Apparatus and method for performing beam management in wireless communication system

Abstract

The objective of the present disclosure is to perform beam management by using a codeword defined in a distance area and an angle area in a wireless communication system. This method may comprise the steps of: determining configuration information related to measurement; transmitting the configuration information to a terminal; transmitting a reference signal to the terminal on the basis of the configuration information; receiving, from the terminal, information related to a measurement result generated on the basis of the reference signal; and transmitting / receiving a first signal to / from the terminal on the basis of the measurement result.

Description

Device and method for performing beam management in a wireless communication system

[0001] The present disclosure relates to a wireless communication system, and more specifically to an apparatus and method for performing beam management in a wireless communication system.

[0002] Wireless access systems are being widely deployed to provide various types of communication services, such as voice and data. Generally, a wireless access system is a multiple access system capable of supporting communication with multiple users by sharing available system resources (bandwidth, transmission power, etc.). Examples of multiple access systems include 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) systems.

[0003] In particular, as many communication devices require large communication capacities, enhanced mobile broadband (eMBB) communication technology is being proposed as an improvement over existing radio access technology (RAT). Furthermore, communication systems are being proposed that consider not only massive machine type communications (mmTC), which connects multiple devices and objects to provide various services anytime and anywhere, but also services and user equipment (UE) that are sensitive to reliability and latency. Various technical configurations are being proposed to achieve this.

[0004] The present disclosure relates to an apparatus and method for performing beam management in a wireless communication system.

[0005] The present disclosure relates to an apparatus and method for performing beam management based on a sub-codebook determined based on an entire codebook in a wireless communication system.

[0006] The present disclosure relates to an apparatus and method for performing beam management based on a hybrid codebook defined for an angle region and a distance region.

[0007] The present disclosure relates to an apparatus and method for performing beam management based on a sparse subcodebook for a distance area of ​​a hybrid codebook.

[0008] The present disclosure relates to an apparatus and method for performing beam management based on a sparse sub-codebook for an angular region of a hybrid codebook.

[0009] The present disclosure relates to an apparatus and method for performing beam management based on sparse subcodebooks for a two-dimensional region of a hybrid codebook.

[0010] The present disclosure relates to an apparatus and method for performing beam management based on measurement results measured based on a subcodebook.

[0011] The present disclosure relates to an apparatus and method for performing beam management based on an artificial intelligence model that takes measurement results as input.

[0012] The present disclosure relates to an apparatus and method for performing beam management using an index-based neural network.

[0013] The present disclosure relates to an apparatus and method for performing beam management using a magnitude-based neural network.

[0014] The present disclosure relates to an apparatus and method for performing beam management based on a joint optimization technique of a codebook and a beam inference function to be used for measurement.

[0015] The present disclosure relates to an apparatus and method for performing beam management using an autoencoder-based neural network.

[0016] The present disclosure relates to an apparatus and method for performing 2-stage beam management.

[0017] The present disclosure relates to an apparatus and method for selecting a beam based on 1-bit feedback.

[0018] The present disclosure relates to an apparatus and method for performing a low-complexity beam management procedure in a very large-scale multi-antenna system.

[0019] The technical objectives to be achieved in this disclosure are not limited to those mentioned above, and other unmentioned technical problems may be considered by those skilled in the art to which the technical configuration of this disclosure applies, based on the embodiments of this disclosure described below.

[0020] As an example of the present disclosure, the method comprises the steps of determining setting information related to measurement, transmitting the setting information to a terminal, transmitting a reference signal to the terminal based on the setting information, receiving information related to a measurement result generated based on the reference signal from the terminal, and transmitting or receiving a first signal to or from the terminal based on the measurement result, wherein the reference signal is transmitted based on a codeword defined for each of an angle area and a distance area, and the first signal may be transmitted or received based on a first beam determined using an artificial intelligence model.

[0021] As an example of the present disclosure, the method comprises the steps of receiving setting information related to measurement from a base station, receiving a reference signal from the base station based on the setting information, performing a measurement based on the reference signal, transmitting information related to the measurement result to the base station, and transmitting or receiving a first signal to or from the base station based on the measurement result, wherein the reference signal is transmitted based on a codeword defined for each of an angle area and a distance area, and the first signal may be transmitted or received based on a first beam determined using an artificial intelligence model.

[0022] As an example of the present disclosure, the device comprises a transceiver and a processor connected to the transceiver, wherein the processor determines setting information related to measurement, transmits the setting information to a terminal, transmits a reference signal to the terminal based on the setting information, receives information related to a measurement result generated based on the reference signal from the terminal, and is configured to transmit or receive a first signal to or from the terminal based on the measurement result, wherein the reference signal is transmitted based on a codeword defined for each of an angle area and a distance area, and the first signal may be transmitted or received based on a first beam determined using an artificial intelligence model.

[0023] As an example of the present disclosure, the device comprises a transceiver and a processor connected to the transceiver, wherein the processor receives setting information related to measurement from a base station, receives a reference signal from the base station based on the setting information, performs a measurement based on the reference signal, transmits information related to the measurement result to the base station, and is configured to transmit or receive a first signal to or from the base station based on the measurement result, wherein the reference signal is transmitted based on a codeword defined for each of an angle area and a distance area, and the first signal may be transmitted or received based on a first beam determined using an artificial intelligence model.

[0024] As an example of the present disclosure, a base station comprises at least one processor and at least one computer memory connected to the at least one processor and storing instructions that direct operations as executed by the at least one processor, wherein the operations include the steps of determining setting information related to measurement, transmitting the setting information to a terminal, transmitting a reference signal to the terminal based on the setting information, receiving information related to a measurement result generated based on the reference signal from the terminal, and transmitting or receiving a first signal to or from the terminal based on the measurement result, wherein the reference signal is transmitted based on a codeword defined for each of an angle area and a distance area, and the first signal may be transmitted or received based on a first beam determined using an artificial intelligence model.

[0025] As an example of the present disclosure, a non-transitory computer-readable medium storing at least one instruction comprises said at least one instruction executable by a processor, said at least one instruction being configured such that a device determines setting information related to a measurement, transmits said setting information to a terminal, transmits said reference signal to the terminal based on said setting information, receives information related to a measurement result generated based on said reference signal from the terminal, and transmits or receives a first signal to or from the terminal based on said measurement result, wherein said reference signal is transmitted based on a codeword defined for each of an angle region and a distance region, and said first signal may be transmitted or received based on a first beam determined using an artificial intelligence model.

[0026] The embodiments of the present disclosure described above are merely some of the preferred embodiments of the present disclosure, and various embodiments reflecting the technical features of the present disclosure can be derived and understood by those skilled in the art based on the detailed description of the present disclosure set forth below.

[0027] The following effects may be achieved by embodiments based on the present disclosure.

[0028] According to the present disclosure, a low-complexity beam management procedure can be performed using an artificial intelligence model.

[0029] The effects obtainable from the embodiments of the present disclosure are not limited to those mentioned above, and other unmentioned effects can be clearly derived and understood by a person skilled in the art to which the technical configuration of the present disclosure applies from the description of the embodiments of the present disclosure below. That is, unintended effects resulting from implementing the configuration described in the present disclosure can also be derived by a person skilled in the art from the embodiments of the present disclosure.

[0030] The drawings attached below are intended to aid in understanding the present disclosure and may provide embodiments of the present disclosure together with the detailed description. However, the technical features of the present disclosure are not limited to specific drawings, and features disclosed in each drawing may be combined with one another to form new embodiments. Reference numerals in each drawing may denote structural elements.

[0031] FIG. 1 illustrates an example of a communication system applicable to the present disclosure.

[0032] FIG. 2 illustrates an example of a wireless device applicable to the present disclosure.

[0033] FIG. 3 illustrates a method for processing a transmission signal applicable to the present disclosure.

[0034] FIG. 4 illustrates a communication procedure between a terminal and a base station applicable to the present disclosure.

[0035] FIG. 5 illustrates an example of a communication structure that can be provided in a 6G (6th generation) system applicable to the present disclosure.

[0036] FIG. 6 illustrates an electromagnetic spectrum applicable to the present disclosure.

[0037] FIG. 7 illustrates a transmitter structure applicable to the present disclosure.

[0038] FIG. 8 illustrates an example of a functional framework for the application of artificial intelligence technology applicable to the present disclosure.

[0039] FIG. 9 illustrates an example of a procedure for utilizing an artificial intelligence model applicable to the present disclosure.

[0040] FIG. 10 illustrates a communication procedure based on artificial intelligence (AI) technology applicable to the present disclosure.

[0041] FIG. 11 illustrates an example of beam management overhead in a very large-scale multi-antenna system according to one embodiment of the present disclosure.

[0042] FIG. 12 illustrates an example of beam management performance in a very large-scale multi-antenna system according to one embodiment of the present disclosure.

[0043] FIG. 13 illustrates an example of a procedure in which a base station performs beam management using some beamforming vectors according to one embodiment of the present disclosure.

[0044] FIG. 14 illustrates an example of a procedure for performing communication using a beam determined by a base station according to one embodiment of the present disclosure.

[0045] FIG. 15 illustrates an example of a hybrid codebook according to one embodiment of the present disclosure.

[0046] FIG. 16 shows that in a hybrid codebook according to one embodiment of the present disclosure, the maximum number of beamforming vectors is K r An example of the 2D receiving beam gain when =4 is illustrated.

[0047] FIG. 17 shows that in a hybrid codebook according to one embodiment of the present disclosure, the maximum number of beamforming vectors is K r An example of the 2D receiving beam gain when =7 is illustrated.

[0048] FIG. 18 shows that in a hybrid codebook according to one embodiment of the present disclosure, the maximum number of beamforming vectors is K a An example of the 2D receiving beam gain when =120 is illustrated.

[0049] FIG. 19 shows that in a hybrid codebook according to one embodiment of the present disclosure, the maximum number of beamforming vectors is K a An example of the 2D receiving beam gain when =160 is illustrated.

[0050] FIG. 20 shows K by applying a two-dimensional region sparse method according to one embodiment of the present disclosure. 2D An example of the 2D receiving beam gain when =4 is illustrated.

[0051] FIG. 21 shows K by applying a two-dimensional region sparse method according to one embodiment of the present disclosure. 2D An example of the 2D receiving beam gain when =3 is illustrated.

[0052] FIG. 22 illustrates an example of a procedure in which a base station determines a beam using an artificial intelligence model according to one embodiment of the present disclosure.

[0053] FIG. 23 illustrates examples of layers of an index-based neural network according to one embodiment of the present disclosure.

[0054] FIG. 24 illustrates an example of the output of an index-based neural network according to one embodiment of the present disclosure.

[0055] FIG. 25 illustrates an example of a procedure in which a base station acquires a total beam gain according to one embodiment of the present disclosure.

[0056] FIG. 26 illustrates examples of layers of a magnitude-based neural network according to one embodiment of the present disclosure.

[0057] FIG. 27 illustrates an example of the output of a magnitude-based neural network according to one embodiment of the present disclosure.

[0058] FIG. 28 illustrates an example of a procedure in which a base station performs 2-stage beam management according to one embodiment of the present disclosure.

[0059] FIG. 29 illustrates an example of a procedure in which a terminal transmits a feedback signal for 2-stage beam management according to one embodiment of the present disclosure.

[0060] FIG. 30 illustrates an example of signaling between a base station and a terminal in a two-stage beam management procedure according to one embodiment of the present disclosure.

[0061] FIG. 31 illustrates an example of a cumulative distribution function of a 2-stage partial search technique using an index-based neural network according to one embodiment of the present disclosure.

[0062] FIG. 32 illustrates an example of a cumulative distribution function of a 2-stage partial search technique using a magnitude-based neural network according to one embodiment of the present disclosure.

[0063] FIG. 33 illustrates an example of an approximation of a beam inference function and an auto-encoder structure according to one embodiment of the present disclosure.

[0064] FIG. 34 illustrates an example of an auto-encoder-based neural network structure according to one embodiment of the present disclosure.

[0065] FIG. 35 illustrates an example of extracting an index indicating angle information using an initial discrete Fourier transform (DFT) search technique according to one embodiment of the present disclosure.

[0066] FIG. 36 illustrates an example of a procedure for acquiring beam-related information based on a ConvLSTM (convolutional long short-term memory) layer according to one embodiment of the present disclosure.

[0067] FIG. 37 illustrates an example of an artificial intelligence model using three ConvLSTM layers according to one embodiment of the present disclosure.

[0068] FIG. 38 illustrates an example of gain performance relative to the signal-to-noise ratio (SNR) of a beam management technique applying only a sparse method and a beam management technique applying an index-based neural network according to one embodiment of the present disclosure.

[0069] FIG. 39 illustrates an example of the performance of the achievement rate relative to the SNR of a beam management technique applying only a sparse method and a beam management technique applying an index-based neural network according to one embodiment of the present disclosure.

[0070] FIG. 40 illustrates an example of normalized gain performance relative to SNR of a beam management technique applying only a sparse method and a beam management technique applying a magnitude-based neural network according to one embodiment of the present disclosure.

[0071] FIG. 41 illustrates an example of the performance of the achievement rate relative to the SNR of a beam management technique applying only a sparse method and a beam management technique applying a magnitude-based neural network according to one embodiment of the present disclosure.

[0072] FIG. 42 illustrates an example of normalized gain performance relative to overhead reduction of a beam management technique applying only a sparse method and a beam management technique applying an index-based neural network according to one embodiment of the present disclosure.

[0073] FIG. 43 illustrates an example of the performance of achievement rate relative to overhead reduction of a beam management technique applying only a sparse method and a beam management technique applying an index-based neural network according to one embodiment of the present disclosure.

[0074] FIG. 44 illustrates an example of normalized gain performance relative to overhead reduction of a beam management technique applying only a sparse method and a beam management technique applying a magnitude-based neural network according to one embodiment of the present disclosure.

[0075] FIG. 45 illustrates an example of the performance of the achievement rate relative to overhead reduction of a beam management technique applying only a sparse method and a beam management technique applying a magnitude-based neural network according to one embodiment of the present disclosure.

[0076] FIG. 46 illustrates an example of normalized gain performance relative to SNR of a beam management technique applying an autoencoder-based neural network according to one embodiment of the present disclosure.

[0077] FIG. 47 illustrates an example of the achievement rate performance relative to SNR of a beam management technique applying an autoencoder-based neural network according to one embodiment of the present disclosure.

[0078] FIG. 48 illustrates an example of normalized gain performance over time of a beam management technique applying ConvLSTM in a spatiotemporal domain according to one embodiment of the present disclosure.

[0079] FIG. 49 illustrates an example of the achievement rate performance over time of a beam management technique applying ConvLSTM in a spatiotemporal domain according to one embodiment of the present disclosure.

[0080] FIG. 50 illustrates an example of normalized gain performance relative to SNR of a beam management technique applying ConvLSTM in the spatiotemporal domain according to one embodiment of the present disclosure.

[0081] FIG. 51 illustrates an example of the achievement rate performance relative to SNR of a beam management technique applying ConvLSTM in a spatiotemporal domain according to one embodiment of the present disclosure.

[0082] FIG. 52 illustrates an example of a wireless device applicable to the present disclosure.

[0083] FIG. 53 illustrates an example of a portable device applicable to the present disclosure.

[0084] FIG. 54 illustrates an example of a vehicle or autonomous vehicle applicable to the present disclosure.

[0085] FIG. 55 illustrates an example of a vehicle applicable to the present disclosure.

[0086] FIG. 56 illustrates an example of an extended reality (XR) device applicable to the present disclosure.

[0087] FIG. 57 illustrates an example of a robot applicable to the present disclosure.

[0088] FIG. 58 illustrates an example of an AI device applicable to the present disclosure.

[0089] The following embodiments are combinations of the components and features of the present disclosure in a predetermined form. Each component or feature may be considered optional unless otherwise explicitly stated. Each component or feature may be implemented in a form not combined with other components or features. Additionally, some components and / or features may be combined to form embodiments of the present disclosure. The order of operations described in the embodiments of the present disclosure may be changed. Some components or features of any embodiment may be included in other embodiments, or may be replaced with corresponding components or features of other embodiments.

[0090] In the description of the drawings, procedures or steps that could obscure the gist of the present disclosure have not been described, nor have procedures or steps that are understandable to those skilled in the art been described.

[0091] Throughout the specification, when a part is described as "comprising" or "including" a component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "...part," "...unit," and "module" as used in the specification refer to a unit that performs at least one function or operation, and this may be implemented in hardware, software, or a combination of hardware and software. Additionally, "one (a or an)," "one," "the," and similar related terms may be used in the context describing the present disclosure (particularly in the context of the following claims) in both singular and plural forms, unless otherwise indicated in the specification or clearly contradicted by the context.

[0092] In this specification, the embodiments of the present disclosure are described with a focus on the data transmission and reception relationship between a base station and a mobile station. Here, the base station refers to a terminal node of a network that communicates directly with a mobile station. Specific operations described in this document as being performed by a base station may, in some cases, be performed by an upper node of the base station.

[0093] That is, in a network consisting of multiple network nodes including a base station, various operations performed for communication with a mobile station may be performed by the base station or other network nodes other than the base station. In this case, 'base station' may be replaced by terms such as fixed station, Node B, eNB (eNode B), gNB (gNode B), ng-eNB, advanced base station (ABS), or access point.

[0094] Additionally, in the embodiments of the present disclosure, the term terminal may be replaced with terms such as user equipment (UE), mobile station (MS), subscriber station (SS), mobile subscriber station (MSS), mobile terminal, or advanced mobile station (AMS).

[0095] Furthermore, the transmitting end refers to a fixed and / or mobile node that provides data or voice services, and the receiving end refers to a fixed and / or mobile node that receives data or voice services. Therefore, in the case of the uplink, a mobile station can be the transmitting end and a base station can be the receiving end. Similarly, in the case of the downlink, a mobile station can be the receiving end and a base station can be the transmitting end.

[0096] Embodiments of the present disclosure may be supported by standard documents disclosed in at least one of the wireless access systems, such as IEEE 802.xx systems, 3GPP (3rd Generation Partnership Project) systems, 3GPP LTE (Long Term Evolution) systems, 3GPP 5G (5th generation) NR (New Radio) systems and 3GPP2 systems, and in particular, embodiments of the present disclosure may be supported by 3GPP TS (technical specification) 38.211, 3GPP TS 38.212, 3GPP TS 38.213, 3GPP TS 38.321 and 3GPP TS 38.331 documents.

[0097] In addition, the embodiments of the present disclosure may be applied to other wireless access systems and are not limited to the systems described above. For example, they may be applicable to systems applied after the 3GPP 5G NR system and are not limited to specific systems.

[0098] That is, obvious steps or parts not described in the embodiments of the present disclosure may be described by referring to the aforementioned documents. Additionally, all terms disclosed in this document may be explained by the aforementioned standard documents.

[0099] Hereinafter, preferred embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. The detailed description disclosed below, together with the accompanying drawings, is intended to describe exemplary embodiments of the present disclosure and is not intended to represent the only embodiment in which the technical configuration of the present disclosure can be implemented.

[0100] Additionally, specific terms used in the embodiments of the present disclosure are provided to aid in understanding the present disclosure, and the use of such specific terms may be modified in other forms without departing from the technical spirit of the present disclosure.

[0101] The following technology can be applied to 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).

[0102] For the sake of clarity, the following description is based on 3GPP communication systems (e.g., LTE, NR, etc.), but the technical scope of this disclosure is not limited thereto. LTE may refer to technology from 3GPP TS 36.xxx Release 8 onwards. Specifically, LTE technology from 3GPP TS 36.xxx Release 10 onwards is referred to as LTE-A, and LTE technology from 3GPP TS 36.xxx Release 13 onwards may be referred to as LTE-A pro. 3GPP NR may refer to technology from TS 38.xxx Release 15 onwards. 3GPP 6G may refer to technology from TS Release 17 and / or Release 18 onwards. "xxx" indicates a specific standard document number. LTE / NR / 6G may be collectively referred to as 3GPP systems.

[0103] Regarding the background technology, terms, abbreviations, etc. used in this disclosure, reference may be made to standard documents published prior to this disclosure. For example, reference may be made to standard documents 36.xxx and 38.xxx.

[0104] Communication systems applicable to the present disclosure

[0105] Although not limited thereto, the various descriptions, functions, procedures, proposals, methods, and / or flowcharts of the disclosure disclosed in this document may be applied to various fields requiring wireless communication / connection (e.g., 5G) between devices.

[0106] Examples are provided in more detail below with reference to the drawings. In the following drawings and descriptions, the same reference numerals may represent the same or corresponding hardware blocks, software blocks, or function blocks unless otherwise described.

[0107] FIG. 1 illustrates an example of a communication system to which the present disclosure applies.

[0108] Referring to FIG. 1, the communication system (100) to which the present disclosure applies includes a wireless device, a base station, and a network. Here, the wireless device refers to a device that performs communication using wireless access technology (e.g., LTE, LTE-A, LTE-A pro, NR, 5G, 5G-A, 6G) 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 Thing) device (100f), and an AI (artificial intelligence) device / server (100g). For example, the vehicle may include a vehicle equipped with wireless communication capabilities, an autonomous vehicle, a vehicle capable of performing inter-vehicle communication, etc. Here, the vehicle (100b-1, 100b-2) may include an unmanned aerial vehicle (UAV) (e.g., a drone). The XR device (100c) includes an augmented reality (AR) / virtual reality (VR) / mixed reality (MR) device and may be implemented in the form of a head-mounted device (HMD), a head-up display (HUD) equipped in a vehicle, a television, a smartphone, a computer, a wearable device, a home appliance, digital signage, a vehicle, a robot, etc. The portable device (100d) may include a smartphone, a smartpad, a wearable device (e.g., a smartwatch, smart glasses), a computer (e.g., a laptop, etc.). The home appliance (100e) may include a TV, a refrigerator, a washing machine, etc. The IoT device (100f) may include a sensor, a smart meter, etc.For example, the base station (120) and network (130) may also be implemented as wireless devices, and a specific wireless device (120a) may act as a base station / network node to other wireless devices.

[0109] Wireless devices (100a to 100f) can be connected to a network (130) through a base station (120). AI technology may be applied to the wireless devices (100a to 100f), and the wireless devices (100a to 100f) can be connected to an AI server (100g) through the network (130). The network (130) can be configured using a 3G network, a 4G (e.g., LTE) network, a 5G (e.g., NR) network, or a 6G network. The wireless devices (100a to 100f) may communicate with each other through the base station (120) / network (130), but may also communicate directly (e.g., sidelink communication) without going through the base station (120) / network (130). For example, vehicles (100b-1, 100b-2) can communicate directly (e.g., V2V (vehicle to vehicle) / V2X (vehicle to everything) communication). Also, an IoT device (100f) (e.g., a sensor) can communicate directly with another IoT device (e.g., a sensor) or other wireless devices (100a to 100f).

[0110] Wireless communication / connection (150a, 150b, 150c) can be established between wireless devices (100a to 100f) / base station (120) and between base station (120) / base station (120). Here, wireless communication / connection can be established through various wireless access technologies 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 / from each other. For example, wireless communication / connection (150a, 150b, 150c) can transmit / receive signals through various physical channels. To this end, based on the various proposals of the present disclosure, at least some of the following may be performed: a process for setting various configuration information for transmitting / receiving wireless signals, a process for various signal processing (e.g., channel encoding / decoding, modulation / demodulation, resource mapping / demapping, etc.), a resource allocation process, etc.

[0111] Devices applicable to the present disclosure

[0112] FIG. 2 illustrates an example of a wireless device that can be applied to the present disclosure.

[0113] Referring to FIG. 2, the wireless device (200) can transmit and receive wireless signals through various wireless access technologies (e.g., LTE, LTE-A, LTE-A pro, NR, 5G, 5G-A, 6G). The wireless device (200) includes at least one processor (202) and at least one memory (204), and may additionally include at least one transceiver (206) and / or at least one antenna (208).

[0114] The processor (202) controls the memory (204) and / or the transceiver (206) and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or sequences of operation disclosed in this document. For example, the processor (202) may process information within the memory (204) to generate a first information / signal and then transmit a wireless signal containing the first information / signal through the transceiver (206). Additionally, the processor (202) may receive a wireless signal containing a second information / signal through the transceiver (206) and then store information obtained from the signal processing of the second information / signal 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, memory (204) may store software code containing instructions for performing some or all of the processes controlled by the processor (202) or for performing the descriptions, functions, procedures, proposals, methods, and / or sequences of operations disclosed in this document. Here, the processor (202) and memory (204) may be part of a communication modem / circuit / chip designed to implement wireless communication technology. A transceiver (206) may be connected to the processor (202) and may transmit and / or receive wireless signals through at least one antenna (208). The transceiver (206) may include a transmitter and / or receiver. The transceiver (206) may be interchangeable with a radio frequency (RF) unit. In this disclosure, a wireless device may mean a communication modem / circuit / chip.

[0115] Hereinafter, hardware elements of the wireless device (200) will be described in more detail. Although not limited thereto, at least one protocol layer may be implemented by at least one processor (202). For example, at least one processor (202) may implement at least one layer (e.g., functional layers such as PHY (physical), MAC (media access control), RLC (radio link control), PDCP (packet data convergence protocol), RRC (radio resource control), and SDAP (service data adaptation protocol). At least one processor (202) may generate at least one PDU (Protocol Data Unit) and / or at least one SDU (service data unit) according to the descriptions, functions, procedures, proposals, methods and / or operation sequences disclosed in this document. At least one processor (202) may generate messages, control information, data, or information according to the descriptions, functions, procedures, proposals, methods and / or operation sequences disclosed in this document. At least one processor (202) may generate a signal (e.g., baseband signal) including a PDU, SDU, message, control information, data, or information according to the functions, procedures, proposals, and / or methods disclosed in this document and provide it to at least one transceiver (206). At least one processor (202) may receive a signal (e.g., baseband signal) from at least one transceiver (206) and may obtain a PDU, SDU, message, control information, data, or information according to the descriptions, functions, procedures, proposals, methods, and / or operation sequences disclosed in this document.

[0116] At least one processor (202) may be referred to as a controller, microcontroller, microprocessor, or microcomputer. At least one processor (202) may be implemented by hardware, firmware, software, or a combination thereof. For example, at least one application-specific integrated circuit (ASIC), at least one digital signal processor (DSP), at least one digital signal processing device (DSPD), at least one programmable logic device (PLD), or at least one field programmable gate array (FPGA) may be included in at least one processor (202). The descriptions, functions, procedures, proposals, methods, and / or operation sequences 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. Firmware or software configured to perform the descriptions, functions, procedures, proposals, methods, and / or operation sequences disclosed in this document may be included in at least one processor (202) or stored in at least one memory (204) and driven by at least one processor (202). The descriptions, functions, procedures, proposals, methods, and / or flowcharts disclosed in this document may be implemented using firmware or software in the form of code, instructions, and / or sets of instructions.

[0117] At least one memory (204) may be connected to at least one processor (202) and may store various forms of data, signals, messages, information, programs, codes, instructions, and / or commands. At least one memory (204) may be composed of ROM (read-only memory), RAM (random access memory), EPROM (erasable programmable read-only memory), flash memory, hard drive, registers, cache memory, computer read storage media, and / or combinations thereof. At least one memory (204) may be located inside and / or outside of at least one processor (202). Additionally, at least one memory (204) may be connected to at least one processor (202) via various technologies, such as wired or wireless connections.

[0118] At least one transceiver (206) may transmit user data, control information, wireless signals / channels, etc., as mentioned in the methods and / or operation flowcharts, etc. of this document to at least one other device. At least one transceiver (206) may receive user data, control information, wireless signals / channels, etc., as mentioned in the descriptions, functions, procedures, proposals, methods and / or operation flowcharts, etc. disclosed in this document from at least one other device. For example, at least one transceiver (206) may be connected to at least one processor (202) and may transmit and receive wireless signals. For example, at least one processor (202) may control at least one transceiver (206) to transmit user data, control information, or wireless signals to at least one other device. Additionally, at least one processor (202) may control at least one transceiver (206) to receive user data, control information, or wireless signals from at least one other device. Additionally, at least one transceiver (206) may be connected to at least one antenna (208), and at least one transceiver (206) may be configured to transmit and receive user data, control information, wireless signals / channels, etc., as described in the descriptions, functions, procedures, proposals, methods, and / or operation sequence diagrams disclosed in this document through at least one antenna (208). In this document, at least one antenna may be a plurality of physical antennas or a plurality of logical antennas (e.g., antenna ports). At least one transceiver (206) may convert the received 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 at least one processor (202). At least one transceiver (206) may convert the processed user data, control information, wireless signals / channels, etc., from baseband signals to RF band signals using at least one processor (202).To this end, at least one transceiver (206) may include an (analog) oscillator and / or filter.

[0119] The components of the wireless device described with reference to FIG. 2 may be referred to by other terms in terms of their function. For example, the processor (202) may be referred to as the control unit, the transceiver (206) as the communication unit, and the memory (204) as the storage unit. In some cases, the communication unit may be used to mean at least a part of the processor (202) and the transceiver (206).

[0120] The structure of the wireless device described with reference to FIG. 2 can be understood as the structure of at least part of various devices. For example, the structure of the wireless device exemplified in FIG. 2 may be at least part of the various devices described with reference to FIG. 1 (e.g., robot (100a), vehicle (100b-1, 100b-2), XR device (100c), portable device (100d), home appliance (100e), IoT device (100f), AI device / server (100g)). Furthermore, according to various embodiments, the device may include other components in addition to the components exemplified in FIG. 2.

[0121] For example, the device may be a portable device such as a smartphone, smartpad, wearable device (e.g., smart watch, smart glasses), or portable computer (e.g., laptop, etc.). In this case, the device may further include at least one of a power supply unit that supplies power and includes a wired / wireless charging circuit, a battery, etc., an interface unit that includes at least one port for connection with another device (e.g., audio input / output port, video input / output port), and an input / output unit for inputting and outputting video information / signals, audio information / signals, data, and / or information input by a user.

[0122] For example, the device may be a mobile device such as a mobile robot, vehicle, train, manned / unmanned aerial vehicle (AV), or ship. In this case, the device may further include at least one of a drive unit comprising at least one of an engine, motor, power train, wheel, brake, and steering device of the device; a power supply unit that supplies power and includes a wired / wireless charging circuit, battery, etc.; a sensor unit that senses state information, environmental information, and user information of the device or its surroundings; an autonomous driving unit that performs functions such as path maintenance, speed control, and destination setting; and a position measurement unit that acquires position information of the moving body through a GPS (global positioning system) and various sensors.

[0123] For example, the device may be an XR device such as an HMD, a HUD (head-up display) equipped in a vehicle, a television, a smartphone, a computer, a wearable device, a home appliance, digital signage, a vehicle, a robot, etc. In this case, the device may further include at least one of a power supply unit that supplies power and includes a wired / wireless charging circuit, a battery, etc., an input / output unit that acquires control information, data, etc. from the outside and outputs a generated XR object, and a sensor unit that senses state information, environment information, and user information of the device or the surroundings of the device.

[0124] For example, the device may be a robot that can be classified into industrial, medical, household, military, etc., depending on the purpose or field of use. In this case, the device may further include at least one of a sensor unit that senses state information, environmental information, and user information of the device or its surroundings, and a drive unit that performs various physical actions, such as moving robot joints.

[0125] For example, the device may be an AI device such as a TV, projector, smartphone, PC, laptop, digital broadcasting terminal, tablet PC, wearable device, set-top box (STB), radio, washing machine, refrigerator, digital signage, robot, vehicle, etc. In this case, the device may further include at least one of an input unit that acquires various types of data from the outside, an output unit that generates output related to sight, hearing, or touch, a sensor unit that senses state information, environmental information, and user information of the device or its surroundings, and a training unit that learns a model composed of an artificial neural network using training data.

[0126] The structure of the wireless device illustrated in FIG. 2 can be understood as part of a RAN node (e.g., base station, DU, RU, RRH, etc.). That is, the device illustrated in FIG. 2 may be a RAN node. In this case, the device may further include a wired transceiver for front haul and / or back haul communication. However, if the front haul and / or back haul communication is based on wireless communication, at least one transceiver (206) illustrated in FIG. 2 is used for front haul and / or back haul communication, and the wired transceiver may not be included.

[0127] FIG. 3 illustrates a method for processing a transmission signal applicable to the present disclosure. For example, the transmission signal may be processed by a signal processing circuit. In this case, the signal processing circuit (300) may include scramblers (310), modulators (320), a layer mapper (330), a precoder (340), resource mappers (350), and signal generators (360). In this case, for example, the operation / function of FIG. 3 may be performed in the processor (202) and / or transceiver (206) of FIG. 2. Also, for example, the hardware elements of FIG. 3 may be implemented in the processor (202) and / or transceiver (206) of FIG. 2. For example, blocks 310 to 360 may be implemented in the processor (202) of FIG. 2. Additionally, blocks 310 to 350 may be implemented in the processor (202) of FIG. 2, and block 360 may be implemented in the transceiver (206) of FIG. 2, and are not limited to the embodiments described above.

[0128] A codeword can be converted into a wireless signal through the signal processing circuit (300) of FIG. 3. Here, the codeword is an encoded bit sequence of an information block. The information block may include a transmission block (e.g., UL-SCH transmission block, DL-SCH transmission block). Here, the information block may include AI-related data (e.g., training data, AI model data, input data, output data, etc.), and the codeword may be an encoded bit sequence corresponding to the AI-related data. The wireless signal may be transmitted through various physical channels (e.g., PUSCH, PDSCH). Specifically, the codeword may be converted into a scrambled bit sequence by scramblers (310). The scrambled sequence used for scrambling is generated based on an initialization value, which may include ID information of the wireless device, etc. The scrambled bit sequence may be modulated into a modulation symbol sequence by modulators (320). Modulation methods may include pi / 2-BPSK (pi / 2-binary phase shift keying), m-PSK (m-phase shift keying), m-QAM (m-quadrature amplitude modulation), etc.

[0129] A complex modulation symbol sequence can be mapped to at least one transmission layer by a layer mapper (330). Here, a transmission layer is a logical resource unit for mapping signals or data transmitted through spatial resources to antenna ports, and one transmission layer can correspond to one stream or one antenna port. Each complex modulation symbol included in the complex modulation symbol sequence is mapped to at least one transmission layer, thereby determining which antenna port it will be transmitted through. The modulation symbols of each transmission layer can be mapped to the corresponding antenna port(s) by a precoder (340). The output z of the precoder (340) can be obtained by multiplying the output y of the layer mapper (330) by an N×M precoding matrix W, where N is the number of antenna ports and M is the number of transmission layers. Here, the precoder (340) can perform precoding after performing transform precoding (e.g., a discrete Fourier transform (DFT)) on the complex modulation symbols. Additionally, the precoder (340) can perform precoding without performing transform precoding.

[0130] Resource mappers (350) can map the modulation symbols of each antenna port to time-frequency resources. The time-frequency resources may include multiple symbols (e.g., CP-OFDMA symbols, DFT-s-OFDMA symbols) in the time domain and multiple subcarriers in the frequency domain. Signal generators (360) generate radio signals from the mapped modulation symbols, and the generated radio signals can be transmitted to other devices through each antenna. To this end, each of the signal generators (360) may include an inverse fast Fourier transform (IFFT) module, a cyclic prefix (CP) inserter, a digital-to-analog converter (DAC), a frequency uplink converter, etc.

[0131] The signal processing process for a received signal in a wireless device can be configured as the inverse of the signal processing process (310 to 360) of FIG. 3. For example, a wireless device (e.g., 200 in FIG. 2) can receive a wireless signal from the outside through an antenna port / transceiver. The received wireless signal can be converted into a baseband signal through a signal restorer. To this end, the signal restorer may include a frequency downlink converter, an analog-to-digital converter (ADC), a CP remover, and a fast Fourier transform (FFT) module. Subsequently, the baseband signal can be restored into a codeword through a resource de-mapper process, a postcoding process, a demodulation process, and a de-scrambling process. The codeword can be restored into the original information block through decoding. Accordingly, a signal processing circuit (not shown) for a received signal may include a signal restorer, a resource de-mapper, a postcoder, a demodulator, a de-scrambler, and a decoder.

[0132] The signal processing circuit (300) described with reference to FIG. 3 is illustrated as including a plurality of scramblers (310), modulators (320), a plurality of resource mappers (350), and a plurality of signal generators (360). However, at least one of the scramblers, modulators, resource mappers, and signal generators may be implemented as a single integrated structure. That is, the number of at least one of the scramblers, modulators, resource mappers, and signal generators may be less than the number of layers. Furthermore, at least one of the components illustrated in FIG. 3 may be omitted.

[0133] FIG. 4 illustrates a communication procedure between a terminal and a base station applicable to the present disclosure. FIG. 4 illustrates the operation of a terminal (410) and a base station (420) transmitting and / or receiving data, and the operation performed prior to this.

[0134] Referring to FIG. 4, in step 401, the terminal (410) and the base station (420) perform synchronization. For example, the terminal (410) performs an initial cell search operation. Specifically, the terminal (410) can detect at least one synchronization signal transmitted from the base station (420) according to a predefined rule. Here, the synchronization signal may include a plurality of synchronization signals (e.g., primary synchronization signal, secondary synchronization signal) classified according to structure or use. Through this, the terminal (410) can identify the boundaries of the frame, subframe, slot, and / or symbol of the base station (420) and obtain information about the base station (420) (e.g., cell identifier).

[0135] In step 403, the terminal (410) obtains system information transmitted from the base station (420). The system information is information related to the attributes, characteristics, and / or capabilities of the base station (420) required to connect to the base station (420) and use the service, and can be classified according to content (e.g., whether it is essential for connection), transmission structure (e.g., channel used, whether it is provided on-demand), etc., and can be classified, for example, into a master information block (MIB) and a system information block (SIB). If necessary, the terminal (410) may transmit a signal requesting the system information prior to receiving the system information. The system information may include information related to AI functions. For example, the system information is information required for operations performed based on AI, and may include at least one of information related to an AI model, information related to training, and information related to inference / prediction. However, the request and provision of the system information may be performed after the random access procedure described later.

[0136] In step 405, the terminal (410) and the base station (420) perform a random access procedure. The terminal (410) may transmit and / or receive at least one message for the random access procedure (e.g., random access preamble, RAR (random access response) message, etc.) based on information related to the random access channel of the base station (420) obtained through system information (e.g., channel location, channel structure, structure of supported preamble, etc.). For example, the terminal (410) may transmit a preamble (e.g., MSG1) through the random access channel, receive a RAR message (e.g., MSG2), transmit a message (e.g., MSG3) containing information related to the terminal (410) (e.g., identification information) to the base station (420) using scheduling information included in the RAR message, and receive a message (e.g., MSG4) for contention resolution and / or connection establishment. As another example, MSG1 and MSG3 can be transmitted and received as a single message, or MSG2 and MSG4 can be transmitted and received as a single message.

[0137] In step 407, the terminal (410) and the base station (420) perform signaling of control information. Here, the control information may be defined in various layers, such as a layer that controls the connection (e.g., a radio resource control (RRC) layer), a layer that handles mapping between logical channels and transmission channels (e.g., a media access control (MAC) layer), and a layer that handles physical channels (e.g., a physical (PHY) layer). For example, the terminal (410) and the base station (420) may perform at least one of signaling to establish a connection, signaling to determine settings related to communication, and signaling to indicate allocated resources. Additionally, the signaling of control information may be performed to convey information related to AI functions. For example, information related to AI functions is information necessary for operations performed based on AI, and may include at least one of information related to an AI model, information related to training, and information related to inference / prediction. More specifically, the information related to the AI ​​function signaled in step 407 can be combined and / or combined with the information related to the AI ​​function signaled in step 403, and both can be defined as having a hierarchical, mutually complementary, or substitute structure.

[0138] In step 409, the terminal (410) and the base station (420) transmit and / or receive data. That is, the terminal (410) and the base station (420) can process, transmit and / or receive data based on the signaling of control information. For example, when transmitting data, the terminal (410) or the base station (420) may perform at least one of channel encoding, rate matching, scrambling, constellation mapping, layer mapping, waveform modulation, antenna mapping, and resource mapping on the information bits. Conversely, when receiving data, the terminal (410) or the base station (420) may perform at least one of signal extraction from resources, antenna-specific waveform demodulation, signal placement considering layer mapping, constellation demapping, descrambling, and channel decoding. Here, the transmitted data is AI-related data, and may include, for example, data for AI-based operations or data generated by AI-based operations.

[0139] Steps 401 through 409 described with reference to FIG. 4 must not necessarily be performed in the order exemplified in FIG. 4, and the order of at least some of the steps may vary. Additionally, at least some of steps 401 through 409 may be combined into a single step or omitted. That is, the steps exemplified in FIG. 4 may be performed in various modified forms.

[0140] 6G communication systems and core implementation technologies of 6G systems

[0141] 5G systems define various operating bands within FR1 (frequency range 1), which includes 410 MHz to 7125 MHz, and FR2 (frequency range 2), which includes 24,250 MHz to 71,000 MHz. Various frequencies are being discussed as operating bands for subsequent 6G systems, and the use of frequencies higher than those of 5G systems is also being considered for wider bandwidth and higher transmission speeds. As one example, the use of the THz (Terahertz) frequency band, which includes approximately 100 GHz to 10 THz, is being discussed. The THz frequency band is a band that possesses both the penetrability of radio waves and the directivity of optical waves, and communication using the THz frequency band is expected to play a transitional role from existing radio-based communication to optical-based communication.

[0142] As such, 6G systems utilizing the THz frequency band aim for i) very high data rates per device, ii) a very large number of connected devices, iii) global connectivity, iv) very low latency, v) reduced energy consumption of battery-free IoT devices, vi) ultra-reliable connectivity, and vii) connected intelligence with machine learning capabilities. The vision of 6G systems can be four aspects such as "intelligent connectivity," "deep connectivity," "holographic connectivity," and "ubiquitous connectivity," and 6G systems can be designed to satisfy requirements such as those shown in [Table 1] below.

[0143] Per device peak data rate1 TbpsE2E latency1 msMaximum spectral efficiency100 bps / HzMobility supportup to 1000 km / hrSatellite integrationFullyAIFullyAutonomous vehicleFullyXRFullyHaptic CommunicationFully

[0144] At this time, the 6G system may have key factors such as enhanced mobile broadband (eMBB), ultra-reliable low latency communications (URLC), massive machine type communications (mMTC), AI integrated communication, tactile internet, high throughput, high network capacity, high energy efficiency, low backhaul and access network congestion, and enhanced data security. FIG. 5 illustrates an example of a communication structure that can be provided by a 6G system applicable to the present disclosure. Referring to FIG. 5, the 6G system is expected to have simultaneous wireless communication connectivity 50 times higher than that of a 5G wireless communication system. URLLC, a key feature of 5G, is expected to become an even more dominant technology in 6G communication by providing end-to-end latency of less than 1ms. In this case, 6G systems will exhibit significantly superior volumetric spectral efficiency, unlike the frequently used area-spectral efficiency. Since 6G systems can provide advanced battery technology for very long battery life and energy harvesting, mobile devices in 6G systems may not require separate charging. New network characteristics in 6G could be as follows: - Satellite integrated network: To provide a global mobile population, 6G is expected to be integrated with satellites. Integrating terrestrial, satellite, and airborne networks into a single wireless communication system is critical for 6G.

[0145] - Connected Intelligence: Unlike previous generations of wireless communication systems, 6G is innovative and will update wireless evolution from "connected things" to "connected intelligence." AI can be applied at each stage of the communication process (or at each step of the signal processing described below).

[0146] - Seamless integration of wireless information and energy transfer: 6G wireless networks will transfer power to charge the batteries of devices such as smartphones and sensors. Therefore, wireless information and energy transfer (WIET) will be integrated.

[0147] - Ubiquitous Super 3D Connectivity: Connectivity to the network and core network functions of drones and very low Earth orbit satellites will create Super 3D connectivity in 6G ubiquitous.

[0148] Some general requirements regarding the new network characteristics of 6G mentioned above may be as follows.

[0149] - Small cell networks: The idea of ​​small cell networks was introduced to improve the quality of received signals in cellular systems as a result of increased throughput, energy efficiency, and spectrum efficiency. Consequently, small cell networks are an essential feature of communication systems for 5G and beyond 5G (5GB). Therefore, 6G communication systems also adopt the characteristics of small cell networks.

[0150] - Ultra-dense heterogeneous network: Ultra-dense heterogeneous networks will be another important characteristic of 6G communication systems. Multi-tier networks composed of heterogeneous networks improve overall QoS and reduce costs.

[0151] - High-capacity backhaul: Backhaul connections are characterized as high-capacity backhaul networks to support high-volume traffic. High-speed fiber optics and free-space optics (FSO) systems can be possible solutions to this problem.

[0152] - Radar technology integrated with mobile technology: High-precision localization (or location-based services) through communication is one of the functions of 6G wireless communication systems. Therefore, radar systems will be integrated with 6G networks.

[0153] - Softwarization and virtualization: Softwarization and virtualization are two important features that form the basis of the design process in 5GB networks to ensure flexibility, reconfigurability, and programmability. Additionally, billions of devices can be shared across a shared physical infrastructure.

[0154] To satisfy the aforementioned characteristics, technologies such as artificial intelligence (AI), THz (Terahertz) communication, optical wireless technology, FSO backhaul network, massive MIMO technology, blockchain, 3D networking, quantum communication, unmanned aerial vehicles, cell-free communication, wireless information and energy transfer (WIET), integration of sensing and communication, integration of access backhaul networks, holographic beamforming, big data analysis, and large intelligent surface (LIS) may be adopted as core implementation technologies of the 6G system.

[0155] For example, THz communication can be utilized in 6G systems. THz communication is a communication that uses a spectrum in the frequency band between 0.3 THz and 3 THz with a corresponding wavelength in the range of 0.1 mm to 1 mm as shown in Fig. 6. Referring to Fig. 6, the frequency band of the THz wave is located in the intermediate region between the infrared band and the millimeter wave band; accordingly, the THz wave can be understood as a radio wave with the shortest wavelength and, at the same time, a light wave with the longest wavelength. As a result, the THz wave shares some characteristics of infrared and microwave waves, and specifically, can simultaneously possess the penetrability of electromagnetic waves and the directivity of light waves.

[0156] FIG. 7 illustrates a transmitter structure applicable to the present disclosure.

[0157] Referring to Fig. 7, in order to modulate data onto an optical signal, the optical source of a laser can be passed through an optical wave guide to change the phase of the signal. At this time, data is loaded by changing electrical characteristics through a microwave contact, etc. Therefore, the optical modulator output is formed as a modulated waveform.

[0158] Data may be provided by a data signal generator. Here, the data may include various user data, configuration information, control information, etc. transmitted through a channel. Furthermore, the data may include data related to AI-based operations, for example, information for configuring an AI model, input / output data for tasks of an AI model, etc. To this end, components related to AI functions (e.g., an AI processing unit) may be included in the data signal generator or may interact with the data signal generator.

[0159] An O / E converter can generate THz pulses based on optical rectification by a nonlinear crystal, O / E conversion by a photoconductive antenna, emission from a bundle of relativistic electrons, etc. THz pulses generated in such a manner can have a length ranging from femtoseconds to picoseconds. The O / E converter performs down-conversion by utilizing the non-linearity of the device.

[0160] When considering the usage of the THz spectrum, it is highly likely that multiple contiguous GHz bands will be used for fixed or mobile service applications for THz systems. According to outdoor scenario criteria, available bandwidth can be classified based on an oxygen attenuation of 10^2 dB / km in the spectrum up to 1 THz. Accordingly, a framework in which the available bandwidth is composed of multiple band chunks can be considered. As an example of the above framework, if the length of the THz pulse for a single carrier is set to 50 ps, ​​the bandwidth (BW) becomes approximately 20 GHz.

[0161] Effective down-conversion from the infrared band to the THz band depends on how the nonlinearity of the photoelectric converter (O / E converter) is utilized. In other words, to achieve down-conversion to the desired THz band, it is required to design an O / E converter with the most ideal nonlinearity for transferring to that specific band. If an O / E converter that does not match the target frequency band is used, there is a high probability of errors occurring regarding the amplitude and phase of the corresponding pulse.

[0162] In a single-carrier system, a THz transceiver system can be implemented using a single photoelectric converter. Depending on the channel environment, in a multi-carrier system, as many photoelectric converters as there are carriers may be required. This phenomenon will be particularly pronounced in multi-carrier systems utilizing multiple broadbands according to the plans related to the aforementioned spectrum applications. In this regard, a frame structure for the multi-carrier system may be considered. A signal down-frequency converted based on a photoelectric converter can be transmitted in a specific resource region (e.g., a specific frame). The frequency domain of the specific resource region may include multiple chunks. Each chunk may consist of at least one component carrier (CC).

[0163] AI technology can be introduced in 6G systems. Efficient resource management and optimization are required to maintain connectivity between various services and devices. AI technology may include techniques capable of performing data analysis, pattern recognition, and predictive modeling using AI / ML (artificial intelligence / machine learning) models. Here, an AI / ML model can be understood as a set of parameter values ​​and / or weight values ​​related to mathematical formulas or algorithms generated through learning, designed to discover patterns in input data or perform predictions. To create such an AI / ML model, an AI / ML model training procedure is required to build the model by learning the relationship between input and output in a data-driven manner. Various learning algorithms, such as supervised learning, unsupervised learning, and reinforcement learning, can be utilized as training algorithms. Users can input specific data into a trained AI / ML model to generate output, and the procedure of obtaining output data by inputting input data into the AI / ML model can be referred to as AI / ML 'inference' or 'prediction'.

[0164] Network control parameters can be obtained as output through AI / ML inference using trained AI / ML models. Users can improve network efficiency by utilizing these output parameter values. For example, AI technology can be applied in various fields, such as wireless network resource allocation, traffic management, fault prediction, and Quality of Service (QoS) management. In particular, machine learning can efficiently allocate resources even in dynamically changing network environments based on real-time data. Therefore, AI technology can be utilized to provide hyper-connectivity and ultra-low latency.

[0165] In this case, AI / ML inference can be performed based on a combination of various devices. For example, the UE and the network can jointly perform AI / ML inference, and such an AI / ML model may be referred to as a two-sided AI / ML model or a two-sided model. In this case, the UE may perform the first part of the inference first, and the base station may perform the remaining inference, and vice versa. As another example, all inference may be performed by the UE, and such an AI / ML model may be referred to as a UE-side AI / ML model or a UE-side model.

[0166] In addition, life cycle management (LCM) for AI / ML models can be performed. Life cycle management may include model training, model deployment, model inference, model monitoring, and model updating. To this end, support may be required for data collection, model training, functionality / model identification, model delivery / transfer, model inference operations, functionality / model selection / enable / disable / fallback, functionality / model monitoring, model updating, and UE capabilities.

[0167] For example, AI / ML technology can be operated based on a functional framework such as FIG. 8. FIG. 8 illustrates an example of a functional framework for the application of AI / ML technology applicable to the present disclosure. First, a data collection function (810) generates training data (801), monitoring data (803), and / or inference data (805) containing processed input data by performing data preparation on input data collected from objects (e.g., UE, RAN node, network node, etc.). A model training function (820), having received the training data (801) from the data collection function (810), performs training on an AI / ML model using the training data (801) and provides the trained / updated model (813) to a model repository (840). The model repository (840) can store and retain the received trained / updated model (813).

[0168] A management function (830) may be used to control AI / ML model training. The management function (830) may control the operation of AI / ML models or AI / ML functions, or supervise their performance. To this end, the management function (830) may receive monitoring data (830) from the data collection function (810) and receive inference output (809) from the inference function (840). The management function (830) performs the role of managing the inference operation so that it can be performed efficiently based on the data received from the data collection function (810) and the inference function (840). That is, the management function (830) may transmit performance feedback or a retraining request (807) to the model training function (820) to improve the inference operation. Here, the performance feedback may be used to direct the learning goal or as a reward for reinforcement learning. Additionally, the management function (830) can provide management instructions (811) that instruct the inference function (840) to select AI / ML models or AI / ML-based functions to use, enable / disable them, or switch to non-AI / ML operations.

[0169] The inference function (840) generates an inference output (809) by performing inference and / or prediction using inference data (805) received by the data collection function (810). Here, the inference output (809) refers to the inference output of the AI / ML model used by the inference function (840), and the details of the inference output may vary depending on the use case. The AI / ML model used by the inference function (840) can be controlled by the management function (830). That is, the management function (830) can transmit a model transmission / delivery request signal (815) to the model repository function (850) to request the necessary AI / ML model, and the model repository function (850) can transmit the corresponding AI / ML model to the inference function (840) via a model transmission / delivery signal (817). Thus, the inference function (840) can perform inference using the AI / ML model (817) according to the received management instructions (811).

[0170] Additionally, the management function (830) can trigger or perform a specified task / action based on the inference output (809). Thus, the management function (830) can trigger a task / action on other objects (e.g., at least one UE, at least one RAN node, at least one network node, etc.) or on itself. Any one of the functions exemplified in FIG. 8 described above may be performed by two or more entities among the RAN, network node, network operator's OAM, or UE in collaboration. This may be referred to as a split AI operation.

[0171] To use an AI / ML model, not all of the functions (810 to 850) illustrated in FIG. 8 must be used, and the method of combining them is not limited to a specific method. Therefore, the functions (810 to 850) may be operated in an integrated manner, or some functions may be omitted. Furthermore, the functions (810 to 850) illustrated in FIG. 8 are not necessarily limited to being implemented as separate devices or apparatuses. For example, some or all of the functions (810 to 850) may be included in the processor (202) of FIG. 2. Additionally, the model storage function (850) may be included in the memory (204) of FIG. 2.

[0172] FIG. 9 illustrates an example of a procedure for utilizing an AI model applicable to the present disclosure. FIG. 9 illustrates a case where a model training function (820) is included in a network node and a model inference function (840) is included in a RAN node. Referring to FIG. 9, in step 1, RAN node 1 and RAN node 2 transmit input data (e.g., training data) for training an AI model to a network node. Here, RAN node 1 and RAN node 2 may also transmit data collected from a UE (e.g., UE measurements related to RSRP, RSRQ, SINR of a serving cell and neighboring cells, UE location, velocity, etc.) to the network node. In step 2, the network node trains the AI ​​model using the received training data. In 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 to perform model training based on the received AI model. In this procedure, it is assumed that the AI ​​model is deployed / updated only to RAN Node 1. In Step 4, RAN Node 1 receives input data (e.g., inference data) for AI model inference from the UE and RAN Node 2. In Step 5, RAN Node 1 generates output data (e.g., prediction or decision) by performing AI model-based inference using the received inference data. In Step 6, if applicable, RAN Node 1 may transmit model performance feedback to the network nodes. In Step 7, RAN Node 1, RAN Node 2, and the UE (or 'RAN Node 1 and UE', or 'RAN Node 1 and RAN Node 2') perform an action based on the output data. For example, in the case of a load balancing action, the UE may move from RAN Node 1 to RAN Node 2. In Step 8, RAN Node 1 and RAN Node 2 transmit feedback information to the network nodes.

[0173] Network nodes can manage AI models based on feedback information regarding the inference results of AI models. For example, network nodes can perform additional training on AI models or generate additional information about AI models (e.g., performance information, accuracy information, etc.). If additional training is performed on AI models, network nodes can distribute the updated AI models to RAN node 1.

[0174] As explained with reference to Fig. 9, model training can be performed by network nodes, and inference using the model can be performed by RAN node 1. In other words, the model training and inference functions can be distributed. Generally, model training requires a large amount of computational resources because it involves optimization using large amounts of data and complex algorithms. In contrast, inference is a process of drawing conclusions about new data using an already trained model, and therefore requires relatively fewer computational resources compared to model training. Therefore, by using the procedure of Fig. 9, model training can be performed through network nodes if the computational resources of the UE or RAN nodes are insufficient. Additionally, security regarding the AI ​​model can be ensured because the AI ​​model is not exposed to the UE.

[0175] FIG. 9 illustrates a case where the model training function (820) is included in a network node and the model inference function (840) is included in a RAN node, but the present disclosure is not limited thereto. For example, if the computational resources of the RAN node are sufficient, both the model training function (820) and the model inference function (840) may be included in RAN node 1. In this case, RAN node 1 receives training data for training an AI model from the UE and RAN node 2. RAN node 1 trains the AI ​​model using the received training data. Subsequently, RAN node 1 receives inference data for AI model inference from the UE and RAN node 2. RAN node 1 generates output data by performing AI model-based inference using the received inference data. Based on the output data, the UE, RAN node 1, and RAN node 2 can perform communication-related operations (e.g., handover, cell change). Subsequently, the UE and RAN node 2 can transmit feedback regarding the operations to RAN node 1. Therefore, RAN Node 1 can train the AI ​​model and update the AI ​​model it will use through feedback information regarding the inference results of the AI ​​model. According to the aforementioned method, since signaling with the network is not required for AI model training and inference, the network load or the latency to train the AI ​​model or receive inference results can be reduced. Additionally, since the UE performs inference using the AI ​​model, the UE's personal information is not transmitted to network nodes, etc. Consequently, security regarding personal information can be enhanced.

[0176] As another example, the model training function (820) may be included in the RAN node, and the model inference function (840) may be included in the UE. The RAN node receives training data for training an AI model from the UE and trains the AI ​​model using the received training data. The RAN node distributes the trained AI model to the UE. The UE can generate output data by performing inference based on the received AI model. At this time, the data for inference can be received from the RAN node or data acquired by the UE itself can be used. The UE and the RAN node can perform communication-related operations based on the output data generated by inference. Subsequently, the UE can send feedback regarding the operation to the RAN node. Thus, through feedback information regarding the inference results of the AI ​​model, the RAN node can train the AI ​​model and distribute the updated AI model to the UE. According to the method described above, the load on the RAN node can be reduced by having the model training function (820) in the RAN node and the model inference function (840) in the UE perform inference. In addition, if the UE performs inference using data acquired independently, even if the UE loses its connection to the RAN node after receiving the AI ​​model, the UE can continue to perform inference using the received AI model and operate based on the inference results.

[0177] According to the aforementioned framework and procedure, an AI model can be trained and utilized in a wireless communication system. The model training function (820) and the model inference function (840) can be combined in various ways and are not necessarily limited to the case of FIG. 9. In the aforementioned framework and procedure, various data such as input data, training data, and inference data are introduced, and the specific details of the aforementioned data may vary depending on the task in which the AI ​​model is utilized. For example, information used in the various embodiments of the present disclosure described below may be included in the aforementioned data.

[0178] FIG. 10 illustrates an AI technology-based communication procedure applicable to the present disclosure. The detailed procedure illustrated in FIG. 10 may be combined with various embodiments of the present disclosure described below. For example, data generated according to various embodiments of the present disclosure may be used for operations (e.g., setup, training, inference, and / or data transmission / reception) in at least one of the detailed procedure illustrated in FIG. 10. As another example, the result of the inference illustrated in FIG. 10 may be used to transmit and / or receive data according to various embodiments of the present disclosure.

[0179] Referring to FIG. 10, in step S1001, at least one of the UE (1010), RAN node (1020), and network node (1030) performs an initial connection procedure. For example, in this step, at least one of an initial cell search operation, a system information acquisition operation, a random access operation, and a registration operation may be performed. In step S1003, at least one of the UE (1010), RAN node (1020), and network node (1030) performs a configuration procedure. Through the configuration procedure, parameters, resources, connections, and / or entities necessary to perform subsequent procedures at layers between the UE (1010) and the RAN node (1020) and / or at least one layer between the UE (1010) and the network node (1030) may be determined and / or created. At this time, the configuration procedure may be performed based on information, status, and / or characteristics of the AI ​​model used for subsequent training and inference.

[0180] In step S1005, at least one of the UE (1010), RAN node (1020), and network node (1030) performs a model training procedure. At least one of the UE (1010), RAN node (1020), and network node (1030) may collect training data and perform training using the training data. For example, the model training procedure may be performed as described with reference to FIG. 9. If an offline trained model is used, this step may be omitted.

[0181] In step S1007, at least one of the UE (1010), RAN node (1020), and network node (1030) performs a task using a trained model. That is, the task may be performed by the result of inference and / or prediction using the trained model. For example, the task may be a procedure belonging to a communication protocol, a preliminary operation for subsequent data transmission and / or reception, related to data transmission and / or reception, or related to data processing (e.g., encoding, decoding, etc.).

[0182] In step S1009, at least one of the UE (1010), RAN node (1020), and network node (1030) transmits and / or receives data. At this time, the result of the task performed in step 1007 may be used. In some cases, the task performed in step 1007 may include the transmission and / or reception of data, in which case this step may be omitted as it is part of step 1007.

[0183] Specific embodiments of the present disclosure

[0184] The present disclosure proposes a method for performing beam search using a reference signal. The present disclosure proposes a method for reducing the number of beams measured for beam search in the time domain or the spatial domain. Furthermore, the present disclosure proposes a procedure for determining an optimal beam using an artificial intelligence model. The present disclosure proposes a method for jointly optimizing a transmitted beam and a beam inference function. By utilizing the methods proposed in the present disclosure, the trade-off problem between beam management performance and the overhead of the beam management procedure can be efficiently resolved.

[0185] In very large-scale multi-antenna systems, beam management that simultaneously includes both near-field and far-field regions is required because the near-field region between the base station and the user expands. First, a method can be proposed to generate a hybrid codebook that includes both beam sets quantized by distance and angle in the near-field region and beam sets quantized by angle in the far-field region, and to search for transmit and receive beams based on this hybrid codebook. However, a hybrid codebook containing all beam sets in both the near-field and far-field regions becomes large, which increases the number of transmit or receive beams that need to be searched. Consequently, such a hybrid codebook can degrade performance characteristics, such as overhead and latency, in the communication system. Therefore, for efficient beam management, a low-complexity beam management technique utilizing a hybrid codebook of limited size is required. For the sake of convenience of explanation below, the range of angles considered in the hybrid codebook will be referred to as the angle region, and the range of distances considered in the hybrid codebook will be referred to as the distance region, but this is not a limitation. For example, the angle area may be referred to as an angle range, angle span, angle field, first direction range, or other terms having an equivalent technical meaning. Similarly, the distance area may be referred to as a distance range, distance span, distance field, second direction range, or other terms having an equivalent technical meaning.

[0186] If a full search of all possible beams is performed, high beam gain performance can be expected, but the overhead consumed in beam searching may increase. If only some beams are searched to reduce this overhead, the overhead is reduced, but a problem may arise where beam management performance deteriorates.

[0187] To address this, partial search techniques can be considered among methods for searching some beams. Here, partial search techniques refer to the entire set of beams belonging to the codebook. A sub-beam set containing some codewords without measuring the beam of It refers to a beam measurement technique that utilizes [it]. Depending on how sub-beam sets are utilized, the overhead of beam management can be reduced.

[0188] In this regard, the following discussion took place in TR 38.843.

[0189] 6.3 Beam Management 6.3.1 Evaluation Assumptions, Methodology, and KPIs Figure 6.3.1-1 provides an example of the beam management inference procedure for BM-Case1 and BM-Case2. Measures based on the beams in Set B are used as model inputs. Additionally, beam ID information may also be provided as input to the AI / ML model. Based on the model output (e.g., the probability that each beam in Set A will become the Top-1 beam, predicted L1-RSRP), the Top-1 / N beam(s) in Set A can be predicted, or predicted together with the predicted L1-RSRP (depending on labeling). In the evaluation, for BM-Case1, measures from Set B (unless otherwise specified) are used as model inputs to predict the Top-1 / N beams in Set A, while for BM-Case2, measures from historical time instances are used as model inputs for the temporal DL beam prediction of the beams in Set A. The evaluation considers the cases where Set A and Set B are different (Set B is not a subset of Set A), where Set B is a subset of Set A, and where Set A and Set B are identical in BM-Case 2. The performance of DL Tx beam prediction and DL Tx-Rx beam pair prediction is evaluated. For both BM-Case 1 and BM-Case 2, the UE can report prediction results to the NW based on the output of the UE-side model, or the NW can predict Top-1 / N beams using the NW-side model based on the reported measurements of Set B. A system-level simulation approach is adopted by default for constructing datasets and evaluating performance (where applicable) for AI / ML use cases for beam management, while link-level simulation is adopted optionally.

[0190] In [Table 1] above, it is explained that for Set B, measurements based on the beams of Set B can be used as model input. That is, Set B can be defined as a set of beams used for use in AI (artificial intelligence) / ML (machine learning) models for BM (beam management), or a set of indices that can direct the beams. Therefore, the beams directed through Set B are measured, and the results of the measurements can be input to the AI / ML model. Specifically, the input to the AI / ML model can be determined based on Set B, which is the set of beams (in the case of BM-Case 1), and the measurements of Set B in historiographic time instances (in the case of BM-Case 2). The output of the AI / ML model can be expressed as the probability that each beam within Set A will become the Top-1 beam, or the predicted L1-RSRP, etc. Additionally, the Top-1 / N beams within Set A can be acquired based on the model output. That is, Set B can be defined as a set of beams that dictates which beams will be used to perform measurements. Here, the measured beam values ​​can be used to obtain beam prediction results from the AI / ML model. However, to efficiently control beam management overhead and performance, techniques for configuring the beams to be measured need to be discussed. The overhead and beam management performance in a very large-scale multi-antenna system are described below.

[0191] FIG. 11 illustrates an example of beam management overhead in a very large-scale multi-antenna system according to one embodiment of the present disclosure. FIG. 11 illustrates a graph of the overhead reduction ratio η according to K. Here, K represents the maximum number of allowable codewords in an angular domain. Here, a codeword refers to an element of a codebook or a hybrid codebook. Thus, a codeword may contain information regarding parameter values ​​for beamforming. However, the codeword in the present disclosure may be referred to by other terms, such as beamforming vector, beam pattern element, weight, weight vector, antenna weight, beam setting parameter, amplitude and phase vector, weight vector, or other terms having an equivalent technical meaning. Thus, a specific codeword may correspond to a specific beam. Measurements may be performed on all codewords included in the codebook to determine the beam to be communicated.

[0192] The overhead reduction ratio η can be modeled as shown in [Equation 1] below.

[0193]

[0194] In [Mathematical Formula 1], represents the total number of codewords in the codebook, and represents the number of codewords used in beam search.

[0195] Referring to Figure 11, it is confirmed that in a hybrid codebook, as the number of unused codewords increases (i.e., as K decreases), measurements for those codewords can be omitted, thus increasing the overhead reduction ratio.

[0196] FIG. 12 illustrates an example of beam management performance in a very large-scale multi-antenna system according to one embodiment of the present disclosure. FIG. 12 illustrates a normalized gain for an overhead reduction ratio η. Here, the normalized gain can be expressed as shown in [Equation 2] below.

[0197]

[0198] In [Mathematical Formula 2], represents the channel vector between the base station and the user, and represents the beam used for beam search.

[0199] Referring to Figure 12, it is confirmed that the normalized gain decreases as the number of unused codewords increases.

[0200] The following describes a beam management method for reducing overhead in a multi-antenna system. In the following, the base station is N t It is assumed that uniform linear array (ULA) antennas are used and that the user or terminal has a single receiving antenna. For convenience of explanation, beam management operations for downlink communication of a base station for a multi-antenna system are described, but are not limited thereto. As an example, the method described in this disclosure may also be applied to a procedure for managing the transmit beam of a user or terminal for uplink communication when the user or terminal has a multi-transmit antenna system.

[0201] In high-frequency band wireless channels, scattering phenomena occur less frequently due to the highly directional propagation characteristics, and consequently, the number of propagation paths can be reduced. In addition, in a very large-scale multi-antenna system, the near-field region between the base station and the terminal can be expanded, and short-range communication can follow a square wavefront propagation environment. Therefore, the channel h between the base station and the terminal, reflecting the characteristics of the near-field region, can be expressed as shown in [Equation 3] below.

[0202]

[0203] In [Equation 3], L is the number of paths, is the gain of the l-th path, represents the spatial angle of the l-th path, and represents the distance of the l-th path, and represents an array response vector.

[0204] Here, the spatial angle is is the actual physical starting angle of the l-th path It is defined as the sine value. In addition, in the far field, it can follow a plane wavefront propagation environment, and according to plane wavefront propagation, the array response vector can be expressed as shown in [Equation 4] below.

[0205]

[0206] In [Mathematical Formula 4], means the signal wavelength, and means antenna spacing.

[0207] Meanwhile, in the near field, the array response vector can be expressed as shown in [Equation 5] below according to square wavefront propagation.

[0208]

[0209] In [Mathematical Formula 5],

[0210] represents the distance to the nth antenna.

[0211] Therefore, the array response vector of the far-field can be determined based on the angle as in [Equation 4] above, and the array response vector of the near-field can be determined based on the angle and distance as in [Equation 5] above.

[0212] For the sake of convenience of explanation, the technique proposed below is described as using beamforming vectors as codewords included in a hybrid codebook, but is not limited thereto. For example, a correspondence relationship between codewords and beamforming vectors may be pre-established, and the codeword may include parameter values ​​capable of indicating beamforming vectors; in this case as well, since beamforming vectors can be obtained based on such parameter values, the following procedures can be applied in the same way.

[0213] The base station is a hybrid codebook pre-configured with a set of beamforming vectors Based on this, a total of M beams can be transmitted. Here, the hybrid codebook can be configured as a codebook where the number of extracted distances differs depending on the angle. The hybrid codebook can be configured in such a way that more codewords are assigned in the frontal direction than in the lateral direction of the antenna. The base station is the i-th codeword The signal y received by the terminal of the unit power transmission symbol s transmitted using i It can be expressed as shown in [Mathematical Formula 6] below.

[0214]

[0215] In [Equation 6], P represents the transmitted power, and refers to the channel between the base station and the user, and The mean is 0 and the variance is It refers to received noise that follows a complex normal distribution.

[0216] The terminal measures the received strength for all beams and determines the optimal codeword It can be searched. The codeword with the highest reception strength can be expressed in the form of [Equation 7] below.

[0217]

[0218] Subsequently, the terminal can report information related to the optimal codeword to the base station. Upon receiving information related to the optimal codeword from the terminal, the base station can manage beams based on the information related to the codeword and transmit data based on the selected beam.

[0219] The achievable rate performance of the terminal can be expressed as shown in [Equation 8] below.

[0220]

[0221] In [Mathematical Equation 8], represents the received SNR.

[0222] The aforementioned method performs beam search on all codewords in the codebook. Therefore, the overhead required for beam search is not insignificant. Furthermore, in very large-scale multi-antenna systems, significant overhead can occur due to the increase in the number of antennas and the expansion of the near-field area. To address this, a procedure for performing beam management using a subset of the codewords in the entire codebook is described below.

[0223] FIG. 13 illustrates an example of a procedure in which a base station performs beam management using some codewords according to one embodiment of the present disclosure. FIG. 13 illustrates a method performed by a base station (e.g., RAN node (1020), network node (1030) of FIG. 10) that performs wireless communication. In the description with reference to FIG. 13, the operating entity is referred to as a base station, and the base station may perform a connection procedure to perform wireless communication with a terminal.

[0224] Referring to FIG. 13, in step S1301, the base station determines a codebook related to the measurement. The codebook may include codewords indicating beamforming vectors. The codebook may be composed of a sub-codebook containing at least one of the codewords of the entire codebook. Here, the entire codebook may be composed of a hybrid codebook defined in an angle domain and a distance domain. The sub-codebook may include some of the codewords of the entire codebook in the angle domain or the distance domain.

[0225] In step S1303, the base station transmits configuration information related to the measurement to the terminal. The configuration information related to the measurement may include at least one of information related to the codebook determined in step S1301 or information related to the reference signal. The configuration information related to the measurement may be transmitted via a radio resource control (RRC) message or MAC CE, etc. For example, the configuration information related to the measurement may be transmitted via CSI-ReportConfig IE.

[0226] In step S1305, the base station transmits a reference signal to the terminal. Here, the reference signal may be transmitted based on a codebook included in the configuration information related to the measurement. The terminal may receive the reference signal based on information regarding the codebook and information regarding the reference signal.

[0227] In step S1307, the base station receives a measurement result for the reference signal. The measurement result may be determined by the terminal based on the received reference signal. The measurement result may include at least one of information related to RSRP (reference signal received power), RSRQ (reference signal received quality), and SINR (signal-to-interference plus noise ratio).

[0228] In step S1309, the base station determines beamforming based on measurement results. The base station can determine the most optimal codeword based on measurement results related to a sub-codebook. An artificial intelligence model may be used to determine the codeword. For example, an optimal codeword may be determined based on measurement results using an artificial intelligence model, and a beam may be selected based on the codeword. As another example, beam gains for the entire codebook may be determined based on measurement results for the sub-codebook using an artificial intelligence model, and the base station may select the beam corresponding to the codeword having the largest value among the total beam gains.

[0229] In step S1311, the base station transmits or receives a data signal with the terminal. Here, the data signal may be transmitted through the beam determined in step S1309.

[0230] FIG. 14 illustrates an example of a procedure for performing communication using a beam determined by a base station according to one embodiment of the present disclosure. FIG. 14 illustrates a method performed by a terminal (e.g., UE (1010) of FIG. 10) that performs wireless communication. In the description with reference to FIG. 14, the operating entity is referred to as a terminal, and the terminal may be provided with a cell for wireless communication from a base station and may be referred to as a UE and a wireless terminal, etc.

[0231] Referring to FIG. 14, in step S1401, the terminal receives configuration information regarding measurement from the base station. The configuration information regarding measurement may include at least one of information regarding a codebook determined by the base station or information regarding a reference signal. The codebook may include codewords indicating a beamforming vector. The codebook may be composed of a sub-codebook containing at least one of the codewords of the entire codebook. Here, the entire codebook may be composed of a hybrid codebook defined in an angle domain and a distance domain. The sub-codebook may include some of the codewords of the entire codebook in the angle domain or the distance domain.

[0232] In step S1403, the terminal receives a reference signal from the base station. Here, the reference signal may be transmitted based on a codebook included in the configuration information related to the measurement.

[0233] In step S1405, the terminal measures the received reference signal. The terminal may perform measurements based on the received reference signal. The measurement of the reference signal may be performed periodically or semi-periodically and may be performed for each of the codewords included in the codebook.

[0234] In step S1407, the terminal reports the measurement results to the base station. The measurement results may include at least one of the information related to RSRP, RSRQ, and SINR.

[0235] In step S1409, the terminal transmits or receives a data signal with the base station. The data signal may be transmitted through a beam determined by the base station based on the measurement results.

[0236] Through the procedure described in FIGS. 13 and 14, the beam can be determined using a sub-codebook containing some of the codewords from the entire codebook, rather than the entire codebook. Therefore, the overhead for optimizing the beam can be reduced. In the following, to reduce overhead, a sub-codebook, which is a set of codewords from some of the entire codebook A technique to reduce beam search complexity using is described.

[0237] i-th codeword at the base station When a signal is transmitted using [Equation 6], the signal received by the terminal can be expressed similarly to the above [Equation 6]. The terminal measures the received signal strength for each of the partial beams transmitted by the base station and reports information related to the measured value to the base station. i-th codeword The signal transmitted based on is of the strength as shown in [Equation 9] below It can be received as.

[0238]

[0239] The beam inference function can be generated based on a neural network. Here, the input of the beam inference function can be set to the intensities of m received signals, and the output of the beam inference function can be set to aim for outputting a codeword that exhibits optimal beam management performance across the entire codebook. Beam inference function input of and output It can be expressed as shown in [Mathematical Formula 10] below.

[0240]

[0241] Therefore, the complexity and performance of a beam inference function may vary depending on the method of selecting the input to the beam inference function. A method for determining the input to a beam inference function is described below. The present disclosure proposes a method for constructing neural network input data based on information of some beams received during the beam reporting stage. Specifically, combinations of some received beams can be reconstructed into a two-dimensional matrix form by mapping them to angle and distance domains. Accordingly, the codebook may include codewords determined for each of the angle domain and the distance domain.

[0242] Here, the rows and columns of a two-dimensional matrix can be represented in a quantized form of the angle and distance domains. The present disclosure proposes a distance domain sparse method, an angle domain sparse method, and a two-dimensional domain sparse method as ways to organize input data. Below, a hybrid codebook defined in the angle domain and the distance domain is first described.

[0243] FIG. 15 illustrates an example of a hybrid codebook according to one embodiment of the present disclosure. FIG. 15 shows a carrier frequency It is GHz and the number of antennas is The number of extracted distances per angle is plotted. The hybrid codebook may include codewords configured to support distance dimensions as well as angles, in order to support both near and far fields while considering beam coverage. That is, the hybrid codebook may include codewords defined for each of the angle and distance domains. The number of codewords defined per angle in the hybrid codebook may be set differently. For example, it may be configured as a codebook in which a larger number of codewords are assigned to the frontal direction of the antenna than to the lateral direction of the antenna.

[0244] Distance domain sparsity method

[0245] The distance domain sparsity method is a method in which, as beams transmitted during the beam search process, codewords from a subset of the distance domains of the entire distance domain of the hybrid codebook are selected, and beam search is performed based on the selected codewords. Some codewords from a specific angle may be selected to have a fixed interval within the distance domain. For example, the received beam gain [M] in the i-th distance domain and j-th angle domain obtainable by the distance domain sparsity method. (i,j) It can be expressed as shown in [Mathematical Formula 11] below.

[0246]

[0247] In [Equation 11], K r represents the maximum number of codewords in the distance domain within the same angular region, and D j represents the number of codewords corresponding to the j-th angle region in the hybrid codebook, and represents the maximum integer function.

[0248] By utilizing [Equation 11], some distance region codewords have a maximum number K in a specific angle region. r Based on this, the index of the distance area can be selected to increase by a constant amount.

[0249] FIG. 16 shows that in a hybrid codebook according to one embodiment of the present disclosure, the maximum number of codewords in the distance domain is K r An example of a two-dimensional receive beam gain when =4 is illustrated. FIG. 17 shows that in a hybrid codebook according to one embodiment of the present disclosure, the maximum number of codewords in the distance domain is K r An example of the 2D receiving beam gain when =7 is illustrated.

[0250] Referring to FIGS. 16 and 17, the maximum number of codewords K in the distance domain corresponding to the distance area is r As increases, the number of beams used for beam search It can be seen that it increases. When using a distance domain sparse method, the overhead of beam search is the maximum number of codewords K in the distance domain for each angle. r It can be controlled based on. Due to the nature of the hybrid codebook, the number of extracted codewords varies by angle, so D, which is the number of codewords corresponding to the j-th angle area, j has a maximum value in the intermediate angle region and decreases as it approaches the angle regions at both ends. The number of codewords D in the j-th angle region. j Ga K r If it is smaller, D at the corresponding angle as in [Equation 11] above. j Only codewords are selected.

[0251] Angle domain sparse method

[0252] The angle domain sparsity method is a method in which codewords from a subset of the angle domains within the entire angle domain of the hybrid codebook are selected as the beams transmitted during the beam search process. The received beam gain [M] in the i-th distance domain and j-th angle domain obtained by the angle domain sparsity method. (i,j) It can be expressed as shown in [Mathematical Formula 12] below.

[0253]

[0254] In [Equation 12], K a represents the maximum number of codewords in the angle domain within the same distance region, and A i represents the set of codeword indices belonging to the i-th distance region in the hybrid codebook.

[0255] By using the above [Equation 12], the codewords of the above partial angle region can be selected such that the index related to the above partial angle region among the entire angle region increases by a constant amount.

[0256] FIG. 18 shows that in a hybrid codebook according to one embodiment of the present disclosure, the maximum number of codewords in the angle domain is K a An example of a two-dimensional receive beam gain when =120 is illustrated. FIG. 19 shows that in a hybrid codebook according to one embodiment of the present disclosure, the maximum number of codewords in the angle domain is K a An example of the 2D receiving beam gain when =160 is illustrated.

[0257] Referring to FIGS. 18 and 19, the maximum number of codewords K in the angle domain a As increases, the number of beams used for beam search It is confirmed that it increases. In the angular domain sparse method, the overhead of beam search is the maximum number of partial codewords K corresponding to the angular domain depending on the distance. a It can be controlled through. Since the codewords extracted by distance in the hybrid codebook vary, as the distance area index i increases, the set of codeword indices A belonging to the i-th distance area i The number of codewords included in can be reduced.

[0258] 2D domain sparse method

[0259] The 2D domain sparsity method refers to a method of selecting a subset of codewords during the beam search process by simultaneously sparsifying transmitted beams in the angle and distance domains of a hybrid codebook. For example, some codewords for beam search can be determined based on the sum of the indices in the distance domain and the angle domain, and an overhead control variable. The received beam gain [M] in the i-th distance domain and j-th angle domain obtained by the 2D domain sparsity method. (i,j) It is expressed as in [Mathematical Formula 13].

[0260]

[0261] In [Equation 13], K 2Drepresents a variable that controls the overhead of beam search, and mod(a,m) represents a function that returns the remainder after dividing a by m.

[0262] FIG. 20 shows K by applying a two-dimensional region sparse method according to one embodiment of the present disclosure. 2D An example of a two-dimensional receive beam gain when =4 is illustrated. FIG. 21 shows K by applying a two-dimensional region sparse method according to one embodiment of the present disclosure. 2D An example of the 2D receive beam gain when =3 is illustrated. Referring to FIGS. 20 and 21, the variable K controls the beam seek overhead. 2D It is confirmed that as d decreases, the number of codewords extracted using the 2D area sparse method increases, and the overhead reduction rate increases.

[0263] The angle domain sparse method, the distance domain sparse method, and the two-dimensional domain sparse method have been described based on the case where the angle domain is quantized into 512 and the distance domain into 24, but are not limited thereto. Therefore, the sparse method described in this disclosure can be used regardless of the number of divisions for the angle domain and the distance domain.

[0264] The following describes partial search techniques based on artificial intelligence models. As previously mentioned, the input data for the neural network model may be one of the angle domain sparse, distance domain sparse, or two-dimensional domain sparse methods. Here, the artificial intelligence model may include a neural network model. In the following examples, the use of a neural network model as the artificial intelligence model is used, but it is not limited thereto.

[0265] FIG. 22 illustrates an example of a procedure in which a base station determines a beam using an artificial intelligence model according to one embodiment of the present disclosure. FIG. 22 illustrates a method performed by a base station (e.g., a RAN node (1020) and a network node (1030) of FIG. 10) that performs wireless communication. In the description with reference to FIG. 22, the operating entity is referred to as a base station, and the base station may perform a connection procedure to perform wireless communication with a terminal. Referring to FIG. 22, a beam index to perform communication can be determined through an index-based neural network partial search technique that utilizes some beam information. Here, the beam index may be referred to as a codeword index, a beamforming vector index, or other terms having an equivalent technical meaning.

[0266] Referring to FIG. 22, in step S2201, the base station acquires some beam information from the total beam information to be used as input to an artificial intelligence model. The some beam information may include information related to measurement results related to a sub-codebook. The sub-codebook may include at least one of the codewords included in the total codebook. The method for determining the sub-codebook can be determined in various ways. For example, the sub-codebook may be determined through an angle domain sparse method, a distance domain sparse method, or a two-dimensional domain sparse method.

[0267] In step S2203, the base station performs inference based on an artificial intelligence model. The artificial intelligence model may be trained using an index-based neural network technique described later. Here, the input of the artificial intelligence model may include information regarding measurement results related to a sub-codebook. The output of the artificial intelligence model may include information regarding codewords determined based on measurement results related to the sub-codebook. Here, the information regarding codewords may include at least one of the following: an optimal codeword, an index value corresponding to the optimal codeword, or beam gain values ​​related to the entire codeword. Here, the index value may be referred to as a beamforming index, a codeword index, a beam index, or other terms having an equivalent technical meaning.

[0268] In step S2205, the base station determines a beam index. In index-based neural network techniques, the beam index can be determined based on a codeword, which is the output value of an artificial intelligence model. In magnitude neural network techniques, the beam index can be determined based on the largest value among the total beam gains.

[0269] FIG. 23 illustrates examples of layers of an index-based neural network according to one embodiment of the present disclosure. An index-based neural network technique refers to a technique in which output data of a neural network model is generated in a manner such as one-hot encoding by utilizing partial beam information. Specifically, an index-based neural network partial search technique allows the neural network model to learn based on input data and predict a single codeword index with the highest beam gain among all codewords using the neural network model. Here, the structure of the neural network may be composed of three layers, such as an input layer (2310), a hidden layer (2320), and an output layer (2330), as shown in FIG. 23.

[0270] Input data in the form of a two-dimensional matrix is ​​transmitted to the input layer (2310), which corresponds to an angle domain and a distance domain based on information from some beams. The input layer (2310) transmits the input data to the hidden layer, and the hidden layer (2320) is trained using two convolutional layers based on the received data. In FIG. 23, the hidden layer (2320) is depicted as being composed of two layers, but it is not limited thereto. The hidden layer (2320) can be implemented with one or three or more layers. The hidden layer (2320) performs the role of extracting characteristics of the input data and imparting non-linearity characteristics. The output layer (2330) is configured to output a matrix in which the codeword index with the highest beam gain has a value of 1 and all other codeword indices have a value of 0 after passing through a single activation function. To this end, the target output silver Based on this, the index with the highest beam gain is configured to have a value of 1, and the remaining indices are configured to have a value of 0. The loss function used at this time is designed to minimize the cross-entropy error and can be expressed as shown in [Equation 14] below.

[0271]

[0272] In [Equation 14], means target output and represents the output of the neural network.

[0273] FIG. 24 illustrates an example of the output of an index-based neural network according to one embodiment of the present disclosure. As shown in FIG. 24, a single codeword with the highest beam gain can be predicted through an artificial intelligence model. Specifically, the output of the neural network can be set to have a value of 1 only for the single index predicted to have the highest beam gain.

[0274] FIG. 25 illustrates an example of a procedure for a base station to acquire a total beam gain according to an embodiment of the present disclosure. FIG. 25 illustrates a method performed by a base station (e.g., a RAN node (1020) and a network node (1030) of FIG. 10) that performs wireless communication. In the description with reference to FIG. 25, the operating entity is referred to as a base station, and the base station may perform a connection procedure to perform wireless communication with a terminal. With reference to FIG. 25, a beam index to perform communication can be determined through an index-based neural network partial search technique that utilizes partial beam information.

[0275] Referring to FIG. 25, in step S2501, the base station acquires some beam information from the total beam information to be used as input to an artificial intelligence model. The some beam information may include information related to measurement results related to a sub-codebook. The sub-codebook may include at least one of the codewords included in the total codebook. The method for determining the sub-codebook can be determined in various ways. For example, the sub-codebook may be determined through an angle domain sparse method, a distance domain sparse method, or a two-dimensional domain sparse method.

[0276] In step S2503, the base station performs inference based on an artificial intelligence model. The artificial intelligence model may be trained using a magnitude-based neural network technique described later. Here, the input to the artificial intelligence model may include information related to measurement results associated with a sub-codebook. The output of the magnitude-based neural network technique may include total beam gains corresponding to codewords included in the entire codebook.

[0277] In step S2505, the base station acquires the total beam gain. The base station can acquire the total beam gains for the entire codebook based on a learned artificial intelligence model. Subsequently, the base station can form a beam based on the codeword having the largest beam gain among the total beam gains.

[0278] FIG. 26 illustrates examples of layers of a magnitude-based neural network according to one embodiment of the present disclosure. The magnitude-based neural network technique aims to predict the received beam gains of all codewords in a hybrid codebook by utilizing some beam information for the output data of the neural network model. The structure of the magnitude-based neural network consists of three layers: an input layer (2610), a hidden layer (2620), and an output layer (2630).

[0279] Input data in the form of a two-dimensional matrix is ​​transmitted to the input layer (2610), which corresponds to angle and distance regions based on information from some beams. The input layer (2610) transmits the input data to the hidden layer (2620), and the hidden layer (2620) is trained using two convolutional layers based on the received data. The hidden layer (2620) performs the role of extracting characteristics of the input data and assigning non-linearity characteristics. The output layer (2630) outputs magnitude information of all codewords through a single convolutional layer. The loss function used at this time is the target output (target output) and neural network output It can be set to minimize the mean squared error between them. The mean squared error can be expressed as shown in [Equation 15] below.

[0280]

[0281] In [Mathematical Formula 15], means some received beam gain, and represents the output of the neural network.

[0282] FIG. 27 illustrates an example of the output of a magnitude-based neural network according to one embodiment of the present disclosure. As shown in FIG. 27, the output of the magnitude-based neural network may have values ​​corresponding to all codewords that can have arbitrary values.

[0283] Beam optimization can be performed based on the aforementioned index or magnitude-based neural network partial search technique. However, this partial search technique has a limitation in that the normalization gain drops significantly when beam inference fails. Therefore, a 2-stage partial search technique that utilizes both partially reported beam information and neural network inference results may be considered.

[0284] 2-Stage Partial Search Technique

[0285] The present disclosure proposes a two-stage partial search technique to improve beam management performance. The two-stage partial search technique may consist of a first stage and a second stage. In the first stage, a partial search technique is performed, and in the second stage, a procedure to finally determine a beam is performed by comparing the beam determined by the partial search technique with the previous beam.

[0286] A partial search technique may be performed in the first stage, wherein the partial search technique may include the aforementioned index or magnitude-based partial search technique or neural network partial search technique. For convenience of explanation, the partial search technique performed in the first stage will be referred to as the direct partial search technique.

[0287] The base station can store a beam index having the largest beam gain among some beam gains received through distance, angle, or a 2D area sparse method via a direct partial search technique of the first stage. Additionally, the terminal can store the largest beam gain among some beam gains received via a sparse method.

[0288] In the second stage, the terminal compares the beam gain inferred through the neural network technique with the previously stored beam gain and reports 1-bit feedback to the base station. Based on the reported 1-bit feedback, the base station can set a beam to be used for beam search again and proceed with communication.

[0289] FIG. 28 illustrates an example of a procedure in which a base station performs 2-stage beam management according to one embodiment of the present disclosure. FIG. 28 illustrates a method performed by a base station (e.g., a RAN node (1020), a network node (1030) of FIG. 10) that performs wireless communication. In the description with reference to FIG. 28, the operating entity is referred to as a base station, and the base station may perform a connection procedure to perform wireless communication with a terminal.

[0290] Referring to FIG. 28, in step S2801, the base station performs a first measurement procedure with the terminal and stores a first beam index associated with the first beam. The base station may perform the first measurement procedure based on a sub-codebook containing at least one of the codewords of the entire codebook. Through the first measurement procedure, the base station may obtain information related to the measurement result corresponding to the sub-codebook. The first beam index may indicate the first beam having the highest beam gain among the beam gains measured through the first measurement procedure. The first beam index may be stored within the terminal.

[0291] In step S2803, the base station determines the second beam index through an artificial intelligence model based on the measurement results of the first measurement procedure. The artificial intelligence model may be configured based on the aforementioned index-based neural network or magnitude-based neural network.

[0292] In step S2805, the base station transmits a reference signal to the terminal via the second beam corresponding to the second beam index. The reference signal may be referred to as an SSB (synchronization signal block), a CSI-RS (channel state information reference signal), or signals having an equivalent technical meaning.

[0293] In step S2807, the base station receives a measurement result of a reference signal from the terminal. The measurement result of the reference signal may be included in a feedback signal, and the measurement result may include information regarding the magnitude of the measurement result for the first beam and the measurement result for the second beam. The information regarding the magnitude may be transmitted as 1 bit.

[0294] In step S2809, the base station selects a beam based on the received measurement results and the first beam index. If a feedback signal transmitted as 1 bit is received, the base station may decide whether to continue using the second beam based on the feedback information. For example, if the second beam has worse performance than the first beam, the base station may perform the beam search procedure again and select a new beam. For another example, if the second beam has worse performance than the first beam, the base station may proceed with communication using the first beam.

[0295] FIG. 29 illustrates an example of a procedure in which a terminal transmits a feedback signal for 2-stage beam management according to one embodiment of the present disclosure. FIG. 29 illustrates a method performed by a terminal performing wireless communication (e.g., the UE (1010) of FIG. 10). In the description with reference to FIG. 29, the operating entity is referred to as a terminal, and the terminal may be provided with a cell for wireless communication from a base station and may be referred to as a UE and a wireless terminal, etc.

[0296] Referring to FIG. 29, in step S2901, the terminal performs a first measurement procedure with the base station and stores a first beam gain. The terminal may perform the first measurement procedure based on a sub-codebook containing at least one of the codewords of the entire codebook. The terminal may report the measurement result measured through the first measurement procedure to the base station. The terminal may store the first beam gain, which is the highest beam gain among the beam gains measured through the first measurement procedure. Additionally, the terminal may store a codeword or codeword index value corresponding to the first beam gain.

[0297] In step S2903, the terminal receives a reference signal through a second beam corresponding to a second beam index. The second beam index can be determined by the base station through an artificial intelligence model.

[0298] In step S2905, the terminal measures the received reference signal. The terminal measures the received reference signal and can derive at least one of the RSRP, RSRQ, and SINR. The terminal can perform a comparison of the measurement result for the first beam and the measurement result for the second beam.

[0299] In step S2907, the terminal generates a feedback signal based on the measurement result of the reference signal and the first beam gain. The feedback signal may include information regarding the magnitude of the measurement result for the first beam and the measurement result for the second beam. The information regarding the magnitude may be transmitted as 1 bit.

[0300] In step S2909, the terminal transmits a feedback signal to the base station. For example, the feedback signal may include '0' if the measurement result for the first beam is greater than the measurement result for the second beam, and '1' if the measurement result for the first beam is less than or equal to the measurement result for the second beam.

[0301] FIG. 30 illustrates an example of signaling between a base station (3010) and a terminal (3020) in a two-stage beam management procedure according to one embodiment of the present disclosure. Referring to FIG. 30, a beam management procedure can be efficiently performed using a sub-codebook containing at least one of the codewords included in the entire codebook. In FIG. 30, the base station (3010) and the terminal (3020) perform a connection establishment procedure, and it is assumed that the base station (3010) has determined the sub-codebook in advance based on the entire codebook. The two-stage beam management procedure may include a first stage procedure for determining a first beam and a second stage procedure for determining whether to continue using the first beam.

[0302] Referring to FIG. 30, in step S3001, the base station (3010) performs transmission beam sweeping and performs a measurement procedure with the terminal (3020). The base station (3010) can form beams for codewords included in a sub-codebook. For example, if there are m codewords included in the sub-codebook, m reference signals may be transmitted by the base station (3010), and m measurements may be performed by the terminal (3020). The terminal (3020) may store a first beam index for the codeword having the greatest intensity among the m measurements.

[0303] In step S3003, the terminal (3020) performs an RSRP report to the base station (3010). The terminal (3020) can measure reference signals transmitted through m beams and transmit the RSRP values ​​of the reference signals to the base station (3010).

[0304] In step S3005, the base station (3010) selects a beam based on an artificial intelligence model. The artificial intelligence model may be trained using an index-based neural network technique or a magnitude-based neural network technique. The base station (3010) determines the predicted optimal second beam based on the trained artificial intelligence model. In the following, steps S3001 through S3005 will be referred to as the first stage procedure, and steps S3007 through S3011, which will be described later, will be referred to as the second stage procedure.

[0305] In step S3007, the base station (3010) transmits a signal based on the determined optimal beam. Since the second beam determined in the first stage procedure is a beam predicted based on an artificial intelligence model, the base station (3010) transmits a reference signal through the second beam to measure beam performance in an actual communication environment.

[0306] In step S3009, the terminal (3020) transmits a 1-bit feedback signal to the base station (3010) based on a reference signal. The 1-bit feedback signal may be determined based on the measurement result of the reference signal and the first beam gain. It may include 1-bit information indicating which of the first beam and the second beam has a higher beam gain.

[0307] In step S3011, the base station (3010) transmits a signal to the terminal (3020) based on the selected beam. The base station (3010) can determine whether to use the second beam based on the received 1-bit information. For example, if the beam gain of the first beam is greater than the beam gain of the second beam, the base station (3010) can repeat the procedure from the first stage to search for another optimal beam. For another example, if the performance of the second beam is inferior to that of the first beam, the base station can proceed with communication using the first beam.

[0308] FIG. 31 illustrates an example of a cumulative distribution function of a two-stage partial search technique using an index-based neural network according to one embodiment of the present disclosure. FIG. 32 illustrates an example of a cumulative distribution function of a two-stage partial search technique using a magnitude-based neural network according to one embodiment of the present disclosure. Referring to FIG. 31 and FIG. 32, it can be seen that when only a direct partial search technique is used, the normalization gain drops significantly if beam inference fails. However, it is confirmed that beam performance is improved when a two-stage partial search technique is utilized.

[0309] Joint-optimization technique for transmit beam and beam inference function

[0310] The present disclosure proposes a joint optimization technique for transmit beams and beam inference functions to reduce beam search overhead and computational complexity. The joint optimization technique refers to a method of determining an off-grid codebook that changes according to the operating environment, rather than a pre-designed on-grid codebook, and simultaneously determining a beam inference function. Here, the beam inference function refers to a function that predicts a beam exhibiting high beam gain by utilizing a small number of received beam information using the determined off-grid codebook. That is, in the joint optimization technique, the transmit beams and beam inference functions corresponding to the codebook can be dynamically changed, and the objective function of the joint optimization technique can be determined based on maximizing beam gain. Here, the constraint condition of the objective function can be set so that the strength of the transmit beams is constant. The joint optimization technique can be expressed as shown in [Equation 16] below.

[0311]

[0312] In [Equation 16], represents the beam inference function, represents the expected value, and x represents the optimal beam in the communication operating environment.

[0313] The beam inference function can be approximated based on a neural network. In the beam inference function, channel h can be configured as the input, and the optimal beam x can be configured as the output. When the beam inference function is configured based on a neural network, it can be expressed as shown in [Equation 17] below.

[0314]

[0315] In [Equation 17], represents the i-th weight, and represents the i-th bias, and represents the i-th activation function.

[0316] Referring to [Equation 17], the activation function can be approximated using L layers, and the input data of the neural network can be extracted as output data by passing through L layers. At this time In the nth layer, Operations regarding weights, biases, and activation functions are performed on the input values ​​of the i-th layer, and the output values ​​resulting from these operations are passed to the next layer. Such a neural network can be designed as an autoencoder structure.

[0317] FIG. 33 illustrates an example of an approximation of a beam inference function and an auto-encoder structure according to one embodiment of the present disclosure. When a neural network is designed as an auto-encoder structure, the first layer can be viewed as an encoder layer, and layers from the second layer to the L-th layer can be viewed as decoder layers. In the first layer of the neural network, weights is a codebook generated depending on the operating environment It can be composed of. Here, bias approximates to 0, and the activation function is the absolute value function It can be set to. Codebook The transmitted beams can be reconstructed into a matrix form as shown in [Equation 18] below.

[0318]

[0319] In [Equation 18], means the k-th transmission beam.

[0320] Also, layers from the second layer to the Lth layer are beam inference functions It can be interpreted as such. Therefore, if a beam inference function such as [Equation 17], approximated to the characteristics of a neural network, is transformed into an autoencoder structure, it can be expressed as [Equation 19] below.

[0321]

[0322] In other words, if a neural network is designed as an autoencoder structure, the transmit beams and beam inference functions included in the codebook can be expressed in encoder and decoder forms, respectively.

[0323] FIG. 34 illustrates an example of an auto-encoder-based neural network structure according to one embodiment of the present disclosure. By using the aforementioned auto-encoder-based neural network technique, the transmit beams and the beam inference function can be jointly optimized. The neural network may include a complex-dense layer, a dense layer, and an absolute value function. Here, the neural network [describes] the input data, the channel, through the complex-dense layer The input data is passed through three dense layers and a ReLU (rectified linear unit) activation function to reduce dimensionality and learn the features of the input data. Here, the ReLU function refers to a function that returns the input as is if it is positive and returns 0 if it is negative. Subsequently, the neural network can be configured to extract high-dimensional data by performing operations with the three dense layers and the ReLU activation function on low-dimensional encoded information. The loss function of the neural network can be set as the mean squared error, which compares the real and imaginary parts of the input data with the output x of the neural network, and the neural network can be trained to minimize the loss function. Here, the loss function can be expressed as shown in [Equation 20] below.

[0324]

[0325] In [Mathematical Formula 20], means a function that extracts the real part, and means a function that extracts the imaginary part.

[0326] That is, in an autoencoder-based neural network model, the input may include information related to the channel between the base station and the terminal, and the output may include parameter values ​​related to the transmit beam. The parameter values ​​related to the transmit beam are parameters for determining the transmit beam and may be referred to as transmit antenna weights, transmit beamforming vectors, precoding vectors, transmit beamforming parameters, or terms having equivalent technical meanings. Additionally, the parameter values ​​related to the transmit beam may include values ​​that are not equivalent to codewords included in a pre-configured codebook. Information related to the channel between the base station and the terminal is repeatedly input, and learning can be performed such that the mean squared error of the input and output is minimized as shown in [Equation 20] above.

[0327] The weights of the first layer of the neural network model that has been trained can be set as transmission beams included in a codebook, and the remaining layers of the neural network model that has been trained can be set as beam inference functions. Thus, a beam management procedure can be performed based on a co-optimized codebook and beam inference functions. For example, in step S1301 of FIG. 13, a co-optimized codebook may be used for the measurement, and subsequently, beamforming in step S1309 of FIG. 13 can be determined through a co-optimized beam inference function.

[0328] The following describes a neural network technique for reducing beam search overhead in the spatiotemporal domain. A beam management technique in the spatiotemporal domain may include an observation phase and a prediction phase. In the observation phase, input data to be used for a beam prediction model is collected. Here, measured values ​​such as received beam gain and received beam strength may be used as input data. The observation phase may consist of T0 coherence time blocks, and in each coherence time block, the communication channel is assumed to be constant. A terminal that receives the m-th beam in the t-th coherence time block measures the strength of the received signal and reports the received beam gain to the base station. The beam gain for the m-th beam in the t-th coherence time block received by the base station can be expressed as shown in [Equation 21] below.

[0329]

[0330] In [Equation 21], represents the channel corresponding to the t-th correlation time block, and is the m-th beam of the t-th correlation time block, The mean is 0 and the variance is It refers to the received noise of the t-th correlation time block that follows a complex normal distribution.

[0331] In the prediction phase, the optimal beam is predicted based on the measurements collected in the measurement phase. In the prediction phase The optimal beam set for the correlation time blocks is expressed as shown in [Equation 22] below.

[0332]

[0333] In [Equation 22], represents the beam inference function, represents the optimal beam set determined during the prediction phase.

[0334] The present disclosure proposes a ConvLSTM (convolutional long short-term memory) neural network technique to reduce beam search overhead in the spatiotemporal domain. In the present disclosure, the ConvLSTM neural network technique refers to a technique that receives frame or time-series data of a certain size from input data and applies a convolution operation to extract multidimensional spatial information from the input time-series data. Here, an LSTM (long short-term memory) structure is applied to process temporal information using the output data of the convolution operation as input, the state and output value of the LSTM structure are updated, and the LSTM structure is applied again with the data of the next time step. Using ConvLSTM, an output containing information about the time series and the beam is generated.

[0335] In the following sections, to perform the ConvLSTM neural network technique, the criteria for collecting input data to be used in the beam prediction model and a beam inference function that predicts the optimal beam in the prediction stage using the collected data are described. The ConvLSTM neural network technique includes a measurement stage and a prediction stage. First, the measurement stage includes an initial Discrete Fourier Transform (DFT) search stage and a reduced search stage.

[0336] 1) Initial DFT search step

[0337] In the initial DFT search phase, the process takes place at the first correlation time block (t=1) of the measurement phase, and the channel angle information is extracted using the DFT codebook. The DFT codebook used at this time The i-th codeword It can be expressed as [Equation 23].

[0338]

[0339] In [Mathematical Equation 23], is the signal wavelength, means antenna spacing.

[0340] The base station A reference signal is transmitted using the DFT codewords. The terminal measures the beam strength of the reference signal and reports it to the base station. Subsequently, the base station searches for the beam with the greatest beam strength and can obtain an index indicating the angle information contained in the beam as shown in [Equation 24].

[0341]

[0342] FIG. 35 illustrates an example of extracting an index indicating angle information using an initial DFT search technique according to one embodiment of the present disclosure. Referring to FIG. 35, it is confirmed that the largest beam intensity is extracted using a DFT codeword as in [Equation 24].

[0343] 2) Reduction search step

[0344] The reduced search technique proceeds from the second (t=2) to the last (t=T0) correlation time block. Angle index obtained through the initial DFT search technique Near-field codebook corresponding to the surroundings Select at least one codeword and perform beam search as in [Equation 25].

[0345]

[0346] In [Mathematical Formula 25], represents the number of distance regions quantized in the near-field codebook.

[0347] The codewords included in the near-field codebook can be determined differently from the DFT codewords included in the initial DFT codebook. For example, the near-field codebook may be a codebook defined in the angle domain and the distance domain. The s-th distance domain near-field codeword of the n-th angle domain used in the near-field codebook can be expressed as [Equation 26].

[0348]

[0349] [Mathematical Formula 26], represents the correlation of the array response vector of the near-field channel.

[0350] Through the narrowed search step, M beam gain information points for each codeword from the second correlation time block to the last correlation time block can be obtained. The obtained M beam gain information points are used as input data for a beam prediction model, and the optimal beam can be determined through an artificial intelligence model.

[0351] FIG. 36 illustrates an example of a procedure for acquiring beam-related information based on a ConvLSTM layer according to one embodiment of the present disclosure. FIG. 36 illustrates a method performed by a base station (e.g., a RAN node (1020) and a network node (1030) of FIG. 10) that performs wireless communication. In the description with reference to FIG. 36, the operating entity is referred to as a base station, and the base station may perform a connection procedure to perform wireless communication with a terminal. Referring to FIG. 36, the base station may determine an optimal beam using a ConvLSTM neural network based on collected beam gain data.

[0352] Referring to FIG. 36, in step S3601, the base station obtains a measurement result through a measurement procedure. The measurement procedure may include the aforementioned initial DFT search step and reduced search step. Thus, the base station can obtain information regarding the beam with the greatest intensity through the initial DFT search step. Through the reduced search step, the base station determines the beam with the greatest intensity in the first correlation time block and can determine a sub-codebook corresponding to a part of the entire codebook based on the beam. Specifically, the sub-codebook may include codewords quantized in the distance domain around the angle of the beam with the greatest intensity. For example, the sub-codebook may be composed of codewords in which the difference between the angle of the beam with the greatest intensity and the angle of the beam corresponding to the codeword is less than or equal to a preset value. Subsequently, the base station may perform a beam search for the determined sub-codebook.

[0353] In step S3603, the base station processes data based on ConvLSTM layers. Specifically, the input data transmitted to the input layer of the neural network may include measurements for a subcodebook determined by a reduced search technique. For example, measurements are performed for the second time-correlation block to the last time-correlation block, and inference is performed on the measurements through three ConvLSTM layers as shown in FIG. 37.

[0354] In step S3605, the base station outputs inferred data using a Conv3D (3D Convolution) layer. The input of the Conv3D layer is set to the output data of the ConvLSTM layers as shown in Fig. 37.

[0355] In step S3607, the base station acquires beam-related information based on data inferred from the Conv3D layer. The data output from the Conv3D layer is of a pre-set correlation time block size (e.g., T in FIG. 37) from the second correlation time block to the last correlation time block. p It may include information regarding beams in consecutive correlation time blocks after ).

[0356] By using the method of Fig. 36, input data can be collected through an initial DFT search step and a reduced search step, and an optimal beam can be predicted based on a ConvLSTM neural network. This allows the overhead of beam search to be reduced in the space-time domain.

[0357] The following describes the simulation results for comparing beam management performance. The variables used in the simulation of the neural network-based partial search technique are as shown in [Table 3] below.

[0358] ParameterValueAntenna configurationULANumber of antennas = 512 Carrier frequency GHzAntenna spacing mChannel gain Path distribution , SNR ( )[-20, 20] dBChannel realization10,000Network typeCNNKernal size{3ⅹ3, 3ⅹ3, 3ⅹ3}Feature map{16, 16, 1}Input normalizationMin-max [0, 1]Batch size64Epochs200OptimizerAdamLearning rate0.001

[0359] The variables used in the simulation of the autoencoder-based neural network technique to solve the joint optimization problem of the transmit beam and beam inference function are as shown in [Table 4] below.

[0360] ParameterValueAntenna configurationULANumber of antennas = 512 Carrier frequency GHzAntenna spacing mChannel gain , Path distribution , SNR ( )[0, 20] dBChannel realization10,000Network typeComplex-dense + U-netKernal size{128}, {1024, 512, 256, 256, 512, 1024}, {1024}Activation functionReLUDropout ratio0.1Batch size128Epochs200OptimizerAdamLearning rate0.0001

[0361] The variables used in the simulation of the ConvLSTM neural network technique to reduce the overhead of beam search in the space-time domain are as shown in [Table 5] below.

[0362] ParameterValueAntenna configurationULANumber of antennas = 512 Carrier frequency GHzAntenna spacing mChannel gain UE's initial position distribution , SNR ( )10 dBChannel realization10,000UE’s velocity (m / s)5UE’s angle distribution Network typeConvLSTMKernal size{3ⅹ3, 3ⅹ3, 3ⅹ3}Feature map{32, 32, 32}Batch size128Epochs200OptimizerAdamLearning rate0.001

[0363] FIG. 38 illustrates an example of gain performance relative to the signal-to-noise ratio (SNR) of a beam management technique applying only a sparse method and a beam management technique applying an index-based neural network according to one embodiment of the present disclosure. FIG. 39 illustrates an example of achievement rate performance relative to the SNR of a beam management technique applying only a sparse method and a beam management technique applying an index-based neural network according to one embodiment of the present disclosure. In FIG. 38 and FIG. 39, normalized gain performance and achievement rate performance according to the SNR of the beam management techniques are illustrated. In FIG. 38 and FIG. 39, a beam management technique applying only a sparse method in the distance domain is labeled 'Partial (distance sparse)', and a beam management technique applying only a sparse method in the angle domain is labeled 'Partial (angle sparse)'. A beam management technique applying an index-based neural network with a sparse method in the distance domain and a direct partial search technique is labeled 'Index neural (direct, distance sparse)'. A beam management technique using an index-based neural network with an angle domain sparse method and a direct partial search technique is labeled as 'Index neural (direct, angle sparse)'. A beam management technique using an index-based neural network with a distance domain sparse method and a two-stage partial search technique is labeled as 'Index neural (two-stage, distance sparse)'. A beam management technique using an index-based neural network with an angle domain sparse method and a two-stage partial search technique is labeled as 'Index neural (two-stage, angle sparse)'. An exhaustive search technique to which the techniques of the present disclosure are not applied is labeled as 'Exhaustive search', and is labeled in the same way in the drawings below.FIG. 40 illustrates an example of normalized gain performance relative to SNR for a beam management technique applying only a sparse method and a beam management technique applying a magnitude-based neural network according to one embodiment of the present disclosure. FIG. 41 illustrates an example of achievement rate performance relative to SNR for a beam management technique applying only a sparse method and a beam management technique applying a magnitude-based neural network according to one embodiment of the present disclosure. In FIG. 40 and FIG. 41, normalized gain performance and achievement rate performance according to SNR of the beam management techniques are illustrated. In FIG. 40 and FIG. 41, a beam management technique applying only a sparse method in the distance domain is labeled 'Partial (distance sparse)', and a beam management technique applying only a sparse method in the angle domain is labeled 'Partial (angle sparse)'. A beam management technique applying a magnitude-based neural network with a sparse method in the distance domain and a direct partial search technique is labeled 'Magnitude neural (direct, distance sparse)'. A beam management technique using a magnitude-based neural network with a sparse angle domain and a direct partial search technique is denoted as 'Magnitude neural (direct, angle sparse)'. A beam management technique using a magnitude-based neural network with a sparse distance domain and a two-stage partial search technique is denoted as 'Magnitude neural (two-stage, distance sparse)'. A beam management technique using a magnitude-based neural network with a sparse angle domain and a two-stage partial search technique is denoted as 'Magnitude neural (two-stage, angle sparse)'.

[0364] As illustrated in FIGS. 38 to 41, when low-complexity beam management is performed according to an embodiment of the present invention, normalized gain performance and achievement rate performance can be increased.

[0365] FIG. 42 illustrates an example of normalized gain performance relative to overhead reduction for a beam management technique applying only a sparse method and a beam management technique applying an index-based neural network according to one embodiment of the present disclosure. FIG. 43 illustrates an example of achievement rate performance relative to overhead reduction for a beam management technique applying only a sparse method and a beam management technique applying an index-based neural network according to one embodiment of the present disclosure. In FIG. 42 and FIG. 43, normalized gain performance and achievement rate performance according to overhead reduction of the beam management technique are illustrated. In FIG. 42 and FIG. 43, a beam management technique applying only a sparse method in the distance domain is labeled 'Partial (distance sparse)', and a beam management technique applying only a sparse method in the angle domain is labeled 'Partial (angle sparse)'. A beam management technique applying an index-based neural network with a sparse method in the distance domain and a direct partial search technique is labeled 'Index neural (direct, distance sparse)'. The beam management technique using an index-based neural network with a sparse angle domain and a direct partial search technique is denoted as 'Index neural (direct, angle sparse)'. The beam management technique using an index-based neural network with a sparse distance domain and a two-stage partial search technique is denoted as 'Index neural (two-stage, distance sparse)'. The beam management technique using an index-based neural network with a sparse angle domain and a two-stage partial search technique is denoted as 'Index neural (two-stage, angle sparse)'.

[0366] FIG. 44 illustrates an example of normalized gain performance relative to overhead reduction for a beam management technique applying only a sparse method and a beam management technique applying a magnitude-based neural network according to one embodiment of the present disclosure. FIG. 45 illustrates an example of achievement rate performance relative to overhead reduction for a beam management technique applying only a sparse method and a beam management technique applying a magnitude-based neural network according to one embodiment of the present disclosure. In FIG. 44 and FIG. 45, normalized gain performance and achievement rate performance according to overhead reduction of the beam management technique are illustrated. In FIG. 44 and FIG. 45, a beam management technique applying only a sparse method in the distance domain is labeled 'Partial (distance sparse)', and a beam management technique applying only a sparse method in the angle domain is labeled 'Partial (angle sparse)'. A beam management technique applying a magnitude-based neural network with a sparse method in the distance domain and a direct partial search technique is labeled 'Magnitude neural (direct, distance sparse)'. A beam management technique using a magnitude-based neural network with a sparse angle domain and a direct partial search technique is denoted as 'Magnitude neural (direct, angle sparse)'. A beam management technique using a magnitude-based neural network with a sparse distance domain and a two-stage partial search technique is denoted as 'Magnitude neural (two-stage, distance sparse)'. A beam management technique using a magnitude-based neural network with a sparse angle domain and a two-stage partial search technique is denoted as 'Magnitude neural (two-stage, angle sparse)'.

[0367] As illustrated in FIGS. 42 to 45, when low-complexity beam management is performed according to an embodiment of the present invention, beam search overhead is reduced and beam management performance degradation can be lowered. Therefore, beam management performance in a very large-scale multi-antenna system can be significantly improved.

[0368] FIG. 46 illustrates an example of normalized gain performance relative to SNR of a beam management technique applying an autoencoder-based neural network according to one embodiment of the present disclosure. FIG. 47 illustrates an example of achievement rate performance relative to SNR of a beam management technique applying an autoencoder-based neural network according to one embodiment of the present disclosure. In FIG. 46 and FIG. 47, the beam management technique applying an autoencoder-based neural network is labeled 'Auto-encoder neural search', and the beam management technique applying a neural network with a partial search technique is labeled 'Partial neural search'. In FIG. 46 and FIG. 47, the number of codewords in the entire codebook is 4114, and the number of codewords used in beam search The overhead reduction ratio is 128. The beam gain at approximately 0.9689 is plotted. When low-complexity beam management is performed according to an embodiment of the present invention, normalized gain performance and achievement rate performance can be significantly improved as the signal-to-noise ratio increases. Therefore, beam management performance in a very large-scale multi-antenna system can be significantly improved.

[0369] FIG. 48 illustrates an example of normalized gain performance over time of a beam management technique applying ConvLSTM in the spatiotemporal domain according to an embodiment of the present disclosure. FIG. 49 illustrates an example of achievement rate performance over time of a beam management technique applying ConvLSTM in the spatiotemporal domain according to an embodiment of the present disclosure. FIG. 50 illustrates an example of normalized gain performance relative to SNR of a beam management technique applying ConvLSTM in the spatiotemporal domain according to an embodiment of the present disclosure. FIG. 51 illustrates an example of achievement rate performance relative to SNR of a beam management technique applying ConvLSTM in the spatiotemporal domain according to an embodiment of the present disclosure.

[0370] In Figures 48 to 51, a beam management technique applying ConvLSTM in the spatiotemporal domain is labeled 'Beam Prediction based ConvLSTM (Cropped)', an exhaustive search technique that narrows the beam search range to a partial area is labeled 'Exhaustive search (Cropped)', and a technique that does not perform beam prediction is labeled 'No Beam Prediction'.

[0371] As illustrated in FIGS. 48 to 51, beam management performance may be significantly degraded if beam prediction is not utilized. In the ConvLSTM-based neural network technique proposed in this disclosure, it is confirmed that performance close to the upper bound for the signal-to-noise ratio is achieved. Therefore, beam management performance can be significantly improved in a very large-scale multi-antenna system.

[0372] Hereinafter, examples of wireless device applications to which various embodiments of the present disclosure are applied will be described.

[0373] FIG. 52 illustrates an example of a wireless device applicable to the present disclosure. The wireless device may be implemented in various forms depending on the use—example / service (see FIG. 1).

[0374] Referring to FIG. 52, the wireless device (200) corresponds to the wireless device (200) of FIG. 2 and may be composed of various elements, components, units / parts, and / or modules. For example, the wireless device (200) may include a communication unit (210), a control unit (220), a memory unit (230), and additional elements (240). The communication unit may include a communication circuit (212) and transceiver(s) (214). For example, the communication circuit (212) may include one or more processors (202) and / or one or more memories (204) of FIG. 2. For example, the transceiver(s) (214) may include one or more transceivers (206) and / or one or more antennas (208) of FIG. 2. The control unit (220) is electrically connected to the communication unit (210), the memory unit (230), and additional elements (240) and controls the overall operation of the wireless device. For example, the control unit (220) can control the electrical / mechanical operation of the wireless device based on a program / code / command / information stored in the memory unit (230). Additionally, the control unit (220) can transmit information stored in the memory unit (230) to an external entity (e.g., another communication device) via a wireless / wired interface through the communication unit (210), or store information received from an external entity (e.g., another communication device) via a wireless / wired interface through the communication unit (210) in the memory unit (230).

[0375] The additional element (240) may be configured in various ways depending on the type of wireless device. For example, the additional element (240) 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. 1, 100a), a vehicle (Fig. 1, 100b-1, 100b-2), an XR device (Fig. 1, 100c), a portable device (Fig. 1, 100d), a home appliance (Fig. 1, 100e), an IoT device (Fig. 1, 100f), a digital broadcasting terminal, a hologram device, a public safety device, an MTC device, a medical device, a fintech device (or financial device), a security device, a climate / environment device, an AI server / device (Fig. 1, 400), a base station (Fig. 1, 200), a network node, etc. Depending on the use—e.g., service—the wireless device may be movable or used in a fixed location.

[0376] In FIG. 52, various elements, components, units / parts, and / or modules within the wireless device (200) may be entirely interconnected via a wired interface, or at least partially connected via a communication unit (210). For example, within the wireless device (200), the control unit (220) and the communication unit (210) may be connected via a wire, and the control unit (220) and the first unit (e.g., 230, 240) may be connected wirelessly via the communication unit (210). Additionally, each element, component, unit / part, and / or module within the wireless device (200) may include one or more additional elements. For example, the control unit (220) may be composed of one or more sets of processors. For example, the control unit (220) 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.

[0377] Hereinafter, an implementation example of FIG. 52 will be described in more detail with reference to the drawings.

[0378] FIG. 53 illustrates an example of a portable device applicable to the present disclosure. A portable device may include a smartphone, a smartpad, a wearable device (e.g., a smartwatch, smart glasses), or a portable computer (e.g., a laptop). A portable device may be referred to as a Mobile Station (MS), a User Terminal (UT), a Mobile Subscriber Station (MSS), a Subscriber Station (SS), an Advanced Mobile Station (AMS), or a Wireless Terminal (WT).

[0379] Referring to FIG. 53, the portable device (200) may include an antenna unit (208), a communication unit (210), a control unit (220), a memory unit (230), a power supply unit (240a), an interface unit (240b), and an input / output unit (240c). The antenna unit (208) may be configured as part of the communication unit (210). Blocks 210 to 230 / 240a to 240c of FIG. 53 correspond to blocks 210 to 230 / 240 of FIG. 52, respectively.

[0380] The communication unit (210) can transmit and receive signals (e.g., data, control signals, etc.) with other wireless devices and base stations. The control unit (220) can control the components of the portable device (200) to perform various operations. The control unit (220) may include an AP (Application Processor). The memory unit (230) can store data / parameters / programs / code / commands required for the operation of the portable device (200). Additionally, the memory unit (230) can store input / output data / information, etc. The power supply unit (240a) supplies power to the portable device (200) and may include wired / wireless charging circuits, batteries, etc. The interface unit (240b) can support the connection between the portable device (200) and other external devices. The interface unit (240b) may include various ports (e.g., audio input / output ports, video input / output ports) for connection with external devices. The input / output unit (240c) can receive or output video information / signals, audio information / signals, data, and / or information input by a user. The input / output unit (240c) may include a camera, a microphone, a user input unit, a display unit (240d), a speaker and / or a haptic module, etc.

[0381] For example, in the case of data communication, the input / output unit (240c) acquires information / signals (e.g., touch, text, voice, image, video) input by the user, and the acquired information / signals can be stored in the memory unit (230). The communication unit (210) converts the information / signals stored in the memory into wireless signals and can directly transmit the converted wireless signals to another wireless device or to a base station. Additionally, the communication unit (210) can receive wireless signals from another wireless device or base station and then restore the received wireless signals to their original information / signals. The restored information / signals are stored in the memory unit (230) and then can be output in various forms (e.g., text, voice, image, video, haptic) through the input / output unit (240c).

[0382] FIG. 54 illustrates an example of a vehicle or autonomous vehicle applicable to the present disclosure. The vehicle or autonomous vehicle may be implemented as a mobile robot, a vehicle, a train, an aerial vehicle (AV), a ship, etc.

[0383] Referring to FIG. 54, a vehicle or autonomous vehicle (200-1) may include an antenna unit (208-1), a communication unit (210-1), a control unit (220-1), a driving unit (240a-1), a power supply unit (240b-1), a sensor unit (240c-1), and an autonomous driving unit (240d-1). The antenna unit (208-1) may be configured as part of the communication unit (210-1). Blocks 210-1 / 230-1 / 240a-1 to 240d-1 of FIG. 54 correspond to blocks 210 / 230 / 240 of FIG. 52, respectively.

[0384] The communication unit (210-1) can transmit and receive signals (e.g., data, control signals, etc.) with external devices such as other vehicles, base stations (e.g., base stations, roadside base stations (Road Side Unit), etc.), and servers. The control unit (220-1) can perform various operations by controlling elements of the vehicle or autonomous vehicle (200-1). The control unit (220-1) may include an Electronic Control Unit (ECU). The driving unit (240a-1) can drive the vehicle or autonomous vehicle (200-1) on the ground. The driving unit (240a-1) may include an engine, motor, power train, wheels, brakes, steering device, etc. The power supply unit (240b-1) supplies power to the vehicle or autonomous vehicle (200-1) and may include wired / wireless charging circuits, batteries, etc. The sensor unit (240c-1) can obtain vehicle status, surrounding environment information, user information, etc. The sensor unit (240c-1) may include an IMU (inertial measurement unit) sensor, a collision sensor, a wheel sensor, a speed sensor, an inclination sensor, a weight detection sensor, a heading sensor, a position module, a vehicle forward / reverse 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 (240d-1) may implement technologies such as maintaining the driving lane, technologies for automatically adjusting speed such as adaptive cruise control, technologies for automatically driving along a predetermined path, and technologies for automatically setting a path and driving when a destination is set.

[0385] For example, the communication unit (210-1) can receive map data, traffic information data, etc. from an external server. The autonomous driving unit (240d-1) can generate an autonomous driving path and a driving plan based on the acquired data. The control unit (220-1) can control the drive unit (240a-1) so that the vehicle or the autonomous vehicle (200-1) moves along the autonomous driving path according to the driving plan (e.g., speed / direction control). During autonomous driving, the communication unit (210-1) can acquire the latest traffic information data from an external server non-periodically and can acquire surrounding traffic information data from surrounding vehicles. Additionally, during autonomous driving, the sensor unit (240c-1) can acquire vehicle status and surrounding environment information. The autonomous driving unit (240d-1) can update the autonomous driving path and the driving plan based on the newly acquired data / information. The communication unit (210-1) can transmit information regarding the vehicle location, autonomous driving path, driving plan, etc. to an external server. An external server can predict traffic information data in advance using AI technology, etc., based on information collected from vehicles or autonomous vehicles, and can provide the predicted traffic information data to vehicles or autonomous vehicles. If the device (220-2) is an autonomous vehicle, it can perform the same procedure as the vehicle or autonomous vehicle (200-1). In addition, if the device (220-2) is a base station or a roadside base station, the device (220-2) can transmit data and control signals to the vehicle or autonomous vehicle (200-1) through the communication unit (210-2).

[0386] FIG. 55 illustrates an example of a vehicle applicable to the present disclosure. The vehicle may be implemented as a means of transport, a train, an aircraft, a ship, etc. Referring to FIG. 55, the vehicle (200) may include a communication unit (210), a control unit (220), a memory unit (230), an input / output unit (240a), and a position measurement unit (240b). Here, blocks 210 to 230 / 240a to 240b correspond to blocks 210 to 230 / 240 of FIG. 52, respectively.

[0387] The communication unit (210) can transmit and receive signals (e.g., data, control signals, etc.) with other vehicles or external devices such as base stations. The control unit (220) can control the components of the vehicle (200) to perform various operations. The memory unit (230) can store data / parameters / programs / codes / commands that support various functions of the vehicle (100). The input / output unit (240a) can output AR / VR objects based on information within the memory unit (230). The input / output unit (240a) may include a HUD. The position measurement unit (240b) can acquire position information of the vehicle (200). The position information may include absolute position information of the vehicle (200), position information within the driving line, acceleration information, position information relative to surrounding vehicles, etc. The position measurement unit (240b) may include GPS and various sensors.

[0388] For example, the communication unit (210) of the vehicle (200) can receive map information, traffic information, etc. from an external server and store it in the memory unit (230). The location measurement unit (240b) can acquire vehicle location information through GPS and various sensors and store it in the memory unit (230). The control unit (220) creates a virtual object based on map information, traffic information, and vehicle location information, etc., and the input / output unit (240a) can display the created virtual object on the glass window inside the vehicle (240a-1, 240a-2). In addition, the control unit (220) can determine whether the vehicle (200) is operating normally within the driving line based on the vehicle location information. If the vehicle (200) deviates abnormally from the driving line, the control unit (220) can display a warning on the glass window inside the vehicle through the input / output unit (240a). Additionally, the control unit (220) can broadcast a warning message regarding a driving abnormality to surrounding vehicles through the communication unit (210). Depending on the situation, the control unit (220) can transmit the vehicle's location information and information regarding the driving / vehicle abnormality to relevant authorities through the communication unit (210).

[0389] FIG. 56 illustrates an example of an XR device applicable to the present disclosure. The XR device may be implemented as an HMD, a Head-Up Display (HUD) equipped in a vehicle, a television, a smartphone, a computer, a wearable device, a home appliance, digital signage, a vehicle, a robot, etc.

[0390] Referring to FIG. 56, the XR device (200a) may include a communication unit (210), a control unit (220), a memory unit (230), an input / output unit (240a), a sensor unit (240b), and a power supply unit (240c). Here, blocks 210 to 230 / 240a to 240c of FIG. 56 correspond to blocks 210 to 230 / 240 of FIG. 52, respectively.

[0391] The communication unit (210) can transmit and receive signals (e.g., media data, control signals, etc.) with external devices such as other wireless devices, mobile devices, or media servers. The media data may include video, images, sound, etc. The control unit (220) can control the components of the XR device (200a) to perform various operations. For example, the control unit (220) may be configured to control and / or perform procedures such as video / image acquisition, (video / image) encoding, metadata generation, and processing. The memory unit (230) may store data / parameters / programs / code / commands required for driving the XR device (200a) or creating an XR object. The input / output unit (240a) acquires control information, data, etc. from the outside and can output the created XR object. The input / output unit (240a) may include a camera, microphone, user input unit, display unit, speaker and / or haptic module, etc. The sensor unit (240b) can obtain XR device status, surrounding environment information, user information, etc. The sensor unit (240b) may include a proximity sensor, an illuminance sensor, an accelerometer, a magnetic sensor, a gyroscope, an inertial sensor, an RGB sensor, an IR sensor, a fingerprint recognition sensor, an ultrasonic sensor, a light sensor, a microphone and / or radar, etc. The power supply unit (240c) supplies power to the XR device (200a) and may include a wired / wireless charging circuit, a battery, etc.

[0392] For example, the memory unit (230) of the XR device (200a) may contain information (e.g., data, etc.) necessary for creating an XR object (e.g., AR / VR / MR object). The input / output unit (240a) may receive a command to operate the XR device (200a) from the user, and the control unit (220) may operate the XR device (200a) according to the user's operation command. For example, if the user intends to watch movies, news, etc. through the XR device (200a), the control unit (220) may transmit content request information to another device (e.g., mobile device (200b)) or a media server through the communication unit (230). The communication unit (230) may download / stream content such as movies, news, etc. from another device (e.g., mobile device (200b)) or a media server to the memory unit (230). The control unit (220) controls and / or performs procedures such as video / image acquisition, (video / image) encoding, and metadata generation / processing for the content, and can generate / output an XR object based on information about the surrounding space or real object acquired through the input / output unit (240a) / sensor unit (240b).

[0393] Additionally, the XR device (200a) is wirelessly connected to the mobile device (200b) through the communication unit (210), and the operation of the XR device (200a) can be controlled by the mobile device (200b). For example, the mobile device (200b) can act as a controller for the XR device (200a). To this end, the XR device (200a) can acquire three-dimensional position information of the mobile device (200b), and then generate and output an XR object corresponding to the mobile device (200b).

[0394] FIG. 57 illustrates an example of a robot applicable to the present disclosure. Robots may be classified into industrial, medical, domestic, military, etc., depending on the purpose or field of use.

[0395] Referring to FIG. 57, the robot (200) may include a communication unit (210), a control unit (220), a memory unit (230), an input / output unit (240a), a sensor unit (240b), and a driving unit (240c). Here, blocks 210 to 230 / 240a to 240c of FIG. 57 correspond to blocks 210 to 230 / 240 of FIG. 52, respectively.

[0396] The communication unit (210) can transmit and receive signals (e.g., driving information, control signals, etc.) with external devices such as other wireless devices, other robots, or control servers. The control unit (220) can control the components of the robot (200) to perform various operations. The memory unit (230) can store data / parameters / programs / codes / commands that support various functions of the robot (200). The input / output unit (240a) can acquire information from outside the robot (200) and output information to outside the robot (200). The input / output unit (240a) may include a camera, microphone, user input unit, display unit, speaker and / or haptic module, etc. The sensor unit (240b) can obtain internal information of the robot (200), surrounding environment information, user information, etc. The sensor unit (240b) may include a proximity sensor, an illuminance sensor, an accelerometer, a magnetic sensor, a gyroscope, an inertial sensor, an IR sensor, a fingerprint recognition sensor, an ultrasonic sensor, a light sensor, a microphone, a radar, etc. The driving unit (240c) may perform various physical movements, such as moving robot joints. Additionally, the driving unit (240c) may enable the robot (200) to travel on the ground or fly in the air. The driving unit (240c) may include an actuator, a motor, a wheel, a brake, a propeller, etc.

[0397] FIG. 58 illustrates an example of an AI device applicable to the present disclosure.

[0398] AI devices can be implemented as stationary devices or mobile devices, such as TVs, projectors, smartphones, PCs, laptops, digital broadcasting terminals, tablet PCs, wearable devices, set-top boxes (STBs), radios, washing machines, refrigerators, digital signage, robots, vehicles, etc.

[0399] Referring to FIG. 58, the AI ​​device (200) may include a communication unit (210), a control unit (220), a memory unit (230), an input / output unit (240a / 240b), a learning processor unit (240c), and a sensor unit (240d). Blocks 210 to 230 / 240a to 240d of FIG. 58 correspond to blocks 210 to 230 / 140 of FIG. 52, respectively.

[0400] The communication unit (210) can transmit and receive wired and wireless signals (e.g., sensor information, user input, learning model, control signal, etc.) with external devices such as other AI devices (e.g., 100a to 100f, 120 in FIG. 1) or AI servers (e.g., 100g in FIG. 1) using wired and wireless communication technology. To this end, the communication unit (210) can transmit information within the memory unit (230) to an external device or transmit signals received from an external device to the memory unit (230).

[0401] The control unit (220) can determine at least one executable operation of the AI ​​device (200) based on information determined or generated using a data analysis algorithm or a machine learning algorithm. The control unit (220) can perform the determined operation by controlling the components of the AI ​​device (200). For example, the control unit (220) can request, search, receive, or utilize data from the learning processor unit (240c) or the memory unit (230), and can control the components of the AI ​​device (200) to execute a predicted operation or an operation determined to be desirable among at least one executable operation. Additionally, the control unit (220) can collect historical information, including the operation content of the AI ​​device (200) or user feedback regarding the operation, and store it in the memory unit (230) or the learning processor unit (240c), or transmit it to an external device such as an AI server (Fig. 1, 100g). The collected historical information can be used to update the learning model.

[0402] The memory unit (230) can store data that supports various functions of the AI ​​device (200). For example, the memory unit (230) can store data obtained from the input unit (240a), data obtained from the communication unit (210), output data from the learning processor unit (240c), and data obtained from the sensing unit (140). Additionally, the memory unit (230) can store control information and / or software code required for the operation / execution of the control unit (220).

[0403] The input unit (240a) can acquire various types of data from outside the AI ​​device (200). For example, the input unit (220) can acquire training data for model training and input data to which the training model is applied. The input unit (240a) may include a camera, a microphone and / or a user input unit, etc. The output unit (240b) can generate output related to visual, auditory, or tactile senses, etc. The output unit (240b) may include a display unit, a speaker and / or a haptic module, etc. The sensing unit (140d) can obtain at least one of internal information of the AI ​​device (200), surrounding environment information of the AI ​​device (200), and user information using various sensors. The sensing unit (140d) may include a proximity sensor, an illuminance sensor, an accelerometer, a magnetic sensor, a gyroscope, an inertial sensor, an RGB sensor, an IR sensor, a fingerprint recognition sensor, an ultrasonic sensor, a light sensor, a microphone and / or radar, etc.

[0404] The learning processor unit (240c) can train a model composed of an artificial neural network using training data. The learning processor unit (240c) can perform AI processing together with the learning processor unit of the AI ​​server (Fig. 1, 100g). The learning processor unit (240c) can process information received from an external device through the communication unit (210) and / or information stored in the memory unit (230). Additionally, the output value of the learning processor unit (240c) can be transmitted to an external device through the communication unit (210) and / or stored in the memory unit (230).

[0405] The proposed methods described above may be implemented independently, but they may also be implemented in the form of a combination (or merger) of some of the proposed methods. Rules may be defined so that the base station informs the terminal of the application status of the proposed methods (or information regarding the rules of the proposed methods) through a predefined signal (e.g., a physical layer signal or an upper layer signal).

[0406] The present disclosure may be embodied in other specific forms without departing from the technical ideas and essential features described herein. Accordingly, the above detailed description should not be interpreted restrictively in all respects and should be considered illustrative. The scope of the present disclosure shall be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present disclosure are included within the scope of the present disclosure. Furthermore, embodiments may be constructed by combining claims that are not explicitly related in the claims, or new claims may be included by amendments made after filing.

[0407] One embodiment can be applied to various wireless access systems. Examples of various wireless access systems include the 3GPP (3rd Generation Partnership Project) or 3GPP2 system.

[0408] One embodiment can be applied not only to the various wireless access systems mentioned above, but also to all technical fields utilizing the various wireless access systems. Furthermore, the proposed method can be applied to mmWave and THz communication systems utilizing the ultra-high frequency band.

[0409] Additionally, some embodiments may be applied to various applications such as autonomous vehicles and drones.

Claims

1. Regarding the method, Step of determining setting information related to measurement; A step of transmitting the above setting information to the terminal; A step of transmitting a reference signal to the terminal based on the setting information; A step of receiving information related to a measurement result generated based on the reference signal from the terminal; and The method includes the step of transmitting or receiving a first signal to the terminal based on the above measurement result, The above reference signal is transmitted based on codewords defined for each of the angle region and distance region, and The above first signal is a method of transmitting or receiving based on a first beam determined using an artificial intelligence model.

2. In Paragraph 1, The above setting information includes information regarding a sub-codebook determined based on at least one codeword among all codewords in the entire codebook, and The above-mentioned entire codebook is a method comprising all codewords determined for each of the entire angle area and the entire distance area.

3. In Paragraph 2, The above sub-codebook is determined based on codewords of a selected portion of the distance area among the above entire distance area.

4. In Paragraph 3, It further includes a step of determining the maximum number of codewords to be selected according to the angle, but, A method in which the codewords of the above-mentioned distance regions are selected such that the index of the distance region increases by a constant amount based on the maximum number in a specific angle region.

5. In Paragraph 2, The above sub-codebook is determined based on codewords of selected partial angle regions among the entire angle region.

6. In Paragraph 5, A method in which codewords of some angle regions are selected such that the index related to the angle region among the entire angle region increases by a constant amount.

7. In Paragraph 2, The above sub-codebook is determined based on selected codewords among the above total distance area and the above total angle area, and A method in which the above-mentioned selected codewords are determined based on the sum of the index related to the distance area and the index related to the angle area and an overhead control variable.

8. In Paragraph 2, The input to the above artificial intelligence model includes information related to measurement results related to the above sub-codebook, and The output of the above artificial intelligence model includes information related to a first codeword determined based on measurement results related to the above sub-codebook, and The above first beam is formed based on the above first codeword.

9. In Paragraph 8, The information related to the first codeword includes the index value of the first codeword inferred through the artificial intelligence model based on the one-hot encoding technique, and The above first codeword is a method that has the greatest beam gain among all codewords.

10. In Paragraph 2, The input to the above artificial intelligence model includes information related to measurement results related to the above sub-codebook, and The output of the artificial intelligence model includes beam gains corresponding to the entire codewords determined based on measurement results related to the sub-codebook, and A method in which the first beam is formed based on a first codeword corresponding to the largest value of the beam gain among the total beam gains.

11. In Paragraph 1, A step of receiving a feedback signal for the first signal from the terminal; A step of selecting a second beam based on the above feedback signal; and A method further comprising the step of transmitting a second signal based on the second beam.

12. In Paragraph 11, A method in which the above feedback signal includes 1 bit indicating whether the measurement result of the first signal and the measurement result of the second signal are greater or less.

13. In Paragraph 1, A method in which a codebook containing the above codeword is determined based on the weights of the first layer of the artificial intelligence model.

14. In Paragraph 13, The above artificial intelligence model includes an autoencoder-based neural network model, and The input of the above autoencoder-based neural network model includes information related to the channel between the base station and the terminal, and The output of the above autoencoder-based neural network model includes parameter values ​​related to at least one transmission beam, and The above-described autoencoder-based neural network model is a method in which learning is performed such that the mean squared error of the input and the output is minimized.

15. In Paragraph 13, The above setting information includes information regarding the above codebook, and The above reference signal is transmitted based on the codebook, and The above first beam is determined by using the remaining layers of the artificial intelligence model based on the above measurement results.

16. In Paragraph 1, A step of extracting an index indicating the angle information of the codeword with the greatest intensity within the initial DFT (discrete Fourier transform) codebook based on the measurement results of the first correlation time block; A step of determining a codebook corresponding to a part of a codebook defined in an angle domain and a distance domain based on an index indicating the above angle information; A step of obtaining beam gain information for each of the codewords included in the above-determined codebook; and A method further comprising the step of determining the first beam through the artificial intelligence model that takes the beam gain information as input.

17. In Paragraph 16, A method in which the beam gain information includes measurement results in a second correlation time block to a last correlation time block for each of the codewords included in the determined codebook.

18. In Paragraph 16, The above artificial intelligence model includes a ConvLSTM (convolutional long short-term memory) neural network, and The input to the above ConvLSTM neural network is a measurement result regarding the second correlation time block to the last correlation time block, and A method in which the output of the above ConvLSTM neural network includes information regarding beams in consecutive correlation time blocks after a pre-set correlation time block size in the second correlation time block to the last correlation time block.

19. Regarding the method, A step of receiving setting information related to measurement from a base station; A step of receiving a reference signal from the base station based on the setting information; A step of performing a measurement based on the above reference signal; A step of transmitting information related to the measurement result to the above base station; and The method includes the step of transmitting or receiving a first signal to or from the base station based on the above measurement results, The above reference signal is transmitted based on codewords defined for each of the angle region and distance region, and The above first signal is a method of transmitting or receiving based on a first beam determined using an artificial intelligence model.

20. In the device, Transmitter / receiver; and It includes a processor connected to the above-mentioned transmitter and receiver, The above processor is, Determine the setting information related to the measurement, and Transmit the above setting information to the terminal, and Transmitting a reference signal to the above terminal based on the above setting information, and Receive information related to the measurement result generated based on the reference signal from the above terminal, and Configured to transmit or receive a first signal to the terminal based on the above measurement results, The above reference signal is transmitted based on codewords defined for each of the angle region and distance region, and The above first signal is a device that transmits or receives based on a first beam determined using an artificial intelligence model.

21. In the device, Transmitter / receiver; and It includes a processor connected to the above-mentioned transmitter and receiver, The above processor is, Receives setting information related to measurement from the base station, and Receive a reference signal from the above base station based on the above setting information, and Measurements are performed based on the above reference signal, and Transmit information related to the measurement results to the above base station, and Configured to transmit or receive a first signal to the base station based on the above measurement results, The above first signal is a device that transmits or receives based on a first beam determined using an artificial intelligence model.

22. Regarding base stations, At least one processor; It includes at least one computer memory connected to the at least one processor and storing instructions that direct operations as they are executed by the at least one processor, The above operations are, Step of determining setting information related to measurement; A step of transmitting the above setting information to the terminal; A step of transmitting a reference signal to the terminal based on the setting information; A step of receiving information related to a measurement result generated based on the reference signal from the terminal; and The method includes the step of transmitting or receiving a first signal to the terminal based on the above measurement result, The above reference signal is transmitted based on codewords defined for each of the angle region and distance region, and The above first signal is a base station that transmits or receives based on a first beam determined using an artificial intelligence model.

23. In a non-transitory computer-readable medium storing at least one instruction, It includes at least one instruction executable by a processor, The above at least one instruction is, the device, Determine the setting information related to the measurement, and Transmit the above setting information to the terminal, and Transmitting a reference signal to the above terminal based on the above setting information, and Receive information related to the measurement result generated based on the reference signal from the above terminal, and Configured to transmit or receive a first signal to the terminal based on the above measurement results, The above reference signal is transmitted based on codewords defined for each of the angle region and distance region, and The first signal is a computer-readable medium that transmits or receives based on a first beam determined using an artificial intelligence model.

Images