Method and device for transmitting sensing data in isac

Abstract

A method by which a first device performs wireless communication and an apparatus for supporting same are provided. The first device can receive, from a second device, sensing data and information related to a first model related to a model parameter, acquire the sensing data on the basis of sensing of an object, acquire the model parameter by inputting the sensing data into the first model, and / or transmit the model parameter to the second device.

Description

Method and device for transmitting sensing data in ISAC

[0001] The present disclosure relates to a wireless communication system.

[0002] 5G NR, the successor to LTE (long-term evolution), is a new clean-slate mobile communications system characterized by high performance, low latency, and high availability. 5G NR can utilize all available spectrum resources, from low-frequency bands below 1 GHz, mid-frequency bands between 1 GHz and 10 GHz, and high-frequency (millimeter wave) bands above 24 GHz.

[0003] The 6G (wireless communication) system aims to achieve (i) very high data rates per device, (ii) a very large number of connected devices, (iii) global connectivity, (iv) very low latency, (v) low energy consumption for battery-free Internet of Things (IoT) devices, (vi) ultra-reliable connectivity, and (vii) connected intelligence with machine learning capabilities. The vision of the 6G system can be divided into four aspects: intelligent connectivity, deep connectivity, holographic connectivity, and ubiquitous connectivity, and the 6G system can satisfy the requirements as shown in Table 1 below. For example, Table 1 can represent an example of the requirements of a 6G system.

[0004] Maximum data rate per device: 1 Tbps, E2E latency: 1 ms, Maximum spectral efficiency: 100 bps / Hz, Mobility support: Up to 1000 km / hr, Satellite integration: Fully AI, Fully autonomous driving, Fully XR, Fully haptic communication

[0005] According to one embodiment of the present disclosure, a method may be provided. For example, the method may include at least one of: a first device receiving, from a second device, information related to a first model associated with sensed data and model parameters; a step of the first device obtaining the sensed data based on sensing of an object; a step of the first device inputting the sensed data into the first model to obtain the model parameters; and / or a step of the first device transmitting the model parameters to the second device.

[0006] According to one embodiment of the present disclosure, a first device may be provided. For example, the first device may include at least one transceiver; at least one processor; and at least one memory coupled to the at least one processor and storing instructions. For example, the instructions may cause the first device to perform operations based on execution by the at least one processor. For example, the operations may include at least one of: receiving, from a second device, information related to a first model related to sensed data and model parameters; acquiring the sensed data based on sensing an object; inputting the sensed data into the first model to acquire the model parameters; and / or transmitting the model parameters to the second device.

[0007] According to one embodiment of the present disclosure, a processing device may be provided. For example, the processing device may include at least one processor; and at least one memory coupled to the at least one processor and storing instructions. For example, the instructions may cause a first device to perform an operation based on execution by the at least one processor. For example, the operation may include at least one of: receiving, from a second device, information related to a first model related to sensed data and model parameters; acquiring the sensed data based on sensing an object; inputting the sensed data into the first model to acquire the model parameters; and / or transmitting the model parameters to the second device.

[0008] According to one embodiment of the present disclosure, a non-transitory computer-readable storage medium having instructions recorded thereon may be provided. For example, the instructions, upon execution, may cause a first device to perform an operation. For example, the operation may include at least one of: receiving, from a second device, information related to a first model related to sensed data and model parameters; acquiring the sensed data based on sensing an object; inputting the sensed data into the first model to acquire the model parameters; and / or transmitting the model parameters to the second device.

[0009] Figure 1 illustrates a device-to-device communication procedure according to one embodiment of the present disclosure.

[0010] FIG. 2 illustrates a radio protocol architecture according to one embodiment of the present disclosure.

[0011] FIG. 3 illustrates the structure of a wireless frame according to one embodiment of the present disclosure.

[0012] FIG. 4 illustrates a slot structure of a frame according to one embodiment of the present disclosure.

[0013] FIG. 5 illustrates an example of a BWP according to one embodiment of the present disclosure.

[0014] FIG. 6 illustrates a communication structure that can be provided in a 6G system according to one embodiment of the present disclosure.

[0015] FIG. 7 illustrates an example of a communication scenario based on a 6G system according to one embodiment of the present disclosure.

[0016] FIG. 8 illustrates an example of a sensing operation according to one embodiment of the present disclosure.

[0017] FIG. 9 illustrates the relationship between RCS, distance (D), and power according to one embodiment of the present disclosure.

[0018] FIG. 10 illustrates a functional framework for AI / ML (Artificial Intelligence and Machine Learning) according to one embodiment of the present disclosure.

[0019] FIG. 11 illustrates a sensing structure and procedure according to one embodiment of the present disclosure.

[0020] FIG. 12 illustrates a method for a first device to perform wireless communication according to one embodiment of the present disclosure.

[0021] FIG. 13 illustrates a method for a second device to perform wireless communication according to one embodiment of the present disclosure.

[0022] Fig. 14 illustrates a communication system (1) according to one embodiment of the present disclosure.

[0023] FIG. 15 illustrates a wireless device according to an embodiment of the present disclosure.

[0024] FIG. 16 illustrates a signal processing circuit for a transmission signal according to one embodiment of the present disclosure.

[0025] FIG. 17 illustrates a wireless device according to one embodiment of the present disclosure.

[0026] FIG. 18 illustrates a mobile device according to one embodiment of the present disclosure.

[0027] In this disclosure, "A or B" can mean "only A," "only B," or "both A and B." In other words, "A or B" in this disclosure can be interpreted as "A and / or B." For example, "A, B or C" in this disclosure can mean "only A," "only B," "only C," or "any combination of A, B and C."

[0028] As used herein, a slash ( / ) or a comma may mean "and / or." For example, "A / B" may mean "A and / or B." Accordingly, "A / B" may mean "only A," "only B," or "both A and B." For example, "A, B, C" may mean "A, B, or C."

[0029] In the present disclosure, “at least one of A and B” may mean “only A,” “only B,” or “both A and B.” Additionally, in the present disclosure, the expressions “at least one of A or B” or “at least one of A and / or B” may be interpreted identically to “at least one of A and B.”

[0030] Additionally, in the present disclosure, “at least one of A, B and C” can mean “only A,” “only B,” “only C,” or “any combination of A, B and C.” Additionally, “at least one of A, B or C” or “at least one of A, B and / or C” can mean “at least one of A, B and C.”

[0031] Additionally, parentheses used in the present disclosure may mean "for example." Specifically, when indicated as "control information (PDCCH)", "PDCCH" may be proposed as an example of "control information." In other words, "control information" in the present disclosure is not limited to "PDCCH," and "PDCCH" may be proposed as an example of "control information." Furthermore, even when indicated as "control information (i.e., PDCCH)", "PDCCH" may be proposed as an example of "control information."

[0032] In the following explanation, ‘when, if, in case of’ can be replaced with ‘based on’.

[0033] Technical features individually described in one drawing in this disclosure may be implemented individually or simultaneously.

[0034] In the present disclosure, higher layer parameters may be parameters set for the terminal, preset, or predefined. For example, a base station or network may transmit higher layer parameters to the terminal. For example, the higher layer parameters may be transmitted via radio resource control (RRC) signaling or medium access control (MAC) signaling.

[0035] In the present disclosure, "setting or defining" may be interpreted as being set or preset to a device through predefined signaling (e.g., SIB, MAC, RRC, DCI (downlink control information), etc.) from a base station or a network. In the present disclosure, "setting or defining" may be interpreted as being set or preset to a device through predefined signaling (e.g., MAC, RRC, SCI (sidelink control information), device-to-device signaling control information, etc.) from another device. In the present disclosure, "setting or defining" may be interpreted as being set or preset to a device.

[0036] In the present disclosure, a user equipment (UE) may refer to a device, a portable device, a wireless device, etc. In the present disclosure, a base station (BS) may refer to a radio access network (RAN) node, a non-terrestrial network (NTN) cell / node, a transmission reception point (TRP), a network, an integrated access and backhaul (IAB) node, a device, a portable device, a wireless device, etc.

[0037] The technology proposed in the present disclosure can be used in various wireless communication systems such as CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), and SC-FDMA (single carrier frequency division multiple access). CDMA can be implemented with wireless technologies such as UTRA (universal terrestrial radio access) or CDMA2000. TDMA can be implemented with wireless technologies such as GSM (global system for mobile communications) / GPRS (general packet radio service) / EDGE (enhanced data rates for GSM evolution). OFDMA can be implemented with wireless technologies such as IEEE (Institute of Electrical and Electronics Engineers) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802-20, E-UTRA (evolved UTRA), LTE (long term evolution), and 5G NR.

[0038] The technology proposed in this disclosure can be implemented with 6G wireless technology and applied to various 6G systems. For example, 6G systems can have key factors such as enhanced mobile broadband (eMBB), ultra-reliable low latency communications (URLLC), massive machine-type communication (mMTC), artificial intelligence (AI) integrated communication, tactile internet, high throughput, high network capacity, high energy efficiency, low backhaul and access network congestion, and enhanced data security.

[0039] FIG. 1 illustrates a device-to-device communication procedure according to one embodiment of the present disclosure. The embodiment of FIG. 1 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted.

[0040] Referring to FIG. 1, in step S101, a first device and a second device can perform synchronization. For example, the first device can be a terminal and / or at least one of the devices proposed in the present disclosure. For example, the second device can be a base station, a network, a RAN node, an NTN node / cell, a TRP, a terminal and / or at least one of the devices proposed in the present disclosure. For example, the first device can perform an initial cell search operation. For example, the first device can detect at least one synchronization signal transmitted by the second device according to a predefined rule. Here, for example, the synchronization signal can include a plurality of synchronization signals classified according to a structure or purpose (e.g., a primary synchronization signal, a secondary synchronization signal, etc.). Through this, the first device can identify the boundaries of the frame, subframe, time unit, slot, and / or symbol of the second device, and the first device can obtain information about the second device (e.g., a cell identifier).

[0041] In step S103, the first device can obtain system information transmitted by the second device. For example, the system information may include information related to the properties, characteristics, and / or capabilities of the second device required to connect to the second device and use the service. For example, the system information may be classified according to content (e.g., whether it is essential for connection), transmission structure (e.g., the channel used, whether it is provided on-demand), etc. For example, the system information may be classified into a master information block (MIB) and a system information block (SIB). For example, if necessary, the first device may transmit a signal requesting system information before receiving the system information. For example, the request and provision of system information may be performed after a random access procedure described below.

[0042] In step S105, the first device and the second device can perform a random access procedure. For example, the first device can transmit and / or receive at least one message (e.g., a random access preamble, a random access response message, etc.) for the random access procedure based on information related to a random access channel of the second device obtained through system information (e.g., channel location, channel structure, structure of supported preamble, etc.). For example, the first device can transmit a preamble (e.g., Msg1) through the random access channel, the first device can receive a random access response message (e.g., Msg2), the first device can transmit a message (e.g., Msg3) including information related to the first device (e.g., identification information) to the second device using scheduling information included in the random access response message, and the first device can receive a message (e.g., Msg4) for contention resolution and / or connection establishment. For example, Msg1 and Msg3 can be sent and received as one message (e.g., MsgA), and / or Msg2 and Msg4 can be sent and received as one message (e.g., MsgB).

[0043] In step S107, the first device and the second device may perform signaling of control information. Here, for example, the control information may be defined in various layers, such as a layer that controls a connection (e.g., a radio resource control (RRC) layer), a layer that handles mapping between logical channels and transport channels (e.g., a media access control (MAC) layer), a layer that handles physical channels (e.g., a physical (PHY) layer), etc. For example, the first device and the second device may perform at least one of signaling for establishing a connection, signaling for determining settings related to communication, and / or signaling for indicating allocated resources. For example, the control information may be signaled / transmitted via a control channel. For example, the control information and / or the control channel may be used to schedule at least one of data, a data channel (e.g., a shared channel), and / or control information on the data channel.

[0044] In step S109, the first device and the second device may transmit and / or receive data. For example, the first device and the second device may process, transmit, and / or receive data based on signaling of control information. For example, when transmitting data, the first device or the second device may perform at least one of channel encoding, rate matching, scrambling, constellation mapping, layer mapping, waveform modulation, antenna mapping, and / or resource mapping on the information bits. For example, when receiving data, the first device or the second device may perform at least one of signal extraction from resources, waveform demodulation for each antenna, signal arrangement considering layer mapping, constellation demapping, descrambling, and / or channel decoding.

[0045] For example, the layers of a radio interface protocol between a first device and a second device can be divided into L1 (layer 1), L2 (layer 2), L3 (layer 3), etc. For example, a physical layer belonging to the first layer can provide an information transfer service using a physical channel, and an RRC (radio resource control) layer located in the third layer can play a role in controlling radio resources between the first device and the second device. For this purpose, for example, the RRC layer can exchange RRC messages between the first device and the second device.

[0046] FIG. 2 illustrates a radio protocol architecture according to an embodiment of the present disclosure. The embodiment of FIG. 2 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted. For example, (a) of FIG. 2 may illustrate a radio protocol stack of a user plane for uplink communication or downlink communication, and (b) of FIG. 2 may illustrate a radio protocol stack of a control plane for uplink communication or downlink communication. For example, (c) of FIG. 2 may illustrate a radio protocol stack of a user plane for device-to-device communication, and (d) of FIG. 2 may illustrate a radio protocol stack of a control plane for device-to-device communication.

[0047] For example, the physical layer can provide information transmission services to upper layers using physical channels. For example, the physical layer can be connected to the upper layer, the medium access control (MAC) layer, through a transport channel. For example, data can be transmitted between the MAC layer and the physical layer through the transport channel. For example, transport channels can be classified according to how and with what characteristics data is transmitted over the wireless interface. For example, data can be transmitted between different physical layers, for example, between the physical layers of a first device and a second device, through a physical channel. For example, the physical channel can be modulated using an orthogonal frequency division multiplexing (OFDM) scheme, and time and frequency can be utilized as radio resources.

[0048] For example, the MAC layer can provide services to the upper layer, the radio link control (RLC) layer, through logical channels. For example, the MAC layer can provide a mapping function from multiple logical channels to multiple transport channels. For example, the MAC layer can provide a logical channel multiplexing function by mapping multiple logical channels to a single transport channel. For example, the MAC sublayer can provide data transmission services on logical channels.

[0049] For example, the RLC layer can perform concatenation, segmentation, and reassembly of RLC service data units (SDUs). For example, to guarantee the various quality of service (QoS) required by radio bearers (RBs), the RLC layer can provide three operating modes: transparent mode (TM), unacknowledged mode (UM), and acknowledged mode (AM). For example, AM RLC can provide error correction through automatic repeat request (ARQ).

[0050] For example, the RRC (radio resource control) layer can be defined only in the control plane. For example, the RRC layer can be responsible for controlling logical channels, transport channels, and physical channels in relation to the configuration, re-configuration, and release of radio bearers. For example, an RB can mean a logical path provided by a first layer (e.g., a physical layer) and a second layer (e.g., a MAC layer, an RLC layer, a PDCP (packet data convergence protocol) layer, a SDAP (service data adaptation protocol) layer, etc.) for data transmission between a first device and a second device.

[0051] For example, the functions of the PDCP layer in the user plane may include forwarding of user data, header compression, and ciphering. For example, the functions of the PDCP layer in the control plane may include forwarding of control plane data and ciphering / integrity protection.

[0052] For example, establishing an RB can refer to the process of defining the characteristics of the radio protocol layer and channel to provide a specific service, and setting specific parameters and operating methods for each. For example, RBs can be divided into two types: signaling radio bearers (SRBs) and data radio bearers (DRBs). For example, SRBs can be used as a channel to transmit RRC messages in the control plane, while DRBs can be used as a channel to transmit user data in the user plane.

[0053] For example, a downlink transmission channel may include at least one of a broadcast channel (BCH) for transmitting system information, and / or a downlink shared channel (SCH) for transmitting user traffic or control messages. For example, traffic or control messages of a downlink multicast or broadcast service may be transmitted through the downlink SCH, or may be transmitted through a separate downlink multicast channel (MCH). Meanwhile, an uplink transmission channel may include at least one of a random access channel (RACH) for transmitting initial control messages, and / or an uplink shared channel (SCH) for transmitting user traffic or control messages. For example, a logical channel located above a transmission channel and mapped to the transmission channel may include at least one of a broadcast control channel (BCCH), a paging control channel (PCCH), a common control channel (CCCH), a multicast control channel (MCCH), and / or a multicast traffic channel (MTCH).

[0054] FIG. 3 illustrates the structure of a wireless frame according to an embodiment of the present disclosure. The embodiment of FIG. 3 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted.

[0055] Referring to FIG. 3, for example, a radio frame may be used in uplink transmission, downlink transmission, and / or device-to-device transmission. For example, a radio frame may have a length of 10 ms and may be defined as two 5 ms half-frames (HF). For example, a half-frame may include five 1 ms subframes (SF). For example, a subframe may be divided into one or more slots, and the number of slots within a subframe may be determined according to a subcarrier spacing (SCS). For example, each slot may include 12 or 14 OFDM (A) symbols, depending on a cyclic prefix (CP).

[0056] For example, when normal CP is used, each slot can contain 14 symbols. For example, when extended CP is used, each slot can contain 12 symbols. Here, for example, the symbols can contain OFDM symbols (or CP-OFDM symbols), SC-FDMA (single carrier-FDMA) symbols (or DFT-s-OFDM (Discrete Fourier Transform-spread-OFDM) symbols).

[0057] Table 2 below shows the number of symbols per slot (N) depending on the SCS setting (u) when normal CP or extended CP is used. slot symb ), number of slots per frame (N frame,u slot ) and the number of slots per subframe (N subframe,u slot) is an example.

[0058] CP type SCS (15*2 u )N slot symb N frame,u slot N subframe,u slot Normal CP15kHz (u=0)1410130kHz (u=1)1420260kHz (u=2)14404120kHz (u=3)14808240kHz (u=4)1416016Extended CP60kHz (u=2)12404

[0059] For example, OFDM(A) numerology (e.g., SCS, CP length, etc.) may be set differently between multiple cells that are merged into a single terminal. Accordingly, the (absolute time) interval of time resources (e.g., subframes, slots, or transmit time intervals (TTIs)) composed of the same number of symbols may be set differently between the merged cells. For example, in the present disclosure, time resources such as subframes, slots, TTIs, etc. may be referred to as time units.

[0060] For example, multiple numerologies, or SCSs, may be supported to support various services. For example, a 15 kHz SCS may support wide areas in traditional cellular bands, while a 30 kHz / 60 kHz SCS may support dense urban areas, lower latency, and wider carrier bandwidth. For example, a 60 kHz or higher SCS may support bandwidths greater than 24.25 GHz to overcome phase noise.

[0061] FIG. 4 illustrates a slot structure of a frame according to an embodiment of the present disclosure. The embodiment of FIG. 4 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted.

[0062] Referring to FIG. 4, for example, a slot may include multiple symbols in the time domain. For example, a carrier may include multiple subcarriers in the frequency domain. For example, a resource block (RB) may be defined as multiple consecutive subcarriers in the frequency domain. For example, a bandwidth part (BWP) may be defined as multiple consecutive (P)RBs ((physical) resource blocks) in the frequency domain, and may correspond to one numerology (e.g., SCS, CP length, etc.). For example, a carrier may include at most N BWPs (where N is a positive integer). For example, data communication may be performed through an activated BWP. For example, each element may be referred to as a resource element (RE) in the resource grid, and one complex symbol may be mapped to it.

[0063] For example, a BWP may be a contiguous set of PRBs in a given numerology. For example, a PRB may be selected from a contiguous subset of common resource blocks (CRBs) for a given numerology on a given carrier.

[0064] For example, the BWP may be at least one of an active BWP, an initial BWP, and / or a default BWP. For example, the UE may not monitor the downlink radio link quality in a DL BWP other than the active DL BWP on the PCell (primary cell). For example, the UE may not receive a physical downlink control channel (PDCCH), a physical downlink shared channel (PDSCH), or a channel state information-reference signal (CSI-RS) (except for radio resource management (RRM)) outside of the active DL BWP. For example, the UE may not trigger channel state information (CSI) reporting for an inactive DL BWP. For example, the UE may not transmit a physical uplink control channel (PUCCH) or a physical uplink shared channel (PUSCH) outside of the active UL BWP. For example, for downlink, the initial BWP can be given as a set of consecutive resource blocks (RBs) for the remaining minimum system information (RMSI) CORESET (control resource set) (set by the physical broadcast channel (PBCH)). For uplink, for example, the initial BWP can be given by the system information block (SIB) for the random access procedure. For example, the default BWP can be set by a higher layer. For example, the initial value of the default BWP can be the initial DL BWP.For energy saving, if a terminal does not detect DCI (downlink control information) for a certain period of time, the terminal may switch its active BWP to a default BWP.

[0065] FIG. 5 illustrates an example of a BWP according to an embodiment of the present disclosure. The embodiment of FIG. 5 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted. In the embodiment of FIG. 5, it is assumed that there are three BWPs.

[0066] Referring to FIG. 5, for example, a common resource block (CRB) may be a carrier resource block numbered from one end of a carrier band to the other, and a PRB may be a numbered resource block within each BWP. For example, point A may indicate a common reference point for a resource block grid.

[0067] For example, BWP is point A, offset from point A (N start BWP ) and bandwidth (N size BWP ) can be set by. For example, point A can be an outer reference point of the PRB of a carrier where subcarrier 0 of all numerologies (e.g., all numerologies supported by the network on that carrier) aligns. For example, the offset can be the PRB spacing between the lowest subcarrier in a given numerology and point A. For example, the bandwidth can be the number of PRBs in a given numerology.

[0068] FIG. 6 illustrates a communication structure that can be provided in a 6G system according to an embodiment of the present disclosure. The embodiment of FIG. 6 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted.

[0069] As core implementation technologies of the 6G system, technologies such as artificial intelligence (AI), THz (terahertz) communication, optical wireless technology, free-space optical transmission (FSO) backhaul networks, massive MIMO (multiple input multiple output) 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) can be adopted.

[0070] - Artificial Intelligence: Incorporating AI into communications can streamline and improve real-time data transmission. AI can use numerous analytics to determine how complex target tasks should be performed. For example, AI can increase efficiency and reduce processing delays. Time-consuming tasks such as handovers, network selection, and resource scheduling can be performed instantly using AI. AI can also play a crucial role in machine-to-machine (M2M), machine-to-human, and human-to-machine communications. AI can also facilitate rapid communication in brain-computer interfaces (BCIs). AI-based communication systems can be supported by metamaterials, intelligent structures, intelligent networks, intelligent devices, intelligent cognitive radios, self-sustaining wireless networks, and machine learning.

[0071] - THz communication (terahertz communication): Data rates can be increased by increasing the bandwidth. This can be achieved by using sub-THz communication with wide bandwidths and applying advanced massive MIMO technology. THz waves, also known as sub-millimeter waves, typically refer to the frequency range between 0.1 THz and 10 THz, with corresponding wavelengths ranging from 0.03 mm to 3 mm. The 100 GHz to 300 GHz band (sub-THz band) is considered a key part of the THz spectrum for cellular communications. Adding the sub-THz band to the mmWave band will increase the capacity of 6G cellular communications. Among the defined THz bands, 300 GHz to 3 THz lies in the far infrared (IR) frequency band. While part of the optical band, the 300 GHz to 3 THz band lies at the boundary of the optical band, immediately following the RF band. Therefore, this 300 GHz to 3 THz band exhibits similarities to RF. Key characteristics of THz communications include (i) the widely available bandwidth to support very high data rates and (ii) the high path loss that occurs at high frequencies (requiring highly directional antennas). The narrow beamwidths generated by highly directional antennas reduce interference. The small wavelength of THz signals allows for a significantly larger number of antenna elements to be integrated into devices and base stations operating in this band. This enables the use of advanced adaptive array technologies to overcome range limitations.

[0072] - Large-scale MIMO technology

[0073] - Hologram beamforming (HBF)

[0074] - Optical wireless technology

[0075] - Free-space optical transmission backhaul network (FSO backhaul network)

[0076] - Quantum communication

[0077] - Cell-free communication

[0078] - Integration of wireless information and power transmission

[0079] - Integration of wireless communication and sensing

[0080] - Integrated access and backhaul network

[0081] - Big data analysis

[0082] - Reconfigurable intelligent surface

[0083] - metaverse

[0084] - Blockchain

[0085] Advanced Air Mobility (AAM): AAM can be a broad concept encompassing urban air mobility (UAM), regional air mobility (RAM), and uncrewed aerial systems (UAS). For example, AAM can include UAM, RAM, UAS, and uncrewed aerial vehicles (UAVs).

[0086] - Autonomous driving (self-driving): V2X (vehicle to everything), a key element in building autonomous driving infrastructure, can be a technology that allows cars to communicate and share with various elements on the road for autonomous driving, such as vehicle to vehicle (V2V) wireless communication and vehicle to infrastructure (V2I) wireless communication.

[0087] Non-terrestrial network (NTN): NTN can refer to a network or network segment that utilizes radio frequency (RF) resources mounted on satellites (or UAS platforms). NTN services may be considered to secure wider coverage or provide wireless communication services in locations where the installation of wireless communication base stations is difficult.

[0088] - Integrated sensing and communication (ISAC): Wireless sensing is a technology that uses radio frequencies to determine the instantaneous linear velocity, angle, distance (range), etc. of an object, thereby obtaining information about the characteristics of the environment and / or objects within the environment.

[0089] - Reconfigurable intelligent surface (RIS): RIS can be used to manipulate and enhance signal propagation in wireless communication environments. For example, a RIS can be composed of many small antennas, or metasurfaces, arranged on a surface, each of which can actively control the phase, amplitude, polarization, etc. of the reflected signal. For example, a RIS can improve signal reception by controlling the path, phase, and / or intensity of the propagating signal. For example, in the case of a RIS, power consumption can be very low because power is consumed only for controlling the phase and amplitude of the small antennas. For example, because a RIS can be reconfigured to suit different environments, it can meet diverse communication requirements and operate effectively in dynamic network environments.

[0090] FIG. 7 illustrates an example of a communication scenario based on a 6G system, according to an embodiment of the present disclosure. The embodiment of FIG. 7 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted.

[0091] Referring to FIG. 7, NTN communication can be performed based on satellite networks, high-altitude platform stations (HAPS) as international mobile telecommunications (IMT) base stations (BS), and terminals capable of aerial communication (e.g., AAMs). For example, to improve coverage, etc., devices such as satellite networks, HIBS, and terminals capable of aerial communication (e.g., AAMs) can act as relays. For example, an AAM can communicate with a base station, a satellite network, etc., and / or an AAM can communicate directly with a terminal, another AAM, etc.

[0092] For example, a terminal can obtain information about the environment and / or the characteristics of objects within the environment by using radio frequency sensing to determine the instantaneous linear velocity, angle, distance (range), etc. of an object. Since radio frequency sensing does not require a device to connect to the object through a network, it can provide a service for object positioning without a device. The ability to obtain range, velocity, and angle information from radio frequency signals can enable a wide range of new capabilities, such as various object detection, object recognition (e.g., vehicles, humans, animals, UAVs), and high-precision localization, tracking, and activity recognition. Wireless sensing services can provide information to a variety of industries (e.g., unmanned aerial vehicles, smart homes, V2X, factories, railways, public safety, etc.), enabling applications that provide, for example, intruder detection, assisted vehicle steering and navigation, trajectory tracking, collision avoidance, traffic management, health and traffic management, and more. In some cases, wireless sensing can utilize non-3GPP type sensors (e.g., radar, cameras) to further support 3GPP-based sensing. For example, the operation of wireless sensing services, e.g., sensing operations, may depend on the transmission, reflection, and scattering of wireless sensing signals. Therefore, wireless sensing offers an opportunity to enhance existing communication systems from a communications network to a wireless communication and sensing network.

[0093] FIG. 8 illustrates an example of a sensing operation according to an embodiment of the present disclosure. The embodiment of FIG. 8 can be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted. Specifically, (a) of FIG. 8 illustrates an example of sensing using a sensing receiver and a sensing transmitter located at the same location (e.g., monostatic sensing), and (b) of FIG. 8 illustrates an example of sensing using a separated sensing receiver and sensing transmitter (e.g., bistatic sensing).

[0094] Referring to FIG. 8, a sensing transmitter can transmit a sensing signal for sensing one or more objects (and / or an environment around the objects). For example, the sensing signal can be a radio (frequency) signal defined to be transmittable by a base station / terminal. For example, a sensing receiver can receive a signal scattered / reflected by one or more objects (and / or an environment around the objects) from a sensing signal transmitted from the sensing transmitter. For example, in the sensing receiver, sensing data can be derived from the scattered / reflected signal, and a sensing result can be generated / obtained through processing the sensing data. Here, for example, the sensing result can include characteristic information (e.g., position, distance, speed, angle, etc.) about one or more objects (and / or an environment around the objects). For example, the sensing results generated / obtained in this way may be utilized for wireless sensing services (e.g., detection, tracking, etc. of objects and / or environments) or provided / disclosed to a trusted third party.

[0095] For example, a sensing transmitter may be a base station or terminal that transmits a sensing signal to be used for a sensing service to operate, and the sensing transmitter may be located in the same or different base station or terminal as a sensing receiver. For example, a sensing receiver may be a base station or terminal that receives a sensing signal to be used for a sensing service to operate, and the sensing receiver may be located in the same or different base station or terminal as a sensing transmitter. For example, a sensing target may be an object to be detected by deriving characteristics of an object in the environment from a sensing signal. For example, a background environment may be a background that is not a sensing target (e.g., clutter, environmental objects, etc.). For example, an environment object may be an object whose location is known other than a sensing target. For example, monostatic sensing may be sensing in which a sensing transmitter and a sensing receiver coexist in the same base station or terminal. For example, bistatic sensing may be sensing in which the sensing transmitter and the sensing receiver are located in different base stations or terminals. For example, multistatic sensing may be sensing in which there are multiple sensing transmitters and / or multiple sensing receivers for a (single) sensing target. For example, monostatic sensing, bistatic sensing, and / or multistatic sensing may be distinguished based on the angle between the sensing transmitter, the sensing target, and the sensing receiver. For example, if the angle between the sensing transmitter, the sensing target, and the sensing receiver is less than or equal to a threshold, it may be defined as monostatic sensing or semi-monostatic sensing. For example, if the angle between the sensing transmitter, the sensing target, and the sensing receiver is greater than or equal to a threshold, it may be defined as bistatic sensing or multistatic sensing.For example, the terminal may transmit a sensing signal over a wireless interface that can be used for sensing purposes. For example, the terminal may transmit a sensing signal over a 3GPP wireless interface that can be used for sensing purposes.

[0096] For example, the common framework of the ISAC channel model can be composed of target channel components and background channel components. For example, this can be obtained based on mathematical equation 1.

[0097]

[0098] Here, for example, target channel H target may include all [multipath] components affected by the sensing target. For example, background channel H Background may contain other [multipath] components that do not belong to the target channel.

[0099] For example, radar cross-section (RCS) may be a measure of how well a radar sensor can detect a target. Therefore, it is often referred to as an electromagnetic characteristic of the target. For example, a larger RCS may indicate that the target is more easily detectable. For example, in a radar sensor measurement, power may be transmitted toward the target, and the target may reflect some of the power back to the receiver. For example, the received power may be based on the RCS of the target, among other factors. For example, the received power may be proportional to the RCS. For example, the RCS of a target may be based on at least one of the frequency of the radar signal, the target material, the target shape, the target size, the direction of the incident and reflected waves relative to the target, the target movement, and / or the target illumination.

[0100] FIG. 9 illustrates the relationship between RCS, range (D), and power according to one embodiment of the present disclosure. The embodiment of FIG. 9 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted.

[0101] Referring to Figure 9, the RCS of a radar target may be a virtual area required to intercept the power density transmitted from the target. For example, the relevant radar mathematical formula may be defined as in Equation 2.

[0102]

[0103] Here, for example, P TX can be the transmitter power [W], and G TXcan be the gain of the transmitting antenna [dimensionless], D can be the distance between the equipment under test (EUT) and the target [m], and RCS can be the radar cross section [m 2 ] can be, P RX can be the power [W] received back by the EUT from the object, and A eff is the effective area of ​​the receiving antenna [m 2 ] can be. For example, A eff can be obtained based on mathematical formula 3.

[0104]

[0105] Here, for example, G RX can be the gain of the receiving antenna [dimensionless], λ can be the wavelength of the radio signal [m], λ = c / f, c can be the speed of light 299792458 [m / s], and f can be the frequency [Hz].

[0106] For example, if the transmitter and receiver are co-located and the same antenna is used for both transmission and reception (G TX = G RX = G), the related radar mathematical formula can be defined as in mathematical formula 4.

[0107]

[0108] Here, for example, P TX can be the transmitter power [W], G can be the gain of the transmitting antenna [dimensionless], D can be the distance between the equipment under test (EUT) and the target [m], and RCS can be the radar cross section [m 2 ] can be, P RX can be the power [W] received back by the EUT from the object.

[0109] Meanwhile, with the technological advancement of AI / ML (Artificial Intelligence and Machine Learning), the node(s) and / or terminal(s) that make up the wireless communication network are becoming more intelligent / advanced. In particular, due to the intelligence of the network / base station, it is expected that various network / base station decision parameter values ​​(e.g., transmit / receive power of each base station, transmit power of each terminal, precoder / beam of the base station / terminal, time / frequency resource allocation for each terminal, duplex method of each base station, etc.) can be quickly optimized and derived / applied according to various environmental parameters (e.g., distribution / location of base stations, distribution / location / material of buildings / furniture, etc., location / movement direction / speed of terminals, climate information, etc.). In line with this trend, many standardization organizations (e.g., 3GPP, O-RAN) are considering the introduction of AI / ML, and research on this is actively underway.

[0110] For example, artificial intelligence (AI) can encompass any automation that allows machines to perform tasks previously performed by humans. Machine learning, for example, can involve machines learning patterns for decision-making based on data without explicitly programming rules. Deep learning, for example, can be a neural network-based model that allows machines to simultaneously extract features from unstructured data and make judgments. For example, algorithms can rely on biological neural systems (e.g., multilayer networks of interconnected nodes for feature extraction and transformation, inspired by neural networks). For example, common deep learning network architectures include deep neural networks (DNNs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs).

[0111] For example, the types of AI / ML based on various criteria can be as follows:

[0112] (1) Classification by offline and online

[0113] For example, offline learning can faithfully follow the sequential process of database collection, training, and prediction. For example, collection and training can be performed offline, and the completed program can be installed on-site and utilized for prediction tasks. This offline learning approach can be used in most situations.

[0114] For example, online learning can be a method that gradually improves performance by taking advantage of the fact that data that can be used for learning is continuously generated through the Internet, and incrementally learning with additional data that is generated.

[0115] (2) Classification according to AI / ML framework concept

[0116] For example, in centralized learning, when learning data collected from multiple different node(s) are reported to a centralized node, all data resources / storage / learning (e.g., supervised, unsupervised, reinforcement learning), etc. can be performed in one central node.

[0117] For example, federated learning allows a collective model to be built based on data across distributed data owners. Instead of importing data into a model, the AI / ML model is imported into the data source, allowing local nodes and / or individual devices to collect data and train their own copies of the model, eliminating the need to report source data to a central node. In federated learning, the parameters / weights of the AI / ML model can be sent back to the central node to support general model training. The advantages of federated learning include increased computational speed and improved information security. For example, it eliminates the need to upload personal data to a central server, thereby preventing personal information leakage and misuse.

[0118] For example, distributed learning can represent the concept of machine learning processes being scaled and distributed across a cluster of nodes. Training models can be split and shared across multiple nodes operating simultaneously to speed up model training.

[0119] (3) Classification by learning method

[0120] For example, supervised learning can be a machine learning task that aims to learn a mapping function from input to output, given a labeled data set. The input data is called training data and may have known labels or outcomes. Examples of supervised learning include:

[0121] - Regression: linear regression, logistic regression

[0122] - Instance-based algorithms: k-nearest neighbor (KNN)

[0123] - Decision tree algorithms: CART

[0124] - Support vector machines (SVM)

[0125] - Bayesian algorithms: Naive Bayes

[0126] - Ensemble algorithms: extreme gradient boosting

[0127] - Bagging: Random forest

[0128] For example, supervised learning can be further grouped into regression and classification problems, where classification might be predicting a label and regression might be predicting a quantity.

[0129] For example, unsupervised learning can be a machine learning task that aims to learn features that describe hidden structures in unlabeled data. The input data may be unlabeled and have no known outcome. Some examples of unsupervised learning include K-means clustering, principal component analysis (PCA), nonlinear independent component analysis (ICA), and long-term memory (LSTM).

[0130] For example, in reinforcement learning, an agent interacts with its environment through a trial-and-error process, aiming to optimize a long-term goal. This can be goal-directed learning based on interaction with the environment. Below are some examples of reinforcement learning (RL) algorithms.

[0131] - Q-learning

[0132] - Multi-armed bandit learning

[0133] - Deep Q network

[0134] - State-action-reward-state-action (SARSA)

[0135] - Temporal difference learning

[0136] - Actor-critic reinforcement learning

[0137] - Deep deterministic policy gradient

[0138] - Monte-Carlo tree search

[0139] For example, reinforcement learning can be further categorized into model-based reinforcement learning and model-free reinforcement learning. For example, model-based reinforcement learning may be an RL algorithm that uses a predictive model to obtain transition probabilities between states using various dynamic states of the environment and a model of how these states lead to rewards. For example, model-free reinforcement learning may be an RL algorithm based on values ​​or policies that maximize future rewards. In multi-agent environments / states, it may be computationally less complex and may not require an accurate representation of the environment. For example, RL algorithms can also be categorized into value-based RL versus policy-based RL, policy-based RL versus non-policy RL, etc.

[0140] For example, representative models of deep learning may include FFNN (feed-forward neural network), RNN (recurrent neural network), CNN (convolution neural network), and autoencoder.

[0141] For example, an FFNN may consist of an input layer, a hidden layer, and / or an output layer.

[0142] For example, an RNN may be a type of artificial neural network in which hidden nodes are connected by directed edges to form a circular structure. For example, this may be a model suitable for processing sequentially appearing data such as voice and text. For example, one type of RNN may be an LSTM (long short-term memory), which may have a structure that adds a cell state to the hidden state of an RNN. For example, an input gate, a forget gate, and / or an output gate may be added to an RNN cell, and / or a cell state may be added.

[0143] For example, CNN can be used for two purposes: reducing model complexity and extracting good features by applying convolution operations commonly used in image processing or video processing.

[0144] - Kernel or filter: a unit / structure that applies weights to inputs of a specific range / unit.

[0145] - Stride: The range of movement of the kernel within the input.

[0146] - Feature map: The result of applying the kernel to the input.

[0147] - Padding: A value added to adjust the size of the feature map.

[0148] - Pooling: An operation to reduce the size of a feature map by downsampling the feature map (e.g., max pooling, average pooling)

[0149] For example, an autoencoder can be a neural network that receives a feature vector x as input and outputs the same or similar vector x'. For example, the input and output nodes of an autoencoder can have the same features. For example, an autoencoder can be a type of unsupervised learning. For example, the loss function can be defined as in Equation 5.

[0150]

[0151] In this disclosure, the following terms may be defined, for example, to describe AI / ML.

[0152] - Data collection: Data collected from network nodes, management entities, or terminals as a basis for ML model training, data analysis, and inference.

[0153] - ML model: A data-driven algorithm that applies machine learning techniques to generate a set of outputs containing predictive information based on a set of inputs.

[0154] - ML training: The online or offline process of training an ML model by learning features and patterns that best represent the data and obtain a trained ML model for inference.

[0155] - ML Inference: The process of making predictions or inducing decisions based on collected data and the ML model using a trained ML model.

[0156] FIG. 10 illustrates a functional framework for AI / ML (Artificial Intelligence and Machine Learning) according to one embodiment of the present disclosure. The embodiment of FIG. 10 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted.

[0157] Referring to Figure 10, for example, data collection may be a function that provides input data to model training and model inference functions. AI / ML algorithm-specific data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) may not be performed in the data collection function. Examples of input data may include measurements from terminals or other network entities, feedback from actors, and output from AI / ML models.

[0158] For example, training data may be data required as input to an AI / ML model training function.

[0159] For example, inference data may be data required as input to the AI / ML model inference function.

[0160] For example, model training may be a function that performs ML model training, validation, and testing, which can generate model performance metrics as part of the model testing process. If necessary, the model training function may also handle data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on training data provided by the data collection function.

[0161] For example, model deployment / update can be used to initially deploy a trained, validated, and tested AI / ML model to a model inference function, or to provide an updated model to a model inference function.

[0162] For example, model inference may be a function that provides AI / ML model inference output (e.g., predictions or decisions). The model inference function may, where applicable, provide model performance feedback to the model training function. If necessary, the model inference function may also handle data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on the inference data provided by the data collection function.

[0163] For example, the output could be the inference output of an AI / ML model generated by the model inference function. Note that the details of the inference output may vary depending on the use case.

[0164] For example, model performance feedback can be used to monitor the performance of AI / ML models.

[0165] For example, an actor might be a function that receives output from a model inference function and triggers or performs corresponding actions. An actor can trigger actions on other entities or on itself.

[0166] For example, feedback may be training or inference data, or information that may be needed to derive performance feedback.

[0167] For example, in AI / ML, the definitions of training / validation / test data can be as follows. For example, training data can be a data set for training a model. For example, validation data can be a data set for validating a model that has already completed training. For example, validation data can be a data set typically used to prevent overfitting of the training data set. For example, validation data can be a data set for selecting the best model among several models trained during the training process. Therefore, it can be viewed as a type of learning. For example, test data can be a data set for final evaluation, and the test data can be unrelated to learning. For example, in the case of the above data set, if the training set is typically divided, the training and validation data can be divided in a ratio of 8:2 or 7:3 within the entire training set. If testing is included, the ratio can be 6:2:2 (training:validation:test).

[0168] Meanwhile, NR positioning up to Release 17 only supports network-based Uu positioning that searches for a location under a connection between a target UE and a network (gNB / LMF (location management function)). Meanwhile, NR Release 18 and later supports sidelink positioning using sidelink communication. Sidelink positioning is a new method that performs positioning operations by exchanging positioning reference signals through a direct connection with anchor UEs around the target UE, rather than a base station. Positioning operations at the physical layer are performed by transmitting and measuring SL PRS (sidelink positioning reference signal) between the target UE and the anchor UE.

[0169] Meanwhile, Uu positioning uses the LTE positioning protocol (LPP). An LPP session is a point-to-point communication protocol between a target UE and an LMF. Through the LPP protocol, the target UE receives positioning information from the LMF. The LMF configures the target UE and the base station (gNB) through the LPP protocol and the NR positioning protocol A (NRPPa) protocol, exchanges positioning-related messages, and performs positioning operations. Meanwhile, in Release 18's sidelink positioning, the target UE, server UE (or LMF), and anchor UE exchange sidelink positioning protocol messages to perform positioning operations. Sidelink positioning uses the sidelink positioning protocol (SLPP) to exchange configuration and messages between UEs.

[0170] Meanwhile, ISAC requires a process of analyzing and processing sensing data to obtain sensing results. The function responsible for this is called the sensing function. Determining where to locate this sensing function is a critical part of the ISAC system / network architecture design.

[0171] Alternatively, there may be a centralized architecture, similar to the LMF of conventional positioning architectures, where sensing functions are located within the core network. Alternatively, there may be a distributed architecture, where sensing functions are located within sensing nodes (e.g., base stations or UEs).

[0172] In a centralized architecture where sensing data is analyzed by a central sensing server, all sensing nodes can transmit their measured sensing data to the central server, which then collects and analyzes the data. This approach, by collecting and analyzing all sensing data in the central server, enables comprehensive and more accurate analysis based on rich data. However, this centralized architecture can lead to the following problems:

[0173] - Centralized model dependency: Most approaches have a structure where a central server collects, integrates, or learns models, which results in high communication costs and server burden, and there is a possibility of personal information leakage due to the central server.

[0174] - Excessive transmission of sensing data: To increase real-time performance and accuracy, a large amount of sensing data is transmitted, which wastes communication resources and reduces energy efficiency.

[0175] - Privacy vulnerability: Personally identifiable information may be leaked as raw data or high-dimensional features collected from sensor equipment are transmitted as is.

[0176] - Model bias and poor generalization performance: The regional characteristics of the data and sensor specificity cause the generated model to be less accurate in different environments or devices.

[0177] In another distributed architecture, the analysis of sensing data can be performed at sensing end devices (e.g., UEs, base stations, TRPs, etc.) rather than at a central sensing server. By performing the analysis of sensing data directly at the end devices that measure / collect the sensing data (e.g., using edge computing technology), the process of transmitting the collected sensing data to a central server is eliminated. Therefore, the time delay required to transmit the sensing data to the central server for analysis can be reduced. Furthermore, by significantly reducing the amount of data to be transmitted, communication overhead can be significantly reduced.

[0178] As described above, a centralized architecture essentially entails data transmission from the end devices that measure / collect sensing data to the central server. This leads to increased resource consumption (both wired and wireless) due to increased communication volume and the resulting privacy exposure. Conversely, a decentralized architecture performs analysis solely based on local data collected from each end device. Therefore, performance may be relatively lower than in a centralized architecture, which can comprehensively analyze all data. Furthermore, data that is difficult to analyze on the end devices, such as raw data, is difficult to utilize. Furthermore, when the sensing results analyzed in a decentralized architecture are transmitted to a third-party application server, similar to the centralized architecture, privacy exposure issues may arise.

[0179] The two architectures described above have different advantages and disadvantages. Therefore, a method is needed to prevent the degradation of sensing performance that occurs in a distributed architecture while reducing the transmission data overhead that occurs in a centralized architecture. Furthermore, a method is needed to address the common issue of personal privacy exposure.

[0180] In this disclosure, a federated learning ISAC sensing architecture is proposed as a method for reducing transmission data overhead and addressing privacy exposure issues. For example, federated learning sensing can be referred to by various terms, such as two-side sensing, distributed sensing, or sensing, and a federated learning model can be referred to by various terms, such as two-side model, two-side sensing model, distributed model, distributed sensing model, model, or sensing model.

[0181] FIG. 11 illustrates a sensing structure and procedure according to an embodiment of the present disclosure. The embodiment of FIG. 11 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted.

[0182] Referring to FIG. 11, in step S1110, an end device (e.g., a sensing node) (e.g., a base station, a TRP, a UE, etc.) may analyze sensing data. In step S1120, the end device may transmit model parameters (instead of the sensing data) to a central server. Here, for example, the sensing node may input the measured sensing data into a federated learning model. For example, model parameters may be generated as an output of the federated learning model.

[0183] In step S1130, the central server (sensing function) aggregates and further analyzes the received model parameters to obtain the desired sensing results. For example, the central server can obtain sensing parameters by inputting the received model parameters (e.g., transmitted by the sensing node) as input values ​​for a federated learning model.

[0184] This architecture not only reduces overhead by not transmitting all sensing data (unlike centralized architectures), but also mitigates privacy concerns. Furthermore, by aggregating and analyzing received model parameters, it addresses the potential for poor analysis performance that can arise when relying solely on local analysis (unlike distributed architectures).

[0185] Additionally, for example, in step S1100, a model operating on an end device (e.g., a sensing node) and a model operating on a central server (e.g., a sensing function) may be acquired, managed, or set.

[0186] For example, in a federated learning architecture, there may be two models: one operating on an edge device (e.g., a sensing node) and one operating on a central server (e.g., a sensing function). For example, the two models may be associated with each other through model parameters and sensing parameters. Note that the present disclosure may not be limited to a specific model. What is important in model generation is generating model parameters based on the correlation between sensing data and sensing parameters. Therefore, a description of specific models is omitted in this document, and various embodiments of the present disclosure can be applied to various models.

[0187] For example, the method for generating model parameters from measured sensing data and the method for obtaining sensing parameters from model parameters can be interrelated. For example, since the two must be paired, the two models can use a mutually agreed-upon algorithm between the sensing node and the sensing server (e.g., point-to-point between the sensing node and the sensing server / function).

[0188] Therefore, for example, (unlike a distributed architecture), a central server can be responsible for learning and managing models for each end device. For example, the central sensing server can transmit and configure models to be used for each end device. Therefore, models used between the sensing server and sensing nodes can be used after going through a mutual authentication and negotiation process. For example, such operations can be performed when establishing a sensing session. For example, a sensing server can propose a sensing model to a sensing node by transmitting information such as the model's (memory) size, required processing speed / capacity, and number of parameters when configuring the model. For example, a sensing node can decide whether to accept or reject the proposal based on the information in the transmitted model.

[0189] For example, a sensing server can configure and operate a common model across all end devices to improve rapid setup / operation and management efficiency. Furthermore, for example, the models operating on each end device can be configured and operated independently for each end device. In this case, the models used by sensing nodes may be configured differently, and model information may not be shared among them.

[0190] For example, a central server can broadcast a common model. For example, sensing nodes can use the broadcasted common model by default. Furthermore, a specific model, for example, for a specific sensing node can be configured using dedicated signaling.

[0191] For example, the model operation level of a federated learning model can be configured. For example, model parameter generation can be considered a single encryption or compression operation. Encryption / compression can operate differently depending on the desired level. For example, high encryption / compression levels may require greater processing power and latency on sensing nodes. However, this can reduce data size (overhead) and provide higher encryption capabilities. Conversely, relatively low encryption / compression levels may require relatively less processing power and time on sensing nodes.

[0192] For example, depending on these operation levels, the number of model parameters may vary. This may also be related to the quality of the sensing parameters that can be extracted. Therefore, this trade-off relationship may be set differently depending on the properties / characteristics (e.g., sensing QoS) of the sensing data to be transmitted. For example, if sufficient transmission bandwidth for model parameters is provided and privacy requirements are low, the sensing node may perform low-level encryption / compression. Conversely, if high privacy is required in an environment where sufficient transmission bandwidth for model parameters is difficult to provide, the sensing node may perform high-level encryption / compression. Therefore, for example, when setting up / operating a federated learning model, the operation level of the model may be requested / configured together.

[0193] For example, security can be enhanced through the active use of multiple models. For additional secure communication, multiple models (e.g., one or more) can be configured / downloaded, and transmission can be performed using a different model for each dataset. In this case, model information can be included in the header (or label) of the dataset and transmitted. Additionally, for example, each model's information can be anonymized by representing it as an enum value, for example.

[0194] For example, learning and / or validation of sensing parameters (federated learning model) can be performed.

[0195] For example, a sensing server can extract sensing parameters from model parameters generated from a sensing node model. Therefore, for example, the sensing server and sensing nodes may require model training to extract sensing parameters from model parameters. For example, after a model is initially completed, validation may be required to ensure that the model operates correctly.

[0196] For this purpose, for example, the sensing server can request the sensing node to transmit sensing data. Through this, for example, the sensing server can initially train the model. In addition, for example, if the accuracy / reliability of the sensing parameter values ​​extracted by the sensing server is low, additional information (e.g., (the model, model parameters, and / or sensing parameters on the sensing node) may be requested for further training of the model. For example, a sensing node (e.g., UE) that lacks the processing power required for model training may be advantageous in that it can download and use the model from the sensing server. However, for example, the sensing node may have the burden of having to transmit the sensing data.

[0197] For example, a sensing server can transmit its sensing server model information to a sensing node. For example, a sensing node can perform learning and validation by linking its own model with the sensing server's model. In this case, for example, the sensing node does not need to transmit sensing data to the sensing server, reducing the burden of sensing data transmission. Instead, for example, sensing processing capabilities may be required on the sensing node.

[0198] For example, if valid data is not obtained, the sensing server or sensing node can select a different model. For example, if a valid model cannot be selected, the sensing server or sensing node can perform training by transmitting sensing data until the model passes the validation test.

[0199] According to various embodiments of the present disclosure, data transmission efficiency and privacy protection can be achieved simultaneously in a federated learning-based ISAC sensing environment. For example, lightweight model learning and / or updating can be performed on a local device. This allows each sensor terminal to directly learn data, and each sensor terminal can prevent raw data leakage by transmitting only the parameters of the learned model. For example, transmission control can be performed based on the communication network and learning situation. For example, the transmission cycle and amount of transmitted data can be dynamically controlled considering network conditions, learning importance, data sensitivity, etc. For example, the level of encryption / compression can be changed by changing the number of model parameters based on the properties / characteristics of the sensing data (e.g., sensing QoS). For example, the trade-off characteristics between the processing capability and time of a sensing node and the size (overhead) of transmitted data can be dynamically adjusted based on the properties / characteristics of the sensing data.

[0200] According to various embodiments of the present disclosure, the risk of personal information leakage can be fundamentally prevented by preventing external transmission of raw data. Furthermore, by limiting transmission data to the model parameter level and optimizing transmission based on the situation, communication resource waste can be reduced. Furthermore, by utilizing a distributed learning structure that utilizes the computational resources of each device, server burden can be reduced and high-precision model learning reflecting regional characteristics can be achieved. Furthermore, by harmonizing local learning tailored to sensor and environmental characteristics with a centralized integrated model, high accuracy can be maintained in diverse environments.

[0201] For example, in the present disclosure, a “specific threshold” may mean a threshold that is defined in advance or set (in advance) by a higher layer (including an application layer) of a network or a base station or a terminal. For example, in the present disclosure, a “specific set value” may mean a value that is defined in advance or set (in advance) by a higher layer (including an application layer) of a network or a base station or a terminal. For example, in the present disclosure, “set by the network / base station” may mean an operation in which the base station sets (in advance) to the UE via higher layer RRC signaling, sets / signals to the UE via MAC CE, or signals to the UE via DCI.

[0202] For example, in the present disclosure, a message may be interpreted as being replaced with at least one of a control message, a data message, a signal, a data signal, and / or a control signal. For example, in the present disclosure, various names are exemplary and may be replaced / considered with other names that perform the same / similar function based on the content described in each step (regardless of the name).

[0203] FIG. 12 illustrates a method for a first device to perform wireless communication according to an embodiment of the present disclosure. The embodiment of FIG. 12 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted.

[0204] Referring to FIG. 12, in step S1210, the first device can receive information related to a first model related to sensing data and model parameters from the second device. In step S1220, the first device can obtain the sensing data based on sensing an object. In step S1230, the first device can input the sensing data into the first model to obtain the model parameters. In step S1240, the first device can transmit the model parameters to the second device.

[0205] For example, information related to the first model may be received from the second device in a procedure for establishing a session between the first device and the second device.

[0206] For example, whether the first device accepts the first model may be determined based on at least one of the model size, the required processing speed or capacity, or the number of parameters included in the information associated with the first model.

[0207] For example, the encryption level or compression level for the sensing data may be based on the properties of the sensing data.

[0208] For example, the encryption level or compression level for sensing data requiring low privacy may be lower than the encryption level or compression level for sensing data requiring high privacy.

[0209] For example, an encryption level or compression level applied to a model parameter that provides a large transmission bandwidth may be lower than an encryption level or compression level applied to a model parameter that provides a small transmission bandwidth.

[0210] For example, the number of model parameters obtained from the sensing data may vary based on the properties of the sensing data. For example, the properties of the sensing data may be the quality of service (QoS) associated with the sensing data.

[0211] Additionally, for example, the first device may transmit the sensing data to the second device for validating the first model.

[0212] Additionally, for example, the first device may receive information related to the second model from the second device.

[0213] Additionally, for example, the first device may perform validation or learning based on information related to the first model and information related to the second model.

[0214] For example, sensing parameters can be obtained by inputting the model parameters into a second model. For example, the first model can be related to the second model.

[0215] For example, the first device may be a sensing node, and the second device may be a server having a sensing function.

[0216] The proposed method can be applied to devices according to various embodiments of the present disclosure. For example, the processor (102) of the first device (100) can control the transceiver (106) to receive, from the second device, information related to a first model related to sensed data and model parameters, and / or the processor (102) of the first device (100) can obtain the sensed data based on sensing an object, and / or the processor (102) of the first device (100) can input the sensed data into the first model to obtain the model parameters, and / or the processor (102) of the first device (100) can control the transceiver (106) to transmit the model parameters to the second device.

[0217] According to one embodiment of the present disclosure, a first device may be provided. For example, the first device may include at least one transceiver; at least one processor; and at least one memory coupled to the at least one processor and storing instructions. For example, the instructions may cause the first device to perform operations based on execution by the at least one processor. For example, the operations may include at least one of: receiving, from a second device, information related to a first model related to sensed data and model parameters; acquiring the sensed data based on sensing an object; inputting the sensed data into the first model to acquire the model parameters; and / or transmitting the model parameters to the second device.

[0218] According to one embodiment of the present disclosure, a processing device may be provided. For example, the processing device may include at least one processor; and at least one memory coupled to the at least one processor and storing instructions. For example, the instructions may cause a first device to perform an operation based on execution by the at least one processor. For example, the operation may include at least one of: receiving, from a second device, information related to a first model related to sensed data and model parameters; acquiring the sensed data based on sensing an object; inputting the sensed data into the first model to acquire the model parameters; and / or transmitting the model parameters to the second device.

[0219] According to one embodiment of the present disclosure, a non-transitory computer-readable storage medium having instructions recorded thereon may be provided. For example, the instructions, upon execution, may cause a first device to perform an operation. For example, the operation may include at least one of: receiving, from a second device, information related to a first model related to sensed data and model parameters; acquiring the sensed data based on sensing an object; inputting the sensed data into the first model to acquire the model parameters; and / or transmitting the model parameters to the second device.

[0220] FIG. 13 illustrates a method for a second device to perform wireless communication according to an embodiment of the present disclosure. The embodiment of FIG. 13 may be combined with various embodiments of the present disclosure, and some descriptions, functions, procedures, proposals, methods, and / or operations of the embodiments may be omitted.

[0221] Referring to FIG. 13, in step S1310, the second device can obtain information related to a second model related to model parameters and sensing parameters. In step S1320, the second device can receive the model parameters from the first device. In step S1330, the second device can input the model parameters into the second model to obtain the sensing parameters.

[0222] Additionally, for example, the second device may transmit to the first device information related to the first model, including sensing data and model parameters.

[0223] For example, the sensing data may be acquired by the first device based on sensing of an object.

[0224] For example, the model parameters can be obtained by the first device or the second device by inputting the sensing data into the first model.

[0225] For example, information related to the first model and / or information related to the second model may be exchanged or transmitted and received in a procedure for establishing a session between the first device and the second device.

[0226] For example, whether the first device accepts the first model may be determined based on at least one of the model size, the required processing speed or capacity, or the number of parameters included in the information associated with the first model.

[0227] For example, the encryption level or compression level for the sensing data may be based on the properties of the sensing data.

[0228] For example, the encryption level or compression level for sensing data requiring low privacy may be lower than the encryption level or compression level for sensing data requiring high privacy.

[0229] For example, an encryption level or compression level applied to a model parameter that provides a large transmission bandwidth may be lower than an encryption level or compression level applied to a model parameter that provides a small transmission bandwidth.

[0230] For example, the number of model parameters obtained from the sensing data may vary based on the properties of the sensing data. For example, the properties of the sensing data may be the quality of service (QoS) associated with the sensing data.

[0231] Additionally, for example, the second device may receive sensing data from the first device to validate the first model.

[0232] For example, the first model may be related to the second model.

[0233] For example, the first device may be a sensing node, and the second device may be a server having a sensing function.

[0234] The proposed method can be applied to devices according to various embodiments of the present disclosure. For example, the processor (202) of the second device (200) can obtain information related to a second model related to model parameters and sensing parameters, and / or the processor (202) of the second device (200) can control the transceiver (206) to receive the model parameters from the first device, and / or the processor (202) of the second device (200) can input the model parameters into the second model to obtain the sensing parameters.

[0235] According to one embodiment of the present disclosure, a second device may be provided. For example, the second device may include at least one transceiver; at least one processor; and at least one memory coupled to the at least one processor and storing instructions. For example, the instructions may cause the second device to perform operations based on execution by the at least one processor. For example, the operations may include at least one of: obtaining information related to a second model related to model parameters and sensing parameters; receiving the model parameters from a first device; and / or inputting the model parameters into the second model to obtain the sensing parameters.

[0236] According to one embodiment of the present disclosure, a processing device may be provided. For example, the processing device may include at least one processor; and at least one memory coupled to the at least one processor and storing instructions. For example, the instructions may cause a second device to perform an operation based on execution by the at least one processor. For example, the operation may include at least one of: obtaining information related to a second model related to model parameters and sensing parameters; receiving the model parameters from a first device; and / or inputting the model parameters into the second model to obtain the sensing parameters.

[0237] According to one embodiment of the present disclosure, a non-transitory computer-readable storage medium having instructions recorded thereon may be provided. For example, the instructions, upon execution, may cause a second device to perform an operation. For example, the operation may include at least one of: obtaining information related to a second model related to model parameters and sensing parameters; receiving the model parameters from the first device; and / or inputting the model parameters into the second model to obtain the sensing parameters.

[0238] The above methods proposed in this disclosure can be applied to both 3GPP sensing data and Non-3GPP sensing data.

[0239] The various embodiments of the present disclosure may be combined with each other, and some descriptions, functions, procedures, proposals, methods and / or operations of the embodiments may be omitted.

[0240] Below, a description is given of devices to which various embodiments of the present disclosure can be applied.

[0241] Although not limited thereto, the various descriptions, functions, procedures, proposals, methods and / or operational flowcharts disclosed in this document may be applied to various fields requiring wireless communication / connectivity (e.g., 5G) between devices.

[0242] Hereinafter, more specific examples will be provided with reference to the drawings. In the drawings / descriptions below, the same drawing reference numerals may represent identical or corresponding hardware blocks, software blocks, or functional blocks, unless otherwise described.

[0243] FIG. 14 illustrates a communication system (1) according to one embodiment of the present disclosure. The embodiment of FIG. 14 can be combined with various embodiments of the present disclosure.

[0244] Referring to FIG. 14, a communication system (1) to which various embodiments of the present disclosure are applied includes a wireless device, a base station, and a network. Here, the wireless device refers to a device that performs communication using a wireless access technology (e.g., 5G NR (New RAT), LTE (Long Term Evolution)) and may be referred to as a communication / wireless / 5G device. Although not limited thereto, the wireless device may include a robot (100a), a vehicle (100b-1, 100b-2), an XR (eXtended Reality) device (100c), a hand-held device (100d), a home appliance (100e), an IoT (Internet of Things) device (100f), and an AI device / server (400). For example, the vehicle may include a vehicle equipped with a wireless communication function, an autonomous vehicle, a vehicle capable of performing vehicle-to-vehicle communication, etc. Here, the vehicle may include an Unmanned Aerial Vehicle (UAV) (e.g., a drone) and / or an Aerial Vehicle (AV) (e.g., an Advanced Air Mobility (AAM)). The XR device may include 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, a digital signage, a vehicle, a robot, etc. The portable device may include a smartphone, a smart pad, a wearable device (e.g., a smart watch, smart glasses), a computer (e.g., a laptop, etc.), etc. The home appliance may include a TV, a refrigerator, a washing machine, etc. The IoT device may include a sensor, a smart meter, etc. For example, a base station and a network may also be implemented as a wireless device, and a specific wireless device (200a) may operate as a base station / network node to other wireless devices.

[0245] Here, the wireless communication technology implemented in the wireless devices (100a to 100f) of the present specification may include not only LTE, NR, and 6G, but also Narrowband Internet of Things for low-power communication. At this time, for example, NB-IoT technology may be an example of LPWAN (Low Power Wide Area Network) technology, and may be implemented with standards such as LTE Cat NB1 and / or LTE Cat NB2, and is not limited to the above-described names. Additionally or alternatively, the wireless communication technology implemented in the wireless devices (100a to 100f) of the present specification may perform communication based on LTE-M technology. At this time, for example, LTE-M technology may be an example of LPWAN technology, and may be called by various names such as eMTC (enhanced Machine Type Communication). For example, LTE-M technology can be implemented by at least one of various standards such as 1) LTE CAT 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-Bandwidth Limited), 5) LTE-MTC, 6) LTE Machine Type Communication, and / or 7) LTE M, and is not limited to the above-described names. Additionally or alternatively, the wireless communication technology implemented in the wireless devices (100a to 100f) of the present specification can include at least one of ZigBee, Bluetooth, and Low Power Wide Area Network (LPWAN) considering low-power communication, and is not limited to the above-described names. For example, ZigBee technology can create personal area networks (PAN) related to small / low-power digital communication based on various standards such as IEEE 802.15.4, and can be called by various names.

[0246] Wireless devices (100a to 100f) can be connected to a network (300) via a base station (200). Artificial Intelligence (AI) technology can be applied to the wireless devices (100a to 100f), and the wireless devices (100a to 100f) can be connected to an AI server (400) via the network (300). The network (300) can be configured using a 3G network, a 4G (e.g., LTE) network, a 5G (e.g., NR) network, etc. The wireless devices (100a to 100f) can communicate with each other via the base station (200) / network (300), but can also communicate directly (e.g., sidelink communication) without going through the base station / network. For example, vehicles (100b-1, 100b-2) can communicate directly (e.g., V2V (Vehicle to Vehicle) / V2X (Vehicle to Everything) communication). In addition, IoT devices (e.g., sensors) can communicate directly with other IoT devices (e.g., sensors) or other wireless devices (100a to 100f).

[0247] Wireless communication / connection (150a, 150b, 150c) can be established between wireless devices (100a~100f) / base stations (200), and base stations (200) / base stations (200). Here, wireless communication / connection can be achieved through various wireless access technologies (e.g., 5G NR) such as uplink / downlink communication (150a), sidelink communication (150b) (or D2D communication), and base station-to-base station communication (150c) (e.g., relay, IAB (Integrated Access Backhaul). Through wireless communication / connection (150a, 150b, 150c), wireless devices and base stations / wireless devices, and base stations and base stations can transmit / receive wireless signals to each other. For example, wireless communication / connection (150a, 150b, 150c) can transmit / receive signals through various physical channels. To this end, at least some of various configuration information setting processes for transmitting / receiving wireless signals, various signal processing processes (e.g., channel encoding / decoding, modulation / demodulation, resource mapping / demapping, etc.), and resource allocation processes can be performed based on various proposals of the present disclosure.

[0248] FIG. 15 illustrates a wireless device according to an embodiment of the present disclosure. The embodiment of FIG. 15 may be combined with various embodiments of the present disclosure.

[0249] Referring to FIG. 15, the first wireless device (100) and the second wireless device (200) can transmit and receive wireless signals via various wireless access technologies (e.g., LTE, NR). Here, {the first wireless device (100), the second wireless device (200)} can correspond to {the wireless device (100x), the base station (200)} and / or {the wireless device (100x), the wireless device (100x)} of FIG. 14.

[0250] A first wireless device (100) includes one or more processors (102) and one or more memories (104), and may further include one or more transceivers (106) and / or one or more antennas (108). The processor (102) controls the memories (104) and / or the transceivers (106), and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document. For example, the processor (102) may process information in the memory (104) to generate first information / signal, and then transmit a wireless signal including the first information / signal via the transceiver (106). Furthermore, the processor (102) may receive a wireless signal including second information / signal via the transceiver (106), and then store information obtained from signal processing of the second information / signal in the memory (104). The memory (104) may be connected to the processor (102) and may store various information related to the operation of the processor (102). For example, the memory (104) may perform some or all of the processes controlled by the processor (102), or may store software code including commands for performing the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this document. Here, the processor (102) and the memory (104) may be part of a communication modem / circuit / chip designed to implement a wireless communication technology (e.g., LTE, NR). The transceiver (106) may be connected to the processor (102) and may transmit and / or receive wireless signals via one or more antennas (108). The transceiver (106) may include a transmitter and / or a receiver. The transceiver (106) may be used interchangeably with an RF (Radio Frequency) unit. In the present disclosure, a wireless device may also mean a communication modem / circuit / chip.

[0251] A second wireless device (200) includes one or more processors (202), one or more memories (204), and may further include one or more transceivers (206) and / or one or more antennas (208). The processor (202) controls the memories (204) and / or the transceivers (206), and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document. For example, the processor (202) may process information in the memory (204) to generate third information / signals, and then transmit a wireless signal including the third information / signals via the transceivers (206). In addition, the processor (202) may receive a wireless signal including fourth information / signals via the transceivers (206), and then store information obtained from signal processing of the fourth information / signals in the memory (204). The memory (204) may be connected to the processor (202) and may store various information related to the operation of the processor (202). For example, the memory (204) may perform some or all of the processes controlled by the processor (202), or may store software code including commands for performing the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this document. Here, the processor (202) and the memory (204) may be part of a communication modem / circuit / chip designed to implement wireless communication technology (e.g., LTE, NR). The transceiver (206) may be connected to the processor (202) and may transmit and / or receive wireless signals via one or more antennas (208). The transceiver (206) may include a transmitter and / or a receiver. The transceiver (206) may be used interchangeably with an RF unit. In the present disclosure, a wireless device may also mean a communication modem / circuit / chip.

[0252] Hereinafter, the hardware elements of the wireless device (100, 200) will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors (102, 202). For example, one or more processors (102, 202) may implement one or more layers (e.g., functional layers such as PHY, MAC, RLC, PDCP, RRC, SDAP). One or more processors (102, 202) may generate one or more Protocol Data Units (PDUs) and / or one or more Service Data Units (SDUs) according to the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this document. One or more processors (102, 202) may generate messages, control information, data, or information according to the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this document. One or more processors (102, 202) can generate signals (e.g., baseband signals) including PDUs, SDUs, messages, control information, data or information according to the functions, procedures, proposals and / or methods disclosed herein, and provide the signals to one or more transceivers (106, 206). One or more processors (102, 202) can receive signals (e.g., baseband signals) from one or more transceivers (106, 206) and obtain PDUs, SDUs, messages, control information, data or information according to the descriptions, functions, procedures, proposals, methods and / or operational flowcharts disclosed herein.

[0253] One or more processors (102, 202) may be referred to as a controller, a microcontroller, a microprocessor, or a microcomputer. One or more processors (102, 202) may be implemented by hardware, firmware, software, or a combination thereof. For example, one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), one or more Digital Signal Processing Devices (DSPDs), one or more Programmable Logic Devices (PLDs), or one or more Field Programmable Gate Arrays (FPGAs) may be included in one or more processors (102, 202). The descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document may be implemented using firmware or software, and the firmware or software may be implemented to include modules, procedures, functions, etc. The descriptions, functions, procedures, suggestions, methods and / or operation flowcharts disclosed in this document may be implemented using firmware or software configured to perform one or more processors (102, 202) or stored in one or more memories (104, 204) and executed by one or more processors (102, 202). The descriptions, functions, procedures, suggestions, methods and / or operation flowcharts disclosed in this document may be implemented using firmware or software in the form of codes, instructions and / or sets of instructions.

[0254] One or more memories (104, 204) may be coupled to one or more processors (102, 202) and may store various forms of data, signals, messages, information, programs, codes, instructions, and / or commands. The one or more memories (104, 204) may be configured as ROM, RAM, EPROM, flash memory, hard drives, registers, cache memory, computer-readable storage media, and / or combinations thereof. The one or more memories (104, 204) may be located internally and / or externally to the one or more processors (102, 202). Additionally, the one or more memories (104, 204) may be coupled to the one or more processors (102, 202) via various technologies, such as wired or wireless connections.

[0255] One or more transceivers (106, 206) can transmit user data, control information, wireless signals / channels, etc., as mentioned in the methods and / or flowcharts of this document, to one or more other devices. One or more transceivers (106, 206) can receive user data, control information, wireless signals / channels, etc., as mentioned in the descriptions, functions, procedures, proposals, methods and / or flowcharts of this document, from one or more other devices. For example, one or more transceivers (106, 206) can be connected to one or more processors (102, 202) and can transmit and receive wireless signals. For example, one or more processors (102, 202) can control one or more transceivers (106, 206) to transmit user data, control information, or wireless signals to one or more other devices. Additionally, one or more processors (102, 202) may control one or more transceivers (106, 206) to receive user data, control information, or wireless signals from one or more other devices. Additionally, one or more transceivers (106, 206) may be coupled to one or more antennas (108, 208), and one or more transceivers (106, 206) may be configured to transmit and receive user data, control information, wireless signals / channels, or the like, as referred to in the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed herein, via one or more antennas (108, 208). In this document, one or more antennas may be multiple physical antennas or multiple logical antennas (e.g., antenna ports). One or more transceivers (106, 206) can convert received user data, control information, wireless signals / channels, etc. from RF band signals to baseband signals in order to process the received user data, control information, wireless signals / channels, etc. using one or more processors (102, 202).One or more transceivers (106, 206) may convert user data, control information, wireless signals / channels, etc. processed by one or more processors (102, 202) from baseband signals to RF band signals. For this purpose, one or more transceivers (106, 206) may include an (analog) oscillator and / or filter.

[0256] FIG. 16 illustrates a signal processing circuit for a transmission signal according to an embodiment of the present disclosure. The embodiment of FIG. 16 can be combined with various embodiments of the present disclosure.

[0257] Referring to FIG. 16, the signal processing circuit (1000) may include a scrambler (1010), a modulator (1020), a layer mapper (1030), a precoder (1040), a resource mapper (1050), and a signal generator (1060). Although not limited thereto, the operations / functions of FIG. 16 may be performed in the processor (102, 202) and / or the transceiver (106, 206) of FIG. 15. The hardware elements of FIG. 16 may be implemented in the processor (102, 202) and / or the transceiver (106, 206) of FIG. 15. For example, blocks 1010 to 1060 may be implemented in the processor (102, 202) of FIG. 15. Additionally, blocks 1010 to 1050 may be implemented in the processor (102, 202) of FIG. 15, and block 1060 may be implemented in the transceiver (106, 206) of FIG. 15.

[0258] The codeword can be converted into a wireless signal through the signal processing circuit (1000) of FIG. 16. Here, the codeword is an encoded bit sequence of an information block. The information block can include a transport block (e.g., an UL-SCH transport block, a DL-SCH transport block). The wireless signal can be transmitted through various physical channels (e.g., a PUSCH or a PDSCH).

[0259] Specifically, the codeword can be converted into a bit sequence scrambled by a scrambler (1010). The scramble sequence used for scrambling is generated based on an initialization value, and the initialization value may include ID information of the wireless device, etc. The scrambled bit sequence can be modulated into a modulation symbol sequence by a modulator (1020). The modulation method may include pi / 2-BPSK (pi / 2-Binary Phase Shift Keying), m-PSK (m-Phase Shift Keying), m-QAM (m-Quadrature Amplitude Modulation), etc. The complex modulation symbol sequence can be mapped to one or more transmission layers by a layer mapper (1030). The modulation symbols of each transmission layer can be mapped to the corresponding antenna port(s) by a precoder (1040) (precoding). The output z of the precoder (1040) can be obtained by multiplying the output y of the layer mapper (1030) by a precoding matrix W of N*M. Here, N is the number of antenna ports, and M is the number of transmission layers. Here, the precoder (1040) can perform precoding after performing transform precoding (e.g., DFT transform) on complex modulation symbols. In addition, the precoder (1040) can perform precoding without performing transform precoding.

[0260] The resource mapper (1050) can map modulation symbols of each antenna port to time-frequency resources. The time-frequency resources can include multiple symbols (e.g., CP-OFDMA symbols, DFT-s-OFDMA symbols) in the time domain and multiple subcarriers in the frequency domain. The signal generator (1060) generates a wireless signal from the mapped modulation symbols, and the generated wireless signal can be transmitted to another device through each antenna. To this end, the signal generator (1060) can include an Inverse Fast Fourier Transform (IFFT) module, a Cyclic Prefix (CP) inserter, a Digital-to-Analog Converter (DAC), a frequency uplink converter, etc.

[0261] The signal processing process for receiving signals in a wireless device can be configured in reverse order of the signal processing process (1010 to 1060) of FIG. 16. For example, a wireless device (e.g., 100, 200 of FIG. 15) can receive wireless signals from the outside through an antenna port / transceiver. The received wireless signals can be converted into baseband signals through a signal restorer. For this purpose, the signal restorer can include a frequency downlink converter, an analog-to-digital converter (ADC), a CP remover, and a fast Fourier transform (FFT) module. Thereafter, the baseband signal can be restored to a codeword through a resource demapper process, a postcoding process, a demodulation process, and a descrambling process. The codewords can be restored to the original information blocks 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.

[0262] Figure 17 illustrates a wireless device according to an embodiment of the present disclosure. The wireless device may be implemented in various forms depending on the use case / service (see Figure 14). The embodiment of Figure 17 may be combined with various embodiments of the present disclosure.

[0263] Referring to FIG. 17, the wireless device (100, 200) corresponds to the wireless device (100, 200) of FIG. 15 and may be composed of various elements, components, units / units, and / or modules. For example, the wireless device (100, 200) may include a communication unit (110), a control unit (120), a memory unit (130), and additional elements (140). The communication unit may include a communication circuit (112) and a transceiver(s) (114). For example, the communication circuit (112) may include one or more processors (102, 202) and / or one or more memories (104, 204) of FIG. 15. For example, the transceiver(s) (114) may include one or more transceivers (106, 206) and / or one or more antennas (108, 208) of FIG. 15. The control unit (120) is electrically connected to the communication unit (110), the memory unit (130), and the additional elements (140) and controls the overall operation of the wireless device. For example, the control unit (120) may control the electrical / mechanical operation of the wireless device based on the program / code / command / information stored in the memory unit (130). In addition, the control unit (120) may transmit information stored in the memory unit (130) to an external device (e.g., another communication device) via a wireless / wired interface through the communication unit (110), or store information received from an external device (e.g., another communication device) via a wireless / wired interface in the memory unit (130).

[0264] The additional element (140) may be configured in various ways depending on the type of the wireless device. For example, the additional element (140) may include at least one of a power unit / battery, an input / output unit (I / O unit), a driving unit, and a computing unit. Although not limited thereto, the wireless device may be implemented in the form of a robot (Fig. 14, 100a), a vehicle (Fig. 14, 100b-1, 100b-2), an XR device (Fig. 14, 100c), a portable device (Fig. 14, 100d), a home appliance (Fig. 14, 100e), an IoT device (Fig. 14, 100f), a digital broadcasting terminal, a hologram device, a public safety device, an MTC device, a medical device, a fintech device (or a financial device), a security device, a climate / environmental device, an AI server / device (Fig. 14, 400), a base station (Fig. 14, 200), a network node, etc. Wireless devices may be mobile or stationary depending on the use / service.

[0265] In FIG. 17, various elements, components, units / parts, and / or modules within the wireless device (100, 200) may be interconnected entirely via a wired interface, or at least some may be wirelessly connected via a communication unit (110). For example, within the wireless device (100, 200), the control unit (120) and the communication unit (110) may be wired, and the control unit (120) and the first unit (e.g., 130, 140) may be wirelessly connected via the communication unit (110). In addition, each element, component, unit / part, and / or module within the wireless device (100, 200) may further include one or more elements. For example, the control unit (120) may be composed of one or more processor sets. For example, the control unit (120) may be composed of a set of a communication control processor, an application processor, an electronic control unit (ECU), a graphics processing processor, a memory control processor, etc. As another example, the memory unit (130) may be composed of a random access memory (RAM), a dynamic RAM (DRAM), a read only memory (ROM), a flash memory, a volatile memory, a non-volatile memory, and / or a combination thereof.

[0266] Below, the implementation example of Fig. 17 is described in more detail with reference to the drawings.

[0267] FIG. 18 illustrates a mobile device according to an embodiment of the present disclosure. The mobile device may include a smartphone, a smart pad, a wearable device (e.g., a smartwatch, smartglasses), or a portable computer (e.g., a laptop, etc.). The mobile 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). The embodiment of FIG. 18 may be combined with various embodiments of the present disclosure.

[0268] Referring to FIG. 18, the portable device (100) may include an antenna unit (108), a communication unit (110), a control unit (120), a memory unit (130), a power supply unit (140a), an interface unit (140b), and an input / output unit (140c). The antenna unit (108) may be configured as a part of the communication unit (110). Blocks 110 to 130 / 140a to 140c correspond to blocks 110 to 130 / 140 of FIG. 17, respectively.

[0269] The communication unit (110) can transmit and receive signals (e.g., data, control signals, etc.) with other wireless devices and base stations. The control unit (120) can control components of the mobile device (100) to perform various operations. The control unit (120) can include an AP (Application Processor). The memory unit (130) can store data / parameters / programs / codes / commands required for operating the mobile device (100). In addition, the memory unit (130) can store input / output data / information, etc. The power supply unit (140a) supplies power to the mobile device (100) and can include a wired / wireless charging circuit, a battery, etc. The interface unit (140b) can support connection between the mobile device (100) and other external devices. The interface unit (140b) can include various ports (e.g., audio input / output ports, video input / output ports) for connection with external devices. The input / output unit (140c) can input or output video information / signals, audio information / signals, data, and / or information input from a user. The input / output unit (140c) may include a camera, a microphone, a user input unit, a display unit (140d), a speaker, and / or a haptic module.

[0270] For example, in the case of data communication, the input / output unit (140c) obtains information / signals (e.g., touch, text, voice, image, video) input by the user, and the obtained information / signals can be stored in the memory unit (130). The communication unit (110) converts the information / signals stored in the memory into wireless signals, and can directly transmit the converted wireless signals to other wireless devices or to a base station. In addition, the communication unit (110) can receive wireless signals from other wireless devices or base stations, and then restore the received wireless signals to the original information / signals. The restored information / signals can be stored in the memory unit (130) and then output in various forms (e.g., text, voice, image, video, haptic) through the input / output unit (140c).

[0271] The claims set forth in this specification may be combined in various ways. For example, the technical features of the method claims of this specification may be combined and implemented as a device, and the technical features of the device claims of this specification may be combined and implemented as a method. Furthermore, the technical features of the method claims and the technical features of the device claims of this specification may be combined and implemented as a device, and the technical features of the method claims and the technical features of the device claims of this specification may be combined and implemented as a method.

Claims

1. In the method, A step in which a first device receives, from a second device, information related to a first model relating to sensing data and model parameters; A step of the first device obtaining the sensing data based on sensing of an object; A step in which the first device inputs the sensing data into the first model to obtain the model parameters; and A method comprising: a step of transmitting, by the first device, the model parameters to the second device; 2. In paragraph 1, A method wherein information related to the first model is received from the second device in a procedure for establishing a session between the first device and the second device.

3. In paragraph 1, A method wherein whether the first device accepts the first model is determined based on at least one of the model size, required processing speed or capacity, or number of parameters included in information related to the first model.

4. In paragraph 1, A method in which the encryption level or compression level for the sensing data is based on the properties of the sensing data.

5. In paragraph 1, A method in which the encryption level or compression level for sensing data requiring low privacy is lower than the encryption level or compression level for sensing data requiring high privacy.

6. In paragraph 1, The encryption level or compression level applied to the model parameters that provide a large transmission bandwidth is lower than the encryption level or compression level applied to the model parameters that provide a small transmission bandwidth.

7. In paragraph 1, A method in which the number of model parameters obtained from the sensing data is changed based on the properties of the sensing data.

8. In paragraph 7, A method in which the property of the above sensing data is QoS (quality of service) related to the above sensing data.

9. In paragraph 1, A method further comprising: a step of transmitting, by the first device, the sensing data for validating the first model to the second device; 10. In paragraph 1, A step in which the first device receives information related to the second model from the second device; and A method further comprising: performing validation or learning based on information related to the first model and information related to the second model.

11. In paragraph 1, A method in which sensing parameters are obtained by inputting the model parameters into a second model.

12. In paragraph 11, A method wherein the first model is related to the second model.

13. In paragraph 1, A method wherein the first device is a sensing node and the second device is a server having a sensing function.

14. In the first device, At least one transmitter / receiver; at least one processor; and At least one memory connected to said at least one processor and storing instructions, said instructions causing said first device to perform an operation based on being executed by said at least one processor, said operation comprising: Receiving information related to the first model, including sensing data and model parameters, from the second device; Obtaining the sensing data based on sensing of an object; Inputting the sensing data into the first model to obtain the model parameters; and A first device comprising: transmitting the model parameters to the second device; 15. In the processing device, at least one processor; and At least one memory connected to said at least one processor and storing instructions, said instructions causing the first device to perform an operation based on execution by said at least one processor, said operation comprising: Receiving information related to the first model, including sensing data and model parameters, from the second device; Obtaining the sensing data based on sensing of an object; Inputting the sensing data into the first model to obtain the model parameters; and A processing device comprising: transmitting the model parameters to the second device; 16. A non-transitory computer-readable storage medium that records commands, The above commands, upon being executed, cause the first device to perform an action, wherein the action is: Receiving information related to the first model, including sensing data and model parameters, from the second device; Obtaining the sensing data based on sensing of an object; Inputting the sensing data into the first model to obtain the model parameters; and A non-transitory computer-readable storage medium comprising: transmitting the model parameters to the second device; 17. In the method, A step of the second device obtaining information related to the second model related to model parameters and sensing parameters; A step in which the second device receives the model parameters from the first device; and A method comprising: a step of the second device obtaining the sensing parameters by inputting the model parameters into the second model; 18. In the second device, At least one transmitter / receiver; at least one processor; and At least one memory connected to said at least one processor and storing instructions, said instructions causing said second device to perform an operation based on execution by said at least one processor, said operation comprising: Obtaining information related to a second model, including model parameters and sensing parameters; Receiving the model parameters from the first device; and A second device comprising: inputting the model parameters into the second model to obtain the sensing parameters; 19. In the processing device, at least one processor; and At least one memory connected to said at least one processor and storing instructions, said instructions causing a second device to perform an operation based on execution by said at least one processor, said operation comprising: Obtaining information related to a second model, including model parameters and sensing parameters; Receiving the model parameters from the first device; and A processing device comprising: inputting the model parameters into the second model to obtain the sensing parameters; 20. A non-transitory computer-readable storage medium that records commands, The above commands, based on which they are executed, cause the second device to perform an action, wherein the action is: Obtaining information related to a second model, including model parameters and sensing parameters; Receiving the model parameters from the first device; and A non-transitory computer-readable storage medium comprising: inputting the model parameters into the second model to obtain the sensing parameters.

Images