Method and device for reporting channel state information in wireless communication system

Abstract

A method of a UE according to an embodiment of the present disclosure may comprise the steps of: receiving a first message including channel CSI reporting configuration information from a base station, wherein the CSI reporting configuration information includes a CSI reporting type and a first configuration for CSI prediction reporting using a UE-side AI model; receiving an RS for CSI reporting from the base station on the basis that the CSI reporting type is a periodic CSI reporting type; generating a CSI prediction value by inputting a value obtained by measuring the received RS to the UE-side AI model, on the basis of the first configuration; and transmitting a second message including the generated CSI prediction value to the base station.

Description

Method and device for reporting channel status information in a wireless communication system

[0001] The present disclosure relates to a technology for reporting channel state information in a wireless communication system, and more specifically, to a technology for reporting channel state information based on Artificial Intelligence (AI) / Machine Learning (ML).

[0002] As wireless communication technology advances, the 5th generation (5 th The commercialization of wireless communication systems (generation, 5G) is underway. In wireless communication technology, communication between a base station and a UE takes place over a specific channel; therefore, the base station must be able to know the channel state information (CSI) with the UE in order to perform proper communication. In particular, in wireless communication systems that use multiple antennas to form a specific beam, channel state information can be a very important factor in communication between the base station and the UE.

[0003] Meanwhile, with the recent advancement of Artificial Intelligence (AI) and Machine Learning (ML), various studies on utilizing AI / ML in wireless communication systems are actively underway. In particular, discussions are being held on methods to provide faster and higher quality services by using AI / ML to estimate (or predict) the CSI between a base station and a UE, and by using the estimated (or predicted) CSI to perform communication.

[0004] However, current wireless communication systems do not offer a method for reporting predicted CSI using AI / ML. Therefore, wireless communication systems require a method for CSI reporting utilizing AI / ML.

[0005] The objective of the present disclosure to address the above-mentioned requirements is to provide a method and apparatus for reporting predicted CSI using AI / ML in a wireless communication system.

[0006] A method of user equipment (UE) according to one embodiment of the disclosure for achieving the above-mentioned purpose may include the steps of: receiving a first message from a base station containing channel state information (CSI) reporting setting information, wherein the CSI reporting setting information includes a CSI reporting type and a first setting for CSI prediction reporting using a UE-side artificial intelligence (AI) model; receiving a reference signal (RS) for CSI reporting from the base station based on the fact that the CSI reporting type is a periodic CSI reporting type; generating a CSI prediction value by inputting a value of the received RS measured into the UE-side AI model based on the first setting; and transmitting a second message including the generated CSI prediction value to the base station.

[0007] The above CSI report setting information may further include a second setting for reporting the value of the RS signal measured.

[0008] The second message above may further include one or more measurement values ​​of the RS signal measured based on the second setting.

[0009] A first setting for the CSI prediction report using the above-described UE-side AI model includes a first parameter indicating that the CSI report is a report of a predicted value by the above-described UE-side AI model, and setting information for one or more channel state-related predicted values ​​to be generated by the above-described UE-side AI model, and the channel state-related predicted values ​​include predicted channel quality information (p-CQI), predicted precoding matrix indicator (p-PMI), predicted CSI-RS resource indicator (p-CRI), predicted reference signal received power RSRP (p-CRI-RSRP) of CSI-RS corresponding to the predicted CRI, predicted synchronization signal block (SSB-index) index (p-SSB-index), or predicted RSRP for the predicted SSB index (p-SSB-index-RSRP), predicted synchronization signal / physical broadcast channel, It may include one or more of the SS / PBCH resource block indicator (p-SSBRI), predicted layer indicator (p-LI), predicted rank indicator (p-RI), or predicted layer 1 (L1)-reference signal received power (p-L1-RSRP).

[0010] The above CSI report setting information may include setting information for triggering states for CSI reporting, and CSI report-related settings associated with each of the triggering states for CSI reporting.

[0011] A method of user equipment (UE) according to one embodiment of the disclosure for achieving the above-mentioned purpose comprises: receiving a first message from a base station that includes channel state information (CSI) reporting setting information, wherein the CSI reporting setting information includes a CSI reporting type, a first setting for CSI prediction reporting using a UE-side artificial intelligence (AI) model, and a second setting for CSI reporting not using the UE-side AI model; receiving downlink control information (DCI) from the base station that triggers the CSI reporting based on the fact that the CSI reporting type is a non-periodic CSI reporting type; identifying whether the DCI indicates a first CSI reporting triggering state within a first CSI reporting triggering state list included in the first setting or a second CSI reporting triggering state within a second CSI reporting triggering state list included in the second setting; and receiving a reference signal (RS) for CSI reporting from the base station based on the fact that the DCI indicates the first CSI reporting triggering state. Based on the first setting and the DCI, the method may include the step of inputting the value of the received RS measured into the UE-side AI model to generate a CSI prediction value; and the step of transmitting a second message containing the generated CSI prediction value to the base station.

[0012] If the above DCI is scrambled with a first radio network temporary identifier (RNTI) that directs the use of the above UE-side AI model, it may be identified as directing a first CSI report triggering state within a first CSI report triggering state list included in the first setting.

[0013] If the above DCI is scrambled into a second RNTI different from the above first RNTI, it can be identified as indicating a second CSI report triggering state within the second CSI report triggering state list included in the above second setting.

[0014] Based on the fact that the first setting further includes a third CSI report triggering status list, the DCI may further include an identifier for indicating either the first CSI report triggering status list or the third CSI report triggering status list.

[0015] The second message above may further include one or more measurement values ​​of the RS signal measured based on the second setting.

[0016] A first setting for the CSI prediction report using the above-described UE-side AI model includes a first parameter indicating that the CSI report is a report of a predicted value by the above-described UE-side AI model, and setting information for one or more channel state-related predicted values ​​to be generated by the above-described UE-side AI model, and the channel state-related predicted values ​​include predicted channel quality information (p-CQI), predicted precoding matrix indicator (p-PMI), predicted CSI-RS resource indicator (p-CRI), predicted reference signal received power RSRP (p-CRI-RSRP) of CSI-RS corresponding to the predicted CRI, predicted synchronization signal block (SSB-index) index (p-SSB-index), or predicted RSRP for the predicted SSB index (p-SSB-index-RSRP), predicted synchronization signal / physical broadcast channel, It may include one or more of the SS / PBCH resource block indicator (p-SSBRI), predicted layer indicator (p-LI), predicted rank indicator (p-RI), or predicted layer 1 (L1)-reference signal received power (p-L1-RSRP).

[0017] A method of user equipment (UE) according to one embodiment of the disclosure for achieving the above-mentioned purpose comprises: receiving a first message from a base station including channel state information (CSI) reporting setting information, wherein the CSI reporting setting information includes a CSI reporting type, a first setting for CSI prediction reporting using a UE-side artificial intelligence (AI) model, and a second setting for CSI reporting not using the UE-side AI model; receiving a second message from the base station for enabling / disabling semi-static CSI reporting based on the fact that the CSI reporting type is a semi-static CSI reporting type, wherein the second message includes two or more CSI reporting triggering states based on at least one of the first setting or the second setting; and receiving downlink control information (DCI) for indicating one of the CSI reporting triggering states included in the second message. The method may include the step of receiving a reference signal (RS) for CSI reporting from the base station based on the CSI reporting triggering state indicated by the DCI; and the step of transmitting a third message to the base station including one or more values ​​based on the received RS, wherein the one or more values ​​based on the received RS may be values ​​indicated by the DCI.

[0018] The second message may further include an indicator for the CSI report triggering states included in the second message to indicate one of the first setting or the second setting.

[0019] If the CSI report triggering states corresponding to the first setting and the CSI report triggering states corresponding to the second setting are included in the first CSI report triggering list, the second message may include all CSI report triggering states included in the first CSI report triggering list.

[0020] If the above DCI is scrambled with a first radio network temporary identifier (RNTI) that directs the use of the above UE-side AI model, it may be identified as directing a first CSI report triggering state within a first CSI report triggering state list included in the first setting.

[0021] If the above DCI is scrambled into a second RNTI different from the above first RNTI, it can be identified as indicating a second CSI report triggering state within the second CSI report triggering state list included in the above second setting.

[0022] If one or more values ​​based on the received RS included in the third message are CSI prediction values ​​obtained by inputting the value indicated by the DCI, which is the value measured by the received RS, into the UE-side AI model, the third message may further include one or more measured values ​​of the RS signal measured based on the second setting.

[0023] A first setting for the CSI prediction report using the above-described UE-side AI model includes a first parameter indicating that the CSI report is a report of a predicted value by the above-described UE-side AI model, and setting information for one or more channel state-related predicted values ​​to be generated by the above-described UE-side AI model, and the channel state-related predicted values ​​include predicted channel quality information (p-CQI), predicted precoding matrix indicator (p-PMI), predicted CSI-RS resource indicator (p-CRI), predicted reference signal received power RSRP (p-CRI-RSRP) of CSI-RS corresponding to the predicted CRI, predicted synchronization signal block (SSB-index) index (p-SSB-index), or predicted RSRP for the predicted SSB index (p-SSB-index-RSRP), predicted synchronization signal / physical broadcast channel, It may include one or more of the SS / PBCH resource block indicator (p-SSBRI), predicted layer indicator (p-LI), predicted rank indicator (p-RI), or predicted layer 1 (L1)-reference signal received power (p-L1-RSRP).

[0024] The above CSI report setting information may include setting information for triggering states for CSI reporting, and CSI report-related settings associated with each of the triggering states for CSI reporting.

[0025] The above CSI report setting information may further include settings associated with the above RS resource.

[0026] According to one embodiment of the present disclosure, a base station can set AI / ML-based CSI reporting settings for a UE, thereby enabling the UE to perform AI / ML-based predictive information or CSI reporting that does not use AI / ML. In particular, when the CSI reporting type is periodic, semi-static, or non-periodic, the base station can set AI / ML-based CSI reporting settings for the UE according to each CSI reporting type. Furthermore, since AI / ML-based CSI reporting according to each CSI reporting type can be set while minimizing changes to current 3GPP standard specifications, there is an advantage of minimizing the impact on UEs that do not support AI / ML.

[0027] In addition, even in cases where AI / ML is not supported or the use of AI / ML methods is not required, UEs can perform AI / ML-based CSI reporting and / or legacy-style CSI reporting according to the CSI reporting settings according to the present disclosure.

[0028] FIG. 1 is a conceptual diagram illustrating an embodiment of a communication system.

[0029] FIG. 2 is a block diagram illustrating an example of a communication node constituting a communication system.

[0030] Figure 3a is a flowchart of a UE performing a CSI report to a base station based on a periodic CSI reporting method in a mobile communication system.

[0031] Figure 3b is a flowchart of a UE performing CSI reporting to a base station based on a semi-static or non-periodic CSI reporting method in a mobile communication system.

[0032] Figure 4 is a conceptual diagram illustrating the configuration of MAC-CE for activation / deactivation according to the semi-static CSI reporting method in a mobile communication system.

[0033] Figure 5 is a conceptual diagram illustrating the configuration of MAC-CE for activation / deactivation according to the non-periodic CSI reporting method in a mobile communication system.

[0034] The present disclosure is capable of various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the present disclosure to specific embodiments, and it should be understood that it includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the present disclosure.

[0035] Terms such as "first," "second," etc., may be used to describe various components, but said components should not be limited by said terms. Such terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of the present disclosure, the first component may be named the second component, and similarly, the second component may be named the first component. The term "and / or" includes a combination of a plurality of related described items or any of a plurality of related described items.

[0036] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0037] The terms used in this disclosure are used merely to describe specific embodiments and are not intended to limit this disclosure. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this disclosure, terms such as “comprising” or “having” are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0038] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which this disclosure pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this disclosure.

[0039] A communication system to which embodiments according to the present disclosure are applied will be described. The communication system to which embodiments according to the present disclosure are applied is not limited to the details described below, and embodiments according to the present disclosure may be applied to various communication systems. Here, the term "communication system" may be used interchangeably with "communication network."

[0040] Throughout the specification, a network may include, for example, wireless internet such as WiFi (wireless fidelity), mobile internet such as WiBro (wireless broadband internet) or WiMAX (world interoperability for microwave access), 2G mobile communication networks such as GSM (global system for mobile communication) or CDMA (code division multiple access), 3G mobile communication networks such as WCDMA (wideband code division multiple access) or CDMA2000, 3.5G mobile communication networks such as HSDPA (high speed downlink packet access) or HSUPA (high speed uplink packet access), 4G mobile communication networks such as LTE (long term evolution) networks or LTE-Advanced networks, and 5G mobile communication networks.

[0041] Throughout the specification, the term "terminal" may refer to a mobile station, mobile terminal, subscriber station, portable subscriber station, user equipment (UE), access terminal, etc., and may include all or part of the functions of a terminal, mobile station, mobile terminal, subscriber station, portable subscriber station, user equipment, access terminal, etc.

[0042] Here, a desktop computer, laptop computer, tablet PC, wireless phone, mobile phone, smartphone, smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital audio recorder, digital audio player, digital picture recorder, digital picture player, digital video recorder, digital video player, etc., capable of communicating with a terminal can be used.

[0043] Throughout the specification, the term "base station" may refer to an access point, a radio access station, a node B, an evolved node B, a base transceiver station, a mobile multihop relay (MMR)-BS, etc., and may include all or part of the functions of a base station, access point, radio access station, node B, eNodeB, base transceiver station, MMR-BS, etc.

[0044] Hereinafter, preferred embodiments of the present disclosure will be described in more detail with reference to the attached drawings. In order to facilitate an overall understanding of the present disclosure, the same reference numerals are used for identical components in the drawings, and redundant descriptions of identical components are omitted.

[0045] FIG. 1 is a conceptual diagram illustrating an embodiment of a communication system.

[0046] Referring to FIG. 1, the communication system (100) may include a plurality of communication nodes (110-1, 110-2, 110-3, 120-1, 120-2, 130-1, 130-2, 130-3, 130-4, 130-5, 130-6). The plurality of communication nodes may support 4G communication (e.g., LTE (long term evolution), LTE-A (advanced)), 5G communication (e.g., NR (new radio)), etc., as defined in the 3GPP (3rd generation partnership project) standard. 4G communication may be performed in a frequency band of 6 GHz or lower, and 5G communication may be performed not only in a frequency band of 6 GHz or lower but also in a frequency band of 6 GHz or higher.

[0047] For example, for 4G communication and 5G communication, multiple communication nodes can support communication protocols based on CDMA (code division multiple access), WCDMA (wideband CDMA), TDMA (time division multiple access), FDMA (frequency division multiple access), OFDM (orthogonal frequency division multiplexing), Filtered OFDM, CP (cyclic prefix)-OFDM, DFT-s-OFDM (discrete Fourier transform-spread-OFDM), OFDMA (orthogonal frequency division multiple access), SC (single carrier)-FDMA, NOMA (Non-orthogonal Multiple Access), GFDM (generalized frequency division multiplexing), FBMC (filter bank multi-carrier) based communication protocol, UFMC (universal filtered multi-carrier) based communication protocol, SDMA (Space Division Multiple Access) based communication protocol, etc.

[0048] Additionally, the communication system (100) may further include a core network. If the communication system (100) supports 4G communication, the core network may include an S-GW (serving-gateway), a P-GW (PDN (packet data network)-gateway), an MME (mobility management entity), etc. If the communication system (100) supports 5G communication, the core network may include a UPF (user plane function), an SMF (session management function), an AMF (access and mobility management function), etc.

[0049] Meanwhile, each of the plurality of communication nodes (110-1, 110-2, 110-3, 120-1, 120-2, 130-1, 130-2, 130-3, 130-4, 130-5, 130-6) constituting the communication system (100) may have the following structure.

[0050] FIG. 2 is a block diagram illustrating an example of a communication node constituting a communication system.

[0051] Referring to FIG. 2, the communication node (200) may include at least one processor (210), a memory (220), and a transceiver (230) that is connected to a network to perform communication. Additionally, the communication node (200) may further include an input interface device (240), an output interface device (250), a storage device (260), etc. Each component included in the communication node (200) may be connected by a bus (270) to communicate with one another.

[0052] However, each component included in the communication node (200) may be connected via individual interfaces or individual buses centered around the processor (210), rather than via a common bus (270). For example, the processor (210) may be connected via a dedicated interface to at least one of a memory (220), a transmission / reception device (230), an input interface device (240), an output interface device (250), and a storage device (260).

[0053] The processor (210) can execute a program command stored in at least one of the memory (220) and the storage device (260). The processor (210) may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which the methods according to embodiments of the present disclosure are performed. Each of the memory (220) and the storage device (260) may be composed of at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory (220) may be composed of at least one of read-only memory (ROM) and random access memory (RAM).

[0054] Referring again to FIG. 1, the communication system (100) may include a plurality of base stations (110-1, 110-2, 110-3, 120-1, 120-2) and a plurality of terminals (130-1, 130-2, 130-3, 130-4, 130-5, 130-6). The communication system (100) including the base stations (110-1, 110-2, 110-3, 120-1, 120-2) and terminals (130-1, 130-2, 130-3, 130-4, 130-5, 130-6) may be referred to as an "access network". Each of the first base station (110-1), the second base station (110-2), and the third base station (110-3) can form a macro cell. Each of the fourth base station (120-1) and the fifth base station (120-2) can form a small cell. The fourth base station (120-1), the third terminal (130-3), and the fourth terminal (130-4) may be located within the cell coverage of the first base station (110-1). The second terminal (130-2), the fourth terminal (130-4), and the fifth terminal (130-5) may be located within the cell coverage of the second base station (110-2). The fifth base station (120-2), the fourth terminal (130-4), the fifth terminal (130-5), and the sixth terminal (130-6) may be located within the cell coverage of the third base station (110-3). The first terminal (130-1) may be located within the cell coverage of the fourth base station (120-1). The sixth terminal (130-6) may be located within the cell coverage of the fifth base station (120-2).

[0055] Here, each of the multiple base stations (110-1, 110-2, 110-3, 120-1, 120-2) may be referred to as Node B, evolved Node B, base transceiver station (BTS), radio base station, radio transceiver, access point, access node, road side unit (RSU), radio remote head (RRH), transmission point (TP), transmission and reception point (TRP), eNB, gNB, etc.

[0056] Each of the multiple terminals (130-1, 130-2, 130-3, 130-4, 130-5, 130-6) may be referred to as a UE (user equipment), terminal, access terminal, mobile terminal, station, subscriber station, mobile station, portable subscriber station, node, device, IoT (Internet of Thing) device, mounted module / device / terminal or on board device / terminal, etc.

[0057] Meanwhile, each of the multiple base stations (110-1, 110-2, 110-3, 120-1, 120-2) may operate in different frequency bands or in the same frequency band. Each of the multiple base stations (110-1, 110-2, 110-3, 120-1, 120-2) may be connected to each other via an ideal backhaul link or a non-ideal backhaul link, and may exchange information with each other via an ideal backhaul link or a non-ideal backhaul link. Each of the multiple base stations (110-1, 110-2, 110-3, 120-1, 120-2) may be connected to a core network via an ideal backhaul link or a non-ideal backhaul link. Each of the multiple base stations (110-1, 110-2, 110-3, 120-1, 120-2) can transmit a signal received from the core network to the corresponding terminal (130-1, 130-2, 130-3, 130-4, 130-5, 130-6), and can transmit a signal received from the corresponding terminal (130-1, 130-2, 130-3, 130-4, 130-5, 130-6) to the core network.

[0058] In addition, each of the multiple base stations (110-1, 110-2, 110-3, 120-1, 120-2) can support MIMO transmission (e.g., SU (single user)-MIMO, MU (multi user)-MIMO, massive MIMO, etc.), CoMP (coordinated multipoint) transmission, CA (carrier aggregation) transmission, transmission in an unlicensed band, device-to-device communication (D2D) (or ProSe (proximity services)), etc. Here, each of the plurality of terminals (130-1, 130-2, 130-3, 130-4, 130-5, 130-6) can perform an operation corresponding to the base station (110-1, 110-2, 110-3, 120-1, 120-2) and an operation supported by the base station (110-1, 110-2, 110-3, 120-1, 120-2). For example, the second base station (110-2) can transmit a signal to the fourth terminal (130-4) based on the SU-MIMO method, and the fourth terminal (130-4) can receive a signal from the second base station (110-2) based on the SU-MIMO method. Alternatively, the second base station (110-2) can transmit a signal to the fourth terminal (130-4) and the fifth terminal (130-5) based on the MU-MIMO method, and each of the fourth terminal (130-4) and the fifth terminal (130-5) can receive a signal from the second base station (110-2) by the MU-MIMO method.

[0059] Each of the first base station (110-1), the second base station (110-2), and the third base station (110-3) can transmit a signal to the fourth terminal (130-4) based on the CoMP method, and the fourth terminal (130-4) can receive a signal from the first base station (110-1), the second base station (110-2), and the third base station (110-3) by the CoMP method. Each of the multiple base stations (110-1, 110-2, 110-3, 120-1, 120-2) can transmit and receive signals based on the CA method with terminals (130-1, 130-2, 130-3, 130-4, 130-5, 130-6) within its cell coverage area. Each of the first base station (110-1), the second base station (110-2), and the third base station (110-3) can control D2D between the fourth terminal (130-4) and the fifth terminal (130-5), and each of the fourth terminal (130-4) and the fifth terminal (130-5) can perform D2D by controlling each of the second base station (110-2) and the third base station (110-3).

[0060] Next, methods for configuring and managing wireless interfaces in a communication system will be described. Even when a method performed by a first communication node among the communication nodes (e.g., transmission or reception of a signal) is described, the corresponding second communication node may perform a method corresponding to the method performed by the first communication node (e.g., reception or transmission of a signal). That is, when the operation of a UE is described, the corresponding base station may perform an operation corresponding to the operation of the UE. Conversely, when the operation of a base station is described, the corresponding UE may perform an operation corresponding to the operation of the base station.

[0061] Meanwhile, in a communication system, a base station can perform all functions of the communication protocol (e.g., remote radio transmission and reception functions, baseband processing functions). Alternatively, among all functions of the communication protocol, the remote radio transmission and reception function may be performed by a TRP (transmission reception point) (e.g., f(flexible)-TRP), and among all functions of the communication protocol, the baseband processing function may be performed by a BBU (baseband unit) block. The TRP may be an RRH (remote radio head), RU (radio unit), TP (transmission point), etc. A BBU block may include at least one BBU or at least one DU (digital unit). A BBU block may be referred to as a "BBU pool," "centralized BBU," etc. A TRP may be connected to a BBU block via a wired fronthaul link or a wireless fronthaul link. A communication system composed of backhaul links and fronthaul links may be as follows. When the function split method of the communication protocol is applied, the TRP can selectively perform some functions of the BBU or some functions of MAC (medium access control) / RLC (radio link control).

[0062] In the present disclosure, a phrase containing "~ case (e.g., when ~)" may be expressed as a phrase containing "~ based on (e.g., based on ~)" or a phrase containing "~ in response to (e.g., in response to ~)". In other words, a phrase containing "~ case" may be interpreted as identical or similar to a phrase containing "~ based on" or a phrase containing "~ in response to".

[0063] Meanwhile, we will examine the procedure for channel state information (CSI) being reported from the UE to the base station in a 5G mobile communication system, also known as new radio (NR), with reference to FIGS. 3a and 3b.

[0064] Figure 3a is a flowchart of a UE performing a CSI report to a base station based on a periodic CSI reporting method in a mobile communication system.

[0065] Referring to FIG. 3a, in step S310, the base station can transmit upper layer configuration information to the UE. The upper layer configuration information may be transmitted, for example, by a radio resource control (RRC) signaling message. The RRC signaling message may include information on the transmission type and CSI reporting type of the CSI-reference signal (RS) (CSI-RS) transmitted to the UE. Since FIG. 3a describes a periodic CSI reporting method, it is assumed that the CSI-RS transmission type is periodic and the CSI reporting type is periodic.

[0066] In step S312, the base station can transmit periodic CSI-RS. Therefore, the UE can receive the periodic CSI-RS transmitted by the base station in step S312. Since base stations generally use the Multiple Input Multiple Output (MIMO) method in 5G NR, CSI-RS can be transmitted through multiple beams. Therefore, the UE can receive the CSI-RS corresponding to each beam through the multiple beams transmitted by the base station. The UE can measure the received CSI-RS. The UE can generate a CSI report message based on the received RRC signaling message and the measured values ​​of the CSI-RS.

[0067] In step S314, the UE can transmit the generated CSI report message to the base station. The timing of transmission of the CSI report message can be determined based on the RRC signaling message in step S310. Since the embodiment of FIG. 3a is a case where periodic measurement reporting is performed, it can be transmitted based on the reporting period set in the RRC signaling message.

[0068] Figure 3b is a flowchart of a UE performing CSI reporting to a base station based on a semi-static or non-periodic CSI reporting method in a mobile communication system.

[0069] Referring to FIG. 3b, in step S320, the base station can transmit upper layer configuration information to the UE. The upper layer configuration information may be transmitted, for example, by an RRC signaling message. The RRC signaling message may include information on the transmission type and CSI reporting type of CSI-RS transmitted to the UE. Since FIG. 3b illustrates a semi-persistent CSI reporting method or an aperioditic CSI reporting method, it is assumed that the CSI-RS transmission type is aperioditic or semi-persistent.

[0070] In step S322, the base station may transmit a CSI report triggering message to the UE. The CSI report triggering message may consist of only one message or two messages. It should be noted that Figure 3b is illustrated as a single form for convenience of explanation. For example, a triggering message for semi-static CSI reporting may be triggered by a medium access control-control element (MAC-CE) message and downlink control information (DCI). A triggering message for non-periodic CSI reporting may be triggered by the DCI. Such triggering is described in more detail with reference to Table 1, which is described below.

[0071] In step S324, the base station may transmit semi-static or non-periodic CSI-RS. Therefore, the UE may receive the semi-static or non-periodic CSI-RS transmitted by the base station in step S324. As previously described, since the base station generally uses the MIMO method, the CSI-RS may be transmitted through multiple beams. Therefore, the UE may receive the CSI-RS corresponding to each beam through the multiple beams transmitted by the base station. The UE may measure the received CSI-RS. The UE may generate a CSI report message based on the measured values ​​of the CSI-RS and the received RRC signaling message.

[0072] In step S326, the UE can transmit the generated CSI report message to the base station. The timing of transmission of the CSI report message can be determined based on the received DCI.

[0073] The CSI report configuration described in the procedure of FIG. 3a and FIG. 3b described above may be provided to the UE by an RRC signaling message. The CSI report configuration (CSI-RrportConfig) information element (IE) transmitted by the RRC signaling message may include information elements such as a report configuration identifier (reportConfigId), resources for channel measurement (resourcesForChannelMeasurement), resources for interference measurement (resourcesForInterferenceMeasurement), report configuration type (reportConfigType), report quantity (reportQuantity), report frequency configuration (reportFreqConfiguration), time restriction for channel measurement (timeRestrictionForChannelMeasurements), time restriction for interference measurement (timeRestrictionForInterferenceMeasurements), and codebook configuration (codebookConfig).

[0074] The IEs exemplified above are for the purpose of facilitating understanding of the present disclosure and only some configurations of the RRC signaling message are described as examples; additional IEs may be included in addition to those exemplified above. In the CSI report configuration, the CSI report type may be configured as any one of the aperioditic reporting method, the semipersistent reporting method, or the periodic reporting method by the report configuration type (reportConfigType) IE, as described in FIGS. 3a and 3b.

[0075] Representative CSIs used in 5G NR include channel quality information (CQI), precoding matrix indicator (PMI), CSI-RS resource indicator (CRI), synchronization signal / physical broadcast channel (SS / PBCH) resource block indicator (SSSBRI), layer indicator (LI), rank indicator (RI), and layer 1 (L1)-reference signal received power (L1-RSRP).

[0076] Among the CSI examples above, the CSI reporting settings allow you to configure reporting for CSI-related quantities or L1-RSRP-related quantities via the ReportQuantity IE. A typical example of L1-RSRP-related quantities is the reporting of beam-related information for beam management (BM). In this case, CRI, SSBRI, etc., can be reported for specific beam indications, and corresponding L1-RSRP values ​​can be reported together for quality reporting regarding that beam. In addition to BM-related matters, CSI can be configured to report CSI-related quantities such as PMI, RI, and CQI. Furthermore, various other reporting-related information settings can be configured.

[0077] The configuration for CSI reporting can be broadly divided into two parts. For example, it can be divided into configuration information for triggering states for CSI reporting, and CSI reporting-related configurations associated with each of the triggering states for CSI reporting.

[0078] The UE may receive from the base station configuration information for one or more CSI-ReportConfigs for CSI report-related report settings and one or more CSI-ResourceConfigs for resource settings, and one or two CSI report triggering state lists (TriggeringStateList) containing multiple triggering states. The CSI report triggering state lists may be, for example, a CSI aperiodic triggering state list (CSI-AperiodicTriggerStateList) and / or a semi-static CSI triggering state list on PUSCH (CSI-SemiPersistentOnPUSCH-TriggerStateList). Triggering states within the CSI report triggering state lists may be associated with the configuration information of the CSI-ReportConfigs and CSI-ResourceConfigs.

[0079] In addition, configuration information related to CSI reporting is defined, and configuration information related to CSI reporting can be configured through association.

[0080] Additionally, the CSI-ReportConfig can be associated with the CSI-ResourceConfig. The values ​​of the CSI-ReportConfig and CSI-ResourceConfig can be associated with resource configuration information that includes resource configuration information of the reference signal (RS) transmitted for CSI reporting. The resource configuration information of the RS may refer, for example, to resource configuration information related to the CSI-RS or the synchronization signal block (SSB).

[0081] CSI reporting can be performed based on the configuration information described above. At this time, the report configuration available according to the CSI-RS configuration can be configured as shown in Table 1 below. Table 1 below is the content of Table 5.2.1.4-1 of 3GPP TS 38.214, a standard specification for mobile communication systems.

[0082] CSI-RS Configuration Periodic CSI Reporting Semi-static CSI Reporting Non-periodic CSI Reporting Periodic CSI-RS Dynamic Triggering / Enable None For PUCH reporting, the UE receives an enable command as described in Section 6.1.3.16 of [10, TS 38.321]. For PUCH reporting, the UE receives triggering from the DCI. Triggered by the DCI; also, the sub-selection indication described in Section 6.1.3.13 of [10, TS 38.321] is available as defined in Section 5.2.1.5.1. Semi-static CSI-RS Not Supported For PUCH reporting, the UE receives an enable command as described in Section 6.1.3.16 of [10, TS 38.321]. For PUCH reporting, the UE receives triggering from the DCI. Triggered by the DCI; Also, the sub-selection indications described in Section 6.1.3.13 of [10, TS 38.321] are possible as defined in Section 5.2.1.5.1. Non-periodic CSI-RS not supported not supported triggered by DCI; also, the sub-selection indications described in Section 6.1.3.13 of [10, TS 38.321] are possible as defined in Section 5.2.1.5.1.

[0083] As exemplified in Table 1 above, in an environment where periodic CSI-RS is configured (as in Fig. 3a), the UE can perform periodic CSI reporting after RRC configuration without triggering / activation for CSI reporting by DCI or MAC-CE. On the other hand, in the case of semi-static CSI reporting or non-periodic CSI reporting (as in Fig. 3b), CSI reporting operations can be performed by triggering / activation for CSI reporting by DCI or a combination of MAC-CE and DCI based on configured information.

[0084] Based on Table 1 above, it can be seen that in an environment where semi-static CSI-RS is configured, it is impossible for the UE to periodically report CSI, and the UE can report CSI semi-permanently or non-periodically through triggering / activation by DCI or MAC-CE.

[0085] In addition, based on Table 1 above, in an environment where non-periodic CSI-RS is configured, the UE cannot report CSI periodically and semi-statically, and the UE can only report CSI non-periodically through triggering / activation by DCI or MAC-CE.

[0086] Meanwhile, artificial intelligence (AI) / machine learning (ML)-based beam management technology was introduced as one of the consensus points at the 3GPP standardization body. Additionally, CSI prediction and CSI compression technologies are also highly likely to be introduced at the 3GPP standardization body. If AI / ML-based beam management and CSI prediction and / or CSI compression are introduced, the UE must be supported with the ability to report at least the results of measuring a specific RS transmitted by the base station and / or the output values ​​from the UE's AI / ML model—in other words, the prediction results. However, a method for the UE to report the results of measuring a specific RS received from the base station and / or the prediction results from the UE's AI / ML model has not yet been presented.

[0087] The present disclosure described below describes a method for a UE to report the result of measuring a specific RS received from a base station and / or the result of a prediction from the UE's AI / ML model. To perform such a method, the UE may have an AI / ML model in an AI / ML-based air interface technology. In the following description, an AI / ML model that is loaded on or runs on the UE will be referred to as a UE-side model. The AI / ML model may also be loaded on or run on a network (e.g., a base station). In the following description, an AI / ML model that is loaded on or runs on a network will be referred to as a Network-side model (NW-side model). Additionally, for convenience of explanation, it is assumed that the network is a base station.

[0088] When an AI / ML model is deployed on both the UE and the network, it may be referred to as a two-sided model, and when an AI / ML model is deployed on only one side, either the UE or the network, it may be referred to as a one-sided model.

[0089] In the case of the UE-side model and the two-side model, the UE may be equipped with an AI / ML model (the UE possesses an AI / ML model). The UE receives a reference signal (RS) transmitted by the base station and can input a measured value of the received RS (e.g., a measured value of reference signal received power (RSRP), or a measured value for beam management (BM), etc.) into the UE-side model. The UE-side model can output a specific prediction value based on the measured RS value. The UE can report the prediction value of the UE-side model to the base station.

[0090] For example, when a UE-side model makes predictions related to a beam, the UE may report identification (ID) information and quality information for the beam to the base station. The ID for the beam may include one of the Channel State Information-Reference Signal Resource Indicator (CRI) or the Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) Block Resource Indicator (SSBRI). Additionally, the quality information for the beam may include Layer 1-RSRP (L1-RSRP) and Signal-to-Interference Noise Ratio (SINR) information.

[0091] In this case, since the information reported by the UE to the base station is the output of the UE-side model, the beam ID can be the CRI or SSBRI predicted by the UE-side model, and the beam quality information can be the L1-RSRP, SINR, etc. predicted by the UE-side model.

[0092] The UE may report all beams predicted by the UE-side model—that is, all predicted values—to the base station, or may report predicted value(s) for some beams to the base station. If the information included in the report message reported by the UE to the base station contains predicted values ​​for only a portion of the CSI information, the remaining information may contain actual measured values ​​of the CSI information.

[0093] If the UE-side model predicts CSI information for the channel in addition to the BM, the UE may generate a report message containing predicted information related to the channel quality indicator (CQI), precoding matrix indicator (PMI), CRI, SSBRI, layer indicator (LI), rank indicator (RI), L1-RSRP, and SINR. The UE may report (or transmit) the generated report message to the base station. Even when the UE-side model predicts CSI information for the channel, the CSI information included in the report message may consist entirely of predicted values ​​or only partially of predicted value(s). If only partially of the CSI information included in the report message consists of predicted value(s), the remainder of the CSI information may include actual measured value(s).

[0094] Meanwhile, in the case of a network-side model or a two-side model, the base station may carry (or include) the network-side model. The base station transmits RS to the UE and may receive measurement information and / or prediction information of the RS from the UE via a report message. The base station may input the measurement values ​​and / or prediction values ​​included in the received report message into the network-side model. The network-side model may output a specific prediction value using the measurement values ​​and / or prediction values.

[0095] The case where the input to the network-side model consists only of measurement values ​​may be any one of the following: the UE does not have a UE-side model; even if a UE-side model exists, it is not used; or even if a UE-side model exists and is used, the base station inputs only the measurement values ​​included in the report message into the network-side model.

[0096] If the input of the network-side model is a predicted value of the UE-side model, the input of the network-side model may be one or more of the output values ​​of the UE-side model described above. In other words, the input of the network-side model may be one or more of the predicted CQI, predicted PMI, predicted CRI, predicted SSBRI, predicted LI, predicted RI, predicted L1-RSRP, or predicted SINR. As another example, the input of the network-side model may be one or more values ​​obtained by compressing the channel values ​​estimated by RS, or values ​​obtained by modifying the estimated channel values ​​by a specific method.

[0097] For example, when using two-sided models, the UE can transmit a report message containing reporting information to the base station. The reporting information may be channel values ​​(or information) estimated by the UE using RS received from the base station. Alternatively, the reporting information may be the data in its original form (output source) output from the UE-side model based on CSI information. The base station may use the reporting information included in the report message (e.g., channel values ​​estimated by the UE or original output data output from the UE-side model) as input to the network-side model. The network-side model may output specific information based on the input information. In this case, if the input information of the network-side model is the output information of the UE-side model, the output of the network-side model may be the reconstructed information of that specific information. In such cases, where the UE-side model compresses specific information and the network-side model reconstructs it, the UE-side model and the network-side model can be understood as auto-encoders. Therefore, when the UE-side model and the network-side model operate as auto-encoders, the value reported by the UE may simply be the output value generated by the UE-side model.

[0098] Meanwhile, in the present disclosure described below, a CSI reporting method in which an AI / ML wireless interface is not used is referred to as legacy CSI reporting. Additionally, in the present disclosure, a CSI reporting method in which an AI / ML wireless interface is used is referred to as AI / ML CSI reporting. Cases where an AI / ML wireless interface is used may include both the UE-side model and the network-side model, which are the one-sided models described above, and the two-sided model.

[0099] Legacy CSI reports may be reports containing both CSI-related quantities and L1-RSRP-related quantities. Additionally, AI / ML CSI reports may include both CSI-related quantities and L1-RSRP-related quantities from legacy CSI reports, and may also include newly defined quantities. For example, AI / ML CSI reports may be channel values ​​estimated based on RS, and / or values ​​that have been compressed or modified.

[0100] [First Embodiment: Upper-level Signaling for AI / ML CSI Reporting]

[0101] In the first embodiment described below, the configuration of an upper layer signaling message is described when a base station transmits an upper layer signaling (e.g., RRC signaling) message to a UE having a UE-side model.

[0102] In the embodiments of FIGS. 3a and 3b described above, when the UE has a UE-side model, the RRC signaling message described below can be transmitted from the base station to the UE. For example, in the case of FIG. 3a, the RRC signaling message can be transmitted from the base station to the UE in step S310, and in the case of FIG. 3b, the RRC signaling message can be transmitted from the base station to the UE in step S320.

[0103] RRC signaling messages may include CSI-ReportConfig IE as previously described. Legacy CSI-ReportConfig IE may include reportQuantity information as previously described. ReportQuantity information may be configured, for example, as shown in Table 2 below.

[0104] reportQuantity CHOICE {none NULL,cri-RI-PMI-CQI NULL,cri-RI-i1 NULL,cri-RI-i1-CQI SEQUENCE {pdsch-BundleSizeForCSI ENUMERATED {n2, n4} OPTIONAL -- Need S},cri-RI-CQI NULL,cri-RSRP NULL,ssb-Index-RSRP NULL,cri-RI-LI-PMI-CQI NULL},

[0105] Each parameter of the reporting quantity of the legacy CSI reporting settings IE included in the RRC signaling message example in Table 2 may have the following meanings.

[0106] - none: Field to set no CSI reports

[0107] - cri-RI-PMI-CQI: Fields for setting the reporting of CRI indicating optimal CSI-RS resources (beams), RI indicating the number of transport layers, PMI indicating the precoding matrix, and CQI indicating channel quality.

[0108] - cri-RI-i1: A field for setting the reporting of CRI indicating the optimal CSI-RS resource (beam), RI indicating the number of transport layers, and i1 indicating the PMI level 1 (coarse) index.

[0109] - cri-RI-i1-CQI: A field for setting the reporting of CRI, indicating optimal CSI-RS resources (beams); RI, indicating the number of transport layers; i1, indicating the PMI level 1 (coarse) index; and CQI, indicating channel quality.

[0110] - cri-RI-CQI: A field for setting the reporting of CRI indicating optimal CSI-RS resources (beams), RI indicating the number of transport layers, and CQI indicating channel quality.

[0111] - cri-RSRP: A field for configuring to report the CRI indicating the optimal CSI-RS resource (beam), and the RSRP of the CSI-RS corresponding to that CRI.

[0112] - ssb-Index-RSRP: Field for setting the reporting of the SSB index and the RSRP of the corresponding SSB

[0113] - cri-RI-LI-PMI-CQI: Fields for setting the reporting of CRI indicating optimal CSI-RS resources (beams), RI indicating the number of transport layers, LI indicating the layer combination, PMI indicating the precoding matrix, and CQI indicating channel quality.

[0114] As examined above, the report quantity of legacy RRC signaling messages does not include CSI information predicted by the UE-side model. Therefore, in this disclosure, CSI values ​​predicted by the UE-side model may be added in addition to the report quantity of the legacy CSI reporting setting IE included in the RRC signaling message. In other words, Table 2 above is an example of a legacy CSI report quantity, and the report quantity (reportQuantity) to support AI / ML-based CSI reporting may include values ​​indicating predicted resource indicators and / or predicted quality indicators. Values ​​indicating predicted resource indicators and / or predicted quality indicators may be expressed, for example, as p-cri-r19, p-cri-RSRP-r19, p-ssb-index-r19, p-ssb-index-RSRP-r19, etc., where the "p-" at the beginning may indicate a predicted value and the "-r19" at the end may indicate a release version of the 3GPP standard. Therefore, the values ​​indicating predicted resource indicators and / or predicted quality indicators may be predicted values ​​of the same information as the values ​​exemplified in Table 2. For example, among the predicted CSI values, the predicted CRI and / or predicted SSB index corresponding to the resource indicator may be set to p-cri-r19 and / or p-ssb-index-r19 as the reported quantity values. In this case, the UE-side model may be applied in both cases: when the UE has a UE-side model in a one-sided model or when the UE has a UE-side model in a two-sided model. there is.

[0115] According to the present disclosure, the base station may include a setting for CSI values ​​predicted by a UE-side model in the reporting quantity of an RRC signaling message. The setting for predicted CSI values ​​may include field(s) indicating the predicted value, such as, for example, the "predicted cri-RI-LI-PMI-CQI" field, the "predicted cri-RI-i1" field, etc. The field names included in the reporting quantity of the RRC signaling message as described above are examples for convenience of explanation and are not limited thereto. Additionally, a higher-level parameter indicating the predicted value may be included in the CSI-ReportConfig to indicate that each of the fields exemplified above is used for prediction-based CSI reporting in the RRC signaling message. If the predicted cri-RI-LI-PMI-CQI field is used, the base station may be configured to report the predicted CRI, predicted RI, predicted LI, predicted PMI, and predicted CQI to the UE. In the same way, when the predicted cri-RI-i1 field is used, the base station can be configured to report the predicted CRI, predicted RI, and predicted i1 to the UE.

[0116] As another example, the base station may configure the fields of the report quantity of the RRC signaling message as follows to report a predicted value for only a specific value. For example, the "cri-ri-predicted PMI-CQI" field may be included in the report quantity within the RRC signaling message to ensure that only the configured report information for predicted CSI values ​​is in a predicted form. When the cri-ri-predicted PMI-CQI field is used among the fields included in the report quantity of the RRC signaling message, the UE may interpret that the CRI, RI, and CQI are configured to report measured values ​​from the base station, and that only the PMI predicted by the UE-side model is configured to report.

[0117] The above example is merely one example to aid in understanding the present disclosure, and various modifications may be possible to report values ​​predicted by the UE-side model for only one specific value or two or more values. For example, if the cri-ri-predicted PMI-predicted CQI field is used as a modified form of the field described above, the UE may interpret CRI and RI as being set to report measured values, and PMI and CQI as being set to report values ​​predicted by the UE-side model.

[0118] Based on the above, the base station may be configured to report predicted values ​​by adding "prediction" to specific one or more values ​​for which the UE-side model's predicted values ​​are required in the report quantity fields of the RRC signaling message, or it may be configured to report predicted values ​​of the UE-side model for all values ​​of a specific parameter.

[0119] The UE can receive report quantity fields from the base station via an RRC signaling message. Based on the settings of the report quantity fields in the RRC signaling message, the UE may report predicted values ​​only for the value(s) set to be reported by the UE-side model, and report measured values ​​for other value(s). Additionally, in the case of periodic CSI reporting as described above in FIG. 3a and Table 1, the UE may perform periodic CSI reporting based on the settings of the RRC signaling message, and in the case of semi-static or non-periodic reporting as described in FIG. 3b and Table 1, the UE may perform CSI reporting based on the settings of the RRC signaling message and triggering on MAC-CE and / or DCI.

[0120] Meanwhile, when CSI reporting for beam management (BM) is configured, the UE can report index information and quality information for the beam to the base station through the settings of the cri-RSRP field, ssb-Index-RSRP field, etc. among the reporting quantities in Table 2.

[0121] Even in this case, as described above, if the UE is equipped with a UE-side model, the base station may configure the UE to report the predicted beam index field and the predicted L1-RSRP as described prior to the CSI reporting settings. Accordingly, the UE can receive and measure the RS from the base station based on the RRC configuration information. The UE can input the measured RS into the UE-side model to obtain the predicted beam index and the predicted L1-RSRP from the UE-side model. Then, the UE can report (or transmit) a report message containing the predicted beam index and the predicted L1-RSRP values ​​to the base station. Regarding the CSI reporting method for the BM, the RRC signaling message may also be configured to use the predicted value(s) of the UE-side model for all values ​​or only some values, in the same manner as the CSI reporting settings mentioned above.

[0122] As another example, RRC signaling messages for a BM may be configured to report both the value (or information) measured by the UE and the predicted value (or information) together without predictions from the UE-side model. For example, the reported quantity information of the RRC signaling message may include a cri-RSRP field and an ssb-Index-RSRP field to configure the reporting of the value measured by the UE, along with a predicted cri-RSRP (e.g., p-cri-RSRP-r19) field and a predicted ssb-Index-RSRP (e.g., p-ssb-index-RSRP-r19) field to configure the reporting of the value based on the prediction of the UE-side model. In this case, the UE may understand from the cri-RSRP field included in the reported quantity of the RRC signaling message received from the base station that the reporting is configured to include the CRI indicating the optimal CSI-RS resource (beam) based on the UE's measurement, and the RSRP of the CSI-RS corresponding to that CRI. Additionally, the UE can understand from the ssb-Index-RSRP field that the SSB index (Index) and the reporting of the RSRP of the corresponding SSB are set.

[0123] In addition, the UE may understand that the CRI indicating the optimal CSI-RS resource (beam) predicted using the UE-side model based on the predicted cri-RSRP field and the predicted ssb-Index-RSRP field, the predicted value of the RSRP of the CSI-RS corresponding to the CRI, the predicted SSB index, and the report of the predicted RSRP of the corresponding SSB are set. In this case, the UE can generate a report message containing the measured values ​​and the predicted values ​​based on the report quantity information of the RRC signaling message, and can transmit (or report) the generated report message to the base station.

[0124] In another embodiment, the reported quantity information of the RRC signaling message may be new information in which the output values ​​of the UE-side model according to the present disclosure do not take on a specific CSI form. For example, the reported quantity information of the RRC signaling message may be set in both models to a value based on a specific method of reporting the output value of the UE-side model to the base station. In this case, the UE may compose a report message with a value (or information) of a specific method obtained through the UE-side model based on the reported quantity information of the RRC signaling message received from the base station. The UE may transmit (or report) the report message generated based on the reported quantity information of the RRC signaling message to the base station. The base station may use the value (or information) included in the report message received from the UE as an input to the network-side model. The network-side model may output CSI information using the output information of the UE-side model. In other words, the base station may obtain CSI information using the value included in the report message received from the UE. In this case, the reported quantity may be set to a different field from the reported quantity included in the legacy RRC signaling message. In other words, the base station may set the reported quantity within the RRC signaling message as a parameter of a form other than CSI, thereby allowing the base station to set a parameter for acquiring CSI information. For convenience of explanation, the output value of the UE-side model that does not take on a specific CSI form in the disclosure described below is referred to as "compressed CSI."

[0125] The base station may include a "compressed CSI" parameter in the report quantity of an RRC signaling message to configure the UE to output a compressed CSI using a UE-side model. If the compressed CSI parameter is included in the report quantity of the RRC signaling message received from the base station, the UE may output a compressed CSI value that does not take on a specific CSI form using the UE-side model as described above. The UE may transmit a report message containing the compressed CSI to the base station.

[0126] The first embodiment described above can be applied by changing the configuration and / or definition of the upper layer signaling message in the legacy method described earlier in FIG. 3a and 3b.

[0127] [Second Embodiment: Method for configuring AI / ML CSI reporting using CSI reporting settings]

[0128] In the second embodiment described below, the configuration of the upper layer signaling message is explained when a base station transmits an upper layer signaling (e.g., RRC signaling) message to a UE having a UE-side model as described in the first embodiment.

[0129] In the second embodiment of the present disclosure, unlike the first embodiment described above, an AI / ML-dedicated CSI report may be indicated or configured in the CSI-ReportConfig IE transmitted via an RRC signaling message. If an AI / ML-dedicated CSI report is not configured (or indicated) in the CSI-ReportConfig IE received from the base station based on the method of the second embodiment of the present disclosure, the UE may interpret it as a legacy CSI report method. On the other hand, if an AI / ML-dedicated CSI report is configured (or indicated) in the CSI-ReportConfig IE received from the base station, the UE may interpret it as a method of transmitting a value predicted by a UE-side model included in the CSI report. For example, if an AI / ML-dedicated CSI report is configured and a legacy report quantity (reportQuantity) is included, the UE may interpret the legacy report quantity as the predicted value. As another example, if an AI / ML-dedicated CSI report is configured and includes a reportQuantity containing report quantity fields of predicted values ​​(e.g., p-cri-r19, p-cri-RSRP-r19, etc.) as described above, the UE can interpret the report quantity of predicted values ​​as the predicted values.

[0130] To facilitate the distinction between legacy CSI reporting settings and UE-side model-only reporting settings regarding the CSI-ReportConfig IE transmitted via RRC signaling messages, the CSI-ReportConfig IE may include setting (or instruction) information to configure (or indicate) whether the CSI reporting uses an AI model (i.e., a UE-side model). For convenience of explanation, the information included in the CSI-ReportConfig IE for configuring (or indicating) whether the CSI reporting uses an AI model will be referred to as the "First Indicator" below. The First Indicator may be included, for example, as a specific upper-level parameter within the CSI-ReportConfig IE to indicate that the corresponding CSI-ReportConfig is an AI / ML-based CSI reporting setting.

[0131] A UE that receives a CSI reporting setting IE including a first indicator may operate in a legacy CSI reporting manner or in a CSI reporting manner using a UE-side model based on the received CSI reporting setting IE. In other words, a UE that receives a CSI reporting setting IE including a first indicator may operate differently from the legacy CSI reporting manner if the first indicator indicates a CSI manner using a UE-side model.

[0132] The first indicator can be set explicitly or implicitly using a specific field of the CSI report setting IE.

[0133] When the first indicator is configured in an implicit manner, the base station may configure, for example, at least one of the order, type, or size of each configuration field of the CSI reporting configuration IE to differ from the configuration for legacy CSI reporting. In other words, if each field of the CSI reporting configuration IE has the same order, type, and size as the legacy field, the UE may interpret the received CSI reporting configuration IE as the legacy CSI reporting configuration IE. On the other hand, if each field of the CSI reporting configuration IE differs from the legacy field in one or more of the order, type, or size, the UE may interpret it as a CSI reporting method using the UE-side model. Therefore, in the case of the implicit method, the first indicator can be understood as one or more of the field order, type, or size of the CSI reporting configuration IE.

[0134] Next, when the first indicator is explicitly set, various forms are possible. For example, a dummy field or an unused field within the CSI reporting settings IE can be used to indicate either the legacy CSI reporting settings or the CSI reporting settings using a UE-side model.

[0135] As another example, value(s) for some fields within the CSI reporting configuration IE are assigned as CSI reporting-specific identifiers (IDs) using an AI / ML model; if the field identifier has a CSI reporting-specific ID, the UE interprets it as a CSI reporting configuration using a UE-side model, and if the field identifier does not have a CSI reporting-specific ID, the UE interprets it as a legacy CSI reporting configuration.

[0136] As a more specific example, the number of CSI-ReportConfigIds can be set from 0 to "maxNrofCSI-ReportConfigurations - 1", where maxNrofCSI-ReportConfigurations is the maximum number of CSI report configurations.

[0137] For the sake of convenience in the following description, it is assumed that the maximum number of CSI report configurations (maxNrofCSI-ReportConfigurations) is 48. Additionally, when the maxNrofCSI-ReportConfigurations value is 48, it can be assumed that among the total 48 CSI-ReportConfigIds, 0 to 23 are allocated only for legacy CSI reporting, and maxNrofCSI-ReportConfigurations values ​​24 to 47 are used for AI / ML CSI reporting.

[0138] When the above assumptions apply, the UE can distinguish whether a CSI report configuration is a legacy CSI report or an AI / ML CSI report based on the CSI-ReportConfigId information within the CSI report configuration, which is an RRC message received from the base station. When distinguishing between legacy CSI reports and AI / ML CSI reports using CSI-ReportConfigId information in this manner, the field order and size of the CSI-ReportConfigId within the CSI report configuration IE can be the same for both legacy CSI reports and AI / ML CSI reports.

[0139] The maximum number of CSI-ReportConfigurations assumed above (maxNrofCSI-ReportConfigurations) is an example to aid in understanding the present disclosure and may be set to a number less or greater than the value exemplified in the present disclosure. For example, the number of legacy CSI-ReportConfiguration identifiers (IDs) and the number of AI / ML-specific CSI-ReportConfiguration identifiers (IDs) may be set differently. maxNrofCSI-ReportConfigurations and the number of identifiers assigned to each CSI-ReportConfiguration may be transmitted via higher-level signaling, such as RRC signaling messages, or via system information (SI). SI may be, for example, a master information block (MIB) and / or a system information block (SIB).

[0140] [Third Embodiment: Method for Establishing AI / ML CSI Reporting Using DCI or MAC-CE]

[0141] In the third embodiment of the present disclosure, a case is described where CSI reporting of the UE-side model is triggered by DCI or MAC-CE. As previously described in FIG. 3a, in the case of periodic CSI reporting, CSI reporting can be set only by RRC signaling messages. This can be applied equally to CSI reporting using AI / ML.

[0142] Accordingly, the case where the CSI reporting described in the third embodiment is triggered by DCI and / or MAC-CE may apply to semi-static or non-periodic CSI reporting. In other words, the case where either AI / ML-based CSI reporting or legacy CSI reporting methods are triggered by DCI and / or MAC-CE may correspond to semi-static or non-periodic CSI reporting.

[0143] To explain this in more detail, as previously described in FIG. 3b, the base station (gNB) can set up CSI reporting using an RRC signaling message, and the set CSI reporting method can be either a semi-static or aperiodic reporting method (S320). Accordingly, the UE can receive an RRC signaling message from the base station at step S320. The received RRC signaling message can set the CSI reporting method to either a semi-static or aperiodic reporting method.

[0144] In step S322, the base station may trigger a CSI report, and in step S326, it may transmit a semi-static CSI-RS or aperiodic CSI-RS. In step S322, the UE receives a MAC-CE and / or DCI from the base station that triggers a CSI report, and may receive a semi-static CSI-RS or aperiodic CSI-RS transmitted by the base station based on the MAC-CE and / or DCI.

[0145] At step S326, the UE may include the received CSI-RS measurement(s) and / or value(s) estimated by an AI / ML model in a CSI report message and transmit it to the base station. In a third embodiment of the present disclosure, a method is described in which MAC-CE and / or DCI determine whether the CSI report message is a legacy CSI report or a CSI report based on a UE-side model.

[0146] The triggering of CSI report messages (or the activation of CSI reporting) may be triggered by DCI alone, by MAC-CE alone, or by a combination of MAC-CE and DCI. Additionally, the physical uplink control channel (PUCCH) or physical uplink shared channel (PUSCH) through which CSI report messages are transmitted may be assigned differently depending on the non-periodic CSI reporting method or the semi-static reporting method.

[0147] When the triggering of a CSI report message (or the activation of a CSI report) is directed by the DCI, the triggering indicator for the CSI report message (hereinafter referred to as the "second indicator") may indicate a specific triggering state within the CSI report triggering state list set in the RRC signaling message or MAC-CE. Here, the triggering state may be associated with one or more CSI report configurations (CSI-ReportConfig). Additionally, a CSI-ReportConfig may be associated with one or more CSI resource configurations (CSI-ResourceConfig). By associating these configuration details with other detailed configuration details, all information required for a CSI report can be configured in association with other detailed configuration details. When performing a CSI report, the UE can perform the CSI report based on these associated configurations.

[0148] Different CSI reporting triggering state list(s) can be configured for semi-static CSI reporting methods or non-periodic CSI reporting methods. Alternatively, different list(s) can be configured for semi-static CSI-RS or non-periodic CSI-RS settings. Regarding the method of configuring CSI reporting triggering state list(s), different forms of CSI reporting triggering state list(s) can be configured through various combinations of CSI reporting triggering state list(s). In such cases, the base station may configure one or more CSI reporting triggering state list(s) for the UE.

[0149] Additionally, the CSI reporting triggering state list according to the present disclosure may be configured differently from the CSI reporting triggering state list according to the legacy CSI reporting method using AI / ML. For example, in the case of a legacy UE that does not support AI / ML operations, the base station may set one non-periodic CSI reporting triggering state list and one semi-static CSI reporting triggering state list to the UE via either an RRC signaling message and / or MAC-CE. In other words, the legacy UE may be set with two CSI reporting triggering state lists from the base station.

[0150] For a UE with a UE-side model, the base station may additionally set an AI / ML aperiodic CSI reporting triggering state list and an AI / ML semi-static CSI reporting triggering state list for the UE with the UE-side model, in addition to the two CSI reporting triggering state lists based on the legacy method. In other words, a UE with a UE-side model may receive one aperiodic CSI reporting triggering state list, one semi-static CSI reporting triggering state list, an AI / ML aperiodic CSI reporting triggering state list, and an AI / ML semi-static CSI reporting triggering state list from the base station via RRC signaling messages and / or MAC-CE messages. A UE with a UE-side model that has received these four CSI reporting triggering state lists may perform CSI reporting based on the method directed by the MAC-CE and / or DCI from the base station.

[0151] When a base station sets four CSI reporting triggering state lists for a UE having a UE-side model as described above, each of the CSI reporting triggering state lists can be configured with different state lists. As another example, when a base station sets CSI reporting triggering state lists for a UE having a UE-side model as described above, CSI reporting triggering state lists may be configured separately for semi-static CSI reporting settings and non-periodic CSI reporting settings, regardless of AI / ML. As yet another example, when a base station sets CSI reporting triggering state lists for a UE having a UE-side model as described above, a single AI / ML CSI reporting triggering state list may be configured regardless of the CSI reporting method and CSI-RS settings. As yet another example, the base station may additionally configure a state list for AI / ML CSI reporting within the non-periodic CSI reporting triggering state list corresponding to legacy CSI reporting, and additionally configure a state list for AI / ML CSI reporting within the semi-static CSI reporting triggering state list corresponding to semi-static CSI reporting.

[0152] If a status list for AI / ML CSI reporting is additionally configured within the non-periodic CSI reporting triggering status list corresponding to legacy CSI reporting, the non-periodic CSI reporting triggering status list may be configured to include both the status for legacy non-periodic CSI reporting and the status for AI / ML non-periodic CSI reporting. In the same way, if a status list for AI / ML CSI reporting is additionally configured within the semi-static CSI reporting triggering status list corresponding to semi-static CSI reporting, the semi-static CSI reporting triggering status list may be configured to include both the status for legacy semi-static CSI reporting and the status for AI / ML semi-static CSI reporting.

[0153] [Example 3-1]

[0154] In the 3-1 embodiment, among the methods described in the 3rd embodiment, the trigger status lists for AI / ML and legacy are configured separately, and a method is described in which CSI reporting is triggered (or activated) by DCI alone. The 3-1 embodiment can be subdivided into various methods as follows.

[0155] <AI / ML과 관련된 하나의 CSI 보고 트리거링 상태 리스트가 사용되는 경우>

[0156] The first example of the 3-1 embodiment described below may indicate that the DCI transmitted by the base station is a triggering for AI / ML CSI reporting. Additionally, it may be a case where a single list of CSI reporting triggering states related to AI / ML is used.

[0157] In the first example, there may be a method for indicating that the DCI transmitted from the base station to the UE is a triggering DCI for AI / ML CSI reporting. In this disclosure, the base station may transmit the DCI to the UE by scrambling it with a pre-configured radio network temporary identifier (RNTI) to indicate that the DCI is a triggering DCI for AI / ML CSI reporting. The procedure for scrambling the DCI with a specific RNTI may mean a procedure for transforming the cyclic redundancy check (CRC) bits included in the DCI for error detection through an exclusive OR operation using specific RNTI values. It is assumed that the specific RNTI is an AI / ML-CSI-RNTI. It should be noted that the AI / ML-CSI-RNTI described in this disclosure is for the purpose of facilitating understanding of this disclosure, and that the referred name may be expressed in other forms.

[0158] When the UE receives a DCI scrambled via AI / ML-CSI-RNTI from the base station, it can descramble the DCI using AI / ML-CSI-RNTI to acquire the DCI. Here, acquiring the DCI means verifying that there are no errors in the CRC check result, which is obtained by transforming the DCI through an exclusive OR operation with the CRC bits using AI / ML-CSI-RNTI. The UE can identify a specific triggering state indicated by an indicator (or field) within the acquired DCI that indicates the triggering state. For the sake of convenience in the following description, the indicator indicating the triggering state within the DCI will be referred to as the "triggering state indicator."

[0159] The triggering status indicator can indicate one of the triggering statuses set in RRC signaling and / or MAC-CE. The UE can perform CSI reporting based on configuration information for AI / ML CSI reporting associated with the triggering status indicated by the triggering status indicator.

[0160] A triggering state indicator according to the present disclosure may be indicated to the UE by adding a new field within a DCI field or by redefining an existing DCI field. The method of defining a new field may be a method of adding a field to the DCI.

[0161] Next, a method for redefining existing DCI fields is described. When reusing existing DCI fields, for example, the CSI request field included in the DCI may be utilized. For 5G NR, the CSI request field may use any one of the following DCI formats: DCI format 0_1, DCI format 0_2, or DCI format 0_3. In this case, the triggering state indicated by the CSI request field may indicate one of the triggering states within the AI / ML CSI Report Triggering State List. Additionally, the size of the CSI request field may change depending on the configuration. For example, the size of the CSI request field may be determined based on the number of triggering states configured within the AI / ML CSI Report Triggering State List. If the size of the CSI request field is 4 bits, any one of up to 16 triggering states may be indicated.

[0162] The first method described above assumes that DCI is scrambled into AI / ML-CSI-RNTI without distinguishing between non-periodic CSI reporting or semi-static CSI reporting. However, if two or more lists of AI / ML-related CSI reporting triggering states are used, RNTIs corresponding to each state list may be defined separately.

[0163] <AI / ML과 관련 둘 이상의 CSI 보고 트리거링 상태 리스트들이 사용되는 경우 1>

[0164] The following describes the first example of a case where two or more AI / ML-related CSI reporting triggering status lists are used. In the first example, two different RNTIs may be used to distinguish each of the two or more CSI reporting triggering status lists.

[0165] Assume that for a UE using a UE-side model, the CSI report triggering state list for AI / ML CSI acyclic reporting and the CSI report triggering state list for AI / ML CSI semi-static reporting are set by RRC signaling messages or MAC-CE messages. In this case, the base station may use DCI to instruct the UE to use RNTI to set the CSI report triggering state list for AI / ML CSI acyclic reporting or the CSI report triggering state list for AI / ML CSI semi-static reporting.

[0166] For example, AI / ML-aperiodic-CSI-RNTI can be defined as being used for non-periodic CSI reporting, and AI / ML-SP-CSI-RNTI can be defined as being used for semi-static CSI reporting. These definitions may be pre-configured in RRC signaling messages and / or MAC-CE messages, or pre-defined in standard specifications.

[0167] Based on the above settings or definitions, the UE can descramble the DCI received from the base station using AI / ML-aperiodic-CSI-RNTI. If the DCI is acquired as a result of descrambling using AI / ML-aperiodic-CSI-RNTI (if CRC is successful), the UE may interpret this as being instructed to perform aperiodic CSI reporting using the UE-side model. Therefore, if the received DCI is acquired through descrambling with AI / ML-aperiodic-CSI-RNTI, the UE may interpret the CSI request field included in the DCI as indicating a specific triggering state within the AI / ML aperiodic CSI reporting triggering state list. Based on this interpretation, the UE may perform the CSI reporting procedure based on the triggering state indicated by the DCI among the triggering states within the AI / ML aperiodic CSI reporting triggering state list during the CSI reporting procedure.

[0168] Additionally, based on the above settings or definitions, the UE may descramble the DCI received from the base station using AI / ML-SP-CSI-RNTI. If the DCI is acquired as a result of descrambling using AI / ML-SP-CSI-RNTI (if CRC is successful), the UE may interpret this as being instructed to perform semi-static CSI reporting using the UE-side model. Therefore, if the received DCI is acquired through descrambling with AI / ML-SP-CSI-RNTI, the UE may interpret the CSI request field included in the DCI as indicating a triggering state within the AI / ML semi-static CSI reporting triggering state list. Based on this interpretation, the UE may perform the CSI reporting procedure based on the triggering state indicated by the DCI among the triggering states within the AI / ML semi-static CSI reporting triggering state list during the CSI reporting procedure.

[0169] <AI / ML과 관련 둘 이상의 CSI 보고 트리거링 상태 리스트들이 사용되는 경우 2>

[0170] A second example is described below in which two or more AI / ML-related CSI reporting triggering state lists are used. In the second example, a single RNTI is used to distinguish each of the two or more CSI reporting triggering state lists. The single RNTI used in the second embodiment may be an AI / ML-CSI-RNTI. In other words, the base station may use an AI / ML-CSI-RNTI to scramble and transmit to the UE a DCI for non-periodic CSI reporting or a DCI for semi-static CSI reporting.

[0171] DCI may further include a field indicating a specific list of CSI reporting triggering statuses. The field indicating a specific list of CSI reporting triggering statuses will be described as the "CSI reporting triggering status list indicator."

[0172] If an AI / ML semi-static CSI reporting triggering state list and an AI / ML non-periodic CSI reporting triggering state list are set for a single UE based on RRC signaling messages and / or MAC-CE messages, the CSI reporting triggering state list indicator within the DCI may be set to indicate one of the two lists (the AI / ML semi-static CSI reporting triggering state list and the AI / ML non-periodic CSI reporting triggering state list).

[0173] DCI may include CSI reporting triggering status indicators. The triggering status indicators are as previously mentioned "<AI / ML과 관련된 하나의 CSI 보고 트리거링 상태 리스트가 사용되는 경우> It may be the same indicator as the one described in ".

[0174] In other words, the CSI reporting triggering status list indicator included in the DCI can indicate one of two or more CSI reporting triggering status lists related to AI / ML, and the CSI reporting triggering status indicator included in the DCI can indicate one of the CSI reporting triggering states included in the CSI reporting triggering status list indicated by the CSI reporting triggering status list indicator. Here, the CSI reporting triggering status indicator may be indicated through the interpretation method of the CSI request field included in the DCI as previously described, or a method of adding a new field may be used.

[0175] Upon receiving the above DCI, the UE can determine whether the CSI reporting triggering state list indicated by the CSI reporting triggering state list indicator indicates an AI / ML semi-static CSI reporting triggering state list or an AI / ML aperiodic CSI reporting triggering state list. The UE can also check the CSI reporting triggering state within the indicated CSI reporting triggering state list based on the CSI request field (or new field) included in the DCI. In other words, the UE can verify the activation (or triggering) of CSI reporting based on the DCI received from the base station. Subsequently, the UE can measure the CSI-RS received from the base station and generate a CSI reporting message to be reported to the base station using the measured CSI-RS as input to the UE-side model. The UE can perform the CSI reporting procedure by transmitting the generated CSI reporting message to the base station.

[0176] <When defining a new DCI format>

[0177] The above describes a case where the AI / ML CSI reporting procedure is triggered by using existing DCIs but scrambling the DCIs with a specific RNTI. Below, a method for defining a new DCI format is described.

[0178] For the sake of convenience of explanation, the new DCI format for triggering the AI / ML CSI reporting procedure will be referred to as the "AI / ML CSI Reporting Dedicated DCI" below. The base station can trigger AI / ML CSI reporting by transmitting the AI / ML CSI Reporting Dedicated DCI to the UE.

[0179] A UE that receives an AI / ML CSI reporting-specific DCI that triggers AI / ML CSI reporting can perform the AI / ML CSI reporting procedure based on each field included in the AI / ML CSI reporting-specific DCI.

[0180] If there are two or more AI / ML CSI reporting triggering status lists assigned to the UE by an RRC signaling message or MAC-CE, the AI / ML CSI reporting dedicated DCI may include a "CSI reporting triggering status list indicator" to indicate one of the two or more AI / ML CSI reporting triggering status lists. The CSI reporting triggering status list indicator is the aforementioned "<AI / ML과 관련 둘 이상의 CSI 보고 트리거링 상태 리스트들이 사용되는 경우 2>As explained in ", it can be the value of a specific field.

[0181] As another example, if there are two or more AI / ML CSI reporting triggering state lists assigned to the UE by an RRC signaling message or MAC-CE, the AI / ML CSI reporting-only DCI may be scrambled and transmitted by an RNTI to identify the state indicator. For instance, if an AI / ML non-periodic CSI reporting triggering state list and an AI / ML semi-static CSI reporting triggering state list are configured for the UE, the AI / ML CSI reporting-only DCI may be directed by one of two RNTIs to indicate one of the two CSI reporting triggering state lists. As a specific example, let us assume that the two RNTIs used are the C-RNTI and the AI / ML-CSI-RNTI.

[0182] Under the above assumption, the DCI dedicated to AI / ML CSI reporting can be scrambled and transmitted as C-RNTI or scrambled and transmitted as AI / ML-CSI-RNTI.

[0183] The mapping between the RNTI that scrambles the DCI dedicated to AI / ML CSI reporting and the CSI reporting triggering status list can be pre-configured by the setting of the RRC signaling message or the setting of the MAC-CE message.

[0184] For example, based on the settings of an RRC signaling message or a MAC-CE message, if an AI / ML CSI reporting-only DCI is scrambled to a C-RNTI, it may be configured to map to an AI / ML non-periodic CSI reporting triggering status list, and if an AI / ML CSI reporting-only DCI is scrambled to an AI / ML-CSI-RNTI, it may be configured to map to an AI / ML semi-static CSI reporting triggering status list.

[0185] The above example is for the purpose of facilitating understanding of the present disclosure, and other RNTIs other than those exemplified above may be used. Additionally, it should be noted that the mapping relationship between a specific RNTI and a list of CSI report triggering statuses is also for the purpose of facilitating understanding of the present disclosure, and that mappings opposite to those exemplified above are also possible.

[0186] In this way, when a list of CSI reporting triggering states is pre-mapped by a specific RNTI, the UE can determine the list of CSI reporting triggering states based on the RNTI that obtained the AI / ML CSI reporting-specific DCI through descrambling.

[0187] The DCI dedicated to AI / ML CSI reporting may additionally include CSI reporting triggering status indicators. The CSI reporting triggering status indicators mentioned earlier are "<AI / ML과 관련된 하나의 CSI 보고 트리거링 상태 리스트가 사용되는 경우> As described in ", it may indicate one of the CSI reporting triggering states included in a specific list of CSI reporting triggering states.

[0188] Therefore, a UE that has acquired a DCI dedicated to AI / ML CSI reporting can check the CSI reporting triggering status based on the CSI reporting triggering status indicator included in the DCI dedicated to AI / ML CSI reporting.

[0189] <AI / ML-CSI-RNTI를 사용하지 않는 경우>

[0190] The present disclosure described below describes a method that does not use AI / ML-CSI-RNTI, a new RNTI for AI / ML CSI reporting.

[0191] In this disclosure, it is assumed that the DCI includes a CSI request field. In other words, as previously described, any one of DCI formats 0_1, 0_2, or 0_3 may be used. In this case, if two or more lists of CSI reporting triggering states are configured in the UE, the DCI may indicate a specific CSI reporting triggering state using the value of the CSI request field.

[0192] For example, assume that the legacy CSI reporting triggering status list and the AI / ML CSI reporting triggering status list are configured on the UE, and that the size of the DCI's CSI request field is 4 bits.

[0193] If the size of the CSI request field is 4 bits, the CSI request field can indicate a total of 16 codepoints. DCI codepoints can be mapped to CSI reporting triggering states included in the legacy CSI reporting triggering state list and CSI reporting triggering states included in the AI / ML CSI reporting triggering state list, respectively, by RRC signaling messages or MAC-CE messages. For example, an RRC signaling message or MAC-CE message can configure 8 of the 16 codepoints to be mapped to CSI reporting triggering states included in the legacy CSI reporting triggering state list, and the remaining 8 codepoints to be mapped to CSI reporting triggering states included in the AI / ML CSI reporting triggering state list.

[0194] Therefore, the UE can identify a specific CSI reporting triggering state within a specific CSI reporting triggering state list by using mapping information obtained from an RRC signaling message or MAC-CE message previously received from the base station and the code point of the CSI request field included in the DCI.

[0195] In the example described above, it was assumed that a single list of CSI reporting triggering states contains eight CSI reporting triggering states. However, it is possible for one list of CSI reporting triggering states to contain fewer than eight CSI reporting triggering states, while another list contains more than eight CSI reporting triggering states. In this case, if the total number of CSI reporting triggering states does not exceed 16, mapping rules can be established based on the above example.

[0196] Additionally, each of the two lists of CSI reporting triggering states may have fewer than 8 CSI reporting triggering states. In such cases, a specific code point may be used to indicate that there is no mapping value or that CSI reporting should not be performed.

[0197] Among the sizes of the CSI request fields and the number of code points described above, the number of code points used to indicate the CSI report triggering status within each list and the mapping method can be modified in various forms based on the content described above.

[0198] <Combination and Extension Method of Embodiment 3-1>

[0199] In the above, embodiments have been described by classifying them into a total of five cases. The five embodiments described above may be independent of each other, or may be combined with or extended with specific embodiments. Specific combinations or extensions have been partially described in each embodiment, and additional combinations or extensions are further described below.

[0200] A list of CSI reporting triggering states for four CSI reports can be configured for a specific UE. For example, assume that a list of four CSI reporting triggering states is configured for a UE as follows.

[0201] a) List of legacy non-periodic CSI report triggering statuses,

[0202] b) Legacy semi-static CSI report triggering status list,

[0203] c) List of AI / ML non-periodic CSI reporting triggering statuses, and

[0204] d) List of AI / ML semi-static CSI reporting triggering statuses

[0205] When four lists of CSI reporting triggering states are configured for a single UE as described above, the base station must be able to direct one of the four lists of CSI reporting triggering states through the DCI, and also direct one of the CSI reporting triggering states included in the directed list of CSI reporting triggering states.

[0206] As one embodiment for this purpose, the DCI may be scrambled as SP-CSI-RNTI or as C-RNTI. If the DCI is scrambled as SP-CSI-RNTI, the UE may interpret the DCI as pointing to either the legacy semi-static CSI reporting triggering status list or the AI / ML semi-static CSI reporting triggering status list. If the DCI is scrambled as C-RNTI, the UE may interpret the DCI as pointing to either the legacy non-periodic CSI reporting triggering status list or the AI / ML non-periodic CSI reporting triggering status list.

[0207] In addition, the base station can pre-configure mapping information for the code point values ​​of the DCI's CSI request field based on RRC signaling messages or MAC-CE messages.

[0208] When a UE obtains a DCI by descramming SP-CSI-RNTI, it can interpret that a specific state list among the corresponding CSI report triggering state lists is indicated by using the mapping information pre-configured by the RRC signaling message or MAC-CE message and the code point values ​​of the CSI request field.

[0209] In the same way, when the UE obtains the DCI by descramming with C-RNTI, it can interpret that a specific state list among the corresponding CSI report triggering state lists is indicated by using the mapping information pre-configured by the RRC signaling message or MAC-CE message and the code point values ​​of the CSI request field.

[0210] Subsequently, the UE can perform CSI reporting based on a specific status list.

[0211] The combination and extension methods described above are merely examples to aid in understanding the combination and extension methods of the present disclosure. Since it is impossible to describe all combination and extension methods based on the methods described above, it should be noted that combinations and extensions of such methods can be easily derived from the present disclosure by a person skilled in the art.

[0212] [Example 3-2]

[0213] In the 3-2nd embodiment, a method is described in which CSI reporting is triggered (or activated) by DCI alone when the trigger status lists for AI / ML and legacy are not set separately among the methods described in the 3rd embodiment.

[0214] The list of legacy non-periodic CSI reporting triggering states configured for legacy CSI reporting may include AI / ML non-periodic CSI reporting triggering states. Additionally, the list of legacy semi-static CSI reporting triggering states may include AI / ML semi-static CSI reporting triggering states.

[0215] When the CSI report triggering status list is configured as above, the base station can specify one of the legacy CSI report triggering status(s) and the AI / ML CSI report triggering status(s) through the CSI request field included in the DCI.

[0216] For example, let us assume that the legacy non-periodic CSI reporting triggering status list contains 8 legacy non-periodic CSI reporting triggering statuses and 8 AI / ML non-periodic CSI reporting triggering statuses, and that the CSI request field is 4 bits. In this case, 8 of the code points can be used to indicate the legacy CSI reporting triggering statuses, and the remaining 8 code points can be used to indicate the AI / ML CSI reporting triggering statuses.

[0217] As a more specific example, the 4-bit CSI request field included in the DCI may indicate one of the legacy CSI reporting triggering states in the legacy non-periodic CSI reporting triggering state list or one of the AI / ML non-periodic CSI reporting triggering states in the legacy non-periodic CSI reporting triggering state list.

[0218] It should be noted that the total number of CSI reporting triggering states that can be specified through the CSI request field, and the number of legacy CSI reporting triggering states and AI / ML CSI reporting triggering states within the total number of CSI reporting triggering states, can be configured in various forms.

[0219] An extended embodiment of the method described above is described below.

[0220] Assume that the legacy non-periodic CSI reporting triggering state list and the legacy semi-static CSI reporting triggering state list are configured for the UE. The legacy non-periodic CSI reporting triggering state list may further include AI / ML non-periodic CSI reporting triggering state list(s) as previously described. Additionally, the legacy semi-static CSI reporting triggering state list may further include AI / ML semi-static CSI reporting triggering state(s) as previously described.

[0221] In the above case, based on the RNTI used for the DCI transmitted from the base station to the UE, the DCI may be indicated as either a legacy non-periodic CSI reporting triggering state list or a legacy semi-static CSI reporting triggering state list.

[0222] As described in the previous 3-1 embodiment, a list of CSI report triggering statuses can be determined through scrambling and descramming using a specific RNTI.

[0223] For example, if a DCI is obtained by descramming SP-CSI-RNTI, the UE may interpret that the legacy semi-static CSI reporting triggering status list has been selected. Therefore, the UE can verify that, depending on the code point value of the CSI request field in the DCI, one of the legacy semi-static CSI reporting triggering statuses or one of the AI / ML semi-static CSI reporting triggering statuses has been indicated.

[0224] On the other hand, if the DCI is obtained by descramming with C-RNTI, the UE can interpret that the legacy non-periodic state list has been selected. Therefore, the UE can verify that, depending on the code point value of the CSI request field in the DCI, one of the legacy non-periodic CSI reporting triggering states or one of the AI / ML non-periodic CSI reporting triggering states has been indicated.

[0225] [Example 3-3]

[0226] In the third embodiment, a method in which CSI reporting is triggered (or activated) by MAC-CE alone is described among the methods described in the third embodiment. The method in which CSI reporting is triggered (or activated) by MAC-CE messages alone can be applied to the case of semi-static CSI reporting triggering as described in Table 1 above.

[0227] A MAC-CE message can activate or deactivate one of a plurality of CSI-ReportConfigs configured within the csi-ReportConfigToAddModList field of an RRC signaling message, which is a higher-level signaling. Before describing the third-3rd embodiment of the present disclosure, a method for activating a configuration for semi-static CSI reporting using a MAC-CE message is first described.

[0228] Figure 4 is a conceptual diagram illustrating the configuration of MAC-CE for activation / deactivation according to the semi-static CSI reporting method in a mobile communication system.

[0229] The configuration of the MAC-CE exemplified in FIG. 4 may include Octet 1 and Octet 2. Octet 1 may be a subheader of the MAC layer containing a logical channel ID (LCID) used in semi-static CSI. As exemplified in FIG. 4, the MAC-CE for enabling / disabling according to the semi-static CSI reporting method may be composed of Octet 1 and Octet 2, each consisting of 8 bits. In other words, the total number of bits of the MAC-CE for enabling / disabling according to the semi-static CSI reporting method may be 16 bits.

[0230] The most significant bit (MSB) (401) of octet 1 may be a reserved (R) bit, the serving cell ID may consist of 5 bits, and the bandwidth part (BOP) ID may consist of 2 bits. The serving cell ID consisting of 5 bits may represent the identifier of the serving cell to which MAC CE applies. The BWP ID consisting of 2 bits may represent the uplink (UL) BWP to which MAC CE applies as the code point of the DCI bandwidth part indicator field. Additionally, the reserved (R) bits exemplified in FIG. 4 may all be set to a zero value.

[0231] In octet 2, the consecutive 4 bits (410) from the MSB are reserved (R) bits (411, 412, 413, 414), and the remaining consecutive 4 bits (S0, S1, S2, S3) (420) may be configuration information for a semi-static CSI reporting method. S0 to S3 of the configuration information for a semi-static CSI reporting method (420) composed of 4 bits may have a value of either a first value (e.g., zero (0)) or a second value (e.g., 1). S0 to S3 of the configuration information for a semi-static CSI reporting method (420) composed of 4 bits may each be mapped to a CSI reporting configuration identifier (CSI-ReportConfigId) to indicate the activation / deactivation of a specific CSI reporting configuration (CSI-ReportConfig).

[0232] For example, if S0 has a first value, it may indicate that the lowest CSI-ReportConfigId among the semi-statically configured CSI report settings transmitted over PUCCH is deactivated, and if it has a second value (1), it may indicate that the lowest CSI-ReportConfigId among the semi-statically configured CSI report settings transmitted over PUCCH is activated. In the same way, if S2 has a first value, it may indicate that the second lowest CSI-ReportConfigId among the semi-statically configured CSI report settings transmitted over PUCCH is deactivated, and if it has a second value (1), it may indicate that the second lowest CSI-ReportConfigId among the semi-statically configured CSI report settings transmitted over PUCCH is activated. The same method may be applied to S2 and S3. Therefore, if the configuration information for the semi-static CSI reporting method, consisting of 4 bits, all have the first value, CSI-ReportConfig may be instructed to be deactivated.

[0233] Semi-static CSI reporting setting information can be set by MAC-CE in the manner described above.

[0234] In the following, a method is described in which semi-static CSI reporting setting information is set by MAC-CE when an AI / ML model is used according to the 3-3 embodiment of the present disclosure.

[0235] CSI-ReportConfigs for AI / ML CSI reporting settings according to the third-third embodiment of the present disclosure may be configured independently of CSI-ReportConfigs for legacy CSI reporting settings. For example, when a CSI-ReportConfig for AI / ML having an identifier (ID) distinct from the legacy CSI-ReportConfigID is configured and used, it may be enabled / disabled using MAC-CE as in the first or second method described below.

[0236] For the sake of convenience in the following description, the CSI-ReportConfig for AI / ML CSI reporting that has an ID separate from the legacy CSI-ReportConfigID will be referred to as "AI / ML CSI-ReportConfig". When AI / ML CSI reporting and legacy CSI reporting configure different CSI-ReportConfigIDs, different lists of CSI reporting triggering states can be configured for each AI / ML CSI reporting and legacy CSI reporting configuration. When different lists of CSI reporting triggering states are configured for each AI / ML CSI reporting and legacy CSI reporting configuration, CSI-ReportConfigID groups within each list can be configured to exist separately for each AI / ML CSI reporting and legacy CSI reporting configuration.

[0237] <Method 1>

[0238] In the first method of the present disclosure, the four consecutive reserved bits (410) of octet 2 described above in FIG. 4 may be used as instructions for the AI / ML CSI-ReportConfig. The four reserved bits (411, 412, 413, 414) may be used in the same way as the configuration information (420) for the semi-static CSI reporting method. Thus, the four reserved bits (410) may have one of a first value (e.g., zero (0)) or a second value (e.g., 1), as in the configuration information (420) for the semi-static CSI reporting method.

[0239] Each of the reserved 4 bits (411, 412, 413, 414) can be mapped to an AI / ML CSI report configuration identifier (AI / ML CSI-ReportConfigID) for each bit, such as configuration information (420) for a semi-static CSI reporting method. This allows each of the reserved 4 bits (411, 412, 413, 414) to indicate the activation / deactivation of a specific AI / ML CSI report configuration (AI / ML CSI-ReportConfig).

[0240] For example, if the reserved bit (411) closest to the configuration information (420) for the semi-static CSI reporting method in Octet 2 has a first value, it may indicate that the lowest AI / ML CSI-ReportConfigId among the semi-statically configured AI / ML CSI reporting settings transmitted over PUCCH is deactivated, and if it has a second value (1), it may indicate that the lowest AI / ML CSI-ReportConfigId among the semi-statically configured AI / ML CSI reporting settings transmitted over PUCCH is activated. The remaining bits (412, 413, 414) may also indicate the activation / deactivation of the AI / ML CSI-ReportConfigId in the same way.

[0241] <Method 2>

[0242] In the second method of the present disclosure, the configuration described above in FIG. 4 may also be used. In the second method, the reserved bit (401), which is the MSB of octet 1 described in FIG. 4, may be used to identify AI / ML CSI reports and legacy CSI reports. As previously described, the reserved bit (401) may be set to a zero value.

[0243] In the second method of the present disclosure, if the reserved bit (401) of octet 1 is the first value (0), it is defined as a legacy CSI report, and if the reserved bit (401) of octet 1 is the second value (1), it is defined as an AI / ML CSI report.

[0244] Based on the above definition, a UE receiving MAC-CE can interpret the 4-bit semi-static CSI reporting method of Octet 2 as either a legacy CSI reporting method or an AI / ML CSI reporting method based on the value of the reserved bit (401) of Octet 1. For example, if the reserved bit (401) of Octet 1 is a first value (0), the UE can interpret the setting information (420) for the 4-bit semi-static CSI reporting method of Octet 2 as described in FIG. 4. On the other hand, if the reserved bit (401) of Octet 1 is a second value (1), the UE can interpret the 4-bit (420) of Octet 2 as setting information for the semi-static AI / ML CSI reporting method.

[0245] To this end, if the reserved bit (401) of octet 1 is the second value (1), the 4 bits (420) of octet 2 can be mapped to an AI / ML CSI Report Config Identifier (AI / ML CSI-ReportConfigID) for each bit. If the reserved bit (401) of octet 1 is the second value (1), the 4 bits (420) of octet 2 can be interpreted, for example, as follows.

[0246] If S0 has a first value, it may indicate that the lowest AI / ML CSI-ReportConfigId among the semi-statically configured AI / ML CSI report settings transmitted over PUCCH is deactivated, and if it has a second value (1), it may indicate that the lowest AI / ML CSI-ReportConfigId among the semi-statically configured AI / ML CSI report settings transmitted over PUCCH is activated. In the same way, if S2 has a first value, it may indicate that the second lowest AI / ML CSI-ReportConfigId among the semi-statically configured AI / ML CSI report settings transmitted over PUCCH is deactivated, and if it has a second value (1), it may indicate that the second lowest AI / ML CSI-ReportConfigId among the semi-statically configured AI / ML CSI report settings transmitted over PUCCH is activated. The same method may be applied to S2 and S3. Therefore, if all configuration information for the 4-bit semi-static AI / ML CSI reporting method has the first value, the AI / ML CSI-ReportConfig may be instructed to be deactivated.

[0247] In describing the second method, it was assumed that the AI / ML CSI report and legacy CSI report use the reserved bit (401) of octet 1. However, it should be noted that the same method can be configured even if any of the reserved bits (410) of octet 2 are used.

[0248] The second method described above can determine whether the CSI-ReportConfigId indicated by the MAC-CE belongs to the legacy CSI-ReportConfig group or the AI / ML CSI-ReportConfig group by using one bit reserved in the MAC-CE. For example, if the RRC signaling message has four legacy CSI-ReportConfigIds from 0 to 3 set in the legacy CSI-ReportConfig group and four AI / ML CSI-ReportConfigIds from 0 to 3 set in the AI / ML CSI-ReportConfig group, the UE can identify which group it belongs to through the reserved bit of the MAC-CE. And the CSI-ReportConfigId within the corresponding group can be indicated by the setting information (420) for the semi-static CSI reporting method of the MAC-CE.

[0249] Meanwhile, the first and second methods described above may apply when a CSI-ReportConfigId is individually assigned to the legacy CSI-ReportConfig group and the AI / ML CSI-ReportConfig group, respectively. In cases where the CSI-ReportConfigs for AI / ML CSI reporting settings are not operated separately, unlike the first and second methods, one of the third or fourth methods below may be used. In other words, for a method of mapping configuration information for legacy CSI reporting or AI / ML CSI reporting to CSI-ReportConfigIDs, one of the third or fourth methods below may be used.

[0250] In the case of the third or fourth method described below, the maximum value for the number of CSI-ReportConfigIDs may increase as CSI reporting settings for AI / ML are added. If AI / ML CSI reporting and legacy CSI reporting consist of the same CSI-ReportConfigIDs, the CSI-ReportConfigIDs for both AI / ML CSI reporting and legacy CSI reporting may be included together within the legacy CSI reporting triggering status lists.

[0251] <Third Method>

[0252] The third method of the present disclosure is for triggering semi-static CSI reporting and may be a method using only MAC-CE. Additionally, in the third method of the present disclosure, the list of CSI reporting triggering states included in CSI-ReportConfig may include one or more legacy CSI-ReportConfigID(s) and one or more AI / ML CSI-ReportConfigID(s). Accordingly, the number of CSI-ReportConfigID(s) included in the list of CSI reporting triggering states may increase.

[0253] As the number of CSI-ReportConfigIDs increases, it may not be possible to indicate all CSI-ReportConfigIDs using only the configuration information (420) for the semi-static CSI reporting method of the 4 bits of octet 2 exemplified in FIG. 4. Therefore, in the third embodiment of the present disclosure, some or all of the reserved bits (410) of the 4 bits of octet 2 can be used to configure mapping to the CSI-ReportConfigIDs included in the CSI reporting triggering status list.

[0254] For example, the MSB (414) of Octet 2 and the bit immediately below the MSB (413) can be set as reserved bits, and the remaining reserved bits (411, 412) can be configured to map to CSI-ReportConfigID. In other words, 6 bits in Octet 2 of MAC-CE can be used to map to CSI-ReportConfigID. When the 2 additional bits reserved in Octet 2 are used in this way, the configuration information for the semi-static CSI reporting method can be understood in a form having a total length of 6 bits, such as S0, S1, S2, S3, S4, and S5. The 6-bit configuration information for the semi-static CSI reporting method can indicate the activation / deactivation of 6 CSI-ReportConfigIDs. Since the first and second values ​​of the 6-bit configuration information for the semi-static CSI reporting method can be understood as described above, a redundant explanation is omitted.

[0255] Additionally, one or more of the six CSI-ReportConfigIDs may be legacy CSI-ReportConfigIDs, and the remaining CSI-ReportConfigIDs among the six CSI-ReportConfigIDs may be AI / ML CSI-ReportConfigIDs. In this case, according to the present disclosure, the remaining CSI-ReportConfigIDs may include at least one AI / ML CSI-ReportConfigID.

[0256] <4th Method>

[0257] In the third method described above, since the CSI-ReportConfigID in the CSI report triggering status list is incremented, it was explained that some of the reserved bits (411, 412, 413, 414) of Octet 2 of MAC-CE are extended and used as configuration information for the semi-static CSI reporting method for mapping to this. In the fourth method to be described below, as described in the second method above, the reserved bit (401) of Octet 1 exemplified in FIG. 4 can be used to indicate either the legacy CSI reporting method or the AI / ML reporting method. For convenience of explanation, the reserved bit (401) of Octet 1 exemplified in FIG. 4, which indicates either the legacy CSI reporting method or the AI / ML reporting method, will be referred to as the "G field" in the following description.

[0258] In the fourth method according to the present disclosure, when the G field (401) has a first value (zero) as described above, the S0 to S3 bits, which are configuration information (420) for the semi-static CSI reporting method of octet 2, can be mapped to the legacy CSI-ReportConfigID, and when the G field (401) has a second value (1) as described above, the S0 to S3 bits, which are configuration information (420) for the semi-static CSI reporting method of octet 2, can be mapped to the AI / ML CSI-ReportConfigID.

[0259] In other words, as described in Method 1 above, the field values ​​from S0 to S3 of the configuration information (420) for the semi-static CSI reporting method of Octet 2 can be mapped to the AI / ML CSI-ReportConfigID within the AI / ML CSI-ReportConfig using the bit values ​​from S0 to S3, just as in the case where a specific AI / ML CSI-ReportConfigID is indicated. For example, if a specific field (or bit value) of the configuration information (420) for the semi-static CSI reporting method is 1, the AI / ML CSI-ReportConfig corresponding to that field is activated, and if a specific field (or bit value) of the configuration information (420) for the semi-static CSI reporting method is 0, the AI / ML CSI-ReportConfig corresponding to that field can be deactivated.

[0260] Unlike the second method described above, the fourth method of the present disclosure includes both legacy CSI-ReportConfig and AI / ML CSI-ReportConfig within the CSI-ReportConfigID group, so the CSI-ReportConfigID mapped to S0 through S3 may differ depending on the G field (410).

[0261] For example, let us assume that the ReportConfigIDs of the configuration information for 4 legacy CSI reports are 2, 4, 6, and 8, and the ReportConfigIDs of the configuration information for 4 AI / ML CSI reports are 1, 3, 5, and 7. When the G field (401) is 0, the bits (420) from S0 to S3 can correspond to the IDs 2, 4, 6, and 8 of the configuration information for legacy CSI reports, respectively. On the other hand, when the G field (401) is 1, the bits (420) from S0 to S3 can correspond to the IDs 1, 3, 5, and 7 of the configuration information for AI / ML CSI reports, respectively. Accordingly, by indicating each bit value of each S field (420) as 0 or 1, the CSI-ReportConfig indicated by the ReportConfigID corresponding to each S field can be disabled (if the corresponding bit value is 0) or enabled (if the corresponding bit value is 1).

[0262] [Fourth Embodiment: Method for Establishing AI / ML CSI Reporting Using DCI and MAC-CE]

[0263] In the third embodiment, a method for configuring legacy CSI reporting and AI / ML CSI reporting using only DCI or only MAC-CE was described. In the fourth embodiment described below, a method for configuring legacy CSI reporting and AI / ML CSI reporting using both DCI and MAC-CE is described. Furthermore, the fourth embodiment of the present disclosure can be further specified by the following two embodiments.

[0264] [Example 4-1]

[0265] When enabling (or triggering) CSI reporting with a combination of DCI and MAC-CE, one of multiple CSI-ReportConfigs set by higher-level signaling, such as RRC signaling messages, can be enabled or disabled.

[0266] First, the method by which the setting for non-periodic CSI reporting that does not support AI / ML is activated (or triggered) is explained with reference to the attached Fig. 5.

[0267] Figure 5 is a conceptual diagram illustrating the configuration of MAC-CE for activation / deactivation according to the non-periodic CSI reporting method in a mobile communication system.

[0268] The MAC-CE exemplified in FIG. 5 may consist of N octets. Here, N is a natural number and may be set by upper-layer signaling (e.g., RRC signaling messages). Octet 1 may be a subheader of the MAC layer containing a logical channel ID (LCID) used in non-periodic CSI. The MSB of Octet 1 may be a reserved (R) bit (501), the serving cell ID may consist of 5 bits, and the BWP ID may consist of 2 bits. The serving cell ID consisting of 5 bits may represent the identifier of the serving cell to which the MAC CE applies. The BWP ID consisting of 2 bits may represent the uplink (UL) BWP to which the MAC CE applies as a code point of the DCI bandwidth portion indicator field.

[0269] Octets 2 through N, each consisting of 8 bits, will be referred to as "T fields" below for convenience of explanation. Each of the T fields (510) can be used to indicate specific triggering states within an aperiodic trigger state list (aperiodicTriggerStateList) for CSI reporting set by upper-level signaling (e.g., RRC signaling message). And the CSI request field within the DCI can indicate one of the triggering states for CSI reporting selected by MAC-CE.

[0270] Assume that there are 16 triggering states in the aperiodicTriggerStateList for CSI reporting, and that the CSI request field in the DCI is allocated 3 bits. If the length of the CSI request field in the DCI is 3 bits, the CSI request field can indicate 8 code points. On the other hand, since MAC-CE has 16 triggering states for CSI reporting, the CSI request field in the DCI, which has a size of 3 bits, cannot indicate 16 triggering states for CSI reporting. In other words, for MAC-CE to indicate 16 triggering states for CSI reporting, the CSI request field must have a size of 4 bits.

[0271] In the 4-1 embodiment, when the CSI request field has 3 bits, the MAC-CE can be configured to include only 8 triggering states out of 16 triggering states for CSI reporting within the list of non-periodic triggering states for CSI reporting. And the DCI can map the code points of the CSI request field, which has a size of 3 bits, to the triggering states included in the MAC-CE. Thus, by receiving the MAC-CE, the UE can identify 8 triggering states for CSI reporting out of 16 triggering states for CSI reporting included in the list of non-periodic triggering states for CSI reporting. And the UE can receive the DCI and identify a selected triggering state for CSI reporting out of the 8 triggering states for CSI reporting from the CSI request field included in the DCI.

[0272] Through the above operation, the UE can perform non-periodic CSI reporting operations by activating (or triggering) CSI reporting-related settings associated with the triggering state for the selected CSI report.

[0273] When CSI-ReportConfigs for AI / ML CSI reporting settings are configured independently of CSI-ReportConfigs for legacy CSI reporting settings, they can be activated (or triggered) using MAC-CE and DCI as described in the fifth method below. For the convenience of explanation in describing the fifth method, a CSI-ReportConfig for AI / ML CSI reporting that has an ID separate from the legacy CSI-ReportConfigID is referred to as the AI / ML CSI-ReportConfig. When AI / ML CSI reporting and legacy CSI reporting configure different CSI-ReportConfigIDs, different CSI reporting triggering status lists can be configured for each AI / ML CSI reporting and legacy CSI reporting setting. Additionally, each of the CSI reporting status lists can be configured to exist within a CSI-ReportConfigID group.

[0274] <The 5th Method>

[0275] In the fifth method of the present disclosure, a legacy MAC-CE for CSI reporting and a MAC-CE for AI / ML CSI reporting may be defined separately. To this end, the legacy MAC-CE for CSI reporting and the MAC-CE for AI / ML CSI reporting can be identified using the reserved bit (501) of octet 1 exemplified in FIG. 5. For example, it may be defined to be interpreted as a legacy MAC-CE for CSI reporting when the reserved bit (501) of octet 1 has a first value (e.g., a zero value), and defined to be interpreted as a MAC-CE for AI / ML CSI reporting when the reserved bit (501) of octet 1 has a second value (e.g., a value of 1).

[0276] In other words, when the reserved bit (501) of octet 1 has a first value, the triggering states for CSI reporting of octets 2 through N included in the legacy MAC-CE for CSI reporting may be multiple triggering states included in the list of legacy triggering states for CSI reporting of the RRC signaling message. On the other hand, when the reserved bit (501) of octet 1 has a second value, the triggering states for CSI reporting of octets 2 through N included in the legacy MAC-CE for CSI reporting may be multiple AI / ML triggering states included in the list of AI / ML triggering states for CSI reporting of the RRC signaling message.

[0277] Subsequently, one of the triggering states included in the MAC-CE can be indicated by the CSI request field of the DCI. Therefore, upon receiving the MAC-CE, the UE can determine whether legacy-style CSI reporting or AI / ML-style CSI reporting has been indicated for non-periodic CSI reporting. Additionally, the UE can check the triggering state for CSI reporting by the CSI request field of the DCI.

[0278] As a variation of the fifth method according to the present disclosure, additional indication may be provided as to whether the CSI reporting method triggered by the DCI is a legacy CSI reporting method or an ACI / ML reporting method by reusing other reserved fields or other fields used in the DCI in addition to the CSI request field included in the DCI. When other fields of the DCI are additionally utilized in this manner, said fields may be used to eliminate potential ambiguity in the CSI reporting operation for the UE.

[0279] As another variation of the fifth method, the base station may use the DCI to direct AI / ML CSI reporting or legacy CSI reporting without using the reserved bit (501) of octet 1 of the MAC-CE. In this case, the T fields (510) included in the MAC-CE exemplified in FIG. 5 may be transmitted to the UE without information on whether they are triggering states for AI / ML CSI reporting or triggering states for legacy CSI reporting. The base station may direct one of the triggering states for CSI reporting included in the T fields (510) of the MAC-CE using the CSI request field of the DCI. At this time, the DCI may use additional indicators to indicate whether the selected triggering state for CSI reporting among the triggering states for CSI reporting included in the T fields (510) of the MAC-CE is set for legacy CSI reporting or for AI / ML CSI reporting. In this case, additional indicators included in the DCI may reuse one of the fields other than the CSI request field, or one of the other fields used in the DCI. Therefore, the UE can receive triggering states for CSI reporting that are enabled in MAC-CE, and can identify one of the triggering states for CSI reporting included in MAC-CE by the DCI. Furthermore, the UE can determine whether the triggering state for CSI reporting selected by the additional indicators of the DCI is a triggering state for legacy CSI reporting or a triggering state for AI / ML reporting.

[0280] As another variation of the fifth method, the base station may use the DCI to direct AI / ML CSI reporting or legacy CSI reporting without using the reserved bit (501) of octet 1 of the MAC-CE. In this case, a new DCI format capable of directing AI / ML CSI reporting may be defined. The newly defined DCI may include an indicator to identify whether the CSI report is legacy CSI reporting or AI / ML CSI reporting. In this case, the T fields (510) included in the MAC-CE exemplified in FIG. 5 may be transmitted to the UE without information on whether they are triggering states for AI / ML CSI reporting or triggering states for legacy CSI reporting.

[0281] The base station may indicate one of the triggering states for CSI reporting included in the T fields (510) of the MAC-CE using the CSI request field of the DCI. At this time, the DCI may use additional indicators to indicate whether the selected triggering state for CSI reporting among the triggering states for CSI reporting included in the T fields (510) of the MAC-CE is a setting for legacy CSI reporting or a setting for AI / ML CSI reporting.

[0282] Therefore, the UE can receive triggering states for CSI reporting that are enabled in MAC-CE, and can identify one of the triggering states for CSI reporting included in MAC-CE by the DCI. Additionally, the UE can determine whether the triggering state for CSI reporting selected by an additional indicator of the DCI is a triggering state for legacy CSI reporting or a triggering state for AI / ML CSI reporting.

[0283] In the variations described above, without defining a new DCI, including additional indicator fields in the DCI, or redefining existing fields of the DCI, it is also possible to set whether the transmitted DCI indicates a CSI triggering state for AI / ML CSI reporting or a legacy CSI reporting using two or more RNTIs for scrambling the DCI. For example, the UE may receive triggering states for CSI reporting that can be enabled via MAC-CE in the manner described in FIG. 5. And when the UE acquires the DCI using the first RNTI, the triggering state for CSI reporting selected by the code point of the CSI request field of the DCI may be interpreted as a triggering state for legacy CSI reporting, and when the UE acquires the DCI using the second RNTI, the triggering state for CSI reporting selected by the code point of the CSI request field of the DCI may be interpreted as a triggering state for AI / ML CSI reporting.

[0284] <Method 6>

[0285] In the previously described fifth method, the case where CSI-ReportConfig for AI / ML CSI reporting settings and CSI-ReprotConfig for legacy CSI reporting settings are configured separately was described. Therefore, in the fifth method, CSI-ReportConfig for AI / ML CSI reporting settings and CSI-ReprotConfig for legacy CSI reporting settings can be identified by using the reserved bit (501) of octet 1 of MAC-CE.

[0286] On the other hand, the sixth method of the present disclosure, to be described below, describes a case where the CSI-ReportConfig for AI / ML CSI reporting settings and the CSI-ReportConfig for legacy CSI reporting settings are not configured separately. In other words, a method for activating a specific CSI reporting list by MAC-CE and DCI is described when the CSI-ReportConfigID(s) for legacy CSI reporting and the CSI-ReportConfigID(s) for AI / ML CSI reporting are included together within the triggering state list for CSI reporting. It should be noted that when the CSI-ReportConfigID(s) for legacy CSI reporting and the CSI-ReportConfigID(s) for AI / ML CSI reporting are included together within the triggering state list for CSI reporting, the number of CSI-ReportConfigID(s) may exceed the maximum configurable value; therefore, the maximum configurable value of the CSI-ReportConfigID(s) may be set to a value greater than the currently defined value.

[0287] Accordingly, the triggering status list for CSI reporting may include one or more CSI-ReportConfigID(s) for legacy CSI reporting and one or more CSI-ReportConfigID(s) for AI / ML CSI reporting. In the sixth manner of the present disclosure, the reserved bit (501) of octet 1 exemplified in FIG. 5 may be used to limit the group of IDs to which the T field (510) of MAC-CE is mapped to CSI-ReportConfigID(s) for legacy CSI reporting or to limit the group of IDs to which the T field (510) of MAC-CE is mapped to CSI-ReportConfigID(s) for AI / ML CSI reporting.

[0288] For example, let us assume a case where a MAC-CE is used with eight fields (or bits) from T0 to T7 within the MAC-CE, and let us assume that within the triggering status list there are CSI-ReportConfigIDs for eight legacy CSI reports, 0, 1, 2, 3, 4, 5, 6, 7, and CSI-ReportConfigIDs for eight AI / ML CSI reports, 8, 9, 10, 11, 12, 13, 14, 15. In this case, if the reserved bit (501) of octet 1 of the MAC-CE is set to a first value (e.g., a value of 0), each of the eight T fields can be mapped to the CSI-ReportConfigIDs for eight legacy CSI reports, 0, 1, 2, 3, 4, 5, 6, 7. On the other hand, if the reserved bit (501) of octet 1 of MAC-CE is set to a second value (e.g., a value of 1), the 8 T fields can be mapped to 8, 9, 10, 11, 12, 13, 14, and 15, which are CSI-ReportConfigIDs for 8 AI / ML CSI reports. And the CSI request field of DCI can indicate one of the triggering states for a CSI report that is set to be enabled in MAC-CE.

[0289] Based on the above settings and instructions, the UE can enable (or trigger) a triggering state for CSI reporting. For example, the UE can identify eight triggering states for legacy CSI reporting that can be enabled based on the value of the reserved bit (510) of octet 1 of MAC-CE and the T field (510), or eight triggering states for AI / ML CSI reporting that can be enabled. The UE can also identify that the CSI-ReportConfigID indicated by the CSI request field of the DCI is enabled.

[0290] As an example of a variation of the 6th method, an additional indicator may be included to indicate whether the currently active (or triggering) CSI report is a legacy CSI report or an AI / ML CSI report by reusing other reserved fields or other fields in addition to the CSI request field within the DCI. This allows the UE to eliminate ambiguity that may occur during CSI reporting operations.

[0291] As another variation of the sixth method, the base station may use the DCI to direct AI / ML CSI reporting or legacy CSI reporting without using the reserved bit (501) of octet 1 of the MAC-CE. In this case, the T fields (510) of the MAC-CE exemplified in FIG. 5 may be transmitted to the UE without information on whether they are triggering states for AI / ML CSI reporting or triggering states for legacy CSI reporting. The base station may direct one of the triggering states for CSI reporting included in the T fields (510) of the MAC-CE using the CSI request field of the DCI. At this time, the DCI may use additional indicators to indicate whether the selected triggering state for CSI reporting among the triggering states for CSI reporting included in the T fields (510) of the MAC-CE is set for legacy CSI reporting or for AI / ML CSI reporting. In this case, additional indicators included in the DCI may reuse one of the fields other than the CSI request field, or one of the other fields used in the DCI. Therefore, the UE can receive triggering states for CSI reporting that are enabled in MAC-CE, and can identify one of the triggering states for CSI reporting included in MAC-CE by the DCI. Furthermore, the UE can determine whether the triggering state for CSI reporting selected by the additional indicators of the DCI is a triggering state for legacy CSI reporting or a triggering state for AI / ML reporting.

[0292] As another variation of the sixth method, the base station may direct an AI / ML CSI report or a legacy CSI report using the DCI without using the reserved bit (501) of octet 1 of the MAC-CE. In this case, a new DCI format capable of directing an AI / ML CSI report may be defined. The newly defined DCI may include an indicator to identify whether the CSI report is a legacy CSI report or an AI / ML CSI report. In this case, the T fields (510) included in the MAC-CE exemplified in FIG. 5 may be transmitted to the UE without information on whether they are triggering states for an AI / ML CSI report or triggering states for a legacy CSI report. The base station may direct one of the triggering states for a CSI report included in the T fields (510) of the MAC-CE using the CSI request field of the DCI. At this time, DCI can use additional indicators to indicate whether the selected triggering state for CSI reporting among the triggering states for CSI reporting included in the T fields (510) of MAC-CE is a setting for legacy CSI reporting or a setting for AI / ML CSI reporting.

[0293] Therefore, the UE can receive triggering states for CSI reporting that are enabled in MAC-CE, and can identify one of the triggering states for CSI reporting included in MAC-CE by the DCI. Additionally, the UE can determine whether the triggering state for CSI reporting selected by an additional indicator of the DCI is a triggering state for legacy CSI reporting or a triggering state for AI / ML CSI reporting.

[0294] In the variations described above, without defining a new DCI, including additional indicator fields in the DCI, or redefining existing fields of the DCI, it is also possible to set whether the transmitted DCI indicates a CSI triggering state for AI / ML CSI reporting or a legacy CSI reporting using two or more RNTIs for scrambling the DCI. For example, the UE may receive triggering states for CSI reporting that can be enabled via MAC-CE in the manner described in FIG. 5. And when the UE acquires the DCI using the first RNTI, the triggering state for CSI reporting selected by the code point of the CSI request field of the DCI may be interpreted as a triggering state for legacy CSI reporting, and when the UE acquires the DCI using the second RNTI, the triggering state for CSI reporting selected by the code point of the CSI request field of the DCI may be interpreted as a triggering state for AI / ML CSI reporting.

[0295] When enabling (or tugging) CSI reporting using a combination of DCI and MAC-CE, the final CSI report may be directed by the DCI after the configuration information for some CSI reports is set by MAC-CE. Alternatively, the final CSI report may be directed by a MAC-CE message following a directive via the CSI request field by the DCI.

[0296] Each of the embodiments described above may be combined with one another to the extent possible. For example, in the case of non-periodic CSI reporting where MAC-CE and DCI are used together, the operations described in the third embodiment above may be used together in the fourth embodiment. Additionally, the RRC signaling messages described in the first and / or second embodiments may be applied identically in the third and fourth embodiments. Furthermore, those skilled in the art should note that various combinations may be possible in addition to the methods of combinations exemplified above.

[0297] The operation of the method according to an embodiment of the present disclosure can be implemented as a computer-readable program or code on a computer-readable recording medium. A computer-readable recording medium includes all types of recording devices in which information that can be read by a computer system is stored. Additionally, the computer-readable recording medium may be distributed across networked computer systems, allowing the computer-readable program or code to be stored and executed in a distributed manner.

[0298] In addition, computer-readable recording media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Program instructions may include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0299] Some aspects of the present disclosure have been described in the context of a device, but may also be described according to a corresponding method, wherein a block or device corresponds to a method step or a feature of a method step. Similarly, aspects described in the context of a method may also be described according to a corresponding block or item or a feature of a corresponding device. Some or all of the method steps may be performed by (or using) a hardware device, such as, for example, a microprocessor, a programmable computer, or an electronic circuit. In some embodiments, at least one of the most important method steps may be performed by such a device.

[0300] In the embodiments, a programmable logic device (e.g., a field-programmable gate array) may be used to perform some or all of the functions of the methods described herein. In the embodiments, the field-programmable gate array may operate with a microprocessor to perform one of the methods described herein. Generally, it is preferable that the methods be performed by some hardware device.

[0301] Although the present disclosure has been described with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the present disclosure without departing from the spirit and scope of the present disclosure as set forth in the following claims.

Claims

1. In the method of user equipment (UE), A step of receiving a first message from a base station containing channel state information (CSI) reporting setting information—the CSI reporting setting information includes a CSI reporting type and a first setting for CSI prediction reporting using a UE-side Artificial Intelligence (AI) model; Based on the fact that the above CSI reporting type is a periodic CSI reporting type, the step of receiving a reference signal (RS) for CSI reporting from the base station; Based on the first setting above, a step of inputting the measured value of the received RS into the UE-side AI model to generate a CSI prediction value; and A step comprising transmitting a second message containing the generated CSI prediction value to the base station. UE's method.

2. In Claim 1, The above CSI report setting information further includes a second setting for reporting the value of the RS signal measured above. UE's method.

3. In Claim 2, The second message further includes one or more measurement values ​​of the RS signal measured based on the second setting, UE's method.

4. In Claim 1, The first setting for the CSI prediction report using the above-mentioned UE-side AI model includes a first parameter indicating that the CSI report is a report of a predicted value by the above-mentioned UE-side AI model, and setting information for one or more channel state-related predicted values ​​to be generated by the above-mentioned UE-side AI model, and The above-mentioned predicted values ​​related to channel status include predicted channel quality information (p-CQI), predicted precoding matrix indicator (p-PMI), predicted CSI-RS resource indicator (p-CRI), predicted reference signal received power RSRP (p-CRI-RSRP) of CSI-RS corresponding to the predicted CRI, index of the predicted synchronization signal block (SSB) (p-SSB-index), or predicted RSRP for the predicted SSB index (p-SSB-index-RSRP), resource block indicator of the predicted synchronization signal / physical broadcast channel (SS / PBCH) (SS / PBCH resource block indicator, p-SSBRI), predicted layer indicator (p-LI), predicted rank indicator (p-RI), or the predicted first including one or more of layer (predicted layer 1, L1) - reference signal received power (p-L1-RSRP), UE's method.

5. In Claim 1, The above CSI reporting setting information includes setting information for triggering states for CSI reporting, and CSI reporting related settings associated with each of the triggering states for CSI reporting. UE's method.

6. In the method of user equipment (UE), A step of receiving a first message from a base station containing channel state information (CSI) reporting setting information—the CSI reporting setting information includes a CSI reporting type, a first setting for CSI prediction reporting using a UE-side artificial intelligence (AI) model, and a second setting for CSI reporting not using the UE-side AI model; Based on the fact that the above CSI report type is a non-periodic CSI report type, the step of receiving downlink control information (DCI) from the base station that triggers the CSI report; A step of identifying whether the DCI indicates a first CSI report triggering state within a first CSI report triggering state list included in the first setting or a second CSI report triggering state within a second CSI report triggering state list included in the second setting; A step of receiving a reference signal (RS) for CSI reporting from the base station based on the DCI indicating the first CSI reporting triggering state; Based on the first setting and the DCI, the step of inputting the measured value of the received RS into the UE-side AI model to generate a CSI prediction value; and A step comprising transmitting a second message containing the generated CSI prediction value to the base station. UE's method.

7. In Claim 6, When the above DCI is scrambled with a first radio network temporary identifier (RNTI) instructing the use of the UE-side AI model, it is identified as indicating a first CSI reporting triggering state within a first CSI reporting triggering state list included in the first setting, UE's method.

8. In Claim 7, When the above DCI is scrambled with a second RNTI different from the above first RNTI, identified as indicating a second CSI reporting triggering state within the second CSI reporting triggering state list included in the second setting, UE's method.

9. In Claim 6, Based on the fact that the above first setting further includes a third CSI report triggering status list, the DCI further includes an identifier for indicating one of the first CSI report triggering status list or the third CSI report triggering status list, UE's method.

10. In Claim 6, The second message further includes one or more measurement values ​​of the RS signal measured based on the second setting, UE's method.

11. In Claim 6, The first setting for the CSI prediction report using the above-mentioned UE-side AI model includes a first parameter indicating that the CSI report is a report of a predicted value by the above-mentioned UE-side AI model, and setting information for one or more channel state-related predicted values ​​to be generated by the above-mentioned UE-side AI model, and The above-mentioned predicted values ​​related to channel status include predicted channel quality information (p-CQI), predicted precoding matrix indicator (p-PMI), predicted CSI-RS resource indicator (p-CRI), predicted reference signal received power RSRP (p-CRI-RSRP) of CSI-RS corresponding to the predicted CRI, index of the predicted synchronization signal block (SSB) (p-SSB-index), or predicted RSRP for the predicted SSB index (p-SSB-index-RSRP), resource block indicator of the predicted synchronization signal / physical broadcast channel (SS / PBCH) (SS / PBCH resource block indicator, p-SSBRI), predicted layer indicator (p-LI), predicted rank indicator (p-RI), or the predicted first including one or more of layer (predicted layer 1, L1) - reference signal received power (p-L1-RSRP), UE's method.

12. In a method of user equipment (UE), A step of receiving a first message from a base station containing channel state information (CSI) reporting setting information—the CSI reporting setting information includes a CSI reporting type, a first setting for CSI prediction reporting using a UE-side artificial intelligence (AI) model, and a second setting for CSI reporting not using the UE-side AI model; Based on the fact that the above CSI reporting type is a semi-static CSI reporting type, the step of receiving a second message for enabling / disabling semi-static CSI reporting from the base station—the second message includes two or more CSI reporting triggering states based on at least one of the first setting or the second setting; A step of receiving downlink control information (DCI) for indicating one of the CSI reporting triggering states included in the second message; A step of receiving a reference signal (RS) for CSI reporting from the base station based on the CSI reporting triggering state indicated by the DCI; and The method includes the step of transmitting a third message to the base station that includes one or more values ​​based on the received RS, and One or more values ​​based on the received RS are values ​​indicated by the DCI, UE's method.

13. In Claim 12, The second message further includes an indicator for the CSI report triggering states included in the second message to indicate one of the first setting or the second setting. UE's method.

14. In Claim 12, If the CSI report triggering states corresponding to the first setting and the CSI report triggering states corresponding to the second setting are included in the first CSI report triggering list, the second message includes all CSI report triggering states included in the first CSI report triggering list. UE's method.

15. In Claim 12, When the above DCI is scrambled with a first radio network temporary identifier (RNTI) instructing the use of the UE-side AI model, it is identified as indicating a first CSI reporting triggering state within a first CSI reporting triggering state list included in the first setting, UE's method.

16. In Claim 15, When the above DCI is scrambled with a second RNTI different from the above first RNTI, identified as indicating a second CSI reporting triggering state within the second CSI reporting triggering state list included in the second setting, UE's method.

17. In Claim 12, If one or more values ​​based on the received RS included in the third message are CSI prediction values ​​obtained by inputting the value indicated by the DCI, which is the value measured by the received RS, into the UE-side AI model, the third message further includes one or more measured values ​​of the RS signal measured based on the second setting. UE's method.

18. In Claim 12, The first setting for the CSI prediction report using the above-mentioned UE-side AI model includes a first parameter indicating that the CSI report is a report of a predicted value by the above-mentioned UE-side AI model, and setting information for one or more channel state-related predicted values ​​to be generated by the above-mentioned UE-side AI model, and The above-mentioned predicted values ​​related to channel status include predicted channel quality information (p-CQI), predicted precoding matrix indicator (p-PMI), predicted CSI-RS resource indicator (p-CRI), predicted reference signal received power RSRP (p-CRI-RSRP) of CSI-RS corresponding to the predicted CRI, index of the predicted synchronization signal block (SSB) (p-SSB-index), or predicted RSRP for the predicted SSB index (p-SSB-index-RSRP), resource block indicator of the predicted synchronization signal / physical broadcast channel (SS / PBCH) (SS / PBCH resource block indicator, p-SSBRI), predicted layer indicator (p-LI), predicted rank indicator (p-RI), or the predicted first including one or more of layer (predicted layer 1, L1) - reference signal received power (p-L1-RSRP), UE's method.

19. In Claim 12, The above CSI reporting setting information includes setting information for triggering states for CSI reporting, and CSI reporting related settings associated with each of the triggering states for CSI reporting. UE's method.

20. In Claim 12, The above CSI report setting information further includes settings associated with the above RS resource, UE's method.

Images