Method and apparatus for operating beam in wireless communication system

Abstract

An operation method of a base station, according to one embodiment of the present disclosure, comprises the operations of: receiving, from a terminal, information indicating capabilities of the terminal; transmitting, to the terminal, configuration information based on the information indicating capabilities of the terminal; transmitting a wireless signal to the terminal by performing first beam sweeping; receiving, from the terminal, output information of a first artificial intelligence model related to the first beam sweeping; generating prediction information for beam selection by inputting the output information of the first artificial intelligence model to a second artificial intelligence model; and determining n number of beams on the basis of the prediction information for beam selection.

Description

Method and device for operating a beam in a wireless communication system

[0001] The present disclosure relates to a method and device for operating a beam in a wireless communication system, and more particularly, to a method and device for improving beam prediction accuracy and reducing overhead by using artificial intelligence in a base station and a terminal.

[0002] Looking back at the evolution of wireless communication over successive generations, technologies have primarily been developed for human-facing services such as voice, multimedia, and data. With the commercialization of the 5G (5th Generation) communication system, an explosive increase in connected devices is expected to be connected to communication networks. Examples of networked objects include vehicles, robots, drones, home appliances, displays, smart sensors installed in various infrastructures, construction equipment, and factory equipment. Mobile devices are also expected to evolve into diverse form factors, such as augmented reality glasses, virtual reality headsets, and holographic devices. In the 6G (6th Generation) era, efforts are being made to develop improved 6G communication systems to connect hundreds of billions of devices and objects and provide diverse services. For this reason, 6G communication systems are often referred to as "beyond 5G."

[0003] The 6G communication system, expected to be realized around 2030, will have a maximum transmission speed of terabytes (i.e., 1,000 gigabits) per second (bps) and a wireless latency of 100 microseconds (μsec). In other words, compared to 5G, the transmission speed in a 6G communication system will be 50 times faster and the wireless latency will be reduced to one-tenth.

[0004] To achieve these high data rates and ultra-low latency, 6G communication systems are being considered for implementation in the terahertz (THz) band (e.g., from 95 gigahertz (GHz) to 3 terahertz (THz)). Compared to the millimeter wave (mmWave) band introduced in 5G, the terahertz band is expected to have more severe path loss and atmospheric absorption, making it more important to develop technologies that can guarantee signal reach, or coverage. Key technologies to ensure coverage include Radio Frequency (RF) components, antennas, new waveforms that offer better coverage than Orthogonal Frequency Division Multiplexing (OFDM), beamforming, and multiple antenna transmission technologies such as massive Multiple-Input and Multiple-Output (MIMO), Full Dimensional MIMO (FD-MIMO), array antennas, and large-scale antennas. In addition, new technologies such as metamaterial-based lenses and antennas, high-dimensional spatial multiplexing using Orbital Angular Momentum (OAM), and Reconfigurable Intelligent Surface (RIS) are being discussed to improve the coverage of terahertz band signals.

[0005] In addition, in order to improve frequency efficiency and system network, 6G communication systems are developing full duplex technology that utilizes the same frequency resources at the same time for uplink and downlink; network technology that integrates satellites and HAPS (High-Altitude Platform Stations); network structure innovation technology that supports mobile base stations and enables optimization and automation of network operation; dynamic spectrum sharing technology through collision avoidance based on spectrum usage prediction; AI-based communication technology that utilizes AI (Artificial Intelligence) from the design stage and internalizes end-to-end AI support functions to realize system optimization; and next-generation distributed computing technology that realizes services with complexity that exceeds the limits of terminal computing capabilities by utilizing ultra-high-performance communication and computing resources (Mobile Edge Computing (MEC), cloud, etc.). In addition, efforts are being made to further strengthen connectivity between devices, further optimize networks, promote softwareization of network entities, and increase the openness of wireless communications through the design of new protocols to be used in 6G communication systems, the implementation of hardware-based security environments, the development of mechanisms for the safe use of data, and the development of technologies for maintaining privacy.

[0006] Research and development of these 6G communication systems are expected to enable a new level of hyper-connected experience through the hyper-connectivity of 6G communication systems, which encompass not only connections between things but also connections between people and things. Specifically, 6G communication systems are expected to enable services such as truly immersive eXtended Reality (XR), high-fidelity mobile holograms, and digital replicas. Furthermore, services such as remote surgery, industrial automation, and emergency response, which are provided through 6G communication systems through enhanced security and reliability, will be applied in diverse fields such as industry, medicine, automobiles, and home appliances.

[0007] The present disclosure relates to a method and device for reducing overhead and improving beam prediction performance by using an artificial intelligence model during beam management in 5G / 5G-Advanced / 6G mobile communication systems. In particular, when using analog beamforming in high-frequency bands (mmWave, Tera hertz, etc.), a technology is needed to efficiently operate and manage beams while taking into account overhead and latency constraints.

[0008] Beam management of the present disclosure is a technology that forms an optimal transmit / receive beam pair between a base station and a terminal (UE) through beam sweeping transmission. Since analog beam forming is generally an important technology at higher frequencies than at lower frequencies due to its characteristics, beam management plays a greater role in frequency range (FR) 2 (i.e., mmWave range) than in FR 1. In a massive MIMO (Multiple-input multiple-output) system of FR 2, a synchronization procedure is initiated when a terminal connects to a base station. For this operation, the base station transmits a synchronization signal, and the signal must be able to reach multiple terminals around the base station. However, due to the characteristics of a large-sized antenna array, the beam width is inevitably narrow, and a narrow beam cannot cover a wide area simultaneously.

[0009] To solve this problem, the base station transmits a beam in a specific direction at a specific time, and then transmits the beam while slightly changing the direction in the next time frame to cover the entire area. This is called beam management. Specifically, the base station transmits a synchronization signal block (SSB) in a specific direction beam for beam management, and the terminal can measure this signal and feed back information about the signal (e.g., peak power beam index) to the base station. In particular, accurate beam selection is important because the paired beam index continuously changes for a moving terminal. The base station selects a beam to form a beam pair with the terminal based on the feedback received from the terminal, and can transmit and receive information by forming the beam pair.

[0010] During this beam management process, the base station performs a beam sweeping operation to select a beam. This requires repeated beam transmissions in multiple directions, resulting in overhead. Therefore, if beam sweeping can be simplified, overhead can be reduced. To achieve this, an AI model can be utilized. This AI model can predict signal information even when the base station does not actually transmit a beam, and beams can be selected based on the predicted values.

[0011] The present disclosure may provide a method and device for operating a beam using artificial intelligence in a wireless communication system. Furthermore, the present disclosure may provide a method and device for operating a beam using an artificial intelligence model on the base station and / or terminal side.

[0012] A method according to one embodiment of the present disclosure is a method performed by a base station in a wireless communication system, comprising: a step of receiving information indicating a capability of a terminal from a terminal; a step of transmitting configuration information based on the information indicating the capability of the terminal to the terminal; a step of transmitting a wireless signal to the terminal by performing a first beam sweeping; a step of receiving, from the terminal, output information of a first artificial intelligence model related to the first beam sweeping based on the configuration information; a step of inputting the output information of the first artificial intelligence model into a second artificial intelligence model to generate prediction information for beam selection; and a step of determining n beams based on the prediction information for beam selection.

[0013] A method according to one embodiment of the present disclosure is a method performed by a terminal in a wireless communication system, comprising the steps of: transmitting information indicating a capability of the terminal to a base station; receiving configuration information based on the information indicating the capability of the terminal from the base station; receiving signals for first beam-swept beams from the base station; generating signal quality information for the first beam-swept beams; generating output information of a first artificial intelligence model based on the signal quality information for the first beam-swept beams; transmitting the output information to the base station; receiving signals for second beam-swept beams from the base station; and transmitting information about a beam having the best signal quality among the second beam-swept beams to the base station.

[0014] A method and device according to one embodiment of the present disclosure can improve overhead of beam operation and beam prediction accuracy in a wireless communication system.

[0015] Specifically, the method and device according to one embodiment of the present disclosure can perform efficient beam operation using an artificial intelligence model on the base station side and an artificial intelligence model on the terminal side.

[0016] In addition, the method and device according to one embodiment of the present disclosure can minimize delay time when changing a beam pair according to a change in a communication environment and improve the reliability of information transmission.

[0017] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the description below.

[0018] The features and advantages of one embodiment of the present disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings.

[0019] FIG. 1 illustrates a wireless communication system according to one embodiment of the present disclosure.

[0020] Figure 2 is a drawing for explaining the structure of a terminal according to one embodiment.

[0021] FIG. 3 is a drawing for explaining the structure of a base station according to one embodiment.

[0022] FIG. 4 is a drawing for explaining a beam sweeping operation according to one embodiment of the present disclosure.

[0023] FIG. 5 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0024] FIG. 6 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0025] FIG. 7 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0026] FIG. 8 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0027] FIG. 9 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0028] Figure 10 shows capability information of artificial intelligence according to one embodiment of the present disclosure.

[0029] FIG. 11 is a table showing beam prediction types according to one embodiment of the present disclosure.

[0030] FIG. 12 is a table showing beam prediction types corresponding to a system environment according to one embodiment of the present disclosure.

[0031] FIG. 13 illustrates beam patterns according to one embodiment of the present disclosure.

[0032] FIG. 14 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0033] FIG. 15 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0034] FIG. 16 illustrates beam prediction parameters corresponding to a beam prediction type according to one embodiment of the present disclosure.

[0035] FIG. 17 illustrates an operation method of a base station according to one embodiment of the present disclosure.

[0036] Fig. 18 illustrates an operation method of a terminal according to one embodiment of the present disclosure.

[0037] Embodiments of the present disclosure may address the problems and / or disadvantages described above and provide the advantages described below. One aspect of the present disclosure may provide a network entity (or node) and a communication method thereof in a wireless communication system.

[0038] The terms used in this disclosure are used only to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the art described in this disclosure. Terms defined in general dictionaries among the terms used in this disclosure may be interpreted as having the same or similar meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this disclosure. In some cases, even if a term is defined in this disclosure, it cannot be interpreted to exclude embodiments of the present disclosure.

[0039] The various embodiments of the present disclosure described below illustrate hardware-based approaches. However, since the various embodiments of the present disclosure encompass techniques utilizing both hardware and software, the various embodiments of the present disclosure do not exclude software-based approaches.

[0040] Additionally, although various embodiments of the present disclosure describe various embodiments using terminology used in certain communication standards (e.g., 3rd generation partnership project (3GPP)), this is merely an example for illustrative purposes. Various embodiments of the present disclosure can be easily modified and applied to other communication systems.

[0041] Hereinafter, various embodiments of the present disclosure will be described.

[0042] Meanwhile, the core of AI-based beam management is that the base station performs SSB transmission using some beams from the entire beam grid pattern. The UE can feed back the reference signals received power (RSRP) value of the received SSB beam to the base station. The base station can perform beam prediction using the RSRP values ​​received from the UE as inputs to the AI ​​model. The base station can predict the RSRP values ​​corresponding to the beams that have not been transmitted through beam prediction. The base station can sweep the beams corresponding to the top k RSRP values ​​among the RSRP values ​​of the entire beam grid obtained through beam prediction (k is a hyper-parameter related to beam operation). The UE can report to the base station the beam corresponding to the largest RSRP value among the k received beams.

[0043] For AI-based beam management, beam prediction can be performed using an AI model at the base station using RSRP values ​​reported from the terminal as input. This type of inference performed by a single entity is referred to as "one-sided model inference." The input to the base station AI model can be the RSRP values ​​reported from the terminal.

[0044] When seeking to improve the performance of AI-based beam management (e.g., reducing beam sweeping overhead or improving beam prediction accuracy), leveraging only one-sided model inference is unlikely to yield significant performance gains. In particular, the hardware complexity of mobile communication systems is limited, making it difficult to increase the size of AI models or the amount of data processed indiscriminately. Consequently, operating beam management solely with a one-sided model presents limitations.

[0045] A method and device according to one embodiment of the present disclosure are a method and device for performing beam operation by applying two-sided model inference to reduce overhead and improve beam prediction accuracy compared to beam operation based on one-sided model inference.

[0046] In general, UEs can utilize raw values ​​for reporting information and additional UE-oriented information. For example, signal-related information such as L1-RSRP, received signal strength indicator (RSSI), and reference signal received quality (RSRQ); UE-side beam information such as Rx beam shape / direction, Rx beam angle, Rx beam-width, and Rx beam boresight; UE position information such as UE location and UE moving direction; and channel information such as historical CIR, SINRs, and CQIs. Since this information is available to the UE, performing UE-side model inference using this information can improve beam management efficiency. In the case of the existing one-sided model inference based on the NW-side model, since inference is performed only on the NW-side, UE-oriented information and raw data cannot be used for AI inference unless the UE reports all information. Therefore, we plan to utilize two-sided model inference that performs inference on both the UE-side and the NW-side.

[0047] FIG. 1 illustrates a wireless communication system according to one embodiment of the present disclosure.

[0048] FIG. 1 illustrates some of the nodes utilizing a wireless channel in a wireless communication system, including a base station (110), a first terminal (120), and / or a second terminal (130). Although FIG. 1 illustrates only one base station, this is merely an example. The wireless communication system of FIG. 1 may further include other base stations identical or similar to the base station (110).

[0049] The base station (110) is a network infrastructure that provides wireless access to terminals (120, 130). The base station (110) has coverage defined as a certain geographical area based on the distance at which a signal can be transmitted. In addition to the base station, the base station (110) may be referred to as an 'access point (AP)', 'eNodeB (eNB)', 'gNodeB (gNB)', '5G node (5th generation node)', 'wireless point', 'transmission / reception point (TRP)', or other terms having equivalent technical meanings.

[0050] The first terminal (120) and the second terminal (130) are each devices used by a user and can communicate with the base station (110) via a wireless channel. At least one of the first terminal (120) or the second terminal (130) can be operated without the user's intervention. For example, at least one of the first terminal (120) or the second terminal (130) may be a device that performs machine type communication (MTC) and may not be carried by the user. Each of the first terminal (120) and the second terminal (130) may be referred to as a terminal, or other terms having equivalent technical meanings, such as 'user equipment (UE),' 'mobile station,' 'subscriber station,' 'customer premises equipment (CPE),' 'remote terminal,' 'wireless terminal,' 'electronic device,' or 'user device.'

[0051] The base station (110), the first terminal (120), and the second terminal (130) can transmit and / or receive wireless signals in the millimeter wave (mmWave) band (e.g., 28 GHz, 30 GHz, 38 GHz, 60 GHz). At this time, in order to improve channel gain, the base station (110), the first terminal (120), and / or the second terminal (130) can perform beamforming.

[0052] Beamforming may include transmit beamforming and / or receive beamforming. That is, the base station (110), the first terminal (120), and / or the second terminal (130) may impart directionality to the transmit signal or the receive signal. To impart directionality to the receive signal, the base station (110) and / or the terminals (120, 130) may select serving beams (112, 113, 121, 131) through a beam search or beam management procedure. After the serving beams (112, 113, 121, 131) are selected, subsequent communication may be performed through resources that are in a quasi-co-located (QCL) relationship with the resources that transmitted the serving beams (112, 113, 121, 131).

[0053] The base station (110), the first terminal (120), and the second terminal (130) of the present disclosure may each be a transmitting apparatus, a transmitting node, a receiving apparatus, and / or a receiving node. For example, the base station (110) may transmit an RF (radio frequency) signal to the first terminal (120). The base station (110) may receive the RF signal from the first terminal (120). As another example, the first terminal (120) may transmit an RF signal to the base station (110) or the second terminal (130). The first terminal (120) may receive the RF signal from the base station (110) or the second terminal (130).

[0054] Figure 2 is a drawing for explaining the structure of a terminal according to one embodiment.

[0055] Referring to FIG. 2, a terminal (200) according to one embodiment may include a transceiver (210), a memory (220), and / or a processor (230). Although the terminal (200) is described in the present disclosure as including a transceiver (210), a memory (220), and / or a processor (230), this is merely an example. For example, the terminal (200) may further include other components in addition to the transceiver (210), the memory (220), and the processor (230).

[0056] According to one embodiment, the transceiver (210), memory (220), and processor (230) may be implemented or formed as separate chips. However, this is merely an example, and the transceiver (210), memory (220), and / or processor (230) may be implemented or formed as a single chip.

[0057] According to one embodiment, the transceiver (210) may include at least one transmitter and / or at least one receiver. For example, the transceiver (210) may include an RF transmitter for amplifying and up-converting the frequency of a transmitted signal. The transceiver (210) may include an RF receiver for down-converting the frequency of a received signal and amplifying low-noise.

[0058] The configurations of the transceiver (210) described in the present disclosure are merely examples, and the configuration of the transceiver (210) is not limited to an RF transmitter and an RF receiver. For example, the transceiver (210) may further include a coupler to ensure isolation between the RF transmitter and the RF receiver.

[0059] In one embodiment, the transceiver (210) may transmit or receive signals to the processor (230). For example, the transceiver (210) may transmit or deliver an RF signal received via a wireless communication channel to the processor (230). The transceiver (210) may receive or deliver an RF signal from the processor (230).

[0060] In one embodiment, the transceiver (210) may be referred to as a UE transmitter or a UE receiver.

[0061] According to one embodiment, the transceiver (210) may transmit signals to or receive signals from a base station (e.g., base station (110) of FIG. 1) or a network entity (e.g., access and mobility management function (AMF) entity). In one embodiment, the transmitted or received signals may include control signals and data.

[0062] According to one embodiment, the memory (220) may include or store programs and data necessary for the operations of the terminal (200). For example, the memory (220) may be a non-transitory memory, and a program stored in the non-transitory memory may be organically combined with a hardware configuration of the terminal (200) (e.g., a processor (230) or a transceiver (210)). The memory (220) may store control information or data including a signal acquired by the terminal (200). In one embodiment, the memory (220) may include a read-only memory (ROM), a random access memory (RAM), a hard disk, a CD-ROM, a DVD, and / or a storage medium.

[0063] According to one embodiment, the processor (230) may include one processor or multiple processors. For example, the processor (230) may include a communication processor. For example, the processor (230) may include a communication processor and / or an application processor.

[0064] In one embodiment, the processor (230) may control a series of processes performed by the terminal (200). For example, the transceiver (210) may receive a data signal including control information transmitted by a base station or network entity. The processor (230) may process the received control signal and data signal.

[0065] The term "processor" in the present disclosure may be replaced with various terms referring to a configuration that executes or performs operations of the terminal (200). For example, the term "processor" may be replaced with a controller or a computing circuit.

[0066] The terminal (200) of the present disclosure may correspond to the first terminal (120) and / or the second terminal (130) of FIG. 1.

[0067] FIG. 3 is a drawing for explaining the structure of a base station according to one embodiment.

[0068] Referring to FIG. 3, a base station (300) according to one embodiment may include a transceiver (310), a memory (320), and / or a processor (330). Although the base station (300) is described in the present disclosure as including a transceiver (310), a memory (320), and / or a processor (330), this is merely an example. For example, the base station (300) may further include other components in addition to the transceiver (310), the memory (320), and the processor (330).

[0069] According to one embodiment, the transceiver (310), memory (320), and processor (330) may be implemented or formed as separate chips. However, this is merely an example, and the transceiver (310), memory (320), and / or processor (330) may be implemented or formed as a single chip.

[0070] According to one embodiment, the transceiver (310) may include at least one transmitter and / or at least one receiver. For example, the transceiver (310) may include an RF transmitter for amplifying and up-converting the frequency of a transmitted signal. The transceiver (310) may include an RF receiver for down-converting the frequency of a received signal and amplifying low-noise.

[0071] The configurations of the transceiver (310) described in the present disclosure are merely examples, and the configuration of the transceiver (310) is not limited to an RF transmitter and an RF receiver. For example, the transceiver (310) may further include a coupler to ensure isolation between the RF transmitter and the RF receiver.

[0072] In one embodiment, the transceiver (310) may transmit or receive signals to the processor (330). For example, the transceiver (310) may transmit or deliver an RF signal received via a wireless communication channel to the processor (330). The transceiver (310) may receive or deliver an RF signal from the processor (230).

[0073] In one embodiment, the transceiver (310) may be referred to as a base station transmitter or a base station receiver.

[0074] In one embodiment, the transceiver (310) may transmit a signal to the terminal (200) or receive a signal from the terminal (200). In one embodiment, the transmitted or received signal may include a control signal and data.

[0075] According to one embodiment, the memory (320) may include programs and data necessary for the operations of the base station (300). For example, the memory (320) may be a non-transitory memory, and the program stored in the non-transitory memory may be organically combined with the hardware configuration of the base station (300) (e.g., the processor (330) or the transceiver (310)). The memory (320) may store control information or data including a signal acquired by the base station (300). In one embodiment, the memory (320) may include a read-only memory (ROM), a random access memory (RAM), a hard disk, a CD-ROM, a DVD, and / or a storage medium.

[0076] According to one embodiment, the processor (330) may include one processor or multiple processors. For example, the processor (330) may include a communication processor. For example, the processor (330) may include a communication processor and / or an application processor.

[0077] In one embodiment, the processor (330) may control a series of processes performed by the base station (300). For example, the transceiver (310) may receive a data signal containing control information transmitted by the base station or a network entity. The processor (330) may process the received control signal and data signal.

[0078] The term "processor" in the present disclosure may be replaced with various terms referring to a configuration that executes or performs operations of the base station (300). For example, the term "processor" may be replaced with a controller or a computing unit.

[0079] The devices described in FIGS. 2 and 3 may correspond to devices of a transmitter or receiver. A terminal or base station according to an embodiment of the present disclosure may be a transmitter if it is a transmitter, and may be a receiver if it is a receiver.

[0080] Hereinafter, the transmitter and receiver may refer to the terminals or base stations described in FIGS. 1 to 3, respectively. When describing downlink signals, the base station will be the transmitter and the terminal will be the receiver, and when describing uplink signals, the terminal will be the transmitter and the base station will be the receiver.

[0081] FIG. 4 is a drawing for explaining a beam sweeping operation according to one embodiment of the present disclosure.

[0082] Referring to FIG. 4, a base station (410) can perform a beam sweeping operation. The base station (410) can transmit a SSB (Synchronization Signal Block) to a beam that is a target of the sweeping operation based on a beam grid (or beam pattern information). The base station (410) transmits beams (432, 434, 436, 438) with different directions over time, and the terminal (420) can measure an RSRP (Reference Signals Received Power) value corresponding to the SSB of the received beams. That is, the terminal (420) can measure an RSRP value corresponding to each beam. The RSRP value corresponding to each beam can indicate the reception quality for each beam. The terminal can measure and utilize not only the RSRP value but also the RSRQ (Reference Signal Received Quality) and the RSSI (received signal strength indicator).

[0083] FIG. 5 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0084] Referring to FIG. 5, a method of operating a beam using an artificial intelligence model on the base station (510) side is illustrated.

[0085] The base station (510) of FIG. 5 can correspond to the base stations described in FIGS. 1, 3, and 4.

[0086] Operation 530 indicates that the base station (510) performs a beam sweeping operation based on the beam grid (5301) (or beam pattern information) when t=T0. The beam sweeping of operation 530 may correspond to the beam sweeping operation described in FIG. 4. The beam grid (5301) may represent some beams on which beam sweeping is to be performed among all beams that can be transmitted from the base station (510). For example, the beam grid (5301) may represent 9 beams among 36 beams that can be transmitted from the base station. In this case, the base station may perform a beam sweeping operation with the 9 beams based on the beam grid. The beam sweeping operation according to one embodiment of the present disclosure may be understood as an operation in which the base station transmits a wireless signal to a terminal on each of a plurality of beams.

[0087] Operation 532 represents an operation in which the terminal (520) measures RSRP for beams transmitted from the base station (510) and transmits the measured RSRP values ​​to the base station (510). For example, when the base station (510) transmits a signal on the first to fourth beams, the terminal (520) can measure a first RSRP value for the first beam, a second RSRP value for the second beam, a third RSRP value for the third beam, and a fourth RSRP value for the fourth beam, and transmit the measured first to fourth RSRP values ​​to the base station (510).

[0088] In one embodiment, the terminal (520) may transmit at least one of the RSRP value, RSSI value, or RSRQ value for each beam to the base station (510). The terminal (520) may transmit information indicating the quality of the signal for each beam to the base station (510).

[0089] Operation 534 represents an operation in which the base station (510) operates an artificial intelligence model based on the RSRP values ​​received from the terminal (520). The artificial intelligence model of the base station (510) can predict RSRP values ​​for other beams by using the RSRP values ​​for each beam received from the terminal (520) as input. In addition, the base station (510) can select K beams expected to have good signal quality based on the predicted RSRP values.

[0090] For example, the base station (510) can predict RSRP values ​​for beams that are not transmitted in operation 530. If the base station (510) performs beam sweeping for 9 beams out of 36 beams that can be transmitted, the base station (510) can receive RSRP values ​​for the 9 beams from the terminal, and the base station can run an artificial intelligence model with the received RSRP values ​​as input to predict RSRP values ​​for the remaining 27 beams.

[0091] Operation 536 represents an operation of performing beam sweeping on K beams selected by the base station (510). The beam sweeping of operation 536 may correspond to the beam sweeping operation described in FIG. 4. If the base station (510) selects four beams in operation 534, the base station (510) may perform a beam sweeping operation with the four beams in operation 536. The selected beams may be expressed by a beam grid (5361) (or beam pattern information). For example, the beam grid (5361) may represent four beams selected from among 36 beams. Accordingly, operation 536 may be performed based on the beam grid (5361) representing the selected beams. Operation 536 may be performed at a time point t = T0 + a. However, operation 536 is an operation that performs beam sweeping on the top k beams predicted based on signal quality information for beam sweeping performed at time t = T0.

[0092] Operation 538 represents an operation in which the terminal (520) measures RSRP for signals of K beams transmitted from the base station (510), selects the best beam based on the measured RSRP values, and transmits information about the best beam to the base station (510). For example, when the base station (510) transmits signals through the first to fourth beams by operation 536, the terminal (520) can measure a first RSRP value for the first beam, a second RSRP value for the second beam, a third RSRP value for the third beam, and a fourth RSRP value for the fourth beam, and when the RSRP value with the best signal quality is the fourth RSRP value, information about the beam corresponding to the fourth RSRP value can be transmitted to the base station (510).

[0093] By means of operations 530 to 538, the base station (510) can determine which beam is the best. Accordingly, the base station (510) can transmit information using the corresponding beam in a subsequent communication process.

[0094] FIG. 6 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0095] Referring to Fig. 6, a method of operating a beam using an artificial intelligence model on the base station (610) side is illustrated. Fig. 6 illustrates that the beam sweeping operation of the base station (610) is t=T in order to utilize the correlation according to the passage of time. -N This is an embodiment performed at multiple points in time from t=T0.

[0096] The base station (610) of FIG. 6 can correspond to the base stations described in FIGS. 1, 3, 4, and 5.

[0097] 630 motion, the base station (610) t=T -NWhen , it indicates that a beam sweeping operation is performed based on a beam grid (6301). The beam sweeping of the 630 operation may correspond to the beam sweeping operation described in FIG. 4. The beam grid (6301) may represent some beams on which beam sweeping is to be performed among all beams that can be transmitted from the base station (630). For example, the beam grid (6301) may represent 9 beams among 36 beams that can be transmitted from the base station. In this case, the base station may perform a beam sweeping operation with the 9 beams based on the beam grid (6301).

[0098] 632 operation is, the terminal (620) transmits the beam (t=T) from the base station (610) -N This represents an operation of measuring RSRP for the first to fourth beams and transmitting the measured RSRP values ​​to the base station (610). For example, when the base station (610) transmits a signal on the first to fourth beams, the terminal (620) can measure a first RSRP value for the first beam, a second RSRP value for the second beam, a third RSRP value for the third beam, and a fourth RSRP value for the fourth beam, and transmit the measured first to fourth RSRP values ​​to the base station (610).

[0099] In one embodiment, the terminal (620) may transmit at least one of the RSRP value, RSSI value, or RSRQ value for each beam to the base station (610). The terminal (620) may transmit information indicating the quality of the signal for each beam to the base station (610).

[0100] Operation 634 indicates that the base station (610) performs a beam sweeping operation based on the beam grid (6341) (or beam pattern information) when t=T0. The beam sweeping of operation 634 may correspond to the beam sweeping operation described in FIG. 4. The beam grid (6341) may represent some beams on which beam sweeping is to be performed among all beams that can be transmitted from the base station (630). For example, the beam grid (6341) may represent 9 beams among 36 beams that can be transmitted from the base station. In this case, the base station may perform a beam sweeping operation with the 9 beams based on the beam grid.

[0101] Operation 636 represents an operation in which the terminal (620) measures RSRP for beams transmitted from the base station (610) (when t=T0) and transmits the measured RSRP values ​​to the base station (610). For example, when the base station (610) transmits a signal on the first to fourth beams, the terminal (620) can measure a first RSRP value for the first beam, a second RSRP value for the second beam, a third RSRP value for the third beam, and a fourth RSRP value for the fourth beam, and transmit the measured first to fourth RSRP values ​​to the base station (610).

[0102] Action 630 to Action 634 is when the base station (610) is at t=T -N ...beam sweeping operations can be performed at each time point up to T0. In addition, in operations 632 to 636, the terminal (620) can transmit RSRP measurement information corresponding to the beam sweeping of the base station (610) to the base station (610). In one embodiment, the temporal order of operations 632 and 634 may be different.

[0103] Operation 638 represents an operation in which the base station (610) operates an artificial intelligence model based on the RSRP values ​​received from the terminal (620). The artificial intelligence model of the base station (610) can predict RSRP values ​​for other beams by using the RSRP values ​​for each beam received from the terminal (620) as input. In addition, the base station (610) can select K beams expected to have good signal quality based on the predicted RSRP values.

[0104] The base station (610) is the input of the artificial intelligence model t=T -N The RSRP values ​​for beam sweeping performed at t=T0 can be used. That is, the RSRP values ​​for beam sweeping performed at multiple points in time at the base station (610) can be used as inputs for the artificial intelligence model. In addition, the artificial intelligence model of the base station (610) can be used when t=T -N The base station (610) can predict RSRP values ​​for beams that are not beam swept at t=T0, and the base station (610) can select K beams that are expected to have good signal quality based on the predicted RSRP values. In addition, the artificial intelligence model of the base station (610) can predict RSRP values ​​for beams that are not beam swept at t=T0, and the base station (610) can select K beams that are expected to have good signal quality based on the predicted RSRP values. That is, the base station (610) can predict RSRP values ​​for beams that are not beam swept at t=T0, and the base station (610) can select K beams that are expected to have good signal quality based on the predicted RSRP values. -N K beams corresponding to each time point can be selected from t=T0. The base station (610) selects K beams corresponding to each time point from t=T1,...,T M Beam sweeping can be performed at this point (640 operations and 644 operations).

[0105] The artificial intelligence model of the base station (610) is based on multiple points in time (e.g. t=T -N ,....,T0) as input and RSRP measurement values ​​corresponding to multiple time points (e.g. t=T1,....,TM ) can predict the RSRP value corresponding to each point in time. Then, the artificial intelligence model of the base station (610) can select K beams based on the predicted RSRP value corresponding to each point in time, and the base station (610) can perform beam sweeping for the selected K beams.

[0106] Operation 640 represents an operation in which the base station (610) performs beam sweeping on the K beams selected at the time point t=T1. The beam sweeping of operation 640 may correspond to the beam sweeping operation described in FIG. 4. If the base station (610) selects four beams in operation 638, the base station (610) may perform a beam sweeping operation with the four beams in operation 640. The selected beams may be expressed by a beam grid (6401) (or beam pattern information). For example, the beam grid (6401) may represent four beams selected from among 36 beams. Accordingly, operation 640 may be performed based on the beam grid (6401) representing the selected beams. Operation 640 may be performed at the time point t=T1. Operation 640 may be performed when t=T -N It may be an operation of performing beam sweeping on the top k beams predicted based on signal quality information for beam sweeping performed at the time point.

[0107] Operation 642 represents an operation in which the terminal (620) measures RSRP for K beams transmitted from the base station (610), selects the best beam based on the measured RSRP values, and transmits information about the best beam to the base station (610). For example, when the base station (610) transmits a signal to the first to fourth beams by operation 640, the terminal (620) can measure a first RSRP value for the first beam, a second RSRP value for the second beam, a third RSRP value for the third beam, and a fourth RSRP value for the fourth beam, and when the RSRP value with the best signal quality is the fourth RSRP value, the terminal can transmit information about the beam corresponding to the fourth RSRP value (e.g., a beam identifier) ​​to the base station (610).

[0108] 644 The action is that the base station (610) t=T M It represents an operation of performing beam sweeping on K beams selected at a time point. The beam sweeping of operation 644 may correspond to the beam sweeping operation described in FIG. 4. If the base station (610) selects four beams in operation 638, the base station (510) may perform a beam sweeping operation with the four beams in operation 644. At this time, the selected beams may be expressed as a beam grid (6441) (or beam pattern information). For example, the beam grid (6441) may represent four beams selected from 36 beams. Therefore, operation 644 may be performed based on the beam grid (6441) representing the selected beams. Operation 644 is t = T M The 644 operation may be an operation of performing beam sweeping on the top k beams predicted based on signal quality information for beam sweeping performed at the time t = T0.

[0109] Operation 646 represents an operation in which the terminal (620) measures RSRP for K beams transmitted from the base station (610), selects the best beam based on the measured RSRP values, and transmits information about the best beam to the base station (610). For example, when the base station (610) transmits a signal through the first to fourth beams by operation 644, the terminal (620) can measure a first RSRP value for the first beam, a second RSRP value for the second beam, a third RSRP value for the third beam, and a fourth RSRP value for the fourth beam, and when the RSRP value with the best signal quality is the fourth RSRP value, information about the beam corresponding to the fourth RSRP value can be transmitted to the base station (610).

[0110] By means of operations 640 to 646, the base station (610) can determine which of the K candidate beams is the best beam for each time point. Accordingly, the base station (610) can transmit information using the beam corresponding to each time point in a subsequent communication process.

[0111] A beam operation method according to one embodiment of the present disclosure can select candidate beams that are predicted to have excellent signal quality over time by predicting a signal quality measurement value that changes over time in an environment in which a terminal (620) moves, recognize a beam with the best signal quality through beam sweeping of the candidate beams, and transmit information using the beam.

[0112] FIG. 7 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0113] Referring to Fig. 7, a method of operating a beam using an artificial intelligence model at a base station (710) and a terminal (720) is illustrated. Fig. 7 illustrates that the beam sweeping operation of the base station (710) is t=T in order to utilize the correlation over time. -NThis is an embodiment performed at multiple points in time from t=T0.

[0114] The base station (710) of FIG. 7 can correspond to the base stations described in FIGS. 1, 3, 4 to 6.

[0115] 730 motion, the base station (710) t=T -N When , it indicates that a beam sweeping operation is performed based on a beam grid (7301). The beam sweeping of operation 730 may correspond to the beam sweeping operation described in FIG. 4. The beam grid (7301) may represent some beams on which beam sweeping is to be performed among all beams that can be transmitted from the base station (710). For example, the beam grid (7301) may represent 9 beams among 36 beams that can be transmitted from the base station. In this case, the base station may perform a beam sweeping operation with the 9 beams based on the beam grid.

[0116] Operation 732 indicates that the base station (710) performs a beam sweeping operation based on the beam grid (7321) when t=T0. In operations 730 to 732, the base station (710) performs a beam sweeping operation based on the beam grid (7321) when t=T -N ... can perform beam sweeping operations corresponding to each time point up to T0.

[0117] The 734 operation is that the terminal (720) transmits a beam (t=T) from the base station (710). -N...T0) and an operation of measuring at least one of RSRP, RSSI or RSRQ, inputting the measured values ​​as input to an artificial intelligence model on the terminal (720) and outputting information. The terminal (720) may drive the artificial intelligence model using as input not only information indicating the quality of a signal such as RSRP, RSSI or RSRQ, but also beam-related information on the terminal (720) such as RX beam shape / direction, Rx beam angle, Rx beam width, Rx beam boresight, position information of the terminal (720) such as the location of the terminal (720), the moving direction of the terminal (720), and information about the channel such as CIR (carrier to interference ratio), SINR (signal to interference plus noise ratio), CQI (channel quality indicator). In addition, in operation 734, the terminal (720) may transmit information output from the artificial intelligence model on the terminal side to the base station (710).

[0118] The operation 736 represents an operation of driving an artificial intelligence model of the base station (710) based on information received from the terminal (720). The artificial intelligence model of the base station (710) can select K beams that are expected to have good signal quality based on information received from the terminal (720). At this time, the base station (710) operates from t=T1 to t=T M For multiple time points, K beams corresponding to each time point can be selected.

[0119] The artificial intelligence model of the base station (710) receives information from the terminal (720) as input and processes it over time (e.g., t=T1,...,T M) can predict information about the beam corresponding to each point in time. And, the artificial intelligence model of the base station (710) can select K beams based on information about the predicted beam corresponding to each point in time.

[0120] Operation 738 represents an operation in which the base station (710) performs beam sweeping on K beams selected in response to time t=T1. The beam sweeping of operation 738 may correspond to the beam sweeping operation described in FIG. 4. If the base station (710) selects four beams in operation 738, the base station (710) may perform a beam sweeping operation with the four beams in operation 738. The selected beams may be represented by a beam grid (7381). For example, the beam grid (7381) may represent four beams selected from among 36 beams. Accordingly, operation 738 may be performed based on the beam grid (7381) representing the selected beams. Operation 740 may be performed at time t=T1. Operation 740 may be performed when t=T -N Based on signal quality information about beam sweeping performed at a time point t = T0, the base station may perform beam sweeping for the top k beams predicted for the time point t = T0.

[0121] Operation 740 represents an operation in which the terminal (720) measures signal quality values ​​(e.g., RSRP, RSSI, and / or RSRQ) for K beams transmitted from the base station (710), selects the best beam based on the measured signal quality values, and transmits information about the best beam to the base station (710). For example, when the base station (710) transmits a signal through the first to fourth beams by operation 738, the terminal (720) can measure a first signal quality value for the first beam, a second signal quality value for the second beam, a third signal quality value for the third beam, and a fourth signal quality value for the fourth beam, and when the signal quality value having the best signal quality is the fourth signal quality value, the terminal can transmit information about the beam corresponding to the fourth signal quality value to the base station (710).

[0122] 742 Action, the base station (710) t=T M It represents an operation of performing beam sweeping for K beams selected for a time point. The beam sweeping of operation 742 may correspond to the beam sweeping operation described in FIG. 4. If the base station (610) selects four beams in operation 736, the base station (710) may perform a beam sweeping operation with the four beams in operation 742. The selected beams may be represented by a beam grid (7421). For example, the beam grid (7421) may represent four beams selected from 36 beams. Accordingly, operation 742 may be performed based on the beam grid (7421) representing the selected beams. Operation 742 is t = T M can be performed at the point t = T. The 740 operation is performed at the point t = T. -N Based on the signal quality information for the beam sweeping performed at time t = T0, t = T M It may be an operation in which the base station performs beam sweeping for the top k beams predicted for a point in time.

[0123] Operation 744 represents an operation in which the terminal (720) measures signal quality values ​​(e.g., RSRP, RSSI, and / or RSRQ) for K beams transmitted from the base station (710), selects the best beam based on the measured signal quality values, and transmits information about the best beam to the base station (710). For example, when the base station (710) transmits a signal through the first to fourth beams by operation 742, the terminal (720) can measure a first signal quality value for the first beam, a second signal quality value for the second beam, a third signal quality value for the third beam, and a fourth signal quality value for the fourth beam, and when the signal quality value having the best signal quality is the fourth signal quality value, the terminal can transmit information about the beam corresponding to the fourth signal quality value to the base station (710).

[0124] By operation 738 to operation 744, the base station (710) performs each time point (t=T1,....,T M ) can recognize which beam among the K candidate beams is the best. Therefore, the base station (610) can transmit information using the beam with the best signal quality in the subsequent communication process.

[0125] In a beam operation method according to one embodiment of the present disclosure, a terminal (720) inputs a signal quality measurement value according to time change to drive an artificial intelligence model, and a base station (710) receives information output from the terminal (720)-side artificial intelligence model to drive the base station (710)-side artificial intelligence model to select K candidate beams for each time point. The base station (710) performs beam sweeping on the K candidate beams for each time point, and receives information on an excellent beam corresponding to each beam sweep from the terminal (720), thereby being able to use a beam with excellent signal quality.

[0126] FIG. 8 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0127] Referring to Fig. 8, a method of operating a beam using an artificial intelligence model at a base station (810) is illustrated. The base station (810) of Fig. 8 may correspond to the base stations described in Figs. 1, 3, 4 to 7.

[0128] The embodiment described in Fig. 8 can correspond to the embodiments described in Figs. 5 and 6.

[0129] Operation 832 represents an operation of performing beam sweeping at the base station (810). Operation 832 may correspond to operation 530 of FIG. 5 or operations 630 and 634 of FIG. 6. The base station (810) may perform a beam sweeping operation based on a beam grid. The beam grid may represent some beams on which beam sweeping is to be performed among all beams that can be transmitted from the base station (810). For example, the beam grid may represent 9 beams among 36 beams that can be transmitted from the base station. In this case, the base station may perform a beam sweeping operation with the 9 beams based on the beam grid. The beam sweeping operation according to one embodiment of the present disclosure may be understood as an operation in which the base station transmits a wireless signal to a terminal on each of a plurality of beams.

[0130] In one embodiment, operation 832 is performed when the base station (810) t=T -N ...beam sweeping operation can be performed at each time point until T0. In addition, in operation 834, the terminal (820) can transmit measurement information corresponding to the beam sweeping of the base station (810) to the base station (610).

[0131] Operation 834 represents an operation in which the terminal (820) transmits information about a beam to the base station (810). Operation 834 may correspond to operation 532 of FIG. 5 or operations 632 and 636 of FIG. 6. For example, in operation 832, when the base station (810) beam sweeps the first to fourth beams, the terminal (820) may measure information about the first beam, information about the second beam, third information about the third beam, and fourth information about the fourth beam, and transmit the measured first to fourth information to the base station (810).

[0132] In one embodiment, the information about the beam may include at least one of an RSRP value, an RSSI value, or an RSRQ value. The information about the beam may indicate information indicating the quality of a signal for each beam.

[0133] Operation 836 represents an operation in which the base station (810) predicts information about beams based on the first artificial intelligence model and selects k beams based on the predicted information. Operation 836 may correspond to operation 534 of FIG. 5 or operation 638 of FIG. 6. Operation 836 may represent an operation in which the base station (810) drives the first artificial intelligence model based on signal quality information about beams received from the terminal (820). The artificial intelligence model of the base station (810) may use signal quality information (e.g., RSRP, RSSI, or RSRQ, etc.) for each beam received from the terminal (820) as input to predict signal quality information about other beams. In this case, the other beams may refer to beams that the base station (810) has not beam-swept. In addition, the artificial intelligence model of the base station (810) may select K beams expected to have good signal quality based on the predicted values. The artificial intelligence model of the base station (810) may select K beams corresponding to each point in time for a plurality of points in time.

[0134] For example, the base station (810) can predict the signal quality value for the beam that was not transmitted in operation 832. If the base station (810) performs beam sweeping for 9 beams among 36 beams that can be transmitted, the base station (810) can receive signal quality measurement values ​​for the 9 beams from the terminal, and the base station can predict signal quality measurement values ​​for the remaining 27 beams by running an artificial intelligence model with the received measurement values ​​as input. In addition, the artificial intelligence model of the base station (810) can output K beams based on the signal quality measurement values.

[0135] Operation 838 represents an operation in which the base station (810) performs beam sweeping on K beams. The base station (810) can perform beam sweeping on K beams selected in operation 836. Operation 838 may correspond to operation 536 of FIG. 5 or operations 640 and 644 of FIG. 6.

[0136] Operation 840 represents an operation in which the terminal (820) selects a beam based on measurement information about the beam. In operation 840, the terminal (820) can measure the signal quality for the beam sweeping operation of the base station (810) and select the beam with the best signal quality based on the measured value. For example, in operation 838, if the base station (810) performs the beam sweeping operation with four selected beams, the terminal (820) can measure the signal quality for the four selected beams. Then, the terminal (820) can select the beam with the best signal quality among the four selected beams.

[0137] Operation 842 represents an operation in which the terminal (820) transmits information about the selected beam to the base station (810). The terminal (820) may transmit information about the beam with the best signal quality to the base station (810) based on the signal quality value measured in operation 840. At this time, the information about the beam may represent information for identifying the beam.

[0138] Actions 840 and 842 may correspond to actions 538 of FIG. 5 or actions 642 and 646 of FIG. 6.

[0139] Operation 844 represents an operation in which the base station (810) transmits information based on the selected beam. The base station (810) can receive information about the beam with the best signal quality through operation 842. Accordingly, the base station (810) can transmit information using the beam with the best signal quality.

[0140] FIG. 9 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0141] Referring to FIG. 9, a method of operating a beam using an artificial intelligence model at a base station (910) and a terminal (920) is illustrated.

[0142] The base station (910) of FIG. 9 can correspond to the base stations described in FIGS. 1, 3, 4 to 8.

[0143] Operation 930 represents an operation in which the base station (910) receives a UE capability report from the terminal (920). The UE capability report may include information related to the capabilities of the terminal (920). For example, the UE capability report may include information on whether the terminal (920) supports an artificial intelligence model, performance information of the terminal related to the use of the artificial intelligence model, capability information related to the artificial intelligence model, and / or expression format information for supportable artificial intelligence models. In addition, the base station (910) may receive information on beam prediction accuracy requirements according to UE mobility, intra-cell channel environments, etc. from the terminal (920).

[0144] Terminal performance information related to the use of AI models may include input / output performance indicators such as I / O memory bandwidth, floating point operations per second (FLOPS), and the amount of power consumed when running AI models.

[0145] Capability information related to an artificial intelligence model may include information about the number of parameters available to the artificial intelligence model, and memory or storage capacity.

[0146] Information on the AI ​​model representation format (MRF) that can be supported may include a representation method such as open neural network exchange (ONNX) as a way to express the structure of the AI ​​model.

[0147] Operation 932 represents an operation in which the base station (910) transmits configuration information on a beam prediction type and / or parameters to the terminal (920). The base station (910) may transmit configuration information on the beam prediction type and parameters to be used for beam prediction to the terminal (920) in the form of DCI (Downlink control information), RRC (Radio resource control) parameters, or MAC (Medium Access control) CE (Control element). In operation 930, the base station (910) may determine the prediction type and parameters based on the capability information of the terminal (920), beam prediction accuracy requirement according to the mobility of the terminal (UE mobility), and the channel environment within the cell.

[0148] The beam prediction-related parameters that the base station (910) can set for the terminal (920) are as follows.

[0149] AI Model: The base station can transmit information representing an AI model to the terminal. Since hardware implementations vary across terminals, the base station can transmit the AI ​​model to the terminal to achieve highly reliable AI inference performance. The AI ​​model can be transmitted to the terminal as a runtime image or by transmitting the model's architecture and weight information.

[0150] Input information for the terminal-side artificial intelligence model: Input information for the terminal-side artificial intelligence model can be indicated. The input information for the terminal-side artificial intelligence model can indicate information related to signal strength such as RSRP, RSSI, RSRQ, etc.; Rx beam-related information such as Rx beam shape / direction / angle / width / boresight; position information of the terminal such as the location and moving direction of the terminal; and / or downlink channel information such as historical CIRs, SINRs, CQI that can be obtained through channel estimation. Information to be used as input for the terminal-side artificial intelligence model can be mapped through model and pre-training, and can be selectively used by the terminal.

[0151] Beam Pattern Information: Beam pattern information can indicate information about the beams that the base station uses when performing beam sweeping among all beams that can be transmitted from the base station's antenna. For example, if there are a total of 36 beams that can be transmitted from the base station's antenna, the base station can transmit beam pattern information indicating which of the 36 beams is used for beam sweeping to the terminal. Therefore, when the terminal measures RSRP for each beam, the terminal can know for which beam the measured RSRP is a measurement value through the beam pattern information.

[0152] Output Information for the Terminal-Side AI Model: Output information for the terminal-side AI model can be displayed. The output information for the terminal-side AI model may include information corresponding to the upper Q beams, pre-reconstructed RSRPs, intermediate information, and / or time information. The output information for the terminal-side AI model may also be mapped to the AI ​​model in advance.

[0153] The information corresponding to the upper Q beams indicates that the terminal-side artificial intelligence model outputs information corresponding to the upper Q candidate beams. In other words, the terminal-side artificial intelligence model can output information corresponding to the Q candidate beams and transmit the information to the base station.

[0154] Pre-reconfigured RSRPs indicate that the terminal-side AI model predicts and outputs RSRP values. That is, the terminal can predict and output signal quality information (e.g., RSRP values) for other beams that are not beam-swept by the base station, and transmit these predicted values ​​to the base station. In one embodiment, the terminal-side AI model can also predict and output other values ​​that can replace RSRP, such as RSSI and RSRQ.

[0155] Intermediate information can be collectively referred to as the vector-format output from the terminal-side AI model. While intermediate information itself has no specific meaning, it is transmitted to the base station and used as input for the base station-side AI model, thereby assisting the base station-side AI model in selecting k candidate beams.

[0156] Time information can represent the time interval corresponding to the information output from the terminal-side AI model. For example, at the base station, t=T -N ...when beam sweeping is performed multiple times during T0, the terminal-side AI model is t=T -N ...information about beams swept during T0 can be received as input and output values ​​corresponding to a certain time interval can be generated. At this time, the values ​​output from the terminal-side artificial intelligence model may be information corresponding to a specific time interval (time window size) based on configuration information.

[0157] The 934 operation is that the base station (910) is based on the beam grid at t=T -N...represents performing a beam sweeping operation corresponding to each time point T0. The beam sweeping of operation 934 may correspond to the beam sweeping operation described in FIG. 4. In addition, operation 934 may correspond to operations 730 to 732 of FIG. 7. The beam grid may represent some beams on which beam sweeping is to be performed among all beams that can be transmitted from the base station (910). For example, the beam grid may represent 9 beams among 36 beams that can be transmitted from the base station. In this case, the base station may perform a beam sweeping operation with the 9 beams based on the beam grid.

[0158] The 936 operation is that the terminal (920) transmits a beam (t=T) from the base station (910). -N ...T0) and an operation of measuring at least one of RSRP, RSSI or RSRQ, inputting the measured values ​​as input to an artificial intelligence model on the terminal (920) and outputting information (or vector). The terminal (920) can drive the artificial intelligence model by using as input not only information indicating the quality of the signal such as RSRP, RSSI or RSRQ, but also beam-related information on the terminal (720) such as RX beam shape / direction, Rx beam angle, Rx beam width, Rx beam boresight, position information of the terminal (720) such as the location of the terminal (720), the moving direction of the terminal (720), and information about the channel such as CIR (carrier to interference ratio), SINR (Signal to interference plus noise ratio), CQI (channel quality indicator). Operation 936 may correspond to operation 734 of FIG. 7.

[0159] Operation 938 represents an operation in which the terminal (920) transmits information (or vector) output from the terminal-side artificial intelligence model to the base station (910). The information output from the terminal-side artificial intelligence model can be set by operation 932. Operation 938 may correspond to operation 734 of FIG. 7.

[0160] Operation 940 represents an operation of driving an artificial intelligence model of the base station (910) based on information (or vector) received from the terminal (920). Operation 940 may correspond to operation 736 of FIG. 7. The base station (910) may process the information received from the terminal (920) as input to the artificial intelligence model of the base station (910) to select K beams that are expected to have good signal quality. At this time, the base station (910) may select K beams from t=T0 to t=T. M For multiple time points, K beams corresponding to each time point can be selected (or determined).

[0161] The artificial intelligence model of the base station (910) receives information from the terminal (920) as input and processes it over time (e.g., t=T0,....,T M ) can be predicted for the beam corresponding to the point in time. At this time, the information about the beam can be referred to as prediction information for beam selection. In addition, the artificial intelligence model of the base station (910) can select K beams based on the information about the predicted beam corresponding to each point in time.

[0162] In one embodiment, the AI ​​model of the base station (910) may use as input not only information received from the terminal (920) but also information generated by the base station itself. For example, the information generated by the base station itself may include channel-related information such as the shape / direction / angle / width / boresight of the transmission beam, historical UL channels, SRS measurement, and antenna configuration information such as logical port antenna and physical port antenna.

[0163] Operation 942 represents an operation in which the base station (910) performs beam sweeping on the selected K beams. The beam sweeping of operation 942 may correspond to the beam sweeping operation described in FIG. 4. If the base station (910) selects four beams in operation 940, the base station (910) may perform a beam sweeping operation on the four beams in operation 942.

[0164] In one embodiment, the value of K may be 1. That is, the base station (910) can select one beam and perform communication immediately.

[0165] Operation 944 represents an operation in which the terminal (920) measures signal quality values ​​(e.g., RSRP, RSSI, and / or RSRQ) for K beams transmitted from the base station (910) and selects the best beam based on the measured signal quality values. For example, when the base station (910) transmits the first to fourth beams by operation 942, the terminal (920) can measure a first signal quality value for the first beam, a second signal quality value for the second beam, a third signal quality value for the third beam, and a fourth signal quality value for the fourth beam, and when the signal quality value with the best signal quality is the fourth signal quality value, the terminal (920) can select the beam corresponding to the fourth signal quality value.

[0166] Operation 946 represents an operation in which the terminal (920) transmits information about the best beam selected in operation 944 to the base station (910). The information about the best beam may be information for identifying the beam.

[0167] In operation 948, the base station (910) can transmit information using the beam with the best signal quality by using the information about the best beam received by operation 946.

[0168] In a beam operation method according to one embodiment of the present disclosure, a terminal (920) inputs a signal quality measurement value according to time change to drive an artificial intelligence model, and a base station (910) receives information output from the terminal (920)-side artificial intelligence model to drive the base station (910)-side artificial intelligence model to select K candidate beams for each time point. The base station (910) performs beam sweeping on the K candidate beams for each time point, and receives information on an excellent beam corresponding to each beam sweep from the terminal (920), thereby being able to use a beam with excellent signal quality.

[0169] Figure 10 shows artificial intelligence-related capability information of a terminal according to one embodiment of the present disclosure.

[0170] The AI-related capability information of the terminal illustrated in FIG. 10 may be included in the terminal capability report transmitted in operation 930 of FIG. 9. FIG. 10 may represent performance information of the terminal related to the use of an AI model.

[0171] Referring to Figure 10, the AI-related capabilities of a terminal can be classified into categories. For example, the AI-related capabilities of a terminal can be classified from category 0 to category 4. The criteria for classifying the AI-related capabilities of a terminal can be based on the floating point operations per second (FLOPS) and the speed at which the AI ​​model reads and writes input (AI memory). For example, if FLOPS is 10 6 And, a terminal with 100MB of AI memory can be classified as category 0. FLOPS is 10 7 And, a terminal with 100MB of AI memory can be classified as category 1. FLOPS is 10 8 And, a terminal with 200MB of AI memory can be classified as category 2. FLOPS is 10 9 And, a terminal with 200MB of AI memory can be classified as category 3. FLOPS is 10 10 And, terminals with AI memory of 500MB can be classified as category 4.

[0172] The criteria for classifying the terminal's AI-related capabilities are not limited to the aforementioned content, and the terminal's AI-related capabilities may be classified by including other factors.

[0173] FIG. 11 is a table showing beam prediction types according to one embodiment of the present disclosure.

[0174] The beam prediction type information illustrated in FIG. 11 may be information included in the beam prediction type information and parameter setting information transmitted in operation 932 of FIG. 9.

[0175] Referring to FIG. 11, beam prediction types according to one embodiment of the present disclosure can be classified as follows.

[0176] Index 0: Indicates a beam prediction method that does not use artificial intelligence. The setting for index 0 can be used when the terminal is in an environment where artificial intelligence cannot be used.

[0177] Index 1: Represents a one-sided spatial-domain beam prediction method using artificial intelligence at a base station.

[0178] Index 2: Represents a beam prediction method in the temporal-spatial domain using artificial intelligence at the base station (one-sided).

[0179] Index 3: Represents a two-sided spatial-domain beam prediction method using artificial intelligence at the base station and terminal.

[0180] Index 4: Represents a two-sided temporal-spatial-domain beam prediction method using artificial intelligence at the base station and the terminal.

[0181] The beam prediction method corresponding to index 1 can correspond to the method described in Fig. 5. Referring to Fig. 5, a base station-side artificial intelligence model is used, and the passage of time is not considered.

[0182] The beam prediction method corresponding to index 2 can correspond to the method described in Fig. 6. Referring to Fig. 6, a base station-side artificial intelligence model is used and a beam is predicted by considering the flow of time (K candidate beams are selected for each time point).

[0183] The beam prediction method corresponding to index 4 can correspond to the method described in Fig. 7. Referring to Fig. 7, an artificial intelligence model of a base station and a terminal is used (two-sided), and a beam is predicted by considering the flow of time (K candidate beams are selected for each time point).

[0184] In the case of the beam prediction method corresponding to index 3, unlike the method described in FIG. 7, the base station performs beam sweeping for a single point in time (e.g., t= T0), the terminal drives a terminal-side artificial intelligence model based on measurement information for beam sweeping, and the base station drives the artificial intelligence model with the output value of the terminal artificial intelligence model to select (or predict) K beams.

[0185] The base station can determine a beam prediction type or related parameters based on a terminal capability report received from the terminal, and transmit the determined setting information to the terminal.

[0186] FIG. 12 is a table showing beam prediction types corresponding to a system environment according to one embodiment of the present disclosure.

[0187] Referring to FIG. 12, the base station can set beam prediction type information to the terminal according to the system environment. The beam prediction type information can indicate a beam prediction method.

[0188] For example, if the terminal is a low-cost device and the artificial intelligence-related performance of the terminal is not good, the base station can set the beam prediction type corresponding to index 0 to the terminal. If the terminal is static (not moving) and the beam change is small, the beam prediction type corresponding to index 0 or index 1 can be set. If the terminal is moving at a high speed and the prediction accuracy needs to be improved, the beam prediction type corresponding to index 3 or index 4 can be set. In addition, if the channel environment changes dynamically or the model prediction performance of the terminal is important, the beam prediction type corresponding to index 3 or index 4 can be set.

[0189] That is, the base station can transmit beam prediction type information to the terminal by considering not only the terminal's capabilities but also other factors such as the system environment.

[0190] FIG. 13 illustrates beam patterns according to one embodiment of the present disclosure.

[0191] Referring to FIG. 13, beam patterns according to one embodiment of the present disclosure are illustrated by a beam grid. Each unit grid included in the beam grid may correspond to beams that can be transmitted from an antenna of a base station. For example, 36 grids may each correspond to 36 beams. Shaded unit grids in the beam grid represent beams used when beam sweeping at the base station. Accordingly, the beam grid may represent beam patterns because it represents beams that are beam-swept at the base station.

[0192] Assuming that each unit grid included in the beam grid is assigned an index from 1 to 36 in order from left to right and top to bottom, the beam grid of pattern 0 can indicate that beams corresponding to indices 1, 3, 5, 13, 15, 17, 25, 27, and 29 are beam-swept.

[0193] The beam grid of pattern 1 may indicate that beams corresponding to indices 2, 4, 6, 14, 16, 18, 26, 28 and 30 are beam swept.

[0194] The beam grid of pattern 2 may indicate that beams corresponding to indices 7, 9, 11, 19, 21, 23, 31, 33, and 35 are beam swept.

[0195] The beam grid of pattern 3 can indicate that beams corresponding to indices 8, 10, 12, 20, 22, 24, 32, 34 and 36 are beam swept.

[0196] The beam grid pattern is not limited to the aforementioned patterns and may include various other patterns. That is, the number of beams swept by the base station and the index intervals may be subject to various variations. Furthermore, the number of unit grids included in the beam grid may be defined based on the number of beams that can be transmitted from the base station.

[0197] One embodiment of the present disclosure uses the term "beam grid" as information for indicating beams transmitted during beam sweeping from a base station. However, the beam grid may be a matrix or vector, or may be applied to various other data representation formats. In other words, the beam grid may comprehensively refer to information indicating one or more of a plurality of beams.

[0198] The aforementioned beam grid can correspond to the beam pattern information transmitted in operation 932 of FIG. 9. The base station can set multiple beam pattern information to the terminal. In this case, the base station can perform beam sweeping by using multiple beam patterns in a mixed manner according to the beam sweeping cycle or the base station's monitoring results. Accordingly, both the signal quality value measured before the beam pattern change and the signal quality value measured for the new beam pattern can be used for the prediction of the artificial intelligence model, thereby achieving performance gains.

[0199] FIG. 14 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0200] Referring to Figure 14, input information and output information of a terminal-side artificial intelligence model (1410) and a base station-side artificial intelligence model (1420) are shown.

[0201] In one embodiment, the terminal can receive beam pattern information from the base station to know the beams used in beam sweeping. When the base station performs beam sweeping at t= T0, the terminal can measure the signal quality of the beams used in beam sweeping and obtain signal quality measurement values ​​(e.g., RSRP value, etc.) for each beam. Then, the terminal can input the directly measured information, other information such as terminal location information and information (shape, direction, etc.) about the received beam into the terminal-side artificial intelligence model (1410). The terminal-side artificial intelligence model (1410) can predict the signal quality values ​​for other beams that have not been beam swept from the input information.

[0202] For example, if beams corresponding to indices 1, 3, 5, 13, 15, 17, 25, 27, and 29 in the beam grid are beam-swept at the base station, the terminal can measure and know the signal quality values ​​(e.g., RSRP values, etc.) of the beams corresponding to the corresponding index values. In addition, the terminal can generate signal quality prediction values ​​corresponding to other beams that are not beam-swept (e.g., beams corresponding to beam grid indices 8, 10, 12, 20, 22, 24, 32, 34, and 36) through the terminal-side artificial intelligence model (1410). That is, the terminal-side artificial intelligence model (1410) can generate prediction information on the signal quality of some beams among all beams.

[0203] The terminal may transmit the measured signal quality measurement value and / or the signal quality prediction value predicted by the terminal-side artificial intelligence to the base station, and the base station may use the received information as input to the base station-side artificial intelligence model (1420). In addition, the base station may generate information on the top K beams with the best prediction results.

[0204] In one embodiment, the terminal-side artificial intelligence model (1410) can generate signal quality prediction values ​​corresponding to some beams that are not beam swept at the base station.

[0205] FIG. 15 is a drawing for explaining a beam operation method according to one embodiment of the present disclosure.

[0206] Referring to Figure 15, input information and output information of a terminal-side artificial intelligence model (1510) and a base station-side artificial intelligence model (1520) are shown.

[0207] In one embodiment, when the base station performs beam sweeping at t = T0, the terminal can measure the signal quality of the beams used in the beam sweeping and obtain signal quality measurement values ​​(e.g., RSRP value, etc.) for each beam. Then, the terminal can input the directly measured information, as well as the terminal's location information, information about the received beam (shape, direction, etc.), etc., into the terminal-side artificial intelligence model (1510). The terminal-side artificial intelligence model (1510) can output information corresponding to the top Q beams predicted to have good signal quality from the input information.

[0208] For example, if beams corresponding to indices 1, 3, 5, 13, 15, 17, 25, 27, and 29 in the beam grid are beam-swept at the base station, the terminal can measure and know the signal quality values ​​(e.g., RSRP values, etc.) of the beams corresponding to the corresponding index values. In addition, the terminal can generate signal quality prediction values ​​corresponding to other beams that are not beam-swept (e.g., the remaining beams) through the terminal-side artificial intelligence model (1410). Accordingly, the terminal can generate information corresponding to the top Q beams based on the measured signal quality measurement values ​​and the signal quality prediction values ​​predicted by the artificial intelligence, and transmit the information to the base station. The base station can use the received information as an input to the base station-side artificial intelligence model (1520). In addition, the base station can generate information on the top K beams with the best prediction results. At this time, Q may be a value greater than K.

[0209] FIG. 16 illustrates beam prediction parameters corresponding to a beam prediction type according to one embodiment of the present disclosure.

[0210] The method and device according to one embodiment of the present disclosure can be used in combination with the aforementioned beam prediction types and parameters. The table in Fig. 16 illustrates an example of combining beam prediction types and parameters. This configuration information can be indicated from the base station to the terminal via MAC CE or RRC configuration. The table in Fig. 16 illustrates parameter setting combinations when the prediction type index is 4, i.e., when both the base station and the terminal use artificial intelligence models and the beam prediction type is in the time-space domain.

[0211] Referring to Figure 16, the "Prediction type" column indicates the beam prediction type as an index. The "Beam prediction parameter" column can be composed of the "Model" column, the "NW-configured input type" column, the "Beam pattern" column, and the "Reporting AI output type" column.

[0212] The "NW-configured input type" column indicates input information for the terminal-side AI model. The input information for the terminal-side AI model may include at least one of signal quality information (e.g., RSRP, RSSI), information about the received beam (e.g., beam shape, beam direction), information about the terminal's position, and / or information about the channel (e.g., CIR, SIR). The input information for the terminal-side AI model may be information corresponding to the beam prediction type index.

[0213] The "Beam pattern" column can indicate whether the beam pattern is fixed (Fixed) or changing (dynamic). The beam pattern type information can be information corresponding to the beam prediction type index.

[0214] "Reporting AI output type" may indicate output information of a terminal-side AI model. The output information of the terminal-side AI model may include at least one of intermediate information, pre-reconstructed signal quality information, and / or information corresponding to the top Q beams. The output information of the terminal-side AI model may be information corresponding to a beam prediction type index.

[0215] As shown in FIG. 16, a beam prediction type and a corresponding parameter information set can be transmitted from a base station to a terminal.

[0216] FIG. 17 illustrates an operation method of a base station according to one embodiment of the present disclosure.

[0217] The base station performing the operation of Fig. 17 may correspond to the base stations described in Figs. 1 to 16.

[0218] Operation 1710 may represent an operation in which a base station receives capability information of a terminal from a terminal. Operation 1710 may correspond to operation 930 of FIG. 9. The capability information of the terminal may include whether the terminal supports an artificial intelligence model, performance information of the terminal related to the use of the artificial intelligence model, capability information related to the artificial intelligence model, and / or expression format information regarding a supportable artificial intelligence model. In addition, the base station may additionally receive information from the terminal regarding beam prediction accuracy requirements based on UE mobility, intra-cell channel conditions, etc.

[0219] Operation 1720 represents an operation in which a base station determines configuration information for beam prediction based on capability information of a terminal and transmits the information to the terminal. The configuration information for beam prediction may include information on an artificial intelligence model on the terminal side. Operation 1720 may correspond to operation 932 of FIG. 9. In operation 1720, the base station may transmit configuration information for a beam prediction type and parameters to be used for beam prediction in the form of DCI (Downlink control information), RRC (Radio resource control) parameters, or MAC (Medium Access control) CE (Control element). In operation 1710, the base station may determine a prediction type and parameters based on the capability information of the terminal received from the terminal, beam prediction accuracy requirements according to the mobility of the terminal (UE mobility), and the channel environment within the cell.

[0220] The beam prediction-related parameters that the base station can set for the terminal may include at least one of parameters representing a terminal-side artificial intelligence model, parameters representing input information for the terminal-side artificial intelligence model, parameters representing a beam pattern, and / or parameters representing output information for the terminal-side artificial intelligence model. Descriptions of the relevant parameters are omitted as they are described above in FIG. 9.

[0221] Operation 1730 represents an operation in which the base station performs the first beam sweeping. The beam sweeping operation of the base station may correspond to the beam sweeping operation described in FIG. 4. Operation 1730 may correspond to operation 934 of FIG. 9. The base station may perform the beam sweeping operation according to the beam pattern.

[0222] Operation 1740 represents an operation in which the base station receives output information of the first artificial intelligence model for the first beam sweeping performed in operation 1730. Operation 1740 may correspond to operation 938 of FIG. 9. The first artificial intelligence model may represent a terminal-side artificial intelligence model. The terminal may use signal quality measurement information for the first beam sweeping, other beam information, terminal position information, etc. as inputs to drive the first artificial intelligence model and output information. The type of information output from the terminal-side artificial intelligence model and transmitted to the base station may be set by the base station to the terminal in operation 1720.

[0223] Operation 1750 represents an operation in which the base station generates information about at least one beam (or prediction information for beam selection) using the second artificial intelligence model based on the output information of the first artificial intelligence model. Operation 1750 may correspond to operation 940 of FIG. 9. The second artificial intelligence model may represent an artificial intelligence model on the base station side. The base station may operate the second artificial intelligence model using the output information of the first artificial intelligence model received from the terminal and / or other information generated by the base station as input. The second artificial intelligence model may generate predicted signal quality information (e.g., an RSRP value). For example, the second artificial intelligence model may generate predicted signal quality information for beams that are not beam-swept on the beam grid.

[0224] Operation 1760 represents an operation in which the base station determines the top K beams based on information about at least one beam (e.g., predicted signal quality information, predicted information for beam selection). Operation 1760 may correspond to operation 940 of FIG. 9. The base station may determine the top K beams based on predicted signal quality information for each beam.

[0225] Operation 1770 represents an operation in which the base station performs a second beam sweeping for the upper K beams determined in operation 1760. Operation 1770 may correspond to operation 942 of FIG. 9.

[0226] Operation 1780 represents the operation of the base station receiving beam information for the second beam sweep from the terminal. The terminal may select the best beam based on the measured signal quality value (e.g., RSRP) for the second beam sweep. The terminal may then transmit information (e.g., identifier information) regarding the best beam to the base station.

[0227] By receiving information about the best beam, the base station can transmit information using the best beam.

[0228] In one embodiment, the base station may receive output information of a third artificial intelligence model (on the terminal side) for second beam sweeping from the terminal, and use the output information of the third artificial intelligence model as input to a fourth artificial intelligence model (on the base station side) to generate information about at least one beam. Furthermore, the base station may determine R beams with superior signal quality based on the information about at least one beam. In other words, the base station and the terminal may repeatedly perform beam prediction operations by exchanging information with each other.

[0229] Fig. 18 illustrates an operation method of a terminal according to one embodiment of the present disclosure.

[0230] The terminal performing the operation of Fig. 18 may correspond to the terminal described in Figs. 1 to 17.

[0231] Operation 1810 represents an operation in which a terminal transmits capability information of the terminal to a base station. Operation 1810 may correspond to operation 930 of FIG. 9. The capability information of the terminal may include whether the terminal supports an artificial intelligence model, performance information of the terminal related to the use of the artificial intelligence model, capability information related to the artificial intelligence model, and / or expression format information regarding the supported artificial intelligence model. In addition, the terminal may additionally transmit information to the base station regarding beam prediction accuracy requirements based on UE mobility, intra-cell channel conditions, etc.

[0232] Operation 1820 represents an operation in which a terminal receives configuration information based on capability information of the terminal from a base station. Operation 1820 may correspond to operation 932 of FIG. 9. The base station may transmit configuration information on a beam prediction type and parameters to be used for beam prediction in the form of DCI (Downlink control information), RRC (Radio resource control) parameters, or MAC (Medium Access control) CE (Control element). The base station may determine a prediction type and parameters based on the capability information of the terminal received from the terminal in operation 1810, beam prediction accuracy requirements according to UE mobility, and channel environments within the cell.

[0233] The beam prediction-related parameters that the base station can set for the terminal may include at least one of parameters representing a terminal-side artificial intelligence model, parameters representing input information for the terminal-side artificial intelligence model, parameters representing a beam pattern, and / or parameters representing output information for the terminal-side artificial intelligence model. Descriptions of the relevant parameters are omitted as they are described above in FIG. 9.

[0234] Operation 1830 represents an operation in which the terminal receives the first beam sweep from the base station. Operation 1830 may correspond to operation 934 of FIG. 9. The terminal may measure signals for the beams used for the first beam sweep and generate signal quality information such as RSRP, RSSI, or RSRQ.

[0235] Operation 1840 represents an operation in which the terminal generates information based on a first artificial intelligence model based on information about the first beam sweeping (e.g., signal quality information). The first artificial intelligence model may represent a terminal-side artificial intelligence model and may be set to the terminal by the base station. The first artificial intelligence model may additionally receive position information of the terminal, beam information (shape, direction, etc.) or channel information in addition to signal quality information measured at the terminal, and output information. At this time, the type of information output from the first artificial intelligence model may be set to the terminal by the base station by operation 1820. The type of information output from the first artificial intelligence model may include intermediate information, pre-reconstructed signal quality prediction information, or information about the upper Q beams. The type of information output from the first artificial intelligence model is described in operation 932 of FIG. 9.

[0236] Operation 1850 represents the operation in which the terminal transmits information output from the first artificial intelligence model to the base station. Operation 1850 may correspond to operation 938 of FIG. 9. The type of information output from the first artificial intelligence model is described in operation 932 of FIG. 9.

[0237] Operation 1860 represents an operation in which a terminal receives a second beam sweeping from a base station. Operation 1860 may correspond to operation 942 of FIG. 9. The base station may operate a second artificial intelligence model based on the information received in operation 1850 and / or information of the base station itself. The second artificial intelligence model represents an artificial intelligence model on the base station side. In addition, the second artificial intelligence model may generate information on the upper K beams. When the base station performs the second beam sweeping using the upper K beams, the terminal receives the second beam sweeping from the base station.

[0238] Operation 1870 represents an operation in which the terminal generates information about beams for the second beam sweeping. The beams for the second beam sweeping may represent the upper K beams selected by the base station. The terminal may measure signal quality for the K beams and generate signal quality information. Operation 1870 may correspond to operation 944 of FIG. 9.

[0239] Operation 1880 represents an operation in which the terminal transmits information about one of the beams for the second beam sweeping to the base station. The terminal can generate signal quality information about the beams for the second beam sweeping and, based on this, transmit information (e.g., a beam identifier) ​​about the beam with the best signal quality to the base station. Accordingly, the base station can perform communication using the beam with the best signal quality. Operation 1880 may correspond to operation 946 of FIG. 9.

[0240] In one embodiment, the terminal may transmit information about the top P beams with the best signal quality (e.g., beam index information and signal quality information) to the base station. In this case, the base station may use the received information as input to a second artificial intelligence model to predict or select the top N beams. In addition, the base station may perform a beam sweeping operation again using the predicted top N beams, and receive information about the signal quality measured by the beam sweeping operation or the best beam from the terminal, thereby performing communication using the best beam.

[0241] According to various embodiments of the present disclosure, a base station can effectively operate beams using AI models on the base station and terminal sides. For example, the base station can perform beam sweeping on some beams without having to perform beam sweeping on all beams, and receive the resulting information to predict the optimal beam. At this time, the base station can reduce the computational burden by using AI models on both the terminal side and the AI ​​side to predict the optimal beam. Furthermore, the terminal side AI model can utilize its own information generated by the terminal as input, and the base station side AI model can utilize its own information generated by the base station as input. Therefore, the prediction accuracy of the AI ​​model can be improved, and the amount of information transmitted and received can be significantly reduced compared to transmitting the own information of the terminal or base station to one side and using it as input for the AI ​​model. Furthermore, the terminal can utilize the signal quality information measured at the terminal as input for the AI ​​model without a quantization process, thereby deriving improved results based on more accurate input values. In addition, according to an embodiment of the present disclosure, multiple beam sweeps can be performed over a predetermined period of time, and measurement information according to the passage of time can be utilized as input values ​​of an artificial intelligence model, thereby improving beam prediction accuracy in a moving environment of a terminal or an environmental change situation.

[0242] The various embodiments of the present disclosure and the terminology used therein are not intended to limit the technical features described in the present disclosure to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more items, unless the relevant context clearly indicates otherwise. In the present disclosure, each of the phrases "A or B," "at least one of A and B," "at least one of A or B," "A, B, or C," "at least one of A, B, and C," and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among the phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0243] The term "module" as used herein may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integrally formed component or a minimum unit or part of a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0244] Various embodiments of the present disclosure may be implemented as software (e.g., a program (140)) including one or more commands stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a device (e.g., a processor (e.g., processor (120) of an electronic device (101)) can call at least one command from among one or more commands stored from a storage medium and execute it. This enables the device to operate to perform at least one function according to the called at least one command. The one or more commands may include code generated by a compiler or code executable by an interpreter. A storage medium readable by the device may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain a signal (e.g., EM wave), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily in the storage medium.

[0245] According to one embodiment, the method according to various embodiments disclosed in the present disclosure may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a device-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0246] According to various embodiments, each component (e.g., a module or a program) of the described components may include one or more entities. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. A method performed by a base station in a wireless communication system, A step of receiving information indicating the capabilities of the terminal from the terminal; A step of transmitting setting information based on information indicating the capabilities of the terminal to the terminal; A step of transmitting a wireless signal to the terminal by performing a first beam sweeping; A step of receiving output information of a first artificial intelligence model related to the first beam sweeping based on the setting information from the terminal; A step of inputting the output information of the first artificial intelligence model into the second artificial intelligence model to generate prediction information for beam selection; and A step of determining n beams based on prediction information for the beam selection, method.

2. In claim 1, a step of performing a second beam sweeping on the n beams; and Further comprising a step of receiving information about a beam with the best signal quality among the n beams from the terminal. method.

3. In claim 1, Information indicating the capabilities of the above terminal is: Includes information on whether the above terminal supports an artificial intelligence model or performance information of the terminal related to the artificial intelligence model. The performance information of the terminal related to the above artificial intelligence model is classified based on the terminal's floating point operation per second (FLOPS) information. method.

4. In claim 1, The above setting information includes at least one of type information indicating a beam prediction method, input information for the first artificial intelligence model, and output information for the first artificial intelligence model. method.

5. In claim 4, The input information for the above first artificial intelligence model is: Including at least one of information indicating the quality of the signal for the first beam sweeping, information on the shape or direction of the beam received by the terminal, and information on the position of the terminal. method.

6. In claim 4, The output information for the above first artificial intelligence model is: Prediction information on the signal quality of some beams among all beams, prediction information corresponding to the top Q beams among all beams, and at least one of vector information, method.

7. In claim 1, The step of performing the above first beam sweeping performs a plurality of beam sweepings for a predetermined period of time, The step of determining the above n beams is: For multiple time points, n beams corresponding to each time point are determined. method.

8. As a base station of a wireless communication system, Transmitter and receiver; and Including a processor connected to the above transceiver, The above processor: An operation of receiving information indicating the capabilities of the terminal from the terminal, An operation of transmitting setting information based on information indicating the capabilities of the terminal to the terminal; An operation of transmitting a wireless signal to the terminal by performing a first beam sweeping; An operation of receiving output information of a first artificial intelligence model related to the first beam sweeping based on the setting information from the terminal; An operation of inputting the output information of the first artificial intelligence model into the second artificial intelligence model to generate prediction information for beam selection, and Based on the prediction information for the above beam selection, an operation of determining n beams is set to be performed. Base station.

9. In claim 8, The above processor, An operation of performing a second beam sweeping on the above n beams, It is configured to further perform an operation of receiving information about a beam with the best signal quality among the n beams from the terminal. Base station.

10. In claim 8, Information indicating the capabilities of the above terminal is: Includes information on whether the above terminal supports an artificial intelligence model or performance information of the terminal related to the artificial intelligence model. The performance information of the terminal related to the above artificial intelligence model is classified based on the terminal's floating point operation per second (FLOPS) information. Base station.

11. In claim 10, The above setting information includes at least one of type information indicating a beam prediction method, input information for the first artificial intelligence model, and output information for the first artificial intelligence model. Base station.

12. In claim 11, The input information for the above first artificial intelligence model is: Including at least one of information indicating the quality of the signal for the first beam sweeping, information on the shape or direction of the beam received by the terminal, and information on the position of the terminal. Base station.

13. In claim 11, The output information for the above first artificial intelligence model is: Prediction information on the signal quality of some beams among all beams, prediction information corresponding to the top Q beams among all beams, and at least one of vector information, Base station.

14. A method performed by a terminal in a wireless communication system, A step of transmitting information indicating the capabilities of the terminal to a base station; A step of receiving setting information based on information indicating the capability of the terminal from the base station; A step of receiving a signal for first beam swept beams from the base station; A step of generating signal quality information for the first beam swept beams; A step of generating output information of a first artificial intelligence model based on signal quality information for the first beam-swept beams; A step of transmitting the output information to the base station; A step of receiving a signal for the second beam swept beams from the above base station; and A step of transmitting information about a beam with the best signal quality among the second beam-swept beams to the base station, method.

15. As a user terminal of a wireless communication system, Transmitter and receiver; and Including a processor connected to the above transceiver, The above processor: An action of transmitting information indicating the capabilities of the terminal to a base station; An operation of receiving, from the base station, configuration information based on information indicating the capabilities of the terminal; An operation of receiving a signal for first beam swept beams from the base station; An operation of generating signal quality information for the first beam swept beams; An operation of generating output information of a first artificial intelligence model based on signal quality information for the first beam-swept beams; An operation of transmitting the output information to the above base station; An operation of receiving a signal for second beam swept beams from the base station; and Including an operation of transmitting information about a beam with the best signal quality among the second beam-swept beams to the base station. User terminal.

Images