Method and device for performing beam management by using artificial intelligence and machine learning

AI/ML models are employed for beam management in wireless networks to enhance accuracy and reduce overhead, addressing inefficiencies in complex environments and improving resource management and service quality.

WO2026240466A1PCT designated stage Publication Date: 2026-11-19KT CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2026/006142
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-16
Filing Date
2026-05-18
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

Existing wireless communication systems face limitations in optimizing beam management in complex environments, particularly in ultra-high frequency bands, leading to inefficiencies in resource management and service quality improvement.

Method used

Implementing artificial intelligence and machine learning (AI/ML) models for beam management by using AI/ML models to infer and monitor reference signal resources, allowing for high-accuracy performance evaluation without measuring all reference signals, thereby minimizing signaling overhead.

Benefits of technology

The proposed method enhances beam management accuracy and reduces signaling overhead, providing efficient resource management and improved service quality in next-generation wireless networks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2026006142_19112026_PF_FP_ABST
    Figure KR2026006142_19112026_PF_FP_ABST
Patent Text Reader

Abstract

The present embodiments provide a method by which a terminal performs beam management by using artificial intelligence and machine learning (AI / ML), the method comprising the steps of: receiving, from a base station through at least one CSI report configuration message, first reference signal resource information for inference of an AI / ML model and second reference signal resource information for monitoring the performance of the AI / ML model; selecting at least one monitoring reference signal resource set from among one or more monitoring reference signal resource sets on the basis of the second reference signal resource information, and measuring a reference signal received in a reference signal resource included in the selected monitoring reference signal resource set; and determining a performance evaluation result on the basis of the measurement result and the inference result of the AI / ML model, and transmitting, to the base station, a monitoring report message including the performance evaluation result.
Need to check novelty before this filing date? Find Prior Art

Description

Method and apparatus for performing beam management using artificial intelligence and machine learning

[0001] The embodiments propose a method and apparatus for performing beam management using artificial intelligence and machine learning in a next-generation wireless access network (in this disclosure, "5G", "NR [New Radio]", "5G-Advanced", "6G" or subsequent 3GPP wireless access networks).

[0002] As next-generation wireless communication technology evolves beyond 5G to 6G, it aims to achieve faster data transmission speeds and ultra-low latency compared to 5G in ultra-high frequency bands such as the terahertz (THz) band. Accordingly, technology is advancing in the direction of incorporating artificial intelligence (AI) and machine learning (ML) technologies from the design stage of communication systems. As a result, wireless communication systems are establishing a technical foundation to support new services and applications in an ultra-high performance, ultra-low latency, and ultra-connected environment.

[0003] In particular, AI / ML technologies are being introduced in wireless communication networks to optimize network operations and ensure real-time quality. By performing various roles such as situational awareness through big data analysis, adaptive utilization of network resources and data, and intelligent, data-driven system optimization, AI / ML can enable efficient resource management and service quality improvement in complex wireless environments, over which existing methods had limitations.

[0004] As part of this aspect, a specific design is required to enable wireless communication using AI / ML models.

[0005] Embodiments of the present disclosure can provide a method and apparatus for performing beam management using artificial intelligence and machine learning in a next-generation wireless access network.

[0006] In one aspect, the present embodiments provide a method for a terminal (user equipment; UE) to perform beam management using artificial intelligence and machine learning (AI / ML), comprising the steps of: receiving from a base station, through at least one CSI report setting message, first reference signal resource information for inference of an AI / ML model and second reference signal resource information for performance monitoring of an AI / ML model; selecting at least one monitoring reference signal resource set from one or more monitoring reference signal resource sets based on the second reference signal resource information and performing a measurement on a reference signal received from a reference signal resource included in the selected monitoring reference signal resource set; determining a performance evaluation result based on the result of the measurement and the inference result of the AI / ML model, and transmitting a monitoring report message including the performance evaluation result to the base station, wherein one or more monitoring reference signal resource sets include a plurality of groups of reference signal resources that constitute at least a subset of the entire reference signal resource set corresponding to the first reference signal resource information.

[0007] In another aspect, the present embodiments provide a method for a base station (BS) to perform beam management using artificial intelligence and machine learning (AI / ML), comprising the steps of: transmitting first reference signal resource information for inference of an AI / ML model and second reference signal resource information for performance monitoring of an AI / ML model to a terminal (user equipment; UE) through at least one CSI report setting message; transmitting a reference signal from a reference signal resource included in at least one of one or more monitoring reference signal resource sets set based on the second reference signal resource information; and receiving a monitoring report message from the terminal including a performance evaluation result determined based on the result of a measurement of the reference signal and the result of inference of the AI / ML model, wherein one or more monitoring reference signal resource sets include a plurality of groups of reference signal resources that constitute at least a subset of the entire reference signal resource set corresponding to the first reference signal resource information.

[0008] In another aspect, the present embodiments may provide a terminal (user equipment; UE) that performs beam management using artificial intelligence and machine learning, comprising a transmitter, a receiver, and a control unit that controls the operation of the transmitter and the receiver, wherein the control unit receives from a base station, through at least one CSI report setting message, first reference signal resource information for inference of an AI / ML model and second reference signal resource information for performance monitoring of an AI / ML model, and based on the second reference signal resource information, selects at least one monitoring reference signal resource set from one or more monitoring reference signal resource sets, performs a measurement on a reference signal received from a reference signal resource included in the selected monitoring reference signal resource set, determines a performance evaluation result based on the result of the measurement and the inference result of the AI / ML model, and transmits a monitoring report message including the performance evaluation result to the base station, wherein one or more monitoring reference signal resource sets include a plurality of groups of reference signal resources that constitute at least a subset of the entire reference signal resource set corresponding to the first reference signal resource information.

[0009] In another aspect, the embodiments may provide a base station that performs beam management using artificial intelligence and machine learning, comprising a transmitter, a receiver, and a control unit that controls the operation of the transmitter and the receiver, wherein the control unit transmits first reference signal resource information for inference of an AI / ML model and second reference signal resource information for performance monitoring of an AI / ML model to a terminal (user equipment; UE) through at least one CSI report setting message, transmits a reference signal from a reference signal resource included in at least one of one or more monitoring reference signal resource sets set based on the second reference signal resource information, and receives a monitoring report message from the terminal including a performance evaluation result determined based on the result of a measurement of the reference signal and the result of inference of the AI / ML model, wherein one or more monitoring reference signal resource sets include a plurality of groups of reference signal resources that constitute at least a subset of the entire reference signal resource set corresponding to the first reference signal resource information.

[0010] According to the embodiments, a method and apparatus for performing beam management using artificial intelligence and machine learning in a next-generation wireless access network can be provided.

[0011] In addition, according to the embodiments, by providing a method to minimize signaling overhead and increase accuracy even without measuring all reference signals for Set A, high-accuracy performance evaluation results can be provided to the network.

[0012] FIG. 1 is a diagram briefly illustrating the structure of an NR wireless communication system to which the present embodiment can be applied.

[0013] FIG. 2 is a drawing illustrating the frame structure in an NR system to which the present embodiment can be applied.

[0014] FIG. 3 is a diagram illustrating a resource grid supported by wireless access technology to which the present embodiment can be applied.

[0015] FIG. 4 is a diagram illustrating the bandwidth part supported by the wireless access technology to which the present embodiment can be applied.

[0016] FIG. 5 is a diagram illustrating an exemplary synchronization signal block in a wireless access technology to which the present embodiment can be applied.

[0017] FIG. 6 is a diagram illustrating a random access procedure in a wireless access technology to which the present embodiment can be applied.

[0018] Figure 7 is a diagram for explaining CORESET.

[0019] FIG. 8 is a flowchart illustrating a procedure in which a terminal according to one embodiment performs beam management using artificial intelligence and machine learning (AI / ML).

[0020] FIG. 9 is a flowchart illustrating a procedure in which a base station according to one embodiment performs beam management using artificial intelligence and machine learning (AI / ML).

[0021] FIG. 10 is a diagram illustrating the mapping of reference signal resources (RS resources) of Set A according to one embodiment and RS resources belonging to each group of the monitoring set.

[0022] FIG. 11 is a diagram illustrating the mapping of RS resources of Set A and RS resources belonging to each group of the monitoring set according to another embodiment.

[0023] FIG. 12 is a diagram illustrating the mapping of RS resources of Set A and RS resources belonging to each group of the monitoring set according to another embodiment.

[0024] FIG. 13 is a diagram illustrating the timing of grouping-based monitoring transmission according to one embodiment.

[0025] FIG. 14 is a diagram illustrating a grouping-based monitoring transmission time according to another embodiment.

[0026] FIG. 15 is a diagram illustrating a grouping-based monitoring transmission time according to another embodiment.

[0027] FIG. 16 is a diagram illustrating a grouping-based monitoring transmission time according to another embodiment.

[0028] FIG. 17 is a diagram showing the configuration of a terminal according to another embodiment.

[0029] FIG. 18 is a diagram showing the configuration of a base station according to another embodiment.

[0030] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. In assigning reference numerals to the components of each drawing, the same components may have the same reference numeral as much as possible, even if they are shown in different drawings. Furthermore, in describing the embodiments, if it is determined that a detailed description of related known components or functions may obscure the essence of the technical concept, such detailed description may be omitted. Where terms such as "comprising," "having," or "consisting of" are used in this specification, other parts may be added unless "only" is used. Where a component is expressed in the singular, it may include a plural unless otherwise specified.

[0031] Additionally, terms such as first, second, A, B, (a), (b), etc., may be used to describe the components of the present disclosure. These terms are used merely to distinguish the components from other components, and the nature, order, sequence, or number of the components are not limited by such terms.

[0032] In describing the positional relationship of components, where it is stated that two or more components are "connected," "combined," or "joined," it should be understood that while the two or more components may be directly "connected," "combined," or "joined," they may also be "connected," "combined," or "joined" with other components "intervened." Here, the other components may be included in one or more of the two or more components that are "connected," "combined," or "joined" with one another.

[0033] In describing the temporal flow relationship regarding components, methods of operation, or methods of production, for example, when the temporal or sequential relationship is described using "after," "following," "next," or "before," it may include cases where the relationship is not continuous unless "immediately" or "directly" is used.

[0034] Meanwhile, where numerical values ​​or corresponding information regarding a component (e.g., levels, etc.) are mentioned, even without separate explicit notation, the numerical values ​​or corresponding information may be interpreted as including a range of error that may occur due to various factors (e.g., process factors, internal or external shocks, noise, etc.).

[0035] A wireless communication system in this specification refers to a system for providing various communication services, such as voice and data packets, using wireless resources, and may include a terminal, a base station, or a core network.

[0036] The embodiments disclosed below may be applied to wireless communication systems using various wireless access technologies. For example, the embodiments may be applied to various wireless access technologies such as CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), SC-FDMA (single carrier frequency division multiple access), or NOMA (non-orthogonal multiple access). Furthermore, wireless access technology may refer not only to specific access technologies but also to communication technologies for each generation established by various telecommunication organizations such as 3GPP, 3GPP2, WiFi, Bluetooth, IEEE, and ITU. For example, CDMA may be implemented as a wireless technology such as UTRA (universal terrestrial radio access) or CDMA2000. TDMA may be implemented as a wireless technology such as GSM (global system for mobile communications), GPRS (general packet radio service), or EDGE (enhanced datarates for GSM evolution). OFDMA can be implemented using wireless technologies such as IEEE (Institute of Electrical and Electronic Engineers) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802-20, and E-UTRA (evolved UTRA). IEEE 802.16m is an evolution of IEEE 802.16e and provides backward compatibility with systems based on IEEE 802.16e.UTRA is part of UMTS (universal mobile telecommunications system). 3GPP (3rd generation partnership project) LTE (long term evolution) is part of E-UMTS (evolved UMTS) that uses E-UTRA (evolved-UMTS terrestrial radio access), employing OFDMA in the downlink and SC-FDMA in the uplink. As such, these embodiments can be applied to currently disclosed or commercialized radio access technologies, and can also be applied to radio access technologies currently under development or to be developed in the future.

[0037] Meanwhile, the term "terminal" in this specification is a comprehensive concept meaning a device including a wireless communication module that communicates with a base station in a wireless communication system. It should be interpreted as a concept that includes not only User Equipment (UE) in WCDMA, LTE, NR, HSPA, and IMT-2020 (5G or New Radio), but also Mobile Station (MS), User Terminal (UT), Subscriber Station (SS), and wireless device in GSM. Furthermore, depending on the usage type, the terminal may be a user portable device such as a smartphone, or in a V2X communication system, it may refer to a vehicle or a device including a wireless communication module inside a vehicle. Additionally, in the case of a Machine Type Communication (MMC) system, it may refer to an MTC terminal, M2M terminal, URLLC terminal, etc., equipped with a communication module to perform machine type communication.

[0038] In this specification, "base station" or "cell" refers to an end that communicates with a terminal in terms of a network, and encompasses various coverage areas such as Node-B, eNB (evolved Node-B), gNB (gNode-B), LPN (Low Power Node), Sector, Site, various types of antennas, BTS (Base Transceiver System), Access Point, Point (e.g., Transmitter Point, Receiver Point, Transceiver Point), Relay Node, Mega Cell, Macro Cell, Micro Cell, Pico Cell, Femto Cell, RRH (Remote Radio Head), RU (Radio Unit), and Small Cell. Additionally, "cell" may include a Bandwidth Part (BWP) in the frequency domain. For example, a serving cell may refer to the Activation BWP of a terminal.

[0039] Since there is a base station controlling one or more of the various cells listed above, the term "base station" can be interpreted in two senses. 1) It may refer to the device itself that provides a mega cell, macro cell, micro cell, pico cell, femto cell, or small cell in relation to a wireless area, or 2) it may refer to the wireless area itself. In 1), all devices that provide a specific wireless area are controlled by the same entity or interact to configure the wireless area collaboratively are referred to as base stations. Depending on the configuration method of the wireless area, a point, a transmitting / receiving point, a transmitting point, a receiving point, etc., are examples of a base station. In 2), the wireless area itself that receives or transmits a signal from the perspective of a user terminal or from the perspective of a neighboring base station may also be referred to as a base station.

[0040] In this specification, "Cell" may refer to a component carrier having coverage of a signal transmitted from a transmitting / receiving point or coverage of a signal transmitted from a transmitting / receiving point (transmission point or transmission / reception point), or the transmitting / receiving point itself.

[0041] Uplink (UL, or Uplink) refers to the method of transmitting and receiving data from a terminal to a base station, and Downlink (DL, or Downlink) refers to the method of transmitting and receiving data from a base station to a terminal. Downlink may refer to communication or a communication path from multiple transmission and reception points to a terminal, and uplink may refer to communication or a communication path from a terminal to multiple transmission and reception points. In this case, in the downlink, the transmitter may be part of the multiple transmission and reception points, and the receiver may be part of the terminal. Additionally, in the uplink, the transmitter may be part of the terminal, and the receiver may be part of the multiple transmission and reception points.

[0042] The uplink and downlink transmit and receive control information through control channels such as PDCCH (Physical Downlink Control Channel) and PUCCH (Physical Uplink Control Channel), and transmit and receive data by configuring data channels such as PDSCH (Physical Downlink Shared Channel) and PUSCH (Physical Uplink Shared Channel). In the following description, the situation in which signals are transmitted and received through channels such as PUCCH, PUSCH, PDCCH, and PDSCH is also referred to as "transmitting and receiving PUCCH, PUSCH, PDCCH, and PDSCH."

[0043] To clarify the explanation, the technical concept described below is based primarily on 3GPP LTE / LTE-A / NR (New RAT) communication systems, but the technical features are not limited to said communication systems.

[0044] Following research on 4G (4th-Generation) communication technology, 3GPP develops 5G (5th-Generation) communication technology to meet the requirements of the ITU-R for next-generation radio access technology. Specifically, 3GPP develops LTE-A pro, which enhances LTE-Advanced technology to meet ITU-R requirements, and NR, a new communication technology distinct from 4G communication technology, as 5G communication technologies. Since both LTE-A pro and NR refer to 5G communication technology, the following description of 5G communication technology will focus on NR unless a specific technology is being identified.

[0045] The operational scenarios in NR define various operation scenarios by adding considerations for satellites, automobiles, and new verticals to the existing 4G LTE scenarios, and in terms of service, they support eMBB (Enhanced Mobile Broadband) scenarios, mMTC (Massive Machine Communication) scenarios which require low data rates and asynchronous access while having high terminal density and being deployed over a wide range, and URLLC (Ultra Reliability and Low Latency) scenarios which require high responsiveness and reliability and can support high-speed mobility.

[0046] To satisfy these scenarios, NR introduces a wireless communication system equipped with new waveform and frame structure technologies, low latency technology, mmWave support technology, and forward compatibility technology. In particular, the NR system presents various technical changes in terms of flexibility to provide forward compatibility. The main technical features of NR are explained below with reference to the drawings.

[0047]

[0048] <NR 시스템 일반>

[0049] FIG. 1 is a simplified diagram illustrating the structure of an NR system to which the present embodiment can be applied.

[0050] Referring to FIG. 1, the NR system is divided into a 5G Core Network (5GC) and an NR-RAN part. The NG-RAN consists of gNBs and ng-eNBs that provide control plane (RRC) protocol endpoints for the user plane (SDAP / PDCP / RLC / MAC / PHY) and User Equipment (UE). gNBs are interconnected with each other, or gNBs and ng-eNBs are interconnected via Xn interfaces. Each gNB and ng-eNB is connected to the 5GC via an NG interface. The 5GC may be configured to include an Access and Mobility Management Function (AMF), which is responsible for control plane functions such as terminal access and mobility control, and a User Plane Function (UPF), which is responsible for control functions for user data. The NR system includes support for both frequency bands below 6 GHz (FR1, Frequency Range 1) and frequency bands above 6 GHz (FR2, Frequency Range 2).

[0051] gNB refers to a base station that provides NR user plane and control plane protocol terminations to a terminal, and ng-eNB refers to a base station that provides E-UTRA user plane and control plane protocol terminations to a terminal. The base station described in this specification should be understood as encompassing both gNB and ng-eNB, and may also be used to refer to gNB or ng-eNB separately as necessary.

[0052] <NR 웨이브 폼, 뉴머롤러지 및 프레임 구조>

[0053] In NR, CP-OFDM waveforms using a cyclic prefix are used for downlink transmission, and CP-OFDM or DFT-s-OFDM are used for uplink transmission. OFDM technology is easy to combine with MIMO (Multiple Input Multiple Output) and has the advantage of allowing the use of low-complexity receivers along with high frequency efficiency.

[0054] Meanwhile, in NR, since the requirements for data rate, latency, coverage, etc. differ for each of the three scenarios mentioned above, it is necessary to efficiently satisfy the requirements for each scenario through the frequency bands that constitute an arbitrary NR system. To this end, a technology has been proposed to efficiently multiplex wireless resources based on multiple different numerologies.

[0055] Specifically, the NR transmission numerator is determined based on sub-carrier spacing and CP (Cyclic prefix), and as shown in Table 1 below, the μ value is used as an exponential value of 2 based on 15 kHz and changes exponentially.

[0056] μ서브캐리어 간격Cyclic prefixSupported for dataSupported for synch015NormalYesYes130NormalYesYes260Normal, ExtendedYesNo3120NormalYesYes4240NormalNoYes

[0057] As shown in Table 1 above, the numerators of NR can be classified into five types based on the subcarrier spacing. This differs from LTE, one of the 4G communication technologies, where the subcarrier spacing is fixed at 15 kHz. Specifically, the subcarrier spacings used for data transmission in NR are 15, 30, 60, and 120 kHz, while the subcarrier spacings used for synchronization signal transmission are 15, 30, 12, and 240 kHz. Additionally, extended CP applies only to the 60 kHz subcarrier spacing. Meanwhile, the frame structure in NR defines a frame with a length of 10ms, composed of 10 subframes of equal length of 1ms. A single frame can be divided into 5ms half-frames, and each half-frame contains 5 subframes. In the case of a 15 kHz subcarrier interval, one subframe consists of one slot, and each slot consists of 14 OFDM symbols. FIG. 2 is a diagram illustrating the frame structure in an NR system to which the present embodiment can be applied. Referring to FIG. 2, in the case of a normal CP, the slot is fixedly composed of 14 OFDM symbols, but the length of the slot in the time domain may vary depending on the subcarrier interval. For example, in the case of a numeral with a 15 kHz subcarrier interval, the slot is composed of a length of 1 ms, which is the same length as the subframe. In contrast, in the case of a numeral with a 30 kHz subcarrier interval, the slot is composed of 14 OFDM symbols, but two slots may be included in one subframe with a length of 0.5 ms. That is, the subframe and the frame are defined with a fixed time length, while the slot is defined by the number of symbols, and the time length may vary depending on the subcarrier interval.Meanwhile, NR defines the basic unit of scheduling as a slot and introduced mini-slots (or sub-slots or non-slot based schedules) to reduce transmission delay in the wireless section. Using a wide subcarrier spacing reduces transmission delay in the wireless section because the length of a single slot becomes inversely shorter. Mini-slots (or sub-slots) are designed for efficient support of URLLC scenarios and allow scheduling in units of 2, 4, or 7 symbols.

[0058] Furthermore, unlike LTE, NR defines uplink and downlink resource allocation at the symbol level within a single slot. To reduce HARQ latency, a slot structure was defined that allows HARQ ACK / NACK to be transmitted directly within the transmission slot; this slot structure is described as a self-contained structure.

[0059] NR is designed to support a total of 256 slot formats, of which 62 are used in 3GPP Rel-15. Additionally, it supports common frame structures that form FDD or TDD frames through various slot combinations. For example, it supports slot structures where all slot symbols are set to downlink, slot structures where all symbols are set to uplink, and slot structures where downlink and uplink symbols are combined. Furthermore, NR supports data transmission being distributed and scheduled across one or more slots. Therefore, base stations can use a Slot Format Indicator (SFI) to inform a terminal whether a slot is a downlink slot, an uplink slot, or a flexible slot. Base stations can indicate the slot format by using the SFI to indicate an index of a table configured via UE-specific RRC signaling, or they can indicate it dynamically via Downlink Control Information (DCI) or statically or semi-statically via RRC.

[0060] <NR 물리 자원 >

[0061] Regarding physical resources in NR, antenna ports, resource grids, resource elements, resource blocks, and bandwidth parts are considered.

[0062] An antenna port is defined such that the channel carrying a symbol on the antenna port can be inferred from the channel carrying another symbol on the same antenna port. If the large-scale property of the channel carrying a symbol on one antenna port can be inferred from the channel carrying a symbol on another antenna port, the two antenna ports can be said to be in a QC / QCL (quasi co-located or quasi co-location) relationship. Here, the large-scale property includes one or more of delay spread, Doppler spread, frequency shift, average received power, and received timing.

[0063] FIG. 3 is a diagram illustrating a resource grid supported by wireless access technology to which the present embodiment can be applied.

[0064] Referring to FIG. 3, a resource grid may exist for each numerator because NR supports multiple numerators on the same carrier. Additionally, a resource grid may exist depending on the antenna port, subcarrier spacing, and transmission direction.

[0065] A resource block consists of 12 subcarriers and is defined only in the frequency domain. Additionally, a resource element consists of one OFDM symbol and one subcarrier. Therefore, as shown in Fig. 3, the size of a single resource block can vary depending on the subcarrier spacing. Furthermore, NR defines "Point A," which serves as a common reference point for the resource block grid, as well as common resource blocks, virtual resource blocks, etc.

[0066] FIG. 4 is a diagram illustrating the bandwidth part supported by the wireless access technology to which the present embodiment can be applied.

[0067] In NR, unlike LTE where the carrier bandwidth is fixed at 20 MHz, the maximum carrier bandwidth is set from 50 MHz to 400 MHz depending on the subcarrier interval. Therefore, it is not assumed that all terminals use this entire carrier bandwidth. Accordingly, in NR, as shown in Fig. 4, a Bandwidth Part (BWP) can be designated within the carrier bandwidth for the terminal to use. Additionally, a Bandwidth Part is associated with a single numerator and consists of a subset of a continuous common resource block, and can be dynamically activated over time. Up to four Bandwidth Parts are configured for the uplink and downlink respectively, and data is transmitted and received using the Bandwidth Part activated at a given time.

[0068] In the case of paired spectrum, the uplink and downlink bandwidth parts are set independently, whereas in the case of unpaired spectrum, the downlink and uplink bandwidth parts are paired to share a center frequency in order to prevent unnecessary frequency re-tuning between downlink and uplink operations.

[0069] <NR 초기 접속>

[0070] In NR, the terminal performs cell search and random access procedures to connect to the base station and perform communication.

[0071] Cell search is a procedure in which a terminal uses a Synchronization Signal Block (SSB) transmitted by a base station to synchronize with the corresponding base station's cell, obtain a physical layer cell ID, and acquire system information.

[0072] FIG. 5 is a diagram illustrating an exemplary synchronization signal block in a wireless access technology to which the present embodiment can be applied.

[0073] Referring to FIG. 5, the SSB consists of a primary synchronization signal (PSS) and a secondary synchronization signal (SSS) each occupying 1 symbol and 127 subcarriers, and a PBCH spanning 3 OFDM symbols and 240 subcarriers.

[0074] The terminal monitors the SSB in the time and frequency domains and receives the SSB.

[0075] SSBs can be transmitted up to 64 times within 5ms. Multiple SSBs are transmitted via different transmission beams within the 5ms timeframe, and the terminal performs detection by assuming that an SSB is transmitted every 20ms when viewed from the perspective of a specific beam used for transmission. The number of beams available for SSB transmission within the 5ms timeframe can increase as the frequency band increases. For example, up to 4 SSB beams can be transmitted at 3GHz or lower, up to 8 beams in the frequency band from 3GHz to 6GHz, and up to 64 different beams can be used to transmit SSBs in the frequency band above 6GHz.

[0076] Two SSBs are included in a single slot, and the starting symbol and number of repetitions within the slot are determined according to the subcarrier interval as follows.

[0077] Meanwhile, unlike the SS of conventional LTE, the SSB is not transmitted at the center frequency of the carrier bandwidth. That is, the SSB can be transmitted even at locations other than the center of the system band, and multiple SSBs can be transmitted across the frequency domain when broadband operation is supported. Accordingly, the terminal monitors the SSB using a synchronization raster, which is a candidate frequency location for monitoring the SSB. The carrier raster, which is information on the center frequency location of the channel for initial connection, and the synchronization raster were newly defined in NR, and the synchronization raster is set with a wider frequency interval compared to the carrier raster, thereby supporting fast SSB search by the terminal.

[0078] The terminal can obtain the MIB through the PBCH of the SSB. The Master Information Block (MIB) contains minimum information for the terminal to receive the Remaining Minimum System Information (RMSI) broadcast by the network. Additionally, the PBCH may include information regarding the location of the first DM-RS symbol in the time domain, information for the terminal to monitor SIB1 (e.g., SIB1 numeral information, information related to SIB1 CORESET, search space information, PDCCH related parameter information, etc.), and offset information between the Common Resource Block and the SSB (the absolute location of the SSB within the carrier is transmitted via SIB1). Here, the SIB1 numeral information is applied identically to some messages used in the random access procedure for the terminal to connect to the base station after completing the cell search procedure. For example, the SIB1 numeral information may be applied to at least one of messages 1 to 4 for the random access procedure.

[0079] The aforementioned RMSI may refer to SIB1 (System Information Block 1), and SIB1 is broadcast periodically (e.g., 160ms) from the cell. SIB1 contains information necessary for the terminal to perform the initial random access procedure and is transmitted periodically via PDSCH. To receive SIB1, the terminal must receive the numerology information used for transmitting SIB1 and the CORESET (Control Resource Set) information used for scheduling SIB1 via PBCH. The terminal checks the scheduling information for SIB1 using SI-RNTI within the CORESET and obtains SIB1 on the PDSCH according to the scheduling information. The remaining SIBs, excluding SIB1, may be transmitted periodically or upon the terminal's request.

[0080] FIG. 6 is a diagram illustrating a random access procedure in a wireless access technology to which the present embodiment can be applied.

[0081] Referring to FIG. 6, when cell search is completed, the terminal transmits a random access preamble for random access to the base station. The random access preamble is transmitted via PRACH. Specifically, the random access preamble is transmitted to the base station via PRACH, which consists of a series of radio resources in specific slots that are repeated periodically. Generally, when the terminal initially connects to a cell, a contention-based random access procedure is performed, and when performing random access for Beam Failure Recovery (BFR), a non-contention-based random access procedure is performed.

[0082] The terminal receives a random access response for the transmitted random access preamble. The random access response may include a random access preamble identifier (ID), an UL Grant (uplink radio resource), a temporary C-RNTI (Temporary Cell - Radio Network Temporary Identifier), and a TAC (Time Alignment Command). Since a single random access response may contain random access response information for one or more terminals, the random access preamble identifier may be included to indicate which terminal the included UL Grant, temporary C-RNTI, and TAC are valid for. The random access preamble identifier may be an identifier for the random access preamble received by the base station. The TAC may be included as information for the terminal to coordinate uplink synchronization. The random access response may be indicated by the random access identifier on the PDCCH, namely the RA-RNTI (Random Access - Radio Network Temporary Identifier).

[0083] A terminal that receives a valid random access response processes the information contained in the random access response and performs a transmission scheduled to the base station. For example, the terminal applies a TAC and stores a temporary C-RNTI. Additionally, using a UL Grant, it transmits data stored in the terminal's buffer or newly generated data to the base station. In this case, information that can identify the terminal must be included.

[0084] Finally, the terminal receives a downlink message to resolve competition.

[0085] <NR CORESET>

[0086] The downlink control channel in NR is transmitted in a CORESET (Control Resource Set) with a length of 1 to 3 symbols, and transmits uplink / downlink scheduling information, SFI (Slot format Index), TPC (Transmit Power Control) information, etc.

[0087] In this way, NR introduced the concept of CORESET to ensure system flexibility. CORESET (Control Resource Set) refers to time-frequency resources for downlink control signals. A terminal can decode control channel candidates by using one or more search spaces from the CORESET time-frequency resources. Quasi CoLocation (QCL) assumptions were established for each CORESET, and these are used to indicate characteristics regarding the analog beam direction in addition to the characteristics assumed by conventional QCL, such as delay spread, Doppler spread, Doppler shift, and mean delay.

[0088] Figure 7 is a diagram for explaining CORESET.

[0089] Referring to FIG. 7, CORESET can exist in various forms within a single slot and within the carrier bandwidth, and in the time domain, CORESET can be composed of up to 3 OFDM symbols. Additionally, CORESET is defined as a multiple of 6 resource blocks up to the carrier bandwidth in the frequency domain.

[0090] The first CORESET is specified via the MIB as part of the initial bandwidth part configuration to enable the reception of additional configuration and system information from the network. After establishing a connection with the base station, the terminal can be configured by receiving one or more CORESET information via RRC signaling.

[0091] In this specification, frequencies, frames, subframes, resources, resource blocks, regions, bands, subbands, control channels, data channels, synchronization signals, various reference signals, various signals, or various messages related to NR (New Radio) may be interpreted in the sense used in the past or present, or in various senses used in the future.

[0092] Wider bandwidth operations

[0093] In the case of existing LTE systems, scalable bandwidth operation was supported for any LTE Component Carrier (CC). That is, depending on the frequency deployment scenario, any LTE operator could configure a bandwidth ranging from a minimum of 1.4 MHz to a maximum of 20 MHz when configuring a single LTE CC, and normal LTE terminals supported a transmit / receive capability of 20 MHz bandwidth for a single LTE CC.

[0094] However, in the case of NR, the design is made to enable support for NR terminals with different transmit / receive bandwidth capabilities through a single wideband NR CC. Accordingly, it is required to configure one or more bandwidth parts (BWPs) consisting of subdivided bandwidths for any NR CC, and to support flexible wider bandwidth operation through different bandwidth part configurations and activations for each terminal.

[0095] Specifically, in NR, one or more bandwidth parts can be configured through a single serving cell configured from the perspective of a terminal, and the terminal is defined to activate one downlink bandwidth part (DL bandwidth part) and one uplink bandwidth part (UL bandwidth part) in the serving cell to use for uplink / downlink data transmission and reception. In addition, for terminals where multiple serving cells are configured, i.e., terminals to which CA is applied, it is defined to activate one downlink bandwidth part and / or uplink bandwidth part for each serving cell to use the wireless resources of the serving cell for uplink / downlink data transmission and reception.

[0096] Specifically, an initial bandwidth part for the initial access procedure of a terminal is defined in any serving cell, and one or more terminal-specific (UE-specific) bandwidth parts are configured for each terminal through dedicated RRC signaling, and a default bandwidth part for a fallback operation can also be defined for each terminal.

[0097] However, depending on the capability and bandwidth part(s) configuration of the terminal in any serving cell, it may be defined to simultaneously activate and use multiple downlink and / or uplink bandwidth parts, but in NR rel-15, it is defined to activate and use only one downlink bandwidth part (DL bandwidth part) and one uplink bandwidth part (UL bandwidth part) at any time in any terminal.

[0098]

[0099] The present disclosure relates to a method for evaluating the accuracy of deployed AI / ML for a terminal capable of performing beam management through beam prediction using AI / ML, comprising the steps of configuring a beam for model monitoring and a method for measuring and monitoring associated reference signal (RS) resources and calculating the monitoring results.

[0100] Specifically, the AI / ML model in the present disclosure may include a data-driven algorithm that takes as input a value of the received power of a reference signal (e.g., L1-RSRP) measured in a reference signal resource set (Set B) smaller than the entire reference signal resource set (Set A), and generates as output a best beam index and / or predicted RSRP for each beam included in the entire reference signal resource set (Set A). For example, the AI / ML model may include a neural network-based model, where the input dimension corresponds to the number of reference signal resources in Set B, and the output dimension corresponds to the number of reference signal resources in Set A.

[0101] The training of the AI / ML model can be performed using a supervised learning method with training data consisting of pairs of received power values ​​measured at the reference signal resource of Set B and received power values ​​measured at the entire reference signal resource of Set A. During the training process, the model parameters of the AI / ML model can be optimized to predict the received power values ​​for the entire beam of Set A from the measurements of Set B, or to classify the optimal beam index. The trained AI / ML model can be deployed to a terminal or network and used for inference.

[0102] Regarding AI / ML-applied wireless communication, terms can be defined as follows.

[0103] Data collection refers to the process by which network nodes, managed entities, or UEs collect data for the purpose of training AI / ML models, data analysis, and inference.

[0104] An AI / ML model (hereinafter also referred to as a 'model') refers to a data-driven algorithm that applies AI / ML technology to generate a series of outputs based on a series of inputs. AI / ML model training refers to the process of training an AI / ML model in a data-driven manner by learning input / output relationships, and obtaining the trained AI / ML model for inference. AI / ML model inference refers to the process of generating a series of outputs based on a series of inputs using the trained AI / ML model. AI / ML model validation refers to a sub-process of training that evaluates the quality of an AI / ML model using a dataset different from the one used for training. AI / ML model testing refers to a sub-process of training used to evaluate the performance of the final AI / ML model using a dataset different from those used for training and validation. Unlike AI / ML model validation, testing does not assume subsequent tuning of the model.

[0105] A UE-side (AI / ML) model refers to an AI / ML model where inference is performed entirely within the UE. A Network-side (AI / ML) model refers to an AI / ML model where inference is performed entirely within the network. A One-sided (AI / ML) model refers to either a UE-side (AI / ML) model or a Network-side (AI / ML) model. A Two-sided (AI / ML) model refers to a pair of AI / ML models where co-inference is performed. Here, co-inference consists of AI / ML inference performed jointly across the UE and the network. That is, the first part of the inference is performed by the UE first, and the remaining part by the gNB, or vice versa.

[0106] AI / ML model transfer refers to the transmission of an AI / ML model via a wireless interface, using parameters of a model structure known to the receiving side or a new model with such parameters. The transmission may include a full model or a partial model. Model download refers to the transmission of a model from the network to the UE. Model upload refers to the transmission of a model from the UE to the network.

[0107] Federated learning / federated training refers to a machine learning technique that trains AI / ML models on multiple distributed edge nodes (e.g., UEs, gNBs), each performing local model training using local data samples. While this requires various interactions between the models, the exchange of local data samples is not necessary. Offline field data is data collected in the field and used for the offline training of AI / ML models. Online field data is data collected in the field and used for the online training of AI / ML models.

[0108] Model monitoring refers to the procedure of monitoring the inference performance of AI / ML models.

[0109] Supervised learning refers to the process of training a model using inputs and their corresponding labels. Unsupervised learning refers to the process of training a model without labeled data. Semi-supervised learning refers to the process of training a model by mixing labeled and unlabeled data. Reinforcement Learning (RL) refers to the process of training an AI / ML model from inputs (i.e., states) and feedback signals (i.e., rewards) resulting from the model's outputs (i.e., actions) in an environment where the model interacts.

[0110] Model activation refers to activating an AI / ML model for a specific function. Model deactivation refers to deactivating an AI / ML model for a specific function. Model switching refers to deactivating the currently activated AI / ML model and activating a different AI / ML model for a specific function.

[0111] When applying AI / ML models, the following levels of network-UE collaboration are considered.

[0112] 1. Level x: No collaboration.

[0113] 2. Level y: Signaling-based collaboration without model migration.

[0114] 3. Level z: Signal-based collaboration via model transmission.

[0115] In relation to life cycle management (LCM) procedures for AI / ML models, the AI / ML model may have a model ID containing relevant information and / or model functions for at least some AI / ML operations.

[0116] With regard to model selection, activation, deactivation, switching, and replacement for the UE-side model and both-side models, if determined by the network, the network may initiate the process, or the terminal may initiate and request the network. If determined by the UE, the UE's decision may be reported to the network in accordance with an event configured by the network.

[0117] For AI / ML-based feature groups (FGs), an additional condition refers to all aspects assumed for model training, but it is not part of the UE capability for the AI / ML-based feature group. This does not mean that additional conditions are necessarily explicitly specified. Additional conditions can be divided into two categories: network-side additional conditions and UE-side additional conditions.

[0118] For the inference of the UE-side model, to ensure consistency between training and inference with respect to additional NW-side conditions (if identified), the following options can be taken as possible approaches:

[0119] - Model identification to achieve alignment of additional NW-side conditions between the NW side and the UE side

[0120] - Train the model under additional conditions in the network and deliver it to the UE

[0121] - Provide the UE with information and / or instructions regarding additional conditions on the NW side

[0122] - Consistency is supported by monitoring (model / function selection by UE and / or NW based on the performance of candidate models / functions on the UE side).

[0123] - Other approaches are not excluded

[0124] - The possibility that different approaches can achieve the same function is not denied.

[0125] Regarding data collection, it can be defined as follows.

[0126] For the UE-side AI / ML model on the UE side, the UE reports to the NW a supported / preferred configuration for downlink reference signal (DL RS) transmission. For the data collection trigger / start, data collection may be started / triggered by the NW's configuration or by a request from the UE for data collection.

[0127] Signals / configurations / measurements / reporting for data collection, for example, signaling aspects relate to assistance information (if supported), reference signals, the content / type of collected data, configurations related to Set A and / or Set B, and information regarding the association / mapping between Set A and Set B.

[0128] Support information provided by the network to the UE (where supported) may be provided for the purpose of classifying data for the purpose of differentiating data characteristics. Support information must protect privacy / proprietary information.

[0129] For NW-side AI / ML models, mechanisms related to reporting, additional information regarding report content, reduction of reporting overhead, and signals / configuration / measurement / reporting for data collection, for example, signal aspects are related to supporting information (if supported) and reference signals.

[0130] According to one example of the present disclosure, UE-assisted performance monitoring can be performed on a UE-sided AI / ML model for beam management. In particular, when a UE-sided AI / ML model is applied in BM-Case1 and BM-Case2, the network can be configured to acquire performance information for UE-assisted performance monitoring, or for the UE to calculate or report said performance information.

[0131] In the present disclosure, Top K beams refer to the top K beams predicted to have the highest received signal strength (e.g., L1-RSRP (Layer 1 Reference Signal Received Power)) as a result of inference by an AI / ML model, where K is an integer greater than or equal to 1. Top M beams refer to the top M beams with the highest received signal strength (e.g., L1-RSRP) actually measured from a reference signal resource for monitoring, where M is an integer greater than or equal to 1. That is, Top K represents the beam ranking based on the prediction of an AI / ML model, and Top M represents the beam ranking based on actual measurements.

[0132] In one example, a performance metric for UE auxiliary performance monitoring may be Top 1 or Top K beam prediction accuracy. For example, the UE may calculate beam prediction accuracy by comparing the prediction result of an AI / ML model with the Top 1 or Top K beams determined based on measurements obtained from a resource set for monitoring or resources for monitoring. In this case, the beam prediction accuracy may be calculated with or without considering the margin.

[0133] In another example, performance information for UE-assisted performance monitoring may be L1-RSRP difference information. For example, the UE may calculate L1-RSRP difference information based on actual L1-RSRP measurements for one or more of the Top K predicted beams and L1-RSRP measurements obtained from a set of resources for monitoring or resources for monitoring.

[0134] In another example, performance information for UE-assisted performance monitoring may be the difference information between the predicted RSRP and the measured L1-RSRP. In this case, the UE can calculate the RSRP difference information by comparing the RSRP predicted by the AI / ML model with the L1-RSRP measured for the resource set for monitoring or the corresponding beam of the resources for monitoring. This method can be applied when the AI / ML model can predict the RSRP. Additionally, the use of resources from Set B for monitoring is not excluded.

[0135] In another example, performance information for UE-assisted performance monitoring may be probability information that a predicted beam will be a Top 1 or Top K beam. In this case, the UE can generate information indicating the probability that a predicted beam or multiple predicted beams correspond to a Top 1 or Top K beam, based on the probability information generated by the AI / ML model. This approach can be applied when the AI / ML model is capable of generating probability information.

[0136] In one example, a set of resources for monitoring or resources for monitoring may be configured for the calculation of performance information. For example, the full set of Set A may be used for measurement. In another example, where the full set of Set A is not used, a method for acquiring measurements for the predicted Top 1 or Top K beams may be defined for the calculation of prediction accuracy or RSRP difference. Performance information may be calculated using a one-shot scheme based on a single sample or a single prediction-measure pair, or it may be calculated for a window consisting of multiple samples.

[0137] In one example, the accuracy of the Top 1 or Top K beam predictions can be defined as follows. If at least one of the Top M beams determined based on L1-RSRP measurements from one or more resource sets for monitoring is included in one of the Top K prediction beams for Set A, the prediction may be determined to be accurate. In this case, at least one of the Top M beams may be connected to at least one of the Top K prediction beams of Set A according to a specific rule or signaling.

[0138] Here, K may represent the number of predicted beams in the inference report for the corresponding time instance. Additionally, Top M beams may represent the M best beams based on the measured L1-RSRP for the resource set for monitoring. M can be configured by the network in the CSI report configuration for monitoring, for example, M can be set to 1 or 2.

[0139] In one example, to calculate performance metrics for Type 1 Option 2 performance monitoring for a UE-side model, the size of the set for monitoring may be configured to be equal to the size of Set A. In this case, the nth resource of the set for monitoring may be connected to the nth resource of Set A. In another example, the size of the set for monitoring may be configured to be smaller than the size of Set A.

[0140] In one example of BM-Case 1, a measurement result for a transmission occasion of a CSI-RS or SSB resource for monitoring may be linked to an inference report. In this case, the CSI reference resource of the inference report may have a minimal slot offset with respect to the transmission occasion of the CSI-RS or SSB resource for monitoring. Additionally, the inference report and the transmission occasion of the CSI-RS or SSB resource for monitoring may not be delayed compared to the CSI reference resource corresponding to the CSI report for monitoring.

[0141] In one example, a threshold X for the minimum slot offset can be set. For instance, if the minimum slot offset k is less than or equal to the threshold X, the transmission occasion for monitoring can be associated with the corresponding inference report. Conversely, if the minimum slot offset k exceeds the threshold X, the transmission occasion for monitoring may be determined not to have an associated inference report. The threshold X can be optionally configured by the RRC.

[0142] In one example of BM-Case 1, beam prediction accuracy can be calculated based on the latest N transmission occasions of a monitoring resource having an associated inference report that is not delayed compared to the CSI reference resource corresponding to the CSI report for monitoring. Here, N can be an integer greater than or equal to 1 and can be configured in CSI-ReportConfig. Additionally, in BM-Case 1, one set of resources for monitoring can be configured in one CSI-ReportConfig for monitoring.

[0143] In one example of BM-Case 2, AP CSI-RS for Set B may not be supported for the inference of the UE-side model. Additionally, in BM-Case 2, one beam prediction accuracy may be reported for one configured time instance configured by one CSI-ReportConfig for monitoring. In this case, only one resource set may be configured in CSI-ReportConfig.

[0144] In one example of BM-Case 2, a configured time instance for metric calculation may be the f-th time instance among the time instances within a single inference report, and the f-th time instance may be configured in the CSI-ReportConfig for monitoring. The performance metric of the f-th time instance may be calculated based on the latest N transmission occasions of the monitoring resource having the linked time instance, which are not later than the CSI reference resource corresponding to the CSI report for monitoring. Here, N may be an integer greater than or equal to 1 and may be configured in the CSI-ReportConfig.

[0145] In one example of BM-Case 2, the measurement result for the transmission occasion of the CSI-RS or SSB resource for monitoring can be associated with the f-th time instance for prediction. In this case, the f-th time instance may have a minimum slot offset with respect to the transmission occasion of the CSI-RS or SSB resource for monitoring. Additionally, the transmission occasion of the corresponding inference report and the CSI-RS or SSB resource for monitoring may not be delayed compared to the CSI reference resource corresponding to the CSI report for monitoring.

[0146] In one example, a threshold X for the minimum slot offset can also be set for BM-Case 2. For example, if the minimum slot offset k is less than or equal to the threshold X, the transmission occasion for monitoring can be associated with the corresponding time instance. On the other hand, if the minimum slot offset k exceeds the threshold X, the transmission occasion for monitoring may be determined not to have an associated time instance. The threshold X can be optionally configured by the RRC.

[0147] According to the above description, the terminal may receive a monitoring set from the base station in which the size of the CSI-RS / SSB resources for monitoring is the same as Set A, or a monitoring set in which the size is smaller than that of Set A.

[0148] In addition, to determine the occasion when CSI-RS / SSB resources for monitoring are transmitted to evaluate the performance / accuracy of inference results at any given time point, the terminal assumes that a monitoring RS transmission time point having a minimal slot offset is linked to a (reference) time point for the inference result (report). Accordingly, monitoring results can be reported based on N linked pairs for N latest monitoring RS transmission times points. The CSI-ReportConfig for monitoring can be assumed to configure only one resource set.

[0149] As a metric to evaluate the current model performance, the Top 1 or Top K beam prediction accuracy is used, which is calculated by comparing the prediction results with the Top 1 or Top K beams based on the aforementioned resource set for monitoring or measurements from the resources. If the terminal is configured with a monitoring set smaller than the size of Set A, the accuracy of the predicted Top-K for the entire beam must be calculated based on the Top-M for a subset of beams, rather than the Top-M for the entire beam. In this case, if the beams belonging to the monitoring set for a subset of Set A consist only of Top-K beams, this always yields the result that the beam prediction is accurate.

[0150] Conversely, if the beams in the monitoring set consist only of beams that do not belong to Top-K, this always results in inaccurate beam prediction. However, if the total number of beams in Set A is large, measuring all beams for monitoring causes an increased burden on the terminal. Even if the monitoring set consists of beams smaller than Set A, a method is required to provide reliability regarding beam prediction accuracy.

[0151] In addition, as mentioned above, other methods are being considered as metrics to evaluate model performance, but support for them has not yet been decided. Specific mapping and metric calculation methods also need to be defined for cases where a terminal is configured with a monitoring set smaller than the size of Set A and other metrics are applied.

[0152]

[0153]

[0154] In the following, a method for performing beam management using artificial intelligence and machine learning will be explained in detail with reference to the relevant drawings.

[0155] FIG. 8 is a diagram illustrating a procedure (800) in which a terminal according to one embodiment performs beam management using artificial intelligence and machine learning.

[0156] Referring to FIG. 8, the terminal can receive from a base station at least one CSI report setting message, a first reference signal resource information for inference of an AI / ML model and a second reference signal resource information for performance monitoring of an AI / ML model (S810).

[0157] Here, at least one CSI report configuration message may include a CSI report configuration message for inference (CSI-ReportConfig) and a CSI report configuration message for monitoring. The first reference signal resource information may be received through the CSI report configuration message for inference, and the second reference signal resource information may be received through the CSI report configuration message for monitoring. The CSI report configuration message for monitoring may be connected to the CSI report configuration message for inference.

[0158] The first reference signal resource information may include information regarding an entire set of reference signal resources (e.g., Set A) corresponding to the inference results of an AI / ML model.

[0159] The second reference signal resource information may include information regarding one or more monitoring reference signal resource sets (e.g., monitoring set) having a size smaller than the entire reference signal resource set (e.g., Set A).

[0160] The second reference signal resource information may include time-domain behavior and physical resource information for the reference signal resources included in each of one or more monitoring reference signal resource sets. The time-domain behavior may be set to one of periodic transmission, semi-persistent transmission, or aperioditic transmission, and a common time-domain behavior may be set for one or more monitoring reference signal resource sets or an independent time-domain behavior may be set for each monitoring reference signal resource set.

[0161] Time gap information between one or more monitoring reference signal resource sets can be set through second reference signal resource information. The time gap can be set by considering the processing time for the terminal to calculate a performance metric for one monitoring reference signal resource set. Based on the time gap information, the terminal can distinguish the transmission time and transmission occasion of the reference signal resources included in each monitoring reference signal resource set.

[0162] Referring again to FIG. 8, the terminal can select at least one monitoring reference signal resource set among one or more monitoring reference signal resource sets based on second reference signal resource information, and perform a measurement of a reference signal received from a reference signal resource included in the selected monitoring reference signal resource set (S820).

[0163] Here, the terminal can measure the signal strength of a Channel State Information - Reference Signal (CSI-RS) or Synchronization Signal Block (SSB) received from a reference signal resource included in a selected set of monitoring reference signal resources. In the present disclosure, a single transmission time at which a reference signal resource included in each set of monitoring reference signal resources is transmitted can be defined as a monitoring RS sub-occasion. The terminal can perform a measurement by selecting at least one monitoring RS sub-occasion from among one or more monitoring RS sub-occasions.

[0164] According to one example, one or more monitoring reference signal resource sets may include a plurality of groups of reference signal resources that constitute at least a subset of the entire reference signal resource set corresponding to the first reference signal resource information.

[0165] According to one example, multiple groups may be configured by sequentially mapping reference signal resources included in an entire reference signal resource set. That is, consecutive reference signal resources in the index order of the reference signal resources included in the entire reference signal resource set may be included in a single monitoring reference signal resource set. According to another example, multiple groups may be configured by distributingly mapping reference signal resources included in an entire reference signal resource set. That is, each reference signal resource may be cyclically included in different monitoring reference signal resource sets in the index order of the reference signal resources included in the entire reference signal resource set. According to yet another example, multiple groups may be determined according to a configuration explicitly directed by a base station through signaling.

[0166] The second reference signal resource information may include information regarding the correspondence relationship between a reference signal resource included in the entire reference signal resource set and a reference signal resource included in one or more monitoring reference signal resource sets, or information for deriving the correspondence relationship.

[0167] The correspondence relationship may be determined based on at least one of the index of a reference signal resource included in the entire reference signal resource set, the index of one or more monitoring reference signal resource sets, the number of one or more monitoring reference signal resource sets, the number of reference signal resources included in each monitoring reference signal resource set, the index of a reference signal resource within each monitoring reference signal resource set, bitmap information, group information, or reference signal resource indication information.

[0168] Specifically, in a sequential mapping scheme, when A reference signal resources included in the entire reference signal resource set (Set A) are sequentially mapped to G monitoring reference signal resource sets X at a time, the beam index of Set A corresponding to the CRI(i) of the g-th monitoring reference signal resource set can be determined as (g_id(g) * X) + CRI(i). Here, i is an integer greater than or equal to 0 and less than X, G is the rounded-up value of A / X, and g is an integer greater than or equal to 0 and less than G.

[0169] In a distributed mapping scheme, the beam index of Set A corresponding to the CRI(i) of the g-th monitoring reference signal resource set can be determined as (CRI(i) * G) + g_id(g). Here, i is an integer greater than or equal to 0 and less than X, G is the rounded-up value of A / X, and g can be an integer greater than or equal to 0 and less than G.

[0170] Additionally, the correspondence relationship may be explicitly indicated by bitmap information received from the base station. In the bitmap, each bit may correspond to each reference signal resource included in the entire reference signal resource set, and a reference signal resource with a bit value of '1' may be included in the corresponding monitoring reference signal resource set. Based on the correspondence relationship information received from the base station, the terminal may determine the reference signal resources included in each monitoring reference signal resource set and perform measurements on the reference signals received from the determined reference signal resources.

[0171] At least one monitoring reference signal resource set may be selected based on at least one of the identifier of one or more monitoring reference signal resource sets, transmission order, transmission time, time interval, instruction information of a base station, beam information included in the inference result, time relationship between the inference result and the one or more monitoring reference signal resource sets, or a predetermined rule.

[0172] According to one example, the terminal may select at least one monitoring reference signal sub-occupation based on instruction information from a base station. The base station may transmit instruction information for sub-occupation selection to the terminal via at least one of MAC-CE (Medium Access Control - Control Element) or DCI (Downlink Control Information). According to another example, the terminal may select a monitoring reference signal sub-occupation containing a reference signal resource corresponding to a beam based on beam information (e.g., optimal beam index, beam pair information) included in the inference result. According to yet another example, the terminal may select a sub-occupation based on the time relationship between the time when inference is performed and the time when the monitoring reference signal sub-occupation is transmitted, and the sub-occupation closest to the time of inference may be selected.

[0173] Referring again to FIG. 8, the terminal can determine a performance evaluation result based on the measurement result and the inference result of the AI / ML model, and transmit a monitoring report message containing the performance evaluation result to the base station (S830).

[0174] Here, to determine the performance evaluation result, the terminal can determine whether there is a match between beam information based on the measurement result (e.g., optimal beam index determined by measurement) and beam information based on the inference result of an AI / ML model (e.g., predicted optimal beam index). According to one example, the terminal can calculate a performance metric based on whether the optimal beam determined by measurement and the optimal beam predicted by inference are identical. Additionally, the terminal can calculate a performance metric based on the difference between the received power of the Top-K beam determined by measurement and the received power of the optimal beam predicted by inference.

[0175] According to one example, the performance evaluation result may be determined based on at least one of beam information and / or received power information determined by the result of measurement, beam information, predicted received power information, or probability information determined by the result of inference.

[0176] The monitoring report message may include at least one of a performance metric value, an optimal beam index determined by measurement, received power information, or accuracy information of the inference result. Based on the performance evaluation result included in the monitoring report message, the base station may determine whether the performance of the AI / ML model has degraded and, if necessary, instruct the terminal to perform subsequent actions such as updating, switching, or deactivating the model.

[0177] According to this, a method and device for performing beam management using artificial intelligence and machine learning in a next-generation wireless access network can be provided. Furthermore, by providing a method to minimize signaling overhead and increase accuracy even without measuring all reference signals for Set A, high-accuracy performance evaluation results can be provided to the network.

[0178]

[0179] FIG. 9 is a diagram illustrating a procedure (900) in which a base station according to one embodiment performs beam management using artificial intelligence and machine learning. The description in FIG. 8 above may be omitted to avoid redundant descriptions, and in this case, the omitted content may be applied substantially the same to the base station as long as it does not contradict the technical concept of the invention.

[0180] Referring to FIG. 9, the base station can transmit first reference signal resource information for inference of an AI / ML model and second reference signal resource information for performance monitoring of the AI / ML model to a terminal (user equipment; UE) through at least one CSI report setting message (S910).

[0181] Here, at least one CSI report configuration message may include a CSI report configuration message for inference (CSI-ReportConfig) and a CSI report configuration message for monitoring. A base station may transmit first reference signal resource information to a terminal via the CSI report configuration message for inference and may transmit second reference signal resource information to a terminal via the CSI report configuration message for monitoring. The CSI report configuration message for monitoring may be connected to the CSI report configuration message for inference. The first reference signal resource information may include information regarding an entire reference signal resource set (e.g., Set A) corresponding to the inference result of an AI / ML model. The second reference signal resource information may include information regarding one or more monitoring reference signal resource sets (e.g., monitoring sets) having a size smaller than that of the entire reference signal resource set (e.g., Set A).

[0182] The second reference signal resource information may include time-domain operation and physical resource information for a reference signal resource included in each of one or more monitoring reference signal resource sets. The time-domain operation may be set to one of periodic transmission, semi-continuous transmission, or non-periodic transmission, and a common time-domain operation may be set for one or more monitoring reference signal resource sets, or an independent time-domain operation may be set for each monitoring reference signal resource set. The base station may set time gap information between one or more monitoring reference signal resource sets through the second reference signal resource information, and the time gap may be set by considering the processing time for the terminal to calculate a performance metric for one monitoring reference signal resource set.

[0183] Referring again to FIG. 9, the base station can transmit a reference signal from a reference signal resource included in at least one of the monitoring reference signal resource sets that are set based on the second reference signal resource information (S920).

[0184] Here, the base station may transmit CSI-RS or SSB from a reference signal resource included in a selected set of monitoring reference signal resources. In the present disclosure, a single transmission time in which a reference signal resource included in each set of monitoring reference signal resources is transmitted may be defined as a monitoring RS sub-occasion. The base station may transmit a reference signal from a monitoring RS sub-occasion corresponding to one or more configured sets of monitoring reference signal resources.

[0185] According to one example, one or more monitoring reference signal resource sets may include a plurality of groups of reference signal resources that constitute at least a subset of the entire reference signal resource set corresponding to the first reference signal resource information.

[0186] According to one example, a plurality of groups may be configured by sequentially mapping reference signal resources included in an entire reference signal resource set. In a sequential mapping scheme, when A reference signal resources included in an entire reference signal resource set (Set A) are sequentially mapped X times to G monitoring reference signal resource sets, the beam index of Set A corresponding to the CRI(i) of the g-th monitoring reference signal resource set may be determined as (g_id(g) * X) + CRI(i). According to another example, a plurality of groups may be configured by distributed mapping reference signal resources included in an entire reference signal resource set.

[0187] In a distributed mapping scheme, the beam index of Set A corresponding to the CRI(i) of the g-th monitoring reference signal resource set can be determined as (CRI(i) * G) + g_id(g). Here, i is an integer greater than or equal to 0 and less than X, G is the rounded-up value of A / X, and g is an integer greater than or equal to 0 and less than G. The base station may transmit at least one of G and X to the terminal to enable the terminal to derive the corresponding mapping information. According to another example, a plurality of groups may be determined according to a configuration explicitly indicated by the base station through signaling.

[0188] The second reference signal resource information may include information regarding the correspondence relationship between a reference signal resource included in the entire reference signal resource set and a reference signal resource included in one or more monitoring reference signal resource sets, or information for deriving the correspondence relationship. The correspondence relationship may be determined based on at least one of the index of a reference signal resource included in the entire reference signal resource set, the index of one or more monitoring reference signal resource sets, the number of one or more monitoring reference signal resource sets, the number of reference signal resources included in each monitoring reference signal resource set, bitmap information, group information, or reference signal resource indication information. Additionally, the correspondence relationship may be explicitly indicated by the base station through bitmap information, and each bit in the bitmap may correspond to each reference signal resource included in the entire reference signal resource set, and a reference signal resource with a bit value of '1' may be included in the corresponding monitoring reference signal resource set.

[0189] Referring again to FIG. 9, the base station can receive a monitoring report message from the terminal containing a performance evaluation result determined based on the result of a measurement of a reference signal and the inference result of an AI / ML model (S930).

[0190] The monitoring report message may include at least one of a performance metric value, an optimal beam index determined by measurement, received power information, or accuracy information of the inference result. The base station may determine the performance status of the AI / ML model based on the performance evaluation result included in the monitoring report message and determine whether the performance is satisfactory or unsatisfactory. The performance evaluation result may be a result determined by the terminal based on at least one of beam information and / or received power information determined by the measurement result, beam information determined by the inference result, predicted received power information, or probability information.

[0191] According to one example, the performance evaluation result may be determined based on beam prediction accuracy. Specifically, a performance metric may be calculated based on whether the optimal beam determined by measurement and the optimal beam predicted by inference of an AI / ML model are the same. According to another example, the performance evaluation result may be determined based on the difference between the received power of the Top-K beam determined by measurement and the received power of the optimal beam predicted by inference. Based on the performance evaluation result, the base station may perform at least one subsequent action among updating the AI / ML model, changing the reference signal resource settings, or resetting the monitoring reference signal resource set.

[0192] According to this, a method and device for performing beam management using artificial intelligence and machine learning in a next-generation wireless access network can be provided. Furthermore, by providing a method to minimize signaling overhead and increase accuracy even without measuring all reference signals for Set A, high-accuracy performance evaluation results can be provided to the network.

[0193]

[0194] Hereinafter, with reference to the relevant drawings, each embodiment related to a method for performing beam management using artificial intelligence and machine learning will be described in detail.

[0195] The present disclosure proposes that a terminal performing beam management using an AI / ML model receive G monitoring sets for the model, measure a reference signal for at least one monitoring set among the G monitoring sets, and calculate a monitoring metric based on the measured result value.

[0196] First, the present disclosure defines a method for configuring G monitoring sets. A base station provides information to a terminal to derive information about which beam of Set A a beam belonging to the G monitoring sets is mapped to, based on at least one of the following methods, or sets clear mapping information, so that the terminal can obtain which RS indicator of Set A a beam mapped to an RS resource belonging to each monitoring group is a beam.

[0197] One of the following mapping methods can be applied between the RS resources constituting the monitoring set and the RS resources belonging to Set A (total size = A).

[0198] FIG. 10 is a diagram illustrating the mapping of reference signal resources (RS resources) of Set A according to one embodiment and RS resources belonging to each group of the monitoring set.

[0199] - Plan 1. RS resources belonging to Set A are sequentially mapped X items each to G monitoring sets.

[0200] That is, it can be mapped as Set A beam ID for CRI(i) of Group_id(g) = (g_id (g)* X) + CRI (i).

[0201] Here, i is an integer greater than or equal to 0 and less than x.

[0202] Here, G is the carry-over value of A / X (G = A / X), and g is an integer greater than or equal to 0 and less than g.

[0203] The base station must transmit at least one of G and X information to enable the terminal to derive the corresponding mapping information.

[0204] Figure 10 is an example of RS resources of Set A that are mapped to RS resources belonging to each group when Set A consists of a total of 16 RS resources and the monitoring set is divided into two groups.

[0205]

[0206] FIG. 11 is a diagram illustrating the mapping of RS resources of Set A and RS resources belonging to each group of the monitoring set according to another embodiment.

[0207] - Method 2. Map RS resources belonging to Set A to be distributed across G monitoring sets.

[0208] That is, Set A beam ID for CRI(i) of Group_id(g) = (CRI(i) * G) + g_id(g)

[0209] Here, i is an integer greater than or equal to 0 and less than x.

[0210] Here, G is the carry-over of A / X (G = A / X), where g is an integer greater than or equal to 0 and less than g.

[0211] The base station must transmit at least one of G and X information to enable the terminal to derive the corresponding mapping information.

[0212] Figure 11 is an example of RS resources of Set A that are mapped to RS resources belonging to each group when Set A consists of a total of 16 RS resources and the monitoring set is divided into two groups.

[0213]

[0214] FIG. 12 is a diagram illustrating the mapping of RS resources of Set A and RS resources belonging to each group of the monitoring set according to another embodiment.

[0215] Method 3. RS indicators of Set A, mapped to each reference signal indicator (RS indicator) belonging to each of the G groups configured as subsets among the RS resources belonging to Set A, are transmitted via CSI-ReportConfig for monitoring with clear signaling.

[0216] 3-1. Beams included in a group are indicated by setting them to 1 via an A-bit length bitmap, in which case the A-bit length bitmap may be included as information for each group, or

[0217] 3-2. May include information indicating group information for CRIs belonging to Set A, or

[0218] 3-3. For each CRI included in each group, the CRI for Set A can be signaled together.

[0219] Figure 12 is an example showing the information of the RS resources of Set A mapped to the RS resources belonging to each group based on the above 3-1 and 3-2 methods when Set A consists of a total of 16 RS resources and the monitoring set is divided into 4 groups.

[0220]

[0221] Grouping information for monitoring may be included in the CSI-ReportConfig message for monitoring or configured through other RRC configuration messages. This configuration may include time-domain behavior and physical resource information regarding the transmission of CSI-RS / SSB resources belonging to each group.

[0222] The base station can set the number of groups to which it will actually perform transmission among a total of G groups through the corresponding configuration message, and the time information for the g groups configured by the base station to be transmitted can be defined by the time gap between groups. By defining the time gap information between adjacent groups, the transmission time and transmission occasions of each group can be distinguished by the terminal. Here, it is preferable that the time gap be set by considering the processing time for the terminal to calculate a performance metric for one group.

[0223] RS resources belonging to the above G monitoring groups are defined as different CSI resource sets for each group. The time behavior for each resource set can be set through independent configuration information or through common time behavior configuration information for the configured G (or transmitted g) monitoring groups. That is, in the latter case, if periodic transmission is set, it means that transmission occurs in one period for all g groups; if aperiodidic transmission is set, it means that transmission occurs at once by one MAC CE for all g groups; and if semi-persistent (SP) transmission is set, it means that it is triggered at once by one MAC CE or DCI and transmitted in one period.

[0224] FIG. 13 is a diagram illustrating the timing of grouping-based monitoring transmission according to one embodiment.

[0225] Figure 13 is an example of transmission sub-occasions of CSI-RS / SSB resources belonging to each group using a time gap when the base station is configured to transmit up to three groups.

[0226] Next, a method is proposed in which a terminal receiving the above-mentioned configuration information measures RS resources belonging to at least one of G monitoring groups and evaluates monitoring performance based on this.

[0227] A terminal that receives a CSI-reportConfig message for monitoring including at least G sets of monitoring resources, selects one of the configured G groups and measures the signal strength of RS resources transmitted to the corresponding resource set. As illustrated in FIG. 13, the present disclosure defines a single transmission time when RS resources belonging to each group are transmitted as a monitoring RS sub-occasion. At this time, the present disclosure proposes defining a method for selecting at least one RS sub-occasion for monitoring based on one of the following.

[0228] - Sub-occasion Selection Method 1. Random selection

[0229] Randomly select one of the sub-occasions.

[0230] - Sub-occasion Selection Plan 2. Sequential selection based on base station instructions

[0231] The base station indicates the group ID of one of the g groups being transmitted.

[0232] - Sub-occasion Selection Plan 3. Select the group containing the most Top-K.

[0233] Since the terminal can identify the beams belonging to each group in advance based on the index of the Top-K beam already predicted by the inference of the AI / ML model and the mapping information (Plan 1, 2, or 3) set from the base station, it can select the group containing the most Top-K beams, which are the inference results linked to the corresponding monitoring RS occasion, before performing actual measurements.

[0234] - Sub-occasion Selection Plan 4. Group selection for the sub-occasion located at the very front

[0235] The terminal selects a group for the first transmitted sub-occasion within the monitoring RS occasion linked to Top-K.

[0236] - Sub-occasion Selection Method 5. Select in order of Group ID

[0237] Select the group with the lowest or highest group ID.

[0238] - Sub-occasion Selection Plan 6. Select the group of sub-occasions transmitted to the location closest to the reference point for Top-K first.

[0239] For BM-Case1, a sub-occasion with a reference time and minimal slot offset for a report message containing Top-K is selected.

[0240] For BM-Case2, a sub-occasion with a time instance and minimal slot offset for Top-K is selected.

[0241] The above sub-occasion selection can be defined to be selected commonly for N linked pairs or to be selected individually for each linked pair.

[0242] Based on the above method, the terminal performs measurements on a monitoring set for at least one group among one or more groups included in the monitoring RS occasion, and calculates a performance metric based on the measured result value.

[0243] (Performance Evaluation Method 1) The terminal selects one group of sub-occasions transmitted within the above-configured Monitoring RS occasion that is transmitted randomly / sequentially / the group containing the most linked Top-Ks / the location closest to the reference point for the linked Top-Ks based on the method for selection, and determines the performance evaluation result for this as the result value for the linked pair.

[0244] FIG. 14 is a diagram illustrating a grouping-based monitoring transmission time according to another embodiment.

[0245] The terminal selects a monitoring RS occasion linked to the predicted Top-K. The linked monitoring RS occasion assumes that G monitoring sets are transmitted based on one or more sub-occasions. Ultimately, the Top-K is linked to one sub-occasion transmitted within the selected monitoring RS occasion. Here, the terminal measures the signal strength of RS resources transmitted in the sub-occasion for one monitoring set selected by one of the above methods. When a monitoring RS occasion containing G sub-occasions is linked to one Top-K, the monitoring result for that one linked pair refers to the result value for one linked pair among up to N linked pairs that affect the performance result value included in the performance result report message.

[0246] (Performance Evaluation Method 2) For G sub-occasions of a single linked pair, all RS resources transmitted to up to G sub-occasions can be measured based on arbitrarily set conditions. That is, if a terminal that has selected the first sub-occasion based on the above sub-occasion selection method calculates the performance evaluation result for that sub-occasion as unsatisfactory and that sub-occasion is not the last sub-occasion, it selects a second sub-occasion within that occasion and additionally measures the signal strength of the RS resources transmitted from that second sub-occasion. The terminal calculates the performance for Top-K based on the measurement results of the first + second sub-occasions.

[0247] In other words, the terminal measures the signal strength of RS resources transmitted to the first selected sub-occasion, and if the performance evaluation result calculated based on the measured result is determined to be satisfactory, or if the corresponding sub-occasion is the last sub-occasion(s) set / transmitted within the corresponding monitoring RS occasion, it does not perform measurements on RS resources transmitted in additional sub-occasions, and determines the performance evaluation result calculated based on the results measured so far as the performance result value for the corresponding linked pair.

[0248] FIG. 15 is a diagram illustrating a grouping-based monitoring transmission time according to another embodiment.

[0249] When defined based on Performance Evaluation Method 2, first and second sub-occasion selection methods are required. This can be defined as follows for each sub-occasion selection method.

[0250] - Sub-occasion Selection Method 1. Random selection

[0251] Randomly select one of the sub-occasions.

[0252] If you choose a second sub-occasion,

[0253] Randomly select one of the groups for sub-occasions excluding the first sub-occasion; or

[0254] One of the groups of sub-occasions, including the first sub-occasion, can be randomly selected.

[0255] - Sub-occasion Selection Plan 2. Sequential selection based on base station instructions

[0256] The base station signals the selection order for g groups being transmitted through explicit instructions.

[0257] The terminal performs monitoring of sub-occasions based on the instructed order.

[0258] - Sub-occasion Selection Plan 3. Select the group with the most Top-K entries first.

[0259] The terminal performs monitoring by selecting the group containing the most Top-K, which is the inference result linked to the corresponding monitoring RS occasion.

[0260] - Sub-occasion Selection Plan 4. Select the group for the sub-occasion located at the very front.

[0261] The terminal prioritizes the group for the first transmitted sub-occasion within the monitoring RS occasion linked to Top-K.

[0262] If sub-occasions are located in order of group ID, it may mean that they are selected in order of group ID.

[0263] - Sub-occasion Selection Method 5. Select in order of Group ID

[0264] Prioritize selecting the group with the lowest or highest group ID.

[0265] - Sub-occasion Selection Plan 6. Select the group of sub-occasions transmitted to the location closest to the reference point for Top-K first.

[0266] In the case of BM-Case1, a sub-occasion with a reference time and minimal slot offset for a report message containing Top-K is selected first.

[0267] In the case of BM-Case2, a sub-occasion with a time instance and minimal slot offset for Top-K is selected first.

[0268] The following describes implementation examples for each performance metric when using Performance Evaluation Method 2.

[0269] First, when the performance metric is based on the aforementioned beam prediction accuracy, this disclosure provides a method for evaluating model performance through a group-based sub-occasion. Here, the terminal checks whether one of the Top-Ms, which measures the signal strength of CSI-RS / SSB resources transmitted to a single monitoring RS occasion linked to Top-K, belongs to Top-K. Here, the terminal can calculate the settings of the Top-M for comparison with Top-K by dividing them into the following two methods.

[0270] 1. Calculation of M-based metric set in RRC

[0271] A. Even if the number of RS resources belonging to the monitoring set is smaller than Set A, the terminal selects the RS resources with the highest RSRP among the measured RSRPs as Top-M.

[0272] 2. In addition to M set in RRC, receive an additional m (a positive integer smaller than M), and calculate metrics based on m and M.

[0273] A. Here, an additional threshold for m can be set. This threshold can be set to the size of the RS resources used for monitoring and the ratio value of Set A.

[0274] i. For example, if Set A is 16 and the threshold is set to 0.5, for monitoring sets with a size of 8 or less, the metric is calculated based on Top-m among the measured RSs, and for monitoring sets with a size exceeding 8, the metric is calculated based on Top-M.

[0275] B. m may be implicitly set based on the set M and the number of Groups (G).

[0276] Next, if the performance metric is calculated based on the RSRP difference value, the terminal calculates the difference between the RSRP measured for the signal strength of CSI-RS / SSB resources transmitted to a single monitoring RS occasion linked to Top-K and the predicted RSRP for an RS having a CRI of Set A mapped to the RS measured among the predicted beams, and if the result value (e.g., the average of the difference values) is greater than a set threshold, it determines that the performance is unsatisfactory. Here, if at least one RS resource (or a set number) among the RS resources included in the monitoring set is mapped to a CRI belonging to Top-K, the terminal determines the corresponding performance evaluation result value as the performance result value for the corresponding linked pair.

[0277] Otherwise, the signal strength of the RS resources transmitted in the second sub-occasion is additionally measured, and the performance evaluation result value calculated based on the result value for the first + second sub-occasion is determined as the performance result value for the corresponding linked pair. This may be repeated until at least one (or a set number) of RS resources mapped to a CRI belonging to Top-K is included among the RS resources included in the monitoring set, or until all measurements for G sub-occasion(s) are performed.

[0278] (Performance Evaluation Method 3) As another method, when G monitoring sets are configured based on the proposed method above, G resource sets corresponding to G groups are transmitted sequentially, and linked pairs are formed for G monitoring resource sets mapped to different beams. This allows the performance of the monitoring beam transmitted at the monitoring occasion linked to Top-K to be evaluated based on the measurement result values ​​for different beams, and the result values ​​for the evaluated N linked pairs are reported through a single monitoring report message.

[0279] FIG. 16 is a diagram illustrating a grouping-based monitoring transmission time according to another embodiment.

[0280] As illustrated in FIG. 16, it is assumed that among the G monitoring sets, monitoring sets for the same group are transmitted periodically based on G*period, while monitoring sets transmitted consecutively for different groups are transmitted at period intervals. In this way, transmission rules for monitoring RS occasions for each group are transmitted to the terminal through the grouping and time behavior described above. Based on the configured information, the terminal can determine which RS resources in Set A the RS transmitted at each occasion are mapped to through the transmission occasions of the RS resources belonging to the groups. The terminal selects a Top-K linked to a monitoring RS occasion for an arbitrary group and determines a single linked pair consisting of the RS signal strength result measured at that occasion and the predicted result for the linked Top-K (Top-K if the prediction method is beam identification accuracy, or the predicted result for the RS mapped to the measured RS if it is reception strength difference). The terminal performs a performance evaluation on N linked pairs and determines the number of pairs (N) that satisfy the performance among the total N linked pair(s). p Information about ) (N p Reports / N) to the base station.

[0281] It is desirable that the number of RS resources (X) transmitted in a single sub-occasion set in the aforementioned performance evaluation methods 1, 2, and 3 have a size greater than K. In particular, when the monitoring metric beam identification accuracy is applied, the number of RS resources included in the resource set set for monitoring must be equal to or smaller than Set A and have a value greater than K.

[0282] Here, if the beam of RS resources belonging to the sub-occasion(s) measured for monitoring includes all beams for Top-K and the monitoring performance result calculated based thereon is determined to be unsatisfactory performance, the terminal determines the monitoring performance result (i.e., unsatisfactory performance) as the performance result for the corresponding linked pair. In particular, in the case of the above performance evaluation method 2, even if the beam of RS resources belonging to the sub-occasion(s) measured for monitoring includes all beams for Top-K and the monitoring performance result calculated based thereon is determined to be unsatisfactory performance, the terminal determines the monitoring performance result (i.e., unsatisfactory performance) as the performance result for the corresponding linked pair without additional performance evaluation for sub-occasions.

[0283] Here, a monitoring resource set consisting of one or more groups configured as subsets of Set A may be configured with G RS resource sets for G groups by a single CSI-ReportConfig, or configured individually by G different CSI-ReportConfig(s). When configured by different CSI-ReportConfigs, a configuration message containing CSI resource information for each group is associated with a single CSI-ReportConfig for inference.

[0284] As described above, according to the present disclosure, when performing a performance evaluation of a beam management technique using AI / ML, if the number of reference signal resources for monitoring is smaller than the number of reference signal resources for Set A, signaling overhead is minimized by providing an implicit method for mapping between the reference signal resources for monitoring and the reference signal resources for Set A, and a method is provided to increase accuracy even without measuring all reference signals for Set A, thereby providing a high-accuracy performance evaluation result as NW.

[0285] The aforementioned embodiments may be applied independently of each other, or two or more embodiments may be combined and implemented.

[0286]

[0287] Hereinafter, the configuration of a terminal and a base station capable of performing some or all of the embodiments described with reference to FIGS. 1 to 16 will be described with reference to the drawings. The foregoing description may be omitted to avoid redundant descriptions, and in such cases, the omitted content may be applied substantially identically to the following description, provided that it does not contradict the technical concept of the invention.

[0288] FIG. 17 is a diagram showing the configuration of a terminal (1700) according to another embodiment.

[0289] Referring to FIG. 17, a terminal (1700) according to another embodiment includes a transmitter (1720), a receiver (1730), and a control unit (1710) that controls the transmitter and the receiver.

[0290] The control unit (1710) controls the overall operation of the terminal (1700) according to the method of performing beam management using artificial intelligence and machine learning necessary to perform the above-described embodiments.

[0291] The transmitting unit (1720) and the receiving unit (1730) are used to transmit and receive signals, messages, and data to and from a base station that are necessary to perform the above-described embodiments.

[0292] The control unit (1710) can control the reception unit (1730) to receive first reference signal resource information for inference of an AI / ML model and second reference signal resource information for performance monitoring of the AI / ML model from a base station through at least one CSI report setting message. Here, the first reference signal resource information may include information regarding an entire reference signal resource set (e.g., Set A) corresponding to the inference result of the AI / ML model, and the second reference signal resource information may include information regarding one or more monitoring reference signal resource sets (e.g., monitoring set) having a size smaller than that of the entire reference signal resource set (e.g., Set A).

[0293] The control unit (1710) can select at least one of one or more monitoring reference signal resource sets based on the second reference signal resource information and control the performance of a measurement of a reference signal received from a reference signal resource included in the selected monitoring reference signal resource set. Here, one or more monitoring reference signal resource sets may include a plurality of groups of reference signal resources that constitute at least a subset of the entire reference signal resource set, and the plurality of groups may be configured by sequential mapping, distributed mapping, or explicit signaling of a base station.

[0294] The second reference signal resource information may include information regarding the correspondence relationship between a reference signal resource included in the entire reference signal resource set and a reference signal resource included in one or more monitoring reference signal resource sets, or may include information for deriving the correspondence relationship.

[0295] The correspondence relationship may be determined based on at least one of the index of a reference signal resource included in the entire reference signal resource set, the index of one or more monitoring reference signal resource sets, the number of one or more monitoring reference signal resource sets, the number of reference signal resources included in each monitoring reference signal resource set, the index of a reference signal resource within each monitoring reference signal resource set, bitmap information, group information, or reference signal resource indication information.

[0296] The control unit (1710) can control the selection of at least one monitoring RS sub-occasion based on at least one of the identifier of one or more monitoring reference signal resource sets, transmission order, transmission time, time interval, instruction information of a base station, beam information included in the inference result, time relationship between the inference result and one or more monitoring reference signal resource sets, or a predetermined rule.

[0297] The control unit (1710) can determine a performance evaluation result based on the measurement result and the inference result of the AI / ML model, and control the transmission of a monitoring report message containing the performance evaluation result to a base station through the transmission unit (1720). Here, the performance evaluation result may be determined based on at least one of beam information and / or received power information determined by the measurement result, and beam information, predicted received power information, or probability information determined by the inference result.

[0298] According to this, a method and device for performing beam management using artificial intelligence and machine learning in a next-generation wireless access network can be provided. Furthermore, by providing a method to minimize signaling overhead and increase accuracy even without measuring all reference signals for Set A, high-accuracy performance evaluation results can be provided to the network.

[0299] FIG. 18 is a drawing showing the configuration of a base station (1800) according to another embodiment.

[0300] Referring to FIG. 18, a base station (1800) according to another embodiment includes a transmitter (1820), a receiver (1830), and a control unit (1810) that controls the transmitter and the receiver.

[0301] The control unit (1810) controls the overall operation of the base station (1800) and the operation of the repeater according to the method of performing beam management using artificial intelligence and machine learning necessary to perform the above-described embodiments.

[0302] The transmitting unit (1820) and the receiving unit (1830) are used to transmit and receive signals, messages, and data to and from the terminal that are necessary to perform the above-described embodiments.

[0303] The control unit (1810) can control the transmission unit (1820) to transmit first reference signal resource information for inference of an AI / ML model and second reference signal resource information for performance monitoring of the AI / ML model to a terminal through at least one CSI report setting message. Here, the first reference signal resource information may include information regarding an entire reference signal resource set (e.g., Set A) corresponding to the inference result of the AI / ML model, and the second reference signal resource information may include information regarding one or more monitoring reference signal resource sets (e.g., monitoring set) having a size smaller than that of the entire reference signal resource set (e.g., Set A).

[0304] The control unit (1810) can control the transmission of a reference signal from a reference signal resource included in at least one of the monitoring reference signal resource sets configured based on the second reference signal resource information to a terminal through the transmission unit (1820). Here, the one or more monitoring reference signal resource sets may include a plurality of groups of reference signal resources that constitute at least a subset of the entire reference signal resource set, and the plurality of groups may be configured by sequential mapping, distributed mapping, or explicit signaling.

[0305] The second reference signal resource information may include information regarding a correspondence relationship between a reference signal resource included in an entire reference signal resource set and a reference signal resource included in one or more monitoring reference signal resource sets, or information for deriving said correspondence relationship. Here, the correspondence relationship may be determined based on at least one of an index of a reference signal resource included in an entire reference signal resource set, an index of one or more monitoring reference signal resource sets, the number of one or more monitoring reference signal resource sets, the number of reference signal resources included in each monitoring reference signal resource set, an index of a reference signal resource within each monitoring reference signal resource set, bitmap information, group information, or reference signal resource indication information.

[0306] The control unit (1810) can control the transmission of a reference signal in at least one monitoring RS sub-occasion based on at least one of the identifier of one or more monitoring reference signal resource sets, transmission order, transmission time, time interval, instruction information, beam information included in the inference result, time relationship between the inference result and one or more monitoring reference signal resource sets, or a predetermined rule.

[0307] Additionally, the control unit (1810) can control the reception unit (1830) to receive a monitoring report message from the terminal, and the performance evaluation result included in the monitoring report message can be determined based on at least one of beam information and / or received power information determined by the result of measurement, beam information determined by the result of inference, predicted received power information, or probability information.

[0308] According to this, a method and device for performing beam management using artificial intelligence and machine learning in a next-generation wireless access network can be provided. Furthermore, by providing a method to minimize signaling overhead and increase accuracy even without measuring all reference signals for Set A, high-accuracy performance evaluation results can be provided to the network.

[0309] The aforementioned embodiments may be supported by standard documents disclosed in at least one of the wireless access systems IEEE 802, 3GPP, and 3GPP2. That is, steps, configurations, and parts in the embodiments that are not described to clearly reveal the technical concept may be supported by the aforementioned standard documents. Furthermore, all terms disclosed in this specification may be explained by the standard documents disclosed above.

[0310] The embodiments described above may be implemented through various means. For example, the embodiments may be implemented by hardware, firmware, software, or a combination thereof.

[0311] In the case of implementation by hardware, the method according to the embodiments may be implemented by one or more ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), processors, controllers, microcontrollers, or microprocessors.

[0312] In the case of implementation by firmware or software, the method according to the embodiments may be implemented in the form of a device, procedure, or function that performs the functions or operations described above. Software code may be stored in a memory unit and executed by a processor. The memory unit may be located inside or outside the processor and may exchange data with the processor by various means already known.

[0313] Additionally, terms such as "system," "processor," "controller," "component," "module," "interface," "model," or "unit" described above may generally refer to computer-related entities, hardware, combinations of hardware and software, software, or running software. For example, the aforementioned components may be, but are not limited to, processes driven by a processor, processors, controllers, control processors, objects, execution threads, programs, and / or computers. For example, both the application running on the controller or processor and the controller or processor may be components. One or more components may reside within a process and / or execution thread, and the components may be located on a single device (e.g., a system, a computing device, etc.) or distributed across two or more devices.

[0314] The foregoing description is merely an illustrative explanation of the technical concept of the present disclosure, and those skilled in the art to which the present disclosure pertains may make various modifications and variations within the scope of the essential characteristics of the technical concept. Furthermore, since these embodiments are intended to explain, not limit, the scope of the technical concept is not limited by these embodiments. The scope of protection of the present disclosure shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of the present disclosure.

[0315]

[0316] CROSS-REFERENCE TO RELATED APPLICATION

[0317] This patent application claims priority pursuant to Section 119(a) of the U.S. Patent Act (35 USC § 119(a)) to Korean Patent Application No. 10-2025-0064029 filed on May 16, 2025, all of which are incorporated by reference into this patent application. Furthermore, this patent application claims priority in countries other than the United States for the same reasons as above, all of which are incorporated by reference into this patent application.

Claims

1. A method in which a terminal (user equipment; UE) performs beam management using artificial intelligence and machine learning (AI / ML), A step of receiving, from a base station, first reference signal resource information for inference of an AI / ML model and second reference signal resource information for performance monitoring of said AI / ML model through at least one CSI report setting message; Based on the second reference signal resource information above, selecting at least one monitoring reference signal resource set among one or more monitoring reference signal resource sets, and performing a measurement on a reference signal received from a reference signal resource included in the selected monitoring reference signal resource set; and The method includes the step of determining a performance evaluation result based on the results of the above measurement and the inference results of the above AI / ML model, and transmitting a monitoring report message including the performance evaluation result to the base station. A method in which one or more monitoring reference signal resource sets include a plurality of groups of reference signal resources constituting at least a subset of the entire reference signal resource set corresponding to the first reference signal resource information.

2. In Paragraph 1, The above first reference signal resource information is, It includes information regarding the entire reference signal resource set corresponding to the inference result of the above AI / ML model, and The above second reference signal resource information is, A method comprising information regarding one or more monitoring reference signal resource sets having a size smaller than the entire reference signal resource set.

3. In Paragraph 2, The above second reference signal resource information is, A method comprising information regarding a correspondence relationship between a reference signal resource included in the above-mentioned entire reference signal resource set and a reference signal resource included in the above-mentioned one or more monitoring reference signal resource sets, or information for deriving said correspondence relationship.

4. In Paragraph 3, The above correspondence relationship is, A method determined based on at least one of the index of a reference signal resource included in the entire reference signal resource set, the index of one or more monitoring reference signal resource sets, the number of one or more monitoring reference signal resource sets, the number of reference signal resources included in each monitoring reference signal resource set, the index of a reference signal resource within each monitoring reference signal resource set, bitmap information, group information, or reference signal resource indication information.

5. In Paragraph 1, The above at least one set of monitoring reference signal resources is, A method selected based on at least one of the identifier of one or more monitoring reference signal resource sets, transmission order, transmission time, time interval, instruction information of a base station, beam information included in the inference result, the time relationship between the inference result and the one or more monitoring reference signal resource sets, or a predetermined rule.

6. In Paragraph 1, The above performance evaluation results are, A method determined based on at least one of beam information and / or received power information determined by the result of the above measurement, and beam information, predicted received power information, or probability information determined by the result of the above inference.

7. A method in which a base station (BS) performs beam management using artificial intelligence and machine learning (AI / ML), A step of transmitting first reference signal resource information for inference of an AI / ML model and second reference signal resource information for performance monitoring of said AI / ML model to a terminal (user equipment; UE) through at least one CSI report setting message; A step of transmitting a reference signal from a reference signal resource included in at least one monitoring reference signal resource set among one or more monitoring reference signal resource sets set based on the second reference signal resource information; and The method includes the step of receiving a monitoring report message from the terminal containing a performance evaluation result determined based on the result of a measurement of the reference signal and the inference result of the AI / ML model, wherein A method in which one or more monitoring reference signal resource sets include a plurality of groups of reference signal resources constituting at least a subset of the entire reference signal resource set corresponding to the first reference signal resource information.

8. In Paragraph 7, The above first reference signal resource information is, It includes information regarding the entire reference signal resource set corresponding to the inference result of the above AI / ML model, and The above second reference signal resource information is, A method comprising information regarding one or more monitoring reference signal resource sets having a size smaller than the entire reference signal resource set.

9. In Paragraph 8, The above second reference signal resource information is, A method comprising information regarding a correspondence relationship between a reference signal resource included in the above-mentioned entire reference signal resource set and a reference signal resource included in the above-mentioned one or more monitoring reference signal resource sets, or information for deriving said correspondence relationship.

10. In Paragraph 9, The above correspondence relationship is, A method determined based on at least one of the index of a reference signal resource included in the entire reference signal resource set, the index of one or more monitoring reference signal resource sets, the number of one or more monitoring reference signal resource sets, the number of reference signal resources included in each monitoring reference signal resource set, the index of a reference signal resource within each monitoring reference signal resource set, bitmap information, group information, or reference signal resource indication information.

11. In Paragraph 7, The above at least one set of monitoring reference signal resources is, A method selected based on at least one of the identifier of one or more monitoring reference signal resource sets, transmission order, transmission time, time interval, instruction information of a base station, beam information included in the inference result, the time relationship between the inference result and the one or more monitoring reference signal resource sets, or a predetermined rule.

12. In Paragraph 7, The above performance evaluation results are, A method determined based on at least one of beam information and / or received power information determined by the result of the above measurement, and beam information, predicted received power information, or probability information determined by the result of the above inference.

13. In a terminal (user equipment; UE) that performs beam management using artificial intelligence and machine learning (AI / ML), Transmitter; Receiver; and It includes a control unit that controls the operation of the transmitting unit and the receiving unit, wherein The above control unit is, Receive from a base station, first reference signal resource information for inference of an AI / ML model and second reference signal resource information for performance monitoring of the AI / ML model through at least one CSI report setting message, Based on the second reference signal resource information above, at least one monitoring reference signal resource set among one or more monitoring reference signal resource sets is selected, and a measurement is performed on a reference signal received from a reference signal resource included in the selected monitoring reference signal resource set. A performance evaluation result is determined based on the results of the above measurement and the inference results of the above AI / ML model, and a monitoring report message including the performance evaluation result is transmitted to the base station, The above one or more monitoring reference signal resource sets comprise a plurality of groups of reference signal resources that constitute at least a subset of the entire reference signal resource set corresponding to the first reference signal resource information.

14. In Paragraph 13, The above first reference signal resource information is, It includes information regarding the entire reference signal resource set corresponding to the inference result of the above AI / ML model, and The above second reference signal resource information is, A terminal comprising information regarding one or more monitoring reference signal resource sets having a size smaller than the entire reference signal resource set.

15. In Paragraph 14, The above second reference signal resource information is, A terminal comprising information regarding a correspondence relationship between a reference signal resource included in the above-mentioned entire reference signal resource set and a reference signal resource included in the above-mentioned one or more monitoring reference signal resource sets, or information for deriving said correspondence relationship.

16. In Paragraph 15, The above correspondence relationship is, A terminal determined based on at least one of the index of a reference signal resource included in the above-mentioned entire reference signal resource set, the index of one or more monitoring reference signal resource sets, the number of one or more monitoring reference signal resource sets, the number of reference signal resources included in each monitoring reference signal resource set, the index of a reference signal resource within each monitoring reference signal resource set, bitmap information, group information, or reference signal resource indication information.

17. In Paragraph 13, The above at least one set of monitoring reference signal resources is, A terminal selected based on at least one of the identifier of one or more monitoring reference signal resource sets, transmission order, transmission time, time interval, base station instruction information, beam information included in the inference result, the time relationship between the inference result and the one or more monitoring reference signal resource sets, or a predetermined rule.

18. In Paragraph 13, The above performance evaluation results are, A terminal determined based on at least one of beam information and / or received power information determined by the result of the above measurement, and beam information, predicted received power information, or probability information determined by the inference result.