Method and device for transmitting precoding matrix in wireless communication system

Abstract

An operation method of a terminal, according to embodiments of the present disclosure, comprises the steps of: receiving, from a base station, configuration information for monitoring the transmission performance of a precoding matrix; receiving, from the base station, a reference signal for measuring a channel state; generating a precoding matrix on the basis of the reference signal; generating compressed information corresponding to the precoding matrix, on the basis of the precoding matrix and the configuration information; generating performance information for the compressed information; and reporting the performance information to the base station, wherein the configuration information includes monitoring type information indicating at least one among codebook-based and artificial intelligence model-based monitoring schemes.

Description

Method and device for transmitting a precoding matrix in a wireless communication system

[0001] The present disclosure relates to a method and apparatus for processing information in a wireless communication system, and to a monitoring technique for transmitting a precoding matrix from a network entity (e.g., a base station, etc.) 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 may provide a method and device for reducing overhead for transmitting a precoding matrix in a communication system such as 5G, 5G-Advanced, and 6G, and improving communication performance between networks and terminals.

[0008] A method performed by a network entity (base station) in a wireless communication system, comprising: a step of transmitting configuration information for monitoring transmission performance of a precoding matrix to a terminal; a step of transmitting a reference signal for measuring a channel state to the terminal; and a step of receiving a report on monitoring performed based on the configuration information from the terminal, wherein the configuration information includes monitoring type information indicating at least one of a monitoring method based on a codebook or an artificial intelligence model.

[0009] A method of operating a terminal according to embodiments of the present disclosure, comprising: a step of receiving configuration information for monitoring transmission performance of a precoding matrix from a base station; a step of receiving a reference signal for measuring a channel state from the base station; a step of generating a precoding matrix based on the reference signal; a step of generating compressed information corresponding to the precoding matrix based on the precoding matrix and the configuration information; a step of generating performance information for the compressed information; and a step of reporting the performance information to the base station, wherein the configuration information includes monitoring type information indicating at least one of a monitoring method based on a codebook or an artificial intelligence model.

[0010] The method and device according to embodiments of the present disclosure can provide an operation capable of effectively transmitting a precoding matrix in a wireless communication system.

[0011] Specifically, the method and apparatus according to one embodiment of the present disclosure can adaptively transmit information about a precoding matrix by monitoring implicit information for transmitting the precoding matrix, thereby reducing overhead in a transmission and reception process.

[0012] 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.

[0013] The features and advantages of the embodiments of the present disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings.

[0014] FIG. 1 illustrates a wireless communication system according to embodiments of the present disclosure.

[0015] FIG. 2 is a drawing for explaining the structure of a terminal according to embodiments of the present disclosure.

[0016] FIG. 3 is a diagram illustrating the structure of a network entity according to embodiments of the present disclosure.

[0017] FIG. 4 is a diagram for explaining a method of transmitting precoding matrix information based on a codebook according to embodiments of the present disclosure.

[0018] FIG. 5 is a diagram for explaining a method of transmitting precoding matrix information based on an artificial intelligence model according to embodiments of the present disclosure.

[0019] FIG. 6 is a diagram illustrating a method for monitoring transmission performance of precoding matrix information according to embodiments of the present disclosure.

[0020] FIG. 7 is a diagram illustrating a method for monitoring the transmission performance of precoding matrix information according to embodiments of the present disclosure based on an artificial intelligence model.

[0021] FIG. 8 is a diagram illustrating a method for monitoring transmission of a precoding matrix in a user equipment according to embodiments of the present disclosure.

[0022] FIG. 9 is a diagram illustrating a method for monitoring transmission of a precoding matrix based on an artificial intelligence model in a user equipment according to embodiments of the present disclosure.

[0023] FIG. 10 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0024] FIG. 11 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0025] FIG. 12 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0026] FIG. 13 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0027] FIG. 14 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0028] FIG. 15 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0029] FIG. 16 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0030] FIG. 17 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0031] FIG. 18 is a diagram for explaining a terminal's monitoring operation for a precoding matrix according to embodiments of the present disclosure.

[0032] FIG. 19 is a diagram for explaining a base station monitoring operation for a precoding matrix according to embodiments of the present disclosure.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] Hereinafter, various embodiments of the present disclosure will be described.

[0038] Meanwhile, the core of AI-based beam management is that the base station performs SSB (synchronization signal and physical broadcast channel block) 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 terminal as inputs to the AI ​​model. The base station can predict the RSRP values ​​corresponding to the untransmitted beams 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 terminal can report to the base station the beam corresponding to the largest RSRP value among the k received beams.

[0039] 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.

[0040] 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.

[0041] The method and device according to embodiments 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.

[0042] 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.

[0043] FIG. 1 illustrates a wireless communication system according to embodiments of the present disclosure.

[0044] 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).

[0045] 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)', 'evolved Node B (eNB)', 'next generation node B (gNB)', '5G node (5th generation node)', 'wireless point', 'transmission / reception point (TRP)', or other terms having equivalent technical meanings.

[0046] 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.'

[0047] 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.

[0048] 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).

[0049] 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).

[0050] Figure 2 is a drawing for explaining the structure of a terminal according to embodiments.

[0051] Referring to FIG. 2, a terminal (200) according to embodiments may include a transceiver (transmitting and receiving unit) (210), a memory (220), and / or a processor (230). In the present disclosure, the terminal (200) is described as including the transceiver (210), the memory (220), and / or the processor (230), but 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).

[0052] According to embodiments, 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.

[0053] According to embodiments, 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.

[0054] 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.

[0055] According to embodiments, the transceiver (210) may transmit or receive a signal 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).

[0056] According to embodiments, the transceiver (210) may be referred to as a UE transmitter or a UE receiver.

[0057] According to embodiments, the transceiver (210) may transmit a signal to a base station (e.g., base station (110) of FIG. 1) or a network entity (e.g., access and mobility management function (AMF) entity) or receive a signal from the base station or the network entity. In embodiments, the transmitted or received signal may include a control signal and data.

[0058] According to embodiments, 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 embodiments, 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.

[0059] According to embodiments, 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.

[0060] According to embodiments, 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.

[0061] 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.

[0062] The terminal (200) of the present disclosure may correspond to the first terminal (120) and / or the second terminal (130) of FIG. 1.

[0063] FIG. 3 is a diagram for explaining the structure of a network entity according to embodiments.

[0064] Referring to FIG. 3, a network entity (300) according to embodiments may include a transceiver (transmitter / receiver) (310), a memory (320), and / or a processor (330). Although the network entity (300) is described in the present disclosure as including the transceiver (310), the memory (320), and / or the processor (330), this is merely an example. For example, the network entity (300) may further include other components in addition to the transceiver (310), the memory (320), and the processor (330). The network entity (300) may represent network functions included in a base station or other core network.

[0065] According to embodiments, the transceiver (310), memory (320), and processor (330) may be implemented or formed as separate chips, respectively. 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.

[0066] According to embodiments, 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.

[0067] 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.

[0068] According to embodiments, the transceiver (310) may transmit or receive a signal 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).

[0069] According to embodiments, the transceiver (310) may be referred to as a network entity transmitter or a network entity receiver.

[0070] According to embodiments, the transceiver (310) may transmit a signal to the terminal (200) or receive a signal from the terminal (200). In embodiments, the transmitted or received signal may include a control signal and data.

[0071] According to embodiments, the memory (320) may include programs and data necessary for the operations of the network entity (300). For example, the memory (320) may be a non-transitory memory, and a program stored in the non-transitory memory may be organically combined with a hardware configuration (e.g., a processor (330) or a transceiver (310)) of the network entity (300). The memory (320) may store control information or data including a signal acquired by the network entity (300). In embodiments, 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.

[0072] According to embodiments, 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.

[0073] According to embodiments, the processor (330) may control a series of processes performed by the network entity (300). For example, the transceiver (310) may receive a data signal including control information transmitted by the network entity. The processor (330) may process the received control signal and data signal.

[0074] The term "processor" in the present disclosure may be replaced with various terms referring to a configuration that executes or performs operations of a network entity (300). For example, the term "processor" may be replaced with a controller or a computing unit.

[0075] The network entity (300) of the present disclosure may correspond to the base station (110) of FIG. 1.

[0076] The devices described in FIGS. 2 and 3 may correspond to devices of a transmitter or receiver. A terminal or network entity according to embodiments of the present disclosure may be a transmitter if it is a transmitter, and may be a receiver if it is a receiver.

[0077] Hereinafter, the transmitter and receiver may each refer to the terminals or network entities described in FIGS. 1 to 3 above. When describing downlink signals, the network entity will be the transmitter and the terminal will be the receiver, and when describing uplink signals, the terminal will be the transmitter and the network entity will be the receiver.

[0078] Meanwhile, 5G New Radio (NR) communication systems must be able to freely reflect the diverse needs of service providers and users, requiring support for services that simultaneously satisfy diverse requirements. Services being considered for 5G communication systems include enhanced Mobile Broadband (eMBB), massive Machine Type Communication (mNTC), and Ultra Reliability Low Latency Communication (URLLC).

[0079] eMBB aims to provide data transmission rates that are significantly higher than those supported by existing LTE, LTE-A, or LTE-Pro. For example, in a 5G communication system, eMBB may aim to provide a peak data rate of 20 Gbps in the downlink and a peak data rate of 10 Gbps in the uplink from the perspective of a single base station. Furthermore, a 5G communication system may aim to provide both the peak data rate and the increased user-perceived data rate for the terminal. To meet these requirements, improvements in various transmission and reception technologies, including further enhanced multi-antenna (MIMO; Multi-Input Multi-Output) transmission technology, are required. A 5G communication system can meet the data transmission rates required by the 5G communication system by using a frequency bandwidth wider than 20 MHz in the 3-6 GHz or 6 GHz or higher frequency bands.

[0080] mMTC can be considered to support application services such as the Internet of Things (IoT) in 5G communication systems. To efficiently provide the IoT, mMTC requires supporting large-scale terminal connections within a cell, improved terminal coverage, enhanced battery life, and reduced terminal costs. The IoT requires the ability to support a large number of terminals (e.g., 1,000,000 terminals / km2) within a cell, as it provides communication capabilities through the attachment of various sensors and devices. Furthermore, due to the nature of the service, terminals supporting mMTC are likely to be located in shadow areas, such as basements, beyond cell coverage. Therefore, mMTC requires broader coverage compared to other services provided by 5G communication systems. Furthermore, terminals supporting mMTC must be inexpensive, and since frequent battery replacement is difficult, a very long battery life, such as 10 to 15 years, is required.

[0081] Finally, URLLC refers to cellular-based wireless communication services used for specific mission-critical purposes. Examples include remote control of robots or machinery, industrial automation, unmanned aerial vehicles (UAVs), remote health care, and emergency alerts. Therefore, URLLC communications must offer extremely low latency and high reliability. For example, URLLC-enabled services must meet air interface latency requirements of less than 0.5 milliseconds and may also require a packet error rate (PER) of less than 10^-5. Therefore, for URLLC-enabled services, 5G systems must provide a smaller Transmit Time Interval (TTI) than other services, and design considerations may require the allocation of extensive resources in the frequency band to ensure communication link reliability.

[0082] Satisfying these diverse services often requires beam management and support for multiple frequency bands. In these situations, diverse channel conditions can arise across frequency bands and beams, and resource consumption for terminals performing channel estimation and reporting to the base station is significant. To address this, discussions on CSI Compression, which compresses channel state information (CSI) from terminals and transmits it to the base station, began in 3GPP Release 18.

[0083] In conventional 5G communication systems, the channel state recovered through the codebook-based CSI report may experience information loss due to the quantization problem of the codebook during the process of transmitting the estimated channel H.

[0084] Embodiments of the present disclosure relate to a method and apparatus for calculating precoding matrix information to be used by a base station from an estimated channel after a terminal performs channel estimation, and transmitting the calculated precoding matrix information to the base station with minimal loss.

[0085] FIG. 4 is a diagram for explaining a method of transmitting precoding matrix information based on a codebook according to embodiments of the present disclosure.

[0086] The terminal and base station for performing the operation described in Fig. 4 may correspond to the terminal of Fig. 2 and the network entity of Fig. 3, respectively.

[0087] In Fig. 4, in order for a base station (NW) (420) to know the downlink channel estimated by a terminal (user equipment, UE) (410), the terminal (410) can transmit channel information to the base station (420). Specifically, when the base station (420) transmits a CSI-reference signal (CSI-RS) to the terminal (410), the terminal (410) performs channel estimation based on the received CSI-RS and estimates the estimated channel ( ) can be obtained. Then, the terminal (410) can obtain the precoding matrix V based on the EVD or SVD technique for the estimated channel. In addition, the terminal (410) can transmit to the base station an index (e.g., PMI) of a codebook corresponding to a value most similar to the precoding matrix V calculated based on a predefined codebook. The base station (420) can derive a value most similar to the precoding matrix V from the predefined codebook based on the received PMI (precoding matrix indicator) and apply the value as the precoding matrix.

[0088] Referring to FIG. 4, operations performed by a terminal (UE) (410) to transmit precoding matrix information to a base station (NW) (420) are described.

[0089] In operation 412, the terminal (410) estimates the channel state based on the CSI-RS (Channel state information - reference signal) received from the base station, thereby estimating the estimated channel ( ) can be created.

[0090] In operation 414, the terminal (410) can perform pre-processing on the estimated channel based on an eigenvalue decomposition (EVD) or singular value decomposition (SVD) technique.

[0091] In operation 416, the terminal (410) can generate a precoding matrix V based on the preprocessing result of operation 414.

[0092] In operation 418, the terminal (410) can transmit to the base station, based on a predefined codebook, an index corresponding to a value most similar to V for the precoding matrix V obtained in operation 416, in the form of a precoding matrix index (PMI). The base station (420) that receives the PMI can derive a value similar to V from a predefined codebook using the PMI, and can transmit data by applying the derived value as a precoding matrix.

[0093] Based on operations 412 to 418, the user terminal (410) may transmit information about the precoding matrix (e.g., PMI) to the base station. However, the precoding matrix restored by the base station (420) based on the information about the precoding matrix (e.g., PMI) may differ from the precoding matrix generated by the user terminal (410).

[0094] That is, by transmitting the index value of the codebook instead of directly transmitting the precoding matrix value calculated by the terminal (410), there is an advantage of being able to transmit less data, but performance degradation may occur due to the difference between the value actually calculated by the terminal and the value restored by the base station. On the other hand, if the number of bits used by the terminal for CSI reporting increases in order to transmit a more accurate precoding matrix value, overhead may increase significantly.

[0095] FIG. 5 is a diagram for explaining a method of transmitting precoding matrix information based on an artificial intelligence model according to embodiments of the present disclosure.

[0096] The terminal and base station performing the operations described in FIG. 5 may correspond to the terminal and network entity of FIG. 2 and FIG. 3, respectively.

[0097] Referring to FIG. 5, the terminal can compress the precoding matrix V based on artificial intelligence (AI), machine learning (ML), or deep learning to generate a low-dimensional vector z (latent vector), and transmit the vector z to the base station. The base station can restore the original V from the compressed vector z and apply it as a precoding matrix.

[0098] The terminal may include an encoder for compressing a precoding matrix V to generate z, and the base station may include a decoder for reconstructing V from z. The encoder and decoder may be configured as corresponding artificial intelligence models.

[0099] Referring to FIG. 5, in operation 510, the terminal estimates the channel state based on the CSI-RS (Channel state information - reference signal) received from the base station, thereby estimating the estimated channel ( ) can be created.

[0100] In operation 520, the terminal may perform pre-processing on the estimated channel based on an eigenvalue decomposition (EVD) or singular value decomposition (SVD) technique.

[0101] In operation 530, the terminal can generate a precoding matrix V based on the preprocessing result of operation 520, and input the precoding matrix V to an encoder to generate a compressed vector z. At this time, the encoder can include an artificial intelligence (or, artificial intelligence) model based on machine learning or deep learning.

[0102] In operation 540, the terminal can transmit the z vector as feedback to the base station (BS).

[0103] In operation 550, the base station inputs the z vector received from the terminal into the decoder and restores the V( ) can be generated. At this time, the decoder may include an artificial intelligence (or, artificial intelligence) model based on machine learning or deep learning. The decoder is an artificial intelligence model corresponding to the encoder of the terminal, and can output a restored precoding matrix using the z vector, which is the output of the encoder, as input.

[0104] According to the aforementioned operations 510 to 550, the terminal compresses the precoding matrix using an AI model and transmits it to the base station, and the base station can restore the compressed precoding matrix using the AI ​​model. However, in the case of using an AI model in this way, performance may deteriorate due to environments that change over time, such as the occurrence of unexpected events, the performance fluidity of the AI ​​model, and changes in input / output data. Therefore, monitoring of the AI ​​model is required, and FIGS. 6 and 7 describe a monitoring method.

[0105] FIG. 6 is a diagram illustrating a method for monitoring transmission performance of precoding matrix information according to embodiments of the present disclosure.

[0106] The terminal and base station performing the operations described in FIG. 6 may correspond to the terminal and network entity of FIG. 2 and FIG. 3, respectively.

[0107] Referring to FIG. 6, the terminal (610) can quantize the precoding matrix V and transmit the quantized precoding matrix V_q to the base station (620). In addition, the terminal (610) can transmit the vector z, which is the compressed precoding matrix V, to the base station (620) as in the embodiment of FIG. 5. The base station (620) can restore the received vector z based on an artificial intelligence model (decoder) to V( ) and the quantized precoding matrix V_q received from the terminal (610) can be compared to perform monitoring.

[0108] The terminal (610) can periodically transmit the quantized precoding matrix V_q to the base station (620), and the base station (620) can restore V( based on the received quantized precoding matrix V_q and the artificial intelligence model. ) can be used to monitor the transfer performance of the precoding matrix.

[0109] FIG. 7 is a diagram illustrating a method for monitoring the transmission performance of precoding matrix information according to embodiments of the present disclosure based on an artificial intelligence model.

[0110] The terminal and base station performing the operations described in FIG. 7 may correspond to the terminal and network entity of FIG. 2 and FIG. 3, respectively.

[0111] Referring to FIG. 7, the terminal (710) can perform monitoring using a proxy model (714). For example, the proxy model (714) is a model that simulates a decoder model of a base station, and the terminal (710) can perform monitoring by comparing the original precoding matrix V with the value output from the proxy model (714).

[0112] In various embodiments, the proxy model (714) may receive an original precoding matrix V and a compressed vector z as input and predict (or output) a value (e.g., squared generalized cosine similarity, SGCS, etc.) representing the difference between the reconstructed precoding matrix and the original precoding matrix. That is, the proxy model (714) may include an artificial intelligence model trained to produce a value representing the difference between the reconstructed precoding matrix and the original precoding matrix. The terminal (710) may transmit the value output from the proxy model (714) to the base station. The base station may determine the transmission performance of the precoding matrix based on the received value.

[0113] In various embodiments, the proxy model for monitoring the artificial intelligence model (encoder and / or decoder) of the terminal (710) may be a model received from a base station or a model built into the terminal (710).

[0114] FIG. 8 is a diagram illustrating a method for monitoring transmission of a precoding matrix in a user equipment according to embodiments of the present disclosure.

[0115] The terminal and base station performing the operations described in FIG. 8 may correspond to the terminal and network entity of FIG. 2 and FIG. 3, respectively.

[0116] The terminal (810) can monitor performance by deriving a PMI using a predefined codebook based on the precoding matrix V (see FIG. 4). For example, the terminal (810) can perform monitoring using a specific metric function.

[0117] Referring to FIG. 8, the terminal (810) can monitor the difference between the original precoding matrix and the restored precoding matrix based on a specific metric function. The metric function can output a value indicating restoration performance based on the original precoding matrix value and the PMI value. The terminal (810) can transmit the output value of the metric function to the base station (820), and the base station (820) can use the received value to determine performance.

[0118] In operation 812, the terminal (810) estimates the channel state based on the CSI-RS (Channel state information - reference signal) received from the base station, thereby estimating the estimated channel ( ) can be created.

[0119] In operation 814, the terminal (810) may perform pre-processing on the estimated channel based on an eigenvalue decomposition (EVD) or singular value decomposition (SVD) technique.

[0120] In operation 815, the terminal (810) can generate a precoding matrix V based on the preprocessing result of operation 814.

[0121] In operation 816, the terminal (810) can calculate an index corresponding to a value similar to V as a precoding matrix indicator (PMI) based on a predefined codebook for the precoding matrix V obtained in operation 815. In addition, the terminal (810) can also calculate a plurality of PMIs corresponding to a plurality of values ​​similar to the precoding matrix V.

[0122] In operation 818, the terminal (810) can calculate a value representing the performance of the PMI calculated by applying the precoding matrix V and PMI to the metric function. The value representing the performance of the PMI may be a value representing the similarity between the original precoding matrix V and the precoding matrix restored by the PMI. The terminal (810) transmits a monitoring result including performance information on the PMI to the base station (820), and the base station can use the received monitoring result to change or maintain existing setting information.

[0123] In various embodiments, the terminal (810) can calculate values ​​representing restoration performance corresponding to a plurality of PMIs. For example, the terminal (810) can derive a plurality of PMIs corresponding to values ​​close to the original precoding matrix based on the codebook, and can transmit performance values ​​corresponding to the plurality of PMIs to the base station (820). For example, the terminal (810) can derive PMI 1, PMI 2, and PMI 3 corresponding to V1, V2, and V3, which are close to the original precoding matrix, respectively, and can calculate performance values ​​corresponding to each PMI and transmit them to the base station (820). Therefore, the terminal (810) can reduce overhead because it does not need to transmit separate PMI values ​​and quantized precoding matrices generated for monitoring to the base station.

[0124] FIG. 9 is a diagram illustrating a method for monitoring transmission of a precoding matrix based on an artificial intelligence model in a user equipment according to embodiments of the present disclosure.

[0125] The terminal and base station performing the operations described in FIG. 9 may correspond to the terminal and network entity of FIG. 2 and FIG. 3, respectively.

[0126] The terminal (910) can monitor performance by deriving PMI through a predefined codebook based on the precoding matrix V. For example, the terminal (910) can perform monitoring using an artificial intelligence model.

[0127] Referring to FIG. 9, the terminal (910) can monitor the similarity between the original precoding matrix and the restored precoding matrix based on an artificial intelligence model. The artificial intelligence model for monitoring can output performance information based on the original precoding matrix values ​​and the PMI values. The terminal (910) can transmit the output of the artificial intelligence model to the base station (920), and the base station (920) can utilize the received information to change or maintain existing configuration information.

[0128] In operation 912, the terminal (910) estimates the channel state based on the CSI-RS (Channel state information - reference signal) received from the base station, thereby estimating the estimated channel ( ) can be created.

[0129] In operation 914, the terminal (910) may perform pre-processing on the estimated channel based on an eigenvalue decomposition (EVD) or singular value decomposition (SVD) technique.

[0130] In operation 915, the terminal (910) can generate a precoding matrix V based on the preprocessing result of operation 914.

[0131] In operation 916, the terminal (910) can calculate an index corresponding to a value similar to the precoding matrix V as a precoding matrix indicator (PMI) based on a predefined codebook for the precoding matrix V obtained in operation 915. In addition, the terminal (910) can calculate a plurality of PMIs corresponding to a plurality of values ​​similar to the precoding matrix V.

[0132] In operation 918, the terminal (910) can calculate a value representing the performance of the PMI calculated by applying the precoding matrix V and PMI to the artificial intelligence model. The value representing the performance of the PMI may be a value representing the similarity between the original precoding matrix V and the precoding matrix restored by the PMI. The terminal (910) transmits a monitoring result including performance information on the PMI to the base station (920), and the base station can change or maintain existing setting information by utilizing the received monitoring result. The artificial intelligence model can receive the precoding matrix V and / or PMI as input, and output a value (e.g., SGCS, etc.) representing the similarity between the restored precoding matrix corresponding to the PMI and the original precoding matrix.

[0133] In various embodiments, the terminal (910) can calculate values ​​representing restoration performance corresponding to a plurality of PMIs. For example, the terminal (910) can derive a plurality of PMIs corresponding to values ​​close to the original precoding matrix based on the codebook, and can transmit performance values ​​corresponding to the plurality of PMIs to the base station (920). For example, the terminal (910) can derive PMI 1, PMI 2, and PMI 3 corresponding to V1, V2, and V3, which are close to the original precoding matrix, respectively, and can calculate performance values ​​corresponding to each PMI and transmit the performance values ​​to the base station (920).

[0134] In various embodiments, the terminal (910) may receive an artificial intelligence model for monitoring from the base station (920). The artificial intelligence model for monitoring may output performance information corresponding to the PMI.

[0135] The base station (920) can perform monitoring by receiving the output of an artificial intelligence model that is not disclosed to other vendors and terminal manufacturers, and overhead can be reduced by not having to receive separate PMI and quantized precoding matrix from the terminal.

[0136] Meanwhile, the codebook according to the embodiments of the present disclosure is 3 rd The codebook may include a codebook defined in the 3rd Generation Partnership Project (3GPP) standard document. For example, in the case of an eType II codebook, the terminal can derive a PMI corresponding to a precoding matrix from the codebook based on multiple parameter combinations (PCs). Depending on the parameter combination, the terminal can transmit PMIs with different resolutions to the base station. The higher the resolution of the PMI to be transmitted, the larger the bit size for the terminal to feed back information, and the higher the accuracy of the transmitted information. Examples of bit sizes according to parameter combinations are shown in [Table 1] below.

[0137]

[0138] Referring to Table 1, when the codebook type is eType II, the bit size for the terminal to transmit PMI varies depending on the parameter combination (PC). A larger bit size indicates an increase in the resolution of the transmitted PMI, and as the PMI resolution increases, the precoding matrix restored based on the PMI can more closely resemble the original precoding matrix.

[0139] However, a larger bit size indicates that a PMI composed of many beams is transmitted to the base station, and a larger number of beams may indicate that information is transmitted and received using beams with a narrow range. Therefore, when the mobility of the terminal is high, using a high-resolution PMI may result in a large error between the timing at which the base station sends the CSI-RS and the channel condition measured by the terminal, which may result in performance degradation. In other words, there may be cases where a PMI with a small bit size and low resolution shows better performance than a PMI with a large bit size. In addition, a large bit size may increase overhead.

[0140] The device and method according to embodiments of the present disclosure can determine and transmit a parameter combination for generating PMI to a terminal (when the codebook type is eType II). For example, the base station can transmit the parameter combination for generating PMI to the terminal through an RRC configuration message or an RRC reconfiguration message. In various embodiments, when the codebook type is Type I or Type II, the base station can transmit information corresponding to the type of the codebook, such as a codebook mode or number of beams, to the terminal. The terminal can generate PMI based on information (such as a parameter combination, codebook mode, or number of beams) received from the base station depending on the type of the codebook.

[0141] The method and device according to embodiments of the present disclosure describe a content in which a base station transmits configuration information including a parameter combination to a terminal, assuming that the codebook type is eType II. However, if the codebook type is Type I or Type II, the base station can transmit information or parameters (codebook mode or number of beams) corresponding to each codebook type to the terminal, and the technical idea applied to embodiments in which the codebook type is eType II can also be applied to other codebook types. The parameter combination, codebook mode, or beam number information, etc. referenced to generate a PMI according to each codebook type can be referred to as reference information.

[0142] The base station transmits reference information corresponding to the codebook type to the terminal, and the terminal can perform a monitoring operation based on the received reference information (e.g., parameter combination when the codebook type is eType II). When the codebook type is eType II, the base station receives a monitoring result corresponding to the parameter combination from the terminal, and can determine an appropriate parameter combination based on the received result. For example, the base station can determine a parameter combination that has similar performance or lower overhead between the parameter combination currently applied by the terminal and the monitored parameter combination. A specific threshold may be considered when the base station determines the parameter combination.

[0143] The terminal can monitor performance for each parameter combination and transmit the monitoring results to the base station. The base station can determine a parameter combination based on the monitoring results and transmit the determined parameter combination to the terminal by including it in the configuration information. The terminal can apply the determined parameter combination to calculate a PMI based on the codebook and transmit the PMI to the base station to convey precoding matrix information.

[0144] Meanwhile, in the case of precoding matrix compression and restoration using an artificial intelligence model, the vector z in which the precoding matrix is ​​compressed can be transmitted from the terminal to the base station. At this time, the terminal can use various artificial intelligence models that output vectors of different resolutions based on the configuration information received from the base station. Therefore, the similarity of the restored precoding matrix may vary depending on the resolution of the vector z, and the performance of the vector z with a high resolution may be poor depending on the mobility of the terminal. The device and method according to the embodiments of the present disclosure can secure effective performance adaptively according to the situation by monitoring the performance of each artificial intelligence model and determining an appropriate artificial intelligence model.

[0145] The devices and methods according to embodiments of the present disclosure can also perform performance monitoring for codebook-based PMI and performance monitoring for artificial intelligence models simultaneously. In this case, the most appropriate precoding matrix transmission method can be determined based on the overall monitoring results.

[0146] Embodiments of the present disclosure can improve the performance degradation caused by narrow beam widths due to increased PMI resolution in environments with high terminal mobility. Furthermore, embodiments of the present disclosure have the effect of increasing precoding matrix transmission performance between terminals and base stations and reducing overhead.

[0147] Below, signaling information between a base station and a terminal for performing monitoring and result reporting operations according to embodiments of the present disclosure is described. That is, the signaling information described may represent configuration information for monitoring transmission performance regarding a precoding matrix.

[0148] [Table 2] below may indicate monitoring types as monitoring configuration information according to embodiments of the present disclosure. The base station may transmit configuration information for monitoring transmission performance regarding the precoding matrix to the terminal by transmitting an RRC configuration or RRC reconfiguration message.

[0149]

[0150] Referring to Table 2, index 0 may indicate monitoring performance for PMI derived from a codebook, index 1 may indicate monitoring performance for compressed vectors derived from an artificial intelligence model, and index 2 may indicate monitoring performance for compressed information (PMI or compressed vectors) derived from both a codebook and an artificial intelligence model. Index 3 may indicate that monitoring for transmitting a precoding matrix is ​​not performed.

[0151] Although not shown in Table 2, the information indicating the monitoring type may indicate the type of codebook. For example, the information indicating the monitoring type may indicate the type of codebook as Type I, Type II, or eType II.

[0152] [Table 3] below may represent monitoring configuration information according to embodiments of the present disclosure. [Table 3] may represent additional configuration information according to the signaling information of [Table 2] described above. The base station may transmit configuration information for monitoring transmission performance regarding the precoding matrix to the terminal by transmitting an RRC configuration or RRC reconfiguration message.

[0153]

[0154] Table 3 contains information indicating the parameter combination set to monitor and the codebook-based monitoring type when the monitoring type index in Table 2 is 0 or 2.

[0155] Additionally, Table 3 may include information indicating the AI ​​model to monitor (AI model set to monitor) when the monitoring type index of Table 2 is 1 or 2.

[0156] The information indicating the parameter combination(s) to be monitored (parameter combination set to monitor) may indicate at least one parameter combination among a plurality of parameter combinations. For example, the information indicating the parameter combination(s) to be monitored may indicate the first parameter combination and the eighth parameter combination among the first to eighth parameter combinations. The parameter combination(s) to be monitored may be determined by the base station or the terminal.

[0157] Information indicating the codebook-based monitoring type can indicate the performance output type for the monitoring results.

[0158] Index 1 may indicate that performance is calculated based on the squared generalized cosine similarity (SGCS) value. For example, the terminal may calculate a PMI corresponding to the indicated parameter combination and, based on the calculated PMI, calculate the difference between the reconstructed precoding matrix and the original precoding matrix as the SGCS value. The closer the calculated SGCS value is to 1, the more similar the reconstructed precoding matrix is ​​to the original precoding matrix.

[0159] Index 2 may indicate that monitoring performance is calculated based on the signal-to-interference plus noise ratio (SINR). For example, the terminal may calculate the PMI corresponding to the indicated parameter combination and, based on the calculated PMI, calculate the received SINR when using the restored precoding matrix.

[0160] Index 3 may indicate that performance is calculated based on the mean squared error (MSE). For example, the terminal may calculate the PMI corresponding to the indicated parameter combination and calculate the difference between the reconstructed precoding matrix and the original precoding matrix based on the calculated PMI as the MSE value.

[0161] Index 4 may indicate that monitoring performance is calculated using an AI model. For example, a terminal may input PMI into an AI model for monitoring and produce an output value representing performance. The AI ​​model may correspond to the proxy model in operation 918 of FIG. 9.

[0162] Codebook-based monitoring types can be used to calculate performance values ​​using a metric function, such as PMI, or to calculate monitoring performance values ​​based on artificial intelligence received from a base station. These values ​​can be derived from other calculation methods, including SGCS and MSE. In other words, codebook-based monitoring types are not limited to those shown in [Table 3].

[0163] The information indicating the AI ​​model to be monitored (AI model set to monitor) may indicate which AI model among multiple AI models will perform monitoring. For example, the information indicating the AI ​​model to be monitored may indicate at least one AI model among the first through Nth AI models. The AI ​​model to be monitored may be determined by the base station. The terminal may receive the AI ​​model to be monitored from the base station or maintain its own AI model.

[0164] Meanwhile, although not shown in Table 3, when the monitoring type information indicates a codebook (index 0, 2), information for indicating the type of codebook to be monitored may be added to the configuration information. For example, the type information of the codebook to be monitored may indicate a first type codebook, a second type codebook, and a third type codebook, each with a separate index. In other words, configuration information that can indicate various types of codebooks may be included. In addition, reference information for generating PMI to be monitored may be indicated for each type of codebook. For example, when a first type codebook (e.g., Type I) is indicated, reference information (e.g., codebook mode set to monitor) indicating a codebook mode (at least one of mode 1 or mode 2) may be included as detailed configuration information therefor. In addition, when a second type codebook (e.g., Type II) is indicated, reference information (e.g., numberOfBeams set to monitor) indicating the number of beams (at least one of 2 to 4) may be included as detailed configuration information therefor. In addition, when a third type of codebook (e.g., eType II) is indicated, reference information indicating parameter combination(s) (at least one of 1 to 8) as detailed configuration information for the same may be included (PC set to monitor). That is, reference information indicating a target to be monitored may be included depending on the type of codebook. The type of codebook may include not only Type I, Type II, or eType II defined in the 3GPP standard specification document, but also other types, and Table 3 may further include reference information indicating a target to be monitored depending on the type of each codebook.

[0165] [Table 4] below may represent monitoring configuration information according to embodiments of the present disclosure. The base station may transmit configuration information for monitoring transmission performance regarding the precoding matrix to the terminal by transmitting an RRC configuration or RRC reconfiguration message.

[0166]

[0167] Referring to Table 4, when the Monitoring type index is 0, 1, or 2, that is, when monitoring the transmission performance of the precoding matrix, additional information can be displayed.

[0168] Entity information can indicate whether the entity determining changes to existing configuration information is a terminal or a base station. For example, entity information can indicate an entity capable of determining changes to parameter combinations (or codebook modes, number of beams, etc.) for calculating PMI based on a codebook. Furthermore, entity information can indicate an entity capable of determining changes to an AI model for compressing a precoding matrix.

[0169] When entity information indicates a terminal, the terminal can decide to change existing configuration information if the monitoring results satisfy the conditions received from the base station. The conditions for deciding to change existing configuration information can be referenced in Table 5 below. Furthermore, the terminal can determine whether to change existing configuration information based on not only the monitoring results but also the number of feedback bits. For example, if the performance of the existing configuration and the monitored configuration are similar, and the number of feedback bits of the monitored configuration is significantly lower, resulting in less overhead, the terminal can decide to change the existing configuration.

[0170] When entity information indicates a base station, the base station can decide to change existing configuration information based on performance information contained in monitoring reports received from terminals. For base stations, existing configuration information can be changed by comprehensively considering factors that increase overall throughput, not just the conditions shown in Table 5.

[0171] Event-based triggering information may indicate whether a monitoring operation or a reporting operation according to embodiments of the present disclosure is triggered based on a specific event. If the aforementioned entity information indicates a terminal, the index of the event-based triggering information may be 0. If a monitoring operation or a reporting operation is triggered based on a specific event, the monitoring or reporting operation of the terminal may be performed at the request of the base station. In this case, the request of the base station may be performed through L1 / L2 signaling, such as DCI or MAC CE signaling.

[0172] Monitoring period information may indicate a reporting period. The reporting period may include periodic, aperiodic, and semi-persistent. If the reporting period indicates periodic or semi-persistent, a field indicating the period may be required. If the reporting period indicates aperiodic or semi-persistent, low-layer signaling may be required to trigger an action. Low-layer signaling may include downlink control information (DCI) or a MAC control element (CE). If the monitoring reporting action according to embodiments of the present disclosure is triggered based on a specific event, the reporting period information may be omitted.

[0173] In various embodiments of the present disclosure, monitoring period information may indicate the period of monitoring operations separately from reporting. For example, a terminal may periodically perform monitoring operations separately from reporting operations, and may also perform reporting operations only when certain conditions are met.

[0174] Subband information can indicate a monitoring and reporting method for subbands. Index 0 can indicate that the terminal reports the average performance of the monitoring results performed for each subband. For example, the terminal can receive CSI-RS for the first subband and the second subband, perform monitoring based on the configuration information, and calculate a value (e.g., SGSC, MSE, etc.) representing the precoding matrix restoration performance corresponding to the calculated PMI (in the case of codebook-based) or compressed vector (in the case of AI model-based). In addition, the terminal can report the average performance value for the monitoring calculated for each subband to the base station.

[0175] Index 1 may indicate that the terminal reports performance for each subband based on the monitoring results. For example, the terminal may receive CSI-RS for the first and second subbands, perform monitoring based on configuration information, and calculate a value (e.g., SGSC, MSE, etc.) representing the precoding matrix restoration performance corresponding to the calculated PMI (in the case of codebook-based) or compressed vector (in the case of AI model-based). Furthermore, the terminal may separately report the calculated performance values ​​for each subband to the base station.

[0176] Index 2 may indicate that the terminal reports monitoring performance for each subband selected from among multiple subbands. For Index 2, information indicating at least one subband among the multiple subbands may be further included.

[0177] In the case of monitoring operations according to embodiments of the present disclosure, unlike the typical case where a terminal reports PMI to a base station, monitoring may not be performed for all subbands. That is, since monitoring operations do not need to be performed for all subbands, information regarding monitoring operations related to subbands, such as the subband information in Table 4, may be included in the configuration information.

[0178] Layer information can indicate which layer will perform monitoring and reporting. Layers can correspond to receiving antennas on the terminal side. Depending on the indicated layer information, the terminal can monitor and report the results for signals received from all antennas, or it can report the monitoring results for a subset of antennas.

[0179] Specifically, index 0 may indicate that the terminal reports the average of the monitoring results for each layer (or receiving antenna). Index 1 may indicate that the terminal reports the monitoring results for each layer separately. Index 2 may indicate that the terminal reports the monitoring results for each indicated (or selected) layer separately. In the case of index 2, information for indicating at least one layer among the multiple layers may be further included in the configuration information.

[0180] In the case of monitoring operations according to embodiments of the present disclosure, unlike the typical case where a terminal reports PMI to a base station, monitoring may not be performed for all layers. That is, since monitoring operations do not need to be performed for all layers, information regarding monitoring operations related to layers, such as the layer information in Table 4, may be included in the configuration information.

[0181] Report offset information can indicate reporting of monitoring results from a point in time offset from the reporting time of the terminal. For example, index 0 can indicate reporting of monitoring results from a point in time A offset prior to the reporting time of the terminal. Index 1 can indicate reporting of the average of monitoring results from a point in time A offset prior to the reporting time of the terminal. In the case of index 0 or index 1, the configuration information (e.g., RRC reconfiguration) can additionally include time information indicating the A offset.

[0182] [Table 5] below may represent monitoring configuration information according to embodiments of the present disclosure. The base station may transmit configuration information for monitoring transmission performance regarding the precoding matrix to the terminal by sending an RRC configuration or RRC reconfiguration message. Table 5 may indicate conditions that trigger the terminal's reporting operation when event-based monitoring result reporting is instructed. Table 5 may also indicate conditions for the terminal to change existing configuration information when the terminal is an entity capable of changing existing configuration information.

[0183]

[0184] Referring to Table 5, index 0 indicates a condition in which the current SGCS value (SGCS_present) corresponding to the PMI transmitted from the terminal to the base station is lower than an arbitrary threshold value.

[0185] Index 1 may indicate a condition in which the SGCS value (SGCS_monitored) corresponding to the PMI monitored by the terminal is greater than a specific offset or more than the current SGCS value (SGCS_present) of the PMI transmitted to the base station.

[0186] Index 2 indicates a condition where the SGCS value (SGCS_monitored) corresponding to the PMI monitored at the terminal is greater than an arbitrary threshold value.

[0187] Index 3 may indicate a condition in which the SGCS value (SGCS_present) corresponding to the PMI transmitted from the terminal to the base station is less than the first threshold value (Threshold 1), and the SGCS value (SGCS_monitored) corresponding to the PMI calculated by monitoring at the terminal is greater than the second threshold value (Threshold 2).

[0188] In Table 5, the conditions corresponding to indices 0 to 3 are conditions set based on SGCS values, but in embodiments of the present disclosure, monitoring report trigger conditions can be set based on MSE, SINR, or other performance evaluation values.

[0189] The configuration information in Table 5 may further include information regarding the duration for which the aforementioned conditions must persist. For example, Table 5 may include information regarding the duration for which a condition must persist for a reporting action to be triggered at the terminal. In this case, the terminal may report to the base station if any one of the conditions at index 0 to index 3 is satisfied and the condition persists for a predetermined period of time.

[0190] Additionally, the configuration information in Table 5 can indicate information indicating the number of times monitoring using CSI-RS is performed.

[0191] The threshold, offset, and time information required to determine whether the conditions in Table 5 are satisfied may be additionally included in the monitoring configuration information.

[0192] The information set in Tables 1 to 5 described above can be expressed in the form of a bitmap. The information set in Tables 1 to 5 can be included in an RRC configuration or RRC reconfiguration message. Additionally, the information can correspond to fields added within the CSI report configuration information (CSI report config).

[0193] Below, based on the aforementioned setup information, a monitoring method for transmitting a precoding matrix is ​​described.

[0194] FIG. 10 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0195] The terminal and base station performing the operations described in Fig. 10 may correspond to the terminal and network entity of Figs. 2 and 3, respectively.

[0196] The embodiment of FIG. 10 may represent an embodiment in which monitoring based on a codebook is performed periodically.

[0197] Referring to FIG. 10, in operation 1030, a terminal (1020) receives an RRC reconfiguration from a base station (1010). At this time, the RRC reconfiguration may include configuration information regarding a codebook for transmitting a precoding matrix. For example, the RRC reconfiguration may indicate the type information of the codebook and a parameter combination that the terminal uses to calculate a PMI based on the codebook. More specifically, when the codebook is of the eType II type, the RRC reconfiguration may indicate any one of parameter combination 1 to parameter combination 8. Alternatively, when the codebook is of the Type I type, the RRC reconfiguration may indicate any one of a plurality of codebook modes. The terminal may calculate a PMI based on the indicated content and transmit it to the base station, thereby transmitting precoding matrix information to the base station.

[0198] In various embodiments of the present disclosure, the type information of the codebook may indicate any one of Type I, Type II, or eType II defined in the 3GPP standard document.

[0199] In operation 1032, the terminal (1020) may receive an RRC reconfiguration including monitoring configuration information from the base station (1010). The monitoring configuration information may include signaling information set in Tables 1 to 5 described above. The terminal (1020) may perform a monitoring operation to transmit precoding matrix information based on the received monitoring configuration information.

[0200] In Fig. 10, operations 1030 and 1032 are described separately, but operations 1030 and 1032 may be a single operation. For example, the terminal (1020) receives RRC reconfiguration from the base station (1010), and the RRC reconfiguration may include codebook-related configuration information for transmitting a precoding matrix and monitoring configuration information related thereto.

[0201] Actions 1034 to 1040 represent actions in which the terminal (1020) performs monitoring and results reporting based on monitoring setting information.

[0202] Operation 1034 represents an operation in which a terminal (1020) receives a CSI (channel state indicator)-RS (reference signal) from a base station (1010). At this time, the CSI-RS received by the terminal (1020) is not a signal additionally transmitted by the base station (1010) for the monitoring process, and may represent a signal typically transmitted by the base station (1010) for communication between the terminal (1020) and the base station (1010).

[0203] Operation 1036 may represent an operation in which the terminal (1020) calculates a PMI for the CSI-RS received in operation 1034 based on the monitoring configuration information received in operation 1032. Specifically, the terminal (1020) may calculate a PMI corresponding to each combination based on the parameter combinations (or codebook modes, number of beams) to be monitored indicated in the monitoring configuration information. For example, if parameter combination 1 and parameter combination 3 are indicated as parameter combinations to be monitored in the monitoring configuration information, the terminal (1020) may calculate PMI 1 based on parameter combination 1 and may calculate PMI 3 based on parameter combination 3.

[0204] Operation 1038 may represent an operation in which the terminal (1020) calculates performance for the PMI value calculated in operation 1036. The terminal (1020) may calculate performance based on codebook-based monitoring type information indicated in the monitoring configuration information. For example, the terminal (1020) may calculate performance for the PMI value based on the SGCS value, or based on MSE, SINR, or an artificial intelligence model, according to the content indicated in the monitoring configuration information.

[0205] Operation 1040 may represent an operation in which the terminal (1020) reports the performance values ​​calculated in operation 1038, i.e., the monitoring results, to the base station (1010). Operation 1040 may be performed based on the instructions in the monitoring configuration information. For example, if the terminal (1020) is configured to perform event-based reporting, the terminal (1020) may perform reporting when the configured conditions are satisfied.

[0206] Operation 1042 represents an operation in which the base station (1010) determines whether to change the existing codebook setting based on the report result received in operation 1040. For example, if the performance of PMI 3 calculated by monitored parameter combination 3 is superior to the performance of PMI 1 calculated by parameter combination 1 currently applied by the terminal (1020), the base station (1010) may decide to change the codebook setting information so that the terminal (1020) applies parameter combination 3.

[0207] In various embodiments of the present disclosure, the decision as to whether to translate existing configuration information may be performed at the terminal or base station based on monitoring configuration information.

[0208] Operation 1044 represents an operation in which the base station (1010) transmits an RRC reconfiguration including the codebook configuration information changed in operation 1042 to the terminal (1020). Thereafter, the terminal (1020) can calculate a PMI based on the changed codebook configuration information and transmit the PMI to the base station (1010). For example, the terminal (1020) can perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, generate a PMI by applying a changed parameter combination based on the generated precoding matrix and the codebook, and transmit the generated PMI to the base station (1010). The base station (1010) can restore the precoding matrix based on the received PMI and the codebook, and transmit data using the restored precoding matrix.

[0209] FIG. 11 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0210] The terminal and base station performing the operations described in Fig. 11 may correspond to the terminal and network entity of Figs. 2 and 3, respectively.

[0211] The embodiment of FIG. 11 may represent an embodiment in which monitoring based on an artificial intelligence model is performed periodically.

[0212] Referring to FIG. 11, in operation 1130, a terminal (1120) receives an RRC reconfiguration from a base station (1110). At this time, the RRC reconfiguration may include configuration information regarding an artificial intelligence model for transmitting a precoding matrix. For example, the RRC reconfiguration may indicate an artificial intelligence model (or encoder) that the terminal will use to produce a vector z that compresses the precoding matrix. More specifically, the RRC reconfiguration may indicate any one of a plurality of artificial intelligence models capable of compressing the precoding matrix. The terminal may use the indicated artificial intelligence model to compress the precoding matrix, produce a vector z, and transmit the vector z to the base station. The base station may input the received vector z into a corresponding artificial intelligence model (or decoder) to restore the precoding matrix.

[0213] In operation 1132, the terminal (1120) may receive an RRC reconfiguration including monitoring configuration information from the base station (1110). The monitoring configuration information may include signaling information set in Tables 1 to 5 described above. The terminal (1120) may perform a monitoring operation to transmit precoding matrix information based on the received monitoring configuration information.

[0214] In Fig. 11, operations 1130 and 1132 are described separately, but operations 1130 and 1132 may be a single operation. For example, the terminal (1120) receives RRC reconfiguration from the base station (1110), and the RRC reconfiguration may include configuration information related to an artificial intelligence model for transmitting a precoding matrix and monitoring configuration information related thereto.

[0215] Actions 1134 to 1140 represent actions in which the terminal (1120) performs monitoring and results reporting based on monitoring setting information.

[0216] Operation 1134 represents an operation in which a terminal (1120) receives a CSI (channel state indicator)-RS (reference signal) from a base station (1110). At this time, the CSI-RS received by the terminal (1120) is not a signal separately transmitted by the base station (1110) for the monitoring process, and may represent a signal normally transmitted by the base station (1110) for communication between the terminal (1120) and the base station (1110).

[0217] Operation 1136 may indicate an operation in which the terminal (1120) compresses a precoding matrix using an artificial intelligence model indicated in the monitoring configuration information received in operation 1132 to produce a vector. Specifically, the terminal (1120) may produce a vector (s) by compressing a precoding matrix using at least one artificial intelligence model (s) among a plurality of artificial intelligence models indicated in the monitoring configuration information. For example, if Model 1 and Model 3 are indicated as artificial intelligence models to be monitored in the monitoring configuration information, the terminal (1120) may obtain Vector 1 output from Model 1 and Vector 3 output from Model 3.

[0218] Operation 1138 may indicate an operation in which the terminal (1120) calculates the performance of an artificial intelligence model indicated in the monitoring configuration information. For example, the terminal (1120) may calculate the performance of the artificial intelligence model using a proxy model (see related content of FIG. 7). The values ​​output from the proxy model may be expected values ​​such as SGSC and MSE, or simple vector values ​​that do not represent any meaning.

[0219] Operation 1140 may represent an operation in which the terminal (1120) reports the performance values ​​calculated in operation 1138, i.e., the monitoring results, to the base station (1110). Operation 1140 may be performed based on the instructions in the monitoring configuration information. For example, if the terminal (1120) is configured to perform event-based reporting, the terminal (1120) may perform reporting when the configured conditions are satisfied.

[0220] Operation 1142 represents an operation in which the base station (1110) determines whether to change the existing settings based on the report results received in operation 1140. For example, if the performance of vector 3 calculated by the monitored artificial intelligence model 3 is superior to the performance of vector 1 calculated by the artificial intelligence model 1 currently being applied by the terminal (1120), the base station (1110) may decide to change the setting information so that the terminal (1120) applies artificial intelligence model 3.

[0221] In various embodiments of the present disclosure, the decision as to whether to translate existing configuration information may be performed at the terminal or base station based on monitoring configuration information.

[0222] Operation 1144 represents an operation in which the base station (1110) transmits an RRC reconfiguration including the configuration information changed in operation 1142 to the terminal (1120). Thereafter, the terminal (1120) can calculate a vector using an artificial intelligence model based on the changed configuration information and transmit the calculated vector to the base station (1110). For example, the terminal (1120) can perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, input the generated precoding matrix to the artificial intelligence model (or encoder) to generate a compressed vector z, and transmit the generated vector to the base station (1110). The base station (1110) can input the received vector to the artificial intelligence model (e.g., decoder) corresponding to the encoder to restore the precoding matrix, and transmit data using the restored precoding matrix.

[0223] FIG. 12 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0224] The terminal and base station performing the operations described in Fig. 12 may correspond to the terminal and network entity of Figs. 2 and 3, respectively.

[0225] The embodiment of FIG. 12 may represent an embodiment in which monitoring is performed periodically based on an artificial intelligence model and codebook. That is, FIG. 12 may represent an embodiment for the monitoring type corresponding to index 2 of Table 2 described above.

[0226] Referring to FIG. 12, in operation 1230, a terminal (1220) receives an RRC reconfiguration from a base station (1210). At this time, the RRC reconfiguration may include configuration information regarding an artificial intelligence model or codebook for transmitting a precoding matrix. For example, the RRC reconfiguration may indicate an artificial intelligence model (or encoder) that the terminal will use to derive a vector z that compresses the precoding matrix. More specifically, the RRC reconfiguration may indicate any one of a plurality of artificial intelligence models capable of compressing the precoding matrix. The terminal may use the indicated artificial intelligence model to compress the precoding matrix, derive the vector z, and transmit the vector z to the base station. The base station may input the received vector z into a corresponding artificial intelligence model (or decoder) to restore the precoding matrix. In addition, for example, the RRC reconfiguration may indicate a parameter combination that the terminal uses to derive a PMI based on a codebook. More specifically, if the codebook is of type eType II, the RRC reconfiguration may indicate any one of parameter combinations 1 to 8. Alternatively, if the codebook is of type Type I, the RRC reconfiguration may indicate any one of multiple codebook modes. The terminal may transmit precoding matrix information to the base station by calculating and transmitting a PMI based on the indicated content to the base station.

[0227] In various embodiments of the present disclosure, the type information of the codebook may indicate any one of Type I, Type II, or eType II defined in the 3GPP standard document.

[0228] In operation 1232, the terminal (1220) may receive an RRC reconfiguration including monitoring configuration information from the base station (1210). The monitoring configuration information may include signaling information set in Tables 1 to 5 described above. The terminal (1220) may perform a monitoring operation to transmit precoding matrix information based on the received monitoring configuration information.

[0229] In Fig. 12, operations 1230 and 1232 are described separately, but operations 1230 and 1232 may be a single operation. For example, the terminal (1220) receives RRC reconfiguration from the base station (1210), and the RRC reconfiguration may include artificial intelligence model-related configuration information or codebook-related configuration information for transmitting a precoding matrix, along with monitoring configuration information related thereto.

[0230] Actions 1234 to 1240 represent actions in which the terminal (1220) performs monitoring and results reporting based on monitoring setting information.

[0231] Operation 1234 represents an operation in which a terminal (1220) receives a CSI (channel state indicator)-RS (reference signal) from a base station (1210). At this time, the CSI-RS received by the terminal (1220) is not a signal separately transmitted by the base station (1210) for the monitoring process, and may represent a signal typically transmitted by the base station (1210) for communication between the terminal (1220) and the base station (1210).

[0232] Operation 1236 may indicate an operation in which the terminal (1220) compresses a precoding matrix using an artificial intelligence model indicated in the monitoring configuration information received in operation 1232 to produce a vector, and calculates a PMI based on the indicated parameter combination. Specifically, the terminal (1220) may produce a vector(s) by compressing a precoding matrix using at least one artificial intelligence model(s) among a plurality of artificial intelligence models indicated in the monitoring configuration information. For example, if Model 1 and Model 3 are indicated as artificial intelligence models to be monitored in the monitoring configuration information, the terminal (1220) may obtain a vector 1 output from Model 1, and obtain a vector 3 output from Model 3. In addition, the terminal (1220) may calculate a PMI corresponding to each combination based on the parameter combination(s) to be monitored (or, codebook mode, number of beams) indicated in the monitoring configuration information. For example, if parameter combination 1 and parameter combination 3 are indicated as parameter combinations to be monitored in the monitoring setting information, the terminal (1220) can calculate PMI 1 based on parameter combination 1 and can calculate PMI 3 based on parameter combination 3.

[0233] The 1238 operation may indicate an operation in which the terminal (1220) calculates the performance for the artificial intelligence model and the calculated PMI indicated in the monitoring configuration information. For example, the terminal (1220) may calculate the performance for the artificial intelligence model using a proxy model (see related content of FIG. 7). The values ​​output from the proxy model may be expected values ​​such as SGSC, MSE, etc., or may be simple vector values ​​that do not indicate meaning. In addition, the terminal (1220) may calculate the performance based on the codebook-based monitoring type information indicated in the monitoring configuration information. For example, the terminal (1220) may calculate the performance for the PMI value based on the SGCS value, or based on the MSE, SINR, or artificial intelligence model, according to the content indicated in the monitoring configuration information.

[0234] Operation 1240 may represent an operation in which the terminal (1220) reports the performance values ​​calculated in operation 1238, i.e., the monitoring results, to the base station (1210). Operation 1240 may be performed based on the instructions in the monitoring configuration information. For example, if the terminal (1220) is configured to perform event-based reporting, the terminal (1220) may perform reporting when the configured conditions are satisfied.

[0235] Operation 1242 represents an operation in which the base station (1210) determines whether to change the existing settings based on the report results received in operation 1240. For example, if the performance of the monitored artificial intelligence model or parameter combination is superior to the performance of the currently applied artificial intelligence model or parameter combination (or codebook mode, number of beams, etc.) of the terminal (1220), the base station (1210) may determine to change the setting information so that the terminal (1220) applies the superior artificial intelligence model or parameter combination (or codebook mode, number of beams, etc.).

[0236] In various embodiments of the present disclosure, the decision as to whether to translate existing configuration information may be performed at the terminal or base station based on monitoring configuration information.

[0237] Operation 1244 represents an operation in which the base station (1210) transmits an RRC reconfiguration including the configuration information changed in operation 1242 to the terminal (1220). Thereafter, the terminal (1220) can transmit information about a precoding matrix to the base station based on the changed configuration information. For example, the terminal (1220) can perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, input the generated precoding matrix to an artificial intelligence model (or encoder) to generate a compressed vector z, and transmit the generated vector to the base station (1210). The base station (1210) can input the received vector to an artificial intelligence model (e.g., decoder) corresponding to the encoder to restore the precoding matrix, and transmit data using the restored precoding matrix. Additionally, for example, the terminal (1220) may perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, generate a PMI by applying a changed parameter combination based on the generated precoding matrix and the codebook, and transmit the generated PMI to the base station (1210). The base station (1210) may restore the precoding matrix based on the received PMI and the codebook, and transmit data using the restored precoding matrix.

[0238] FIG. 13 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0239] The terminal and base station performing the operations described in Fig. 13 may correspond to the terminal and network entity of Figs. 2 and 3, respectively.

[0240] The embodiment of FIG. 13 may represent an embodiment in which monitoring and / or reporting operations are performed in an aperiodic or semi-persistent manner.

[0241] Referring to FIG. 13, in operation 1330, a terminal (1320) receives an RRC reconfiguration from a base station (1310). At this time, the RRC reconfiguration may include configuration information (e.g., codebook type information) regarding an artificial intelligence model or codebook for transmitting a precoding matrix. For example, the RRC reconfiguration may indicate an artificial intelligence model (or encoder) that the terminal will use to produce a vector z that compresses the precoding matrix. More specifically, the RRC reconfiguration may indicate any one of a plurality of artificial intelligence models capable of compressing the precoding matrix. The terminal may use the indicated artificial intelligence model to compress the precoding matrix, produce a vector z, and transmit the vector z to the base station. The base station may input the received vector z into a corresponding artificial intelligence model (or decoder) to restore the precoding matrix. Additionally, for example, RRC reconfiguration can indicate a parameter combination used by the terminal to calculate PMI based on a codebook. More specifically, if the codebook is of type eType II, RRC reconfiguration can indicate any one of parameter combinations 1 to 8. Alternatively, if the codebook is of type I, RRC reconfiguration can indicate any one of multiple codebook modes. The terminal can calculate PMI based on the indicated content and transmit it to the base station, thereby transmitting precoding matrix information to the base station.

[0242] In various embodiments of the present disclosure, the type information of the codebook may indicate any one of Type I, Type II, or eType II defined in the 3GPP standard document.

[0243] In operation 1332, the terminal (1320) may receive an RRC reconfiguration including monitoring configuration information from the base station (1310). The monitoring configuration information may include signaling information set in Tables 1 to 5 described above. The terminal (1320) may perform a monitoring operation to transmit precoding matrix information based on the received monitoring configuration information.

[0244] In Fig. 13, operations 1330 and 1332 are described separately, but operations 1330 and 1332 may be a single operation. For example, the terminal (1320) receives RRC reconfiguration from the base station (1310), and the RRC reconfiguration may include artificial intelligence model-related configuration information or codebook-related configuration information for transmitting a precoding matrix and monitoring configuration information related thereto.

[0245] Operation 1334 represents an operation in which the base station (1310) requests the terminal (1320) to monitor and report on the transmission of the precoding matrix. That is, if the period information included in the monitoring configuration information in operation 1332 indicates Aperiodic or semi-persistent, monitoring or result reporting may be performed at the request of the base station (1310). Operation 1334 may be performed based on low-layer signaling, an uplink control information (UCI) message. If the period information is Aperiodic, the monitoring or reporting operation may be performed once at the request of the base station (1310). If the period information is semi-persistent, the monitoring or reporting operation may be performed repeatedly after the request of the base station (1310).

[0246] Operation 1336 may represent a monitoring and reporting operation performed between a base station (1310) and a terminal (1320). Operation 1336 may correspond to operations 1034 to 1040 of FIG. 10, operations 1134 to 1140 of FIG. 11, and operations 1234 to 1240 of FIG. 12.

[0247] Operation 1338 represents an operation in which the base station (1310) determines whether to change the existing settings based on the report results received in operation 1336. For example, if the performance of the monitored artificial intelligence model or parameter combination is superior to the performance of the currently applied artificial intelligence model or parameter combination (or codebook mode, number of beams, etc.) of the terminal (1320), the base station (1310) may determine to change the setting information so that the terminal (1320) applies the superior artificial intelligence model or parameter combination (or codebook mode, number of beams, etc.).

[0248] In various embodiments of the present disclosure, the decision as to whether to translate existing configuration information may be performed at the terminal or base station based on monitoring configuration information.

[0249] Operation 1340 represents an operation in which the base station (1310) transmits an RRC reconfiguration including the configuration information changed in operation 1338 to the terminal (1320). Thereafter, the terminal (1320) can transmit information about a precoding matrix to the base station based on the changed configuration information. For example, the terminal (1320) can perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, input the generated precoding matrix to an artificial intelligence model (or encoder) to generate a compressed vector z, and transmit the generated vector to the base station (1310). The base station (1310) can input the received vector to an artificial intelligence model (e.g., decoder) corresponding to the encoder to restore the precoding matrix, and transmit data using the restored precoding matrix. Additionally, for example, the terminal (1320) may perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, generate a PMI by applying a changed parameter combination based on the generated precoding matrix and the codebook, and transmit the generated PMI to the base station (1310). The base station (1310) may restore the precoding matrix based on the received PMI and the codebook, and transmit data using the restored precoding matrix.

[0250] FIG. 14 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0251] The terminal and base station performing the operations described in Fig. 14 may correspond to the terminal and network entity of Figs. 2 and 3, respectively.

[0252] The embodiment of FIG. 14 may represent an embodiment in which monitoring and / or reporting operations are performed on an event basis. The embodiment of FIG. 14 may be implemented in combination with the embodiments of FIGS. 10 to 13.

[0253] Referring to FIG. 14, in operation 1430, a terminal (1420) receives an RRC reconfiguration from a base station (1410). At this time, the RRC reconfiguration may include configuration information (e.g., codebook type information) regarding an artificial intelligence model or codebook for transmitting a precoding matrix. For example, the RRC reconfiguration may indicate an artificial intelligence model (or encoder) that the terminal will use to produce a vector z that compresses the precoding matrix. More specifically, the RRC reconfiguration may indicate any one of a plurality of artificial intelligence models capable of compressing the precoding matrix. The terminal may use the indicated artificial intelligence model to compress the precoding matrix, produce a vector z, and transmit the vector z to the base station. The base station may input the received vector z into a corresponding artificial intelligence model (or decoder) to restore the precoding matrix. Additionally, for example, RRC reconfiguration can indicate a parameter combination used by the terminal to calculate PMI based on a codebook. More specifically, if the codebook is of type eType II, RRC reconfiguration can indicate any one of parameter combinations 1 to 8. Alternatively, if the codebook is of type I, RRC reconfiguration can indicate any one of multiple codebook modes. The terminal can calculate PMI based on the indicated content and transmit it to the base station, thereby transmitting precoding matrix information to the base station.

[0254] In various embodiments of the present disclosure, the type information of the codebook may indicate any one of Type I, Type II, or eType II defined in the 3GPP standard document.

[0255] In operation 1432, the terminal (1420) may receive an RRC reconfiguration including monitoring configuration information from the base station (1410). The monitoring configuration information may include signaling information set in Tables 1 to 5 described above. The terminal (1420) may perform a monitoring operation for transmitting precoding matrix information based on the received monitoring configuration information. In the embodiment of FIG. 14, the monitoring configuration information may indicate that the monitoring or reporting operation is triggered based on an event. That is, the embodiment of FIG. 14 may represent a case where the index of event-based triggering in Table 4 is indicated as 0. In addition, the monitoring configuration information may include measurement configuration information (see Table 5) indicating a condition for performing the monitoring or reporting operation.

[0256] In Fig. 14, operations 1430 and 1432 are described separately, but operations 1430 and 1432 may be a single operation. For example, the terminal (1420) receives RRC reconfiguration from the base station (1410), and the RRC reconfiguration may include artificial intelligence model-related configuration information or codebook-related configuration information for transmitting a precoding matrix and monitoring configuration information related thereto.

[0257] Actions 1434 to 1442 represent actions in which the terminal (1420) performs monitoring and results reporting based on monitoring setting information.

[0258] Operation 1434 represents an operation in which a terminal (1420) receives a CSI (channel state indicator)-RS (reference signal) from a base station (1410). At this time, the CSI-RS received by the terminal (1420) is not a signal separately transmitted by the base station (1410) for the monitoring process, and may represent a signal typically transmitted by the base station (1410) for communication between the terminal (1420) and the base station (1410).

[0259] Operation 1436 may indicate an operation in which the terminal (1420) compresses a precoding matrix using an artificial intelligence model indicated in the monitoring configuration information received in operation 1432 to produce a vector, or calculates a PMI based on an indicated parameter combination (or codebook mode, number of beams, etc.). Specifically, the terminal (1420) may produce a vector(s) by compressing a precoding matrix using at least one artificial intelligence model(s) among a plurality of artificial intelligence models indicated in the monitoring configuration information. For example, if Model 1 and Model 3 are indicated as artificial intelligence models to be monitored in the monitoring configuration information, the terminal (1420) may obtain a vector 1 output from Model 1 and obtain a vector 3 output from Model 3. In addition, the terminal (1420) may calculate a PMI corresponding to each combination based on the parameter combination(s) to be monitored (or codebook mode, number of beams) indicated in the monitoring configuration information. For example, if parameter combination 1 and parameter combination 3 are indicated as parameter combinations to be monitored in the monitoring setting information, the terminal (1420) can calculate PMI 1 based on parameter combination 1 and can calculate PMI 3 based on parameter combination 3.

[0260] The 1438 operation may indicate an operation in which the terminal (1420) calculates performance for an artificial intelligence model or calculated PMI indicated in the monitoring configuration information. For example, the terminal (1420) may calculate performance for an artificial intelligence model using a proxy model (see related content of FIG. 7). The values ​​output from the proxy model may be expected values ​​such as SGSC or MSE, or may be simple vector values ​​that do not indicate meaning. In addition, the terminal (1420) may calculate performance based on codebook-based monitoring type information indicated in the monitoring configuration information. For example, the terminal (1420) may calculate performance for a PMI value based on an SGCS value, or based on MSE or SINR, or an artificial intelligence model, according to the content indicated in the monitoring configuration information.

[0261] Operation 1440 indicates an operation in which the terminal (1420) identifies that a condition for reporting monitoring performance results has been satisfied. In other words, operation 1440 may indicate that a monitoring reporting operation has been triggered. In operation 1440, the terminal (1420) may identify whether the trigger condition (see Table 5) for the reporting operation indicated in the monitoring configuration information received in operation 1432 has been satisfied.

[0262] Operation 1442 may represent an operation in which the terminal (1420) reports the performance values ​​calculated in operation 1438, i.e., the monitoring results, to the base station (1410). Operation 1442 may be triggered by operation 1440 and performed by the terminal (1420).

[0263] Operation 1442 represents an operation in which the base station (1410) determines whether to change the existing settings based on the report results received in operation 1440. For example, if the performance of the monitored artificial intelligence model or parameter combination is superior to the performance of the currently applied artificial intelligence model or parameter combination (or codebook mode, number of beams, etc.) of the terminal (1420), the base station (1410) may determine to change the setting information so that the terminal (1420) applies the superior artificial intelligence model or parameter combination (or codebook mode, number of beams, etc.).

[0264] In various embodiments of the present disclosure, the decision as to whether to translate existing configuration information may be performed at the terminal or base station based on monitoring configuration information.

[0265] Operation 1446 represents an operation in which the base station (1210) transmits an RRC reconfiguration including the configuration information changed in operation 1444 to the terminal (1420). Thereafter, the terminal (1420) can transmit information about a precoding matrix to the base station based on the changed configuration information. For example, the terminal (1420) can perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, input the generated precoding matrix to an artificial intelligence model (or encoder) to generate a compressed vector z, and transmit the generated vector to the base station (1410). The base station (1410) can input the received vector to an artificial intelligence model (e.g., decoder) corresponding to the encoder to restore the precoding matrix, and transmit data using the restored precoding matrix. Additionally, for example, the terminal (1420) may perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, generate a PMI by applying a changed parameter combination based on the generated precoding matrix and the codebook, and transmit the generated PMI to the base station (1410). The base station (1410) may restore the precoding matrix based on the received PMI and the codebook, and transmit data using the restored precoding matrix.

[0266] FIG. 15 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0267] The terminal and base station performing the operations described in Fig. 15 may correspond to the terminal and network entity of Figs. 2 and 3, respectively.

[0268] The embodiment of FIG. 15 may represent an embodiment in which monitoring and / or reporting operations are performed based on events. Furthermore, the embodiment of FIG. 15 may represent a case in which a terminal determines whether to change configuration information.

[0269] Referring to FIG. 15, in operation 1530, a terminal (1520) receives an RRC reconfiguration from a base station (1510). At this time, the RRC reconfiguration may include configuration information (e.g., codebook type information) regarding an artificial intelligence model or codebook for transmitting a precoding matrix. For example, the RRC reconfiguration may indicate an artificial intelligence model (or encoder) that the terminal will use to produce a vector z that compresses the precoding matrix. More specifically, the RRC reconfiguration may indicate any one of a plurality of artificial intelligence models capable of compressing the precoding matrix. The terminal may use the indicated artificial intelligence model to compress the precoding matrix, produce a vector z, and transmit the vector z to the base station. The base station may input the received vector z into a corresponding artificial intelligence model (or decoder) to restore the precoding matrix. Additionally, for example, RRC reconfiguration can indicate a parameter combination used by the terminal to calculate PMI based on a codebook. More specifically, if the codebook is of type eType II, RRC reconfiguration can indicate any one of parameter combinations 1 to 8. Alternatively, if the codebook is of type I, RRC reconfiguration can indicate any one of multiple codebook modes. The terminal can calculate PMI based on the indicated content and transmit it to the base station, thereby transmitting precoding matrix information to the base station.

[0270] In various embodiments of the present disclosure, the type information of the codebook may indicate any one of Type I, Type II, or eType II defined in the 3GPP standard document.

[0271] In operation 1532, the terminal (1520) may receive an RRC reconfiguration including monitoring configuration information from the base station (1510). The monitoring configuration information may include signaling information set in Tables 1 to 5 described above. The terminal (1520) may perform a monitoring operation for transmitting precoding matrix information based on the received monitoring configuration information. In the embodiment of FIG. 15, the monitoring configuration information may indicate that the operation for determining a change in the configuration information by the terminal is triggered based on an event. That is, the embodiment of FIG. 15 may represent a case where the index of the entity information in Table 4 is 1. The monitoring configuration information may include measurement configuration information (see Table 5) indicating conditions for the terminal to determine a change in the configuration information.

[0272] In FIG. 15, operations 1530 and 1532 are described separately, but operations 1530 and 1532 may be a single operation. For example, the terminal (1520) receives RRC reconfiguration from the base station (1510), and the RRC reconfiguration may include artificial intelligence model-related configuration information or codebook-related configuration information for transmitting a precoding matrix, along with monitoring configuration information related thereto.

[0273] Operation 1534 represents operations in which the terminal (1520) monitors and calculates performance based on monitoring configuration information. Operation 1534 may correspond to operations 1034 to 1038 of FIG. 10, operations 1134 to 1138 of FIG. 11, operations 1234 to 1238 of FIG. 12, or operations 1434 to 1438 of FIG. 14.

[0274] Operation 1536 represents an operation in which the terminal (1520) identifies that a condition for changing configuration information has been satisfied. In other words, operation 1536 may indicate that a configuration change operation has been triggered. In operation 1536, the terminal (1520) may identify whether the trigger condition (see Table 5) indicated in the monitoring configuration information received in operation 1532 has been satisfied. Operation 1536 may be performed based on the performance values ​​acquired in operation 1534.

[0275] Operation 1538 may represent an operation in which the terminal (1520) transmits the changed configuration information determined in operation 1536 to the base station (1510). Operation 1538 may be triggered by operation 1536 and performed by the terminal (1520). If the performance of the monitored artificial intelligence model or parameter combination is superior to the performance of the currently applied artificial intelligence model or parameter combination (or codebook mode, number of beams, etc.), the terminal (1520) may request the base station (1510) to change the configuration information so that the artificial intelligence model or parameter combination (or codebook mode, number of beams, etc.) with superior performance can be applied.

[0276] Operation 1540 represents an operation in which the base station (1510) transmits to the terminal (1520) an RRC reconfiguration including changed configuration information based on what was received in operation 1538. The terminal (1520) can transmit precoding matrix information to the base station (1510) based on the changed configuration information. For example, the terminal (1520) can perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, input the generated precoding matrix to an artificial intelligence model (or encoder) to generate a compressed vector z, and transmit the generated vector to the base station (1510). The base station (1510) can input the received vector to an artificial intelligence model (e.g., decoder) corresponding to the encoder to restore the precoding matrix, and transmit data using the restored precoding matrix. Additionally, for example, the terminal (1520) may perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, generate a PMI by applying a changed parameter combination based on the generated precoding matrix and the codebook, and transmit the generated PMI to the base station (1510). The base station (1510) may restore the precoding matrix based on the received PMI and the codebook, and transmit data using the restored precoding matrix.

[0277] FIG. 16 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0278] The terminal and base station performing the operations described in FIG. 16 may correspond to the terminal and network entity of FIG. 2 and FIG. 3, respectively.

[0279] The embodiment of FIG. 16 may represent an embodiment in which information regarding a target to be monitored is not indicated in the monitoring configuration information. For example, the embodiment of FIG. 16 may represent an embodiment in which the monitoring configuration information of Table 3 does not indicate "parameter combination set to monitor" and / or "AI model set to monitor." In this case, the terminal may independently select a specific parameter combination or AI model to perform monitoring, and transmit information regarding the selected parameter combination or AI model to the base station.

[0280] Referring to FIG. 16, in operation 1630, a terminal (1620) receives an RRC reconfiguration from a base station (1610). At this time, the RRC reconfiguration may include configuration information (e.g., codebook type information) regarding an artificial intelligence model or codebook for transmitting a precoding matrix. For example, the RRC reconfiguration may indicate an artificial intelligence model (or encoder) that the terminal will use to produce a vector z that compresses the precoding matrix. More specifically, the RRC reconfiguration may indicate any one of a plurality of artificial intelligence models capable of compressing the precoding matrix. The terminal may use the indicated artificial intelligence model to compress the precoding matrix, produce a vector z, and transmit the vector z to the base station. The base station may input the received vector z into a corresponding artificial intelligence model (or decoder) to restore the precoding matrix. Additionally, for example, RRC reconfiguration can indicate a parameter combination used by the terminal to calculate PMI based on a codebook. More specifically, if the codebook is of type eType II, RRC reconfiguration can indicate any one of parameter combinations 1 to 8. Alternatively, if the codebook is of type I, RRC reconfiguration can indicate any one of multiple codebook modes. The terminal can calculate PMI based on the indicated content and transmit it to the base station, thereby transmitting precoding matrix information to the base station.

[0281] In various embodiments of the present disclosure, the type information of the codebook may indicate any one of Type I, Type II, or eType II defined in the 3GPP standard document.

[0282] In operation 1632, the terminal (1620) may receive an RRC reconfiguration including monitoring configuration information from the base station (1610). The monitoring configuration information may include signaling information set in Tables 1 to 5 described above. The terminal (1620) may perform a monitoring operation to transmit precoding matrix information based on the received monitoring configuration information. In the embodiment of FIG. 16, the monitoring configuration information of operation 1632 may omit the contents of "parameter combination set to monitor" and / or "AI model set to monitor" and may not be indicated.

[0283] In Fig. 16, operations 1630 and 1632 are described separately, but operations 1630 and 1632 may be a single operation. For example, the terminal (1620) receives RRC reconfiguration from the base station (1610), and the RRC reconfiguration may include artificial intelligence model-related configuration information or codebook-related configuration information for transmitting a precoding matrix and monitoring configuration information related thereto.

[0284] Operation 1634 represents operations that the terminal (1620) monitors and reports based on monitoring configuration information. Operation 1634 may correspond to operations 1034 to 1040 of FIG. 10, operations 1134 to 1140 of FIG. 11, operations 1234 to 1240 of FIG. 12, operation 1336 of FIG. 13, or operations 1434 to 1442 of FIG. 14. In operation 1634, since the terminal (1620) does not know the target to be monitored from the monitoring configuration information, the terminal (1620) can determine the target to be monitored (such as a parameter combination or an artificial intelligence model) by itself, monitor it, and calculate performance information (such as SGSC, MSE).

[0285] Operation 1636 represents an operation in which the terminal (1620) transmits information indicating a target (e.g., a parameter combination or an artificial intelligence model) monitored in operation 1634 to the base station (1610). As another example, the information indicating a target monitored by the terminal (1620) may be transmitted to the base station together when the terminal reports the monitoring result in operation 1634. The information indicating a target monitored by the terminal (1620) may include a bit indicating a "PC set to monitor" or "model set to monitor" field and a bit indicating which parameter combination or artificial intelligence model was monitored in each set. The information indicating a target monitored by the terminal (1620) may be transmitted to the base station (1610) via uplink control information (UCI).

[0286] Operation 1638 represents an operation in which the base station (1610) transmits an RRC reconfiguration including monitoring configuration information to the terminal (1620). Based on the information received in operation 1636, the base station (1610) can transmit information indicating a target to be monitored through the monitoring configuration information to the terminal (1620).

[0287] Although omitted in FIG. 16, the base station (1610) can determine whether to change existing configuration information based on the monitoring result and monitoring target information received by operation 1634 or operation 1636, and if the configuration information is changed, can transmit an RRC reconfiguration including the changed configuration information to the terminal (1620).

[0288] The terminal (1620) can transmit precoding matrix information to the base station (1610) based on the changed configuration information. For example, the terminal (1620) can perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, input the generated precoding matrix into an artificial intelligence model (or encoder) to generate a compressed vector z, and transmit the generated vector to the base station (1610). The base station (1610) can input the received vector into an artificial intelligence model (e.g., a decoder) corresponding to the encoder to restore the precoding matrix, and transmit data using the restored precoding matrix. In addition, for example, the terminal (1620) can perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, apply a changed parameter combination based on the generated precoding matrix and a codebook to generate a PMI, and transmit the generated PMI to the base station (1610). The base station (1610) can restore a precoding matrix based on the received PMI and codebook, and transmit data using the restored precoding matrix.

[0289] FIG. 17 illustrates a monitoring method for transmitting a precoding matrix according to embodiments of the present disclosure.

[0290] The terminal and base station performing the operations described in Fig. 17 may correspond to the terminal and network entity of Figs. 2 and 3, respectively.

[0291] The embodiment of Fig. 17 may represent an embodiment in which information regarding the target to be monitored is not indicated in the monitoring configuration information. Furthermore, the embodiment of Fig. 17 may represent an embodiment in which the terminal's monitoring and reporting operations are performed aperiodic or semi-persistently.

[0292] The embodiment of FIG. 17 may represent an embodiment in which the "parameter combination set to monitor" and / or "AI model set to monitor" are not indicated in the monitoring configuration information of Table 3. In this case, the terminal may independently select a specific parameter combination or AI model to perform monitoring, and transmit information about the selected parameter combination or AI model to the base station.

[0293] Referring to FIG. 17, in operation 1730, a terminal (1720) receives an RRC reconfiguration from a base station (1710). At this time, the RRC reconfiguration may include configuration information (e.g., codebook type information) regarding an artificial intelligence model or codebook for transmitting a precoding matrix. For example, the RRC reconfiguration may indicate an artificial intelligence model (or encoder) that the terminal will use to produce a vector z that compresses the precoding matrix. More specifically, the RRC reconfiguration may indicate any one of a plurality of artificial intelligence models capable of compressing the precoding matrix. The terminal may use the indicated artificial intelligence model to compress the precoding matrix, produce a vector z, and transmit the vector z to the base station. The base station may input the received vector z into a corresponding artificial intelligence model (or decoder) to restore the precoding matrix. Additionally, for example, RRC reconfiguration can indicate a parameter combination used by the terminal to calculate PMI based on a codebook. More specifically, if the codebook is of type eType II, RRC reconfiguration can indicate any one of parameter combinations 1 to 8. Alternatively, if the codebook is of type I, RRC reconfiguration can indicate any one of multiple codebook modes. The terminal can calculate PMI based on the indicated content and transmit it to the base station, thereby transmitting precoding matrix information to the base station.

[0294] In various embodiments of the present disclosure, the type information of the codebook may indicate any one of Type I, Type II, or eType II defined in the 3GPP standard document.

[0295] In operation 1732, the terminal (1720) may receive an RRC reconfiguration including monitoring configuration information from the base station (1710). The monitoring configuration information may include signaling information set in Tables 1 to 5 described above. The terminal (1720) may perform a monitoring operation to transmit precoding matrix information based on the received monitoring configuration information. In the embodiment of FIG. 17, the monitoring configuration information of operation 1732 may omit the contents of "parameter combination set to monitor" and / or "AI model set to monitor" and may not be indicated. In addition, information indicating a period in the monitoring configuration information may be set to "Aperiodic" or "semi-persistent."

[0296] In Fig. 17, operations 1730 and 1732 are described separately, but operations 1730 and 1732 may be a single operation. For example, the terminal (1720) receives RRC reconfiguration from the base station (1710), and the RRC reconfiguration may include artificial intelligence model-related configuration information or codebook-related configuration information for transmitting a precoding matrix and monitoring configuration information related thereto.

[0297] Operation 1734 represents an operation in which the base station (1710) requests the terminal (1720) to monitor and report on the transmission of the precoding matrix. That is, if the period information included in the monitoring configuration information in operation 1732 indicates Aperiodic or semi-persistent, monitoring or result reporting may be performed at the request of the base station (1710). Operation 1734 may be performed based on low-layer signaling, an uplink control information (UCI) message. If the period information is Aperiodic, the monitoring or reporting operation may be performed once at the request of the base station (1710). If the period information is semi-persistent, the monitoring or reporting operation may be performed repeatedly after the request of the base station (1710).

[0298] Operation 1736 represents operations that the terminal (1720) monitors and reports based on monitoring configuration information. Operation 1736 may correspond to operations 1034 to 1040 of FIG. 10, operations 1134 to 1140 of FIG. 11, operations 1234 to 1240 of FIG. 12, operation 1336 of FIG. 13, or operations 1434 to 1442 of FIG. 14. In operation 1736, since the terminal (1720) does not know the target to be monitored from the monitoring configuration information, the terminal (1720) can determine the target to be monitored (such as a parameter combination or an artificial intelligence model) by itself, monitor it, and calculate performance information (such as SGSC, MSE).

[0299] Operation 1738 represents an operation in which the terminal (1720) transmits information indicating a target (e.g., a parameter combination or an artificial intelligence model) monitored in operation 1736 to the base station (1710). As another example, the information indicating a target monitored by the terminal (1720) may be transmitted to the base station together when the terminal reports the monitoring result in operation 1736. The information indicating a target monitored by the terminal (1720) may include a bit indicating a "PC set to monitor" or "model set to monitor" field and a bit indicating which parameter combination or artificial intelligence model was monitored in each set. The information indicating a target monitored by the terminal (1720) may be transmitted to the base station (1710) via UCI (uplink control information).

[0300] Operation 1740 represents an operation in which the base station (1710) transmits an RRC reconfiguration including monitoring configuration information to the terminal (1720). Based on the information received in operation 1738, the base station (1710) can transmit information indicating a target to be monitored (PC set to monitor, AI model set to monitor) to the terminal (1720) through the monitoring configuration information.

[0301] Although omitted in FIG. 17, the base station (1710) can determine whether to change existing configuration information based on the monitoring result and monitoring target information received by operation 1736 or operation 1738, and if the configuration information is changed, can transmit an RRC reconfiguration including the changed configuration information to the terminal (1720).

[0302] The terminal (1720) can transmit precoding matrix information to the base station (1710) based on the changed configuration information. For example, the terminal (1720) can perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, input the generated precoding matrix into an artificial intelligence model (or encoder) to generate a compressed vector z, and transmit the generated vector to the base station (1710). The base station (1710) can input the received vector into an artificial intelligence model (e.g., a decoder) corresponding to the encoder to restore the precoding matrix, and transmit data using the restored precoding matrix. In addition, for example, the terminal (1720) can perform channel estimation based on the CSI-RS received from the base station, generate a precoding matrix based on the estimated channel, apply a changed parameter combination based on the generated precoding matrix and a codebook to generate a PMI, and transmit the generated PMI to the base station (1710). The base station (1710) can restore a precoding matrix based on the received PMI and codebook, and transmit data using the restored precoding matrix.

[0303] FIG. 18 is a diagram for explaining a terminal's monitoring operation for a precoding matrix according to embodiments of the present disclosure.

[0304] The terminal performing the operation described in Fig. 18 can correspond to the terminal of Fig. 2.

[0305] The terminal operation described in Fig. 18 may be related to the terminal operations described in Figs. 4 to 17.

[0306] Referring to FIG. 18, in operation 1810, the terminal may receive configuration information for monitoring the transmission performance of the precoding matrix from the base station. At this time, the configuration information for monitoring the transmission performance of the precoding matrix may indicate the signaling information described in Tables 1 to 5 described above. In addition, the configuration information for monitoring may indicate information expressed as monitoring configuration information with respect to FIGS. 10 to 17. That is, it may indicate configuration information related to the monitoring and result reporting operations of the terminal. Operation 1810 may correspond to operation 1032 of FIG. 10, operation 1132 of FIG. 11, operation 1232 of FIG. 12, operation 1332 of FIG. 13, operation 1432 of FIG. 14, operation 1532 of FIG. 15, operation 1632 of FIG. 16, or operation 1732 of FIG. 17.

[0307] Operation 1820 may represent an operation in which a terminal receives a reference signal for measuring a channel state from a base station. The reference signal for measuring the channel state may represent a CSI-RS transmitted by the base station. Operation 1820 may correspond to operation 1034 of FIG. 10, operation 1134 of FIG. 11, operation 1234 of FIG. 12, and operation 1434 of FIG. 14.

[0308] Operation 1830 may represent an operation in which the terminal generates a precoding matrix based on a reference signal received from a base station. More specifically, the terminal may generate an estimated channel based on the received reference signal and may apply an EVD or SVD technique to the estimated channel to produce a precoding matrix. Operation 1830 may correspond to operations 412 to 416 of FIG. 4 and operations 510 to 520 of FIG. 5 .

[0309] Operation 1840 represents an operation in which a terminal generates compressed information corresponding to a precoding matrix based on a precoding matrix and configuration information. For example, if the configuration information indicates a monitoring method based on a codebook and indicates a combination of parameters to be monitored (or, codebook mode, number of beams, etc.) according to the codebook type, the terminal may generate a PMI (precoding matrix indicator) based on the precoding matrix, the codebook, and the parameter combination. If the configuration information indicates multiple combinations of parameters to be monitored, the terminal may generate a corresponding PMI for each parameter combination. That is, the compressed information corresponding to the precoding matrix may indicate the PMI. In addition, for example, if the configuration information indicates a monitoring method based on an artificial intelligence model and indicates an artificial intelligence model to be monitored, the terminal may input a precoding matrix into the indicated artificial intelligence model to generate a compressed vector. In this case, the compressed information corresponding to the precoding matrix may indicate a vector output from the artificial intelligence model. Operation 1840 may correspond to operation 418 of FIG. 4 or operation 530 of FIG. 5.

[0310] Operation 1850 represents an operation in which the terminal generates performance information for the compressed information (PMI or compressed vector) corresponding to the precoding matrix. That is, the terminal can generate information indicating the performance of the PMI or compressed vector generated in operation 1840. Here, the performance can be evaluated based on the degree to which the precoding matrix reconstructed by the PMI or compressed vector is similar to the original precoding matrix. That is, the higher the similarity of the reconstructed precoding matrix to the original precoding matrix, the better the performance for the PMI or compressed vector can be evaluated. However, the performance may take into account not only the similarity but also the overhead resulting from the feedback operation of the terminal. For example, even if the similarity is somewhat low, the performance may be evaluated as good if the number of bits required for feedback is small.

[0311] Performance information can be generated based on configuration information. The configuration information can include information indicating a method for calculating performance information for compressed information corresponding to a precoding matrix. The method for calculating performance information for the compressed information can be an SGSC-based method, an MSE-based method, an SINR-based method, or an AI model-based method. The terminal can calculate performance information based on the method indicated in the configuration information. For example, the AI ​​model-based method indicates calculating performance information using an AI model, and can correspond to operation 918 of FIG. 9. In the case of the SGSC-based method, the MSE-based method, and the SINR-based method, the terminal can indicate calculating performance information based on a metric function, and can correspond to operation 818 of FIG. 8.

[0312] For monitoring methods based on AI models, performance information on compressed vectors generated by the AI ​​model can be derived using a proxy model. The proxy model represents a model trained to output performance information and corresponds to component 714 of Figure 7.

[0313] The 1850 operation may correspond to the 818 operation of FIG. 8, the 918 operation of FIG. 9, the 1038 operation of FIG. 10, the 1138 operation of FIG. 11, the 1238 operation of FIG. 12, or the 1438 operation of FIG. 14.

[0314] The 1860 operation may indicate an operation in which a terminal reports performance information to a base station. The operation in which performance information is reported may be performed based on configuration information. For example, the configuration information may include periodic information for reporting and trigger information for reporting. The periodic information for reporting may indicate periodic, aperiodic, or semi-persistent. Periodic may indicate that the terminal performs the reporting operation periodically, while aperiodic or semi-persistent may indicate that the terminal performs the reporting operation upon a request from the base station. Aperiodic may indicate that the terminal performs the reporting operation once after a request from the base station, and semi-persistent may indicate that the terminal performs the reporting operation repeatedly after a request from the base station.

[0315] Trigger information for reporting can indicate conditions that must be met for a terminal to perform a reporting operation. For example, trigger information for reporting can be set as shown in Table 5 above. The terminal can identify whether the set conditions are met, and if so, report performance information to the base station. That is, if the conditions are met, the terminal can report monitoring results to the base station. The monitoring results can indicate performance information regarding the parameter combination or artificial intelligence model monitored by the terminal.

[0316] Although not shown in FIG. 18, the terminal may receive changed configuration information from the base station. For example, an RRC configuration including the changed configuration information may be received. The changed configuration information may indicate an AI model or codebook type that the terminal must apply to transmit the precoding matrix to the base station, and reference information according to the codebook type. That is, if the base station determines more efficient configuration information than before by referring to the monitoring results of the terminal, the terminal may receive the changed configuration information from the base station, apply the changed configuration information, and transmit the precoding matrix to the base station. For example, the terminal may calculate a PMI based on the changed codebook type or parameter combination based on the changed configuration information, and transmit the calculated PMI to the base station.

[0317] FIG. 19 is a diagram for explaining a monitoring operation of a base station for a precoding matrix according to embodiments of the present disclosure.

[0318] The base station performing the operation described in Fig. 19 may correspond to the base station of Fig. 2.

[0319] The base station operation described in FIG. 19 may be related to the base station operations described in FIGS. 4 to 17.

[0320] Referring to FIG. 19, operation 1910 represents an operation in which a base station transmits configuration information for monitoring the transmission performance of a precoding matrix to a terminal. At this time, the configuration information for monitoring the transmission performance of the precoding matrix may represent the signaling information described in Tables 1 to 5 described above. In addition, the configuration information for monitoring may represent information expressed as monitoring configuration information with respect to FIGS. 10 to 17. That is, it may represent configuration information related to the monitoring operation and result reporting operation of the terminal. Operation 1910 may correspond to operation 1032 of FIG. 10, operation 1132 of FIG. 11, operation 1232 of FIG. 12, operation 1332 of FIG. 13, operation 1432 of FIG. 14, operation 1532 of FIG. 15, operation 1632 of FIG. 16, or operation 1732 of FIG. 17.

[0321] Operation 1920 represents an operation in which a base station transmits a reference signal to a terminal for measuring channel conditions. The reference signal for measuring the channel conditions may represent a CSI-RS transmitted by the base station. Operation 1820 may correspond to operation 1034 of FIG. 10, operation 1134 of FIG. 11, operation 1234 of FIG. 12, and operation 1434 of FIG. 14.

[0322] Action 1930 represents the operation in which the base station receives a report on monitoring performed based on configuration information from the terminal. The monitoring report may include performance information regarding the monitoring method.

[0323] A terminal can generate performance information for a precoding matrix and corresponding compressed information (PMI or compressed vector). The performance information can be calculated based on the degree to which a precoding matrix reconstructed from the PMI or compressed vector is similar to the original precoding matrix. That is, the higher the similarity of the reconstructed precoding matrix to the original precoding matrix, the better the performance of the PMI or compressed vector can be evaluated. However, the performance may take into account not only the similarity but also the overhead resulting from the terminal's feedback operation. For example, even if the similarity is somewhat low, if the number of bits required for feedback is small, the performance may be evaluated as good.

[0324] Performance information can be generated based on configuration information. The configuration information can include information indicating a method for calculating performance information for compressed information corresponding to a precoding matrix. The method for calculating performance information for the compressed information can be an SGSC-based method, an MSE-based method, an SINR-based method, or an AI model-based method. The terminal can calculate performance information based on the method indicated in the configuration information. For example, the AI ​​model-based method indicates calculating performance information using an AI model, and can correspond to operation 918 of FIG. 9. In the case of the SGSC-based method, the MSE-based method, and the SINR-based method, the terminal can indicate calculating performance information based on a metric function, and can correspond to operation 818 of FIG. 8.

[0325] For monitoring methods based on AI models, a proxy model can be used to derive performance information on compressed vectors generated by the AI ​​model. The proxy model represents a model trained to output performance information and corresponds to component 714 of Figure 7.

[0326] The operation of reporting performance information may be performed based on configuration information. For example, the configuration information may include periodic information for reporting and trigger information for reporting. The periodic information for reporting may indicate periodic, aperiodic, or semi-persistent. Periodic may indicate that the terminal performs the reporting operation periodically, while aperiodic or semi-persistent may indicate that the terminal performs the reporting operation upon a request from the base station. Aperiodic may indicate that the terminal performs the reporting operation once after a request from the base station, and semi-persistent may indicate that the terminal performs the reporting operation repeatedly after a request from the base station.

[0327] Trigger information for reporting can indicate conditions that must be met for a terminal to perform a reporting operation. For example, trigger information for reporting can be set as shown in Table 5 above. The terminal can identify whether the set conditions are met, and if so, report performance information to the base station. That is, if the conditions are met, the terminal can report monitoring results to the base station. The monitoring results can indicate performance information regarding the parameter combination or artificial intelligence model monitored by the terminal.

[0328] Operation 1940 represents an operation in which the base station determines whether to change the configuration information for transmitting the precoding matrix based on the received report. The base station can determine whether to change the configuration information based on performance information included in the report received from the terminal. For example, if the existing configuration information indicates a first codebook and a first parameter combination, and the monitoring configuration information indicates a first codebook and a second parameter combination, the base station receives performance information about the second parameter combination based on the monitoring result from the terminal. Then, if the base station determines that the precoding matrix transmission performance of the second PMI calculated based on the second parameter combination is better than that of the first PMI calculated based on the first parameter combination, the base station can decide to change the existing configuration information. Operation 1940 may correspond to operation 1042 of FIG. 10, operation 1142 of FIG. 11, operation 1242 of FIG. 12, operation 1338 of FIG. 13, or operation 1444 of FIG. 14.

[0329] In various embodiments, when the terminal determines whether to change the configuration information (e.g., when the entity information index corresponds to 1 in Table 4), the operation of the base station determining whether to change the configuration information may be omitted. In this case, the terminal determines whether to change the configuration information, and if the terminal decides to change the configuration information, the changed information may be transmitted to the base station. The base station may change the configuration information based on the received change information and transmit the changed configuration information to the terminal.

[0330] Operation 1950 represents an operation in which the base station transmits changed configuration information to the terminal. If the base station determines to change the configuration information in operation 1940, the base station may change the configuration information and transmit the changed configuration information to the terminal. Operation 1950 may correspond to operation 1044 of FIG. 10, operation 1144 of FIG. 11, operation 1244 of FIG. 12, operation 1340 of FIG. 13, operation 1446 of FIG. 14, or operation 1540 of FIG. 15.

[0331] Meanwhile, as various embodiments of the present disclosure, a method performed by a terminal in a wireless communication system may include a step of receiving configuration information for monitoring transmission performance of a precoding matrix from a base station, a step of receiving a reference signal for measuring a channel state from the base station, a step of generating a precoding matrix based on the reference signal, a step of generating compressed information corresponding to the precoding matrix based on the precoding matrix and the configuration information, a step of generating performance information for the compressed information, and a step of reporting the performance information to the base station. Here, the configuration information may include monitoring type information indicating at least one of a monitoring method based on a codebook or an artificial intelligence model.

[0332] The step of receiving setup information for monitoring the transmission performance of the precoding matrix from the base station may correspond to operation 1032 of FIG. 10, operation 1132 of FIG. 11, operation 1232 of FIG. 12, operation 1332 of FIG. 13, operation 1432 of FIG. 14, operation 1532 of FIG. 15, operation 1632 of FIG. 16, operation 1732 of FIG. 17, operation 1810 of FIG. 18, or operation 1910 of FIG. 19.

[0333] The step of receiving a reference signal for measuring a channel state from a base station may correspond to operation 1034 of FIG. 10, operation 1134 of FIG. 11, operation 1234 of FIG. 12, operation 1434 of FIG. 14, operation 1820 of FIG. 18, or operation 1920 of FIG. 19.

[0334] The step of generating compressed information corresponding to the precoding matrix based on the precoding matrix and the setting information may correspond to operation 418 of FIG. 4, operation 530 of FIG. 5, operation 816 of FIG. 8, operation 916 of FIG. 9, operation 1036 of FIG. 10, operation 1136 of FIG. 11, operation 1236 of FIG. 12, operation 1436 of FIG. 14, or operation 1840 of FIG. 18. The compressed information may include a PMI generated based on a codebook or a vector generated based on an artificial intelligence model.

[0335] The step of generating performance information for the compressed information may correspond to operation 818 of FIG. 8, operation 918 of FIG. 9, operation 1038 of FIG. 10, operation 1138 of FIG. 11, operation 1238 of FIG. 12, operation 1438 of FIG. 14, or operation 1850 of FIG. 18. The performance information for the compressed information may indicate the similarity between a precoding matrix restored by the compressed information and an original precoding matrix, and may be generated based on a method such as SGCS, MSE, or SINR. Alternatively, the performance information may be a value output by inputting the compressed information described above into an artificial intelligence model.

[0336] The step of reporting performance information to the base station may correspond to operation 1040 of FIG. 10, operation 1140 of FIG. 11, operation 1240 of FIG. 12, operation 1442 of FIG. 14, or operation 1860 of FIG. 18.

[0337] The configuration information includes monitoring type information indicating at least one monitoring method based on a codebook or an artificial intelligence model. For example, based on the index in Table 2 described above, the monitoring method may be based on a codebook or an artificial intelligence model.

[0338] When the monitoring type information indicates monitoring based on a codebook, the configuration information may further include information indicating the type of the codebook and reference information based on the type of the codebook. For example, the information indicating the type of the codebook may indicate the type of the codebook as either Type I, Type II, or eType II. In addition, the configuration information may further include reference information as detailed configuration information corresponding to each type of the codebook, depending on the type of the codebook. For a Type I codebook, the reference information may be codebook mode information. For a Type II codebook, the reference information may be beam count information. For an eType II codebook, the reference information may be a parameter combination (PC).

[0339] When the monitoring type information indicates monitoring based on a codebook, the compressed information corresponding to the precoding matrix may include a codebook of the codebook type indicated in the configuration information and a PMI (precoding matrix indicator) generated based on the indicated reference information.

[0340] On the other hand, if the monitoring type information indicates monitoring based on an artificial intelligence model, the configuration information further includes information indicating at least one artificial intelligence model among a plurality of artificial intelligence models, and the compressed information corresponding to the precoding matrix may be a vector that is input to and output by the precoding matrix at least one artificial intelligence model.

[0341] Monitoring configuration information may include information indicating how performance information is calculated. For example, the information indicating how performance information is calculated may indicate at least one of a squared generalized cosine similarity (SGCS)-based method, a mean squared error (MSE)-based method, a signal-to-interference plus noise ratio (SINR)-based method, and an artificial intelligence model-based method. In other words, this corresponds to the codebook-based monitoring type described in Table 3.

[0342] Additionally, the monitoring configuration information further includes information indicating conditions for reporting performance information, and the step of reporting the performance information may be performed if the conditions are satisfied. Conditions for reporting performance information may be referenced in Tables 4 and 5 of the present disclosure.

[0343] As a communication method according to embodiments of the present disclosure, a method performed by a base station in a wireless communication system may be composed of operations of the base station corresponding to operations of the terminal described above.

[0344] While the operations of the communication method according to the embodiments of the present disclosure have been described separately for each embodiment, the operations included in each embodiment can be combined with operations of other embodiments to form a new embodiment. Accordingly, it can be understood that embodiments in which the embodiments of the present disclosure are combined are also described by the present disclosure.

[0345] The communication method according to embodiments of the present disclosure is a method for transmitting information about a precoding matrix. Based on the information indicated through monitoring configuration information, the terminal can monitor the transmission method of the precoding matrix. Furthermore, the communication method according to embodiments of the present disclosure can improve communication efficiency by comparing the monitored results and adopting and applying a better method than existing methods.

[0346] The communication method according to embodiments of the present disclosure can be applied to not only a codebook-based method for transmitting a precoding matrix but also an artificial intelligence model-based method.

[0347] 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.

[0348] 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).

[0349] 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.

[0350] 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.

[0351] 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. In a method performed by a terminal in a wireless communication system, A step of receiving configuration information for monitoring transmission performance of a precoding matrix from a base station; A step of receiving a reference signal for measuring a channel state from a base station; A step of generating the precoding matrix based on the reference signal; A step of generating compressed information corresponding to the precoding matrix based on the precoding matrix and the setting information; A step of generating performance information for the compressed information; and comprising a step of reporting the performance information to the base station, The above setting information is, Contains monitoring type information indicating at least one of the monitoring methods based on a codebook or an artificial intelligence model; method.

2. In claim 1, The above monitoring type information indicates monitoring based on a codebook, The above setting information is, Information indicating the type of codebook, Further including reference information based on the type of the above codebook, The compressed information corresponding to the above precoding matrix is, Including a codebook of the above codebook type and a PMI (precoding matrix indicator) generated based on the above reference information, method.

3. In claim 1, The above monitoring type information indicates monitoring based on an artificial intelligence model, The above setting information is, Further comprising information indicating at least one artificial intelligence model among a plurality of artificial intelligence models, The compressed information corresponding to the above precoding matrix is, The above precoding matrix includes a vector that is input to and output from at least one artificial intelligence model. method.

4. In claim 1, The above setting information includes information indicating a method of calculating the performance information and information indicating conditions for reporting the performance information. Information indicating a method of producing the above performance information indicates at least one of a squared generalized cosine similarity (SGCS)-based method, a mean squared error (MSE)-based method, a signal to interference plus noise ratio (SINR)-based method, and an artificial intelligence model-based method. The step of reporting the above performance information is performed when the above condition is satisfied. method.

5. As a terminal of a wireless communication system, Transmitter and receiver; and Including a processor connected to the above transceiver, The above processor: Receive configuration information for monitoring the transmission performance of the precoding matrix from the base station; Receive a reference signal from a base station for measuring channel conditions; Generating the precoding matrix based on the above reference signal; Generating compressed information corresponding to the precoding matrix based on the precoding matrix and the setting information; Generate performance information for the compressed information; and It is set to report the above performance information to the base station, The above setting information is, Contains monitoring type information indicating at least one of the monitoring methods based on a codebook or an artificial intelligence model; Terminal.

6. In claim 5, The above monitoring type information indicates monitoring based on a codebook, The above setting information is, Information indicating the type of codebook, Further including reference information based on the type of the above codebook, The compressed information corresponding to the above precoding matrix is, Including a codebook of the above codebook type and a PMI (precoding matrix indicator) generated based on the above reference information, Terminal.

7. In claim 5, The above monitoring type information indicates monitoring based on an artificial intelligence model, The above setting information is, Further comprising information indicating at least one artificial intelligence model among a plurality of artificial intelligence models, The compressed information corresponding to the above precoding matrix is, The above precoding matrix includes a vector that is input to and output from at least one artificial intelligence model. Terminal.

8. In claim 5, The above setting information includes information indicating a method of calculating the performance information and information indicating conditions for reporting the performance information. Information indicating a method of producing the above performance information indicates at least one of a squared generalized cosine similarity (SGCS)-based method, a mean squared error (MSE)-based method, a signal to interference plus noise ratio (SINR)-based method, and an artificial intelligence model-based method. The above processor is set to report performance information to the base station when the above condition is satisfied. Terminal.

9. In a method performed by a base station in a wireless communication system, A step of transmitting configuration information for monitoring the transmission performance of a precoding matrix to a terminal; A step of transmitting a reference signal for measuring a channel status to a terminal; A step of receiving a report on monitoring performed based on the above setting information from the terminal, The above setting information is, Contains monitoring type information indicating at least one of the monitoring methods based on a codebook or an artificial intelligence model; method.

10. In claim 9, The above monitoring type information indicates monitoring based on a codebook, The above setting information is, Information indicating the type of codebook, Further including reference information based on the type of the above codebook, The codebook of the above codebook type and the above reference information are related to the generation of PMI (precoding matrix indicator), method.

11. In claim 9, The above monitoring type information directs monitoring based on an artificial intelligence model, The above setting information is, Further comprising information indicating at least one artificial intelligence model among a plurality of artificial intelligence models, At least one artificial intelligence model is input with the precoding matrix and outputs a vector. method.

12. In claim 9, The above report includes performance information regarding the above monitoring, The above setting information includes information indicating a method of calculating the above performance information and information indicating conditions for the above report. Information indicating a method of producing the above performance information indicates at least one of a squared generalized cosine similarity (SGCS)-based method, a mean squared error (MSE)-based method, a signal to interference plus noise ratio (SINR)-based method, and an artificial intelligence model-based method. The step of receiving the above report is performed when the above condition is satisfied. method.

13. In a base station of a wireless communication system, Transmitter and receiver; and Including a processor connected to the above transceiver, The above processor: Transmits configuration information to the terminal for monitoring the transmission performance of the precoding matrix; Transmitting a reference signal to the terminal for measuring the channel status; Receive a report on monitoring performed based on the above setting information from the terminal, The above setting information is, Contains monitoring type information indicating at least one of the monitoring methods based on a codebook or an artificial intelligence model; Base station.

14. In claim 13, The above monitoring type information indicates monitoring based on the codebook, The above setting information is, Information indicating the type of codebook, Further including reference information based on the type of the above codebook, The codebook of the above codebook type and the above reference information are related to the generation of PMI (precoding matrix indicator), The above report contains performance information regarding the above monitoring, The above setting information further includes information indicating a method of calculating the above performance information and information indicating conditions for the above report. Information indicating a method of producing the above performance information indicates at least one of a squared generalized cosine similarity (SGCS)-based method, a mean squared error (MSE)-based method, a signal to interference plus noise ratio (SINR)-based method, and an artificial intelligence model-based method. The above report is received when the above conditions are satisfied. Base station.

15. In claim 13, The above monitoring type information directs monitoring based on an artificial intelligence model, The above setting information is, Further comprising information indicating at least one artificial intelligence model among a plurality of artificial intelligence models, The above at least one artificial intelligence model is input with the above precoding matrix and outputs a vector, The above report contains performance information regarding the above monitoring, The above setting information further includes information indicating a method of calculating the above performance information and information indicating conditions for the above report. Information indicating a method of producing the above performance information indicates at least one of a squared generalized cosine similarity (SGCS)-based method, a mean squared error (MSE)-based method, a signal to interference plus noise ratio (SINR)-based method, and an artificial intelligence model-based method. The above report is received when the above conditions are satisfied. Base station.

Images