Method and device for model monitoring in beam management using artificial intelligence and machine learning

Abstract

Provided are a method and a device for model monitoring in beam management using artificial intelligence and machine learning. This terminal receives a first channel state information (CSI) report configuration message for model inference. Here, the first CSI report configuration message includes first reference signal resource configuration information and second reference signal resource configuration information. In addition, the terminal performs first measurement on a first reference signal corresponding to the first reference signal resource configuration information, and acquires a prediction result for a second reference signal corresponding to the second reference signal resource configuration information on the basis of the first measurement. In addition, the terminal receives a second CSI report configuration message for model monitoring, and after receiving the second CSI report configuration message, performs second measurement on the second reference signal. Thereafter, the terminal calculates the accuracy of the prediction result on the basis of a result of the second measurement and the prediction result.

Description

Method and apparatus for model monitoring in beam management using artificial intelligence and machine learning

[0001] This specification relates to wireless communication applicable to 5G NR, 5G-Advanced, and 6G.

[0002] As the times change and more communication devices demand larger communication traffic, there is a demand for next-generation 5G systems, which are wireless broadband communication systems that are improved over existing LTE systems. In these next-generation 5G systems, referred to as NewRAT, communication scenarios are classified into Enhanced Mobile BroadBand (eMBB), Ultra-reliability and low-latency communication (URLLC), and Massive Machine-Type Communications (mMTC).

[0003] Here, eMBB is a next-generation mobile communication scenario characterized by High Spectrum Efficiency, High User Experienced Data Rate, and High Peak Data Rate; URLLC is a next-generation mobile communication scenario characterized by Ultra Reliable, Ultra Low Latency, and Ultra High Availability (e.g., V2X, Emergency Service, Remote Control); and mMTC is a next-generation mobile communication scenario characterized by Low Cost, Low Energy, Short Packet, and Massive Connectivity (e.g., IoT).

[0004] One disclosure of this specification aims to provide a method and apparatus for measuring the accuracy of AI / ML deployed to a terminal capable of performing beam management using AI / ML (Artificial Intelligence / Machine Learning) in a wireless communication system, wherein at least one model monitoring period and period change condition are set by a base station, and the model monitoring period is adaptedly changed when the set condition is satisfied.

[0005] In one embodiment of the present specification, in a wireless communication system, a terminal receives a first channel state information (CSI) report configuration message for model inference. Here, the first CSI report configuration message includes first reference signal resource configuration information and second reference signal resource configuration information. The terminal then performs a first measurement on a first reference signal corresponding to the first reference signal resource configuration information and obtains a prediction result for a second reference signal corresponding to the second reference signal resource configuration information based on the first measurement. Additionally, the terminal receives a second CSI report configuration message for model monitoring and, after receiving the second CSI report configuration message, performs a second measurement on the second reference signal. Subsequently, the terminal provides a method for calculating the accuracy of the prediction result based on the result of the second measurement and the prediction result.

[0006] Furthermore, one embodiment of the present invention provides a wireless communication system comprising at least one processor and at least one memory that stores instructions and is operabably electrically connected to at least one processor, wherein the operation performed based on the instruction being executed by at least one processor comprises: receiving a first CSI (channel state information) report configuration message for model inference. Herein, the first CSI report configuration message includes first reference signal resource configuration information and second reference signal resource configuration information. Then, a first measurement is performed on a first reference signal corresponding to the first reference signal resource configuration information, and a prediction result for a second reference signal corresponding to the second reference signal resource configuration information is obtained based on the first measurement. Additionally, a second CSI report configuration message for model monitoring is received, and after receiving the second CSI report configuration message, a second measurement is performed on the second reference signal. Subsequently, a terminal is provided that calculates the accuracy of the prediction result based on the result of the second measurement and the prediction result.

[0007] The accuracy calculated above can be used to evaluate model performance.

[0008] The terminal can transmit a result report based on the accuracy calculated above.

[0009] The first measurement and the second measurement above may be based on at least one of RSRP (Reference Signal Received Power) and RSRQ (Reference Signal Received Quality).

[0010] Meanwhile, the first reference signal resource setting information corresponds to the first CSI resource setting ID (identity), and the second reference signal resource setting information may correspond to the second CSI resource setting ID. The first CSI report setting message may further include the first CSI resource setting ID and the second CSI resource setting ID. Here, the second CSI report setting message may include the second CSI resource setting ID.

[0011] According to the disclosure of the present specification, when an entire beam belonging to Set A is set as a CSI resource for AI / ML model monitoring, the resource setting information for Set A, which is previously set for model inference or training, is applied as is, thereby reducing the overall signaling overhead for model monitoring settings and improving the accuracy of the terminal's model performance.

[0012] Figure 1 is a diagram illustrating a wireless communication system.

[0013] Figure 2 illustrates the structure of a wireless frame used in NR.

[0014] FIGS. 3a to 3c are exemplary diagrams illustrating exemplary architectures for wireless communication services.

[0015] Figure 4 illustrates the slot structure of an NR frame.

[0016] Figure 5 illustrates an example of a subframe type in NR.

[0017] Figure 6 illustrates the structure of a self-contained slot.

[0018] Figure 7 shows an example of initial beam measurement and selection in NR.

[0019] Figure 8 shows an example of the initial connection procedure between a terminal and a base station in NR.

[0020] Figure 9 shows an example of a candidate beam setup in NR.

[0021] Figures 10a to 10c show three procedures for beam management in NR.

[0022] Figures 11a through 11c show examples of beam reporting procedures in NR.

[0023] FIG. 12 is a flowchart illustrating a method of operation of a terminal according to one embodiment of the present specification.

[0024] FIG. 13 illustrates a procedure of a base station and a terminal according to one embodiment of the present specification.

[0025] FIG. 14 is a flowchart illustrating a method of operation of a terminal according to another embodiment of the present specification.

[0026] FIG. 15 shows an apparatus according to one embodiment of the present specification.

[0027] FIG. 16 is a block diagram showing the configuration of a terminal according to one embodiment of the present specification.

[0028] FIG. 17 shows a block diagram of a processor in which the disclosure of the present specification is implemented.

[0029] FIG. 18 is a block diagram showing in detail the transceiver of the first device shown in FIG. 15 or the transceiver of the device shown in FIG. 16.

[0030] It should be noted that technical terms used in this specification are used merely to describe specific embodiments and are not intended to limit the content of this specification. Furthermore, unless specifically defined otherwise in this specification, technical terms used in this specification should be interpreted in the sense generally understood by those skilled in the art to which this disclosure pertains, and should not be interpreted in an overly broad or overly narrow sense. Additionally, if a technical term used in this specification is an incorrect technical term that fails to accurately express the content and concept of this specification, it should be understood as being replaced by a technical term that can be correctly understood by those skilled in the art. Moreover, general terms used in this specification should be interpreted according to their prior definitions or the context, and should not be interpreted in an overly narrow sense.

[0031] Additionally, singular expressions used in this specification include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "composed of" or "have" should not be interpreted as necessarily including all of the various components or steps described in the specification, and should be interpreted as meaning that some of the components or steps may be omitted or additional components or steps may be included.

[0032] Additionally, terms including ordinal numbers, such as first, second, etc., used herein may be used to describe various components, but said components shall 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 rights, the first component may be named the second component, and similarly, the second component may be named the first component.

[0033] When it is stated that a component is connected to or coupled with another component, it may be directly connected to or coupled with that other component, or there may be other components in between. On the other hand, when it is stated that a component is directly connected to or directly coupled with another component, it should be understood that there are no other components in between.

[0034] Hereinafter, embodiments will be described in detail with reference to the attached drawings. Identical or similar components regardless of drawing symbols are assigned the same reference number, and redundant descriptions thereof will be omitted. Furthermore, in describing the contents of this specification, if it is determined that a detailed description of related prior art may obscure the gist of this specification, such detailed description will be omitted. Additionally, it should be noted that the attached drawings are intended only to facilitate understanding of the contents and concepts of this specification, and should not be interpreted as limiting the contents and concepts of this specification. The contents and concepts of this specification should be interpreted as extending to all modifications, equivalents, and substitutions in addition to the attached drawings.

[0035] In this specification, “A or B” may mean “only A,” “only B,” or “both A and B.” Alternatively, in this specification, “A or B” may be interpreted as “A and / or B.” For example, in this specification, “A, B or C” may mean “only A,” “only B,” “only C,” or “any combination of A, B and C.”

[0036] As used herein, a slash ( / ) or a comma may mean “and / or.” For example, “A / B” may mean “A and / or B.” Accordingly, “A / B” may mean “only A,” “only B,” or “both A and B.” For example, “A, B, C” may mean “A, B or C.”

[0037] In this specification, “at least one of A and B” may mean “only A,” “only B,” or “both A and B.” Additionally, in this specification, the expressions “at least one of A or B” or “at least one of A and / or B” may be interpreted as synonymous with “at least one of A and B.”

[0038] Additionally, in this specification, “at least one of A, B and C” may mean “only A,” “only B,” “only C,” or “any combination of A, B and C.” Additionally, “at least one of A, B or C” or “at least one of A, B and / or C” may mean “at least one of A, B and C.”

[0039] Additionally, parentheses used in this specification may mean “for example.” Specifically, where indicated as “Control Information (PDCCH),” “PDCCH (Physical Downlink Control Channel)” may be proposed as an example of “Control Information.” In other words, “Control Information” in this specification is not limited to “PDCCH,” and “PDDCH” may be proposed as an example of “Control Information.” Furthermore, even when indicated as “Control Information (i.e., PDCCH),” “PDCCH” may be proposed as an example of “Control Information.”

[0040] Technical features described individually within a single drawing in this specification may be implemented individually or simultaneously.

[0041] In the attached drawings, User Equipment (UE) is illustrated as an example, but the illustrated UE may also be referred to by terms such as Terminal or Mobile Equipment (ME). Furthermore, the UE may be a portable device such as a laptop, mobile phone, PDA, smartphone, multimedia device, etc., or a non-portable device such as a PC or vehicle-mounted device.

[0042] In the following, UE is used as an example of a wireless communication-capable device (e.g., wireless communication device, wireless device, or wireless apparatus). The operations performed by the UE may be performed by any wireless communication-capable device. A wireless communication-capable device may also be referred to as a wireless communication device, wireless device, or wireless apparatus.

[0043] The term "base station" as used below generally refers to a fixed station that communicates with wireless devices, and can be used as a comprehensive term including eNodeB (evolved-NodeB), eNB (evolved-NodeB), BTS (Base Transceiver System), Access Point, gNB (Next generation NodeB), RRH (remote radio head), TP (transmission point), RP (reception point), relay, etc.

[0044] This specification describes embodiments using LTE systems, LTE-A systems and NR systems, but these embodiments may be applied to any communication system corresponding to the above definitions.

[0045] Wireless Communication System

[0046] Building on the success of LTE (long term evolution) / LTE-Advanced (LTE-A) for 4th generation mobile communication, commercialization and subsequent research for the next generation, namely 5th generation (so-called 5G) mobile communication, are also continuing.

[0047] Fifth-generation mobile communication, as defined by the International Telecommunication Union (ITU), refers to providing data transmission speeds of up to 20 Gbps and a perceived transmission speed of at least 100 Mbps anywhere. Its official name is 'IMT-2020'.

[0048] The ITU presents three major usage scenarios, such as eMBB (enhanced Mobile BroadBand), mMTC (massive Machine Type Communication), and URLLC (Ultra Reliable and Low Latency Communications).

[0049] URLLC concerns use scenarios requiring high reliability and low latency. For example, services such as autonomous driving, factory automation, and augmented reality require high reliability and low latency (e.g., latency of 1ms or less). Currently, the latency of 4G (LTE) is statistically 21-43ms (best 10%) and 33-75ms (median). This is insufficient to support services requiring latency of 1ms or less. Next, eMBB use scenarios concern use scenarios requiring mobile ultra-broadband.

[0050] In other words, 5th generation mobile communication systems support higher capacity than current 4G LTE, increase the density of mobile broadband users, and can support D2D (Device to Device), high stability, and MTC (Machine type communication). 5G research and development also aims for lower latency and lower battery consumption than 4G mobile communication systems to better implement the Internet of Things. New radio access technology (New RAT or NR) may be proposed for such 5G mobile communication.

[0051] The NR frequency band can be defined by two types of frequency ranges (FR1, FR2). The numerical values ​​of the frequency ranges may change; for example, the two types of frequency ranges (FR1, FR2) may be as shown in Table 1 below. For convenience of explanation, among the frequency ranges used in the NR system, FR1 may mean the “sub 6GHz range” and FR2 may mean the “above 6GHz range” and may be referred to as millimeter wave (mmW).

[0052] Frequency Range designationCorresponding frequency rangeSubcarrier SpacingFR1410MHz - 7125MHz15, 30, 60kHzFR224250MHz - 52600MHz60, 120, 240kHz

[0053] The numerical values ​​of the frequency range of the NR system may change. For example, FR1 may include a band of 410 MHz to 7125 MHz as shown in Table 1. That is, FR1 may include a frequency band of 6 GHz (or 5850, 5900, 5925 MHz, etc.) or higher. For example, the frequency band of 6 GHz (or 5850, 5900, 5925 MHz, etc.) or higher included within FR1 may include an unlicensed band. The unlicensed band may be used for various purposes, for example, for communication for vehicles (e.g., autonomous driving).

[0054] Meanwhile, 3GPP-based communication standards define downlink physical channels corresponding to resource elements that carry information originating from upper layers, and downlink physical signals corresponding to resource elements used by the physical layer but not carrying information originating from upper layers. For example, physical downlink shared channel (PDSCH), physical broadcast channel (PBCH), physical multicast channel (PMCH), physical control format indicator channel (PCFICH), physical downlink control channel (PDCCH), and physical hybrid ARQ indicator channel (PHICH) are defined as downlink physical channels, and reference signals and synchronization signals are defined as downlink physical signals. A reference signal (RS), also referred to as a pilot, refers to a signal of a specific waveform that is known to both the gNB and the UE. For example, cell-specific RS, UE-specific RS (UE-RS), positioning RS (PRS), and channel state information RS (CSI-RS) are defined as downlink reference signals. The 3GPP LTE / LTE-A standard defines uplink physical channels corresponding to resource elements that carry information originating from upper layers, and uplink physical signals corresponding to resource elements used by the physical layer but that do not carry information originating from upper layers.For example, the physical uplink shared channel (PUSCH), physical uplink control channel (PUCCH), and physical random access channel (PRACH) are defined as uplink physical channels, and the demodulation reference signal (DMRS) for uplink control / data signals and the sounding reference signal (SRS) used for uplink channel measurement are defined.

[0055] In this specification, PDCCH (Physical Downlink Control Channel) / PCFICH (Physical Control Format Indicator Channel) / PHICH (Physical Hybrid automatic retransmit request Indicator Channel) / PDSCH (Physical Downlink Shared Channel) each refers to a set of time-frequency resources or a set of resource elements carrying DCI (Downlink Control Information) / CFI (Control Format Indicator) / downlink ACK / NACK (ACKnowlegement / Negative ACK) / downlink data. Additionally, PUCCH (Physical Uplink Control Channel) / PUSCH (Physical Uplink Shared Channel) / PRACH (Physical Random Access Channel) each refers to a set of time-frequency resources or a set of resource elements carrying UCI (Uplink Control Information) / uplink data / random access signals.

[0056] Figure 1 is a diagram illustrating a wireless communication system.

[0057] As can be seen with reference to FIG. 1, the wireless communication system includes at least one base station (BS). The BS is divided into a gNodeB (or gNB) (20a) and an eNodeB (or eNB) (20b). The gNB (20a) supports 5th generation mobile communication. The eNB (20b) supports 4th generation mobile communication, i.e., LTE (Long Term Evolution).

[0058] Each base station (20a and 20b) provides communication services for a specific geographical area (generally called a cell) (20-1, 20-2, 20-3). A cell can be further divided into multiple areas (called sectors).

[0059] User Equipment (UE) typically belongs to a single cell, and the cell to which the UE belongs is called the serving cell. The base station that provides communication services to the serving cell is called the serving base station (serving BS). Since the wireless communication system is a cellular system, there exists another cell adjacent to the serving cell. The other cell adjacent to the serving cell is called the neighbor cell. The base station that provides communication services to the neighbor cell is called the neighbor base station (neighbor BS). The serving cell and neighbor cells are determined relatively to the UE.

[0060] In the following, the downlink refers to communication from the base station (20) to the UE (10), and the uplink refers to communication from the UE (10) to the base station (20). In the downlink, the transmitter may be part of the base station (20) and the receiver may be part of the UE (10). In the uplink, the transmitter may be part of the UE (10) and the receiver may be part of the base station (20).

[0061] Meanwhile, wireless communication systems can be broadly classified into Frequency Division Duplex (FDD) and Time Division Duplex (TDD) methods. In the FDD method, uplink and downlink transmissions occupy different frequency bands. In the TDD method, uplink and downlink transmissions occupy the same frequency band and occur at different times. The channel response in the TDD method is practically reciprocal. This means that the downlink channel response and the uplink channel response are nearly identical within a given frequency range. Therefore, in a wireless communication system based on TDD, there is an advantage in that the downlink channel response can be derived from the uplink channel response. In the TDD method, since the entire frequency band is time-divided for uplink and downlink transmissions, downlink transmission by the base station and uplink transmission by the UE cannot be performed simultaneously. In a TDD system where uplink and downlink transmissions are separated by subframes, uplink and downlink transmissions are performed in different subframes.

[0062] Figure 2 illustrates the structure of a wireless frame used in NR.

[0063] In NR, uplink and downlink transmissions consist of frames. A radio frame has a length of 10 ms and is defined as two 5 ms half-frames (HF). A half-frame is defined as five 1 ms subframes (SF). A subframe is divided into one or more slots, and the number of slots within a subframe depends on the subcarrier spacing (SCS). Each slot contains 12 or 14 OFDM(A) symbols depending on the cyclic prefix (CP). When a standard CP is used, each slot contains 14 symbols. When an extended CP is used, each slot contains 12 symbols. Here, the symbols may include OFDM symbols (or CP-OFDM symbols) or SC-FDMA symbols (or DFT-s-OFDM symbols).

[0064] Support for various numerologies

[0065] In NR systems, as wireless communication technology develops, multiple numerologies may be provided to the terminal. For example, when the SCS is 15 kHz, it supports a wide area in traditional cellular bands; when the SCS is 30 kHz / 60 kHz, it supports dense-urban, lower latency, and wider carrier bandwidth; and when the SCS is 60 kHz or higher, it supports a bandwidth greater than 24.25 GHz to overcome phase noise.

[0066] The above numerology can be defined by the cycle prefix (CP) length and the subcarrier spacing (SCS). A single cell can provide multiple numerologies to the terminal. When the index of the numerology is denoted by μ, each subcarrier spacing and the corresponding CP length may be as shown in the table below.

[0067] μ△f=2 μ 15 [kHz]CP015General 130General 260General, Extended 3120General 4240General 5480General 6960General

[0068] For a standard CP, when the numerology index is denoted by μ, the number of OFDM symbols per slot (N slot symb ), number of slots per frame (N frame,μ slot ) And, the number of slots per subframe (N subframe,μ slot ) is as shown in the table below.

[0069] μ△f=2 μ 15 [kHz]N slot symb N frame,μ slot N subframe,μ slot 015141011301420226014404312014808424014160165480143203269601464064

[0070] For extended CP, when the numerology index is denoted by μ, the number of OFDM symbols per slot (N slot symb ), number of slots per frame (N frame,μ slot ) And, the number of slots per subframe (N subframe,μ slot ) is as shown in the table below.

[0071] μSCS (15*2 u )N slot symb N frame,μ slot N subframe,μslot 260KHz (u=2)12404

[0072] In an NR system, the OFDM(A) numerology (e.g., SCS, CP length, etc.) can be configured differently among multiple cells that are merged into a single terminal. Accordingly, the (absolute time) interval of a time resource (e.g., SF, slot, or TTI) (collectively referred to as TU (Time Unit) for convenience) composed of the same number of symbols can be configured differently among the merged cells.

[0073] FIGS. 3a to 3c are exemplary diagrams illustrating exemplary architectures for wireless communication services.

[0074] Referring to Fig. 3a, the UE is connected to an LTE / LTE-A based cell and an NR based cell in a DC (dual connectivity) manner.

[0075] The above NR-based cell is connected to the core network for existing 4th generation mobile communication, namely the EPC (Evolved Packet Core).

[0076] Referring to Fig. 3b, unlike Fig. 3a, the LTE / LTE-A based cell is connected to a core network for 5th generation mobile communication, that is, a 5G core network.

[0077] A service method based on the architecture as illustrated in Figures 3a and 3b above is called NSA (non-standalone).

[0078] Referring to Fig. 3c, the UE is connected only to NR-based cells. A service method based on this architecture is called SA (standalone).

[0079] Meanwhile, in the above NR, it may be considered that reception from the base station utilizes a downlink subframe, and transmission to the base station utilizes an uplink subframe. This method can be applied to paired spectra and unpaired spectra. A paired spectrum means that it includes two carrier spectra for downlink and uplink operations. For example, in a paired spectrum, one carrier may include a downlink band and an uplink band that are paired with each other.

[0080] Figure 4 illustrates the slot structure of an NR frame.

[0081] A slot contains multiple symbols in the time domain. For example, in the case of a standard CP, one slot contains 14 symbols, whereas in the case of an extended CP, one slot contains 12 symbols. A carrier contains multiple subcarriers in the frequency domain. A Resource Block (RB) is defined as multiple (e.g., 12) consecutive subcarriers in the frequency domain. A Bandwidth Part (BWP) is defined as multiple consecutive (physical, P)RBs in the frequency domain and can correspond to a single numerology (e.g., SCS, CP length, etc.). A terminal may be configured with up to N (e.g., 4) BWPs in both the downlink and uplink. Downlink or uplink transmission is performed through an active BWP, and at a given time, only one of the BWPs configured for the terminal may be active. In the resource grid, each element is referred to as a Resource Element (RE), and a single complex symbol may be mapped to it.

[0082] Figure 5 illustrates an example of a subframe type in NR.

[0083] The transmission time interval (TTI) illustrated in Fig. 5 can be referred to as a subframe or slot for NR (or new RAT). The subframe (or slot) of Fig. 5 can be used in the TDD system of NR (or new RAT) to minimize data transmission delay. As illustrated in Fig. 5, the subframe (or slot) contains 14 symbols. The symbols at the beginning of the subframe (or slot) can be used for the downlink (DL) control channel, and the symbols at the end of the subframe (or slot) can be used for the uplink (UL) control channel. The remaining symbols can be used for DL ​​data transmission or UL data transmission. According to this subframe (or slot) structure, downlink transmission and uplink transmission can proceed sequentially within a single subframe (or slot). Thus, downlink data can be received within the subframe (or slot), and uplink acknowledgments (ACK / NACK) can be transmitted within that subframe (or slot).

[0084] The structure of such a subframe (or slot) can be called a self-contained subframe (or slot).

[0085] Specifically, the first N symbols within the slot are used to transmit a DL control channel (hereinafter referred to as the DL control area), and the last M symbols within the slot may be used to transmit a UL control channel (hereinafter referred to as the UL control area). N and M are each integers greater than or equal to 0. A resource area (hereinafter referred to as the data area) located between the DL control area and the UL control area may be used for DL ​​data transmission or for UL data transmission. For example, a physical downlink control channel (PDCCH) may be transmitted in the DL control area, and a physical downlink shared channel (PDSCH) may be transmitted in the DL data area. A physical uplink control channel (PUCCH) may be transmitted in the UL control area, and a physical uplink shared channel (PUSCH) may be transmitted in the UL data area.

[0086] Using such a subframe (or slot) structure has the advantage of reducing the time required to retransmit data that has received errors, thereby minimizing the waiting time for final data transmission. In such a self-contained subframe (or slot) structure, a time gap may be required during the transition from transmit mode to receive mode or from receive mode to transmit mode. To this end, some OFDM symbols during the transition from DL to UL in the subframe structure may be set as a Guard Period (GP).

[0087] Figure 6 illustrates the structure of a self-contained slot.

[0088] In an NR system, a frame is characterized by a self-complete structure in which a DL control channel, DL or UL data, a UL control channel, etc., can all be included within a single slot. For example, the first N symbols within the slot are used to transmit a DL control channel (hereinafter referred to as the DL control area), and the last M symbols within the slot may be used to transmit a UL control channel (hereinafter referred to as the UL control area). N and M are each integers greater than or equal to 0. The resource area (hereinafter referred to as the data area) located between the DL control area and the UL control area may be used for transmitting DL data or for transmitting UL data. As an example, the following configuration can be considered. Each section is listed in chronological order.

[0089] 1. DL only configuration

[0090] 2. UL only configuration

[0091] 3. Mixed UL-DL Configuration

[0092] - DL Area + GP (Guard Period) + UL Control Area

[0093] - DL Control Area + GP + UL Area

[0094] DL Area: (i) DL Data Area, (ii) DL Control Area + DL Data Area

[0095] UL Area: (i) UL Data Area, (ii) UL Data Area + UL Control Area

[0096] PDCCH can be transmitted in the DL control area, and PDSCH can be transmitted in the DL data area. PUCCH can be transmitted in the UL control area, and PUSCH can be transmitted in the UL data area. In PDCCH, DCI (Downlink Control Information), such as DL data scheduling information and UL data scheduling information, can be transmitted. In PUCCH, UCI (Uplink Control Information), such as ACK / NACK (Positive Acknowledgement / Negative Acknowledgement) information for DL ​​data, CSI (Channel State Information) information, and SR (Scheduling Request), can be transmitted. GP provides a time gap during the process of the base station and the terminal switching from transmit mode to receive mode or from receive mode to transmit mode. Within a subframe, some symbols at the point of transition from DL to UL can be set as GP.

[0097] <NR에서 빔 관리(beam management)>

[0098] Currently, the beam management method of 3GPP NR can be divided into an initial access phase and a connection establishment phase. A terminal performing the initial access procedure establishes the terminal's initial transmit / receive (initial Tx / Rx) beam through a random access procedure, namely the RACH (random access channel) procedure.

[0099] Figure 7 shows an example of initial beam measurement and selection in NR.

[0100] Referring to FIG. 7, to provide base station transmission beam (gNB Tx beam) settings to terminals (UE1 / UE2) without cell connection, the base station periodically and repeatedly transmits synchronization signal blocks (SSBs) mapped to beams of different directions. The SSBs can be transmitted at a 20ms interval within 5ms. Specifically, the default value for initial cell selection may be 20ms.

[0101] A terminal can inform the base station of information regarding a selected Tx beam by selecting a qualified SSB through signal measurements of periodically transmitted SSBs and transmitting a PRACH (physical random access channel) preamble mapped to the corresponding SSB. For example, based on signal strength measurements, terminals at different locations—namely, UE1 selecting an SSB with an SSB index of 3 and UE2 selecting an SSB with an SSB index of 9—can each transmit a PRACH preamble corresponding to the selected SSB. Here, it is assumed that each SSB is beamformed in a specific direction.

[0102] Figure 8 shows an example of the initial connection procedure between a terminal and a base station in NR.

[0103] Referring to FIG. 8, after the power of the terminal (UE) is turned on (S801), the UE receives cell-related parameter information required during the initial connection phase (e.g., PRACH information corresponding to each SSB) through a system information message transmitted by the base station (gNB) (S802). Here, the system information message includes SIB1 (system information block 1), which includes MIB (master information block) and cell common information.

[0104] After acquiring a system information message, the terminal receives SSBs that are periodically transmitted from the base station (S803). Then, the terminal measures the reference signal received power (RSRP) for the received SSBs. Among the measured RSRPs for N SSBs, i.e., beams, one SSB (beam) having the highest / qualified value is selected (S804).

[0105] Afterwards, the terminal transmits a random access (RA) preamble belonging to a PRACH resource corresponding to the selected SSB (beam) to the base station (S805). Through this, the terminal can notify the base station of the selected initial beam information.

[0106] The base station receives a random access (RA) preamble belonging to a PRACH resource corresponding to the selected SSB (beam) from the terminal, and in response to this, transmits a random access response (RAR) to the terminal using the selected SSB (beam) (S806).

[0107] Meanwhile, a base station that does not know the location / beam information of the terminal that first entered the cell—that is, the terminal performing the CBRA (contention based random access) procedure—can set up to 64 beams cell-commonly for beam configuration of the unconnected terminal, and the terminal performs the operation of sequentially measuring all beams to find the optimal beam at its location. This not only causes time delays in beam selection and cell connection as the number of beams in the cell increases, but can also cause the terminal's power consumption to increase by forcing the terminal to measure a large number of beams.

[0108] To address the aforementioned issues, the base station may map a wide beam to the SSB to determine the approximate location / beam of the initially connected terminal, and then configure a narrow beam through beam refinement operations after the terminal connects to the cell. However, while the narrow beam provides the terminal with a high data rate, it is sensitive to terminal movement or environmental changes, which can easily lead to disconnections. To resolve this, the base station allocates CSI resources (CSI-RS / SSB) mapped with candidate beams to the terminal in a UE-specific manner, thereby causing the terminal to continuously measure surrounding beam strength and report the measurement results to the base station. This can be configured by the base station through CSI resource configuration and CSI report configuration.

[0109] Figure 9 shows an example of a candidate beam setup in NR.

[0110] A terminal that has been configured for beam reporting performs reporting based on the base station's configuration by measuring the reference signal (RS) assigned to it. This follows the CSI framework defined by 3GPP. However, this type of UE-specific CSI configuration method has a problem in that the RS resources allocated per terminal increase rapidly as the number of terminals within a cell increases. To mitigate this resource overhead, the base station may choose a method of allocating the same candidate beam—that is, the CSI resource—to terminals in similar locations, as shown in Fig. 9. This can be referred to as UE group-specific CSI resource configuration. However, if terminals with different mobility share the same resource, an issue arises where a new candidate beam resource must be allocated to terminals that move out of that resource area. If a minimum number of candidate beams is allocated to terminals with high / medium mobility to reduce resource overhead, the terminals will experience frequent RRC resets. Since candidate beam resets via RRC cause relatively large delays, this can lead to beam drops. To mitigate this issue, base stations can manage candidate beams by appropriately increasing the number of beams in the CSI resource set. However, from the terminal's perspective, there may be a trade-off issue where the burden on measurement increases due to the increased number of beams.

[0111] Figures 10a to 10c show three procedures for beam management in NR.

[0112] Beam management in NR can be defined by dividing it into three procedures in terms of procedures defined at the physical layer. Figure 10a illustrates Procedure 1 (P1), Figure 10b illustrates Procedure 2 (P2), and Figure 10c illustrates Procedure 3 (P3). P1 is an operation to find a transmit / receive beam pair (Tx / Rx beam pair) by simultaneously performing TRP (transmission reception point) beam sweeping and UE beam sweeping, similar to the beam setting method of a terminal performing the initial access procedure described earlier. A terminal that has entered connected mode recognizes that beams configured by the base station through candidate beam (i.e., CSI resource set) configuration will be swept, and first performs a signal strength measurement for the TRP beam. Once the terminal's TRP beam is selected via P2, the base station then repeatedly transmits the selected beam via P3. The terminal can select the UE beam while performing UE beam sweeping. In this operation, the decision of which beam the UE selects can be left to the terminal implementation. The aforementioned operation can be applied to both the downlink (DL) and the uplink (UL).

[0113] Figures 11a through 11c show examples of beam reporting procedures in NR.

[0114] Beam sweeping utilizes a method in which information about a beam is implicitly communicated by the base station providing reference signal (RS) resource information to the terminal through the configuration of specific candidate beams, i.e., CSI resource sets. In other words, rather than informing the terminal of the actual beam index, the terminal recognizes the information of the beam mapped by the base station through index information implicitly mapped to RS information using an RS resource indicator (RI). This is configured using the 3GPP CSI framework, and the terminal implicitly reports RSRP information for the four best beams (RI) to the base station by measuring the RS strength for the resources configured by the base station. The method of reporting these measurement results also follows the base station's RRC configuration, and 3GPP defines that it should be configured using one of the following three methods.

[0115] - Periodic reporting

[0116] - Aperioditic reporting

[0117] - Semi-persistent reporting

[0118] FIG. 11a illustrates a periodic CSI reporting method, which is triggered by an RRC configuration. Specifically, the terminal receives an RRC configuration message from the base station, which includes settings for CSI-related RS resources and reporting methods, i.e., CSI resource set information and information that CSI reporting is periodic (S1101a). Subsequently, the terminal receives periodically transmitted RS based on the received RRC configuration message (S1102a and S1105a), and measures the signal strength of the beam based on the received RS (S1103a and S1106a). Then, the terminal periodically reports the measured result (value) to the base station (S1104a and S1107a).

[0119] FIG. 11b illustrates a non-periodic CSI reporting method. Even if CSI-related RS resources and reporting methods are configured via an RRC configuration message, beam measurement via RS is not performed without a trigger message (or information) from a lower layer. That is, the terminal receives an RRC configuration message from the base station containing information regarding the configuration of CSI-related RS resources and reporting methods, namely CSI resource set information and information that CSI reporting is non-periodic (S1101b). The CSI report trigger is established via a MAC (medium access control) CE (control element) or DCI (downlink control information). The terminal receives CSI report trigger information containing a trigger indication from the base station via the MAC CE or DCI (S1102b), and receives RSs transmitted once based on the received trigger indication (S1103b). Here, the transmission of RSs for the CSI resource set may be transmitted after a specific time (e.g., X slots) in which the CSI report trigger information was transmitted. Subsequently, the terminal measures the signal strength of the beam based on the received RSs (S1104b). Then, the terminal reports the measured result (value) to the base station once (S1105b). Here, the CSI report may be transmitted after a specific time (e.g., Y slots) in which the CSI report trigger information was received.

[0120] FIG. 11c illustrates a semi-persistent reporting method, which is an intermediate method between periodic and non-periodic reporting methods. A terminal that receives settings for CSI-related RS resources and reporting methods via an RRC configuration message performs CSI reporting periodically only when activated by MAC CE, until it receives a deactivation message (or information). That is, the terminal receives an RRC configuration message from the base station containing settings for CSI-related RS resources and reporting methods, namely information on the CSI resource set and that CSI reporting is semi-persistent (S1101c), and CSI report activation is performed via MAC CE. The terminal receives CSI report activation information containing an activation indication from the base station via MAC CE (S1102c and S1110c), receives RSs periodically transmitted based on the received activation indication (S1103c, S1106c, S1111c and S1114c), and measures the signal strength of the beam based on the received RSs (S1104c, S1107c, S1112c and S1115c). Then, the terminal periodically reports the measured results (values) to the base station (S1105c, S1108c, S1113c and S1116c). After CSI reporting is activated, if the terminal receives CSI report deactivation information containing a deactivation indication from the base station via MAC CE (S1109c), the terminal stops CSI reporting.

[0121] The three methods for CSI reporting described above can be configured in relation to the transmission characteristics of the CSI-RS resource. That is, depending on the CSI-RS resource configuration, the RS can be configured to be transmitted periodicly, semi-persistently, or aperiodisically. In the case of periodic CSI-RS, the transmission periodicity and slot offset are set by the RRC, and accordingly, the CSI-RS is transmitted periodically. In the case of semi-persistent CSI-RS, the transmission periodicity and slot offset are set by the RRC, but the activation or deactivation of CSI-RS transmission is directed by the MAC CE (Control Element). In the case of aperiodis, the slot offset is set by the RRC, and CSI-RS transmission is triggered by the reception of DCI (Downlink Control Information). The characteristics of such CSI-RS transmission in the time domain are associated with the CSI reporting settings, which can determine the periodic, semi-persistent, or aperioditic mode of CSI reporting. Specifically, if CSI-RS transmission is set to periodic, CSI reporting can be set to periodic, semi-persistent, or aperioditic; if CSI-RS transmission is set to semi-persistent, CSI reporting can be set to semi-persistent or aperioditic; and if CSI-RS transmission is set to aperioditic, CSI reporting can be set to aperioditic only.

[0122] Meanwhile, 3GPP is conducting a study on a technology that applies AI / ML models to improve the delay and terminal power consumption in the aforementioned beam measurement.

[0123] The list of terms applied to AI / ML is discussed as shown in Table 5 below.

[0124] Terminology Description Data collection A process of collecting data by the network nodes, management entity, or UE for the purpose of AI / ML model training, data analytics, and inference AI / ML Model A data-driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs.)AI / ML Model Training: A process to train an AI / ML model [by learning the input / output relationship] in a data-driven manner and obtain the trained AI / ML model for inference AI / ML Model Inference: A process of using a trained AI / ML model to produce a set of outputs based on a set of inputs AI / ML Model Validation: A subprocess of training, to evaluate the quality of an AI / ML model using a dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for model training. AI / ML Model Testing: Model Training A sub-process of training used to evaluate the performance of the final AI / ML model using a dataset different from that used for validation. Unlike AI / ML model validation, testing does not assume subsequent tuning of the model.(A subprocess of training, to evaluate the performance of a final AI / ML model using a dataset different from one used for model training and validation. Differently from AI / ML model validation, testing does not assume subsequent tuning of the model.) UE-side (AI / ML) model An AI / ML model whose inference is performed entirely at the UE Network-side (AI / ML) model An AI / ML model whose inference is performed entirely at the network One-sided (AI / ML) model A UE-side (AI / ML) model or a Network-side (AI / ML) model Two-sided (AI / ML) model A pair of AI / ML model(s) in which joint inference is performed. Here, co-inference refers to AI / ML inference performed jointly by the UE and the network; that is, the first part of the inference is performed by the UE first, and the remaining part by the gNB, or vice versa.(A paired AI / ML model(s) over which joint inference is performed, where joint inference comprises AI / ML inference whose inference is performed jointly across the UE and the network, i.e., the first part of inference is firstly performed by the UE and then the remaining part is performed by the gNB, or vice versa.) AI / ML model transfer: The transmission of an AI / ML model via a wireless interface, comprising parameters of a model structure known to the receiving side or a new model having such parameters. Delivery may include a full model or a partial model. (Delivery of an AI / ML model over the air interface, either parameters of a model structure known at the receiving end or a new model with parameters. Delivery may contain a full model or a partial model.) Model download Model transfer from the network to UE Model upload Model transfer from UE to the network Federated learning / federated training A machine learning technique that trains AI / ML models on multiple distributed edge nodes (e.g., UE, gNB) each performing local model training using local data samples. This technique requires multiple interactions of the model but does not require the exchange of local data samples.(A machine learning technique that trains an AI / ML model across multiple decentralized edge nodes (e.g., UEs, gNBs) each performing local model training using local data samples. The technique requires multiple interactions of the model, but no exchange of local data samples.) Offline field data: Data collected from the field and used for offline training of the AI / ML model. Online field data: Data collected from the field and used for online training of the AI / ML model. Model monitoring: A procedure that monitors the inference performance of the AI / ML model. Supervised learning: A process of training a model from input and its corresponding labels. Unsupervised learning: A process of training a model without labeled data.Semi-supervised learning: A process of training a model with a mix of labeled and unlabeled data. Reinforcement Learning (RL): A process of training an AI / ML model from input (aka state) and a feedback signal (aka reward) resulting from the model's output (aka action) in an environment the model is interacting with. Model activation: Enabling an AI / ML model for a specific function. Model deactivation: Disabling an AI / ML model for a specific function. Model switching: Deactivating a currently active AI / ML model and activating a different AI / ML model for a specific function. AI / ML model for a specific function.

[0125] Recently, 3GPP RAN WG1 (Radio Access Network Working Group 1, RAN1) agreed to support Type 1 model monitoring methods for cases where UE-side AI / ML models are applied, and Type 1 model monitoring refers to cases where a network (e.g., a base station) sets up beam measurement and reporting for model monitoring on a terminal.

[0126] Type 1 model monitoring can be divided into two options depending on the performing entity. Option 1 is a method in which the terminal reports measurement results for monitoring to the network, and the network uses said measurement results to perform model performance evaluation. On the other hand, Option 2 is a method in which the terminal independently performs model performance evaluation based on the measured results and then reports the evaluation results to the network.

[0127] In particular, for Option 2, the terminal must perform a performance evaluation by comparing the results measured for model monitoring with the results predicted through model inference. To do this, the terminal must be able to recognize mapping or connection information regarding which beam among the beams predicted in the model inference results corresponds to each beam measured for monitoring.

[0128] In RAN1, to support UE-assisted model monitoring of Type 1 Option 2, it was agreed to reuse the existing CSI framework for the configuration for reporting monitoring results. Accordingly, a dedicated CSI reporting configuration for model monitoring is defined, and the configuration can be configured to include dedicated CSI resources for monitoring. Additionally, to link the CSI reporting configuration for inference with the CSI reporting configuration for monitoring, an identifier (identity, ID) to identify the inference reporting configuration may be included within the monitoring configuration.

[0129] However, in this structure, if the CSI resource for model monitoring is set as a subset of the beam set (Set A) used for inference, additional mapping information is required regarding which beam in Set A corresponds to the beam included in the monitoring CSI resource. Conversely, depending on the model performance evaluation method, actual measurements of all beams included in Set A (full set) may be required.

[0130] For example, if model performance evaluation is performed based on predicted Top-1 or Top-K beam accuracy, beam measurements for the entire Set A are required because the Top-1 or Top-K beam among all beams included in Set A must be determined based on actual measurement results. As such, depending on the type of metric used for performance evaluation, CSI resources for monitoring can be set to a subset or the entire set of Set A.

[0131] However, according to current consensus, RS resource configuration for model monitoring is performed by adding dedicated CSI resource configurations within a dedicated CSI report configuration, separate from the CSI configurations for inference or training. Consequently, to perform monitoring on all beams belonging to Set A, CSI resource configurations identical or similar to those already established for inference or training must be reconfigured, which causes a problem of increasing the overall CSI configuration signaling overhead. Therefore, it is necessary to define a method to minimize overhead by utilizing RS resource configuration information already established for model inference or training.

[0132] As a solution to the above, this specification proposes a model monitoring signaling method for determining the accuracy of output results for beams (Set A) inferred by an AI / ML model when performing a beam management procedure between a base station and a terminal using an AI / ML model.

[0133] Specifically, the RS resources of the beams for model monitoring are configured through a dedicated CSI report configuration, and when the dedicated CSI report configuration directs Set A as the beam for monitoring, it is configured to reuse existing inference configuration information without additional CSI resource configuration.

[0134] For example, when a terminal receives a dedicated CSI report configuration from a base station that does not include a dedicated CSI report configuration ID for model monitoring—that is, when it receives a CSI report configuration that includes only configuration information for model performance evaluation or monitoring result reporting—the terminal uses the CSI resource configuration information for Set A included in the CSI report configuration configured for model inference as an RS resource for model monitoring. In this case, the CSI report configuration for model monitoring and the CSI report configuration for model inference can be associated with each other through the inference CSI report configuration ID included within the monitoring configuration.

[0135] Alternatively, the base station may indicate that the RS resources for model monitoring are the full set of beams belonging to Set A by including, within the dedicated CSI report configuration for model monitoring, a CSI resource configuration ID identical to the CSI resource configuration ID set for Set A in the CSI report configuration for model inference.

[0136] Alternatively, the base station may indicate that the resource information for monitoring is for the full set of beams belonging to Set A corresponding to the associated ID by including an associated ID identical to the associated ID included in the CSI report configuration for model inference within the dedicated CSI report configuration for model monitoring.

[0137] FIG. 12 is a flowchart illustrating a method of operation of a terminal according to one embodiment of the present specification.

[0138] In an AI / ML-based beam management scheme, a terminal obtains configuration information for reporting model monitoring results by receiving a dedicated CSI report configuration for model monitoring from a base station. The CSI report configuration can indicate prediction information to be used for performance evaluation by including a CSI report configuration ID for inference associated with model monitoring. Additionally, reference signal (RS) resource information corresponding to the beam for performing the model performance evaluation can be configured through a dedicated CSI resource configuration for monitoring included within the CSI report configuration for model monitoring.

[0139] Meanwhile, a terminal according to one embodiment of the present specification receives a CSI report configuration from a base station (S1201), and the received CSI report configuration may not include a dedicated CSI resource configuration for model monitoring. In other words, if the terminal receives a CSI report configuration for model monitoring from a base station that does not include a CSI resource configuration, the terminal recognizes / considers that it must perform a performance evaluation by measuring beam strength / quality for all beams belonging to Set A, which means the full set of predicted results for the performance evaluation of the model. Upon receiving a message for a CSI report configuration for model monitoring that does not include a CSI resource configuration, the terminal obtains RS resource information and / or RS transmission information corresponding to Set A through a CSI report configuration for inference that is connected to the CSI report configuration for model monitoring (i.e., included within the CSI report configuration for model monitoring).

[0140] That is, if a terminal according to one embodiment of the present specification receives a CSI reporting setting for model monitoring that does not include a dedicated CSI resource setting for model monitoring, it means that the CSI resource setting information for Set A within the CSI reporting setting for inference can be utilized as resource information for monitoring as well as for inference of Set A.

[0141] When a network (e.g., a base station) configures resource information for inference, it configures RSs for Set A to be transmitted periodically, acyclically, or semi-statically, and the configuration is enabled when RSs for monitoring are directed to Set A by the network. Even if Set A configured for model inference is configured to be transmitted periodically, RS transmission for Set A may be enabled by the CSI reporting configuration for monitoring (i.e., transmitted periodically after receiving the CSI reporting configuration for monitoring). If Set A configured for model inference is configured to be transmitted acyclically, RS transmission for Set A may be defined to be enabled by the CSI reporting configuration for monitoring, or by the MAC CE or DCI after the CSI reporting configuration. If Set A configured for model inference is set to be transmitted semi-statically, RS transmission for Set A can be defined to be enabled by the CSI reporting setting for monitoring (i.e., transmitted periodically after receiving the CSI reporting setting for monitoring), or to be enabled / disabled by subsequent MAC CE.

[0142] The CSI reporting settings for inference may or may not include resource setting information for Set A. If resource setting information for Set A is included within the CSI reporting settings for inference, it may be indicated within the inference setting message as a set of RS resources for which the terminal does not perform measurements, a virtual set of RS resources, a set of resources for AI / ML model output, a set of resources for mapping beam information of AI / ML model input values, or beam / RS information for AI / ML model prediction, etc.

[0143] According to one embodiment of the present specification, a CSI reporting setting for monitoring may not explicitly include a dedicated CSI resource setting for monitoring. In this case, the transmission of RSs for Set A defined for model inference is enabled, and for the purpose of model monitoring, the terminal measures the beam strength / quality for Set A (S1202). Subsequently, a model performance evaluation is performed based on this (S1203), and the results of the model performance evaluation are reported (i.e., transmitted to the base station) (S1204).

[0144] Even if Set A consists of a virtual or non-measurement RS resource set in the settings for model inference, Set A may be implicitly designated as an RS resource for monitoring by the CSI reporting settings for monitoring. The terminal may perform measurements for the purpose of monitoring the RS corresponding to the beams belonging to the said Set A. Then, it may evaluate model performance based on the measured values ​​and report the relevant results to the base station.

[0145] If resource configuration information for Set A is not included within the CSI reporting configuration for model inference, the terminal can obtain resource information for Set A by having Set A indicated by an ID that indicates Set A used for model training, such as the associated ID of the CSI reporting configuration for model inference. Additionally, the terminal can configure model monitoring resources by utilizing the RS information for Set A within the configuration information for data collection.

[0146] As previously described, when the full set of RSs for Set A is specified as resource information for model monitoring, the base station is enabled to refer to the CSI resource configuration information for Set A for model training or inference that was previously configured prior to the model monitoring configuration, instead of additionally configuring a dedicated CSI resource configuration for monitoring. In this case, the RSs configured for Set A may be in a state where transmission is disabled while model training or model inference is not being performed, or they may be logical or virtual resource information that is not actually transmitted for model training or inference. That is, even if RSs for Set A are configured through a model training or model inference configuration message, the transmission of said RSs may be enabled only for a specific purpose. Furthermore, within the CSI reporting configuration message for model monitoring, when Set A is specified as a resource for monitoring as previously described, the transmission of RSs for Set A may be enabled by the CSI reporting configuration message for model monitoring.

[0147] FIG. 13 illustrates a procedure of a base station and a terminal according to one embodiment of the present specification.

[0148] With reference to FIG. 13, a method of operation of a terminal according to one embodiment of the present specification is described in detail below.

[0149] The terminal receives a CSI report configuration message for model inference from the base station (S1301).

[0150] A CSI report configuration message may include at least two CSI resource configuration IDs. Additionally, the CSI report configuration message may include a configuration ID for the CSI report configuration, i.e., a CSI report configuration ID.

[0151] The first CSI resource setting ID included in the CSI report setting message can indicate an RS resource, i.e., the first CSI resource setting, that can be used as an input value (Set B) for the UE-sided model. Additionally, the first CSI resource setting ID can indicate that the terminal should perform beam strength / quality measurement.

[0152] The second CSI resource setting ID included in the CSI report setting message can provide resource information for the prediction beams (Set A) by indicating the second CSI resource setting, which is resource information that can be referenced for model inference. Additionally, the second CSI resource setting ID can indicate that measurement of the RS based on the second CSI resource setting does not need to be performed. In other words, the corresponding RS may not be transmitted from the base station. However, the second CSI resource setting for transmitting the corresponding RS may be set periodically, non-periodically, or semi-statically for model monitoring.

[0153] The terminal receives an RS corresponding to the first CSI resource setting based on the CSI report setting for model inference (S1303, S1310), and measures the (beam) intensity / quality therefor (S1304, S1312).

[0154] The terminal predicts the (beam) strength / quality for the RS belonging to the second CSI resource based on the strength / quality measured for the RS corresponding to the first CSI resource setting (S1305). The terminal may report the predicted result to the base station (S1306). Here, the predicted result reported to the base station may be for the top-K beams. (K is a natural number equal to or greater than 1)

[0155] The terminal receives a CSI report setting message for model monitoring from the base station (S1307). The CSI report setting message for model monitoring may include a previously received CSI report setting ID for model inference. The CSI report setting message may include CSI resource setting information for model monitoring. This may mean that a subset of Set A is set as the RS resource for model monitoring. Alternatively, the CSI report setting message may not include CSI resource setting information for model monitoring. This may mean that the full set of Set A is set as the RS resource for model monitoring. In this case, the terminal sets Set A as the monitoring RSs (S1308). That is, if the CSI report setting message does not include CSI resource setting information for model monitoring, the terminal recognizes / considers that it follows the second CSI resource setting indicated by the CSI report setting message for model inference as the RS resource for model monitoring. Afterwards, the terminal receives RSs based on the second CSI resource setting (S1311) and measures the (beam) strength / quality of the received RSs (S1312).

[0156] The terminal performs model performance evaluation, i.e., model monitoring, based on the measurement results and the results predicted by model inference for the RS according to the second CSI resource setting received through the CSI report setting message for model inference (S1313).

[0157] Afterwards, the terminal transmits the result of the model performance evaluation, i.e., the model performance report, performed according to the report setting of the CSI report setting message for model monitoring to the base station (S1314).

[0158] With reference to FIG. 13, a method of operation of a base station according to one embodiment of the present specification is described in detail below.

[0159] The base station sends a CSI report configuration message for model inference to the terminal (S1301).

[0160] A CSI report configuration message may include at least two CSI resource configuration IDs. Additionally, the CSI report configuration message may include a configuration ID for the CSI report configuration, i.e., a CSI report configuration ID.

[0161] The first CSI resource setting ID included in the CSI report setting message can indicate an RS resource, i.e., the first CSI resource setting, that can be used as an input value (Set B) for the UE-sided model. Additionally, the first CSI resource setting ID can indicate that the terminal should perform beam strength / quality measurement.

[0162] The second CSI resource setting ID included in the CSI report setting message can provide resource information for the prediction beams (Set A) by indicating the second CSI resource setting, which is resource information that can be referenced for model inference. Additionally, the second CSI resource setting ID can indicate that measurement of the RS based on the second CSI resource setting does not need to be performed. In other words, the corresponding RS may not be transmitted from the base station. However, the second CSI resource setting for transmitting the corresponding RS may be set periodically, non-periodically, or semi-statically for model monitoring.

[0163] The base station activates an RS corresponding to a first CSI resource setting based on a CSI report setting for model inference (S1302) and transmits the activated RS (S1303, S1310). The terminal measures the (beam) strength / quality for this and can predict the (beam) strength / quality for an RS belonging to a second CSI resource based on the measured strength / quality. The base station can receive a report of the predicted result from the terminal (S1306). Here, the predicted result reported by the terminal may be for the Top-K beams. (K is a natural number equal to or greater than 1)

[0164] The base station transmits a CSI report setting message for model monitoring to the terminal (S1307). The CSI report setting message for model monitoring may include a previously received CSI report setting ID for model inference. The CSI report setting message may include CSI resource setting information for model monitoring. This may mean that a subset of Set A is set as the RS resource for model monitoring. Alternatively, the CSI report setting message may not include CSI resource setting information for model monitoring. This may mean that the full set of Set A is set as the RS resource for model monitoring. In this case, the base station activates the transmission of RSs based on the second CSI resource setting of the CSI report setting message transmitted for model inference (S1309), and transmits the activated RSs (S1311).

[0165] Subsequently, the base station receives the result of the model performance evaluation, i.e., the model performance report, from the terminal according to the report setting of the CSI report setting message for model monitoring (S1314).

[0166] FIG. 14 is a flowchart illustrating a method of operation of a terminal according to another embodiment of the present specification.

[0167] Referring to FIG. 14, the terminal receives a first CSI (channel state information) report configuration message for model inference (S1401). Here, the first CSI report configuration message includes first reference signal resource configuration information and second reference signal resource configuration information. Then, the terminal performs a first measurement on the first reference signal corresponding to the first reference signal resource configuration information (S1402), and obtains a prediction result for the second reference signal corresponding to the second reference signal resource configuration information based on the first measurement (S1403). Additionally, the terminal receives a second CSI report configuration message for model monitoring (S1404), and after receiving the second CSI report configuration message, performs a second measurement on the second reference signal (S1405). Subsequently, the terminal calculates the accuracy of the prediction result based on the result of the second measurement and the prediction result (S1406).

[0168] The accuracy calculated above can be used to evaluate model performance.

[0169] The terminal can transmit a result report based on the accuracy calculated above to the base station.

[0170] The first measurement and the second measurement above may be based on at least one of RSRP (Reference Signal Received Power) and RSRQ (Reference Signal Received Quality).

[0171] Meanwhile, the first reference signal resource setting information corresponds to the first CSI resource setting ID (identity), and the second reference signal resource setting information may correspond to the second CSI resource setting ID. The first CSI report setting message may further include the first CSI resource setting ID and the second CSI resource setting ID. Here, the second CSI report setting message may include the second CSI resource setting ID.

[0172] The disclosures of this specification described above may be implemented through various means. For example, the disclosures of this specification may be implemented by hardware, firmware, software, or a combination thereof. Specifically, they will be described below with reference to the drawings.

[0173] FIG. 15 shows an apparatus according to one embodiment of the present specification.

[0174] Referring to FIG. 15, the wireless communication system may include a first device (100a) and a second device (100b).

[0175] The first device (100a) may be a base station, network node, transmission terminal, receiving terminal, wireless device, wireless communication device, vehicle, vehicle equipped with autonomous driving function, connected car, drone (Unmanned Aerial Vehicle, UAV), AI (Artificial Intelligence) module, robot, AR (Augmented Reality) device, VR (Virtual Reality) device, MR (Mixed Reality) device, hologram device, public safety device, MTC device, IoT device, medical device, fintech device (or financial device), security device, climate / environment device, device related to 5G service, or other device related to the field of the Fourth Industrial Revolution.

[0176] The second device (100b) may be a base station, network node, transmission terminal, receiving terminal, wireless device, wireless communication device, vehicle, vehicle equipped with autonomous driving function, connected car, drone (Unmanned Aerial Vehicle, UAV), AI (Artificial Intelligence) module, robot, AR (Augmented Reality) device, VR (Virtual Reality) device, MR (Mixed Reality) device, hologram device, public safety device, MTC device, IoT device, medical device, fintech device (or financial device), security device, climate / environment device, device related to 5G service, or other device related to the field of the Fourth Industrial Revolution.

[0177] The first device (100a) may include at least one processor, such as a processor (1020a), at least one memory, such as a memory (1010a), and at least one transceiver, such as a transceiver (1031a). The processor (1020a) may perform the aforementioned functions, procedures, and / or methods. The processor (1020a) may perform one or more protocols. For example, the processor (1020a) may perform one or more layers of a wireless interface protocol. The memory (1010a) is connected to the processor (1020a) and may store various forms of information and / or commands. The transceiver (1031a) is connected to the processor (1020a) and may be controlled to transmit and receive wireless signals.

[0178] The second device (100b) may include at least one processor, such as a processor (1020b), at least one memory device, such as a memory (1010b), and at least one transceiver, such as a transceiver (1031b). The processor (1020b) may perform the aforementioned functions, procedures, and / or methods. The processor (1020b) may implement one or more protocols. For example, the processor (1020b) may implement one or more layers of a wireless interface protocol. The memory (1010b) is connected to the processor (1020b) and may store various forms of information and / or commands. The transceiver (1031b) is connected to the processor (1020b) and may be controlled to transmit and receive wireless signals.

[0179] The memory (1010a) and / or the memory (1010b) may be connected to the processor (1020a) and / or the processor (1020b) respectively, either internally or externally, and may also be connected to other processors through various technologies such as wired or wireless connections.

[0180] The first device (100a) and / or the second device (100b) may have one or more antennas. For example, the antenna (1036a) and / or antenna (1036b) may be configured to transmit and receive wireless signals.

[0181] FIG. 16 is a block diagram showing the configuration of a terminal according to one embodiment of the present specification.

[0182] In particular, FIG. 16 is a drawing illustrating the device of FIG. 15 in more detail.

[0183] The device includes a memory (1010), a processor (1020), a transceiver (1031), a power management module (1091), a battery (1092), a display (1041), an input unit (1053), a speaker (1042) and a microphone (1052), a SIM (subscriber identification module) card, and one or more antennas.

[0184] The processor (1020) may be configured to implement the proposed functions, procedures, and / or methods described herein. Layers of a radio interface protocol may be implemented in the processor (1020). The processor (1020) may include an application-specific integrated circuit (ASIC), other chipsets, logic circuits, and / or data processing devices. The processor (1020) may be an application processor (AP). The processor (1020) may include at least one of a digital signal processor (DSP), a central processing unit (CPU), a graphics processing unit (GPU), and a modem (modulator and demodulator). Examples of processors (1020) may be SNAPDRAGON™ series processors manufactured by Qualcomm®, EXYNOSTM series processors manufactured by Samsung®, A series processors manufactured by Apple®, HELIO™ series processors manufactured by MediaTek®, ATOM™ series processors manufactured by INTEL®, KIRINTM series processors manufactured by HiSilicon®, or corresponding next-generation processors.

[0185] The power management module (1091) manages power for the processor (1020) and / or the transceiver (1031). The battery (1092) supplies power to the power management module (1091). The display (1041) outputs the results processed by the processor (1020). The input unit (1053) receives input to be used by the processor (1020). The input unit (1053) may be displayed on the display (1041). A SIM card is an integrated circuit used to securely store the International Mobile Subscriber Identity (IMSI) and associated keys used to identify and authenticate a subscriber in mobile devices such as mobile phones and computers. Contact information may also be stored on many SIM cards.

[0186] Memory (1010) is operably coupled with the processor (1020) and stores various information for operating the processor (610). Memory (1010) may include ROM (read-only memory), RAM (random access memory), flash memory, memory card, storage medium and / or other storage device. Where the embodiment is implemented in software, the techniques described herein may be implemented as modules (e.g., procedures, functions, etc.) that perform the functions described herein. Modules may be stored in memory (1010) and executed by the processor (1020). Memory (1010) may be implemented inside the processor (1020). Alternatively, memory (1010) may be implemented outside the processor (1020) and may be communically connected to the processor (1020) through various means known in the art.

[0187] The transceiver (1031) is operably coupled with the processor (1020) and transmits and / or receives a wireless signal. The transceiver (1031) includes a transmitter and a receiver. The transceiver (1031) may include a baseband circuit for processing a wireless frequency signal. The transceiver controls one or more antennas to transmit and / or receive a wireless signal. The processor (1020) transmits command information to the transceiver (1031) to transmit a wireless signal, for example, constituting voice communication data, in order to initiate communication. The antennas function to transmit and receive wireless signals. When receiving a wireless signal, the transceiver (1031) may transmit the signal to the processor (1020) for processing and convert the signal to baseband. The processed signal may be converted into audible or readable information output through a speaker (1042).

[0188] The speaker (1042) outputs sound-related results processed by the processor (1020). The microphone (1052) receives sound-related input to be used by the processor (1020).

[0189] The user inputs command information, such as a phone number, by, for example, pressing (or touching) a button on the input unit (1053) or by voice activation using the microphone (1052). The processor (1020) receives this command information and processes it to perform appropriate functions, such as making a call to the phone number. Operational data can be extracted from a SIM card or memory (1010). Additionally, the processor (1020) can display the command information or operation information on the display (1041) for the user's awareness and convenience.

[0190] FIG. 17 shows a block diagram of a processor in which the disclosure of the present specification is implemented.

[0191] As can be seen with reference to FIG. 17, a processor (1020) in which the disclosure of this specification is implemented may include a plurality of circuits to implement the proposed functions, procedures and / or methods described in this specification. For example, the processor (1020) may include a first circuit (1020-1), a second circuit (1020-2), and a third circuit (1020-3). Additionally, although not illustrated, the processor (1020) may include more circuits. Each circuit may include a plurality of transistors.

[0192] The above processor (1020) may be called an ASIC (application-specific integrated circuit) or an AP (application processor), and may include at least one of a DSP (digital signal processor), a CPU (central processing unit), and a GPU (graphics processing unit).

[0193] FIG. 18 is a block diagram showing in detail the transceiver of the first device shown in FIG. 15 or the transceiver of the device shown in FIG. 19.

[0194] Referring to FIG. 18, the transceiver unit (1031) includes a transmitter (1031-1) and a receiver (1031-2). The transmitter (1031-1) includes a Discrete Fourier Transform (DFT) unit (1031-11), a subcarrier mapper (1031-12), an IFFT unit (1031-13), a CP insertion unit (1031-14), and a wireless transmitter (1031-15). The transmitter (1031-1) may further include a modulator. Additionally, it may further include, for example, a scramble unit (not shown), a modulation mapper (not shown), a layer mapper (not shown), and a layer permutator (not shown), which may be positioned prior to the DFT unit (1031-11). That is, to prevent an increase in the PAPR (peak-to-average power ratio), the transmitter (1031-1) first passes the information through the DFT (1031-11) before mapping the signal to the subcarrier. After the signal spread (or precoded in the same sense) by the DFT section (1031-11) is mapped to the subcarrier through the subcarrier mapper (1031-12), it is then passed through the IFFT (Inverse Fast Fourier Transform) section (1031-13) to form a signal on the time axis.

[0195] The DFT unit (1031-11) performs a DFT on the input symbols to output complex-valued symbols. For example, if Ntx symbols are input (where Ntx is a natural number), the DFT size is Ntx. The DFT unit (1031-11) may be called a transform precoder. The subcarrier mapper (1031-12) maps the complex-valued symbols to each subcarrier in the frequency domain. The complex-valued symbols may be mapped to resource elements corresponding to resource blocks allocated for data transmission. The subcarrier mapper (1031-12) may be called a resource element mapper. The IFFT unit (1031-13) performs an IFFT on the input symbols to output a baseband signal for the data, which is a time-domain signal. The CP insertion section (1031-14) copies a portion of the latter part of the base band signal for data and inserts it into the front part of the base band signal for data. Through CP insertion, Inter-Symbol Interference (ISI) and Inter-Carrier Interference (ICI) are prevented, so that orthogonality can be maintained even in a multipath channel.

[0196] On the other hand, the receiver (1031-2) includes a wireless receiver (1031-21), a CP removal unit (1031-22), an FFT unit (1031-23), and an equalization unit (1031-24), etc. The wireless receiver (1031-21), CP removal unit (1031-22), and FFT unit (1031-23) of the receiver (1031-2) perform the inverse functions of the wireless transmitter (1031-15), CP insertion unit (1031-14), and IFF unit (1031-13) of the transmitter (1031-1). The receiver (1031-2) may further include a demodulator.

[0197] Although preferred embodiments have been described by way of example above, the disclosure of this specification is not limited to such specific embodiments, and may be modified, changed, or improved in various forms within the scope of the spirit and claims of this specification.

[0198] In the exemplary system described above, methods are described based on a flowchart as a series of steps or blocks, but are not limited to the order of the described steps, and some steps may occur in a different order or simultaneously with other steps as described above. Furthermore, a person skilled in the art will understand that the steps shown in the flowchart are not exclusive, and that other steps may be included, or that one or more steps of the flowchart may be omitted without affecting the scope of rights.

[0199] The claims described in this specification may be combined in various ways. For example, the technical features of the method claims in this specification may be combined to be implemented as a device, and the technical features of the device claims in this specification may be combined to be implemented as a method. Furthermore, the technical features of the method claims and the technical features of the device claims in this specification may be combined to be implemented as a device, and the technical features of the method claims and the technical features of the device claims in this specification may be combined to be implemented as a method.

Claims

1. In a method of operation of a terminal in a wireless communication system, A step of receiving a first CSI (channel state information) report configuration message for model inference, wherein the first CSI report configuration message includes first reference signal resource configuration information and second reference signal resource configuration information; A step of performing a first measurement for a first reference signal corresponding to the first reference signal resource setting information; A step of obtaining a prediction result for a second reference signal corresponding to the second reference signal resource setting information based on the first measurement; Step of receiving a second CSI report setting message for model monitoring; After receiving the second CSI report setting message, a step of performing a second measurement on the second reference signal; and A method comprising the step of calculating the accuracy of the prediction result based on the result of the second measurement and the prediction result.

2. In Paragraph 1, The accuracy calculated above is a method used for evaluating model performance.

3. In Paragraph 1, A method further comprising the step of transmitting a result report based on the accuracy calculated above.

4. In Paragraph 1, A method in which the first measurement and the second measurement are based on at least one of RSRP (Reference Signal Received Power) and RSRQ (Reference Signal Received Quality).

5. In Paragraph 1, A method in which the first reference signal resource setting information corresponds to the first CSI resource setting ID (identity), and the second reference signal resource setting information corresponds to the second CSI resource setting ID.

6. In Paragraph 5, A method in which the first CSI report setting message further includes the first CSI resource setting ID and the second CSI resource setting ID.

7. In Paragraph 6, The above second CSI report setting message includes the above second CSI resource setting ID, a method.

8. As a terminal in a wireless communication system, At least one processor; and The operation performed based on the instruction being executed by the at least one processor includes at least one memory that stores instructions and is operablely electrically connected to the at least one processor: A step of receiving a first CSI (channel state information) report configuration message for model inference, wherein the first CSI report configuration message includes first reference signal resource configuration information and second reference signal resource configuration information; A step of performing a first measurement for a first reference signal corresponding to the first reference signal resource setting above, and A step of obtaining a prediction result for a second reference signal corresponding to the second reference signal resource setting information based on the first measurement, and A step of receiving a second CSI report setting message for model monitoring, and After receiving the second CSI report setting message, the step of performing a second measurement on the second reference signal, and A terminal comprising the step of calculating the accuracy of the prediction result based on the result of the second measurement and the prediction result.

9. In Paragraph 8, The accuracy calculated above is associated with model performance evaluation, terminal.

10. In Paragraph 8, Based on the execution of the above instruction by the at least one processor, the operation performed is: A terminal further comprising the step of transmitting a result report based on the accuracy calculated above.

11. In Paragraph 8, A terminal in which the first measurement and the second measurement are based on at least one of RSRP (Reference Signal Received Power) and RSRQ (Reference Signal Received Quality).

12. In Paragraph 8, A terminal in which the first reference signal resource setting information corresponds to the first CSI resource setting ID (identity) and the second reference signal resource setting information corresponds to the second CSI resource setting ID.

13. In Paragraph 12, The terminal, wherein the first CSI report setting message further includes the first CSI resource setting ID and the second CSI resource setting ID.

14. In Paragraph 13, The above second CSI report setting message is a terminal including the above second CSI resource setting ID.

Images