Method and apparatus for beam management in a communication system

Abstract

Techniques for beam management in a communication system are disclosed. Provided is a method of a terminal, comprising the steps of: receiving a reference signal from a base station through a primary candidate beam; acquiring measurement information about a reference signal of the primary candidate beam; using an AI / ML model to select a secondary candidate beam based on measurement information on the primary candidate beam; and transmitting information on the selected secondary candidate beam to the base station.

Description

Technical Field

[0001] The present disclosure relates to a beam management technique in a communication system, and more particularly, to a beam management technique for managing beams using artificial neural network (AI) / machine learning (ML) in a communication system. Background Art

[0002] With the development of information and communication technology, various wireless communication technologies have been developed. Typical wireless communication technologies include Long Term Evolution (LTE) and New Radio (NR) defined in the 3rd Generation Partnership Project (3GPP) standard. LTE may be one of the fourth generation (4G) wireless communication technologies, and NR may be one of the fifth generation (5G) wireless communication technologies.

[0003] For processing of wireless data that has rapidly increased after the commercialization of the fourth generation (4G) communication system (e.g., long term evolution (LTE) communication system or advanced LTE (LTE-A) communication system), a fifth generation (5G) communication system (e.g., new radio (NR) communication system) using a frequency band higher than that of the 4G communication system (e.g., a frequency band of 6 GHz or more) as well as a frequency band of the 4G communication system (e.g., a frequency band of 6 GHz or less) is being considered. The 5G communication system may support enhanced mobile broadband (eMBB), ultra-reliable and low latency communication (URLLC), and massive machine type communication (mMTC).

[0004] Such a communication system may be designed in consideration of various scenarios, service requirements, potential system compatibility, etc. In particular, in order to perform broadband communication in a high frequency band, discussions on beam-based communication in a 5G NR communication system are active. Therefore, beam-based communication may be used continuously. In addition, the communication system may use artificial intelligence (AI) / machine learning (ML) to improve performance. Summary of the invention

[0005] Technical issues

[0006] The present disclosure aims to provide a method and apparatus for beam management in a communication system, which facilitates beam management using AI / ML techniques.

[0007] Technical Solution

[0008] According to the first exemplary embodiment of the present disclosure, a beam management method in a communication system as a terminal method for achieving the above-mentioned purpose may include: receiving a reference signal from a base station through a primary candidate beam; generating measurement information of the reference signal for the primary candidate beam; based on the measurement information for the primary candidate beam, selecting N secondary candidate beams using an artificial intelligence (AI) / machine learning (ML) model; and sending information about the selected N secondary candidate beams to the base station, wherein N is a positive integer.

[0009] The measurement information for the primary candidate beams may include at least one of a reference signal received power (RSRP), a reference signal received quality (RSRQ), a signal to interference plus noise ratio (SINR), or a signal to noise ratio (SNR) for each of the reference signals of the primary candidate beams.

[0010] Each of the reference signals for the primary candidate beams may be one of a synchronization signal block (SSB), a channel state information reference signal (CSI-RS), or a positioning RS (PRS).

[0011] The terminal may perform the selection of the N secondary candidate beams using the AI / ML model based on the measurement information for the primary candidate beams by additionally using the location and movement path information of the terminal.

[0012] The location and moving path information of the terminal may include at least one of a location, a track, an angle of arrival (AOA), or an angle of departure (AOD).

[0013] The method may also include: before receiving the reference signal of the primary candidate beam from the base station through the primary candidate beam, receiving a reference signal from the base station through the beam; obtaining a received signal strength of the reference signal for the beam; selecting the primary candidate beam based on the received signal strength of the beam; and sending information about the selected primary candidate beam to the base station.

[0014] The method may also include: receiving a reference signal from the base station through a tertiary candidate beam selected from among the secondary candidate beams; generating measurement information of the reference signal for the tertiary candidate beam; selecting M quaternary candidate beams using the AI / ML model based on the measurement information for the tertiary candidate beam; and sending information about the selected M quaternary candidate beams to the base station, wherein M is a positive integer.

[0015] The method may also include: receiving configuration information about the reference signal for the primary candidate beam from the base station through radio resource control (RRC) signaling, wherein the terminal uses the configuration information to receive some reference signals when receiving the reference signal of the primary candidate beam from the base station through the primary candidate beam.

[0016] The configuration information about the reference signal for the primary candidate beam includes a reference signal type and a reference signal period.

[0017] The method may also include: detecting a beam failure; selecting an alternative candidate beam using the AI / ML model based on measurement information for the primary candidate beam; and sending a beam failure report including information about the alternative candidate beam to the base station.

[0018] The method may further include receiving information about resources for beam failure reporting from the base station, wherein the terminal sends the beam failure report including the information about the alternative candidate beam to the base station using the resources for beam failure reporting.

[0019] According to the second exemplary embodiment of the present disclosure, a beam management method in a communication system as a method of a base station for achieving the above-mentioned purpose may include: sending a reference signal to a terminal through a primary candidate beam; receiving information about a secondary candidate beam, wherein the secondary candidate beam is selected by the terminal based on measurement information for the primary candidate beam; based on the information about the secondary candidate beam, selecting a tertiary candidate beam using an AI / ML model; and sending a reference signal to the terminal through the tertiary candidate beam.

[0020] The base station may perform the selection of the tertiary candidate beam using the AI / ML model based on the information about the secondary candidate beams by additionally using at least one of interference information, resource allocation information, or neighboring base station information.

[0021] The method may further include: before transmitting the reference signal to the terminal through the primary candidate beam, transmitting the reference signal to the terminal using a beam; and receiving, from the terminal, information on the primary candidate beam selected based on received signal strength of the beam.

[0022] The method may further include: transmitting information about resources for beam failure reporting to the terminal; and receiving a beam failure report including information about a substitute candidate beam from the terminal using the resources for beam failure reporting.

[0023] The method may further include: selecting a fourth-level candidate beam using the AI / ML model based on the information about the alternative candidate beams; and transmitting the information about the fourth-level candidate beams to the terminal.

[0024] According to the third exemplary embodiment of the present disclosure, a beam management device in a communication system as a terminal for achieving the above-mentioned purpose may include a processor, and the processor may cause the terminal to perform the following operations: receive a reference signal from a base station through a primary candidate beam; generate measurement information of the reference signal for the primary candidate beam; select N secondary candidate beams based on the measurement information for the primary candidate beam using an artificial intelligence (AI) / machine learning (ML) model; and send information about the selected N secondary candidate beams to the base station, wherein N is a positive integer.

[0025] The processor may also cause the terminal to perform the following operations: before receiving the reference signal from the base station through the primary candidate beam, receive a reference signal from the base station through the beam; obtain a received signal strength of the reference signal for the beam; select the primary candidate beam based on the received signal strength of the beam; and send information about the selected primary candidate beam to the base station.

[0026] The processor may also cause the terminal to perform the following operations: detect a beam failure; select an alternative candidate beam using the AI / ML model based on measurement information for the primary candidate beam; and send a beam failure report including information about the alternative candidate beam to the base station.

[0027] The processor may also cause the terminal to perform the following operations: receive information about resources for beam failure reporting from the base station, wherein the terminal sends a beam failure report including information about the alternative candidate beam to the base station using the resources for beam failure reporting.

[0028] Beneficial Effects

[0029] According to the present disclosure, a method for managing beams based on AI / ML is provided. In addition, the present disclosure provides a method for configuring measurement and beam selection periods and beam periods using AI / ML. In addition, the present disclosure provides a method for performing a beam failure recovery process by utilizing AI / ML functions. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a conceptual diagram illustrating a first exemplary embodiment of a communication system.

[0031] Figure 2 is a block diagram showing a first exemplary embodiment of a communication node constituting a communication system.

[0032] Figure 3 is a block diagram illustrating a first exemplary embodiment of a Radio Access Network (RAN) intelligent framework using AI / ML.

[0033] Figure 4 is a conceptual diagram showing a first exemplary embodiment of a beam used in a communication system.

[0034] Figure 5a is a sequence diagram illustrating a first exemplary embodiment of a beam management method in a communication system.

[0035] Figure 5b is a sequence diagram illustrating a second exemplary embodiment of a beam management method in a communication system.

[0036] Figure 5c is a sequence diagram illustrating a third exemplary embodiment of a beam management method in a communication system.

[0037] Figure 6 is a sequence diagram illustrating a fourth exemplary embodiment of a beam management method in a communication system.

[0038] Figure 7a is a sequence diagram illustrating a first exemplary embodiment of a beam management method in the event of a beam failure.

[0039] Figure 7b is a sequence diagram illustrating a second exemplary embodiment of a beam management method in the event of a beam failure.

[0040] Figure 8a is a conceptual diagram illustrating a first exemplary embodiment of a beam management method after a beam failure report.

[0041] Figure 8b is a conceptual diagram illustrating a second exemplary embodiment of a beam management method after a beam failure report.

[0042] Figure 9a is a conceptual diagram showing a first exemplary embodiment of a signaling method for a T1 period and a T2 period.

[0043] Figure 9b is a conceptual diagram showing a second exemplary embodiment of a signaling method for a T1 period and a T2 period.

[0044] Fig.10 is a conceptual diagram showing a first exemplary embodiment of a configuration method for a T1 period and a T2 period.

[0045] Fig.11 is a sequence diagram showing a first exemplary embodiment of a method for establishing an RRC connection between a terminal and a network.

[0046] Fig.12 is a sequence diagram showing a first exemplary embodiment of a method for transmitting UE capability information. DETAILED DESCRIPTION

[0047] Since the present disclosure may be modified in various ways and have several forms, specific exemplary embodiments will be shown in the drawings and will be described in detail in the detailed description. However, it should be understood that it is not intended to limit the present disclosure to specific exemplary embodiments, but on the contrary, the present disclosure will cover all modifications and substitutions that fall within the spirit and scope of the present disclosure.

[0048] Relational terms such as first, second, etc. can be used to describe various elements, but elements should not be limited by the terms. These terms are only used to distinguish one element from another element. For example, without departing from the scope of the present disclosure, a first component can be named as a second component, and the second component can also be similarly named as the first component. The term "and / or" represents any one or combination of multiple related and described items.

[0049] In exemplary embodiments of the present disclosure, “at least one of A and B” may refer to “at least one of A or B” or “at least one of a combination of one or more of A and B”. Furthermore, “one or more of A and B” may refer to “one or more of A or B” or “one or more of a combination of one or more of A and B”.

[0050] When it is mentioned that a certain component is “coupled” or “connected” to another component, it should be understood that the certain component is directly “coupled” or “connected” to the other component, or another component may be disposed therebetween. On the contrary, when it is mentioned that a certain component is “directly coupled” or “directly connected” to another component, it should be understood that no other component is disposed therebetween.

[0051] The terms used in this disclosure are only used to describe specific exemplary embodiments and are not intended to limit the present disclosure. Unless the context clearly dictates otherwise, singular expressions include plural expressions. In this disclosure, terms such as "including" or "having" are intended to indicate the presence of features, quantities, steps, operations, components, parts, or combinations thereof described in the specification, but it should be understood that these terms do not exclude the presence or addition of one or more features, quantities, steps, operations, components, parts, or combinations thereof.

[0052] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as those generally understood by those of ordinary skill in the art to which the present disclosure belongs. Terms commonly used and already in dictionaries should be interpreted as having meanings that match the contextual meanings in the art. In this specification, unless explicitly defined, terms are not necessarily interpreted as having formal meanings.

[0053] Hereinafter, the form of the present disclosure will be described in detail with reference to the accompanying drawings. In describing the present disclosure, in order to facilitate an overall understanding of the present disclosure, the same reference numerals refer to the same elements throughout the description of the accompanying drawings, and repeated descriptions thereof will be omitted.

[0054] Figure 1 is a conceptual diagram illustrating a first exemplary embodiment of a communication system.

[0055] refer to Figure 1 , the communication system 100 may include a plurality of communication nodes 110-1, 110-2, 110-3, 120-1, 120-2, 130-1, 130-2, 130-3, 130-4, 130-5, and 130-6. Here, the communication system may be referred to as a "communication network". Each of the plurality of communication nodes may support a communication protocol based on code division multiple access (CDMA), a communication protocol based on wideband CDMA (WCDMA), a communication protocol based on time division multiple access (TDMA), a communication protocol based on frequency division multiple access (FDMA), a communication protocol based on orthogonal frequency division multiplexing (OFDM), a communication protocol based on filtered OFDM, a communication protocol based on cyclic prefix OFDM (CP-OFDM), a communication protocol based on discrete Fourier transform spread OFDM (DFT-s-OFDM), a communication protocol based on orthogonal frequency division multiple access (OFDMA), a communication protocol based on single carrier FDMA (SC-FDMA), a communication protocol based on non-orthogonal multiple access (NOMA), a communication protocol based on generalized frequency division multiplexing (GFDM), a communication protocol based on filter band multi-carrier (FBMC), a communication protocol based on universal filter multi-carrier (UFMC), a communication protocol based on space division multiple access (SDMA), etc. Each of the plurality of communication nodes may have the following structure.

[0056] Figure 2 is a block diagram showing a first exemplary embodiment of a communication node constituting a communication system.

[0057] refer to Figure 2, the communication node 200 may include at least one processor 210, a memory 220, and a transceiver 230 connected to a network for performing communication. In addition, the communication node 200 may also include an input interface device 240, an output interface device 250, a storage device 260, and the like. The various components included in the communication node 200 may be connected to each other through a bus 270. However, the various components included in the communication node 200 may not be connected to the bus 270, but may be connected to the processor 210 through a separate interface or a separate bus. For example, the processor 210 may be connected to at least one of the memory 220, the transceiver 230, the input interface device 240, the output interface device 250, and the storage device 260 through a dedicated interface.

[0058] The processor 210 may execute a program stored in at least one of the memory 220 and the storage device 260. The processor 210 may refer to a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which the method according to an embodiment of the present disclosure is executed. Each of the memory 220 and the storage device 260 may be composed of at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory 220 may include at least one of a read-only memory (ROM) and a random access memory (RAM).

[0059] Reference again Figure 1 , the communication system 100 may include a plurality of base stations 110-1, 110-2, 110-3, 120-1, and 120-2 and a plurality of terminals 130-1, 130-2, 130-3, 130-4, 130-5, and 130-6. Each of the first base station 110-1, the second base station 110-2, and the third base station 110-3 may form a macro cell, and each of the fourth base station 120-1 and the fifth base station 120-2 may form a small cell. The fourth base station 120-1, the third terminal 130-3, and the fourth terminal 130-4 may belong to the cell coverage of the first base station 110-1. In addition, the second terminal 130-2, the fourth terminal 130-4, and the fifth terminal 130-5 may belong to the cell coverage of the second base station 110-2. In addition, the fifth base station 120-2, the fourth terminal 130-4, the fifth terminal 130-5 and the sixth terminal 130-6 may belong to the cell coverage of the third base station 110-3. In addition, the first terminal 130-1 may belong to the cell coverage of the fourth base station 120-1, and the sixth terminal 130-6 may belong to the cell coverage of the fifth base station 120-2.

[0060] Here, each of the multiple base stations 110-1, 110-2, 110-3, 120-1 and 120-2 may be referred to as a NodeB (NB), an evolved NodeB (eNB), a gNB, an advanced base station (ABS), a high reliability base station (HR-BS), a base transceiver station (BTS), a radio base station, a radio transceiver, an access point (AP), an access node, a radio access station (RAS), a mobile multi-hop relay base station (MMR-BS), a relay station (RS), an advanced relay station (ARS), a high reliability relay station (HR-RS), a home NodeB (HNB), a home eNodeB (HeNB), a road side unit (RSU), a radio remote head (RRH), a transmission point (TP), a transmitting and receiving point (TRP), a relay node, etc. Each of the multiple terminals 130-1, 130-2, 130-3, 130-4, 130-5 and 130-6 may be referred to as a user equipment (UE), a terminal equipment (TE), an advanced mobile station (AMS), a high reliability mobile station (HR-MS), a terminal, an access terminal, a mobile terminal, a station, a user station, a mobile station, a portable user station, a node, a device, etc.

[0061] Each of the plurality of communication nodes 110-1, 110-2, 110-3, 120-1, 120-2, 130-1, 130-2, 130-3, 130-4, 130-5, and 130-6 may support cellular communication (e.g., LTE, Advanced LTE (LTE-A), New Radio (NR), etc.). Each of the plurality of base stations 110-1, 110-2, 110-3, 120-1, and 120-2 may operate in the same frequency band or in different frequency bands. The plurality of base stations 110-1, 110-2, 110-3, 120-1, and 120-2 may be connected to each other via an ideal backhaul link or a non-ideal backhaul link, and exchange information with each other via the ideal backhaul link or the non-ideal backhaul link. In addition, each of the plurality of base stations 110-1, 110-2, 110-3, 120-1, and 120-2 may be connected to the core network via an ideal backhaul link or a non-ideal backhaul link. Each of the plurality of base stations 110-1, 110-2, 110-3, 120-1, and 120-2 may transmit a signal received from the core network to a corresponding terminal 130-1, 130-2, 130-3, 130-4, 130-5, or 130-6, and transmit a signal received from a corresponding terminal 130-1, 130-2, 130-3, 130-4, 130-5, or 130-6 to the core network.

[0062] Each of the multiple base stations 110-1, 110-2, 110-3, 120-1 and 120-2 can support OFDMA-based downlink (DL) transmission and SC-FDMA-based uplink (UL) transmission. In addition, each of the multiple base stations 110-1, 110-2, 110-3, 120-1 and 120-2 can support multiple-input multiple-output (MIMO) transmission (e.g., single-user MIMO (SU-MIMO), multi-user MIMO (MU-MIMO), massive MIMO, etc.), coordinated multi-point (CoMP) transmission, carrier aggregation (CA) transmission, transmission in unlicensed bands, device-to-device (D2D) communication (or proximity service (ProSe)), Internet of Things (IoT) communication, dual connectivity (DC), etc. Here, each of the plurality of terminals 130-1, 130-2, 130-3, 130-4, 130-5 and 130-6 may perform operations corresponding to operations of the plurality of base stations 110-1, 110-2, 110-3, 120-1 and 120-2 (i.e., operations supported by the plurality of base stations 110-1, 110-2, 110-3, 120-1 and 120-2).

[0063] Figure 3 is a block diagram illustrating a first exemplary embodiment of a Radio Access Network (RAN) intelligent framework using AI / ML.

[0064] refer to Figure 3 , the communication node may have RAN intelligence including an enabled AI / ML algorithm. Here, the AI / ML algorithm may be configured in various forms and may not be limited to a specific form. Hereinafter, the present disclosure will describe an AI / ML-based beam management method according to AI / ML functions and corresponding inputs and outputs based on an AI / ML model pre-configured according to the AI / ML algorithm.

[0065] The data collection entity 310 may provide input data to the model training entity 320 and the model reasoning entity 330. As an example, the input data may be at least one of a measurement value of another network entity, a feedback value of a terminal, and a feedback value for an output of an AI / ML model, but is not limited thereto.

[0066] The data collection entity 310 may provide training data to the model training entity 320. Here, the training data may be data provided for the AI / ML model training function. In addition, the data collection entity 310 may provide reasoning data to the model reasoning entity 330. Here, the reasoning data may be data provided for the AI / ML model reasoning function. The model training entity 320 may be an entity that performs training, validation, and testing of the AI / ML model, and may provide performance metrics for the AI / ML model.

[0067] The model training entity 320 may provide an AI / ML model to the model reasoning entity 330. Then, the model reasoning entity 330 may provide model performance feedback to the model training entity 320. That is, the model training entity 320 may perform training on the AI / ML model through feedback from the model reasoning entity 330. In addition, the model training entity 322 may update the AI / ML model through model performance feedback from the model reasoning entity 330. Then, the model training entity 322 may provide an updated AI / ML model to the model reasoning entity 330. In addition, the model reasoning entity 330 may receive reasoning data from the data collection entity 310. In addition, the model reasoning entity 330 may generate output using the AI / ML model and provide the output to the actor 340. Here, the actor 340 may perform an operation based on the output. In addition, the actor 340 may provide feedback to the data collection entity 310 based on the result of the operation.

[0068] That is, the communication node can use the data used to learn (or train) the AI / ML model to train and build the AI / ML model. The communication node can perform operations based on the AI / ML model by using the inference data as the input of the constructed AI / ML model and generating output through the AI / ML model. As a specific example, when the communication node performs AI / ML-based beam management, candidate beam information, measurement information, moving path information, or other information may be input to the model inference entity 330 as inference data. Then, information about the selected one or more beams may be determined as output information and fed back to the AI / ML model. However, this is merely an example and may not be limited to this, and the use of will be described below. Figure 3 Specific ways that AI / ML performs beam management.

[0069] Figure 4 is a conceptual diagram showing a first exemplary embodiment of a beam used in a communication system.

[0070] refer to Figure 4 , Figure 4 (a) may show one or more beam groups for measurement, and each beam group may include multiple beams. In addition, there may be multiple beam groups for measurement (for example, beam group M_A and beam group M_B). That is, the beam group for measurement may be a set of configurable beams. The terminal and the base station can communicate through the above beams. Here, Figure 4 (b) may show a candidate beam group for beam selection. The candidate beam group may include candidate beams 410. For example, Figure 4(b) may show a candidate beam group (e.g., beam group B_A) for a T1 period, in which one or more beams are selected based on measurement. In the T1 period, for measurement, the base station may send a reference signal (RS) through a plurality of candidate beams 410 based on the candidate beam group. The base station and the terminal may determine the selected beam 420 by measuring the reference signal. Figure 4 (c) may show a candidate beam group for beam selection using AI / ML. As an example, Figure 4 (c) of FIG. 4 may show a candidate beam group (e.g., beam group B_B) for a T2 period, in which one or more beams are selected based on AI / ML. In the T2 period, the base station and the terminal may determine the selected beam 420 from the candidate beams 410 according to AI / ML. As a more specific example, in Figure 3 In an AI / ML model, a model reasoning entity may receive information about candidate beams or other information, derive information about a selected beam, and output the information about the selected beam as output information.

[0071] That is, the period may include a T1 period in which one or more beams are selected based on measurement and a T2 period in which one or more beams are selected based on AI / ML. As an example, the base station may send a reference signal for measurement to the terminal in the T1 period. In this case, the reference signal may be at least one of a synchronization signal block (SSB), a channel state information-reference signal (CSI-RS), or a positioning RS (PRS). As another example, the reference signal may be defined as another reference signal and is not limited to a specific exemplary embodiment. In addition, in the T1 period, the terminal may send a reference signal for measurement to the base station. In this case, the reference signal may be a sounding reference signal (SRS). As another example, the reference signal may be defined as another reference signal and is not limited to a specific exemplary embodiment.

[0072] In addition, one or more candidate beam groups (e.g., beam group M_A) transmitted in the T1 period may include multiple candidate beam groups (e.g., beam group M_A1, beam group M_A2, ...). As another example, one or more candidate beam groups (e.g., beam group M_B) used for beam failure recovery management may be different from the one or more candidate beam groups (e.g., beam group M_A) described above, and the one or more candidate beam groups (e.g., beam group M_B) used for beam failure recovery management may also include multiple candidate beam groups (e.g., beam group M_B1, beam group M_B2, ...).

[0073] Figure 5a is a sequence diagram illustrating a first exemplary embodiment of a beam management method in a communication system.

[0074] refer to Figure 5a , the base station 510 may send a reference signal to the terminal 520 based on the candidate beam group (S501). Here, the reference signal may be at least one of the above-mentioned SSB, CSI-RS or PRS, and is not limited to a specific exemplary embodiment. The terminal 520 may determine at least one beam by measuring the reference signal sent via the candidate beam (S502). More specifically, the terminal 520 may determine N beams in order of reference signal received power (RSRP) from large to small for the reference signal sent from the base station 510 via the candidate beam. Then, the terminal 520 may report information about the N beams in order of RSRP from large to small to the base station 510 (S503). That is, in the T1 period, the terminal 520 may perform measurements based on the candidate beams. In addition, the terminal 520 may send information about the determined at least one beam to the base station 510 through a measurement report.

[0075] Figure 5b is a sequence diagram illustrating a second exemplary embodiment of a beam management method in a communication system.

[0076] refer to Figure 5b , the base station 510 may send a reference signal to the terminal 520 based on the candidate beam group (S511). Here, the reference signal may be at least one of the above-mentioned SSB, CSI-RS, or PRS, and is not limited to a specific exemplary embodiment. After performing measurement on the received candidate beams, the terminal 520 may determine at least one beam through an AI / ML model (S512). That is, if the terminal 520 is equipped with an AI / ML model, the terminal 520 may select at least one beam using the AI / ML model.

[0077] As a more specific example, the terminal 520 may select N beams using the AI / ML model, and the terminal may report information about the N beams to the base station 510 (S513). That is, the terminal 520 may select N beams through the AI / ML model, and the terminal may report information about the selected N beams to the base station 510. Here, the AI / ML model may use at least one of the measurement information of RSRP, reference signal received quality (RSRQ), signal to interference plus noise ratio (SINR), or signal to noise ratio (SNR) as input information. In other words, the AI / ML model may use the measurement information as input information.

[0078] As another example, the AI / ML model may use information about the location and movement path of the terminal 520 as input information. As an example, the information about the location and movement path of the terminal 520 may include at least one of the location, trajectory, angle of arrival (AOA), or angle of departure (AOD). Here, the information about the location and movement path may be mobility information. That is, the AI / ML model may use at least one of the measurement information or mobility information of the terminal as input information. The terminal 520 may use at least one of the measurement information of the terminal 520 and the mobility information of the terminal 520 as input to the AI / ML model, and determine and output N beams based on this. As another example, the terminal or base station may provide the result value of the reasoning (i.e., information about one or more selected candidate beams, beam failure probability, etc.) as input information for the AI / ML model of the corresponding (counterpart) base station or terminal.

[0079] Figure 5c is a sequence diagram illustrating a third exemplary embodiment of a beam management method in a communication system.

[0080] refer to Figure 5c , the base station 510 may send a reference signal to the terminal 520 based on the candidate beam group (S521). Here, the reference signal may be at least one of the above-mentioned SSB, CSI-RS, or PRS, and is not limited to a specific exemplary embodiment. The terminal 520 may determine a first beam group including at least one beam by measuring the received candidate beams (S522). More specifically, the terminal 520 may determine N beams as the first beam group in order of RSRP from large to small for the candidate beams sent from the base station 510. Then, the terminal 520 may report to the base station 510 information about the first beam group including N beams in order of RSRP from large to small (S523).

[0081] Optionally, the terminal 520 may determine a first beam group including at least one beam through an AI / ML model after performing measurement on the received candidate beams (S522). That is, if the terminal 520 is equipped with an AI / ML model, the terminal 510 may select a first beam group including at least one beam using the AI / ML model. As a more specific example, the terminal 520 may select a first beam group including N beams using an AI / ML model, and the terminal may report information about the first beam group including N beams to the base station 510 (S523).

[0082] In addition, the base station may receive information about the first beam group from the terminal 520. Here, the base station 510 may be a base station equipped with an AI / ML function. As an example, the base station 510 may use information about N beams (i.e., the first beam group) or other information to determine a second beam group including N1 beams among the N beams through an AI / ML model (S524), and the base station 510 may send information about the second beam group to the terminal (S525). Then, the terminal 520 may receive information about the second beam group from the base station.

[0083] Here, the other information may include at least one of interference information, resource allocation information, or neighboring base station information, and is not limited to a specific exemplary embodiment. In addition, the set of N1 beams may be a second beam group, and N1 may be a value less than N. That is, the base station 510 may select some beams from among the N beams and send corresponding information to the terminal 520.

[0084] As a more specific example, the base station may use information about N beams (i.e., the first beam group) or at least one of the other information received from the terminal 520 as input information of the AI / ML model. The base station may include information about one or more selected beams or at least one of the information that may affect the beam selection as input information of the AI / ML model, without limitation to a specific exemplary embodiment. In this case, the output information of the AI / ML model may be information about N1 beams. Information about N1 beams among the N beams may be selected as output information. That is, the base station may use the AI / ML model to determine from the first beam group a second beam group including fewer beams than the first beam group.

[0085] In addition, the terminal 520 may select N2 beams from among the N1 beams based on the received information, and determine a third beam group including N2 beams (S526). Here, N2 may be a number less than N1, and the set of N2 beams may be the third beam group. As described above, the terminal 520 may identify information about the second beam group, and select beams constituting the third beam group based on the information, wherein the information about the second beam group is information about the beams determined by the base station 510. In this case, the base station 510 may select one or more optimal beams through the above scheme. Then, the terminal 520 may report information about the third beam group including N2 beams to the base station 510 (S527). Therefore, the base station 510 may receive information about the third beam group from the terminal 520.

[0086] In addition, as an example, the above operation may be iterated, and one or more optimal beams may be derived through iteration. Here, the iteration may be performed based on one or more preconfigured conditions. As an example, the above iteration may be performed until the number of determined beams becomes less than a threshold value (e.g., N threshold ). Here, N threshold can be a natural number. That is, the base station 510 and the terminal 520 can select one or more optimal beams by iterating the above process. As another example, N threshold It may be set to 1, and the above operation may be iterated until the final beam is selected, and is not limited to the above exemplary embodiments. As an example, the above iteration may be performed until the RSRP value of one or more determined beams becomes greater than a specific threshold, and the present disclosure is not limited to the above exemplary embodiments.

[0087] Figure 6 is a sequence diagram illustrating a fourth exemplary embodiment of a beam management method in a communication system.

[0088] refer to Figure 6 , the base station 610 may send information about a reference signal for measurement to be transmitted during the T2 period to the terminal 620 through RRC signaling (S601). Then, the terminal 620 may receive information about a reference signal for measurement to be transmitted during the T2 period from the base station 610 through RRC signaling. Here, the information about the reference signal for measurement may include a reference signal type, a reference signal period, or other information.

[0089] Thereafter, the base station 610 may transmit a reference signal for measurement to the terminal 620 based on the configured information about the reference signal for measurement during the T2 period (S602). Then, the terminal 620 may receive the reference signal for measurement through some of the multiple beam groups in the T2 period based on the configured information about the reference signal for measurement. Here, some of the multiple beam groups may be some of the candidate beam groups (beam group M_A) and the candidate beam groups for beam failure recovery management (beam group M_B).

[0090] As described above, the base station 610 may transmit only some of the reference signals to the terminal 620 through some of the multiple beam groups in the T2 period. Here, the reference signals for measurement transmitted during the T2 period may be configured to the terminal 620 through RRC signaling. The base station 610 may transmit information about the reference signals received by the terminal 620 in the T2 period to the terminal 620 through RRC signaling, and based on this, the base station 610 may transmit the reference signals to the terminal 620 in the T2 period. As a specific example, the reference signal type, the reference signal period, or other information transmitted through the RRC signaling may be configured to the terminal 620 without being limited to a specific exemplary embodiment. That is, the terminal 620 may receive the reference signals through some of the multiple beam groups in the T2 period based on the information about one or more reference signals configured by the base station 610.

[0091] The terminal 520 may select a beam using the AI / ML model (S603), and the terminal may report information about the selected beam to the base station 510 (S604). That is, the terminal 620 may select N beams through the AI / ML model, and the terminal may report information about the selected N beams to the base station 610.

[0092] In addition, the terminal 620 may consider the case where the terminal 620 does not receive all reference signals in the T2 period. Here, when the terminal 620 selects one or more specific beams from the candidate beams through the AI / ML model, the input information of the AI / ML model may include the mobility information of the terminal or the other interference information described above, but is not limited thereto.

[0093] As another example, the terminal 620 may receive some reference signals configured based on RRC signaling in the T2 period. In this case, in addition to the above-mentioned mobility information or other interference information, the input information of the AI / ML model may also include information about the reference signal, and information about the selected beam may be derived based on them as output information. As an example, the terminal 620 may receive only the minimum reference signal for beam selection through the AI / ML model, without being limited to a specific exemplary embodiment. The terminal 620 may then send information about one or more determined beams to the base station 610 and operate in the T2 period as described above.

[0094] In addition, the terminal 620 may select one or more beams using the AI / ML model in the T2 period. As an example, the terminal 620 may not receive a reference signal from the base station 610 in the T2 period, and may select a beam using the AI / ML model.

[0095] Figure 7a is a sequence diagram illustrating a first exemplary embodiment of a beam management method in the event of a beam failure.

[0096] refer to Figure 7a , the terminal 720 may not receive any reference signal from the base station 710 in the T2 period. In the above case, the terminal 720 may select at least one beam from the candidate beams through the AI / ML model. Optionally, the terminal 720 may receive some reference signals from the base station 710 in the T2 period. In the above case, the terminal 720 may select at least one beam from the candidate beams through the AI / ML model (S701).

[0097] In addition, in the T2 period, the terminal 720 may detect a beam failure (S702). In this case, the terminal 720 may report the beam failure to the base station 710 using the MAC CE or the allocated beam failure reporting resource (S703). That is, the terminal 720 may detect the occurrence of a beam failure in the T2 period, report corresponding information to the base station 710, and perform subsequent operations.

[0098] As a specific example, the terminal 720 may report the beam failure to the base station 710 in an event-triggered manner. That is, the terminal 720 may detect an event regarding the beam failure. In this case, the terminal may report the beam failure to the base station 710. As an example, the terminal 720 may report the beam failure to the base station 710 via a MAC CE. As another example, the terminal 720 may detect an event regarding the beam failure. In this case, the terminal 720 may request a reference signal for measurement from the base station 710. Then, the terminal 720 may receive the reference signal from the base station 710 and perform measurement or beam selection.

[0099] As another example, during the T2 period, the base station 710 may allocate resources for beam failure reporting to the terminal 720. In this case, if beam failure occurs, the terminal 720 may report the beam failure to the base station 710 through the resources for beam failure reporting.

[0100] Figure 7b is a sequence diagram illustrating a second exemplary embodiment of a beam management method in the event of a beam failure.

[0101] refer to Figure 7b As described above, terminal 720 may detect beam failure during the T2 period.

[0102] refer to Figure 7b, the terminal 720 may not receive any reference signal from the base station 710 in the T2 period. In the above case, the terminal 720 may select at least one beam from the candidate beams through the AI / ML model. Alternatively, the terminal 720 may receive some reference signals from the base station 710 in the T2 period. In the above case, the terminal 720 may select at least one beam from the candidate beams through the AI / ML model (S711).

[0103] In addition, during the T2 period, the terminal 720 may detect a beam failure (S712). In this case, the terminal 720 may report the beam failure to the base station 710 using the MAC CE or the allocated beam failure report resource (S713). In this case, the terminal 720 may transmit information about one or more candidate beams selected using the AI / ML function together with the beam failure report to the base station 710. Therefore, the base station 720 may receive a beam failure report from the terminal 720, wherein the beam failure report includes information about one or more candidate beams selected using the AI / ML function. The base station 710 may then perform subsequent operations by considering the information about the one or more candidate beams selected by the terminal 720 through the AI / ML model.

[0104] Here, as an example, the base station 710 may identify a beam failure. In this case, the base station 710 may send a reference signal for measurement selected for a candidate beam to the terminal 720. Then, the terminal 720 may perform measurement based on the reference signal for measurement. In addition, the terminal 720 may select one or more candidate beams based on the reference signal for measurement. The terminal 720 may report information about the selected one or more candidate beams to the base station 710. The base station 710 may receive information about the selected one or more candidate beams. The base station 710 may determine a new beam based on the information about the selected one or more candidate beams.

[0105] As another example, the base station 710 may recognize a beam failure. In this case, the base station 710 may directly select a new beam and transmit information about the selected new beam to the terminal 720.

[0106] As another example, the base station 710 may identify a beam failure. In this case, the base station 710 may terminate the above-mentioned T2 period. In addition, the base station 710 may instruct the terminal 720 to start the T1 period. That is, the base station 710 may switch the current period to a new period for beam selection based on the reference signal for measurement. Then, the base station 710 and the terminal 720 may determine one or more beams based on the switched period.

[0107] Figure 8a is a conceptual diagram illustrating a first exemplary embodiment of a beam management method after a beam failure report.

[0108] refer to Figure 8a , the terminal may report the beam failure to the base station. In this case, if the terminal is equipped with an AI / ML function, before receiving a response from the base station, the terminal may select a candidate beam as the beam to be used based on the AI / ML function. Here, the candidate beam may be a wide beam. The terminal may communicate with the base station 810 via the candidate beam. Thereafter, as described above, the terminal 820 may select a new beam based on the response of the base station 810.

[0109] Figure 8b is a conceptual diagram illustrating a second exemplary embodiment of a beam management method after a beam failure report.

[0110] refer to Figure 8b , the terminal 820 may fall back to the last beam selected based on the reference signal for measurement. Specifically, the terminal 820 may fall back to the last beam selected based on the reference signal for measurement in the T1 period, and communicate with the base station 810 through the beam. Thereafter, as described above, the terminal 820 may select a new beam based on the response of the base station 810.

[0111] Figure 9a is a conceptual diagram showing a first exemplary embodiment of a signaling method for a T1 period and a T2 period.

[0112] refer to Figure 9aAs described above, the T1 period may be a period for measurement or beam selection, and the T2 period may be a period for beam selection using an AI / ML model. Here, the base station may set a first timer for the T1 period or a second timer for the T2 period to the terminal 920 through signaling. Here, the first timer for the T1 period or the second timer for the T2 period may be configured to the terminal by the base station through an RRC signal as a cell-specific signal or a beam-specific signal. The first timer for the T1 period or the second timer for the T2 period may be updated in the terminal by the base station through a MAC CE or DCI as a terminal-specific (i.e., UE-specific) signal. As a specific example, the base station 910 may set a first timer for the T1 period and a second timer for the T2 period in the terminal 920 through an RRC signal. In this case, the base station may instruct the terminal to activate / deactivate the first timer for the T1 period and the second timer for the T2 period through a MAC CE or a DCI. As an example, the base station may set a first timer for the T1 period and a second timer for the T2 period in a terminal 920 equipped with an AI / ML function through RRC signaling. In this case, the base station 910 may instruct the terminal 920 to activate the first timer for the T1 period and the second timer for the T2 period through MAC CE or DCI. Therefore, the first timer for the T1 period and the second timer for the T2 period may be activated in the base station and the terminal. In this case, the base station and the terminal may perform measurement or beam selection in the T1 period. In addition, the base station and the terminal may select one or more beams in the T2 period through the AI / ML model. On the other hand, the base station 910 may instruct the terminal 920 to deactivate the first timer for the T1 period and the second timer for the T2 period through MAC CE or DCI. Therefore, the first timer for the T1 period and the second timer for the T2 period may be deactivated in the base station and the terminal. When the first timer for the T1 period and the second timer for the T2 period are deactivated as described above, the second timer for the T2 period may not be set in the terminal. Therefore, the terminal may only set a timer for the period for measurement or beam selection as in the existing scheme, but may not be limited to the corresponding exemplary embodiments.

[0113] As another example, configuration information of the first timer for the T1 period and the second timer for the T2 period may be transmitted from the base station 910 to the terminal 920 via at least one of an RRC signal, MAC-CE or DCI which is a UE-specific signal, and may not be limited to a specific exemplary embodiment.

[0114] As another example, the base station may set a first timer for the T1 period and a second timer for the T2 period in the terminal 920. In this case, a method for indicating the T1 period and the T2 period may be required. Here, the T1 period and the T2 period may be indicated based on a starting point or an ending point, and may be configured based on at least one unit among symbols, time slots, milliseconds, or seconds. In addition, the T1 period and the T2 period may be configured as a duration (window) value based on at least one unit among symbols, time slots, milliseconds, or seconds. As a more specific example, the starting point and duration (window) value for each of the T1 period and the T2 period may be indicated by the base station to the terminal so as to be configured in the terminal 920, and the above operations may be performed based on this.

[0115] Figure 9b is a conceptual diagram showing a second exemplary embodiment of a signaling method for a T1 period and a T2 period.

[0116] refer to Figure 9b , beam failure may not occur during the T2 period. In this case, the T2 period can be extended. In other words, after the T2 period ends, the starting point of the next T1 period can be postponed. Here, if beam failure does not occur during the T2 period, the T2 period can be extended by T2a.

[0117] In addition, during the period including the T2 period and the T2a period, beam failure may not occur. In this case, the T2 period may be further extended by the sum of the T2b period and the T2a period.

[0118] In addition, during the period including the T2 period, the T2a period, and the T2b period, beam failure may not occur. In this case, the T2 period may be further extended by the sum of the T2c period, the T2 period, the T2a period, and the T2b period. The above operation may be performed iteratively up to N times. Here, N may be a natural number. Here, the above extension operation may be indicated by the base station 910 to the terminal 920 through RRC signaling, MACCE, or DCI, and is not limited to a specific exemplary embodiment.

[0119] As another example, a case where there is an indication from the base station 910 for extending the T2 period may be considered. For example, during the T2 period, the base station 910 may send a plurality of beam groups (e.g., beam group M_A) for non-periodic measurement to the terminal, and instruct the terminal 920 to perform the measurement. In this case, the terminal 920 may perform the measurement based on the corresponding beam group (e.g., beam group M_A), and report the measurement result to the base station 910. The base station 910 may then instruct the terminal to extend the T2 period through a MAC CE or a DCI. Based on the indication, the T2 period may be extended. As another example, the base station 910 may instruct the terminal 920 to extend the T2 period, regardless of the above-mentioned measurement process, and may not be limited to a specific exemplary embodiment.

[0120] Fig.10 is a conceptual diagram showing a first exemplary embodiment of a configuration method for a T1 period and a T2 period.

[0121] refer to Fig.10 During the T1 period, the terminal 1020 may select one or more beams by measuring the reference signal before connecting to the base station 1010. That is, the terminal 1020 may connect to the base station 1010 for the first time. In this case, since the terminal 1020 cannot identify information related to the base station 1010, the terminal 1020 may select one or more beams by measuring the reference signal.

[0122] Thereafter, the terminal 1020 may be connected to the base station 1020 by performing initial access. After the terminal 1020 is connected to the base station 1010, the terminal may identify information about the previous beam, and the terminal 1020 may obtain information related to the base station 1010. Here, if the terminal 1020 is equipped with an AI / ML function, the terminal 1020 may perform AI / ML-based beam selection during the T2 period after connecting to the base station 1010, through information about the previous beam and information related to the base station 1010. For example, when the above-mentioned beam failure occurs, the base station 1010 may send a reference signal to the terminal 1020 based on the beam failure, and may perform beam selection based on measurement. As another example, the terminal 1020 may perform beam selection based on AI / ML, and may perform measurement-based beam selection based on a non-periodic base station request. As another example, the terminal 1020 may perform beam selection based on an AI / ML model, and may perform measurement-based beam selection according to the long periodicity of reference signal transmission, but is not limited to a specific exemplary embodiment.

[0123] Fig.11 is a sequence diagram showing a first exemplary embodiment of a method for establishing an RRC connection between a terminal and a network.

[0124] refer to Fig.11, the terminal 1110 may send an RRC establishment request to the network 1120 (S1101). Then, the network 1120 may receive the RRC establishment request from the terminal 1110, and the network 1120 may send an RRC establishment response to the terminal 1110 (S1102). Then, the terminal 1110 may receive the RRC establishment response from the network 1120 and complete the RRC establishment. Thereafter, the terminal 1110 may send an RRC establishment completion message to the network 1120 (S1103). Then, the network 1120 may receive an RRC establishment completion message from the terminal 1110. In this case, as an example, an indication of whether AI / ML can be utilized may be required in the above operations. More specifically, considering the operation of a legacy terminal that does not support the AI / ML function, the availability of AI / ML may be different for each terminal.

[0125] In addition, the terminal may need to communicate without performing the AI / ML function. In this case, an indication of whether AI / ML can be utilized may be required based on this. Here, as an example, whether AI / ML can be utilized may be indicated by RRC. In other words, whether AI / ML can be utilized may be indicated by RRC signaling. As a more specific example, the base station may indicate "AI / ML_beam_enable=ON" to the terminal through RRC signaling. In this case, the terminal may utilize the AI / ML function. On the other hand, the base station may indicate "AI / ML_beam_enable=OFF" to the terminal. In this case, the terminal may not utilize the AI / ML function. However, this is merely an example, and the present disclosure is not limited to the above exemplary embodiments.

[0126] In this case, when AI / ML utilization is possible, the beam management process utilizing the AI / ML function as described above may be supported between the base station and the terminal. Here, the above process may be applied to all terminals. Alternatively, the above process may be applied only to terminals equipped with AI / ML functions, and they may not be limited to specific exemplary embodiments.

[0127] In addition, whether AI / ML utilization is possible may be configured using at least one of a cell-specific parameter, a beam-specific parameter, or a terminal-specific parameter, but the present disclosure is not limited to a specific exemplary embodiment.

[0128] Fig.12 is a sequence diagram showing a first exemplary embodiment of a method for transmitting UE capability information.

[0129] refer to Fig.12, the network 1220 may send a UE capability query signal to the terminal 1210 to query the capabilities of the terminal (S1201). Then, the terminal 1210 may receive the UE capability query signal from the network 1220, and the terminal 1210 may report the UE capability information to the network 1220 (S1202). Here, the capabilities of the terminal may include the ability to utilize the above-mentioned AI / ML functions. That is, a terminal equipped with an AI / ML function may perform the above-mentioned operations, and the terminal 1210 may include the corresponding information in the UE capability information and report it to the network 1220. As a specific example, the terminal may report that the terminal has the AI / ML function by sending the RRC parameter "AI / ML_UE_enable=ON" to the network. Optionally, the terminal may report that the terminal does not have the AI / ML function by sending the RRC parameter "AI / ML_UE_enable=OFF" to the network.

[0130] Here, as an example, when beam management using the AI / ML function is signaled to be possible using an RRC parameter ("AI / ML_beam_enable = ON"), the above-mentioned AI / ML-based beam management process may be performed, and the present disclosure is not limited to a specific exemplary embodiment.

[0131] Optionally, as another example, when an RRC parameter ("AI / ML_beam_enable=ON") is used to signal that beam management using the AI / ML function is possible and the terminal is signaled with an RRC parameter ("AI / ML_UE_enable=ON") that it is equipped with AI / ML capability, the above-mentioned AI / ML-based beam management process may be performed, and the present disclosure is not limited to a specific exemplary embodiment.

[0132] In addition, the base station or terminal may perform beam management using AI / ML during the T2 period after performing training during the T1 period (T1,1), and may determine whether to update the training value (result value or input value) for the previous T1 period (T1,1) when performing training during the next T1 period (T1,2), and may notify (indicate or report) this to each other.

[0133] Optionally, after performing training during the T1 period (T1,1), the base station or the terminal may perform beam management using AI / ML during the T2 period, and may determine whether to ignore the value trained during the previous T1 period (T1,1) and perform new training when performing training during the next T1 period (T1,2), and may notify (indicate or report) this to each other.

[0134] In addition, the base station or terminal may update the AI / ML model by excluding the value trained during a specific period. For example, the base station or terminal may update the AI / ML model based on the value of period (T1,1) by excluding the value trained during period (T1,2) during period (T1,3) after period (T1,1) and period (T1,2).

[0135] As an exemplary case of excluding values ​​trained during a specific period or a previous period, if a beam failure occurs during a T2 period (e.g., period T2,2) as a result of operating based on values ​​trained in a period (e.g., period (T1,2)), the base station or terminal may exclude the values ​​trained during period (T2,2).

[0136] Optionally, as an exemplary case of excluding values ​​trained during a specific period or a previous period, if a reference value (e.g., beam failure probability) of a result value of AI / ML is greater than a reference value as a result of operating during period T2 (e.g., period (T2,2)) based on a value trained in a period (e.g., period T1,2), the base station or terminal may exclude the value trained during period (T1,2).

[0137] The operation of the method according to the exemplary embodiment of the present disclosure can be implemented as a computer-readable program or code in a computer-readable recording medium. The computer-readable recording medium may include all kinds of recording devices for storing data that can be read by a computer system. In addition, the computer-readable recording medium can store and execute programs or codes that can be distributed in computer systems connected via a network and read by computers in a distributed manner.

[0138] The computer readable recording medium may include a hardware device specifically configured to store and execute program commands, such as ROM, RAM or flash memory. The program command may include not only the machine language code created by the compiler, but also the high-level language code that can be executed by the computer using an interpreter.

[0139] Although some aspects of the present disclosure have been described in the context of equipment, these aspects may indicate the corresponding description according to the method, and the block or equipment may correspond to the step of the method or the feature of the step. Similarly, the aspects described in the context of the method may be expressed as the feature of the corresponding block or item or the corresponding equipment. Some or all steps of the method may be performed by (or by using) hardware devices (such as microprocessors, programmable computers or electronic circuits). In certain embodiments, one or more of the most important steps of the method may be performed by such equipment.

[0140] In some exemplary embodiments, a programmable logic device (such as a field programmable gate array) can be used to perform some or all of the functions of the methods described herein. In some exemplary embodiments, the field programmable gate array can be operated with a microprocessor to perform one of the methods described herein. Generally, the method is preferably performed by a hardware device.

[0141] The description of the present disclosure is only exemplary in nature, and therefore, changes that do not depart from the essence of the present disclosure are intended to fall within the scope of the present disclosure. These changes should not be considered to be out of the spirit and scope of the present disclosure. Therefore, it will be understood by those of ordinary skill in the art that various changes can be made in form and detail without departing from the spirit and scope defined by the appended claims.

Claims

1. A terminal method, comprising: receiving a reference signal from a base station via a primary candidate beam; generating measurement information of a reference signal for the primary candidate beam; Selecting N secondary candidate beams using an artificial intelligence (AI) / machine learning (ML) model based on the measurement information for the primary candidate beams; and sending information about the selected N secondary candidate beams to the base station, Wherein, N is a positive integer.

2. The method according to claim 1, wherein: The measurement information for the primary candidate beams includes at least one of a reference signal received power (RSRP), a reference signal received quality (RSRQ), a signal to interference plus noise ratio (SINR), or a signal to noise ratio (SNR) for each of the reference signals of the primary candidate beams.

3. The method according to claim 1, wherein: Each of the reference signals for the primary candidate beams is one of a synchronization signal block (SSB), a channel state information reference signal (CSI-RS), or a positioning RS (PRS).

4. The method according to claim 1, wherein: The terminal performs selection of the N secondary candidate beams using the AI / ML model based on measurement information for the primary candidate beams by additionally using the location and movement path information of the terminal.

5. The method according to claim 4, wherein: The location and movement path information of the terminal includes at least one of a location, a track, an angle of arrival (AOA), or an angle of departure (AOD).

6. The method according to claim 1, further comprising: Before receiving the reference signal of the primary candidate beam from the base station through the primary candidate beam, receiving a reference signal from the base station via a beam; Obtaining a received signal strength of a reference signal for the beam; selecting the primary candidate beam based on the received signal strength of the beam; as well as Information about the selected preliminary candidate beams is sent to the base station.

7. The method according to claim 1, further comprising: receiving a reference signal from the base station through a tertiary candidate beam selected from among the secondary candidate beams; generating measurement information of reference signals for the three-level candidate beams; Based on the measurement information for the third-level candidate beams, select M fourth-level candidate beams using the AI / ML model; as well as sending information about the selected M four-level candidate beams to the base station, Wherein, M is a positive integer.

8. The method according to claim 1, further comprising: Configuration information about a reference signal for the primary candidate beam is received from the base station through radio resource control (RRC) signaling, wherein the terminal receives some reference signals using the configuration information when receiving the reference signal of the primary candidate beam from the base station through the primary candidate beam.

9. The method according to claim 8, wherein: The configuration information about the reference signal for the primary candidate beam includes a reference signal type and a reference signal period.

10. The method according to claim 1, further comprising: Detect beam failures; selecting, using the AI / ML model, an alternative candidate beam based on measurement information for the primary candidate beam; as well as A beam failure report including information about the replacement candidate beam is sent to the base station.

11. The method according to claim 10, further comprising: The terminal receives information about resources for beam failure reporting from the base station, wherein the terminal sends a beam failure report including information about the replacement candidate beam to the base station using the resources for beam failure reporting.

12. A method of a base station, comprising: Sending a reference signal to a terminal via a primary candidate beam; receiving information about a secondary candidate beam, wherein the secondary candidate beam is selected by the terminal based on measurement information for the primary candidate beam; selecting a tertiary candidate beam using an AI / ML model based on the information about the secondary candidate beams; and A reference signal is sent to the terminal through the third-level candidate beam.

13. The method according to claim 12, wherein: The base station performs the selection of the tertiary candidate beams using an AI / ML model based on the information about the secondary candidate beams by additionally using at least one of interference information, resource allocation information, or neighboring base station information.

14. The method according to claim 12, further comprising: Before sending a reference signal to the terminal through the primary candidate beam, transmitting a reference signal to the terminal using a beam; as well as Information on the preliminary candidate beams selected based on received signal strengths of the beams is received from the terminal.

15. The method according to claim 12, further comprising: sending information about resources used for beam failure reporting to the terminal; as well as A beam failure report including information about an alternative candidate beam is received from the terminal using the resource for beam failure reporting.

16. The method according to claim 15, further comprising: selecting a fourth-level candidate beam using the AI / ML model based on the information about the alternative candidate beams; as well as Information about the four-level candidate beams is sent to the terminal.

17. A terminal comprising a processor, in, The processor causes the terminal to perform the following operations: receiving a reference signal from a base station via a primary candidate beam; generating measurement information of a reference signal for the primary candidate beam; Selecting N secondary candidate beams using an artificial intelligence (AI) / machine learning (ML) model based on the measurement information for the primary candidate beams; and sending information about the selected N secondary candidate beams to the base station, Wherein, N is a positive integer.

18. The terminal according to claim 17, wherein: The processor further causes the terminal to perform the following operations: before receiving the reference signal of the primary candidate beam from the base station through the primary candidate beam, receiving a reference signal from the base station via a beam; Obtaining a received signal strength of a reference signal for the beam; selecting the primary candidate beam based on the received signal strength of the beam; as well as Information about the selected preliminary candidate beams is sent to the base station.

19. The terminal according to claim 17, wherein: The processor further causes the terminal to perform the following operations: Detect beam failures; selecting, using the AI / ML model, an alternative candidate beam based on the measurement information for the primary candidate beam; and A beam failure report including information about the replacement candidate beam is sent to the base station.

20. The terminal according to claim 19, wherein: The processor further causes the terminal to perform the following operations: receive information about resources for beam failure reporting from the base station, wherein the terminal sends a beam failure report including information about the alternative candidate beam to the base station using the resources for beam failure reporting.

Images