Method for performing beam management operation in wireless communication system and apparatus therefor

Abstract

The present disclosure relates to a technique for monitoring performance of an AI / ML model implemented in a terminal, and relates to a method and an apparatus, the method comprising the steps of: receiving, from a base station, configuration information for evaluating a model configured for beam prediction; receiving a reference signal on the basis of the configuration information; generating evaluation result information of the model by comparing a measurement result for the reference signal with beam prediction result information generated by using an output of the model; and transmitting the evaluation result information of the model to the base station.

Description

Method and device for performing beam management operation in a wireless communication system

[0001] The present disclosure relates to a communication technology using an AI / ML model, and relates to a method and device for performing a beam management operation in a wireless communication system.

[0002] The International Telecommunication Union (ITU) is working on standardizing next-generation 5th generation (5G) and 6th generation (6G) mobile communications through the International Mobile Telecommunication (IMT)-2020 and IMT-2030 programs.

[0003] The IMT-2020 and IMT-2030 projects are proposing technologies such as expanded numerology, large-scale antennas, and mmWave to meet these technical requirements. In particular, they are discussing the development of new technologies for enhanced 5G mobile communication technologies and the next-generation 6G mobile communication system. For 6G systems, technologies are being discussed that will advance wireless communication technologies and expand usability, including THz bands, AI-based networks, and ultra-precision positioning / sensing.

[0004] Specifically, 5G mobile communication technology defines a wide frequency band to enable fast transmission speeds and new services, and can be implemented not only in the sub-6GHz frequency band ('Sub 6GHz') such as 3.5 gigahertz (3.5GHz), but also in the ultra-high frequency band ('Above 6GHz') called millimeter wave (mmWave) such as 28GHz and 39GHz. In addition, in the case of 6G mobile communication technology, which is called the system after 5G communication (Beyond 5G), implementation in the terahertz band (for example, the 3 terahertz (3THz) band at 95GHz) is being considered to achieve a transmission speed that is 50 times faster than 5G mobile communication technology and an ultra-low latency time that is reduced to one-tenth.

[0005] In addition, the development of these 5G mobile communication systems includes new waveforms to ensure coverage in the terahertz band of 6G mobile communication technology, multi-antenna transmission technologies such as Full Dimensional MIMO (FD-MIMO), Array Antenna, and Large Scale Antenna, metamaterial-based lenses and antennas to improve the coverage of terahertz band signals, high-dimensional spatial multiplexing technology using Orbital Angular Momentum (OAM), Reconfigurable Intelligent Surface (RIS) technology, as well as full duplex technology to improve the frequency efficiency and system network of 6G mobile communication technology, satellite, AI (Artificial Intelligence) from the design stage and AI-based communication technology that realizes system optimization by internalizing end-to-end AI support functions, and ultra-high-performance communication and computing resources to provide services with complexity that exceeds the limits of terminal computing capabilities. It can serve as a basis for the development of next-generation distributed computing technologies that can be realized by utilizing them.

[0006] In this way, AI-based networking is expected to become more active in next-generation mobile communication systems, but a specific framework for this has not yet been presented.

[0007] Therefore, various communication technologies and methods are urgently needed in these AI-based enhanced network systems.

[0008] The present embodiments aim to provide a method and device for performing a beam management operation in a wireless communication system.

[0009] The present embodiments provide a method and device for performing AI / ML model performance monitoring for beam management in a wireless communication system.

[0010] In one aspect, the present embodiments may include a method for a terminal to perform beam management, comprising: receiving configuration information for evaluating a model configured for beam prediction from a base station; receiving a reference signal based on the configuration information; comparing beam prediction result information generated using a measurement result for the reference signal and an output of the model to generate model evaluation result information; and transmitting the model evaluation result information to the base station.

[0011] In another aspect, the present embodiments may provide a method in which a base station performs beam management, the method including a step of transmitting configuration information for evaluating a model configured in the terminal for beam prediction to the terminal, a step of transmitting a reference signal based on the configuration information, and a step of receiving evaluation result information of the generated model by comparing beam prediction result information generated using a measurement result for the reference signal and an output of the model from the terminal.

[0012] In another aspect, the present embodiments can provide a terminal device that includes a receiving unit that receives configuration information for evaluating a model configured for beam prediction from a base station and receives a reference signal based on the configuration information, a control unit that generates model evaluation result information by comparing beam prediction result information generated using a measurement result for the reference signal and an output of the model, and a transmitting unit that transmits the model evaluation result information to the base station, in a terminal that performs beam management.

[0013] In another aspect, the present embodiments can provide a base station that performs beam management, including a transmitter that transmits configuration information for evaluating a model configured in a terminal for beam prediction to a terminal and transmits a reference signal based on the configuration information, and a receiver that compares beam prediction result information generated using a measurement result for the reference signal and an output of the model and receives evaluation result information of the generated model from the terminal.

[0014] According to the present embodiments, it is possible to provide AI-based networking operations that can monitor the performance of AI / ML models for beam management and prevent performance degradation.

[0015] FIG. 1 is a schematic diagram illustrating the structure of an NR wireless communication system to which the present embodiment can be applied.

[0016] FIG. 2 is a drawing for explaining a frame structure in an NR system to which the present embodiment can be applied.

[0017] FIG. 3 is a diagram for explaining a resource grid supported by a wireless access technology to which the present embodiment can be applied.

[0018] FIG. 4 is a diagram for explaining a bandwidth part supported by a wireless access technology to which the present embodiment can be applied.

[0019] FIG. 5 is a diagram illustrating an example of a synchronization signal block in a wireless access technology to which the present embodiment can be applied.

[0020] FIG. 6 is a diagram for explaining a random access procedure in a wireless access technology to which the present embodiment can be applied.

[0021] Figure 7 is a drawing for explaining CORESET.

[0022] FIG. 8 is a diagram illustrating the structure of a functional framework for RAN Intelligence according to one embodiment.

[0023] FIG. 9 is a diagram for explaining a beam management operation using an AI / ML model according to one embodiment.

[0024] FIG. 10 is a diagram for explaining a beam prediction operation using a UE-side AI / ML model according to one embodiment.

[0025] FIG. 11 is a diagram for explaining a beam prediction operation using a NW-side AI / ML model according to one embodiment.

[0026] FIG. 12 is a diagram illustrating the use of an AI / ML model in a beam management environment according to one embodiment.

[0027] FIG. 13 is a diagram for explaining an operation of generating beam prediction result information using an AI / ML model according to one embodiment.

[0028] Fig. 14 is a drawing for explaining terminal operation according to one embodiment.

[0029] Fig. 15 is a diagram for explaining base station operation according to one embodiment.

[0030] FIG. 16 is a signal diagram for explaining a model performance evaluation operation between a terminal and a base station according to one embodiment.

[0031] Fig. 17 is a drawing showing a terminal configuration according to one embodiment.

[0032] Fig. 18 is a diagram showing a base station configuration according to one embodiment.

[0033] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to exemplary drawings. When adding reference numerals to components in each drawing, identical components may have the same numerals as much as possible even if they are shown in different drawings. In addition, when describing the present embodiments, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the technical idea of ​​the present invention, the detailed description may be omitted. When "includes," "has," "consists of," etc. are used in this specification, other parts may be added unless "only" is used. When a component is expressed in the singular, it may include a case in which the plural is included unless specifically stated otherwise.

[0034] Additionally, terms such as first, second, A, B, (a), (b), etc. may be used to describe components of the present disclosure. These terms are only intended to distinguish the components from other components, and the nature, order, sequence, or number of the components are not limited by the terms.

[0035] In a description of the positional relationship of components, when it is described that two or more components are "connected," "combined," or "connected," it should be understood that the two or more components may be directly "connected," "combined," or "connected," but that the two or more components may also be further "interposed" with another component to be "connected," "combined," or "connected." Here, the other component may be included in one or more of the two or more components that are "connected," "combined," or "connected" to each other.

[0036] In the description of the temporal flow relationship related to components, operation methods, or manufacturing methods, for example, when the temporal or flow relationship is described as “after”, “following”, “next to”, “before”, etc., it may also include cases where it is not continuous, unless “immediately” or “directly” is used.

[0037] Meanwhile, when numerical values ​​or corresponding information (e.g., levels, etc.) for components are mentioned, even without separate explicit description, the numerical values ​​or corresponding information may be interpreted as including an error range that may occur due to various factors (e.g., process factors, internal or external impact, noise, etc.).

[0038] The wireless communication system in this specification refers to a system for providing various communication services such as voice, data packets, etc. using wireless resources, and may include a terminal, a base station, or a core network.

[0039] The embodiments disclosed below can be applied to wireless communication systems using various wireless access technologies. For example, the embodiments can 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). In addition, the wireless access technology may not only refer to a specific access technology, but also to each generation of communication technologies established by various communication agreement organizations such as 3GPP, 3GPP2, WiFi, Bluetooth, IEEE, and ITU. For example, CDMA can be implemented with wireless technologies such as UTRA (universal terrestrial radio access) or CDMA2000. TDMA can be implemented with wireless technologies such as GSM (global system for mobile communications) / GPRS (general packet radio service) / EDGE (enhanced data rates for GSM evolution). OFDMA can be implemented in wireless technologies such as IEEE (Institute of Electrical and Electronics 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. Thus, the present embodiments can be applied to currently disclosed or commercialized wireless access technologies, as well as wireless access technologies currently under development or to be developed in the future.

[0040] Meanwhile, the term "terminal" in this specification is a comprehensive concept meaning a device including a wireless communication module that performs communication with a base station in a wireless communication system, and should be interpreted as a concept that includes not only UE (User Equipment) in WCDMA, LTE, NR, HSPA, and IMT-2020 / IMT-2030 (5G, New Radio, and 6G), but also MS (Mobile Station), UT (User Terminal), SS (Subscriber Station), and wireless device in GSM. In addition, the terminal may be a user portable device such as a smartphone depending on the usage type, and in a V2X communication system, it may mean a vehicle, a device including a wireless communication module in the vehicle, etc. In addition, in the case of a Machine Type Communication system, it may include an MTC terminal, an M2M terminal, a URLLC terminal, etc. equipped with a communication module to perform machine type communication.

[0041] The base station or cell in this specification refers to an end that communicates with a terminal in terms of a network, and includes 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., Transmission Point, Reception Point, Transmission / Reception Point), Relay Node, Mega Cell, Macro Cell, Micro Cell, Pico Cell, Femto Cell, RRH (Remote Radio Head), RU (Radio Unit), and Small Cell. In addition, a cell may mean including a BWP (Bandwidth Part) in the frequency domain. For example, a serving cell may mean an Activation BWP of a terminal.

[0042] Since the various cells listed above have a base station that controls one or more cells, the base station can be interpreted in two meanings. 1) It can be a 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 can indicate the wireless area itself. In 1), all devices that provide a given wireless area are controlled by the same entity or that interact to cooperatively configure the wireless area are all indicated as a base station. Depending on how the wireless area is configured, a point, a transceiver point, a transmission point, a reception point, etc. can be an embodiment of a base station. In 2), the wireless area itself that receives or transmits a signal from the perspective of a user terminal or a neighboring base station can also be indicated as a base station.

[0043] In this specification, a cell may mean a component carrier having coverage of a signal transmitted from a transmission / reception point or a transmission / reception point itself.

[0044] Uplink (UL, or uplink) refers to a method of transmitting and receiving data from a terminal to a base station, and downlink (DL, or downlink) refers to a 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 / reception points to a terminal, and uplink may refer to communication or a communication path from a terminal to multiple transmission / reception points. In this case, in the downlink, the transmitter may be part of the multiple transmission / reception points, and the receiver may be part of the terminal. In addition, in the uplink, the transmitter may be part of the terminal, and the receiver may be part of the multiple transmission / reception points.

[0045] 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).

[0046] Hereinafter, the present disclosure describes an NR system as an example, but it will be apparent that the present disclosure can be applied and used to the corresponding functions of a 6G mobile communication network, and the limitations of the present disclosure are not limited by the NR system. This is because, although NR (New Radio) is used as a specific embodiment, it is stated that the technical idea of ​​the present disclosure can be generalized to future systems such as 6G, and is characterized by not being limited to a specific system (NR). Accordingly, the technical scope of the invention is characterized by not being limited to the NR system, but can be implemented in various wireless systems including 6G.

[0047] 6G communication, to which this disclosure applies, is the next-generation wireless communication technology after 5G, and its standardization is underway with the goal of commercialization around 2030. 6G goes beyond simple speed improvement and aims for artificial intelligence, hyper-spatial scalability, and real-digital convergence, and is being prepared with the goal of becoming the core infrastructure of the future digital society. 6G communication organically combines core technologies such as THz communication capable of ultra-wideband transmission, AI-Native network that integrates AI / ML into all layers of the network, RIS (Reconfigurable Intelligent Surface) technology that actively reflects and manipulates radio waves, NTN (Non-Terrestrial Network) that provides 3D coverage such as satellites, Joint Communication & Sensing (JCAS) that integrates communication and sensing functions, ultra-precision positioning, and quantum key cryptography (QKD) for security to support the next-generation digital society.

[0048] This 6G communication network architecture is being discussed with a focus on the following directions and characteristics. First, as an end-to-end intelligent autonomous network (AI-Native Architecture) architecture, AI / ML is fundamentally embedded in all layers of the network to perform data-based policy optimization, network autonomous operation, anomaly detection, and quality of service (QoS / QoE) assurance, and it is expected that AI functions will be distributed and operated in RAN, Core, and service management. Second, it will adopt a 3D extended architecture to support a Non-Terrestrial Network (NTN) that integrates the terrestrial network (RAN), satellite, and high-altitude aerial platforms (HAPS). For this, an integrated cell structure and IAB-based backhaul / fronthaul design will be supported. Third, the Service-Based Architecture (SBA) introduced in 5G will be enhanced to strengthen the modularization of network functions (NF) and enable flexible API-based service creation through NEF, NWDAF, and PCF. Fourth, through a distributed intelligence structure, we plan to move away from a centralized structure and perform real-time AI-based judgment at edge nodes such as RAN, MEC, and UE, and support local decision-making in smart transportation, factories, and medical sites. Fifth, we plan to introduce a structure that integrates communication and sensing (Joint Communication & Sensing) so that RAN can perform environmental sensing functions beyond simple communication functions, and a sensing feature processing and asynchronous collection structure for this will also be designed. Finally, through a digital twin-based virtualization structure, we plan to support the intelligence and efficiency of the entire network by replicating the physical network status in real time and enabling predictive autonomous operation and network simulation.The next-generation wireless system to which this disclosure applies includes support for both sub-6 GHz frequency bands (FR1, Frequency Range 1) and 6 GHz or higher frequency bands (FR2, Frequency Range 2), and in particular, newly defines support for FR3 (Frequency Range 3) between FR1 and FR2, and proposes various support technologies related to end-to-end interoperability and data connectivity targeting the FR3 band (7.125-24.25 GHz).

[0049] For example, NR defines various operating scenarios by adding considerations for satellites, automobiles, and new verticals, and supports the eMBB (Enhanced Mobile Broadband) scenario in terms of services, the mMTC (Massive Machine Communication) scenario that has high terminal density but is deployed over a wide area and requires low data rates and asynchronous access, and the URLLC (Ultra Reliability and Low Latency) scenario that requires high responsiveness and reliability and can support high-speed mobility.

[0050] To meet these scenarios, NR introduces a wireless communication system that incorporates new waveform and frame structure technologies, low latency technologies, support for ultra-high frequency bands (mmWave), and forward compatibility technologies. In particular, NR systems offer various technological changes in terms of flexibility to ensure forward compatibility. The key technical features of NR are described below with reference to the drawings.

[0051] Figure 1 is a schematic diagram illustrating the structure of an NR system to which the present embodiment can be applied.

[0052] Referring to Fig. 1, the NR system is divided into 5GC (5G Core Network) and NR-RAN parts, and the NG-RAN is composed of gNBs and ng-eNBs that provide user plane (SDAP / PDCP / RLC / MAC / PHY) and control plane (RRC) protocol termination for UE (User Equipment). gNBs or gNBs and ng-eNBs are interconnected via the Xn interface. gNBs and ng-eNBs are each connected to the 5GC via the NG interface. The 5GC can be configured to include an AMF (Access and Mobility Management Function) that is responsible for the control plane such as terminal access and mobility control functions, and an UPF (User Plane Function) that is responsible for the control function for user data. NR includes support for both frequency bands below 6 GHz (FR1, Frequency Range 1) and frequency bands above 6 GHz (FR2, Frequency Range 2). In addition, the next-generation wireless communication system after 5G according to the present disclosure can support various technologies related to end-to-end interoperability and data connection targeting the FR3 band (7.125-24.25 GHz).

[0053] gNB refers to a base station that provides NR user plane and control plane protocol termination to terminals, and ng-eNB refers to a base station that provides E-UTRA user plane and control plane protocol termination to terminals. The base station described in this specification should be understood to encompass both gNB and ng-eNB, and may also be used to refer to gNB or ng-eNB separately as needed.

[0054] NR uses the CP-OFDM waveform with a cyclic prefix for downlink transmission, and CP-OFDM or DFT-s-OFDM for uplink transmission. OFDM technology is easily combined with MIMO (Multiple Input Multiple Output) and offers the advantages of high spectral efficiency and low-complexity receivers.

[0055] Meanwhile, in NR, requirements for data rates, latency, and coverage vary across scenarios. Therefore, it is necessary to efficiently satisfy these requirements across the frequency bands that comprise a given NR system. To achieve this, technologies are applied to efficiently multiplex radio resources based on multiple different numerologies.

[0056] Specifically, the NR transmission numerator is determined based on the sub-carrier spacing and CP (Cyclic prefix), and is changed exponentially using the μ value as an exponent value of 2 based on 15 kHz, as shown in Table 1 below.

[0057] μsubcarrier intervalCyclic prefixSupported for dataSupported for synch015NormalYesYes130NormalYesYes260Normal, ExtendedYesNo3120NormalYesYes4240NormalNoYes

[0058] As shown in Table 1 above, the numerology of NR can be divided into five types according to the subcarrier spacing. Specifically, the subcarrier spacing used for data transmission in NR is 15, 30, 60, and 120 kHz, and the subcarrier spacing used for synchronization signal transmission is 15, 30, 12, and 240 kHz. In addition, the extended CP is applied only to the 60 kHz subcarrier spacing. Meanwhile, the frame structure in NR is defined as a frame with a length of 10 ms, which is composed of 10 subframes with the same length of 1 ms. One frame can be divided into half frames of 5 ms, and each half frame contains 5 subframes. In the case of a 15 kHz subcarrier spacing, one subframe consists of 1 slot, and each slot consists of 14 OFDM symbols. FIG. 2 is a drawing for explaining a frame structure in an NR system to which the present embodiment can be applied.

[0059] Referring to FIG. 2, a slot is fixedly composed of 14 OFDM symbols in the case of a normal CP, but the length of the slot in the time domain may vary depending on the subcarrier spacing. For example, in the case of a numerology with a 15 kHz subcarrier spacing, a slot is composed of 1 ms in length, which is the same length as a subframe. In contrast, in the case of a numerology with a 30 kHz subcarrier spacing, a slot is composed of 14 OFDM symbols, but two slots may be included in one subframe with a length of 0.5 ms. In other words, a subframe and a frame are defined with a fixed time length, and a slot is defined by the number of symbols, so the time length may vary depending on the subcarrier spacing.

[0060] Furthermore, the basic unit of scheduling is defined as a slot, and mini-slots (or sub-slots, or non-slot-based scheduling) are also introduced to reduce transmission delay in the wireless section. This offers the advantage of reducing transmission delay in the wireless section, as the length of a single slot is inversely shortened by using a wide subcarrier spacing. These mini-slots (or sub-slots) are designed to efficiently support URLLC scenarios and allow scheduling in units of 2, 4, or 7 symbols.

[0061] Additionally, NR defines uplink and downlink resource allocation at the symbol level within a single slot. To reduce HARQ delay, a slot structure is defined that allows HARQ ACK / NACK transmission within a transmission slot. This slot structure is defined as a self-contained structure.

[0062] NR is designed to support a total of 256 slot formats and supports a common frame structure that configures FDD or TDD frames through various combinations of slots. For example, it can support a slot structure in which all symbols in a slot are set to downlink, a slot structure in which all symbols are set to uplink, and a slot structure in which downlink and uplink symbols are combined. In addition, NR supports data transmission being distributed and scheduled across one or more slots. Therefore, a base station can use a slot format indicator (SFI) to inform a UE whether a slot is a downlink slot, an uplink slot, or a flexible slot. The base station can indicate the slot format by indicating an index of a table configured through UE-specific RRC signaling using the SFI, and can also indicate it dynamically through DCI (Downlink Control Information) or statically or semi-statically through RRC.

[0063] In relation to physical resources in NR, antenna ports, resource grids, resource elements, resource blocks, and bandwidth parts are considered.

[0064] Antenna ports are defined such that the channel through which a symbol on an antenna port is carried can be inferred from the channel through which another symbol on the same antenna port is carried. Two antenna ports are said to be quasi co-located (QC / QCL) if the large-scale properties of the channel through which a symbol on one antenna port is carried can be inferred from the channel through which a symbol on the other antenna port is carried. Here, the large-scale properties include one or more of delay spread, Doppler spread, frequency shift, average received power, and received timing.

[0065] FIG. 3 is a diagram for explaining a resource grid supported by a wireless access technology to which the present embodiment can be applied.

[0066] Referring to Figure 3, since the Resource Grid supports multiple numerals on the same carrier, a resource grid may exist for each numeral. Furthermore, resource grids may exist based on antenna ports, subcarrier spacing, and transmission direction.

[0067] For example, a resource block consists of 12 subcarriers and is defined only in the frequency domain. Furthermore, a resource element consists of one OFDM symbol and one subcarrier. Therefore, as shown in Figure 3, the size of a resource block can vary depending on the subcarrier spacing. NR also defines "Point A," which serves as a common reference point for the resource block grid, as well as common resource blocks and virtual resource blocks.

[0068] FIG. 4 is a diagram for explaining a bandwidth part supported by a wireless access technology to which the present embodiment can be applied.

[0069] In NR, the carrier bandwidth is fixed at 20 MHz, and the maximum carrier bandwidth can be set from 50 MHz to 400 MHz for each subcarrier interval. Here, it is not assumed that all terminals use the entire carrier bandwidth. Therefore, in NR, as illustrated in Figure 4, a bandwidth part (BWP) can be designated within the carrier bandwidth and instructed to be used by the terminal. In addition, a bandwidth part is associated with a single numerology, consists of a subset of consecutive common resource blocks, and can be dynamically activated over time. For example, a terminal is configured with up to four bandwidth parts each for uplink and downlink, and supports data transmission and reception using the bandwidth part activated at a given time.

[0070] Meanwhile, in the case of a paired spectrum, the uplink and downlink bandwidth parts are set independently, and in the case of an unpaired spectrum, the downlink and uplink bandwidth parts are set in pairs so that they can share a center frequency to prevent unnecessary frequency re-tuning between downlink and uplink operations.

[0071] Additionally, in NR, a terminal performs cell search and random access procedures to connect to a base station and perform communication.

[0072] Cell search is a procedure in which a terminal synchronizes to the cell of a corresponding base station, obtains a physical layer cell ID, and obtains system information using a synchronization signal block (SSB) transmitted by the base station.

[0073] FIG. 5 is a diagram illustrating an example of a synchronization signal block in a wireless access technology to which the present embodiment can be applied.

[0074] Referring to FIG. 5, SSB is composed of a primary synchronization signal (PSS) and a secondary synchronization signal (SSS), each occupying one symbol and 127 subcarriers, and a PBCH spanning three OFDM symbols and 240 subcarriers.

[0075] The terminal receives SSB by monitoring SSB in the time and frequency domain.

[0076] SSB can be transmitted up to 64 times in 5ms. Multiple SSBs are transmitted in different transmission beams within 5ms, and the terminal performs detection assuming that SSBs are transmitted every 20ms based on a specific beam used for transmission. The number of beams that can be used for SSB transmission within 5ms can increase as the frequency band increases. For example, up to 4 SSB beams can be transmitted below 3GHz, up to 8 in the frequency band between 3GHz and 6GHz, and up to 64 different beams can be used for SSB transmission in the frequency band above 6GHz.

[0077] SSB contains two symbols in one slot, and the starting symbol and number of repetitions within the slot are determined as follows depending on the subcarrier spacing.

[0078] Meanwhile, SSB can be transmitted at the center frequency of the carrier bandwidth, or can be transmitted at a location other than the center of the system bandwidth, and multiple SSBs can be transmitted in the frequency domain when supporting wideband operation. Accordingly, the terminal monitors SSB using the synchronization raster, which is a candidate frequency location for monitoring SSB. The carrier raster, which is the center frequency location information of the channel for initial access, and the synchronization raster are newly defined in NR. The synchronization raster is set with a wider frequency interval than the carrier raster, which can support the terminal's fast SSB search.

[0079] A UE can obtain the MIB through the PBCH of the SSB. The MIB (Master Information Block) includes the minimum information required for the UE to receive the remaining system information (RMSI, Remaining Minimum System Information) broadcast by the network. In addition, the PBCH may include information on the position of the first DM-RS symbol in the time domain, information for the UE to monitor SIB1 (e.g., SIB1 numerology information, information related to SIB1 CORESET, search space information, PDCCH-related parameter information, etc.), offset information between the common resource block and the SSB (the absolute position of the SSB within the carrier is transmitted through SIB1), etc. Here, the SIB1 numerology information is also applied equally to some messages used in the random access procedure for the UE to access the base station after completing the cell search procedure. For example, the numerology information of SIB1 may be applied to at least one of messages 1 to 4 for the random access procedure.

[0080] The aforementioned RMSI may refer to SIB1 (System Information Block 1), and SIB1 is broadcast periodically (e.g., every 160 ms) in the cell. SIB1 contains information necessary for the UE to perform the initial random access procedure and is periodically transmitted via PDSCH. In order for the UE to receive SIB1, it must receive numerology information used for SIB1 transmission and CORESET (Control Resource Set) information used for SIB1 scheduling via PBCH. The UE checks scheduling information for SIB1 using SI-RNTI in CORESET and acquires SIB1 on PDSCH according to the scheduling information. The remaining SIBs, excluding SIB1, may be transmitted periodically or upon request of the UE.

[0081] FIG. 6 is a diagram for explaining a random access procedure in a wireless access technology to which the present embodiment can be applied.

[0082] Referring to FIG. 6, once cell search is complete, the terminal transmits a random access preamble for random access to the base station. The random access preamble is transmitted via the PRACH. Specifically, the random access preamble is transmitted to the base station via the PRACH, which consists of consecutive radio resources in a specific slot that is periodically repeated. Generally, when a terminal initially accesses 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.

[0083] 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 one random access response may include random access response information for one or more terminals, the random access preamble identifier may be included to indicate to which terminal the included UL Grant, temporary C-RNTI, and TAC are valid. 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 adjust uplink synchronization. The random access response may be indicated by a random access identifier on the PDCCH, i.e., a RA-RNTI (Random Access - Radio Network Temporary Identifier).

[0084] Upon receiving a valid random access response, the terminal processes the information contained in the random access response and performs scheduled transmission to the base station. For example, the terminal applies TAC and stores a temporary C-RNTI. Furthermore, using the UL Grant, the terminal transmits data stored in its buffer or newly generated data to the base station. In this case, information that identifies the terminal must be included.

[0085] Finally, the terminal receives a downlink message for contention resolution.

[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), and TPC (Transmit Power Control) information.

[0087] Additionally, to ensure system flexibility, the CORESET concept is introduced. CORESET (Control Resource Set) represents time-frequency resources for downlink control signals. A terminal can decode control channel candidates using one or more search spaces within the CORESET time-frequency resources. Quasi-CoLocation (QCL) assumptions are established for each CORESET, which are used to inform characteristics of analog beam direction in addition to delay spread, Doppler spread, Doppler shift, and average delay.

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

[0089] Referring to Figure 7, a CORESET can exist in various forms within the carrier bandwidth within a single slot, and in the time domain, a CORESET can consist of up to three OFDM symbols. In addition, a CORESET is defined as a multiple of six resource blocks up to the carrier bandwidth in the frequency domain.

[0090] The first CORESET is indicated via the MIB as part of the initial bandwidth part configuration, allowing the terminal to receive additional configuration and system information from the network. After establishing a connection with the base station, the terminal can receive and configure one or more CORESET information via RRC signaling.

[0091] In this specification, the terms frequency, frame, subframe, resource, resource block, region, band, subband, control channel, data channel, synchronization signal, various reference signals, various signals or various messages related to NR include the meanings used in existing communication systems, and may be applied as concepts that are expanded, changed or added in consideration of newly defined terms in next-generation systems, thereby including the possibility of being interpreted in various meanings.

[0092] As described, communication systems are evolving and developing diverse technologies to support 6G beyond 5G through diverse research and application of next-generation wireless access technologies. To this end, research is being conducted on technologies to support large-scale access, communication in high-frequency bands, and faster, more seamless services. Technologies such as MIMO, which perform beamforming to target specific regions, directions, or terminals, are also being supported to provide more efficient data transmission and reception.

[0093] Furthermore, with the recent increase in terminal mobility, beamforming technology requires various measures to prevent the reduction of terminal service areas and provide uninterrupted services. In other words, there is a need to predict the quality of beams provided to terminals. To this end, AI technology can be applied and utilized in various forms for beam quality prediction. For example, beam quality prediction can include spatial prediction, temporal prediction, etc., and communication services can be provided by proactively providing better-quality beams to terminals based on the beam quality prediction results.

[0094] To this end, the present disclosure proposes a method for providing communication services using various artificial intelligence models, and in particular, proposes a method and device for managing artificial intelligence models to improve service efficiency. Considering that the artificial intelligence model utilizes training data, i.e., considering the potential deterioration of prediction performance due to terminal movement or changes in channel conditions, the present disclosure performs appropriate monitoring and control operations for prediction performance, thereby supporting more effective use of the artificial intelligence model.

[0095]

[0096] FIG. 8 is a diagram illustrating the structure of a functional framework for Intelligence according to one embodiment of the present disclosure.

[0097] Referring to Figure 8, to apply an AI model to a communication service, data collection is first performed. The collected data serves as training data during the model training process. For AI models, training is performed using the training data, and the trained model is deployed / updated on the network or terminal.

[0098] Meanwhile, the collected data can also be used for inference in a trained model. When inference data is input, the AI ​​model generates output based on pre-trained information. For example, the output can be configured in various ways based on the training data, such as quality information for spatially predicted beams, quality information for temporally predicted beams, or information for predicting terminal locations.

[0099] AI models can degrade over time or due to environmental changes. Therefore, retraining may be performed based on performance feedback from the AI ​​model.

[0100] The output information of the AI ​​model can be fed back to the actor and collected as data. This data can then be reused as model training or inference data, allowing the aforementioned lifecycle management operations to operate cyclically. This overall operation can be described as a beam management operation.

[0101] Meanwhile, AI / ML capabilities vary depending on specific use cases and sub-use cases, and may focus on the interaction between the network and UE.

[0102] For example, collaboration levels between the network and the UE can be defined as follows.

[0103] 1. Level 0: No collaboration

[0104] 2. Level 1: Signaling-based collaboration without model transfer

[0105] 3. Level 2: Signaling-based collaboration with model transfer

[0106] The technology described in this specification can be applied to at least one of the three collaboration levels described above. Below, we will describe more diverse examples of using AI models for communication.

[0107] A beam management method according to an example of the present disclosure can be divided into an initial access phase and a post-cell connection establishment phase. A terminal performing initial access sets its initial transmit / receive (Tx / Rx) beam through a RACH procedure. In order to provide base station transmit beam settings to a terminal without cell connection, the base station periodically and repeatedly transmits SSBs to which beams in different directions are mapped. The terminal can select an optimal SSB through signal measurement for the periodically transmitted SSBs and transmit a PRACH preamble mapped to the corresponding SSB, thereby informing the base station of information about the selected transmit beam.

[0108] A terminal performing an initial access procedure receives cell-related parameter information, such as PRACH information corresponding to each SSB required in the initial access phase, via a system information message. The terminal measures RSRP for periodically transmitted SSBs. The terminal inputs beam information for the measured SSBs as input values ​​for an AI / ML model, and calculates predicted beam strengths or RSRP values ​​for all beams of the SSB as output values ​​for the input values. The terminal selects an SSB with the highest value among the calculated values, and can notify the base station of the selected predicted beam information by transmitting a preamble belonging to the PRACH resource corresponding to the selected SSB to the base station.

[0109] A base station that does not know the beam information of the first terminal entering the network can set up to 64 beams for a terminal that has not yet connected. The terminal sequentially measures all beams to find the optimal beam for its location. This not only causes delays in beam selection and cell connection as the number of beams within the cell increases, but can also increase the terminal's power consumption by requiring the terminal to measure a large number of beams.

[0110] To address the above issues, the base station can apply a wide beam for SSB to determine the approximate location / beam of the initially connected terminal, and then configure a narrow beam after the terminal accesses the cell. However, while narrow beams provide high data rates to the terminal, they are sensitive to the terminal's movement or environmental changes, which can easily lead to disconnection. Therefore, the base station assigns the terminal a CSI resource with a candidate beam mapped to it, allowing the terminal to continuously measure the surrounding beam strength and report the measurement results to the base station.

[0111] A UE configured for beam reporting performs CSI reporting by measuring its assigned reference signal. However, this method can lead to a problem in that as the number of UEs in a cell increases, the number of reference signal resources allocated to each UE also increases rapidly. To mitigate this resource overhead, the base station can allocate the same candidate beam (CSI resource) to UEs in similar locations. However, when UEs with different mobility share the same resource, the issue of assigning new candidate beam resources to UEs that leave the resource area arises. If a minimum number of candidate beams is allocated to a UE with high mobility to reduce resource overhead, the UE will experience frequent RRC reconfigurations. This reconfiguration of candidate beams through RRC incurs relatively large delays, which can lead to beam dropouts. The base station can mitigate this by appropriately increasing the number of beams, but this increased number of beams can increase the measurement burden on the UE.

[0112] To improve the delay and terminal power consumption in such beam search, AI / ML models can be applied. For AI / ML-based beam management, BM-Case1 and BM-Case2 are supported for characterization and basic performance evaluation. Here, BM-Case1 performs spatial domain downlink beam prediction for beam set A based on the measurement results of beam set B. BM-Case2 performs temporal DL beam prediction for beam set A based on the historical measurement results of beam set B. In one example, for BM-Case1 and BM-Case2, the beams of sets A and B may be in the same frequency range.

[0113] For BM-Case2, the measurement results of the K (K>=1) most recent measurement instances are used as inputs to the AI / ML model. For BM-Case2, the output of the AI / ML model should be F predictions for F future time instances, and each prediction can be composed for each time instance.

[0114] Set B is a subset of Set A, and among the beams in Set A, Set B can be determined according to a predetermined fixed pattern or a random pattern. Alternatively, Set A and Set B can be different from each other, for example, Set A can be composed of narrow beams and Set B can be composed of wide beams. Here, Set A can be used for DL ​​beam prediction and Set B can be used for DL ​​beam measurement.

[0115] With respect to BM-Case1, the AI / ML input may be, for example, only L1-RSRP measurements based on Set B. Alternatively, L1-RSRP measurements based on Set B and assistance information may be used. The assistance information may include transmit and / or receive beam shape information, such as transmit and / or receive beam patterns, transmit and / or receive beam directions (azimuth and elevation), 3dB beamwidths, etc., or beam angles of expected transmit and / or receive beams for prediction, transmit and / or receive beam IDs for prediction, terminal location information, terminal direction information, etc. Alternatively, CIR based on Set B or L1-RSRP measurements based on Set B and the corresponding DL transmit and / or receive beam IDs may be used as input.

[0116] The goal of AI / ML-based BM (beam management) technology is to reduce measurement overhead and latency by optimizing the beam prediction process in the spatial / temporal domains for data transmission. Here, the AI / ML model needs to be trained before the beam prediction process. Two types of beam sets (Set A, Set B) are utilized in the training process. Set A is a set of beams for which prediction is targeted, and Set B is a set of beams used for measurement. BM-case 1 performs downlink TX beam prediction for Set A in the spatial domain based on the measurement results of Set B beams. BM-case 2 performs downlink TX beam prediction for Set A in the temporal domain based on the past measurement results of Set B beams.

[0117] FIG. 9 is a diagram for explaining a beam management operation using an AI / ML model according to one embodiment.

[0118] Referring to Figure 9, when using an AI / ML model, Set A data and Set B data can be defined separately. For example, the correlation between Set A and Set B used for channel status reporting is described.

[0119] When an AI / ML model is configured in a terminal (901), the terminal (901) transmits a training request to the base station (900) for training the AI / ML model (S910).

[0120] The base station (900) sweeps and transmits a beam configured as Set B for training the AI / ML model of the terminal (901) (S920). For example, CSI-reportConfig#1 corresponds to Set B configured with 16 beams. Here, the transmitted beam may be a reference signal such as CSI-RS or SSB. Set B is a beam set configured to report the channel status measured by the terminal (901) back to the base station (900). The base station (900) transmits an instruction to the terminal (901) to collect channel information by measuring the beam of Set B using a beam sweeping method.

[0121] The terminal (901) measures RSRP for 16 beams and inputs the measured data as model input data (S930). The AI / ML model can output an ID for the predicted best beam using the RSRP input data for the 16 input beams (S950). Alternatively, the AI / ML model can output predicted RSRP values ​​for K beams. K can be set as a high-quality beam based on the predicted RSRP values.

[0122] The base station (900) can sweep multiple beams assigned to Set A and transmit them to the terminal (S940). For example, CSI-reportConfig#2 corresponds to Set A, which consists of 64 beams. It is connected to CSI-reportConfig#1, and data collected from Set B is used in relation to Set A for AI training purposes.

[0123] As described above, when the terminal (901) uses the RSRP measurements of Set B as input data for the AI ​​model, the best beam ID identified in Set A serves as a label for the training data. Basically, the AI / ML model uses the measured signal quality of Set B to predict the optimal beam in a larger Set (Set A). This operation is the training process of the AI / ML model.

[0124] In summary, the terminal (901) measures the actual RSRP for the 16 beams of CSI-reportConfig#1 transmitted by the base station (901) and inputs the measured values ​​as input data for the AI / ML model. The AI / ML model extracts the optimal beam for the 64 beams set by CSI-reportConfig#2, not the 16 beams, and provides it as output. In other words, the AI / ML model can predict the quality of the 64 beams based on the quality of the 16 beams and select the beam showing the highest quality.

[0125] The terminal (901) can also measure the actual RSRP values ​​for the 64 beams according to CSI-reportConfig #2 actually transmitted by the base station (900) to verify whether they match the results predicted by the AI / ML model. By repeating the verification operation, the training process of the AI / ML model can be strengthened.

[0126] Here, 16 beams and 64 beams are exemplary, and the operation of training spatial prediction based on BM-Case 1 is described. Similar operation can be applied to BM-Case 2. 16 beams are transmitted, and the AI / ML model can then predict the quality of RSRP beams at a specific future time instance. In that specific future time instance, the base station actually transmits 16 beams or more, and the terminal actually measures them and compares them with the predicted results to proceed with training.

[0127]

[0128] AI / ML-based beam management models are classified into UE-side models and NW-side models depending on the entity performing model training and inference.

[0129] FIG. 10 is a diagram for explaining a beam prediction operation using a UE-side AI / ML model according to one embodiment.

[0130] Referring to FIG. 10, in step 1000, a terminal transmits information related to training of an AI / ML model configured on the terminal to the network, and the network provides the information through beam sweeping, thereby performing an AI / ML model training operation. The training operation may be performed using the process of FIG. 9 described above.

[0131] Once the AI / ML model training is complete, the terminal transmits inference-related information to the network through process 1010, and the network can actually transmit beams #1 and #3. In other words, inference is performed through beams not transmitted through the AI / ML model. The terminal can measure beams #1 and #3 and input the measurement results as input to the AI / ML model to generate output.

[0132] In step 1020, the inference results can be shared with the base station. The terminal can report the top K beams to the network using the output of the AI / ML model. For example, if beams #1 and #4 are predicted to be of high quality based on the output of the AI / ML model, the network can perform sweeping on those beams.

[0133] The terminal actually measures beams #1 and #4, performs beam reporting, and finally performs beam pairing between the terminal and the network through beam #4.

[0134] When an AI / ML model is configured on the terminal side, training, inference, and beam pairing using the inference results can be performed through the above operations.

[0135] FIG. 11 is a diagram for explaining a beam prediction operation using a NW-side AI / ML model according to one embodiment.

[0136] Referring to Figure 11, when an AI / ML model is configured on the network side, training and inference operations are performed on the network. At step 1100, the network transmits various beams to the terminal through beam sweeping. The terminal performs measurements for each beam and reports the results to the network. The network trains the AI / ML model using beam sweeping information and information reported by the terminal.

[0137] Once training is complete, in step 1110, the network performs beam sweeping on the terminal using some beams, for example, beams #1 and #3. The terminal performs measurements on the swept beams #1 and #3 and transmits the measurement results as beam reports. The network then uses the measurement results for beams #1 and #3 to input them into an AI / ML model, thereby inferring the K beams with the best channel quality.

[0138] For example, if beams #1 and #4 are inferred to have high channel quality, the network sweeps beams #1 and #4 and transmits them to the terminal during process 1120. The terminal measures them and then performs a beam report for beam #4, which is measured to have better channel quality among beams #1 and #4. Thereafter, the network and the terminal perform beam pairing using beam #4 to communicate.

[0139] That is, only beams #1 and #3 are transmitted to the terminal, and the remaining beams are inferred through the AI / ML model to select the optimal beam #4 and perform beam pairing.

[0140] As mentioned above, beam inference can be performed in the same manner not only spatially but also temporally.

[0141] Meanwhile, as training and inference operations for AI / ML models progress, monitoring of the AI / ML model is also necessary. Continuous monitoring of the AI / ML model can detect model degradation due to environmental changes or changes in the terminal's location. Alternatively, the need for model updates, model usability, and accuracy can be assessed.

[0142] Additionally, UE / NW-side AI / ML models can undergo lifecycle management (LCM) after training, which determines whether to use the model (either in the BM process or for AI / ML model retraining) through a performance monitoring process. Performance monitoring can be performed by comparing the AI / ML model's inference results against the received beam ID using pre-configured performance metrics.

[0143] FIG. 12 is a diagram illustrating the use of an AI / ML model in a beam management environment according to one embodiment.

[0144] Referring to Figure 12, performance monitoring is performed using KPIs related to beam prediction accuracy (e.g., Beam ID report), KPIs related to link quality (e.g., L1-RSRP, L1-SINR, hypothetical BLER), metrics based on the input / output data distribution of the AI / ML model, and the difference between measured data and predicted data (e.g., difference between measured L1-RSRP and predicted beam's L1-RSRP).

[0145] For example, a terminal can be trained and inference can be performed on a specific environment within a specific cell. Therefore, the area where real-time monitoring results are valid can be set to a specific area within the cell.

[0146] Networks or terminals can monitor the inference accuracy of AI / ML models periodically or based on specific events. The monitoring results can be used to determine whether to activate the AI / ML model. Alternatively, they can be used to determine the duration of use of the AI / ML model.

[0147] For example, monitoring can be performed at a specific point in time, and if the model's estimated inference accuracy exceeds a threshold, the model can be activated. Furthermore, the model can be used to perform inference operations during the time interval between monitoring cycles. If monitoring periods are determined periodically, monitoring operations for the AI / ML model can be performed again once the monitoring interval is completed.

[0148] Therefore, monitoring operations for AI / ML models are highly important in terms of communication quality and usability. Below, we describe these monitoring operations for AI / ML models in more detail.

[0149] FIG. 13 is a diagram for explaining an operation of generating beam prediction result information using an AI / ML model according to one embodiment.

[0150] Referring to Figure 13, beams from Set B can be used as input for AI / ML models. For models that perform spatial prediction (BM-Case 1), actual measurement results for wide beams or some beams can be used as input. For models that perform temporal prediction (BM-Case 2), actual measurement results for beams belonging to past Set B can be used as input.

[0151] The model outputs predicted L1-RSRP values. Depending on the configuration or needs, the output can be predicted L1-RSRP values ​​for all beams, or the output can be the Top-K beams with the highest quality and the predicted L1-RSRP values ​​for those beams.

[0152] Based on the model output, prediction results for the top K beams from among the beams set as Set A can be selected. The selected results can be reported to the base station. If the model is executed at the base station, a separate reporting procedure may not be required.

[0153] As described, for network-based performance monitoring (NW-side Performance Monitoring), a measurement reporting procedure is utilized to collect information from the terminal necessary for evaluating prediction accuracy or model reliability. This procedure can be triggered automatically by the network when it configures the measurement configuration via an RRCReconfiguration message or under specific conditions (Event Trigger). The terminal transmits a MeasurementReport message to the network containing physical layer (L1)-level information, such as RSRP, SSB index, or CSI-RS Resource ID, collected based on the Monitoring Resource Set. This L1 information can be used to indirectly evaluate the operation results of L1-based AI / ML models. In addition, for position-based inference models or beam prediction models, additional performance data can be collected via PosMeasurementResult or AI-MeasurementResult in the NRPPa protocol.

[0154] Alternatively, model monitoring (model evaluation) can be performed using the model's prediction results.

[0155] For example, in the case of terminal-side AI / ML, performance monitoring operations can be performed for BM-Case1 and BM-Case2. For example, to perform NW-side performance monitoring, a report containing information used for performance monitoring can be transmitted to the network. For example, it can be a measurement result derived from a resource set for monitoring (e.g., L1-RSRP and / or RS index). The report can be configured or triggered by the network. For another example, for UE-assisted performance monitoring, the terminal can calculate performance metrics and report the results to the network. In other words, in UE-assisted performance monitoring, the terminal can directly calculate performance metrics based on the error between the predicted results of the AI / ML model and the actual measured values, and then report the results to the network. Reported metrics include prediction error, confidence score, or AI confidence metric (confidenceLevel), which are delivered via User-Control Information (UCI) reports over PUCCH or PUSCH, or AI-ModelMetricsReport and PosQualityIndicator messages in the RRC layer.

[0156] In addition, for BM-Case1 and BM-Case2, the performance monitoring process can be considered by dividing each case into Option1 and Option2. In addition, the BM-Case1 NW-sided model inference report based only on L1-signaling can also be considered. Each scenario can be divided into Option1 and Option2 depending on the inference performance location and monitoring responsibility. For example, in Option1 of BM-Case1, the terminal collects measurements, performs AI / ML model inference on its own, calculates error and confidence metrics, and reports them to the network. On the other hand, in Option2 of BM-Case1, the network transmits the measurement configuration to the terminal, the terminal reports only the measurements, and the network estimates the model performance based on the received data. Furthermore, in Option1 of BM-Case2, the network directly executes the AI / ML model and evaluates its performance using the input values ​​or result data received from the terminal. In particular, in Option 2 of BM-Case2, the network can independently perform model inference and performance evaluation based only on the L1 measurement report without additional inference results from the terminal. In this case, information such as Beam Index and CQI based on PRS or CSI-RS can be utilized.

[0157] For example, in the case of the NW-side model, beam measurement results can be reported via L1 signaling for inference. For example, for the M values ​​configured by the base station, the L1-RSRP values ​​can be reported as the measurement values ​​for the Top M beams that exhibit the highest quality in the measurement results measured by the terminal among the beams of the measurement resource set. If M is the same size as the measurement resource set, the reported information can be the beam index (e.g., CRI / SSBRI) for the largest measured value of L1-RSRP of the measurement resource set, the L1-RSRP value, and the L1-RSRP values ​​for all beams. That is, the terminal can transmit the measurement values ​​and beam index information for the Top M measured beams to the network (base station). In addition, the base station can configure the L1-RSRP and the maximum measured value of L1-RSRP, X, and the corresponding beam information for up to M beams within the X dB interval from M, and can also determine and instruct whether to report the reported number of beams.

[0158] Here, the maximum value of M may be determined based on terminal performance. The M value can be transmitted from the base station to the terminal.

[0159] Below, an embodiment according to the present disclosure is described focusing on terminal and base station operations.

[0160] As mentioned above, the beam management (BM) step using an AI / ML model trains a model based on a specific beam set. This requires assessing the lifecycle management (LCM) of the trained model. LCM encompasses the model management processes, including activation, deactivation, switch, fallback, training, and retraining. The base station can transmit relevant messages to the terminal to conduct performance monitoring, and these messages can be included in the following signaling channels or blocks:

[0161] - DCI (Downlink Control Information) format; transmitted via PDCCH and can trigger specific measurement or reporting actions.

[0162] - SIB (System Information Block); Used to broadcast common measurement configuration or positioning-related assistance data.

[0163] - RRC (Radio Resource Control); for example, the RRCReconfiguration message may include performance measurement configuration (MeasurementConfiguration) or AI-related measurement report configuration.

[0164] Fig. 14 is a drawing for explaining terminal operation according to one embodiment.

[0165] Referring to FIG. 14, a method for a terminal to perform beam management may include a step of receiving configuration information for evaluating a model configured for beam prediction from a base station (S1410).

[0166] For example, configuration information may include transmission resource information for reference signals for model evaluation, and the terminal receives this information and performs measurements necessary for performance evaluation. For example, the reference signal may be a Cell-specific Reference Signal (CSI-RS) or a Synchronization Signal Block (SSB), and the corresponding resource configuration is conveyed via an RRCReconfiguration message.

[0167] Specifically, the transmission period of the reference signal, frequency domain location, time domain offset, and muting pattern can be defined through CSI-ResourceConfig or SSB-ConfigMobility IE. In order to evaluate the performance of the model configured in the terminal, the terminal receives the reference signal from the base station and performs a measurement procedure for evaluating the performance of the AI / ML-based beam prediction model. Therefore, the configuration information for the reference signal transmitted for evaluation may include reporting configuration information for the terminal to report the model performance evaluation result to the base station, and may be configured with, for example, transmission resource information such as the transmission period, transmission frequency resource (e.g., PUCCH, PUSCH), transmission time resource, and reporting method (triggered / event-based or periodic), and the number of beams to be reported (M).

[0168] For another example, the configuration information may include configuration information for the terminal to report evaluation result information to the base station. For example, the configuration information may further include radio resource information required for the terminal to report evaluation result information to the base station, information on the number of beams to be compared (e.g., the number M) required to generate the evaluation result information, and the like.

[0169] A method in which a terminal performs beam management may include a step of receiving a reference signal based on configuration information (S1420).

[0170] For example, the reference signal may be CSI-RS or SSB. Multiple reference signals are set, and may be set as spatially distinct beams or temporally distinct time instances.

[0171] A terminal can receive a reference signal via a radio resource indicated by configuration information. The reference signal is configured for model monitoring and may be identical to or different from the reference signal of Set B for model inference. Furthermore, the reference signal may be configured to have a smaller size than Set A. The reference signal may be configured to have a corresponding relationship with a reference signal belonging to Set A. The corresponding relationship may be indicated to the terminal based on the aforementioned configuration information.

[0172] The method by which the terminal performs beam management may include a step of generating model evaluation result information by comparing beam prediction result information generated using the measurement result for the reference signal and the output of the model (S1430).

[0173] For example, a terminal measures the reception quality of the aforementioned reference signal and generates a measurement result. The measurement result may be a value measured by receiving a reference signal for actual monitoring, for example, an L1-RSRP value.

[0174] Meanwhile, the terminal may have generated predicted beam prediction result information using the model at a previous point in time and reported it to the base station.

[0175] For example, the beam prediction result information may include information on K beams having high RSRP values ​​among the RSRP values ​​for each beam calculated using the model output. The terminal may measure the beams of Set B and transmit to the base station information on K beams predicted to have good channel quality based on the K value configured by the base station, including the beam prediction result information. The K value is set to a natural number and may be set by the base station.

[0176] The terminal may include identification information of the top K beams in the beam prediction result information. Alternatively, the terminal may include identification information of the top K beams and at least one of the RSRP values ​​of each beam in the beam prediction result information and report the result information to the base station.

[0177] For example, information about the top K beams may include at least one of K beam identification information, the highest RSRP value, and difference information for the highest RSRP value. Here, the highest RSRP value may be indicated by a field consisting of a 7-bit value. Alternatively, the highest RSRP value may be indicated by a 7-bit value divided by a 1 dB step size in the range of [-140, -44] dBm, and the difference information may be indicated by a 4-bit value with a 2 dB step size.

[0178] When only one Top 1 beam is reported in the beam prediction result information, the beam prediction result information may include the identification information of the highest quality beam and the RSRP measurement value of the beam, and the RSRP measurement value is indicated by a field consisting of 7 bits. The 7-bit value may indicate the index of the value to which the RSRP value of the beam belongs in a preset table consisting of 1 dB step sizes.

[0179] When information on K Top K beams is reported in the beam prediction result information, the beam prediction result information indicates the RSRP value of the beam with the highest quality through a 7-bit field, and the RSRP values ​​of the remaining beams indicate the difference value from the RSRP value of the beam with the highest quality through a 4-bit field. That is, RSRP values ​​for multiple beams can be transmitted to the base station through the differential RSRP indication method. Of course, the identification information of each beam can be included in the beam prediction result information in a form corresponding to the value.

[0180] The beam prediction result information transmitted to the base station in this way is used to generate model evaluation result information.

[0181] In other words, the measurement result for the reference signal includes M beams selected based on the RSRP value of the reference signal received for model evaluation, and M can be set by the above configuration information. For example, M can be set to 1 or 2. In this way, the terminal can evaluate the model by comparing the measurement result derived by measuring the reception quality for the reference signal for model evaluation with the beam prediction result information.

[0182] For example, the step of generating model evaluation result information may generate model evaluation result information based on whether at least one of the M beams is included in the top K beams included in the beam prediction result information.

[0183] For example, it is assumed that M is 2, and the beams having the top two RSRP values ​​as a result of measuring the reference signal are beam identification information #1 and #3. In addition, it is assumed that K is set to 4, and the beam identification information for the Top-4 beams predicted with the highest quality that the terminal includes in the beam prediction result information are #2, #8, #3, and #4. In this case, among the M beams measured for model evaluation, #3 is included in the Top K beam identification information in the beam prediction result information transmitted to the base station as beam prediction result information, so the prediction accuracy of the model can be evaluated as high.

[0184] For this operation, the prediction beam information for generating beam prediction result information and the evaluation beam information for generating model evaluation result information can have a corresponding relationship indicated by configuration information.

[0185] The method by which a terminal performs beam management may include a step of transmitting model evaluation result information to a base station (S1440).

[0186] For example, the terminal may transmit evaluation result information to the base station according to the CSI report configuration configured by the configuration information. As an example, the evaluation result information may only include whether the Top M beam belongs to the Top K beam according to the comparison result described above with the model accuracy value. As another example, the evaluation result information may further include information on the number of times the Top M beam is included in the Top K beams, along with information on whether the Top M beam is included. As yet another example, the evaluation result information may further include measurement result information for each identifier of the Top M beam and a difference value between the prediction result of the beam included in the beam identification prediction information corresponding to the Top M beam.

[0187] If the reference signal is for BM-Case 2, the reference signal is configured for each time instance, and the terminal can generate model evaluation result information as a result of measuring the reference signal at one or more time instances and predicting beam prediction result information at the corresponding time instance.

[0188] The model evaluation result information can be included in some information fields of the CSI measurement result report via PUCCH or PUSCH.

[0189] Through these actions, the terminal can perform an evaluation on the AI / ML model configured in the terminal and report the evaluation to the base station.

[0190] Fig. 15 is a diagram for explaining base station operation according to one embodiment.

[0191] Referring to FIG. 15, a method for a base station to perform beam management may include a step of transmitting configuration information for evaluating a model configured in the terminal for beam prediction to the terminal (S1510).

[0192] For example, configuration information may include transmission resource information for reference signals for model evaluation. To evaluate the performance of a model configured in a terminal, the base station must transmit reference signals to the terminal. Therefore, the base station may transmit transmission resource information, such as the transmission period, transmission frequency resources, and transmission time resources, for the reference signals transmitted for evaluation.

[0193] For another example, the configuration information may include configuration information for the terminal to report evaluation result information to the base station. For example, the configuration information may further include radio resource information required for the terminal to report evaluation result information to the base station, information on the number of beams to be compared (e.g., the number M) required to generate the evaluation result information, and the like.

[0194] A method in which a base station performs beam management may include a step of transmitting a reference signal based on configuration information (S1520).

[0195] For example, the reference signal may be CSI-RS or SSB. Multiple reference signals are set, and may be set as spatially distinct beams or temporally distinct time instances.

[0196] A base station can transmit a reference signal via radio resources indicated by configuration information. The reference signal is configured for model monitoring and may be identical to or different from the reference signal of Set B for model inference. Furthermore, the reference signal may be configured to be smaller than Set A. The reference signal may be configured to have a corresponding relationship with the reference signals belonging to Set A. This corresponding relationship may be included in the aforementioned configuration information and indicated to the terminal.

[0197] The method for a base station to perform beam management may include a step of receiving, from a terminal, evaluation result information of a model generated by comparing beam prediction result information generated using a measurement result for a reference signal and an output of a model (S1530).

[0198] For example, a terminal measures the reception quality of the aforementioned reference signal and generates a measurement result. The measurement result may be a value measured by receiving a reference signal for actual monitoring, for example, an L1-RSRP value.

[0199] Meanwhile, the base station can receive beam prediction result information predicted using the model from the terminal at a previous point in time. For example, the beam prediction result information can include information on K beams having high RSRP values ​​among the RSRP values ​​for each beam calculated using the output of the model. The terminal can measure the beams of Set B and include information on K beams predicted in order of channel quality based on the K value configured by the base station in the beam prediction result information. The K value is set to a natural number and can be set by the base station.

[0200] The beam prediction result information may include identification information of the top K beams. Alternatively, the beam prediction result information may include at least one of identification information of the top K beams and RSRP values ​​of each beam. For example, the information on the top K beams may include at least one of the K beam identification information, the highest RSRP value, and difference value information for the highest RSRP value. Here, the highest RSRP value may be indicated by a field consisting of a 7-bit value. Alternatively, the highest RSRP value may be indicated by a 7-bit value divided by a 1 dB step size in the range of [-140, -44] dBm, and the difference value information may be indicated by a 4-bit value with a 2 dB step size.

[0201] The measurement results for the reference signal include M beams selected based on the RSRP value of the reference signal received for model evaluation, and M can be set by configuration information. For example, M can be set to 1 or 2. In this way, the terminal can evaluate the model by comparing the measurement results derived by measuring the reception quality of the reference signal for model evaluation with the beam prediction result information.

[0202] For example, the terminal can generate the model evaluation result information based on whether at least one of the M beams is included in the top K beams included in the beam prediction result information. For example, it is assumed that M is 2, and the beams having the top two RSRP values ​​as a result of measuring the reference signal are beam identification information #1 and #3. In addition, it is assumed that K is set to 4, and the beam identification information for the Top-4 beams predicted with the highest quality that the terminal includes in the beam prediction result information is #2, #8, #3, and #4. In this case, since #3 of the M beams measured for model evaluation is included in the Top K beam identification information in the beam prediction result information transmitted to the base station as the beam prediction result information, it can be evaluated that the prediction accuracy of the model is high.

[0203] For this operation, the prediction beam information for generating beam prediction result information and the evaluation beam information for generating model evaluation result information can have a corresponding relationship indicated by configuration information.

[0204] The base station can receive evaluation result information from the terminal according to the CSI report configuration indicated by the configuration information. For example, the evaluation result information may only include whether the Top M beam belongs to the Top K beam according to the comparison result described above with the model accuracy value. As another example, the evaluation result information may further include information on the number of times the Top M beam is included in the Top K beams, along with information on whether the Top M beam is included. As yet another example, the evaluation result information may further include a difference value between the measurement result information for each identifier of the Top M beam and the prediction result of the beam included in the beam identification prediction information corresponding to the Top M beam.

[0205] When the reference signal is for BM-Case 2, the reference signal is configured for each time instance, and the terminal can measure the reference signal at one or more time instances and generate model evaluation result information based on the beam prediction result information predicted at the corresponding time instance. The model evaluation result information can be included in some information fields of the CSI measurement result report via PUCCH or PUSCH.

[0206] Through these actions, the base station can check the evaluation results of the AI / ML model configured in the terminal and instruct the activation, switching, deactivation, retraining, etc. of the model.

[0207] An embodiment is described in relation to the operation of the terminal and base station described above.

[0208] FIG. 16 is a signal diagram for explaining a model performance evaluation operation between a terminal and a base station according to one embodiment.

[0209] Referring to FIG. 16, a terminal (1602) can report its AI / ML capability indication to a base station (1601) using an uplink channel (S1610). The AI / ML capability indication may include information such as whether the terminal can use an AI / ML model and information about the AI / ML model configured in the terminal. The AI / ML model information may include identification information, functional information, etc. of the corresponding model.

[0210] When the evaluation cycle for a model has arrived or the evaluation requirements for a model have been met, the terminal (1602) may request a dedicated RS transmission for model evaluation from the base station (1601) (S1620). As described above, the dedicated RS may be a reference signal for model evaluation, such as a CSI-RS or SSB.

[0211] The base station (1601) transmits RS according to a dedicated RS request from the terminal (1602) (S1630).

[0212] The terminal (1602) utilizes an AI / ML model based on dedicated RS measurements received from the base station (1601) to calculate model evaluation results or model accuracy (S1640). The model evaluation results or model accuracy can be calculated in various ways, as described in the terminal and base station operations described above. At least one of the following calculation methods may be applied.

[0213] - Whether the Top M beams selected as a result of measuring the reference signal are included in the Top K beams included in the beam prediction result information.

[0214] - Whether the L1-RSRP difference value of the common beam in each result of each beam and the top K beams included in the beam prediction result information according to the measurement result of the reference signal is within the reference value.

[0215] - Optimal value of L1-RSRP (difference between measured and predicted beam within X dB)

[0216] - Upper K value of L1-RSRP (difference between measured and predicted beam within X dB)

[0217] - Average L1-RSRP (difference between measured and predicted beam within X dB) of upper K values

[0218] Here, the beam prediction result information may include information about the predicted beam inferred using the model that is the subject of evaluation at a previous point in time, etc. For example, the beam prediction result information may include at least one of the following information.

[0219] - L1-RSRP value of the beam with the best measured L1-RSRP

[0220] - Top K L1-RSRP values

[0221] - Average of the top K L1-RSRP values

[0222] The terminal (1602) transmits information about the model evaluation results (monitoring KPI) to the base station (1601) (S1650). For example, the terminal (1602) reports the model evaluation results to the base station via a CSI report.

[0223] The base station (1601) transmits LCM operation information of the trained AI / ML model to the terminal (1602) based on the received model evaluation result information (S1660). The base station (1601) receives the report from the terminal (1602), determines whether to perform LCM operation on the model, and instructs the terminal (1602) accordingly. For example, the base station (1601) can instruct the terminal (1602) to perform necessary actions in the LCM operation, such as whether to continue using the model, replace the model, deactivate the model, or retrain the model.

[0224] The terminal (1602) controls the operation of the AI / ML model according to the received LCM operation information (S1670). For example, the terminal (1602) may activate / deactivate the corresponding model according to the indicated information. Alternatively, the terminal (1602) may retrain the corresponding model according to the indicated information. Alternatively, the terminal (1602) may switch the corresponding model to another model according to the indicated information. Alternatively, the terminal (1602) may fallback the corresponding model to a model value at a specific point in the past according to the indicated information.

[0225] The terminal (1602) transmits the results of controlling the operation of the AI / ML model to the base station (1601) (S1680). The terminal (1602) reports the results of the operation performed according to the indicated information to the base station (1601). For example, the terminal (1602) indicates that the processing of the corresponding model was successful according to the indicated information. Alternatively, the terminal (1602) transmits to the base station information indicating that the processing of the corresponding model failed according to the indicated information, along with information on the cause.

[0226] Meanwhile, more diverse embodiments in which the terminal transmits the aforementioned model evaluation result information to the base station are described.

[0227] 1. When reporting using Top M Beam RSRP values ​​(M=1)

[0228] - UE sends UE AI / ML capability indication to gNB

[0229] - UE requests dedicated RS for performance monitoring from gNB

[0230] - gNB transmits dedicated RS to UE

[0231] - UE calculates model evaluation result information based on dedicated RS measurement and AI / ML inference results (difference between the top 1 measured beam and the top K predicted beams according to the predicted L1-RSRP and measured L1-RSRP).

[0232] - UE transmits model evaluation result information to gNB

[0233] - gNB transmits LCM information to UE

[0234] - UE performs LCM operation

[0235] - UE sends LCM operation information to gNB

[0236] 2-1. When reporting Top M Beam RSRP difference values ​​(M>1)

[0237] - UE sends UE AI / ML capability indication to gNB

[0238] - UE requests dedicated RS for performance monitoring from gNB

[0239] - gNB transmits dedicated RS to UE

[0240] - UE calculates model evaluation result information based on dedicated RS measurement and AI / ML inference results (whether the Top M beams are included at least partially in the predicted Top K beams using the predicted L1-RSRP and measured L1-RSRP values)

[0241] - UE transmits monitoring model evaluation results information to gNB

[0242] - gNB transmits LCM information to UE

[0243] - UE is performing LCM operation

[0244] - UE sends LCM operation information to gNB

[0245] 2-2. When reporting the average value of the Top M Beam RSRP difference (M>1)

[0246] - UE sends UE AI / ML capability indication to gNB

[0247] - UE requests dedicated RS for performance monitoring from gNB

[0248] - gNB transmits dedicated RS to UE

[0249] - UE provides model evaluation results based on dedicated RS measurement and AI / ML inference results (predicted L1-RSRP and measured L1-RSRP difference values ​​for the top M beams or the average of the difference values).

[0250] - UE transmits monitoring model evaluation results information to gNB

[0251] - gNB transmits LCM information to UE

[0252] - UE is performing LCM operation

[0253] - UE sends LCM operation information to gNB

[0254]

[0255] Meanwhile, model evaluation result information can be transmitted as a bit value according to the difference gap value between the predicted RSRP and the measured RSRP, as shown in the table below. When calculating L1-RSRP relative information, the terminal calculates the difference (gap) between the measured beam and the predicted beam as a positive integer. The calculated difference can be converted to Mbits and transmitted as an uplink report. When transmitted in Mbits, it can be transmitted by configuring it according to the example in the table below, depending on the predicted L1-RSRP and measured L1-RSRP differences.

[0256] 7-bit RSRP (N=7)L1-RSRP difference (within 1.5dBm00010111.5dBm < gap <= 2dBm......00011115dBm < gap <= 6dBm......001001010dBm < gap <= 12dBm......111111140dBm < gap

[0257] 6-bit RSRP (N=6)L1-RSRP difference (within 12dBm......10100040dBm < gap...Reserved111111Reserved

[0258] Alternatively, in the case of beam prediction result information, if there are two or more Top K beams, the information may be configured and indicated as a 7-bit maximum RSRP value and a 4-bit difference value as shown in the table below. For example, as shown in Table 4, the maximum RSRP value may be set to a 7-bit value and transmitted. Here, the 7-bit value is a value indicating an RSRP value corresponding to Table 4 configured at X dB intervals within a preset range.

[0259] 7-bit RSRP (N=7)RSRP value (X dB interval)0000000-140 ≤ RSRP < -1390000001-139 ≤ RSRP < -1380000010-138 ≤ RSRP < -137… … 1111111-41 ≤ RSRP < -40

[0260] The 4-bit difference value indicates the difference between the RSRP value for the highest quality beam, reported as a 7-bit value, and the RSRP values ​​for the remaining Top K beams. The 4-bit value is set at 2 dB intervals.

[0261] 4-bit RSRP differenceRSRP difference value (Y dB interval)0000gap ≤ 100011 ≤ gap < 300103 ≤ gap < 5… … 111129 ≤ gap < 3

[0262] The above-described operations enable model evaluation of beams configured in a terminal. Below, the aforementioned terminal and base station are briefly described from a configuration perspective. To avoid unnecessary duplication of explanation, overlapping portions may be omitted.

[0263] Fig. 17 is a drawing showing a terminal configuration according to one embodiment.

[0264] Referring to FIG. 17, a terminal (1700) that performs beam management may include a receiving unit (1730) that receives configuration information for evaluating a model configured for beam prediction from a base station, and receives a reference signal based on the configuration information, a control unit (1710) that compares beam prediction result information generated using a measurement result for the reference signal and an output of the model to generate model evaluation result information, and a transmitting unit (1720) that transmits the model evaluation result information to the base station.

[0265] For example, the configuration information may include transmission resource information for reference signals for model evaluation. To evaluate the performance of a model configured in a terminal, the terminal must receive reference signals from a base station. Therefore, the terminal may receive transmission resource information, such as transmission cycles, transmission frequency resources, and transmission time resources, for the reference signals transmitted for evaluation. For another example, the configuration information may include configuration information for the terminal to report evaluation result information to the base station.

[0266] The reference signal may be CSI-RS or SSB. Multiple reference signals are set, and may be set as spatially distinct beams or temporally distinct time instances.

[0267] The terminal may have generated predicted beam prediction result information using the model at a previous point in time and reported it to the base station.

[0268] For example, the beam prediction result information may include information on K beams having high RSRP values ​​among the RSRP values ​​for each beam calculated using the model output. The terminal may measure the beams of Set B and transmit to the base station information on K beams predicted to have good channel quality based on the K value configured by the base station, including the beam prediction result information. The K value is set to a natural number and may be set by the base station.

[0269] The terminal may include identification information of the top K beams in the beam prediction result information. Alternatively, the terminal may include identification information of the top K beams and at least one of the RSRP values ​​of each beam in the beam prediction result information and report the result information to the base station.

[0270] For example, information about the top K beams may include at least one of K beam identification information, the highest RSRP value, and difference information for the highest RSRP value. Here, the highest RSRP value may be indicated by a field consisting of a 7-bit value. Alternatively, the highest RSRP value may be indicated by a 7-bit value divided by a 1 dB step size in the range of [-140, -44] dBm, and the difference information may be indicated by a 4-bit value with a 2 dB step size.

[0271] When only one Top 1 beam is reported in the beam prediction result information, the beam prediction result information may include the identification information of the highest quality beam and the RSRP measurement value of the beam, and the RSRP measurement value is indicated by a field consisting of 7 bits. The 7-bit value may indicate the index of the value to which the RSRP value of the beam belongs in a preset table consisting of 1 dB step sizes.

[0272] When information on K Top K beams is reported in the beam prediction result information, the beam prediction result information indicates the RSRP value of the beam with the highest quality through a 7-bit field, and the RSRP values ​​of the remaining beams are indicated through a 4-bit field indicating the difference value from the RSRP value of the beam with the highest quality.

[0273] The measurement result for the reference signal includes M beams selected based on the RSRP value of the reference signal received for model evaluation, and M can be set by the above configuration information. For example, M can be set to 1 or 2. In this way, the terminal can evaluate the model by comparing the measurement result derived by measuring the reception quality for the reference signal for model evaluation with the beam prediction result information.

[0274] For example, the control unit (1710) can generate model evaluation result information based on whether at least one of the M beams is included in the upper K beams included in the beam prediction result information.

[0275] The transmitter (1720) may transmit evaluation result information to the base station according to the CSI report configuration configured by the configuration information. For example, the evaluation result information may only include whether the Top M beam belongs to the Top K beam according to the comparison result described above as the model accuracy value. As another example, the evaluation result information may further include information on the number of times the Top M beam is included in the Top K beams, along with information on whether the Top M beam is included. As yet another example, the evaluation result information may further include a difference value between the measurement result information for each identifier of the Top M beam and the prediction result of the beam included in the beam identification prediction information corresponding to the Top M beam.

[0276] In addition, the receiver (1730) receives downlink control information, data, and messages from the base station through the corresponding channel.

[0277] Additionally, the control unit (1720) controls the overall operation of the user terminal (1700) according to the performance monitoring method of the AI / ML model for beam management required to perform the aforementioned disclosure.

[0278] The transmitter (1730) transmits uplink control information, data, and messages to the base station through the corresponding channel.

[0279] Fig. 18 is a diagram showing a base station configuration according to one embodiment.

[0280] Referring to FIG. 18, a base station (1800) that performs beam management may include a transmitter (1820) that transmits configuration information for evaluating a model configured in a terminal for beam prediction to the terminal and transmits a reference signal based on the configuration information, and a receiver (1830) that compares beam prediction result information generated using a measurement result for the reference signal and an output of the model and receives evaluation result information of the generated model from the terminal.

[0281] For example, configuration information may include transmission resource information for reference signals for model evaluation. To evaluate the performance of a model configured in a terminal, the base station must transmit reference signals to the terminal. Therefore, the base station may transmit transmission resource information, such as the transmission period, transmission frequency resources, and transmission time resources, for the reference signals transmitted for evaluation.

[0282] For another example, the configuration information may include configuration information for the terminal to report evaluation result information to the base station. For example, the configuration information may further include radio resource information required for the terminal to report evaluation result information to the base station, information on the number of beams to be compared (e.g., the number M) required to generate the evaluation result information, etc. For example, the reference signal may be a CSI-RS or SSB. Multiple reference signals are configured, and may be configured as spatially distinct beams or as beams of temporally distinct time instances.

[0283] The transmitter (1820) can transmit a reference signal via a wireless resource indicated by the configuration information. The reference signal is configured for model monitoring and may be identical to or different from the reference signal of Set B for model inference. In addition, the reference signal may be configured with a smaller size than Set A. The reference signal may be configured in a correspondence relationship with the reference signal belonging to Set A. The correspondence relationship may be included in the aforementioned configuration information and indicated to the terminal.

[0284] Meanwhile, the receiving unit (1830) may receive beam prediction result information predicted using the model from the terminal at a previous point in time. For example, the beam prediction result information may include information on K beams having high RSRP values ​​among the RSRP values ​​for each beam calculated using the output of the model. The terminal may measure the beams of Set B and include information on K beams predicted in order of channel quality based on the K value configured by the base station in the beam prediction result information. The K value is set to a natural number and may be set by the base station.

[0285] The beam prediction result information may include identification information of the top K beams. Alternatively, the beam prediction result information may include at least one of identification information of the top K beams and RSRP values ​​of each beam. For example, the information on the top K beams may include at least one of the K beam identification information, the highest RSRP value, and difference value information for the highest RSRP value. Here, the highest RSRP value may be indicated by a field consisting of a 7-bit value. Alternatively, the highest RSRP value may be indicated by a 7-bit value divided by a 1 dB step size in the range of [-140, -44] dBm, and the difference value information may be indicated by a 4-bit value with a 2 dB step size.

[0286] The receiving unit (1830) may receive evaluation result information from the terminal according to the CSI report configuration indicated by the configuration information. For example, the evaluation result information may only include whether the Top M beam belongs to the Top K beam according to the comparison result described above as the model accuracy value. As another example, the evaluation result information may further include information on the number of times the Top M beam is included in the Top K beams, along with information on whether the Top M beam is included. As yet another example, the evaluation result information may further include a difference value between the measurement result information for each identifier of the Top M beam and the prediction result of the beam included in the beam identification prediction information corresponding to the Top M beam.

[0287] When the reference signal is for BM-Case 2, the reference signal is configured for each time instance, and the terminal can measure the reference signal at one or more time instances and generate model evaluation result information based on the beam prediction result information predicted at the corresponding time instance. The model evaluation result information can be included in some information fields of the CSI measurement result report via PUCCH or PUSCH.

[0288] In addition, the control unit (1810) controls the overall operation of the base station (1800) according to the performance monitoring method of the AI / ML model for beam management required to perform the aforementioned disclosure.

[0289] The transmitter (1820) and receiver (1830) are used to transmit and receive signals, messages, and data necessary for performing the aforementioned embodiment to and from the terminal.

[0290] The above-described 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, components, and parts not described in the present embodiments to clearly illustrate the technical concepts herein may be supported by the above-described standard documents. Furthermore, all terms disclosed in this specification may be explained by the above-described standard documents.

[0291] The embodiments described above may be implemented through various means. For example, the embodiments may be implemented through hardware, firmware, software, or a combination thereof.

[0292] In the case of hardware implementation, the method according to the present 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.

[0293] When implemented using firmware or software, the methods according to the present embodiments may be implemented in the form of devices, procedures, or functions that perform the functions or operations described above. The software code may be stored in a memory unit and executed by a processor. The memory unit may be located within or outside the processor and may exchange data with the processor using various known means.

[0294] Additionally, terms such as "system," "processor," "controller," "component," "module," "interface," "model," or "unit" as described above may generally refer to a computer-related entity, such as hardware, a combination of hardware and software, software, or software in execution. For example, the aforementioned components may be, but are not limited to, a process driven by a processor, a processor, a controller, a control processor, an object, a thread of execution, a program, and / or a computer. For example, both an application running on a controller or a processor and the controller or the processor may be components. One or more components may be within a process and / or thread of execution, 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.

[0295] The above description is merely an illustrative example of the technical idea of ​​the present disclosure, and those skilled in the art to which the present disclosure pertains will appreciate that various modifications and variations can be made without departing from the essential characteristics of the technical idea of ​​the present disclosure. In addition, the present embodiments are not intended to limit the technical idea of ​​the present disclosure but rather to explain it, and therefore the scope of the technical idea of ​​the present disclosure is not limited by these embodiments. The scope of protection of the present disclosure should be interpreted by the claims below, and all technical ideas within a scope equivalent thereto should be interpreted as being included within the scope of the rights of the present disclosure.

[0296]

[0297] CROSS-REFERENCE TO RELATED APPLICATION

[0298] This patent application claims priority under 35 USC §119(a) to Korean Patent Application No. 10-2024-0100877, filed in Korea on July 30, 2024, and Korean Patent Application No. 10-2025-0102314, filed in Korea on July 28, 2025, the entire contents of which are incorporated herein by reference. In addition, this patent application claims priority in countries other than the United States for the same reasons, the entire contents of which are incorporated herein by reference.

Claims

1. In the method of performing beam management by the terminal, A step of receiving configuration information for evaluating a model configured for beam prediction from a base station; A step of receiving a reference signal based on the above configuration information; A step of generating evaluation result information of the model by comparing the beam prediction result information generated using the measurement result for the reference signal and the output of the model; and A method comprising a step of transmitting evaluation result information of the above model to the base station.

2. In paragraph 1, The above configuration information is, A method including transmission resource information of the reference signal for evaluating the above model.

3. In paragraph 1, The above beam prediction result information is, A method including information on the top K beams having high RSRP values ​​among the RSRP (Reference Signals Received Power) values ​​for each beam calculated using the output of the above model.

4. In paragraph 3, Information about the top K beams above is: A method comprising at least one of the K beam identification information, the highest RSRP value, and the difference value information for the highest RSRP value.

5. In paragraph 4, The highest RSRP value above is, A method indicated by a field consisting of a 7-bit value.

6. In paragraph 4, The highest RSRP value above is, It is indicated as a 7-bit value in 1dB step size in the range of [-140, -44]dBm, The above difference information is, How to indicate 4-bit values ​​with 2dB step size.

7. In paragraph 1, The measurement results for the above reference signal are as follows: In order to evaluate the above model, M beams are selected based on the RSRP value of the reference signal received, The above M is a method set by the above configuration information.

8. In paragraph 7, The step of generating evaluation result information of the above model is: A method for generating evaluation result information of the model based on whether at least one of the M beams is included in the upper K beams included in the beam prediction result information.

9. In paragraph 8, The prediction beam information for generating the above beam prediction result information and the evaluation beam information for generating the evaluation result information of the above model are, A method in which a correspondence relationship is indicated by the above configuration information.

10. In the method of performing beam management by the base station, A step of transmitting configuration information for evaluating a model configured in a terminal for beam prediction to the terminal; A step of transmitting a reference signal based on the above configuration information; and A method comprising a step of receiving, from the terminal, evaluation result information of the model generated by comparing the measurement result for the reference signal and beam prediction result information generated using the output of the model.

11. In paragraph 10, The above configuration information is, A method including transmission resource information of the reference signal for evaluating the above model.

12. In paragraph 10, The above beam prediction result information is, A method including information on the top K beams having high RSRP values ​​among the RSRP (Reference Signals Received Power) values ​​for each beam calculated using the output of the above model.

13. In paragraph 12, Information about the top K beams above is: A method comprising at least one of the K beam identification information, the highest RSRP value, and the difference value information for the highest RSRP value.

14. In paragraph 13, The highest RSRP value above is, It is indicated as a 7-bit value in 1dB step size in the range of [-140, -44]dBm, The above difference information is, How to indicate 4-bit values ​​with 2dB step size.

15. In paragraph 10, The evaluation result information of the above model is: A method for generating a beam prediction result based on whether at least one of the M beams selected based on the RSRP value of the reference signal received for evaluation of the model is included in the upper K beams included in the beam prediction result information.

16. In the terminal performing beam management, A receiving unit that receives configuration information for evaluating a model configured for beam prediction from a base station and receives a reference signal based on the configuration information; A control unit that generates evaluation result information of the model by comparing the measurement result of the reference signal and beam prediction result information generated using the output of the model; and A terminal including a transmitter that transmits evaluation result information of the above model to the base station.

17. In paragraph 16, The above beam prediction result information is, A terminal including information on the top K beams having high RSRP values ​​among the RSRP (Reference Signals Received Power) values ​​for each beam calculated using the output of the above model.

18. In paragraph 17, Information about the top K beams above is: A terminal including at least one of the K beam identification information, the highest RSRP value, and the difference value information for the highest RSRP value.

19. In paragraph 18, The highest RSRP value above is, It is indicated as a 7-bit value in 1dB step size in the range of [-140, -44]dBm, The above difference information is, Terminal indicated as a 4-bit value with a 2dB step size.

20. In paragraph 16, The evaluation result information of the above model is: A terminal generated based on whether at least one of the M beams selected based on the RSRP value of the reference signal received for evaluation of the above model is included in the upper K beams included in the beam prediction result information.

Images