Method performed by terminal or network in wireless communication system, and apparatus therefor

Abstract

A method performed by a terminal, according to at least one from among embodiments disclosed in the present specification, may comprise: receiving, from a network, first artificial intelligence / machine learning (AI / ML) model information including information about the results of training a first AI / ML model for channel state information (CSI) reconstruction in the network; training a second AI / ML model for CSI reconstruction in the terminal on the basis of the first AI / ML model information; acquiring a channel quality indicator (CQI) on the basis of first CSI reconstructed from the trained second AI / ML model; and transmitting a CSI report including the CQI to the network.

Description

Method performed by a terminal or network in a wireless communication system and device therefor

[0001] The present disclosure relates to a wireless communication system, and more particularly, to a method and device for transmitting or receiving an uplink / downlink wireless signal by a terminal or a network in a wireless communication system.

[0002] Wireless communication systems are widely deployed to provide various types of communication services, such as voice and data. Typically, wireless communication systems are multiple access systems that support communication with multiple users by sharing available system resources (e.g., bandwidth, transmission power). Examples of multiple access systems include code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), orthogonal frequency division multiple access (OFDMA), and single-carrier frequency division multiple access (SC-FDMA).

[0003] Recently, research is being conducted on CSI feedback based on AI / ML (artificial intelligence / machine learning) in NR standardization, and CSI compression to reduce CSI overhead through AI / ML models is being considered as one of the main research topics.

[0004] CSI compression uses two-sided AI / ML models on the UE side and the NW side, requiring either joint or separate training for their training. Joint training offers superior performance, but suffers from excessive time and signaling overhead. Separate training offers flexibility and extendibility, but because training is performed separately based on a dataset, it suffers from lower performance compared to joint training.

[0005] The technical task of this disclosure is to provide a method and device for efficiently performing wireless signal transmission and reception processes. As an example, a method is provided for a terminal to generate / report CQI in a CSI reporting method based on a two-side AI / ML model.

[0006] In addition to the technical challenges described above, other technical challenges can be inferred from the description below.

[0007] According to one aspect of the present disclosure, a method performed by a terminal may include receiving, from a network, first AI / ML (artificial intelligence / machine learning) model information including information on a result of training a first AI / ML model for channel state information (CSI) reconstruction in the network; training a second AI / ML model for CSI reconstruction in the terminal based on the first AI / ML model information; obtaining a channel quality indicator (CQI) based on the first CSI reconstructed from the trained second AI / ML model; and transmitting a CSI report including the CQI to the network.

[0008] The second AI / ML model can restore the first CSI based on compressed channel information.

[0009] The terminal can obtain the compressed channel information based on the third AI / ML model set in the terminal.

[0010] The above CSI report may include the compressed channel information.

[0011] The second AI / ML model may have lower complexity than the first AI / ML model.

[0012] Information about the result of training the first AI / ML model may include feature activation information or output response information of the first AI / ML model.

[0013] The CSI report may include at least one of information indicating that the CQI was obtained from the second AI / ML model or information regarding the accuracy of the CQI.

[0014] The terminal may report to the network that it has the terminal capability to train the second AI / ML model based on the first AI / ML model information.

[0015] The above first AI / ML model may be a Teacher Model in the Knowledge Distillation technique, and the above second AI / ML model may be a Student Model that compresses the Teacher Model.

[0016] According to another aspect of the present disclosure, a non-transitory computer-readable recording medium having recorded thereon a program for performing the method described above may be provided.

[0017] According to another aspect of the present disclosure, a device comprises a memory configured to store instructions; and a processor configured to perform operations by executing the instructions, wherein the operations of the processor may include receiving, from the network, first AI / ML (artificial intelligence / machine learning) model information including information on a result of training a first AI / ML model for channel state information (CSI) reconstruction in the network; training a second AI / ML model for CSI reconstruction in the terminal based on the first AI / ML model information; obtaining a channel quality indicator (CQI) based on the first CSI reconstructed from the trained second AI / ML model; and transmitting a CSI report including the CQI to the network.

[0018] The above device may further include a transceiver.

[0019] The above device may be a terminal in a wireless communication system.

[0020] The above device may be a processing device configured to control a terminal in a wireless communication system.

[0021] According to another aspect of the present disclosure, a method performed by a base station includes training a first AI / ML (artificial intelligence / machine learning) model for CSI (channel state information) reconstruction; transmitting first AI / ML model information including information on a result of training the first AI / ML model to a terminal; and receiving a CSI report including a CQI (channel quality indicator) output from a second AI / ML model of the terminal from the terminal, wherein the second AI / ML model is an AI / ML model for CSI reconstruction in the terminal, and the base station can transmit the first AI / ML model information to the terminal for training the second AI / ML model.

[0022] According to another aspect of the present disclosure, a base station comprises: a memory configured to store instructions; and a processor configured to perform operations by executing the instructions, wherein the operations of the processor include training a first AI / ML (artificial intelligence / machine learning) model for CSI (channel state information) reconstruction; transmitting first AI / ML model information including information on a result of training the first AI / ML model to a terminal; and receiving a CSI report including a CQI (channel quality indicator) output from a second AI / ML model of the terminal, wherein the second AI / ML model is an AI / ML model for CSI reconstruction in the terminal, and the base station can transmit the first AI / ML model information to the terminal for training the second AI / ML model.

[0023] According to the present disclosure, wireless signal transmission and reception can be efficiently performed in a wireless communication system. For example, since an AI / ML model for CSI restoration is also configured in the terminal, the ambiguity issue regarding CQI generation / reporting in AI / ML model-based CSI reporting can be resolved. In addition, since compressed information (knowledge) about the AI / ML model for CSI restoration on the network side is transmitted when configuring the AI / ML model for CSI restoration in the terminal, low signaling overhead can be expected.

[0024] In addition to the technical effects described above, other technical effects can be inferred from the description below.

[0025] Figure 1 illustrates physical channels used in a 3GPP system, which is an example of a wireless communication system, and a general signal transmission method using the channels.

[0026] Figure 2 illustrates the structure of a radio frame.

[0027] Figure 3 illustrates a resource grid of slots.

[0028] Figure 4 illustrates an example of physical channels being mapped within a slot.

[0029] Figure 5 illustrates the PDSCH and ACK / NACK transmission process.

[0030] Figure 6 illustrates a PUSCH transmission process.

[0031] Figure 7 shows an example of a CSI-related procedure.

[0032] Figure 8 is a diagram to explain the concept of AI / ML / Deep learning.

[0033] Figures 9 to 12 illustrate various AI / ML models of deep learning.

[0034] Figure 13 is a diagram illustrating segmentation AI inference.

[0035] Figure 14 is a diagram illustrating a framework for 3GPP RAN Intelligence.

[0036] Figures 15 to 17 illustrate AI Model Training and Inference environments.

[0037] Figure 18 is a diagram to explain the concept of AI / ML-based CSI compression.

[0038] Figure 19 is a diagram to explain the concept of the knowledge distillation technique of the AI / ML model.

[0039] Figure 20 is a diagram to explain the concept of feature-based knowledge in the knowledge distillation technique.

[0040] Figure 21 is a diagram for explaining the operation of a terminal and a network according to one implementation.

[0041] Figure 22 illustrates a flow of a method performed by a terminal in a wireless communication system according to one embodiment.

[0042] Figure 23 illustrates a flowchart of a method performed by a network node in a wireless communication system according to one embodiment.

[0043] Figures 24 to 27 illustrate a communication system (1) and a wireless device applicable to the present disclosure.

[0044] The following technologies can be used in various wireless access systems, such as CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), and SC-FDMA (single carrier frequency division multiple access). CDMA can be implemented with radio technologies such as UTRA (Universal Terrestrial Radio Access) or CDMA2000. TDMA can be implemented with radio technologies such as GSM (Global System for Mobile communications) / GPRS (General Packet Radio Service) / EDGE (Enhanced Data Rates for GSM Evolution). OFDMA can be implemented with radio technologies such as IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802-20, and E-UTRA (Evolved UTRA). UTRA is a part of UMTS (Universal Mobile Telecommunications System). 3GPP (3rd Generation Partnership Project) LTE (long term evolution) is part of E-UMTS (Evolved UMTS) that uses E-UTRA, and LTE-A (Advanced) is an evolved version of 3GPP LTE. 3GPP NR (New Radio or New Radio Access Technology) is an evolved version of 3GPP LTE / LTE-A.

[0045] As more and more communication devices demand greater communication capacity, the need for improved mobile broadband communications compared to existing RAT (Radio Access Technology) is emerging. Furthermore, massive MTC (Machine Type Communications), which connects multiple devices and objects to provide diverse services anytime, anywhere, is also a key issue to be considered in next-generation communications. Furthermore, communication system design that considers reliability and latency-sensitive services / terminals is being discussed. Accordingly, the introduction of next-generation RATs that consider enhanced Mobile BroadBand Communication (eMBB), massive MTC, and Ultra-Reliable and Low Latency Communication (URLLC) is being discussed. For convenience, this technology is referred to as NR (New Radio or New RAT) in the present invention.

[0046] For clarity of explanation, the description will focus on 3GPP NR, but the technical idea of ​​the present invention is not limited thereto.

[0047] In this specification, the expression "setting" can be replaced with the expression "configure / configuration", and the two can be used interchangeably. In addition, conditional expressions (e.g., "if", "in a case", or "when", etc.) can be replaced with the expression "based on that ~~" or "in a state / status". In addition, the operation of the terminal / base station or the SW / HW configuration according to the satisfaction of the condition can be inferred / understood. In addition, if the process of the receiving (or transmitting) side can be inferred / understood from the process of the transmitting (or receiving) side in signal transmission / reception between wireless communication devices (e.g., base stations, terminals), the description thereof can be omitted. For example, signal determination / generation / encoding / transmission, etc. of the transmitting side can be understood as signal monitoring reception / decoding / determination, etc. of the receiving side. In addition, the expression that the terminal performs (or does not perform) a specific operation can also be interpreted as meaning that the base station operates while expecting / assuming (or expecting / assuming that the terminal does not perform) the specific operation. In addition, the expression that the base station performs (or does not perform) a specific operation can also be interpreted as meaning that the terminal operates while expecting / assuming (or expecting / assuming that the base station does not perform) the specific operation. In addition, the division and index of each section, embodiment, example, option, method, plan, etc. in the following description are for the convenience of explanation and should not be interpreted as meaning that each constitutes an independent invention or that each must be implemented only individually. In addition, in describing each section, embodiment, example, option, method, plan, etc., if there is no explicitly conflicting / opposing description, it can be inferred / interpreted that at least some of them can be combined and implemented together, or at least some can be implemented with the omission of each.

[0048] In a wireless communication system, a terminal receives information from a base station via the downlink (DL) and transmits it to the base station via the uplink (UL). The information transmitted and received between the base station and the terminal includes data and various control information, and various physical channels exist depending on the type and purpose of the information being transmitted and received.

[0049] Figure 1 is a drawing for explaining physical channels used in a 3GPP NR system and a general signal transmission method using them.

[0050] When a terminal is powered on again from a powered-off state or enters a new cell, it performs an initial cell search operation, such as synchronizing with the base station, in step S101. To this end, the terminal receives a Synchronization Signal Block (SSB) from the base station. The SSB includes a Primary Synchronization Signal (PSS), a Secondary Synchronization Signal (SSS), and a Physical Broadcast Channel (PBCH). Based on the PSS / SSS, the terminal synchronizes with the base station and obtains information such as a cell ID (cell identity). In addition, the terminal can obtain broadcast information within the cell based on the PBCH. Meanwhile, the terminal can check the downlink channel status by receiving a Downlink Reference Signal (DL RS) during the initial cell search phase.

[0051] After completing the initial cell search, the terminal can obtain more specific system information by receiving a physical downlink control channel (PDCCH) and a physical downlink shared channel (PDSCH) based on the physical downlink control channel information in step S102.

[0052] Thereafter, the terminal may perform a random access procedure such as steps S103 to S106 to complete connection to the base station. To this end, the terminal may transmit a preamble through a physical random access channel (PRACH) (S103) and receive a response message to the preamble through a physical downlink control channel and a corresponding physical downlink shared channel (S104). In the case of contention-based random access, a contention resolution procedure such as transmission of an additional physical random access channel (S105) and reception of a physical downlink control channel and a corresponding physical downlink shared channel (S106) may be performed.

[0053] The terminal that has performed the procedure as described above can then perform the general uplink / downlink signal transmission procedure, such as receiving a physical downlink control channel / physical downlink shared channel (S107) and transmitting a physical uplink shared channel (PUSCH) / physical uplink control channel (PUCCH) (S108). The control information that the terminal transmits to the base station is collectively referred to as uplink control information (UCI). UCI includes HARQ ACK / NACK (Hybrid Automatic Repeat and request Acknowledgement / Negative-ACK), SR (Scheduling Request), CSI (Channel State Information), etc. CSI includes CQI (Channel Quality Indicator), PMI (Precoding Matrix Indicator), RI (Rank Indication), etc. UCI is generally transmitted through PUCCH, but can be transmitted through PUSCH when control information and traffic data must be transmitted simultaneously. Additionally, UCI can be transmitted aperiodically via PUSCH upon request / instruction from the network.

[0054] Figure 2 illustrates the structure of a radio frame. In NR, uplink and downlink transmissions are organized into frames. Each radio frame is 10 ms long and is divided into two 5 ms half-frames (HF). Each half-frame is divided into five 1 ms sub-frames (SF). A sub-frame is divided into one or more slots, and the number of slots within a sub-frame depends on the subcarrier spacing (SCS). Each slot contains 12 or 14 OFDM (Orthogonal Frequency Division Multiplexing) symbols, depending on the cyclic prefix (CP). When a normal CP is used, each slot contains 14 OFDM symbols. When an extended CP is used, each slot contains 12 OFDM symbols.

[0055] Table 1 illustrates that when CP is normally used, the number of symbols per slot, the number of slots per frame, and the number of slots per subframe vary depending on the SCS.

[0056] SCS (15*2^u)N slot symb N frame,u slot N subframe,u slot 15KHz (u=0)1410130KHz (u=1)1420260KHz (u=2)14404120KHz (u=3)14808240KHz (u=4)1416016

[0057] * N slot symb : Number of symbols in the slot

[0058] * N frame,u slot : Number of slots in the frame

[0059] * N subframe,u slot : Number of slots in a subframe

[0060] Table 2 illustrates that when extended CP is used, the number of symbols per slot, the number of slots per frame, and the number of slots per subframe vary depending on the SCS.

[0061] SCS (15*2^u)N slot symb N frame,u slot N subframe,u slot 60KHz (u=2)12404

[0062] The structure of the frame is only an example, and the number of subframes, number of slots, and number of symbols in the frame can be varied.

[0063] In an NR system, OFDM numerology (e.g., SCS) may be set differently between multiple cells that are merged into a single terminal. Accordingly, the (absolute time) interval of a time resource (e.g., SF, slot, or TTI) (conveniently referred to as TU (Time Unit)) consisting of the same number of symbols may be set differently between the merged cells. Here, the symbol may include an OFDM symbol (or CP-OFDM symbol), an SC-FDMA symbol (or Discrete Fourier Transform-spread-OFDM, DFT-s-OFDM symbol).

[0064] Figure 3 illustrates a resource grid of a slot. A slot contains multiple symbols in the time domain. For example, in the case of a regular CP, one slot contains 14 symbols, but 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 RBs (PRBs) in the frequency domain and can correspond to a single numerology (e.g., SCS, CP length, etc.). A carrier can contain up to N (e.g., 5) BWPs. Data communication is performed through activated BWPs, and only one BWP can be activated for a single terminal. Each element in the resource grid is referred to as a Resource Element (RE), to which one complex symbol can be mapped.

[0065] Figure 4 illustrates an example of how physical channels are mapped within a slot. A PDCCH can be transmitted in the DL control region, and a PDSCH can be transmitted in the DL data region. A PUCCH can be transmitted in the UL control region, and a PUSCH can be transmitted in the UL data region. GP provides a time gap between the base station and the terminal when switching from transmission mode to reception mode or from reception mode to transmission mode. Some symbols within a subframe at the time of transition from DL to UL can be set as GP.

[0066] Below, each physical channel is described in more detail.

[0067] The PDCCH carries Downlink Control Information (DCI). For example, the PCCCH (i.e., DCI) carries the transmission format and resource allocation of the downlink shared channel (DL-SCH), resource allocation information for the uplink shared channel (UL-SCH), paging information for the paging channel (PCH), system information on the DL-SCH, resource allocation information for upper layer control messages such as random access responses transmitted on the PDSCH, transmission power control commands, activation / deactivation of Configured Scheduling (CS), etc. The DCI includes a cyclic redundancy check (CRC), which is masked / scrambled with various identifiers (e.g., Radio Network Temporary Identifier, RNTI) depending on the owner or usage of the PDCCH. For example, if the PDCCH is for a specific terminal, the CRC is masked with a terminal identifier (e.g., Cell-RNTI, C-RNTI). If the PDCCH is for paging, the CRC is masked with the Paging-RNTI (P-RNTI). If the PDCCH is for system information (e.g., a System Information Block, SIB), the CRC is masked with the System Information RNTI (SI-RNTI). If the PDCCH is for a random access response, the CRC is masked with the Random Access-RNTI (RA-RNTI).

[0068] The PDCCH consists of 1, 2, 4, 8, or 16 Control Channel Elements (CCEs) depending on the Aggregation Level (AL). A CCE is a logical allocation unit used to provide a PDCCH with a predetermined code rate depending on the radio channel status. A CCE consists of six Resource Element Groups (REGs). A REG is defined as one OFDM symbol and one (P)RB. The PDCCH is transmitted through a Control Resource Set (CORESET). A CORESET is defined as a set of REGs with a given numerology (e.g., SCS, CP length, etc.). Multiple CORESETs for a single UE can overlap in the time / frequency domain. A CORESET can be configured through system information (e.g., Master Information Block, MIB) or UE-specific upper layer (e.g., Radio Resource Control, RRC, layer) signaling. Specifically, the number of RBs and the number of OFDM symbols (up to 3) that constitute the CORESET can be set by upper layer signaling.

[0069] To receive / detect PDCCH, the UE monitors PDCCH candidates. PDCCH candidates represent the CCE(s) that the UE should monitor for PDCCH detection. Each PDCCH candidate is defined as 1, 2, 4, 8, or 16 CCEs depending on the AL. Monitoring involves (blind) decoding the PDCCH candidates. The set of PDCCH candidates that the UE monitors is defined as a PDCCH Search Space (SS). The search space includes a Common Search Space (CSS) or a UE-specific search space (USS). The UE can acquire DCI by monitoring PDCCH candidates in one or more search spaces configured by the MIB or higher-layer signaling. Each CORESET is associated with one or more search spaces, and each search space is associated with one COREST. The search space can be defined based on the following parameters.

[0070] - controlResourceSetId: Indicates the CORESET associated with the search space.

[0071] - monitoringSlotPeriodicityAndOffset: Indicates the PDCCH monitoring period (in slots) and the PDCCH monitoring interval offset (in slots).

[0072] - monitoringSymbolsWithinSlot: Indicates the PDCCH monitoring symbols within the slot (e.g., the first symbol(s) of the CORESET).

[0073] - nrofCandidates: AL={1, 2, 4, 8, 16} indicates the number of PDCCH candidates (one of 0, 1, 2, 3, 4, 5, 6, 8)

[0074] * An opportunity (e.g., time / frequency resource) for monitoring PDCCH candidates is defined as a PDCCH (monitoring) opportunity. One or more PDCCH (monitoring) opportunities can be configured within a slot.

[0075] Table 3 illustrates the characteristics of each search space type.

[0076] TypeSearch SpaceRNTIUse CaseType0-PDCCHCommonSI-RNTI on a primary cellSIB DecodingType0A-PDCCHCommonSI-RNTI on a primary cellSIB DecodingType1-PDCCHCommonRA-RNTI or TC-RNTI on a primary cellMsg2, Msg4 decoding in RACHType2-PDCCHCommonP-RNTI on a primary cellPaging DecodingType3-PDCCHCommonINT-RNTI, SFI-RNTI, TPC-PUSCH-RNTI, TPC-PUCCH-RNTI, TPC-SRS-RNTI, C-RNTI, MCS-C-RNTI, or CS-RNTI(s)UE SpecificUE SpecificC-RNTI, or MCS-C-RNTI, or CS-RNTI(s)User specific PDSCH decoding

[0077] Table 4 illustrates DCI formats transmitted via PDCCH.

[0078] DCI formatUsage0_0Scheduling of PUSCH in one cell0_1Scheduling of PUSCH in one cell1_0Scheduling of PDSCH in one cell1_1Scheduling of PDSCH in one cell2_0Notifying a group of UEs of the slot format2_1Notifying a group of UEs of the PRB(s) and OFDM symbol(s) where UE may assume no transmission is intended for the UE2_2Transmission of TPC commands for PUCCH and PUSCH2_3Transmission of a group of TPC commands for SRS transmissions by one or more UEs

[0079] DCI format 0_0 is used to schedule a TB-based (or TB-level) PUSCH, and DCI format 0_1 ​​can be used to schedule a TB-based (or TB-level) PUSCH or a CBG (Code Block Group)-based (or CBG-level) PUSCH. DCI format 1_0 is used to schedule a TB-based (or TB-level) PDSCH, and DCI format 1_1 can be used to schedule a TB-based (or TB-level) PDSCH or a CBG-based (or CBG-level) PDSCH (DL grant DCI). DCI format 0_0 / 0_1 may be referred to as UL grant DCI or UL scheduling information, and DCI format 1_0 / 1_1 may be referred to as DL grant DCI or DL ​​scheduling information. DCI format 2_0 is used to convey dynamic slot format information (e.g., dynamic SFI) to the terminal, and DCI format 2_1 is used to convey downlink pre-emption information to the terminal. DCI format 2_0 and / or DCI format 2_1 can be conveyed to the terminals within a group through the group common PDCCH, which is a PDCCH conveyed to the terminals defined as a group.

[0080] DCI format 0_0 and DCI format 1_0 may be referred to as fallback DCI formats, while DCI format 0_1 ​​and DCI format 1_1 may be referred to as non-fallback DCI formats. In the fallback DCI format, the DCI size / field configuration remains the same regardless of the terminal configuration. On the other hand, in the non-fallback DCI format, the DCI size / field configuration varies depending on the terminal configuration.

[0081] PDSCH carries downlink data (e.g., DL-SCH transport block, DL-SCH TB) and applies modulation methods such as Quadrature Phase Shift Keying (QPSK), 16 Quadrature Amplitude Modulation (QAM), 64 QAM, and 256 QAM. TB is encoded to generate a codeword. PDSCH can carry up to two codewords. Scrambling and modulation mapping are performed for each codeword, and modulation symbols generated from each codeword can be mapped to one or more layers. Each layer is mapped to resources along with a Demodulation Reference Signal (DMRS), generated as an OFDM symbol signal, and transmitted through the corresponding antenna port.

[0082] PUCCH carries Uplink Control Information (UCI). UCI includes:

[0083] - SR (Scheduling Request): Information used to request UL-SCH resources.

[0084] - HARQ(Hybrid Automatic Repeat reQuest)-ACK(Acknowledgement): This is a response to a downlink data packet (e.g., codeword) on the PDSCH. It indicates whether the downlink data packet was successfully received. One HARQ-ACK bit can be transmitted in response to a single codeword, and two HARQ-ACK bits can be transmitted in response to two codewords. The HARQ-ACK response includes a positive ACK (simply, ACK), a negative ACK (NACK), a DTX, or a NACK / DTX. Here, HARQ-ACK is used interchangeably with HARQ ACK / NACK and ACK / NACK.

[0085] - CSI (Channel State Information): Feedback information for the downlink channel. MIMO (Multiple Input Multiple Output)-related feedback information includes the Rank Indicator (RI) and Precoding Matrix Indicator (PMI).

[0086] Table 5 illustrates PUCCH formats. Depending on the PUCCH transmission length, they can be classified into Short PUCCH (formats 0 and 2) and Long PUCCH (formats 1, 3, and 4).

[0087] PUCCH formatLength in OFDM symbols N PUCCH symb Number of bitsUsageEtc01 - 2≤2HARQ, SRSequence selection14 - 14≤2HARQ, [SR]Sequence modulation21 - 2>2HARQ, CSI, [SR]CP-OFDM34 - 14>2HARQ, CSI, [SR]DFT-s-OFDM(no UE multiplexing)44 - 14>2HARQ, CSI, [SR]DFT-s-OFDM(Pre DFT OCC)

[0088] PUCCH format 0 carries UCI of up to 2 bits in size and is mapped and transmitted based on sequence. Specifically, the terminal transmits a specific UCI to the base station by transmitting one of multiple sequences through the PUCCH of PUCCH format 0. The terminal transmits the PUCCH of PUCCH format 0 within the PUCCH resources for the corresponding SR configuration only when transmitting a positive SR.

[0089] PUCCH format 1 carries UCI of up to 2 bits in size, and modulation symbols are spread in the time domain using an orthogonal cover code (OCC) (which is set differently depending on whether frequency hopping is used). DMRS are transmitted in symbols where modulation symbols are not transmitted (i.e., transmitted using Time Division Multiplexing (TDM).

[0090] PUCCH format 2 carries UCI with a bit size greater than 2 bits, and modulation symbols are transmitted by frequency division multiplexing (FDM) with DMRS. DM-RSs are located at symbol indices #1, #4, #7, and #10 within a given resource block with a density of 1 / 3. Pseudo Noise (PN) sequences are used for DM_RS sequences. Frequency hopping can be enabled for 2-symbol PUCCH format 2.

[0091] PUCCH format 3 does not multiplex terminals within the same physical resource blocks and carries UCI with a bit size greater than 2 bits. In other words, PUCCH resources in PUCCH format 3 do not include orthogonal cover codes. Modulation symbols are transmitted through time division multiplexing (TDM) with DMRS.

[0092] PUCCH format 4 supports multiplexing of up to four terminals within the same physical resource blocks and carries UCI with a bit size greater than 2 bits. In other words, PUCCH resources in PUCCH format 3 include orthogonal cover codes. Modulation symbols are transmitted through time division multiplexing (TDM) with DMRS.

[0093] At least one of one or more configured cells in a terminal may be configured for PUCCH transmission. At least the primary cell may be configured as a cell for PUCCH transmission. At least one PUCCH cell group may be configured in the terminal based on at least one cell configured for PUCCH transmission, and each PUCCH cell group includes one or more cells. The PUCCH cell group may be simply referred to as a PUCCH group. PUCCH transmission may be configured not only for the primary cell but also for the SCell, and the primary cell belongs to the primary PUCCH group, and the PUCCH-SCell configured for PUCCH transmission belongs to the secondary PUCCH group. For cells belonging to the primary PUCCH group, the PUCCH on the primary cell may be used, and for cells belonging to the secondary PUCCH group, the PUCCH on the PUCCH-SCell may be used.

[0094] PUSCH carries uplink data (e.g., UL-SCH transport block, UL-SCH TB) and / or uplink control information (UCI), and is transmitted based on a CP-OFDM (Cyclic Prefix - Orthogonal Frequency Division Multiplexing) waveform or a DFT-s-OFDM (Discrete Fourier Transform - spread - Orthogonal Frequency Division Multiplexing) waveform. When the PUSCH is transmitted based on a DFT-s-OFDM waveform, the UE transmits the PUSCH by applying transform precoding. For example, when transform precoding is disabled (e.g., transform precoding is disabled), the UE transmits the PUSCH based on the CP-OFDM waveform, and when transform precoding is enabled (e.g., transform precoding is enabled), the UE can transmit the PUSCH based on the CP-OFDM waveform or the DFT-s-OFDM waveform. PUSCH transmissions can be dynamically scheduled by UL grants in DCI, or semi-statically scheduled (configured grant) based on higher layer (e.g., RRC) signaling (and / or Layer 1 (L1) signaling (e.g., PDCCH)). PUSCH transmissions can be performed in a codebook-based or non-codebook-based manner.

[0095] Figure 5 illustrates an ACK / NACK transmission process. Referring to Figure 5, a terminal can detect a PDCCH in slot #n. Here, the PDCCH includes downlink scheduling information (e.g., DCI formats 1_0, 1_1), and the PDCCH indicates a DL assignment-to-PDSCH offset (K0) and a PDSCH-HARQ-ACK reporting offset (K1). For example, DCI formats 1_0, 1_1 can include the following information:

[0096] - Frequency domain resource assignment: Indicates the set of RBs allocated to the PDSCH.

[0097] - Time domain resource assignment: K0 (e.g., slot offset), indicates the starting position of the PDSCH within slot #n+K0 (e.g., OFDM symbol index), and the length of the PDSCH (e.g., number of OFDM symbols).

[0098] - PDSCH-to-HARQ_feedback timing indicator: Indicates K1

[0099] - HARQ process number (4 bits): Indicates the HARQ process ID (Identity) for data (e.g., PDSCH, TB)

[0100] - PUCCH resource indicator (PRI): Indicates the PUCCH resource to be used for UCI transmission among multiple PUCCH resources within the PUCCH resource set.

[0101] Afterwards, the terminal receives PDSCH from slot #(n+K0) according to the scheduling information of slot #n, and when reception of PDSCH is finished in slot #n1 (where, n+K0≤n1), UCI can be transmitted through PUCCH in slot #(n1+K1). Here, UCI may include HARQ-ACK response for PDSCH. In Fig. 5, for convenience, it is assumed that SCS for PDSCH and SCS for PUCCH are the same and slot # n1 = slot #n+K0, but the present invention is not limited thereto. If the SCSs are different, K1 can be indicated / interpreted based on the SCS of PUCCH.

[0102] When the PDSCH is configured to transmit at most 1 TB, the HARQ-ACK response may consist of 1 bit. When the PDSCH is configured to transmit at most 2 TB, the HARQ-ACK response may consist of 2 bits if spatial bundling is not configured, and may consist of 1 bit if spatial bundling is configured. When the HARQ-ACK transmission timing for multiple PDSCHs is designated as slot #(n+K1), the UCI transmitted in slot #(n+K1) includes HARQ-ACK responses for multiple PDSCHs.

[0103] Whether a UE should perform spatial bundling for a HARQ-ACK response can be configured (e.g., via RRC / higher layer signaling) for each cell group. For example, spatial bundling can be individually configured for each HARQ-ACK response transmitted over the PUCCH and / or each HARQ-ACK response transmitted over the PUSCH.

[0104] Spatial bundling can be supported when the maximum number of TBs (or codewords) that can be received at a time (or scheduled via 1 DCI) in the serving cell is 2 (or more than 2) (e.g., when the upper layer parameter maxNrofCodeWordsScheduledByDCI corresponds to 2-TB). Meanwhile, more than 4 layers can be used for 2-TB transmission, and up to 4 layers can be used for 1-TB transmission. Consequently, when spatial bundling is configured for the cell group, spatial bundling can be performed for serving cells that can schedule more than 4 layers among the serving cells in the cell group. On the serving cell, a terminal that wishes to transmit a HARQ-ACK response via spatial bundling can generate the HARQ-ACK response by performing a (bit-wise) logical AND operation on the A / N bits for multiple TBs.

[0105] For example, assuming that a terminal receives a DCI scheduling 2 TB and receives 2 TB via PDSCH based on the DCI, the terminal performing spatial bundling can generate a single A / N bit by logically ANDing the first A / N bit for the first TB and the second A / N bit for the second TB. Consequently, if both the first TB and the second TB are ACK, the terminal reports the ACK bit value to the base station, and if either TB is NACK, the terminal reports the NACK bit value to the base station.

[0106] For example, if only 1-TB is actually scheduled on a serving cell configured to receive 2-TB, the terminal can generate a single A / N bit by logically ANDing the A / N bit for the 1-TB with bit value 1. Consequently, the terminal reports the A / N bit for the 1-TB to the base station as is.

[0107] A base station / terminal has multiple parallel DL HARQ processes for DL ​​transmission. These multiple parallel HARQ processes allow DL transmissions to be performed continuously while waiting for HARQ feedback regarding the success or failure of the previous DL transmission. Each HARQ process is associated with a HARQ buffer in the MAC (Medium Access Control) layer. Each DL HARQ process manages state variables such as the number of transmissions of MAC Physical Data Blocks (PDUs) in the buffer, HARQ feedback for MAC PDUs in the buffer, and the current redundancy version. Each HARQ process is identified by a HARQ process ID.

[0108] Figure 6 illustrates a PUSCH transmission process. Referring to Figure 6, a terminal can detect a PDCCH in slot #n. Here, the PDCCH includes uplink scheduling information (e.g., DCI formats 0_0 and 0_1). DCI formats 0_0 and 0_1 can include the following information.

[0109] - Frequency domain resource assignment: Indicates the set of RBs allocated to PUSCH.

[0110] - Time domain resource assignment: Slot offset K2 indicates the starting position (e.g., symbol index) and length (e.g., number of OFDM symbols) of the PUSCH within the slot. The starting symbol and length can be indicated through SLIV (Start and Length Indicator Value) or can be indicated separately.

[0111] Thereafter, the terminal can transmit a PUSCH in slot #(n+K2) according to the scheduling information of slot #n. Here, the PUSCH includes a UL-SCH TB.

[0112] CSI-related actions

[0113] Figure 7 shows an example of a CSI-related procedure.

[0114] The terminal receives configuration information related to CSI from the base station via RRC signaling (710). The configuration information related to CSI may include at least one of CSI-IM (interference management) resource-related information, CSI measurement configuration-related information, CSI resource configuration-related information, CSI-RS resource-related information, or CSI report configuration-related information.

[0115] - CSI-IM resources can be configured for interference measurement (IM) of the terminal. In the time domain, the CSI-IM resource set can be configured periodically, semi-persistently, or aperiodicly. The CSI-IM resources can be configured as Zero Power (ZP)-CSI-RS for the terminal. The ZP-CSI-RS can be configured separately from the Non-Zero Power (NZP)-CSI-RS.

[0116] - The UE may assume that the CSI-RS resource(s) for channel measurement configured for one CSI reporting and the CSI-IM / NZP CSI-RS resource(s) for interference measurement (when NZP CSI-RS resource(s) are used for interference measurement) are in a QCL relationship with respect to 'QCL-TypeD' per resource.

[0117] - The CSI resource configuration may include at least one of a CSI-IM resource for interference measurement, an NZP CSI-RS resource for interference measurement, and an NZP CSI-RS resource for channel measurement. The CMR (channel measurement resource) may be an NZP CSI-RS for CSI acquisition, and the IMR (Interference measurement resource) may be an NZP CSI-RS for CSI-IM and IM.

[0118] - CSI-RS can be configured for one or more terminals. Different CSI-RS configurations may be provided for each terminal, or the same CSI-RS configuration may be provided to multiple terminals. CSI-RS can support up to 32 antenna ports. CSI-RS corresponding to N (N is 1 or greater) antenna ports can be mapped to N RE locations within a time-frequency unit corresponding to one slot and one RB. When N is 2 or greater, N-port CSI-RS can be multiplexed using CDM, FDM, and / or TDM schemes. CSI-RS can be mapped to REs other than REs to which CORESET, DMRS, and SSB are mapped. In the frequency domain, CSI-RS can be configured for the entire bandwidth, a portion of the bandwidth (BWP), or a portion of the bandwidth. CSI-RS may be transmitted in each RB within the bandwidth for which CSI-RS is configured (i.e., density = 1), or in every second RB (e.g., even or odd RB) (i.e., density = 1 / 2). When CSI-RS is used as a Tracking Reference Signal (TRS), a single-port CSI-RS may be mapped on three subcarriers in each resource block (i.e., density = 3). One or more CSI-RS resource sets may be configured for a UE in the time domain. Each CSI-RS resource set may include one or more CSI-RS configurations. Each CSI-RS resource set may be configured periodically, semi-persistently, or aperiodicly.

[0119] - The CSI report configuration may include configurations for feedback type, measurement resources, report type, etc. The NZP-CSI-RS resource set may be used for the CSI report configuration of the corresponding terminal. The NZP-CSI-RS resource set may be associated with CSI-RS or SSB. In addition, multiple periodic NZP-CSI-RS resource sets may be configured as TRS resource sets. (i) The feedback type may include a Channel Quality Indicator (CQI), a Precoding Matrix Indicator (PMI), a CSI-RS Resource Indicator (CRI), an SSB Resource block Indicator (SSBRI), a Layer Indicator (LI), a Rank Indicator (RI), a Layer 1-Reference Signal Received Strength (RSRP), etc. (ii) Measurement resources may include configurations for downlink signals and / or downlink resources on which the terminal performs measurements to determine feedback information. The measurement resources may be configured as ZP and / or NZP CSI-RS resource sets associated with CSI reporting configurations. The NZP CSI-RS resource set may include a CSI-RS set or an SSB set. For example, L1-RSRP may be measured for a CSI-RS set or an SSB set. (iii) Reporting types may include configurations for a time point at which the terminal performs reporting and an uplink channel, etc. The reporting time point may be configured as periodic, semi-persistent, or aperiodic. Periodic CSI reporting may be transmitted on PUCCH. Semi-persistent CSI reporting may be transmitted on PUCCH or PUSCH based on a MAC CE indicating activation / deactivation. Aperiodic CSI reporting may be indicated by DCI signaling.For example, the CSI request field of an uplink grant may indicate one of several report trigger sizes. Aperiodic CSI reports may be transmitted on the PUSCH.

[0120] The terminal measures CSI based on configuration information related to CSI. CSI measurement may include a procedure of receiving a CSI-RS (720) and computing the received CSI-RS to acquire CSI (730).

[0121] The UE can transmit a CSI report to the base station (740). For the CSI report, the time and frequency resources that the UE can use are controlled by the base station. The CSI (channel state information) can include at least one of a channel quality indicator (CQI), a precoding matrix indicator (PMI), a CSI-RS resource indicator (CRI), an SS / PBCH block resource indicator (SSBRI), a layer indicator (LI), a rank indicator (RI), L1-RSRP, and / or L-SINR.

[0122] The time domain behavior of CSI reporting supports periodic, semi-persistent, and aperiodic. i) Periodic CSI reporting is performed on short PUCCH and long PUCCH. The periodicity and slot offset of periodic CSI reporting can be configured by RRC, and refer to the CSI-ReportConfig IE. ii) SP (semi-periodic) CSI reporting is performed on short PUCCH, long PUCCH, or PUSCH. In case of SP CSI on short / long PUCCH, the periodicity and slot offset are configured by RRC, and CSI reporting is activated / deactivated by separate MAC CE / DCI. In case of SP CSI on PUSCH, the periodicity of SP CSI reporting is configured by RRC, but the slot offset is not configured by RRC, and SP CSI reporting is activated / deactivated by DCI (format 0_1). For SP CSI reporting on PUSCH, a separate RNTI (SP-CSI C-RNTI) is used. The initial CSI reporting timing follows the PUSCH time domain allocation value indicated in the DCI, and subsequent CSI reporting timings follow the cycle set by RRC. DCI format 0_1 ​​includes a CSI request field and can activate / deactivate a specific configured SP-CSI trigger state. SP CSI reporting has the same or similar activation / deactivation mechanism as the data transmission mechanism on the SPS PUSCH.iii) Aperiodic CSI reporting is performed on PUSCH and is triggered by DCI. In this case, information related to the triggering of aperiodic CSI reporting can be transmitted / indicated / configured via MAC-CE. For AP CSI with AP CSI-RS, the AP CSI-RS timing is configured by RRC, and the timing for AP CSI reporting is dynamically controlled by DCI.

[0123] CSI codebooks defined in the NR standard (e.g., PMI codebooks) can be broadly divided into Type I and Type II codebooks. Type I codebooks are primarily targeted at SU (Single User)-MIMO, which supports both high-order and low-order signals. Type II codebooks can primarily support MI-MIMO, which supports up to two layers. Compared to Type I, Type II codebooks can provide more accurate CSI, but may increase signaling overhead. Meanwhile, Enhanced Type II codebooks were introduced to address the CSI overhead shortcomings of existing Type II codebooks. Enhanced Type II codebooks were introduced by reducing the codebook payload by considering frequency-axis correlation.

[0124] CSI reporting via PUSCH can be configured as Part 1 and Part 2. Part 1 has a fixed payload size and is used to identify the number of information bits in Part 2. Part 1 is transmitted in its entirety before Part 2.

[0125] - For Type I CSI feedback, Part 1 contains the RI (if reported), the CRI (if reported), and the CQI of the first code word. Part 2 contains the PMI, and when RI > 4, Part 2 contains the CQI.

[0126] - For Type II CSI feedback, Part 1 contains the RI (if reported), CQI, and an indication of the number of non-zero WB amplitude coefficients per layer of Type II CSI. Part 2 contains the PMI of Type II CSI.

[0127] - For Enhanced Type II CSI feedback, Part 1 contains the RI (if reported), CQI, and the total number of non-zero WB amplitude coefficients for all layers of Enhanced Type II CSI. Part 2 contains the PMI of Enhanced Type II CSI.

[0128] If CSI reporting on PUSCH includes two parts and the CSI payload to be reported is less than the payload size provided by the PUSCH resources allocated for CSI reporting, the UE may omit part of Part 2 CSI.

[0129] Meanwhile, semi-persistent CSI reporting performed in PUCCH format 3 or 4 supports Type II CSI feedback, but only Part 1 of Type II CSI feedback.

[0130] QCL (quasi-co location)

[0131] Two antenna ports are quasi-co-located if the channel properties of one antenna port can be inferred from the channel properties of the other antenna port. The channel properties may include one or more of Delay spread, Doppler spread, Frequency / Doppler shift, Average received power, Received Timing / average delay, and Spatial RX parameters.

[0132] A terminal can configure a list of multiple TCI-State configurations via the upper layer parameter PDSCH-Config. Each TCI-State is associated with one or two DL reference signals and a QCL configuration parameter between the DM-RS port of the PDSCH. The QCL can include qcl-Type1 for the first DL RS and qcl-Type2 for the second DL RS. The QCL type can correspond to one of the following:

[0133] - 'QCL-TypeA': {Doppler shift, Doppler spread, average delay, delay spread}

[0134] - 'QCL-TypeB': {Doppler shift, Doppler spread}

[0135] - 'QCL-TypeC': {Doppler shift, average delay}

[0136] - 'QCL-TypeD': {Spatial Rx parameter}

[0137] Beam Management (BM)

[0138] The BM process is a process for acquiring and maintaining a set of BS (or transmission and reception point (TRP)) and / or UE beams that can be used for downlink (DL) and uplink (UL) transmission / reception, and may include the following processes and terms.

[0139] - Beam measurement: An operation in which a BS or UE measures the characteristics of a received beamforming signal.

[0140] - Beam determination: An operation in which a BS or UE selects its own transmit beam (Tx beam) / receive beam (Rx beam).

[0141] - Beam sweeping: An operation of covering a spatial domain using transmit and / or receive beams over a predetermined time interval in a predetermined manner.

[0142] - Beam report: An operation in which a UE reports information about a beamformed signal based on beam measurement.

[0143] The BM process can be divided into (1) a DL BM process using SSB or CSI-RS, and (2) a UL BM process using SRS (sounding reference signal). In addition, each BM process can include Tx beam sweeping to determine a Tx beam and Rx beam sweeping to determine an Rx beam.

[0144] At this time, the DL BM process may include (1) transmission of beamformed DL RSs (e.g., CSI-RS or SSB) by the BS and (2) beam reporting by the UE.

[0145] Here, the beam report may include preferred DL RS ID(s) and corresponding reference signal received power (RSRP). The DL RS ID may be an SSB Resource Indicator (SSBRI) or a CSI-RS Resource Indicator (CRI).

[0146] Positioning

[0147] Positioning may refer to determining the geographic location and / or velocity of a UE by measuring radio signals. Position information may be requested by a client (e.g., an application) associated with the UE and reported to the client. Furthermore, the location information may be contained within the core network or requested by a client connected to the core network. The location information may be reported in a standard format, such as cell-based or geographic coordinates, and may also include an estimated error value for the UE's position and velocity and / or the positioning method used for positioning.

[0148] LPP can be used as a point-to-point between a location server (E-SMLC and / or SLP and / or LMF) and a target device (UE and / or SET) to position the target device using position-related measurements obtained from one or more reference sources. Through LPP, the target device and the location server can exchange measurement and / or position information based on Signal A and / or Signal B.

[0149] NRPPa can be used to exchange information between a reference source (ACCESS NODE and / or BS and / or TP and / or NG-RAN node) and a location server.

[0150] The functions provided by the NRPPa protocol may include:

[0151] - E-CID Location Information Transfer. This function allows location information to be exchanged between the reference source and the LMF for E-CID positioning purposes.

[0152] - OTDOA Information Transfer. This function allows information to be exchanged between the reference source and the LMF for OTDOA positioning purposes.

[0153] - Reporting of General Error Situations. This feature allows reporting of general error situations for which no function-specific error message is defined.

[0154] The positioning methods supported by NG-RAN may include GNSS (Global Navigation Satellite System), OTDOA, E-CID (enhanced cell ID), barometric positioning, WLAN positioning, Bluetooth positioning, terrestrial beacon system (TBS), and UTDOA (Uplink Time Difference of Arrival). Among the above positioning methods, the position of the UE may be measured using any one of the positioning methods, but the position of the UE may also be measured using two or more positioning methods.

[0155] OTDOA (Observed Time Difference Of Arrival)

[0156] The OTDOA positioning method utilizes the timing measurements of downlink signals received by the UE from multiple TPs, including the eNB, ng-eNB, and PRS-dedicated TPs. The UE measures the timing of the received downlink signals using location assistance data received from a location server. Based on these measurement results and the geographic coordinates of neighboring TPs, the UE's location can be determined.

[0157] A UE connected to a gNB can request a measurement gap for OTDOA measurements from a TP. If the UE does not recognize the SFN for at least one TP in the OTDOA assistance data, the UE can use an autonomous gap to obtain the SFN of the OTDOA reference cell before requesting a measurement gap to perform Reference Signal Time Difference (RSTD) measurements.

[0158] Here, the RSTD can be defined based on the smallest relative time difference between the boundaries of two subframes received from the reference cell and the measurement cell, respectively. That is, it can be calculated based on the relative time difference between the start time of the subframe of the reference cell that is closest to the start time of the subframe received from the measurement cell. Meanwhile, the reference cell can be selected by the UE.

[0159] Accurate OTDOA measurement requires measuring the time of arrival (TOA) of signals received from three or more geographically dispersed TPs or base stations. For example, the TOA for TP 1, TP 2, and TP 3 can be measured, and based on the three TOAs, the RSTD for TP 1-TP 2, the RSTD for TP 2-TP 3, and the RSTD for TP 3-TP 1 can be calculated. Based on these TOAs, a geometric hyperbola can be determined, and the point where these hyperbolas intersect can be used to estimate the UE's location. Since each TOA measurement may have inaccuracies and / or uncertainties, the estimated UE's location can be known within a certain range depending on the measurement uncertainty.

[0160] E-CID (Enhanced Cell ID)

[0161] In the Cell ID (CID) positioning method, the location of the UE can be measured through geographic information of the UE's serving ng-eNB, serving gNB, and / or serving cell. For example, geographic information of the serving ng-eNB, serving gNB, and / or serving cell can be obtained through paging, registration, etc.

[0162] Meanwhile, the E-CID positioning method may utilize additional UE measurements and / or NG-RAN radio resources in addition to the CID positioning method to improve the UE position estimate. In the E-CID positioning method, some of the same measurement methods as the measurement control system of the RRC protocol may be used, but generally, additional measurements are not performed solely for UE position measurement. In other words, a separate measurement configuration or measurement control message may not be provided to measure the UE's position, and the UE may not expect to be requested to perform additional measurement operations solely for position measurement, and may report measurement values ​​obtained through measurement methods that the UE can generally measure.

[0163] For example, a serving gNB can implement an E-CID positioning method using E-UTRA measurements provided from the UE.

[0164] AI / ML (Artificial intelligence / machine learning)

[0165] Technological advancements in AI / ML are leading to the intelligence / advanced development of node(s) and terminal(s) that make up wireless communication networks. In particular, the intelligence of networks / base stations will enable the rapid optimization / derivation / application of various network / base station decision parameter values ​​(e.g., transmit / receive power of each base station, transmit power of each terminal, precoder / beam of base stations / terminals, time / frequency resource allocation for each terminal, duplexing method of each base station, etc.) based on various environmental parameters (e.g., distribution / location of base stations, distribution / location / material of buildings / furniture, etc., location / movement direction / speed of terminals, climate information, etc.). In line with this trend, many standardization organizations (e.g., 3GPP, O-RAN) are considering its introduction, and research on it is also actively underway.

[0166] AI / ML can be easily referred to as artificial intelligence based on deep learning in a narrow sense, but conceptually it is as shown in Figure 8.

[0167] - Artificial Intelligence: This can refer to all automation where machines can replace tasks that people would otherwise do.

[0168] - Machine Learning: Machines can learn patterns for decision-making from data without explicitly programming rules.

[0169] Deep Learning: An AI / ML model based on artificial neural networks. Machines simultaneously extract features from unstructured data and make judgments. The algorithms rely on multilayer networks of interconnected nodes for feature extraction and transformation, inspired by the biological nervous system, or neural networks. Common deep learning network architectures include deep neural networks (DNNs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs).

[0170] Classification of AI / ML types based on various criteria

[0171] 1. Offline vs. Online

[0172] (1) Offline Learning: This follows a sequential process of database collection, learning, and prediction. In other words, collection and learning are performed offline, and the completed program can be installed on-site for use in prediction tasks. This offline learning method is used in most situations. In offline learning, the system does not learn incrementally; learning is performed using all available collected data and applied to the system without further training. If learning on new data is required, learning can be restarted using the entire new data set.

[0173] (2) Online Learning: Online learning leverages the continuous availability of data available for learning via the Internet. This method incrementally improves performance by learning from additional data. Learning is performed in real time on specific data (sets) collected online, enabling the system to quickly adapt to changing data.

[0174] To build an AI system, only online learning may be used, so that learning is performed using only real-time data, or offline learning may be performed using a predetermined data set, and then additional learning may be performed using additional real-time data (online + offline learning).

[0175] 2. Classification by AI / ML Framework Concept

[0176] (1) Centralized Learning: Training data collected from multiple different nodes are reported to a centralized node, and all data resources / storage / learning (e.g., supervised, unsupervised, reinforcement learning) are performed in one central node.

[0177] (2) Federated Learning: A collective AI / ML model is built based on data across distributed data owners. Instead of importing data into an AI / ML model, the AI / ML model is imported as a data source, allowing local nodes / individual devices to collect data and train their own copies of the AI / ML model, eliminating the need to report source data to a central node. In federated learning, the parameters / weights of the AI / ML model are simply sent back to the centralized node to support general AI / ML model training. The advantages of federated learning include increased computational speed and superior information security. This eliminates the need to upload personal data to a central server, preventing personal information leaks and misuse.

[0178] (3) Distributed Learning: This concept represents the concept of machine learning processes being scaled and distributed across a cluster of nodes. Training AI / ML models are split and shared across multiple nodes operating simultaneously to accelerate AI / ML model training.

[0179] 3. Classification by learning method

[0180] (1) Supervised Learning: Supervised learning is a machine learning task that aims to learn a mapping function from input to output given a labeled data set. The input data is called training data and has known labels or outcomes. Examples of supervised learning include (i) Regression: Linear Regression, Logistic Regression, (ii) Instance-based Algorithms: k-Nearest Neighbor (KNN), (iii) Decision Tree Algorithms: CART, (iv) Support Vector Machines: SVM, (v) Bayesian Algorithms: Naive Bayes, and (vi) Ensemble Algorithms: Extreme Gradient Boosting, Bagging: Random Forest. Supervised learning can be further grouped into regression and classification problems, where classification predicts labels and regression predicts quantities.

[0181] (2) Unsupervised Learning: A machine learning task that aims to learn features that explain hidden structures in unlabeled data. The input data is unlabeled and has no known outcome. Some examples of unsupervised learning include K-means clustering, principal component analysis (PCA), nonlinear independent component analysis (ICA), and long-term memory (LSTM).

[0182] (3) Reinforcement Learning: In reinforcement learning (RL), an agent interacts with the environment through a trial-and-error process, aiming to optimize a long-term goal. It is a goal-oriented learning method based on interaction with the environment. Examples of RL algorithms include (i) Q-learning, (ii) multi-armed bandit learning, (iii) deep Q network, state-action-reward-state-action (SARSA), (iv) temporal difference learning, (v) actor-critic reinforcement learning, (vi) deep deterministic policy gradient, and (vii) Monte-Carlo tree search. Reinforcement learning can be further grouped into AI / ML model-based reinforcement learning and AI / ML model-free reinforcement learning. Model-based reinforcement learning is an RL algorithm that uses a predictive AI / ML model to obtain transition probabilities between states by using various dynamic states of the environment and the AI / ML model that leads to these states as rewards. Model-free reinforcement learning is a value- or policy-based RL algorithm that maximizes future rewards. It is computationally less complex in multi-agent environments / states and does not require an accurate representation of the environment. RL algorithms can also be categorized into value-based RL versus policy-based RL, and policy-based RL versus non-policy RL.

[0183] AI / ML models

[0184] Figure 9 illustrates an FFNN (Feed-Forward Neural Network) AI / ML model. Referring to Figure 9, the FFNN AI / ML model includes an input layer, a hidden layer, and an output layer.

[0185] Figure 10 illustrates an RNN (Recurrent Neural Network) AI / ML model. Referring to Figure 10, the RNN AI / ML model is a type of artificial neural network in which hidden nodes are connected by directed edges to form a cyclic structure (directed cycle), and is an AI / ML model suitable for processing data that appears sequentially, such as voice and text. One type of RNN is LSTM (Long Short-Term Memory), and LSTM is a structure that adds a cell state to the hidden state of RNN. Specifically, in LSTM, an input gate, a forget gate, and an output gate are added to the RNN cell, and a cell state is added. In Figure 10, A represents a neural network, x t is the input value, h t represents the output value. Here, h t can mean a status value that represents the present based on time, and h t-1 can represent the previous state value.

[0186] Figure 11 illustrates a CNN (Convolution Neural Network) AI / ML model. CNN uses convolution operations commonly used in image processing and video processing to achieve two goals: reducing AI / ML model complexity and extracting good features. Referring to Figure 11, a kernel or filter refers to a unit / structure that applies weights to inputs within a specific range / unit. The kernel (or filter) can be modified through learning. The stride refers to the range of movement of the kernel within the input. The feature map refers to the result of applying the kernel to the input. Padding refers to a value added to adjust the size of the feature map. Multiple feature maps can be extracted to induce robustness to distortion and changes. Pooling refers to an operation (e.g., max pooling, average pooling) to reduce the size of the feature map by downsampling it.

[0187] Figure 12 illustrates an auto-encoder AI / ML model. Referring to Figure 12, an auto-encoder is a neural network that receives a feature vector x as input and outputs the same or similar vector x'. The input and output nodes have the same features, and it is a type of unsupervised learning. Since an auto-encoder reconstructs the input, the output can be referred to as a reconstruction. The loss function can be expressed as in Mathematical Formula 1.

[0188]

[0189] The loss function of the auto encoder exemplified in Figure 12 is calculated based on the difference between the input and the output, and based on this, the degree of loss of the input is identified, and the auto encoder performs an optimization process to minimize the loss.

[0190] Figure 13 is a diagram illustrating segmentation AI inference.

[0191] Figure 13 illustrates a case where, among split AI operations, the Model Inference function is performed collaboratively by an end device such as a UE and a network AI / ML endpoint.

[0192] In addition to the Model Inference function, the Model Training function, Actor, and Data Collection functions can each be split into multiple parts depending on the current task and environment, and performed by multiple entities collaborating.

[0193] For example, computationally intensive and energy-intensive parts may be performed at the network endpoint, while privacy-sensitive and latency-sensitive parts may be performed at the end device. In this case, the end device may execute the task / model from input data up to a specific part / layer, and then transmit the intermediated data to the network endpoint. The network endpoint then executes the remaining parts / layers and provides the inference outputs to one or more devices that perform the actions / tasks.

[0194] The following describes a functional framework for AI operations.

[0195] Below, to explain AI (or AI / ML) more specifically, the terms can be defined as follows.

[0196] - Data collection: Data collected from network nodes, management entities, or UEs as a basis for AI model training, data analysis, and inference.

[0197] - AI Model: A data-driven algorithm that applies AI technology to generate a set of outputs containing predictive information and / or decision parameters based on a set of inputs.

[0198] - AI / ML Training: An online or offline process of training an AI model by learning features and patterns that best represent the data and obtain a trained AI / ML model for inference.

[0199] - AI / ML Inference: The process of making predictions or inducing decisions based on collected data and the AI ​​model using a trained AI model.

[0200] Referring to FIG. 14, the Data Collection function (10) is a function that collects input data and provides processed input data to the Model Training function (20) and the Model Inference function (30).

[0201] Examples of input data may include measurements from UEs or other network entities, feedback from actors, and output from AI models.

[0202] The Data Collection function (10) performs data preparation based on input data and provides input data processed through data preparation. Here, the Data Collection function (10) does not perform data preparation specific to each AI algorithm (e.g., data pre-processing and cleaning, formatting, and transformation), but can perform data preparation common to AI algorithms.

[0203] After the data preparation process is performed, the Model Training function (10) provides training data (11) to the Model Training function (20) and provides inference data (Inference Data) (12) to the Model Inference function (30). Here, the Training Data (11) is data required as input for the AI ​​Model Training function (20). The Inference Data (12) is data required as input for the AI ​​Model Inference function (30).

[0204] The Data Collection function (10) may be performed by a single entity (e.g., UE, RAN node, network node, etc.) or may be performed by multiple entities. In this case, Training Data (11) and Inference Data (12) may be provided to the Model Training function (20) and Model Inference function (30), respectively, from multiple entities.

[0205] The Model Training function (20) is a function that performs AI model training, validation, and testing, which can generate model performance metrics as part of the AI ​​model testing process. If necessary, the Model Training function (20) also handles data preparation (e.g., data pre-processing and cleaning, forming, and transformation) based on the Training Data (11) provided by the Data Collection function (10).

[0206] Here, Model Deployment / Update (13) is used to initially deploy the trained, verified, and tested AI model to the Model Inference function (30) or to provide the updated model to the Model Inference function (30).

[0207] The Model Inference function (30) is a function that provides AI model inference output (16) (e.g., prediction or decision). If applicable, the Model Inference function (30) may provide model performance feedback (14) to the Model Training function (20). In addition, the Model Inference function (30) is also responsible for data preparation (e.g., data pre-processing and cleaning, forming, and transformation) based on the Inference Data (12) provided by the Data Collection function (10), if necessary.

[0208] Here, Output (16) refers to the inference output of the AI ​​model generated by the Model Inference function (30), and the details of the inference output may vary depending on the use case.

[0209] Model Performance Feedback (14) can be used to monitor the performance of the AI ​​model if available, and this feedback may be omitted.

[0210] The actor function (40) is a function that receives the output (16) from the model inference function (30) and triggers or performs a corresponding task / action. The actor function (40) can trigger tasks / actions for other entities (e.g., one or more UEs, one or more RAN nodes, one or more network nodes, etc.) or for itself.

[0211] Feedback (15) can be used to derive training data (11), inference data (12), or to monitor the performance of the AI ​​model, its impact on the network, etc.

[0212] Meanwhile, the definitions of training / validation / test in the data set used in AI / ML can be distinguished as follows.

[0213] - Training data: This refers to the data set for learning the model.

[0214] - Validation data: This refers to a data set used to validate a model that has already completed training. In other words, it refers to a data set typically used to prevent overfitting of the training data set.

[0215] It also refers to a data set for selecting the best model among the various models learned during the learning process. Therefore, it can be viewed as a type of learning.

[0216] - Test data: This refers to the data set for final evaluation. This data is unrelated to learning.

[0217] In the case of the above data set, if the training set is generally divided, the training data and validation data can be divided and used in a ratio of 8:2 or 7:3 within the entire training set, and if the test is included, it can be divided and used in a ratio of 6:2:2 (training: validation: test).

[0218] Depending on the capability of the AI / ML function between the base station and the terminal, the level of cooperation can be defined as follows, and variations due to combination of multiple levels or separation of any one level are also possible.

[0219] Cat 0a) No collaboration framework: AI / ML algorithms are purely implementation-based and do not require any changes to the wireless interface.

[0220] Cat 0b) This level corresponds to a framework with a modified wireless interface tailored to efficient implementation-based AI / ML algorithms, but without collaboration.

[0221] Category 1) involves inter-node support to improve the AI / ML algorithms of each node. This applies when the UE receives support from the gNB (for training, adaptation, etc.) and vice versa. At this level, model exchange between network nodes is not required.

[0222] Category 2) Joint ML tasks can be performed between the UE and gNB. This level requires the exchange of AI / ML model commands or network nodes.

[0223] The functions exemplified in FIG. 14 above may be implemented in a RAN node (e.g., a base station, a TRP, a central unit (CU) of a base station, etc.), a network node, an operation administration maintenance (OAM) of a network operator, or a UE.

[0224] Alternatively, two or more entities, such as a RAN, a network node, a network operator's OAM, or a UE, may cooperate to implement the functions exemplified in FIG. 14. For example, one entity may perform some of the functions of FIG. 14, and another entity may perform the remaining functions. In this way, since some of the functions exemplified in FIG. 14 are performed by a single entity (e.g., a UE, a RAN node, a network node, etc.), the transmission / provision of data / information between each function may be omitted. For example, if the Model Training function (20) and the Model Inference function (30) are performed by the same entity, the transmission / provision of Model Deployment / Update (13) and Model Performance Feedback (14) may be omitted.

[0225] Alternatively, any one of the functions illustrated in FIG. 14 may be performed through collaboration between two or more entities, including a RAN, a network node, a network operator's OAM, or a UE. This may be referred to as a split AI operation.

[0226] Figure 15 illustrates a case where the AI ​​Model Training function is performed by a network node (e.g., a core network node, an OAM of a network operator, etc.) and the AI ​​Model Inference function is performed by a RAN node (e.g., a base station, a TRP, a CU of a base station, etc.).

[0227] Step 1: RAN node 1 and RAN node 2 transmit input data (i.e., training data) for AI model training to the network node. Here, RAN node 1 and RAN node 2 can also transmit data collected from the UE (e.g., UE measurements related to RSRP, RSRQ, SINR of the serving cell and neighboring cells, UE location, speed, etc.) to the network node.

[0228] Step 2: Network nodes train the AI ​​model using the received training data.

[0229] Step 3: The network node distributes / updates the AI ​​Model to RAN Node 1 and / or RAN Node 2. RAN Node 1 (and / or RAN Node 2) may continue model training based on the received AI Model.

[0230] For convenience of explanation, we assume that the AI ​​Model is deployed / updated only to RAN node 1.

[0231] Step 4: RAN node 1 receives input data for AI Model Inference (i.e., Inference data) from UE and RAN node 2.

[0232] Step 5: RAN node 1 performs AI Model Inference using the received Inference data to generate output data (e.g., prediction or decision).

[0233] Step 6: If applicable, RAN node 1 may transmit model performance feedback to the network nodes.

[0234] Step 7: RAN node 1, RAN node 2, and the UE (or 'RAN node 1 and the UE', or 'RAN node 1 and the RAN node 2') perform actions based on the output data. For example, in the case of a load balancing operation, the UE may move from RAN node 1 to RAN node 2.

[0235] Step 8: RAN node 1 and RAN node 2 transmit feedback information to the network nodes.

[0236] Figure 16 illustrates a case where both the AI ​​Model Training function and the AI ​​Model Inference function are performed by RAN nodes (e.g., base station, TRP, CU of base station, etc.).

[0237] Step 1: UE and RAN node 2 transmit input data (i.e., training data) for AI model training to RAN node 1.

[0238] Step 2: RAN node 1 trains the AI ​​model using the received training data.

[0239] Step 3: RAN node 1 receives input data for AI Model Inference (i.e., Inference data) from the UE and RAN node 2.

[0240] Step 4: RAN node 1 performs AI Model Inference using the received Inference data to generate output data (e.g., prediction or decision).

[0241] Step 5: RAN node 1, RAN node 2, and the UE (or 'RAN node 1 and the UE', or 'RAN node 1 and the RAN node 2') perform actions based on the output data. For example, in the case of a load balancing operation, the UE may move from RAN node 1 to RAN node 2.

[0242] Step 6: RAN node 2 sends feedback information to RAN node 1.

[0243] Figure 17 illustrates a case where the AI ​​Model Training function is performed by a RAN node (e.g., a base station, a TRP, a CU of the base station, etc.) and the AI ​​Model Inference function is performed by a UE.

[0244] Step 1: The UE transmits input data (i.e., training data) for AI model training to the RAN node. Here, the RAN node can collect data (e.g., UE measurements related to RSRP, RSRQ, SINR of the serving cell and neighboring cells, UE location, speed, etc.) from various UEs and / or from other RAN nodes.

[0245] Step 2: The RAN node trains the AI ​​model using the received training data.

[0246] Step 3: The RAN node distributes / updates the AI ​​model to the UE. The UE may also continue model training based on the received AI model.

[0247] Step 4: Receive input data (i.e., Inference data) for AI Model Inference from the UE and RAN nodes (and / or from other UEs).

[0248] Step 5: The UE performs AI Model Inference using the received Inference data to generate output data (e.g., prediction or decision).

[0249] Step 6: If applicable, the UE may send model performance feedback to the RAN node.

[0250] Step 7: The UE and RAN nodes perform actions based on the output data.

[0251] Step 8: The UE transmits feedback information to the RAN node.

[0252] CQI determination based on knowledge distillation

[0253] Hereinafter, a method for generating / determining CQI based on knowledge distillation in an environment where a two-sided model is used is proposed. The embodiments described below focus on a two-sided model for CSI compression, but the application of the present disclosure is not limited to CSI compression and can be applied to various other two-sided model use cases (e.g., positioning, beam management). Training can also be expressed as learning. The CSI compression described below can mean compression of CSI / channel information in the TSF (temporal, spatial, and frequency) domain, and past CSI can be provided as input to an AI / ML model as temporal information for such compression.

[0254] In NR Rel-18, AI / ML-based NR air interfaces and their key use cases, including CSI feedback enhancement, beam management, and positioning accuracy enhancement, were studied. Specifically, for CSI feedback enhancement, AI / ML models were used to reduce overhead and improve accuracy in CSI reporting. Further research is planned for NR Rel-19, with the following considerations for improving CSI feedback:

[0255] For CSI compression (two-sided model), improvements have been made to the trade-off between performance and complexity / overhead. For example, expanding spatial / frequency compression to spatial / temporal / frequency compression, cell / site-specific models, and considering prediction in addition to CSI compression (compared to Rel-18 non-AI / ML-based methods).

[0256] For CSI prediction (one-side models), research on the complexity associated with performance gains compared to existing non-AI / ML-based methods. For example, cell- and site-specific models could be considered to improve performance.

[0257] Thus, CSI feedback improvement can be broadly classified into two categories: CSI compression and CSI prediction, and the proposals described below can be mainly related to CSI compression.

[0258] Figure 18 is a diagram to explain the concept of AI / ML-based CSI compression.

[0259] Referring to Figure 18, CSI compression can follow a two-sided model (from an inference perspective), where the UE and the base station each have their own AI / ML models and operate as a pair. For convenience, the UE model is referred to as the AI-encoder, and the base station model is referred to as the AI-decoder.

[0260] The UE uses measured / estimated channel information (e.g., raw channel matrix or precoder type channel information vector (e.g., eigenvector)) as input to the AI-encoder, which generates output, quantizes it, and feeds it back to the base station as AI / ML-based CSI.

[0261] The base station dequantizes AI / ML-based CSI fed back from the UE and uses it as input to an AI decoder to recover the output CSI. This CSI process compresses the channel information that the UE must send through AI / ML, reducing feedback overhead. This process is called CSI compression.

[0262] In the current NR standard, when reporting CSI feedback based on legacy codebooks (e.g., non-AI / ML-based CSI), the UE's CQI and RI are determined based on a precoding matrix corresponding to the PMI calculated by the UE. The base station transmits DL data to the UE based on the CQI / RI / PMI received from the UE.

[0263] On the other hand, when CSI compression feedback is based on the AI / ML two-sided model, it is difficult to calculate CQI / RI because information about the AI / ML model output on the UE side cannot be directly applied as PMI.

[0264] The following options may be considered to address these issues:

[0265] (i) Option 1: CQI is not calculated based on the output of the CSI reconstruction part from the actual channel estimation.

[0266] - Option 1a: CQI is calculated based on target CSI using actual channel measurements.

[0267] - Option 1b: CQI is calculated based on target CSI using actual channel measurements and potential adjustments.

[0268] - Option 1c: CQI is calculated based on the existing codebook.

[0269] (ii) Option 2: CQI is calculated based on the output of the CSI reconstruction part from the actual channel estimation.

[0270] - Option 2a: CQI is calculated based on the CSI reconstruction output if a CSI reconstruction model is available at the UE and the UE can perform reconstruction model inference using potential adjustments. The CSI reconstruction part of the UE may differ from the actual CSI reconstruction part used by the NW.

[0271] -Option 2b: CQI is calculated through a two-step approach, where the UE derives the CQI using the precoded CSI-RS transmitted based on the reconstructed precoder.

[0272] Other options may be used. However, regarding the above options, the gap between the UE-side CQI calculation results and the NW (network)-side results must be considered, and their impact on scheduling performance must be considered. CQI calculation complexity and potential RS / signaling overhead must also be considered.

[0273] In CSI compression using a two-sided AI / ML model, there are two options to determine CQI (and / or RI), and the distinction between each option can be based on whether the CSI encoding part on the UE side as well as the CSI reconstruction part on the NW side are available on the UE side.

[0274] For Option 1, there is a method that does not rely on the CSI reconstruction part, such as calculating CQI through target CSI through actual channel measurement or relying on a legacy codebook, but this has a mismatch issue with the CSI applied to the AI / ML model.

[0275] For Option 2, the CSI reconstruction part can be available to the UE, or a predetermined proxy model(s) known to both the UE side and the NW side can be utilized as the CSI reconstruction part. In terms of performance, it is most advantageous if the CSI reconstruction part can be used in the UE, but there is a signaling overhead issue for transmitting the CSI reconstruction part configured in the NW side to the UE, and even if the information is transmitted, problems may arise in terms of computational complexity, storage, and power consumption for deriving the CQI on the UE side. If proxy model(s) are used, these problems can be resolved to some extent, but there is a reliability issue for the CQI derived by applying the proxy model(s).

[0276] As a solution to these problems, knowledge distillation, as shown in Figure 19, can be considered among methods for reducing the complexity of AI / ML models.

[0277] The knowledge distillation technique illustrated in Figure 19 involves a teacher model and a student model sharing the same dataset. The teacher model is relatively complex but boasts high inference accuracy. The student model mimics the teacher model, although it has lower processing complexity (e.g., occupies relatively fewer AI processing units and / or has a relatively small number of model layers). To achieve inference and / or feature activation as similar as possible to the teacher model, certain knowledge about the teacher model's structure (e.g., feature-based knowledge, response-based knowledge, relation-based knowledge, etc.) is extracted and transferred to the student model. The student model is trained using this knowledge.

[0278] Figure 20 is a diagram to explain the concept of feature-based knowledge in the knowledge distillation technique.

[0279] Feature-based knowledge means that the student model can perform AI / ML model operations (e.g., feature activation) as similarly as possible to the teacher model's layer / parameter configuration.

[0280] For example, a feature can refer to a specific pattern or attribute extracted by a model from input data (e.g., an image or text), while activation can indicate the degree to which a model's node is activated in response to a specific feature of the input data. Consequently, feature activation refers to the process by which a specific layer or node in an AI / ML model becomes activated in response to a specific feature of the input data. It plays a crucial role in helping the model learn and express useful features from the input data. Feature activation information can indicate which features the model primarily operates on, which can be used to analyze the model's performance or remove unnecessary features to improve efficiency.

[0281] Referring to Figure 20, learning is done in the direction of minimizing the loss for feature-based knowledge (e.g., the difference in feature activation between the teacher model and the student model).

[0282] Response-based knowledge focuses on the output layer of the teacher model, allowing the student model to learn based on the teacher model's output. Examples include the similarity between the target CSI and the model output, or the gap / threshold.

[0283] In the knowledge distillation technique, rather than simply passing the input for training and the corresponding output to the student model and having the student model perform model training based on this, it has an advantage in terms of signaling overhead due to passing the dataset for training purposes and computational complexity for model learning because it can similarly configure the inference / feature activation of the teacher model based on the passed knowledge.

[0284] Accordingly, this specification proposes a method of utilizing knowledge distillation techniques for CQI determination in CSI compression based on a two-sided AI / ML model.

[0285] According to the proposed embodiments, for CQI determination, the NW side CSI reconstruction part is not directly transmitted to the UE, but knowledge of the corresponding information is transmitted, so there is an overhead reduction effect, and on the UE side, a model similar to the NW side CSI reconstruction part is constructed and operated based on the knowledge, so high AI / ML model performance can be maintained.

[0286] The proposals described below do not necessarily have to be implemented independently, but may be implemented at least partially in combination.

[0287] Proposal 1

[0288] Based on one embodiment, a CQI determination method based on the knowledge distillation method for a two-sided AI / ML CSI compression model is proposed. For this purpose, at least some of the following steps may be implemented.

[0289] (1) Step 1. Set the 'NW side CSI reconstruction part' set through training as the first AI / ML model.

[0290] NW can configure / train a first AI / ML model that performs CSI restoration. For example, the first AI / ML model can be trained using a data set shared with a second AI / ML model of the terminal described below.

[0291] (2) Step 2. Assistance information for CQI determination related to the first AI / ML model (e.g., feature activation information, output response information, proxy model index information, etc.) is transmitted to the UE side.

[0292] For example, the NW may transmit assistance information (e.g., knowledge distillation) related to training of the first AI / ML model to the UE. The assistance information may include, but is not limited to, at least one of feature activation information, output response information, and proxy model index information.

[0293] For example, assistance information may be transmitted as 'additional condition information' through training information transmitted by the NW (in case of separate training), or the UE side may separately request assistance information from the NW side for CQI determination.

[0294] Meanwhile, to generate / provide assistance information for CQI determination, the NW-side may require (at least) capability information regarding the AI / ML model structure and associated additional condition application methods for the UE's second AI / ML model. Accordingly, the UE can provide this information to the network via a UE capability report.

[0295] Depending on the method of assistance information, it is possible to align and operate the (at least) model structures for the first AI / ML model and the second AI / ML model.

[0296] In an embodiment where CQI determination is performed using proxy model(s) that the UE side and the NW side have agreed upon in advance, the NW can instruct the UE to select a specific proxy model based on similarity with a predetermined metric (e.g., feature activation perspective, etc.) with respect to the first AI / ML model, and additional condition information can be included in the instruction.

[0297] (3) Step 3. Configure the ‘UE-side CSI reconstruction part’ (hereinafter referred to as the second AI / ML model) using the assistance information for the transmitted CQI determination.

[0298] The UE can train a second AI / ML model based on the assistance information.

[0299] When training a second AI / ML model based on assistance information for CQI determination, if the similarity (in terms of feature activation) with the first AI / ML model is below a certain level or if it is determined that the structure and configuration of the second AI / ML model cannot configure the feature activation of the first AI / ML model (e.g., low-end UE), a CQI value determination method based on a legacy codebook (e.g., non-AI / ML model) may be used as a fallback operation.

[0300] CQI determination prior to the second AI / ML model being constructed / trained can be based on target CSI with realistic channel measurements, configured with values ​​based on legacy codebooks, or omitted.

[0301] Meanwhile, the UE may include an indicator indicating whether the CQI value it reports is a value determined based on the CSI reconstruction part. And / or, it may report accuracy information regarding the CSI reconstruction part and / or the CQI determined based on the CSI reconstruction part.

[0302] As described above, a procedure for exchanging capability information regarding the configuration of the first AI / ML model and the second AI / ML model and whether assistance information (for performing knowledge distillation operations) is applied can be defined.

[0303] Let us look at more specific examples of Proposal 1.

[0304] Proposal 1 is a method for performing CQI determination based on the CSI reconstruction part in a two-sided AI / ML CSI compression model. Rather than simply transmitting the NW-side CSI reconstruction part to the UE side, this method utilizes a knowledge distillation method to perform operations similar to the corresponding CSI reconstruction part while reducing the signaling overhead associated with the exchange / transfer of the corresponding part.

[0305] (1) In Step 1, the CSI generation part of the UE side and the CSI reconstruction part of the NW side can be configured through a predetermined training method (e.g., joint / separate training).

[0306] On the UE side, the 'NW side CSI reconstruction part' is not currently known. Therefore, for CQI determination from the UE perspective, it is necessary to obtain information on the NW side CSI reconstruction part. At this time, rather than operating by directly receiving the CSI reconstruction part from the NW side, the knowledge distillation method can be applied, in which case the NW side CSI reconstruction part can be utilized as the first AI / ML model (teacher model). The 'UE-side CSI reconstruction part' can be configured as the second AI / ML model (student model) to be as similar as possible to the CSI reconstruction part on the NW side or can be configured to produce similar outputs. To this end, as in (2) Step 2, the NW can extract additional condition information for model training, such as the configuration method of the 'CSI reconstruction part' on the NW side and / or feature activation, output response, etc., and transmit this as training information to the UE side. Alternatively, the UE can separately request the feature activation and output response information from the NW side for CQI determination.

[0307] Meanwhile, in order to generate assistance information to be transmitted from the first AI / ML model to the second AI / ML model, (at least) capability information on the AI / ML model structure and the method of applying the related assistance information for the second AI / ML model on the UE side may be required.

[0308] In an embodiment where the UE / NW side performs CQI determination by utilizing proxy model(s) known in advance, the NW can indicate a specific proxy model by determining the similarity between the first AI / ML model and the corresponding proxy model(s) in terms of feature activation, and the indication can be configured as assistance information and transmitted to the UE side.

[0309] (3) In Step 3, the UE can use the assistance information for CQI determination of the first AI / ML model received from the NW side to train the student model, the 'UE side CSI reconstruction part' (second AI / ML model), so that it can perform inference or feature activation similar to the first AI / ML model.

[0310] If the similarity (in terms of feature activation) between the second AI / ML model and the first AI / ML model is below a certain level when the second AI / ML model performs training, or if it is determined that the structure and configuration of the second AI / ML model cannot configure the feature activation of the first AI / ML model (e.g. low-end UE), the CQI can be configured by applying another method, such as utilizing the CQI value based on the legacy codebook as a fallback operation.

[0311] Before training the second AI / ML model based on assistance information for CQI determination is completed, the UE's CQI determination may be pre-defined, based on target CSI with realistic channel measurement, configured with values ​​based on legacy codebook, or CQI determination may be omitted.

[0312] The CSI report may include an indicator indicating whether the CQI value reported by the UE is a value determined based on the CSI reconstruction part as described above. Furthermore, the UE may configure the CSI report to include accuracy information of the configured CSI reconstruction part, such as the similarity with assistance information received from the first AI / ML model, to indicate the degree of accuracy with which the corresponding CQI is derived.

[0313] Proposal 2

[0314] Proposal 1 examines CQI determination based on a knowledge distillation method for a two-sided AI / ML CSI compression model. Proposal 2 proposes a CQI performance monitoring method related to this CQI determination.

[0315] At least one of the following two cases can be considered in relation to CQI performance monitoring:

[0316] (Case 1) When the difference between the CQI estimated / determined at the terminal and the CQI on the NW side is above a certain level.

[0317] For example, the CQI on the NW-side can be calculated using a PMI based on a codebook according to the legacy method, or through a proxy (encoder) model on the NW-side.

[0318] (Case 2) When the accuracy information included in the CSI report for the CQI estimated / determined at the terminal is below a certain level.

[0319] For example, Accuracy can be the assistance information (knowledge) passed from the first AI / ML model and the distillation loss information of the second AI / ML model.

[0320] For cases like the above, at least one of the following options can be used.

[0321] (1) Option A. As a fallback operation, the UE may operate in a non-AI / non-compressed CSI report manner without applying the CQI determination method of Proposal 1, or may perform AI-compressed CSI report but perform CQI determination based on the legacy codebook.

[0322] - For Case 1, the NW side can signal the UE side to perform fallback operation. And / or the UE can report to the NW including an indicator of how it calculated the CQI (whether or not to perform fallback).

[0323] - For Case 2, the subsequent CQI may be (always) calculated via fallback operation, or the UE may report the CSI to the NW including an indicator of how the CQI was calculated.

[0324] (2) Option B. Subsequent operations for the second AI / ML model can be performed using the threshold(s) for the CQI difference of Case 1 and / or the accuracy level of Case 2.

[0325] For example, if the monitored performance is below the threshold(s) based on the CQI difference in Case 1 and / or the accuracy level in Case 2, the following follow-up actions may be performed. The follow-up actions to be performed may include, but are not limited to, at least one of the following:

[0326] - Action 1: Fallback action similar to Option A

[0327] - Action 2: Perform fine-tuning actions or re-training actions

[0328] - Action 3: Model transfer action

[0329] For example, multiple thresholds may be set, and different operation(s) may be set / defined for each threshold interval. For example, a first operation may be performed for the interval between a first threshold and a second threshold, and a second operation may be performed for the interval between a second threshold and a third threshold.

[0330] For example, the above options can be executed based on a specific x number of instances where the case occurs during a specific time duration.

[0331] Let us look at more specific examples of Proposal 2.

[0332] Proposal 2 is a CQI performance monitoring method in a situation where the CSI reconstruction part is configured / trained on the UE side (in the same manner as Proposal 1). For example, since the CQI performance calculated by the knowledge distillation-based operation in Proposal 1 may deteriorate, a monitoring method for this is required. The deterioration of CQI performance may include a case where the difference between the estimated CQI value on the UE side and the CQI value on the NW side exceeds a certain level, or a case where the second AI / ML model described in Proposal 1 reports accuracy information (e.g., accuracy information based on the similarity with the first AI / ML model) along with the CQI, and the value of the accuracy information is below a certain level. In this case, the reliability of the CQI determination in the CSI reconstruction part of the UE cannot be guaranteed, and therefore a certain fallback operation may be performed. As an example of the fallback operation, the UE may determine and report the CQI using a legacy codebook.

[0333] In Case 1, the NW side can determine the error, so the NW side can signal the UE side to perform fallback operation.

[0334] For Case 2, subsequent CQI reports may be pre-defined to apply values ​​derived through the fallback method, or the UE may report the CQI by including an indicator of whether or not fallback operation is performed.

[0335] As in Option B, a method of setting multiple thresholds for each case and performing subsequent actions according to the level of error corresponding to the threshold may also be used. For example, for two thresholds T1 and T2, (T1 <T2), CQI 값의 오차가 T1과 T2 사이인 경우 NW side에서는 제1 AI / ML 모델로부터 assistance 정보 추출 방식 혹은 accuracy 수준 등에 대한 modification을 거쳐 이를 다시 UE side로 전달할 수 있다. 이를 수신한 UE-side에서는 제2 AI / ML 모델을 다시 training 할 수 있다. 만약, 이러한 assistance 정보 전달 횟수가 특정 duration 동안 특정 n번 발생하면 Option A에서의 fallback 동작이 수행될 수도 있다.

[0336] Meanwhile, threshold T1 and T2 values ​​can be set / indicated to be the same / different. Alternatively, threshold T1 and T2 can be preset values, or the threshold for T2 can be changed and instructed based on the degree of similarity between the first AI / ML model and the second AI / ML model. In addition, the above options can also operate based on a specific x number of instances(s) in which the corresponding case occurs during a specific time duration.

[0337] Figure 21 is a diagram for explaining the operation of a terminal and a network according to one implementation.

[0338] Referring to FIG. 21, a terminal may transmit a UE capability report to the network (2105). The UE capability report may include information indicating that the terminal supports a second AI / ML model (e.g., a student model) for CSI restoration, for example, information indicating that the terminal supports training of the second AI / ML model (e.g., training based on knowledge distillation).

[0339] The network can train a first AI / ML model (e.g., teach model) for CSI restoration (2110).

[0340] The network can provide various configuration information to the terminal via upper-layer signaling (2115). The configuration information may include first AI / ML model information. The first AI / ML model information may include information (e.g., knowledge) regarding the results of training the first AI / ML model in the network.

[0341] The terminal can train a second AI / ML model based on the first AI / ML model information (2120).

[0342] The terminal may generate compressed channel information in the TSF domain (2125). For example, the terminal may generate compressed channel information in the TSF domain in a third AI / ML model (e.g., a UE-side AI / ML model for CSI generation).

[0343] The terminal can restore CSI from the second AI / ML model based on the compressed channel information (2130). For example, the terminal can restore CSI by inputting the compressed channel information and past CSI into the second AI / ML model.

[0344] The terminal can generate a CQI (2135). For example, the terminal can calculate / generate a CQI using the restored CSI in the second AI / ML model.

[0345] The terminal may transmit a CSI report including CQI to the network (2140). The CSI report may include compressed channel information in the TSF domain.

[0346] The network can restore CSI from the first AI / ML model based on the CSI report (2145). The network can restore CSI by inputting compressed channel information and past CSI from the TSF domain into the first AI / ML model.

[0347] Figure 22 illustrates a flow of a method performed by a terminal in a wireless communication system according to one embodiment.

[0348] Referring to FIG. 22, the terminal can receive first AI / ML (artificial intelligence / machine learning) model information from the network, which includes information on the results of training the first AI / ML (artificial intelligence / machine learning) model for CSI (channel state information) reconstruction in the network (2205).

[0349] The terminal can train a second AI / ML model for CSI restoration in the terminal based on the first AI / ML model information (2210).

[0350] The terminal can obtain a CQI (channel quality indicator) based on the first CSI restored from the trained second AI / ML model (2215).

[0351] The terminal can transmit a CSI report including the CQI to the network (2220).

[0352] The second AI / ML model can restore the first CSI based on compressed channel information.

[0353] The terminal can obtain the compressed channel information based on the third AI / ML model set in the terminal.

[0354] The above CSI report may include the compressed channel information.

[0355] The second AI / ML model may have lower complexity than the first AI / ML model.

[0356] Information about the result of training the first AI / ML model may include feature activation information or output response information of the first AI / ML model.

[0357] The CSI report may include at least one of information indicating that the CQI was obtained from the second AI / ML model or information regarding the accuracy of the CQI.

[0358] The terminal may report to the network that it has the terminal capability to train the second AI / ML model based on the first AI / ML model information.

[0359] The above first AI / ML model may be a Teacher Model in the Knowledge Distillation technique, and the above second AI / ML model may be a Student Model that compresses the Teacher Model.

[0360] Figure 23 illustrates a flowchart of a method performed by a network node in a wireless communication system according to one embodiment. The network node may be, but is not limited to, a base station.

[0361] The network node can train a first AI / ML (artificial intelligence / machine learning) model for CSI (channel state information) reconstruction (2305).

[0362] The network node can transmit first AI / ML model information including information on the result of training the first AI / ML model to the terminal (2310).

[0363] The network node can receive a CSI report including a CQI (channel quality indicator) output from the second AI / ML model of the terminal from the terminal (2315).

[0364] The above second AI / ML model may be an AI / ML model for CSI restoration in the terminal.

[0365] The above network node can transmit the first AI / ML model information to the terminal for training the second AI / ML model.

[0366] The above CSI report may include compressed channel information.

[0367] The compressed channel information may be generated based on a third AI / ML model set in the terminal.

[0368] The above network node can restore CSI by inputting the compressed channel information into the first AI / ML model.

[0369] The second AI / ML model may have lower complexity than the first AI / ML model.

[0370] Information about the result of training the first AI / ML model may include feature activation information or output response information of the first AI / ML model.

[0371] The CSI report may include at least one of information indicating that the CQI was obtained from the second AI / ML model or information regarding the accuracy of the CQI.

[0372] The base station may receive information from the terminal indicating that the terminal has terminal capability to train the second AI / ML model based on the first AI / ML model information.

[0373] The above first AI / ML model may be a Teacher Model in the Knowledge Distillation technique, and the above second AI / ML model may be a Student Model that compresses the Teacher Model.

[0374] Fig. 24 illustrates a communication system (1) applicable to the present disclosure.

[0375] Referring to FIG. 24, a communication system (1) includes a wireless device, a base station, and a network. Here, the wireless device refers to a device that performs communication using a wireless access technology (e.g., 5G NR (New RAT), LTE (Long Term Evolution)) and may be referred to as a communication / wireless / 5G device. Although not limited thereto, the wireless device may include a robot (100a), a vehicle (100b-1, 100b-2), an XR (eXtended Reality) device (100c), a hand-held device (100d), a home appliance (100e), an IoT (Internet of Things) device (100f), and an AI device / server (400). For example, the vehicle may include a vehicle equipped with a wireless communication function, an autonomous vehicle, a vehicle capable of performing vehicle-to-vehicle communication, etc. Here, the vehicle may include an Unmanned Aerial Vehicle (UAV) (e.g., a drone). XR devices include AR (Augmented Reality) / VR (Virtual Reality) / MR (Mixed Reality) devices, and can be implemented in the form of HMD (Head-Mounted Device), HUD (Head-Up Display) installed in a vehicle, television, smartphone, computer, wearable device, home appliance, digital signage, vehicle, robot, etc. Mobile devices can include smartphone, smart pad, wearable device (e.g., smart watch, smart glass), computer (e.g., laptop, etc.), etc. Home appliances can include TV, refrigerator, washing machine, etc. IoT devices can include sensors, smart meters, etc. For example, base stations and networks can also be implemented as wireless devices, and a specific wireless device (200a) can act as a base station / network node to other wireless devices.

[0376] Wireless devices (100a to 100f) can be connected to a network (300) via a base station (200). Artificial Intelligence (AI) technology can be applied to the wireless devices (100a to 100f), and the wireless devices (100a to 100f) can be connected to an AI server (400) via the network (300). The network (300) can be configured using a 3G network, a 4G (e.g., LTE) network, a 5G (e.g., NR) network, etc. The wireless devices (100a to 100f) can communicate with each other via the base station (200) / network (300), but can also communicate directly (e.g., sidelink communication) without going through the base station / network. For example, vehicles (100b-1, 100b-2) can communicate directly (e.g., V2V (Vehicle to Vehicle) / V2X (Vehicle to Everything) communication). In addition, IoT devices (e.g., sensors) can communicate directly with other IoT devices (e.g., sensors) or other wireless devices (100a to 100f).

[0377] Wireless communication / connection (150a, 150b, 150c) can be established between wireless devices (100a~100f) / base stations (200), and base stations (200) / base stations (200). Here, wireless communication / connection can be achieved through various wireless access technologies (e.g., 5G NR) such as uplink / downlink communication (150a), sidelink communication (150b) (or, D2D communication), and communication between base stations (150c) (e.g., relay, IAB (Integrated Access Backhaul). Through wireless communication / connection (150a, 150b, 150c), wireless devices and base stations / wireless devices, and base stations and base stations can transmit / receive wireless signals to each other. For example, wireless communication / connection (150a, 150b, 150c) can transmit / receive signals through various physical channels. To this end, at least some of various configuration information setting processes for transmitting / receiving wireless signals, various signal processing processes (e.g., channel encoding / decoding, modulation / demodulation, resource mapping / demapping, etc.), and resource allocation processes can be performed based on various proposals of the present disclosure.

[0378] Figure 25 illustrates a wireless device applicable to the present disclosure.

[0379] Referring to FIG. 25, the first wireless device (100) and the second wireless device (200) can transmit and receive wireless signals through various wireless access technologies (e.g., LTE, NR). Here, {the first wireless device (100), the second wireless device (200)} can correspond to {the wireless device (100x), the base station (200)} and / or {the wireless device (100x), the wireless device (100x)} of FIG. 24.

[0380] A first wireless device (100) includes one or more processors (102) and one or more memories (104), and may further include one or more transceivers (106) and / or one or more antennas (108). The processor (102) controls the memories (104) and / or the transceivers (106), and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document. For example, the processor (102) may process information in the memory (104) to generate first information / signal, and then transmit a wireless signal including the first information / signal via the transceiver (106). In addition, the processor (102) may receive a wireless signal including second information / signal via the transceiver (106), and then store information obtained from signal processing of the second information / signal in the memory (104). The memory (104) may be connected to the processor (102) and may store various information related to the operation of the processor (102). For example, the memory (104) may perform some or all of the processes controlled by the processor (102), or may store software code including commands for performing the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this document. Here, the processor (102) and the memory (104) may be part of a communication modem / circuit / chip designed to implement a wireless communication technology (e.g., LTE, NR). The transceiver (106) may be connected to the processor (102) and may transmit and / or receive wireless signals via one or more antennas (108). The transceiver (106) may include a transmitter and / or a receiver. The transceiver (106) may be used interchangeably with an RF (Radio Frequency) unit. In the present disclosure, a wireless device may also mean a communication modem / circuit / chip.

[0381] The second wireless device (200) includes one or more processors (202), one or more memories (204), and may further include one or more transceivers (206) and / or one or more antennas (208). The processor (202) controls the memories (204) and / or the transceivers (206), and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document. For example, the processor (202) may process information in the memory (204) to generate third information / signals, and then transmit a wireless signal including the third information / signals via the transceivers (206). Furthermore, the processor (202) may receive a wireless signal including fourth information / signals via the transceivers (206), and then store information obtained from signal processing of the fourth information / signals in the memory (204). The memory (204) may be connected to the processor (202) and may store various information related to the operation of the processor (202). For example, the memory (204) may perform some or all of the processes controlled by the processor (202), or may store software code including commands for performing the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this document. Here, the processor (202) and the memory (204) may be part of a communication modem / circuit / chip designed to implement wireless communication technology (e.g., LTE, NR). The transceiver (206) may be connected to the processor (202) and may transmit and / or receive wireless signals via one or more antennas (208). The transceiver (206) may include a transmitter and / or a receiver. The transceiver (206) may be used interchangeably with an RF unit. In the present disclosure, a wireless device may also mean a communication modem / circuit / chip.

[0382] Hereinafter, the hardware elements of the wireless device (100, 200) will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors (102, 202). For example, one or more processors (102, 202) may implement one or more layers (e.g., functional layers such as PHY, MAC, RLC, PDCP, RRC, SDAP). One or more processors (102, 202) may generate one or more Protocol Data Units (PDUs) and / or one or more Service Data Units (SDUs) according to the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this document. One or more processors (102, 202) may generate messages, control information, data, or information according to the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this document. One or more processors (102, 202) can generate signals (e.g., baseband signals) including PDUs, SDUs, messages, control information, data or information according to the functions, procedures, proposals and / or methods disclosed herein, and provide the signals to one or more transceivers (106, 206). One or more processors (102, 202) can receive signals (e.g., baseband signals) from one or more transceivers (106, 206) and obtain PDUs, SDUs, messages, control information, data or information according to the descriptions, functions, procedures, proposals, methods and / or operational flowcharts disclosed herein.

[0383] One or more processors (102, 202) may be referred to as a controller, a microcontroller, a microprocessor, or a microcomputer. One or more processors (102, 202) may be implemented by hardware, firmware, software, or a combination thereof. For example, one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), one or more Digital Signal Processing Devices (DSPDs), one or more Programmable Logic Devices (PLDs), or one or more Field Programmable Gate Arrays (FPGAs) may be included in one or more processors (102, 202). The descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document may be implemented using firmware or software, and the firmware or software may be implemented to include modules, procedures, functions, etc. The descriptions, functions, procedures, suggestions, methods and / or operation flowcharts disclosed in this document may be implemented using firmware or software configured to perform one or more processors (102, 202) or stored in one or more memories (104, 204) and executed by one or more processors (102, 202). The descriptions, functions, procedures, suggestions, methods and / or operation flowcharts disclosed in this document may be implemented using firmware or software in the form of codes, instructions and / or sets of instructions.

[0384] One or more memories (104, 204) may be coupled to one or more processors (102, 202) and may store various forms of data, signals, messages, information, programs, codes, instructions, and / or commands. The one or more memories (104, 204) may be configured as ROM, RAM, EPROM, flash memory, hard drives, registers, cache memory, computer-readable storage media, and / or combinations thereof. The one or more memories (104, 204) may be located internally and / or externally to the one or more processors (102, 202). Additionally, the one or more memories (104, 204) may be coupled to the one or more processors (102, 202) via various technologies, such as wired or wireless connections.

[0385] One or more transceivers (106, 206) can transmit user data, control information, wireless signals / channels, etc., as mentioned in the methods and / or flowcharts of this document, to one or more other devices. One or more transceivers (106, 206) can receive user data, control information, wireless signals / channels, etc., as mentioned in the descriptions, functions, procedures, proposals, methods and / or flowcharts of this document, from one or more other devices. For example, one or more transceivers (106, 206) can be connected to one or more processors (102, 202) and can transmit and receive wireless signals. For example, one or more processors (102, 202) can control one or more transceivers (106, 206) to transmit user data, control information, or wireless signals to one or more other devices. Additionally, one or more processors (102, 202) may control one or more transceivers (106, 206) to receive user data, control information, or wireless signals from one or more other devices. Additionally, one or more transceivers (106, 206) may be coupled to one or more antennas (108, 208), and one or more transceivers (106, 206) may be configured to transmit and receive user data, control information, wireless signals / channels, or the like, as referred to in the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed herein, via one or more antennas (108, 208). In this document, one or more antennas may be multiple physical antennas or multiple logical antennas (e.g., antenna ports). One or more transceivers (106, 206) can convert received user data, control information, wireless signals / channels, etc. from RF band signals to baseband signals in order to process the received user data, control information, wireless signals / channels, etc. using one or more processors (102, 202).One or more transceivers (106, 206) may convert user data, control information, wireless signals / channels, etc. processed by one or more processors (102, 202) from baseband signals to RF band signals. For this purpose, one or more transceivers (106, 206) may include an (analog) oscillator and / or filter.

[0386] Figure 26 illustrates another example of a wireless device applicable to the present disclosure. The wireless device may be implemented in various forms depending on the use case / service (see Figure 24).

[0387] Referring to FIG. 26, the wireless device (100, 200) corresponds to the wireless device (100, 200) of FIG. 25 and may be composed of various elements, components, units / units, and / or modules. For example, the wireless device (100, 200) may include a communication unit (110), a control unit (120), a memory unit (130), and an additional element (140). The communication unit may include a communication circuit (112) and a transceiver(s) (114). For example, the communication circuit (112) may include one or more processors (102, 202) and / or one or more memories (104, 204) of FIG. 25. For example, the transceiver(s) (114) may include one or more transceivers (106, 206) and / or one or more antennas (108, 208) of FIG. 25. The control unit (120) is electrically connected to the communication unit (110), the memory unit (130), and the additional elements (140) and controls the overall operation of the wireless device. For example, the control unit (120) may control the electrical / mechanical operation of the wireless device based on the program / code / command / information stored in the memory unit (130). In addition, the control unit (120) may transmit information stored in the memory unit (130) to an external device (e.g., another communication device) via a wireless / wired interface through the communication unit (110), or store information received from an external device (e.g., another communication device) via a wireless / wired interface in the memory unit (130).

[0388] The additional element (140) may be configured in various ways depending on the type of the wireless device. For example, the additional element (140) may include at least one of a power unit / battery, an input / output unit (I / O unit), a driving unit, and a computing unit. Although not limited thereto, the wireless device may be implemented in the form of a robot (Fig. 24, 100a), a vehicle (Fig. 24, 100b-1, 100b-2), an XR device (Fig. 24, 100c), a portable device (Fig. 24, 100d), a home appliance (Fig. 24, 100e), an IoT device (Fig. 24, 100f), a digital broadcasting terminal, a hologram device, a public safety device, an MTC device, a medical device, a fintech device (or a financial device), a security device, a climate / environmental device, an AI server / device (Fig. 24, 400), a base station (Fig. 24, 200), a network node, etc. Wireless devices may be mobile or stationary depending on the use / service.

[0389] In FIG. 26, various elements, components, units / parts, and / or modules within the wireless device (100, 200) may be entirely interconnected via a wired interface, or at least some may be wirelessly connected via a communication unit (110). For example, within the wireless device (100, 200), the control unit (120) and the communication unit (110) may be wired, and the control unit (120) and a first unit (e.g., 130, 140) may be wirelessly connected via the communication unit (110). In addition, each element, component, unit / part, and / or module within the wireless device (100, 200) may further include one or more elements. For example, the control unit (120) may be composed of a set of one or more processors. For example, the control unit (120) may be composed of a set of a communication control processor, an application processor, an electronic control unit (ECU), a graphics processing processor, a memory control processor, etc. As another example, the memory unit (130) may be composed of RAM (Random Access Memory), DRAM (Dynamic RAM), ROM (Read Only Memory), flash memory, volatile memory, non-volatile memory, and / or a combination thereof.

[0390] Figure 27 illustrates a vehicle or autonomous vehicle applicable to the present disclosure. The vehicle or autonomous vehicle may be implemented as a mobile robot, a car, a train, a manned or unmanned aerial vehicle (AV), a ship, or the like.

[0391] Referring to FIG. 27, a vehicle or autonomous vehicle (100) may include an antenna unit (108), a communication unit (110), a control unit (120), a driving unit (140a), a power supply unit (140b), a sensor unit (140c), and an autonomous driving unit (140d). The antenna unit (108) may be configured as a part of the communication unit (110). Blocks 110 / 130 / 140a to 140d correspond to blocks 110 / 130 / 140 of FIG. 26, respectively.

[0392] The communication unit (110) can transmit and receive signals (e.g., data, control signals, etc.) with external devices such as other vehicles, base stations (e.g., base stations, road side units, etc.), and servers. The control unit (120) can control elements of the vehicle or autonomous vehicle (100) to perform various operations. The control unit (120) can include an ECU (Electronic Control Unit). The drive unit (140a) can drive the vehicle or autonomous vehicle (100) on the ground. The drive unit (140a) can include an engine, a motor, a power train, wheels, brakes, a steering device, etc. The power supply unit (140b) supplies power to the vehicle or autonomous vehicle (100) and can include a wired / wireless charging circuit, a battery, etc. The sensor unit (140c) can obtain vehicle status, surrounding environment information, user information, etc. The sensor unit (140c) may include an IMU (inertial measurement unit) sensor, a collision sensor, a wheel sensor, a speed sensor, an incline sensor, a weight detection sensor, a heading sensor, a position module, a vehicle forward / backward sensor, a battery sensor, a fuel sensor, a tire sensor, a steering sensor, a temperature sensor, a humidity sensor, an ultrasonic sensor, an illuminance sensor, a pedal position sensor, etc. The autonomous driving unit (140d) may implement a technology for maintaining a driving lane, a technology for automatically controlling speed such as adaptive cruise control, a technology for automatically driving along a set path, a technology for automatically setting a path and driving when a destination is set, etc.

[0393] For example, the communication unit (110) can receive map data, traffic information data, etc. from an external server. The autonomous driving unit (140d) can generate an autonomous driving route and driving plan based on the acquired data. The control unit (120) can control the drive unit (140a) so that the vehicle or autonomous vehicle (100) moves along the autonomous driving route according to the driving plan (e.g., speed / direction control). During autonomous driving, the communication unit (110) can irregularly / periodically acquire the latest traffic information data from an external server and can acquire surrounding traffic information data from surrounding vehicles. In addition, during autonomous driving, the sensor unit (140c) can acquire vehicle status and surrounding environment information. The autonomous driving unit (140d) can update the autonomous driving route and driving plan based on newly acquired data / information. The communication unit (110) can transmit information regarding the vehicle location, autonomous driving route, driving plan, etc. to the external server. External servers can predict traffic information data in advance using AI technology or other technologies based on information collected from vehicles or autonomous vehicles, and provide the predicted traffic information data to the vehicles or autonomous vehicles.

[0394] The embodiments described above are combinations of components and features of the present disclosure in a predetermined form. Each component or feature should be considered optional unless explicitly stated otherwise. Each component or feature may be implemented without being combined with other components or features. Furthermore, it is also possible to form embodiments of the present disclosure by combining some components and / or features. The order of operations described in the embodiments of the present disclosure may be changed. Some components or features of one embodiment may be included in another embodiment or may be replaced with corresponding components or features of another embodiment. It is self-evident that claims that do not have an explicit citation relationship in the patent claims may be combined to form embodiments or incorporated as new claims through post-application amendments.

[0395] It will be apparent to those skilled in the art that the present invention can be embodied in other specific forms without departing from the spirit or scope of the invention. Therefore, the above detailed description should not be construed as limiting in any respect, but rather as illustrative. The scope of the present invention should be determined by a reasonable interpretation of the appended claims, and all modifications within the scope of equivalents are intended to be included within the scope of the present invention.

[0396] The present disclosure may be used in a terminal, base station, or other equipment of a wireless mobile communication system.

Claims

1. In a method performed by a terminal, Receiving first AI / ML model information from the network, which includes information on the results of training a first AI / ML (artificial intelligence / machine learning) model for CSI (channel state information) reconstruction in the network; Training a second AI / ML model for CSI restoration in the terminal based on the first AI / ML model information; Obtaining a CQI (channel quality indicator) based on the first CSI restored from the trained second AI / ML model; and A method comprising transmitting a CSI report including the CQI to the network.

2. In paragraph 1, A method in which the second AI / ML model restores the first CSI based on compressed channel information.

3. In paragraph 2, A method further comprising obtaining the compressed channel information based on a third AI / ML model set in the terminal.

4. In paragraph 2, A method wherein the CSI report includes the compressed channel information.

5. In paragraph 1, A method wherein the second AI / ML model has lower complexity than the first AI / ML model.

6. In paragraph 1, A method wherein information on the result of training the first AI / ML model includes feature activation information or output response information of the first AI / ML model.

7. In paragraph 1, A method wherein the CSI report includes at least one of information indicating that the CQI is obtained from the second AI / ML model or information regarding the accuracy of the CQI.

8. In paragraph 1, A method further comprising reporting to the network that the terminal has the capability to train the second AI / ML model based on the first AI / ML model information.

9. In paragraph 1, The above first AI / ML model is a Teacher Model in the Knowledge Distillation technique, A method wherein the second AI / ML model is a Student Model that compresses the Teacher Model.

10. A non-transitory computer-readable recording medium having recorded thereon a program for performing the method described in paragraph 1.

11. In the device, a memory configured to store instructions; and A processor configured to perform operations by executing the above instructions, The operations of the above processor are: Receiving first AI / ML model information from the network, which includes information on the results of training a first AI / ML (artificial intelligence / machine learning) model for CSI (channel state information) reconstruction in the network; Training a second AI / ML model for CSI restoration in the terminal based on the first AI / ML model information; Obtaining a CQI (channel quality indicator) based on the first CSI restored from the trained second AI / ML model; and A device comprising transmitting a CSI report including the CQI to the network.

12. In paragraph 11, Including a transmitter and receiver, The above device is a terminal in a wireless communication system.

13. In paragraph 11, The above device is a processing device configured to control a terminal in a wireless communication system.

14. In a method performed by a base station, Training the first AI / ML (artificial intelligence / machine learning) model for CSI (channel state information) reconstruction; Transmitting first AI / ML model information including information on the result of training the first AI / ML model to the terminal; and Including receiving a CSI report including a CQI (channel quality indicator) output from a second AI / ML model of the terminal from the terminal, The above second AI / ML model is an AI / ML model for CSI restoration in the terminal, A method in which the base station transmits the first AI / ML model information to the terminal for training the second AI / ML model.

15. At the base station, a memory configured to store instructions; and A processor configured to perform operations by executing the above instructions, The operations of the above processor are: Training the first AI / ML (artificial intelligence / machine learning) model for CSI (channel state information) reconstruction; Transmitting first AI / ML model information including information on the result of training the first AI / ML model to the terminal; and Including receiving a CSI report including a CQI (channel quality indicator) output from a second AI / ML model of the terminal from the terminal, The above second AI / ML model is an AI / ML model for CSI restoration in the terminal, A base station that transmits the first AI / ML model information to the terminal for training the second AI / ML model.

Images