE. The UE may use the dense CSI-RS/sparse DMRS measurements to train the ML model. The UE may use the trained ML model to perform high density CSI-RS equivalent channel estimation based on low density CSI-RS and perform CSI reporting.

Measurement results based on high-density CSI-RS, estimation results based on low-density CSI-RS extracted from the high-density CSI-RS, density/resource information of the high-density CSI-RS, and the The low-density CSI-RS density/resource information and/or any combination of these correspond to training data for the ML model.

For modeling the ML model for AI-assisted CSI-RS estimation, it is preferable to use embodiment B2, for example.

[[AI-assisted CSI report]]
The ML model in the first embodiment may be utilized for AI-assisted CSI reporting. The input of the ML model is a low overhead (low information content) CSI report (e.g. existing CSI report including PMI etc.) and the output is an accurate high overhead (high information content) CSI report (e.g. , detailed channel matrix, UE location, optimal PMI, etc.). By using this ML model, a highly accurate CSI report can be estimated while reducing the communication overhead of the CSI report.

　The content of each CSI report is preferably configured in the UE. The BS may use low-overhead/high-overhead CSI reports to train the ML model. The BS may recover high-overhead CSI reports based on low-overhead CSI reports using a trained ML model (which may be referred to as an AI decoder).

Any of a low overhead CSI report, a high overhead CSI report, CSI-RS information (eg, density) corresponding to the low overhead CSI report, and CSI-RS information corresponding to the high overhead CSI report Or any combination thereof corresponds to training data for the ML model.

For modeling the ML model for this AI-assisted CSI report, it is preferable to use embodiments A1 and A2, for example.

　The ML model of AI-assisted CSI reporting may be utilized by both the BS and the UE. The input of this ML model is the received CSI-RS (or its estimation result) and the output may be the exact CSI (eg detailed channel matrix, UE location, optimal PMI, etc.) . By using this ML model, highly accurate CSI can be estimated while reducing CSI communication overhead.

　The CSI resource indicator, encoded information size, etc. are preferably configured in the UE. The UE may train the model using the received CSI-RS and the encoded information size. The BS may train an ML model that takes the encoded information as input and outputs the correct CSI. The UE may encode or compress and transmit CSI based on the received CSI-RS using a trained ML model (which may be referred to as an AI encoder). The BS may decode received encoded or compressed CSI using a trained ML model (which may be referred to as an AI decoder) to obtain accurate CSI.

Any or any combination of the estimation result of the CSI-RS, the encoded information size, the accurate CSI, and the information of the CSI-RS (for example, the density) is a teacher for the ML model Applicable to data.

For modeling the ML model for this AI-assisted CSI report, it is preferable to use embodiments C2 and C3, for example.

According to the first embodiment described above, an ML model for wireless communication trained by an appropriate subject can be used.

<Second embodiment>
A second embodiment relates to the distinction between training mode and test mode.

The UE/BS may determine which mode the UE/BS is in based on at least one of the following:
(2-1) Report information about the mode to the BS,
(2-2) Receipt of information (instruction) about the mode from the BS;
(2-3) Specific rules/patterns.

The information in (2-1) above may be transmitted using physical layer signaling (eg, UCI), higher layer signaling (eg, RRC signaling, MAC CE), specific signals/channels, or a combination thereof. .

The information in (2-2) above may be transmitted using physical layer signaling (eg, DCI), higher layer signaling (eg, RRC signaling, MAC CE), specific signals/channels, or a combination thereof. .

The rules/patterns of (2-3) above may be defined in advance by specifications, physical layer signaling (eg, DCI), higher layer signaling (eg, RRC signaling, MAC CE), specific signals/channels, Or you may be notified using these combinations.

The information on the modes (2-1) and (2-2) above may be called trigger information, may include information indicating training mode or test mode, and may indicate mode switching (or mode switching). may include information indicating that a specific mode (for example, a test mode) may be performed, or the above (2-3) after receiving the trigger information. may include information indicating that it operates according to certain rules/patterns of

Note that the information about the mode may indicate the number of samples (eg, 50, 100, 200 samples) until training/testing is completed. A UE operating in training (test) mode may transition to test (training) mode after transmitting/receiving that number of samples.

The information about the mode may also indicate the time to complete training/testing (eg, number of slots (eg, 5, 10 slots), number of symbols). For example, a UE operating in training (test) mode may transition to test (training) mode after the time has elapsed.

9A and 9B are diagrams showing an example of mode switching control. In this example, it is assumed that mode operation can be switched on a slot-by-slot basis.

In FIG. 9A, in the first four slots shown, the UE is operating in training mode. In the 5th slot, the UE receives trigger information (eg, MAC CE). The trigger information specifies the operation of switching between the test mode and the training mode for each slot. In FIG. 9A, the mode switching operation is performed from the next slot after receiving the trigger information. It may be after transmission of ACKnowledge (ACK) (or after a certain period of time after this transmission).

In FIG. 9B, trigger information is notified based on DCI. A UE that has been operating in training mode (for example, PDSCH DMRS ML model training) in the first two slots illustrated receives a DCI indicating a training end instruction in the third slot, and from the next fourth slot It may work in test mode.

According to the second embodiment described above, the timing of the training mode and the test mode can be appropriately controlled.

<Third Embodiment>
The third embodiment relates to transmission and reception of ML model information.

Information on at least one of a trained ML model and a pre-trained ML model (hereinafter also referred to as ML model information, ML model report, etc.) is sent from a subject (UE/BS) to another subject (BS/UE/another UE/another BS).

The UE/BS may train/adjust/update (eg, fine-tuning)/transfer-learn the ML model based on received, trained or pre-trained ML model information. The UE/BS may also implement a combination of the ML model it has trained and the received ML model (e.g., use the output of the received ML model as input for the ML model it has trained. may be used).

Note that the pre-trained ML model may be selected from multiple models based on the location of the UE/BS (location information), channel measurement results at the UE/BS, and the like. The pre-trained ML model information may be pre-stored in the UE/BS or configured by higher layer signaling.

　The performance information (performance report) of the ML model may be sent/received from one subject to another subject. The performance report may be sent together with the ML model information, or may be sent separately. The performance report may include at least one of the estimation (prediction) accuracy (or error) of an ML model, the number of samples used to train the ML model, and/or the like.

FIG. 10 is a diagram showing an example of information transmission/reception according to the third embodiment. In this example, trained ML model reports (which may be accompanied by performance reports) may be sent to and received from each other between BS-UE1, BS-UE2, UE1-UE2, and so on. Each UE/BS may utilize the received information to update (tune) the ML model.

ML model report / performance report (hereinafter simply referred to as ML model report) contains one or more weights (weights) used in each layer of the ML model, base pre-trained ML model information, a specific ML model ( (which may be referred to as a reference ML model), and differences from the reference ML model (for example, differences in weights, differences in the number of hidden layers, etc.). Here, the pre-trained ML model/reference ML model information may be an index of one or more ML models, for example when multiple ML models are indexed (numbered).

　The parameters of the ML model indicated by the ML model report may be indicated with a predetermined granularity (unit). The granularity of the parameters of the ML model may be at least one of input parameters, output parameters, hidden layer parameters (eg, weights, hyperparameters (eg, number of hidden layers), etc.) for the ML model.

Note that the granularity of the parameters of the ML model may be determined in advance by specifications (may be determined by a specific rule), physical layer signaling (eg, DCI, UCI), higher layer signaling (eg, RRC signaling , MAC CE), a specific signal/channel, or a combination thereof, to the UE/BS. The notified granularity may be called recommended granularity, specified granularity, or the like.

　The parameters of the ML model indicated by the ML model report may be represented by at least one of absolute and relative values. Also, the parameters of the ML model indicated by the ML model report may be represented by at least one of discrete values (or digital values) and continuous values (or analog values).

ML model reports may be sent using physical layer signaling (eg, DCI, UCI), higher layer signaling (eg, RRC signaling, MAC CE), specific signals/channels, or a combination thereof. The ML model report/performance report may be sent in the same cell as the cell for this ML model (the cell where the ML model is utilized), or in a different cell (e.g., the cell where the ML model is not utilized, the primary cell, a specific secondary cell).

The ML model report may be sent and received periodically/semi-persistently/aperiodically. The ML model report transmission period may be configured in the UE by higher layer signaling. The UE may implement periodic transmission/reception of ML model reports when configured by higher layer signaling to periodically transmit/receive ML model reports. The UE may implement semi-persistent transmission/reception of ML model reports when triggered by DCI to semi-persistent transmission/reception of ML model reports.

For aperiodic ML model report transmission/reception, the UE may implement ML model report transmission/reception when requested (or triggered) by other UE/BS. The UE may also implement ML model report transmission/reception if conditions are met. The conditions may be predetermined according to specifications, or information about the conditions may be notified from other UE/BS using higher layer signaling or the like. The condition is, for example, that the reception quality of a specific channel/signal (for example, Reference Signal Received Power (RSRP)) has fallen below a threshold, or that a specific channel/signal has been retransmitted (or decoding has failed) , etc., may be at least one.

Note that the UE may transmit information about the UE (which may be referred to as UE information) to the BS in order to prompt the BS to select a pre-trained ML model to be used by the UE. The UE information may be information for identifying the position of the UE, for example, the position information of the present disclosure is information obtained using a positioning system such as the Global Positioning System (GPS), information adjacent to the UE (or serving) base station information (e.g., base station/cell identifier (ID), distance between BS-UE, direction of UE seen from BS, etc.), specific address of the UE ( For example, at least one such as an Internet Protocol (IP) address) may be included. The UE information may also include reference signals for positioning (eg, Positioning Reference Signal (PRS), CSI-RS, SRS, etc.).

The UE information may include information about its own implementation (eg, antenna location/position, antenna panel position/orientation, number of antennas, number of antenna panels, etc.).

According to the third embodiment described above, ML model information can be preferably shared among a plurality of devices (UE, BS).

<Fourth Embodiment>
A fourth embodiment relates to reporting the desired form of information for the ML model.

The UE may report the desired form of information for training the ML model (which may be referred to as the desired information form) to or from another entity (BS/another UE) may receive. The preferred format may be reported using physical layer signaling (eg DCI, UCI), higher layer signaling (eg RRC signaling, MAC CE), specific signals/channels, or a combination thereof.

The UE may report the desired form of information for input of the ML model (in other words, information for testing the ML model) to another entity (BS/another UE), or another entity may be received from

In addition, the desired format means at least one of, for example, the desired density, the desired period (or offset), etc. for the reference signal (e.g., DMRS, CSI-RS) to be measured for training / input of the ML model. may

For example, in the case of AI-assisted CSI-RS estimation, the UE is preferred for training the ML model based on the CSI-RS measurements sent from the BS (in other words, to improve the estimation accuracy of the ML model likely to contribute) density/resource pattern and report the information of the preferred density/resource pattern to the BS, and the BS may transmit CSI-RS using the preferred density/resource pattern.

The desired format report of the fourth embodiment may be sent and received periodically/semi-persistently/aperiodically in the same manner as described for the ML model report of the third embodiment.

According to the fourth embodiment described above, it is possible to appropriately specify the configuration of the reference signal for improving the accuracy of the ML model.

<Fifth Embodiment>
The fifth embodiment relates to application conditions of the ML model.

ML model application conditions may be defined in advance by specifications, physical layer signaling (e.g., DCI, UCI), higher layer signaling (e.g., RRC signaling, MAC CE), specific signals/channels, or these A combination may be used to inform the UE/BS.

The UE under conditions where the ML model cannot be applied cannot perform training of the ML model and estimation using the ML model until the conditions where the ML model can be applied (for example, the estimation operation defined by Rel.16 It may be assumed that

Note that ML model sharing (sharing) (in other words, the information of the ML model trained by a certain UE, to be used by notifying other UE) is the position of the UE (for example, between BS-UE distance, orientation of the UE with respect to the BS, etc.), implementation of the UE (eg, location of antennas, number of antennas, etc.), elapsed time after training, and/or the like.

According to the fifth embodiment described above, the ML model can be appropriately applied only to preferred UEs/BSs.

<Others>
FIG. 11 is a diagram showing an example of what techniques are utilized for each embodiment of the present disclosure. A circle (○) may mean that it can be applied, or it does not mean that it must be applied. Also, a cross (x) may mean not applicable. It should be noted that this is merely an example, and the combinations of ◯ and × in each embodiment are not limited to those shown.

At least one of the above-described embodiments may be applied only to UEs that have reported or support a specific UE capability.

The specific UE capabilities may indicate at least one of the following:
- whether to support AI-assisted PHY operation;
whether to support AI-assisted DMRS estimation;
whether to support AI-assisted CSI-RS estimation;
whether to support AI-assisted CSI reporting;
Whether or not the ML model can be trained,
whether it is possible to report capabilities for pre-trained ML models;
whether or not to support extended DMRS configurations;
whether to support extended CSI-RS resource mapping;
・whether or not to support a particular sampling pattern;
・whether or not to support notification of ML model information;
• Whether to support identification of training and test modes.

The UE capability may be reported for each frequency, may be reported for each frequency range (for example, Frequency Range 1 (FR1), Frequency Range 2 (FR2)), or may be reported for each subcarrier spacing (SubCarrier Spacing ( SCS))). In other words, the UE may apply control based on the ML model only on specific frequencies/FR/SCS.

The above UE capabilities may be reported commonly for Time Division Duplex (TDD) and Frequency Division Duplex (FDD), or may be reported independently.

Also, at least one of the above embodiments may be applied if the UE is configured with specific information related to the above embodiments by higher layer signaling. For example, the specific information may be information indicating to enable ML model-based control, any RRC parameters for a specific release (eg, Rel.18), and the like.

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

FIG. 12 is a diagram showing an example of a schematic configuration of a wireless communication system according to one embodiment. The wireless communication system 1 may be a system that realizes communication using Long Term Evolution (LTE), 5th generation mobile communication system New Radio (5G NR), etc. specified by the Third Generation Partnership Project (3GPP). .

The wireless communication system 1 may also support dual connectivity between multiple Radio Access Technologies (RATs) (Multi-RAT Dual Connectivity (MR-DC)). MR-DC is 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. may be included.

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.

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

A wireless communication system 1 includes a base station 11 forming a macrocell C1 with a relatively wide coverage, and base stations 12 (12a-12c) arranged in the macrocell C1 and forming a small cell C2 narrower than the macrocell C1. You may prepare. A user terminal 20 may be located within at least one cell. The arrangement, number, etc. of each cell and user terminals 20 are not limited to the embodiment shown in the figure. Hereinafter, the base stations 11 and 12 are collectively referred to as the base station 10 when not distinguished.

The user terminal 20 may connect to at least one of the multiple base stations 10 . The user terminal 20 may utilize at least one of carrier aggregation (CA) using a plurality of component carriers (CC) and dual connectivity (DC).

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

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

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

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

The user terminal 20 may be a terminal compatible with at least one of communication schemes such as LTE, LTE-A, and 5G.

In the radio communication system 1, a radio access scheme based on orthogonal frequency division multiplexing (OFDM) may be used. For example, in at least one of Downlink (DL) and Uplink (UL), Cyclic Prefix OFDM (CP-OFDM), Discrete Fourier Transform Spread OFDM (DFT-s-OFDM), Orthogonal Frequency Division Multiple Access (OFDMA), Single Carrier Frequency Division Multiple Access (SC-FDMA), etc. may be used.

A radio access method may be called a waveform. Note that in the radio communication system 1, other radio access schemes (for example, other single-carrier transmission schemes and other multi-carrier transmission schemes) may be used as the UL and DL radio access schemes.

In the radio communication system 1, as downlink channels, a downlink shared channel (Physical Downlink Shared Channel (PDSCH)) shared by each user terminal 20, a broadcast channel (Physical Broadcast Channel (PBCH)), a downlink control channel (Physical Downlink Control Channel (PDCCH)) or the like may be used.

In the radio communication system 1, as uplink channels, an uplink shared channel (PUSCH) shared by each user terminal 20, an uplink control channel (PUCCH), a random access channel (Physical Random Access Channel (PRACH)) or the like may be used.

User data, upper layer control information, System Information Block (SIB), etc. are transmitted by the PDSCH. User data, higher layer control information, and the like may be transmitted by PUSCH. Also, a Master Information Block (MIB) may be transmitted by the PBCH.

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

The DCI that schedules PDSCH may be called DL assignment, DL DCI, etc., and the DCI that schedules PUSCH may be called UL grant, UL DCI, etc. PDSCH may be replaced with DL data, and PUSCH may be replaced with UL data.

A control resource set (CControl Resource SET (CORESET)) and a search space (search space) may be used for PDCCH detection. CORESET corresponds to a resource searching for DCI. The search space corresponds to the search area and search method of PDCCH candidates. A CORESET may be associated with one or more search spaces. The UE may monitor CORESETs associated with certain search spaces based on the search space settings.

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

By PUCCH, channel state information (CSI), acknowledgment information (for example, Hybrid Automatic Repeat reQuest ACKnowledgement (HARQ-ACK), ACK/NACK, etc.) and scheduling request (Scheduling Request ( SR)) may be transmitted. A random access preamble for connection establishment with a cell may be transmitted by the PRACH.

In addition, in the present disclosure, downlink, uplink, etc. may be expressed without adding "link". Also, various channels may be expressed without adding "Physical" to the head.

In the wireless communication system 1, synchronization signals (SS), downlink reference signals (DL-RS), etc. may be transmitted. In the radio communication system 1, the DL-RS includes a cell-specific reference signal (CRS), a channel state information reference signal (CSI-RS), a demodulation reference signal (DeModulation Reference Signal (DMRS)), Positioning Reference Signal (PRS)), Phase Tracking Reference Signal (PTRS)), etc. may be transmitted.

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

Also, in the radio communication system 1, even if measurement reference signals (SRS), demodulation reference signals (DMRS), etc. are transmitted as uplink reference signals (UL-RS), good. Note that DMRS may also be called a user terminal-specific reference signal (UE-specific reference signal).

(base station)
FIG. 13 is a diagram illustrating an example of the configuration of a base station according to one embodiment. The base station 10 comprises a control section 110 , a transmission/reception section 120 , a transmission/reception antenna 130 and a transmission line interface 140 . One or more of each of the control unit 110, the transmitting/receiving unit 120, the transmitting/receiving antenna 130, and the transmission line interface 140 may be provided.

It should be noted that this example mainly shows the functional blocks that characterize the present embodiment, and it may be assumed that the base station 10 also has other functional blocks necessary for wireless communication. A part of the processing of each unit described below may be omitted.

The control unit 110 controls the base station 10 as a whole. The control unit 110 can be configured from a controller, a control circuit, and the like, which are explained based on common recognition in the technical field according to the present disclosure.

The control unit 110 may control signal generation, scheduling (eg, resource allocation, mapping), and the like. The control unit 110 may control transmission/reception, measurement, etc. using the transmission/reception unit 120 , the transmission/reception antenna 130 and the transmission line interface 140 . The control unit 110 may generate data to be transmitted as a signal, control information, a sequence, etc., and transfer them to the transmission/reception unit 120 . The control unit 110 may perform call processing (setup, release, etc.) of communication channels, state management of the base station 10, management of radio resources, and the like.

The transmitting/receiving section 120 may include a baseband section 121 , a radio frequency (RF) section 122 and a measuring section 123 . The baseband section 121 may include a transmission processing section 1211 and a reception processing section 1212 . The transmitting/receiving unit 120 is configured from a transmitter/receiver, an RF circuit, a baseband circuit, a filter, a phase shifter, a measurement circuit, a transmitting/receiving circuit, etc., which are explained based on common recognition in the technical field according to the present disclosure. be able to.

The transmission/reception unit 120 may be configured as an integrated transmission/reception unit, or may be configured from a transmission unit and a reception unit. The transmission section may be composed of the transmission processing section 1211 and the RF section 122 . The receiving section may be composed of a reception processing section 1212 , an RF section 122 and a measurement section 123 .

The transmitting/receiving antenna 130 can be configured from an antenna described based on common recognition in the technical field related to the present disclosure, such as an array antenna.

The transmitting/receiving unit 120 may transmit the above-described downlink channel, synchronization signal, downlink reference signal, and the like. The transmitting/receiving unit 120 may receive the above-described uplink channel, uplink reference signal, and the like.

The transmitting/receiving unit 120 may form at least one of the transmission beam and the reception beam using digital beamforming (eg, precoding), analog beamforming (eg, phase rotation), or the like.

The transmission/reception unit 120 (transmission processing unit 1211) performs Packet Data Convergence Protocol (PDCP) layer processing, Radio Link Control (RLC) layer processing (for example, RLC retransmission control), Medium Access Control (MAC) layer processing (for example, HARQ retransmission control), etc. may be performed to generate a bit string to be transmitted.

The transmission/reception unit 120 (transmission processing unit 1211) performs channel coding (which may include error correction coding), modulation, mapping, filtering, and discrete Fourier transform (DFT) on the bit string to be transmitted. Processing (if necessary), Inverse Fast Fourier Transform (IFFT) processing, precoding, transmission processing such as digital-to-analog conversion may be performed, and the baseband signal may be output.

The transmitting/receiving unit 120 (RF unit 122) may perform modulation to a radio frequency band, filter processing, amplification, and the like on the baseband signal, and may transmit the radio frequency band signal via the transmitting/receiving antenna 130. .

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

The transmission/reception unit 120 (reception processing unit 1212) performs analog-to-digital conversion, Fast Fourier transform (FFT) processing, and Inverse Discrete Fourier transform (IDFT) processing on the acquired baseband signal. )) processing (if necessary), filtering, demapping, demodulation, decoding (which may include error correction decoding), MAC layer processing, RLC layer processing and PDCP layer processing. User data and the like may be acquired.

The transmitting/receiving unit 120 (measuring unit 123) may measure the received signal. For example, the measurement unit 123 may perform Radio Resource Management (RRM) measurement, Channel State Information (CSI) measurement, etc. based on the received signal. The measurement unit 123 measures received power (for example, Reference Signal Received Power (RSRP)), reception quality (for example, Reference Signal Received Quality (RSRQ), Signal to Interference plus Noise Ratio (SINR), Signal to Noise Ratio (SNR)) , signal strength (for example, Received Signal Strength Indicator (RSSI)), channel information (for example, CSI), and the like may be measured. The measurement result may be output to control section 110 .

The transmission path interface 140 transmits and receives signals (backhaul signaling) to and from devices included in the core network 30, other base stations 10, etc., and user data (user plane data) for the user terminal 20, control plane data, and the like. Data and the like may be obtained, transmitted, and the like.

Note that the transmitter and receiver of the base station 10 in the present disclosure may be configured by at least one of the transmitter/receiver 120, the transmitter/receiver antenna 130, and the transmission path interface 140.

Note that the transmitting/receiving unit 120 may receive reference signals (eg, DMRS, SRS).

The control unit 110 may control prediction based on the second setting of the reference signal using a machine learning model trained based on the first setting of the reference signal.

(user terminal)
FIG. 14 is a diagram illustrating an example of the configuration of a user terminal according to an embodiment; The user terminal 20 includes a control section 210 , a transmission/reception section 220 and a transmission/reception antenna 230 . One or more of each of the control unit 210, the transmitting/receiving unit 220, and the transmitting/receiving antenna 230 may be provided.

It should be noted that this example mainly shows the functional blocks of the features of the present embodiment, and it may be assumed that the user terminal 20 also has other functional blocks necessary for wireless communication. A part of the processing of each unit described below may be omitted.

The control unit 210 controls the user terminal 20 as a whole. The control unit 210 can be configured from a controller, a control circuit, and the like, which are explained based on common recognition in the technical field according to the present disclosure.

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

The transmitting/receiving section 220 may include a baseband section 221 , an RF section 222 and a measurement section 223 . The baseband section 221 may include a transmission processing section 2211 and a reception processing section 2212 . The transmitting/receiving unit 220 can be configured from a transmitter/receiver, an RF circuit, a baseband circuit, a filter, a phase shifter, a measurement circuit, a transmitting/receiving circuit, etc., which are explained based on common recognition in the technical field according to the present disclosure.

The transmission/reception unit 220 may be configured as an integrated transmission/reception unit, or may be configured from a transmission unit and a reception unit. The transmission section may be composed of a transmission processing section 2211 and an RF section 222 . The receiving section may include a reception processing section 2212 , an RF section 222 and a measurement section 223 .

The transmitting/receiving antenna 230 can be configured from an antenna described based on common recognition in the technical field related to the present disclosure, such as an array antenna.

The transmitting/receiving unit 220 may receive the above-described downlink channel, synchronization signal, downlink reference signal, and the like. The transmitting/receiving unit 220 may transmit the above-described uplink channel, uplink reference signal, and the like.

The transmitter/receiver 220 may form at least one of the transmission beam and the reception beam using digital beamforming (eg, precoding), analog beamforming (eg, phase rotation), or the like.

The transmission/reception unit 220 (transmission processing unit 2211) performs PDCP layer processing, RLC layer processing (for example, RLC retransmission control), MAC layer processing (for example, for data and control information acquired from the control unit 210, for example , HARQ retransmission control), etc., to generate a bit string to be transmitted.

The transmitting/receiving unit 220 (transmission processing unit 2211) performs channel coding (which may include error correction coding), modulation, mapping, filtering, DFT processing (if necessary), and IFFT processing on a bit string to be transmitted. , precoding, digital-analog conversion, and other transmission processing may be performed, and the baseband signal may be output.

Whether or not to apply DFT processing may be based on transform precoding settings. Transmitting/receiving unit 220 (transmission processing unit 2211), for a certain channel (for example, PUSCH), if transform precoding is enabled, the above to transmit the channel using the DFT-s-OFDM waveform The DFT process may be performed as the transmission process, or otherwise the DFT process may not be performed as the transmission process.

The transmitting/receiving unit 220 (RF unit 222) may perform modulation to a radio frequency band, filter processing, amplification, and the like on the baseband signal, and may transmit the radio frequency band signal via the transmitting/receiving antenna 230. .

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

The transmission/reception unit 220 (reception processing unit 2212) performs analog-to-digital conversion, FFT processing, IDFT processing (if necessary), filtering, demapping, demodulation, decoding (error correction) on the acquired baseband signal. decoding), MAC layer processing, RLC layer processing, PDCP layer processing, and other reception processing may be applied to acquire user data and the like.

The transmitting/receiving section 220 (measuring section 223) may measure the received signal. For example, the measurement unit 223 may perform RRM measurement, CSI measurement, etc. based on the received signal. The measuring unit 223 may measure received power (eg, RSRP), received quality (eg, RSRQ, SINR, SNR), signal strength (eg, RSSI), channel information (eg, CSI), and the like. The measurement result may be output to control section 210 .

The transmitter and receiver of the user terminal 20 in the present disclosure may be configured by at least one of the transmitter/receiver 220, the transmitter/receiver antenna 230, and the transmission line interface 240.

Note that the transmitting/receiving unit 220 may receive reference signals (eg, DMRS, CSI-RS).

Control unit 210 uses a machine learning model trained based on a first setting of the reference signal (eg, a training mode setting) to set a second setting of the reference signal (eg, a test mode setting). You may control to perform prediction based on.

The transmitting/receiving unit 220 may receive information instructing training of the machine learning model based on the first setting or prediction based on the second setting.

The transmitting/receiving unit 220 may receive information on the trained machine learning model from the base station 10 or another user terminal 20.

The control unit 210 may control transmission of information in a desired format for the machine learning model to the base station 10 or other user terminals 20 .

(Hardware configuration)
It should be noted that the block diagrams used in the description of the above embodiments show blocks in units of functions. These functional blocks (components) are realized by any combination of at least one of hardware and software. Also, the method of implementing each functional block is not particularly limited. That is, each functional block may be implemented using one device that is physically or logically coupled, or directly or indirectly using two or more devices that are physically or logically separated (e.g. , wired, wireless, etc.) and may be implemented using these multiple devices. A functional block may be implemented by combining software in the one device or the plurality of devices.

where function includes judgment, decision, determination, calculation, calculation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, deem , broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, assigning, etc. Not limited. For example, a functional block (component) that performs transmission may be called a transmitting unit, a transmitter, or the like. In either case, as described above, the implementation method is not particularly limited.

For example, a base station, a user terminal, etc. in an embodiment of the present disclosure may function as a computer that performs processing of the wireless communication method of the present disclosure. FIG. 15 is a diagram illustrating an example of hardware configurations of a base station and user terminals according to an embodiment. The base station 10 and user terminal 20 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like. .

In the present disclosure, terms such as apparatus, circuit, device, section, and unit can be read interchangeably. The hardware configuration of the base station 10 and the user terminal 20 may be configured to include one or more of each device shown in the figure, or may be configured without some devices.

For example, although only one processor 1001 is illustrated, there may be multiple processors. Also, processing may be performed by one processor, or processing may be performed by two or more processors concurrently, serially, or otherwise. Note that processor 1001 may be implemented by one or more chips.

Each function in the base station 10 and the user terminal 20, for example, by loading predetermined software (program) on hardware such as a processor 1001 and a memory 1002, the processor 1001 performs calculations, communication via the communication device 1004 and at least one of reading and writing data in the memory 1002 and the storage 1003 .

The processor 1001, for example, operates an operating system and controls the entire computer. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, registers, and the like. For example, at least part of the above-described control unit 110 (210), transmission/reception unit 120 (220), etc. may be realized by the processor 1001. FIG.

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

The memory 1002 is a computer-readable recording medium, such as Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically EPROM (EEPROM), Random Access Memory (RAM), or at least any other suitable storage medium. may be configured by one. The memory 1002 may also be called a register, cache, main memory (main storage device), or the like. The memory 1002 can store executable programs (program code), software modules, etc. for implementing a wireless communication method according to an embodiment of the present disclosure.

The storage 1003 is a computer-readable recording medium, for example, a flexible disk, a floppy (registered trademark) disk, a magneto-optical disk (for example, a compact disk (Compact Disc ROM (CD-ROM), etc.), a digital versatile disk, Blu-ray disc), removable disc, hard disk drive, smart card, flash memory device (e.g., card, stick, key drive), magnetic stripe, database, server, or other suitable storage medium may be configured by Storage 1003 may also be called an auxiliary storage device.

The communication device 1004 is hardware (transmitting/receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also called a network device, a network controller, a network card, a communication module, or the like. The communication device 1004 includes a high-frequency switch, duplexer, filter, frequency synthesizer, etc. in order to realize at least one of frequency division duplex (FDD) and time division duplex (TDD), for example. may be configured to include For example, the transmitting/receiving unit 120 (220), the transmitting/receiving antenna 130 (230), and the like described above may be realized by the communication device 1004. FIG. The transmitter/receiver 120 (220) may be physically or logically separated into a transmitter 120a (220a) and a receiver 120b (220b).

The input device 1005 is an input device (for example, keyboard, mouse, microphone, switch, button, sensor, etc.) that receives input from the outside. The output device 1006 is an output device (for example, a display, a speaker, a Light Emitting Diode (LED) lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated (for example, a touch panel).

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

In addition, the base station 10 and the user terminal 20 include a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), etc. It may be configured including hardware, and a part or all of each functional block may be realized using the hardware. For example, processor 1001 may be implemented using at least one of these pieces of hardware.

(Modification)
The terms explained in this disclosure and the terms necessary for understanding the present disclosure may be replaced with terms having the same or similar meanings. For example, channel, symbol and signal (signal or signaling) may be interchanged. A signal may also be a message. A reference signal may be abbreviated as RS, and may also be called a pilot, a pilot signal, etc., depending on the applicable standard. A component carrier (CC) may also be called a cell, a frequency carrier, a carrier frequency, or the like.

A radio frame may consist of one or more periods (frames) in the time domain. Each of the one or more periods (frames) that make up a radio frame may be called a subframe. Furthermore, a subframe may consist of one or more slots in the time domain. A subframe may be a fixed time length (eg, 1 ms) independent of numerology.

Here, a numerology may be a communication parameter applied to at least one of transmission and reception of a certain signal or channel. Numerology, for example, subcarrier spacing (SCS), bandwidth, symbol length, cyclic prefix length, transmission time interval (TTI), number of symbols per TTI, radio frame configuration , a particular filtering process performed by the transceiver in the frequency domain, a particular windowing process performed by the transceiver in the time domain, and/or the like.

A slot may consist of one or more symbols (Orthogonal Frequency Division Multiplexing (OFDM) symbol, Single Carrier Frequency Division Multiple Access (SC-FDMA) symbol, etc.) in the time domain. A slot may also be a unit of time based on numerology.

A slot may contain multiple mini-slots. Each minislot may consist of one or more symbols in the time domain. A minislot may also be referred to as a subslot. A minislot may consist of fewer symbols than a slot. A PDSCH (or PUSCH) transmitted in time units larger than a minislot may be referred to as PDSCH (PUSCH) Mapping Type A. PDSCH (or PUSCH) transmitted using minislots may be referred to as PDSCH (PUSCH) mapping type B.

Radio frames, subframes, slots, minislots and symbols all represent time units when transmitting signals. Radio frames, subframes, slots, minislots and symbols may be referred to by other corresponding designations. Note that time units such as frames, subframes, slots, minislots, and symbols in the present disclosure may be read interchangeably.

For example, one subframe may be called a TTI, a plurality of consecutive subframes may be called a TTI, and one slot or one minislot may be called a TTI. That is, at least one of the subframe and TTI may be a subframe (1 ms) in existing LTE, a period shorter than 1 ms (eg, 1-13 symbols), or a period longer than 1 ms may be Note that the unit representing the TTI may be called a slot, mini-slot, or the like instead of a subframe.

Here, TTI refers to, for example, the minimum scheduling time unit in wireless communication. For example, in the LTE system, a base station performs scheduling to allocate radio resources (frequency bandwidth, transmission power, etc. that can be used by each user terminal) to each user terminal on a TTI basis. Note that the definition of TTI is not limited to this.

A TTI may be a transmission time unit such as a channel-encoded data packet (transport block), code block, or codeword, or may be a processing unit such as scheduling and link adaptation. Note that when a TTI is given, the time interval (for example, the number of symbols) in which transport blocks, code blocks, codewords, etc. are actually mapped may be shorter than the TTI.

When one slot or one minislot is called a TTI, one or more TTIs (that is, one or more slots or one or more minislots) may be the minimum scheduling time unit. Also, the number of slots (the number of mini-slots) constituting the minimum time unit of the scheduling may be controlled.

A TTI having a time length of 1 ms may be called a normal TTI (TTI in 3GPP Rel. 8-12), normal TTI, long TTI, normal subframe, normal subframe, long subframe, slot, or the like. A TTI that is shorter than a normal TTI may be called a shortened TTI, a short TTI, a partial or fractional TTI, a shortened subframe, a short subframe, a minislot, a subslot, a slot, and the like.

Note that the long TTI (e.g., normal TTI, subframe, etc.) may be replaced with a TTI having a time length exceeding 1 ms, and the short TTI (e.g., shortened TTI, etc.) is less than the TTI length of the long TTI and 1 ms A TTI having the above TTI length may be read instead.

A resource block (RB) is a resource allocation unit in the time domain and frequency domain, and may include one or more consecutive subcarriers (subcarriers) in the frequency domain. The number of subcarriers included in the RB may be the same regardless of the neumerology, eg twelve. The number of subcarriers included in an RB may be determined based on neumerology.

Also, an RB may contain one or more symbols in the time domain and may be 1 slot, 1 minislot, 1 subframe or 1 TTI long. One TTI, one subframe, etc. may each be configured with one or more resource blocks.

One or more RBs are Physical Resource Block (PRB), Sub-Carrier Group (SCG), Resource Element Group (REG), PRB pair, RB Also called a pair.

Also, a resource block may be composed of one or more resource elements (Resource Element (RE)). For example, 1 RE may be a radio resource region of 1 subcarrier and 1 symbol.

A Bandwidth Part (BWP) (which may also be called a bandwidth part) represents a subset of contiguous common resource blocks (RBs) for a numerology on a carrier. good too. Here, the common RB may be identified by an RB index based on the common reference point of the carrier. PRBs may be defined in a BWP and numbered within that BWP.

BWP may include UL BWP (BWP for UL) and DL BWP (BWP for DL). One or multiple BWPs may be configured for a UE within one carrier.

At least one of the configured BWPs may be active, and the UE may not expect to transmit or receive a given signal/channel outside the active BWP. Note that "cell", "carrier", etc. in the present disclosure may be read as "BWP".

It should be noted that the structures of radio frames, subframes, slots, minislots, symbols, etc. described above are merely examples. For example, the number of subframes contained in a radio frame, the number of slots per subframe or radio frame, the number of minislots contained within a slot, the number of symbols and RBs contained in a slot or minislot, the number of Configurations such as the number of subcarriers and the number of symbols in a TTI, symbol length, cyclic prefix (CP) length, etc. can be varied.

In addition, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values from a predetermined value, or may be expressed using other corresponding information. may be represented. For example, radio resources may be indicated by a predetermined index.

The names used for parameters and the like in this disclosure are not restrictive names in any respect. Further, the formulas and the like using these parameters may differ from those expressly disclosed in this disclosure. Since the various channels (PUCCH, PDCCH, etc.) and information elements can be identified by any suitable names, the various names assigned to these various channels and information elements are not limiting names in any way. .

The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may refer to voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these. may be represented by a combination of

Also, information, signals, etc. can be output from a higher layer to a lower layer and/or from a lower layer to a higher layer. Information, signals, etc. may be input and output through multiple network nodes.

Input/output information, signals, etc. may be stored in a specific location (for example, memory), or may be managed using a management table. Input and output information, signals, etc. may be overwritten, updated or appended. Output information, signals, etc. may be deleted. Input information, signals, etc. may be transmitted to other devices.

Notification of information is not limited to the aspects/embodiments described in the present disclosure, and may be performed using other methods. For example, the notification of information in the present disclosure includes physical layer signaling (e.g., Downlink Control Information (DCI)), Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, broadcast information (Master Information Block (MIB), System Information Block (SIB), etc.), Medium Access Control (MAC) signaling), other signals, or combinations thereof may be performed by

The physical layer signaling may also be called Layer 1/Layer 2 (L1/L2) control information (L1/L2 control signal), L1 control information (L1 control signal), and the like. RRC signaling may also be called an RRC message, and may be, for example, an RRC connection setup message, an RRC connection reconfiguration message, or the like. Also, MAC signaling may be notified using, for example, a MAC Control Element (CE).

In addition, notification of predetermined information (for example, notification of “being X”) is not limited to explicit notification, but implicit notification (for example, by not notifying the predetermined information or by providing another information by notice of

The determination may be made by a value (0 or 1) represented by 1 bit, or by a boolean value represented by true or false. , may be performed by numerical comparison (eg, comparison with a predetermined value).

Software, whether referred to as software, firmware, middleware, microcode, hardware description language or otherwise, includes instructions, instruction sets, code, code segments, program code, programs, subprograms, and software modules. , applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, and the like.

In addition, software, instructions, information, etc. may be transmitted and received via a transmission medium. For example, the software uses wired technology (coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), etc.) and/or wireless technology (infrared, microwave, etc.) , a server, or other remote source, these wired and/or wireless technologies are included within the definition of transmission media.

The terms "system" and "network" used in this disclosure may be used interchangeably. A “network” may refer to devices (eg, base stations) included in a network.

In the present disclosure, "precoding", "precoder", "weight (precoding weight)", "Quasi-Co-Location (QCL)", "Transmission Configuration Indication state (TCI state)", "spatial "spatial relation", "spatial domain filter", "transmission power", "phase rotation", "antenna port", "antenna port group", "layer", "number of layers", Terms such as "rank", "resource", "resource set", "resource group", "beam", "beam width", "beam angle", "antenna", "antenna element", "panel" are interchangeable. can be used as intended.

In the present disclosure, "base station (BS)", "radio 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,” “component carrier,” etc. may be used interchangeably. A base station may also be referred to by terms such as macrocell, small cell, femtocell, picocell, and the like.

A base station can accommodate one or more (eg, three) cells. When a base station accommodates multiple cells, the overall coverage area of the base station can be partitioned into multiple smaller areas, and each smaller area is assigned to a base station subsystem (e.g., a small indoor base station (Remote Radio)). Head (RRH))) may also provide communication services. The terms "cell" or "sector" refer to part or all of the coverage area of at least one of the base stations and base station subsystems that serve communication within such coverage.

In this disclosure, terms such as "Mobile Station (MS)", "user terminal", "User Equipment (UE)", and "terminal" are used interchangeably. can be

Mobile stations include 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. , a handset, a user agent, a mobile client, a client, or some other suitable term.

At least one of the base station and the mobile station may be called a transmitting device, a receiving device, a wireless communication device, or the like. At least one of the base station and the mobile station may be a device mounted on a mobile object, the mobile object itself, or the like. The mobile object may be a vehicle (e.g., car, airplane, etc.), an unmanned mobile object (e.g., drone, self-driving car, etc.), or a robot (manned or unmanned ). Note that at least one of the base station and the mobile station includes devices that do not necessarily move during communication operations. For example, at least one of the base station and mobile station may be an Internet of Things (IoT) device such as a sensor.

Also, the base station in the present disclosure may be read as a user terminal. For example, communication between a base station and a user terminal is replaced with communication between multiple user terminals (for example, Device-to-Device (D2D), Vehicle-to-Everything (V2X), etc.) Regarding the configuration, each aspect/embodiment of the present disclosure may be applied. In this case, the user terminal 20 may have the functions of the base station 10 described above. Also, words such as "up" and "down" may be replaced with words corresponding to inter-terminal communication (for example, "side"). For example, uplink channels, downlink channels, etc. may be read as side channels.

Similarly, user terminals in the present disclosure may be read as base stations. In this case, the base station 10 may have the functions of the user terminal 20 described above.

In the present disclosure, operations that are assumed to be performed by the base station may be performed by its upper node in some cases. In a network that includes one or more network nodes with a base station, various operations performed for communication with a terminal may involve the base station, one or more network nodes other than the base station (e.g., Clearly, this can be done by a Mobility Management Entity (MME), Serving-Gateway (S-GW), etc. (but not limited to these) or a combination thereof.

Each aspect/embodiment described in the present disclosure may be used alone, may be used in combination, or may be used by switching along with execution. Also, the processing procedures, sequences, flowcharts, etc. of each aspect/embodiment described in the present disclosure may be rearranged as long as there is no contradiction. For example, the methods described in this disclosure present elements of the various steps using a sample order, and are not limited to the specific order presented.

Each aspect/embodiment described in this disclosure includes 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) (xG (x is, for example, an integer or a decimal number)), Future Radio Access (FRA), New - Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB) , IEEE 802.11 (Wi-Fi®), IEEE 802.16 (WiMAX®), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth®, or other suitable wireless It may be applied to systems using communication methods, next-generation systems extended based on these, and the like. Also, multiple systems may be applied in combination (for example, a combination of LTE or LTE-A and 5G).

The term "based on" as used in this disclosure does not mean "based only on" unless otherwise specified. In other words, the phrase "based on" means both "based only on" and "based at least on."

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

The term "determining" as used in this disclosure may encompass a wide variety of actions. For example, "determination" includes judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiry ( For example, looking up in a table, database, or another data structure), ascertaining, etc. may be considered to be "determining."

Also, "determining (deciding)" includes receiving (e.g., receiving information), transmitting (e.g., transmitting information), input, output, access ( accessing (e.g., accessing data in memory), etc.

Also, "determining" is considered to be "determining" resolving, selecting, choosing, establishing, comparing, etc. good too. That is, "determining (determining)" may be regarded as "determining (determining)" some action.

Also, "judgment (decision)" may be read as "assuming", "expecting", or "considering".

"Maximum transmit power" described in this disclosure may mean the maximum value of transmit power, may mean the nominal maximum transmit power (the nominal UE maximum transmit power), or may mean the rated maximum transmit power (the rated UE maximum transmit power).

The terms “connected”, “coupled”, or any variation thereof, as used in this disclosure, refer to any connection or coupling, direct or indirect, between two or more elements. and can include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. Couplings or connections between elements may be physical, logical, or a combination thereof. For example, "connection" may be read as "access".

In this disclosure, when two elements are connected, using one or more wires, cables, printed electrical connections, etc., and as some non-limiting and non-exhaustive examples, radio frequency domain, microwave They can be considered to be “connected” or “coupled” together using the domain, electromagnetic energy having wavelengths in the optical (both visible and invisible) domain, and the like.

In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean that "A and B are different from C". Terms such as "separate," "coupled," etc. may also be interpreted in the same manner as "different."

Where "include," "including," and variations thereof are used in this disclosure, these terms are inclusive, as is the term "comprising." is intended. Furthermore, the term "or" as used in this disclosure is not intended to be an exclusive OR.

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

Although the invention according to the present disclosure has been described in detail above, it is obvious to those skilled in the art that the invention according to the present disclosure is not limited to the embodiments described in the present disclosure. The invention according to the present disclosure can be implemented as modifications and changes without departing from the spirit and scope of the invention determined based on the description of the claims. Therefore, the description of the present disclosure is for illustrative purposes and does not impose any limitation on the invention according to the present disclosure.

Claims

a receiver that receives a reference signal;
a control unit that controls prediction based on a second setting of the reference signal using a machine learning model trained based on the first setting of the reference signal.
The terminal according to claim 1, wherein the receiving unit receives information instructing training of the machine learning model based on the first setting or prediction based on the second setting.
The terminal according to claim 1 or claim 2, wherein the receiving unit receives information on the trained machine learning model.
The terminal according to any one of claims 1 to 3, wherein the control unit controls transmission of information in a desired format of information for the machine learning model.
receiving a reference signal;
using a machine learning model trained based on the first setting of the reference signal to control prediction based on the second setting of the reference signal.
a receiver that receives a reference signal;
a controller that controls prediction based on a second setting of the reference signal using a machine learning model trained on the first setting of the reference signal.