Method and apparatus for performing semantic communication in wireless communication system

Abstract

The present disclosure relates to a method by which a first node operates in a wireless communication system, and the method may comprise the steps of: establishing a connection with a second node; receiving a first node capability information request from the second node; transmitting first node capability information to the second node on the basis of the first node capability information request; receiving semantic communication instruction information from the second node; performing semantic communication learning on the basis of the received semantic communication instruction information so as to train at least one model; receiving target AI task information from the second node; and encoding input data on the basis of a JSCC encoder model, which corresponds to the target AI task information, and transmitting same to the second node.

Description

Method and device for performing semantic communication in a wireless communication system

[0001] The following describes a method and device for performing semantic communication in a wireless communication system. Specifically, the present invention relates to a method and device for performing semantic communication while considering multi-task operation in a wireless communication system.

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

[0003] In particular, as numerous communication devices demand greater communication capacity, enhanced mobile broadband (eMBB) communication technologies are being proposed, improving upon existing radio access technology (RAT). Furthermore, massive machine type communications (mMTC), which connects multiple devices and objects to provide diverse services anytime and anywhere, as well as communication systems that consider reliability and latency-sensitive services / user equipment (UE), are being proposed. Various technological configurations are being proposed for these solutions.

[0004] The present disclosure relates to a method and device for performing semantic communication in a wireless communication system.

[0005] The present disclosure relates to a method and device for operating a multi-AI (artificial intelligence) task based on semantic communication in a wireless communication system.

[0006] The present disclosure relates to a method and device for performing learning based on AI task combination based on semantic communication in a wireless communication system.

[0007] The present disclosure relates to a method and device for performing multi-AI task-based communication based on a learning model corresponding to a target AI task set based on semantic communication in a wireless communication system.

[0008] The technical objectives to be achieved in the present disclosure are not limited to those mentioned above, and other technical tasks not mentioned can be considered by a person having ordinary skill in the technical field to which the technical configuration of the present disclosure is applied from the embodiments of the present disclosure described below.

[0009] As an example of the present disclosure, a method for operating a first node in a wireless communication system includes the steps of establishing a connection with a second node, receiving a request for first node capability information from the second node, transmitting the first node capability information to the second node based on the request for first node capability information, receiving semantic communication instruction information from the second node, performing semantic communication learning based on the received semantic communication instruction information to perform learning for at least one model, receiving target AI (artificial intelligence) task information from the second node, and encoding input data based on a JSCC (joint source channel coding) encoder model corresponding to the target AI task information and transmitting the encoded input data to the second node, wherein the second node has multiple AI tasks based on semantic communication, and provides reconstructed data generated based on a JSCC decoder model corresponding to the target AI task information as an input to a set target AI task among the multiple AI tasks to derive an output.

[0010] Also, as an example of the present disclosure, in a wireless communication system, a first node includes a transceiver and a processor connected to the transceiver, wherein the processor establishes a connection with a second node, controls the transceiver to receive a first node capability information request from the second node, controls the transceiver to transmit the first node capability information to the second node based on the first node capability information request, controls the transceiver to receive semantic communication instruction information from the second node, performs semantic communication learning based on the received semantic communication instruction information to perform learning for at least one model, controls the transceiver to receive target AI task information from the second node, and controls the transceiver to encode input data based on a JSCC encoder model corresponding to the target AI task information and transmit the encoded input data to the second node, wherein the second node has multiple AI tasks based on semantic communication, and provides reconstructed data generated based on the JSCC decoder model corresponding to the target AI task information as an input of a set target AI task among the multiple AI tasks to derive an output.

[0011] Also, as an example of the present disclosure, in a method for operating a second node in a wireless communication system, there is provided a step of establishing a connection with a first node, a step of transmitting a first node capability information request to the first node, a step of receiving first node capability information from the first node based on the first node capability information request, a step of transmitting semantic communication instruction information to the first node;

[0012] A method comprising: performing semantic communication learning to learn at least one model; transmitting target AI task information to a first node; receiving encoded input data based on a JSCC encoder model corresponding to the target AI task information to generate reconstructed data; and providing the reconstructed data as an input to a target AI task set among multiple AI tasks to derive an output, wherein the second node may be equipped with multiple AI tasks based on semantic communication.

[0013] Also, as an example of the present disclosure, in a wireless communication system, a second node includes a transceiver and a processor connected to the transceiver, wherein the processor establishes a connection with a first node, controls the transceiver to transmit a first node capability information request to the first node, controls the transceiver to receive first node capability information from the first node based on the first node capability information request, controls the transceiver to transmit semantic communication instruction information to the first node, performs semantic communication learning to perform learning for at least one model, controls the transceiver to transmit target AI task information to the first node, controls the transceiver to receive encoded input data based on a JSCC encoder model corresponding to the target AI task information, and provides reconstructed data as an input of a set target AI task among multiple AI tasks to derive an output, wherein the second node may be equipped with multiple AI tasks based on semantic communication.

[0014] Also, as an example of the present disclosure, in a device including at least one memory and at least one processor functionally connected to the at least one memory, the at least one processor controls the device to establish a connection with another device, controls the device to receive a first node capability information request from the other device, controls the device to transmit the first node capability information to the other device based on the first node capability information request, controls the device to receive semantic communication instruction information from the other device, controls the device to perform semantic communication learning based on the received semantic communication instruction information to perform learning for at least one model, controls the device to receive target AI task information from the other device, and controls the device to encode input data based on a JSCC encoder model corresponding to the target AI task information and transmit the encoded input data to the other device, wherein the other device has multiple AI tasks based on semantic communication, and provides reconstructed data generated based on the JSCC decoder model corresponding to the target AI task information as an input of a set target AI task among the multiple AI tasks to derive an output.

[0015] Also, as an example of the present disclosure, a non-transitory computer-readable medium storing at least one instruction includes at least one instruction executable by a processor, wherein the at least one instruction controls a device to establish a connection with another device, controls the device to receive a first node capability information request from the other device, controls the device to transmit the first node capability information to the other device based on the first node capability information request, controls the device to receive semantic communication instruction information from the other device, controls the device to perform semantic communication learning based on the received semantic communication instruction information to perform learning for at least one model, controls the device to receive target AI task information from the other device, and controls the device to encode input data based on a JSCC encoder model corresponding to the target AI task information and transmit the encoded input data to the other device, wherein the other device has a multi-AI task based on semantic communication, and controls the device to generate reconstruction data based on the JSCC decoder model corresponding to the target AI task information among the multi-AI tasks set. It can be provided as input to a target AI task and output can be derived.

[0016] Additionally, the following may be commonly applied:

[0017] As an example of the present disclosure, the first node capability information includes information indicating whether the first node supports multi-AI task-based semantic communication, and the first node capability information may further include at least one of first node generation information, first node collection information, processable raw data type information, and device computation capability information.

[0018] Additionally, as an example of the present disclosure, when the second node decides to perform multi-AI task-based semantic communication based on the first node capability information, semantic communication instruction information may be transmitted to the first node, and semantic communication-related information may be transmitted to the first node together with the semantic communication instruction information.

[0019] In addition, as an example of the present disclosure, the semantic communication-related information may include at least one of rate (R) information, the number of AI tasks supported (N), an index table according to AI task combination, joint source channel coding (JSCC) encoder and JSCC decoder model information, information on whether a quantizer is used, mini-batch size information, loss function information, and reconstruction distortion (D_R) information.

[0020] In addition, as an example of the present disclosure, when the number of AI task combinations is determined based on the number of AI tasks (N) supported, and the JSCC encoder and JSCC decoder models corresponding to the number of AI task combinations and the models for each of the AI ​​tasks supported are set and semantic communication learning is performed, learning for the JSCC encoder and JSCC decoder models corresponding to the number of AI task combinations and learning for each model of the AI ​​tasks supported are performed individually, and then the JSCC encoder and JSCC decoder models and the models for each of the AI ​​tasks supported can be learned together based on a joint method.

[0021] In addition, as an example of the present disclosure, the target AI task information is set based on an index table corresponding to the number of AI task combinations, and when the target AI task information indicates a first index based on the index table, the first node can select a first JSCC encoder model corresponding to the first index to set the JSCC encoder model, and generate a semantic expression through JSCC encoding for input data based on the set JSCC encoder model and transmit the generated semantic expression to the second node.

[0022] In addition, as an example of the present disclosure, the second node can select a first JSCC decoder model corresponding to the first index to set the JSCC decoder model, and decode the received semantic expression through the set JSCC decoder model to obtain reconstructed data.

[0023] Additionally, as an example of the present disclosure, reconstruction data may be provided as input for each set target AI task, and an output may be derived based on the purpose of each set target AI task.

[0024] The above-described aspects of the present disclosure are only some of the preferred embodiments of the present disclosure, and various embodiments reflecting the technical features of the present disclosure can be derived and understood by a person having ordinary skill in the art based on the detailed description of the present disclosure to be described below.

[0025] The following effects may be achieved by embodiments based on the present disclosure.

[0026] According to the present disclosure, a method for performing semantic communication can be provided.

[0027] According to the present disclosure, a multi-AI (artificial intelligence) task operation-based operation method can be provided based on semantic communication.

[0028] According to the present disclosure, learning can be performed based on a combination of AI tasks based on semantic communication.

[0029] The present disclosure can perform multi-AI task-based communication based on a learning model corresponding to a target AI task set based on semantic communication in a wireless communication system.

[0030] The effects that can be obtained from the embodiments of the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly derived and understood by those skilled in the art to which the technical configuration of the present disclosure is applied, from the description of the embodiments of the present disclosure below. In other words, unintended effects that result from implementing the configuration described in the present disclosure can also be derived by those skilled in the art from the embodiments of the present disclosure.

[0031] The accompanying drawings are intended to aid understanding of the present disclosure and, together with detailed descriptions, may provide embodiments of the present disclosure. However, the technical features of the present disclosure are not limited to specific drawings, and the features disclosed in each drawing may be combined with each other to form new embodiments. Reference numerals in each drawing may indicate structural elements.

[0032] Figure 1 illustrates an example of a communication system applicable to the present disclosure.

[0033] FIG. 2 illustrates an example of a wireless device applicable to the present disclosure.

[0034] FIG. 3 illustrates a method for processing a transmission signal applicable to the present disclosure.

[0035] Figure 4 illustrates a communication procedure between a terminal and a base station applicable to the present disclosure.

[0036] FIG. 5 illustrates an example of a communication structure that can be provided in a 6G (6th generation) system applicable to the present disclosure.

[0037] Figure 6 illustrates an electromagnetic spectrum applicable to the present disclosure.

[0038] FIG. 7 illustrates a THz wireless communication transceiver applicable to the present disclosure.

[0039] Figure 8 illustrates a THz signal generation method applicable to the present disclosure.

[0040] FIG. 9 illustrates a wireless communication transceiver applicable to the present disclosure.

[0041] Figure 10 illustrates a transmitter structure applicable to the present disclosure.

[0042] Figure 11 illustrates a modulator structure applicable to the present disclosure.

[0043] Figure 12 illustrates the structure of a perceptron included in an artificial neural network applicable to the present disclosure.

[0044] Figure 13 illustrates an artificial neural network structure applicable to the present disclosure.

[0045] Figure 14 is a diagram showing a communication model divided into three stages applicable to the present disclosure.

[0046] FIG. 15 is a diagram showing an encoder and decoder block applicable to the present disclosure.

[0047] Figure 16 is a diagram showing an information bottleneck method applicable to the present disclosure.

[0048] FIG. 17 is a diagram illustrating a task-based semantic communication operation using rate-distortion theory applicable to the present disclosure.

[0049] FIG. 18 is a diagram illustrating a method for performing multi-task-based semantic communication applicable to the present disclosure.

[0050] FIG. 19 is a diagram illustrating a method for performing an inference operation in semantic communication based on a multi-task applicable to the present disclosure.

[0051] FIG. 20 is a diagram showing the results of performing an inference operation in semantic communication based on a multi-task applicable to the present disclosure.

[0052] Figure 21 is a diagram showing an initial setting method of semantic communication applicable to the present disclosure.

[0053] FIG. 22 is a diagram showing information transmitted when learning for semantic communication based on multi-task applicable to the present disclosure is performed.

[0054] Figure 23 is a diagram illustrating inference performance of multi-task-based semantic communication applicable to the present disclosure.

[0055] Figure 24 is a flowchart showing a first node operation method applicable to the present disclosure.

[0056] Figure 25 is a flowchart showing a second node operation method applicable to the present disclosure.

[0057] The following embodiments combine the components and features of the present disclosure in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented without being combined with other components or features. Furthermore, some components and / or features may be combined to form embodiments of the present disclosure. The order of operations described in the embodiments of the present disclosure may be changed. Some components or features of one embodiment may be included in another embodiment or may be replaced with corresponding components or features of another embodiment.

[0058] In the description of the drawings, procedures or steps that may obscure the gist of the present disclosure are not described, and procedures or steps that can be understood by a person skilled in the art are also not described.

[0059] Throughout the specification, when a part is said to "comprising" or "including" a component, this does not mean that other components may be included, but rather that other components may be excluded, unless otherwise specifically stated. In addition, terms such as "...part," "...unit," and "module" described in the specification mean a unit that processes at least one function or operation, which may be implemented by hardware, software, or a combination of hardware and software. In addition, the words "a" or "an," "one," "the," and similar related words may be used in the context of describing the present disclosure (especially in the context of the claims below) to include both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context.

[0060] Embodiments of the present disclosure described herein focus on the data transmission and reception relationship between a base station and a mobile station. Here, the base station is understood as a terminal node of a network that directly communicates with the mobile station. Certain operations described herein as being performed by the base station may, in some cases, be performed by an upper node of the base station.

[0061] That is, in a network consisting of multiple network nodes including a base station, various operations performed for communication with a mobile station may be performed by the base station or other network nodes other than the base station. In this case, the term 'base station' may be replaced by terms such as fixed station, Node B, eNB (eNode B), gNB (gNode B), ng-eNB, advanced base station (ABS), or access point.

[0062] Additionally, in the embodiments of the present disclosure, the term terminal may be replaced with terms such as user equipment (UE), mobile station (MS), subscriber station (SS), mobile subscriber station (MSS), mobile terminal, or advanced mobile station (AMS).

[0063] Additionally, a transmitter refers to a fixed and / or mobile node that provides data or voice services, and a receiver refers to a fixed and / or mobile node that receives data or voice services. Therefore, for uplink, a mobile station can be the transmitter, and a base station can be the receiver. Similarly, for downlink, a mobile station can be the receiver, and a base station can be the transmitter.

[0064] Embodiments of the present disclosure may be supported by standard documents disclosed in at least one of wireless access systems, such as IEEE 802.xx system, 3rd Generation Partnership Project (3GPP) system, 3GPP Long Term Evolution (LTE) system, 3GPP 5th generation (5G) NR (New Radio) system and 3GPP2 system, and in particular, embodiments of the present disclosure may be supported by 3GPP TS (technical specification) 38.211, 3GPP TS 38.212, 3GPP TS 38.213, 3GPP TS 38.321 and 3GPP TS 38.331 documents.

[0065] Furthermore, the embodiments of the present disclosure can be applied to other wireless access systems and are not limited to the systems described above. For example, they can be applied to systems implemented after the 3GPP 5G NR system and are not limited to a specific system.

[0066] That is, obvious steps or parts not described in the embodiments of the present disclosure can be explained by referring to the above documents. In addition, all terms disclosed in this document can be explained by the above standard documents.

[0067] Hereinafter, preferred embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. The detailed description set forth below, together with the accompanying drawings, is intended to illustrate exemplary embodiments of the present disclosure and is not intended to represent the only embodiments in which the technical configurations of the present disclosure may be implemented.

[0068] Additionally, specific terms used in the embodiments of the present disclosure are provided to aid in understanding of the present disclosure, and the use of such specific terms may be changed to other forms without departing from the technical spirit of the present disclosure.

[0069] The following technology can be applied to various wireless access systems such as CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), and SC-FDMA (single carrier frequency division multiple access).

[0070] For clarity, the following description is based on 3GPP communication systems (e.g., LTE, NR, etc.), but the technical spirit of the present disclosure is not limited thereto. LTE may refer to technology after 3GPP TS 36.xxx Release 8. Specifically, LTE technology after 3GPP TS 36.xxx Release 10 may be referred to as LTE-A, and LTE technology after 3GPP TS 36.xxx Release 13 may be referred to as LTE-A pro. 3GPP NR may refer to technology after TS 38.xxx Release 15. 3GPP 6G may refer to technology after TS Release 17 and / or Release 18. "xxx" refers to a standard document detail number. LTE / NR / 6G may be collectively referred to as a 3GPP system.

[0071] For background information, terms, abbreviations, etc. used in this disclosure, reference may be made to standard documents published prior to this disclosure. For example, reference may be made to standard documents 36.xxx and 38.xxx.

[0072] Communication system applicable to the present disclosure

[0073] Although not limited thereto, the various descriptions, functions, procedures, proposals, methods and / or operational flowcharts of the present disclosure disclosed in this document may be applied to various fields requiring wireless communication / connectivity (e.g., 5G) between devices.

[0074] 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.

[0075] Figure 1 illustrates an example of a communication system applied to the present disclosure.

[0076] Referring to FIG. 1, a communication system (100) applied to the present disclosure 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., LTE, LTE-A, LTE-A pro, NR, 5G, 5G-A, 6G) and may be referred to as a communication / wireless / 5G device. Although not limited thereto, the wireless device may include a robot (100a), a vehicle (100b-1, 100b-2), an XR (extended reality) device (100c), a hand-held device (100d), a home appliance (100e), an IoT (Internet of Things) device (100f), and an AI (artificial intelligence) device / server (100g). 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 vehicles (100b-1, 100b-2) may include unmanned aerial vehicles (UAVs) (e.g., drones). The XR devices (100c) include augmented reality (AR) / virtual reality (VR) / mixed reality (MR) devices, and may be implemented in the form of head-mounted devices (HMDs), head-up displays (HUDs) installed in vehicles, televisions, smartphones, computers, wearable devices, home appliances, digital signage, vehicles, robots, etc. The portable devices (100d) may include smartphones, smart pads, wearable devices (e.g., smartwatches, smart glasses), computers (e.g., laptops, etc.), etc. The home appliances (100e) may include TVs, refrigerators, washing machines, etc. The IoT devices (100f) may include sensors, smart meters, etc.For example, the base station (120) and the network (130) may also be implemented as wireless devices, and a specific wireless device (120a) may act as a base station / network node to other wireless devices.

[0077] Wireless devices (100a to 100f) can be connected to a network (130) via a base station (120). 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 (100g) via a network (130). The network (130) can be configured using a 3G network, a 4G (e.g., LTE) network, a 5G (e.g., NR), or a 6G network. The wireless devices (100a to 100f) can communicate with each other via the base station (120) / network (130), but can also communicate directly (e.g., sidelink communication) without going through the base station (120) / network (130). For example, vehicles (100b-1, 100b-2) can communicate directly (e.g., V2V (vehicle to vehicle) / V2X (vehicle to everything) communication). Additionally, an IoT device (100f) (e.g., a sensor) can communicate directly with another IoT device (e.g., a sensor) or another wireless device (100a to 100f).

[0078] Wireless communication / connection (150a, 150b, 150c) can be established between wireless devices (100a to 100f) / base stations (120), and base stations (120) / base stations (120). Here, the wireless communication / connection can be established through various wireless access technologies 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 the wireless communication / connection (150a, 150b, 150c), the wireless device and base station / wireless device, and base stations and base stations can transmit / receive wireless signals to / from each other. For example, the wireless communication / connection (150a, 150b, 150c) can transmit / receive signals through various physical channels. To this end, based on various proposals of the present disclosure, 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.), resource allocation processes, etc. may be performed.

[0079] Devices applicable to the present disclosure

[0080] FIG. 2 illustrates an example of a wireless device applicable to the present disclosure.

[0081] Referring to FIG. 2, the wireless device (200) can transmit and receive wireless signals via various wireless access technologies (e.g., LTE, LTE-A, LTE-A pro, NR, 5G, 5G-A, 6G). The wireless device (200) includes at least one processor (202) and at least one memory (204), and may additionally include at least one transceiver (206) and / or at least one antenna (208).

[0082] The processor (202) controls the memory (204) and / or the transceiver (206), and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document. For example, the processor (202) may process information in the memory (204) to generate first information / signal, and then transmit a wireless signal including the first information / signal via the transceiver (206). In addition, the processor (202) may receive a wireless signal including second information / signal via the transceiver (206), and then store information obtained from signal processing of the second information / signal in the memory (204). The memory (204) may be connected to the processor (202) and may store various information related to the operation of the processor (202). For example, the memory (204) may store software code including instructions for performing some or all of the processes controlled by the processor (202), or for performing the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed herein. Here, the processor (202) and the memory (204) may be part of a communication modem / circuit / chip designed to implement wireless communication technology. The transceiver (206) may be connected to the processor (202) and may transmit and / or receive wireless signals via at least one antenna (208). The transceiver (206) may include a transmitter and / or a receiver. The transceiver (206) 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.

[0083] Hereinafter, the hardware elements of the wireless device (200) will be described in more detail. Although not limited thereto, at least one protocol layer may be implemented by at least one processor (202). For example, at least one processor (202) may implement at least one layer (e.g., a functional layer such as physical (PHY), media access control (MAC), radio link control (RLC), packet data convergence protocol (PDCP), radio resource control (RRC), and service data adaptation protocol (SDAP)). At least one processor (202) may generate at least one Protocol Data Unit (PDU) and / or at least one Service Data Unit (SDU) according to the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this document. At least one processor (202) may generate a message, control information, data, or information according to the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this document. At least one processor (202) can generate a signal (e.g., a baseband signal) including a PDU, an SDU, a message, control information, data or information according to the functions, procedures, proposals and / or methods disclosed in this document, and provide the signal to at least one transceiver (206). At least one processor (202) can receive a signal (e.g., a baseband signal) from at least one transceiver (206) and obtain the PDU, SDU, message, control information, data or information according to the descriptions, functions, procedures, proposals, methods and / or operational flowcharts disclosed in this document.

[0084] At least one processor (202) may be referred to as a controller, a microcontroller, a microprocessor, or a microcomputer. The at least one processor (202) may be implemented by hardware, firmware, software, or a combination thereof. For example, at least one application specific integrated circuit (ASIC), at least one digital signal processor (DSP), at least one digital signal processing device (DSPD), at least one programmable logic device (PLD), or at least one field programmable gate array (FPGA) may be included in the at least one processor (202). The descriptions, functions, procedures, proposals, methods, and / or operation 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, proposals, methods, and / or operation flowcharts disclosed in this document may be included in the at least one processor (202), or may be stored in at least one memory (204) and driven by the at least one processor (202). The descriptions, functions, procedures, suggestions, methods and / or flowcharts disclosed in this document may be implemented using firmware or software in the form of code, instructions and / or sets of instructions.

[0085] At least one memory (204) can be connected to at least one processor (202) and can store various forms of data, signals, messages, information, programs, codes, instructions and / or commands. The at least one memory (204) can be configured as a read only memory (ROM), a random access memory (RAM), an erasable programmable read only memory (EPROM), a flash memory, a hard drive, a register, a cache memory, a computer readable storage medium and / or a combination thereof. The at least one memory (204) can be located internally and / or externally to the at least one processor (202). In addition, the at least one memory (204) can be connected to the at least one processor (202) via various technologies such as a wired or wireless connection.

[0086] At least one transceiver (206) can transmit user data, control information, wireless signals / channels, etc., mentioned in the methods and / or flowcharts of this document to at least one other device. At least one transceiver (206) can receive user data, control information, wireless signals / channels, etc. mentioned in the descriptions, functions, procedures, proposals, methods and / or flowcharts disclosed in this document from at least one other device. For example, at least one transceiver (206) can be connected to at least one processor (202) and can transmit and receive wireless signals. For example, at least one processor (202) can control at least one transceiver (206) to transmit user data, control information, or wireless signals to at least one other device. Furthermore, at least one processor (202) can control at least one transceiver (206) to receive user data, control information, or wireless signals from at least one other device. In addition, at least one transceiver (206) may be connected to at least one antenna (208), and at least one transceiver (206) may be configured to transmit and receive user data, control information, wireless signals / channels, etc. mentioned in the descriptions, functions, procedures, proposals, methods and / or operation flowcharts disclosed in this document through at least one antenna (208). In this document, at least one antenna may be a plurality of physical antennas or a plurality of logical antennas (e.g., antenna ports). At least one transceiver (206) may convert the received wireless signals / channels, etc. from RF band signals to baseband signals in order to process the received user data, control information, wireless signals / channels, etc. using at least one processor (202). At least one transceiver (206) may convert the processed user data, control information, wireless signals / channels, etc. from baseband signals to RF band signals using at least one processor (202).For this purpose, at least one transceiver (206) may include an (analog) oscillator and / or filter.

[0087] The components of the wireless device described with reference to FIG. 2 may be referred to by different terms in terms of functionality. For example, the processor (202) may be referred to as a control unit, the transceiver (206) as a communication unit, and the memory (204) as a storage unit. In some cases, the communication unit may be used to mean at least a portion of the processor (202) and the transceiver (206).

[0088] The structure of the wireless device described with reference to FIG. 2 can be understood as the structure of at least a portion of various devices. For example, the structure of the wireless device illustrated in FIG. 2 can be at least a portion of various devices described with reference to FIG. 1 (e.g., a robot (100a), a vehicle (100b-1, 100b-2), an XR device (100c), a portable device (100d), a home appliance (100e), an IoT device (100f), an AI device / server (100g)). Furthermore, according to various embodiments, in addition to the components illustrated in FIG. 2, the device may further include other components.

[0089] For example, the device may be a portable device such as a smartphone, a smart pad, a wearable device (e.g., a smart watch, smart glasses), or a portable computer (e.g., a laptop, etc.). In this case, the device may further include at least one of a power supply unit that supplies power and includes a wired / wireless charging circuit, a battery, etc., an interface unit that includes at least one port for connection with another device (e.g., an audio input / output port, a video input / output port), and an input / output unit for inputting and outputting image information / signals, audio information / signals, data, and / or information input from a user.

[0090] For example, the device may be a mobile device such as a mobile robot, a vehicle, a train, an aerial vehicle (AV), a ship, etc. In this case, the device may further include at least one of a driving unit including at least one of an engine, a motor, a power train, wheels, brakes, and a steering unit of the device, a power supply unit including a wired / wireless charging circuit, a battery, etc. that supplies power, a sensor unit that senses status information, environmental information, and user information of the device or its surroundings, an autonomous driving unit that performs functions such as path maintenance, speed control, and destination setting, and a position measurement unit that obtains location information of the mobile device through a global positioning system (GPS) and various sensors.

[0091] For example, the device may be an XR device such as an HMD, a head-up display (HUD) installed in a vehicle, a television, a smartphone, a computer, a wearable device, a home appliance, a digital signage, a vehicle, a robot, etc. In this case, the device may further include at least one of a power supply unit that supplies power and includes a wired / wireless charging circuit, a battery, etc., an input / output unit that obtains control information, data, etc. from the outside and outputs the generated XR object, and a sensor unit that senses status information, environmental information, and user information of the device or the surroundings of the device.

[0092] For example, the device may be a robot that can be classified into industrial, medical, household, military, etc. types depending on the purpose or field of use. In this case, the device may further include at least one of a sensor unit that senses status information, environmental information, and user information of the device or its surroundings, and a driving unit that performs various physical actions, such as moving the robot joints.

[0093] For example, the device may be an AI device such as a TV, a projector, a smartphone, a PC, a laptop, a digital broadcasting terminal, a tablet PC, a wearable device, a set-top box (STB), a radio, a washing machine, a refrigerator, digital signage, a robot, a vehicle, etc. In this case, the device may further include at least one of an input unit that acquires various types of data from the outside, an output unit that generates output related to sight, hearing, or touch, a sensor unit that senses status information, environmental information, and user information of the device or its surroundings, and a training unit that trains a model composed of an artificial neural network using learning data.

[0094] The structure of the wireless device illustrated in FIG. 2 may be understood as a part of a RAN node (e.g., a base station, DU, RU, RRH, etc.). That is, the device illustrated in FIG. 2 may be a RAN node. In this case, the device may further include a wired transceiver for front haul and / or back haul communications. However, if the front haul and / or back haul communications are based on wireless communications, at least one transceiver (206) illustrated in FIG. 2 may be used for front haul and / or back haul communications, and a wired transceiver may not be included.

[0095] FIG. 3 illustrates a method for processing a transmission signal applicable to the present disclosure. For example, the transmission signal may be processed by a signal processing circuit. At this time, the signal processing circuit (300) may include a scrambler (310), a modulator (320), a layer mapper (330), a precoder (340), a resource mapper (350), and a signal generator (360). At this time, as an example, the operations / functions of FIG. 3 may be performed in the processor (202) and / or the transceiver (206) of FIG. 2. Furthermore, as an example, the hardware elements of FIG. 3 may be implemented in the processor (202) and / or the transceiver (206) of FIG. 2. As an example, blocks 310 to 360 may be implemented in the processor (202) of FIG. 2. Additionally, blocks 310 to 350 may be implemented in the processor (202) of FIG. 2, and block 360 may be implemented in the transceiver (206) of FIG. 2, and are not limited to the above-described embodiment.

[0096] The codeword can be converted into a wireless signal through the signal processing circuit (300) of FIG. 3. Here, the codeword is an encoded bit sequence of an information block. The information block may include a transport block (e.g., a UL-SCH transport block, a DL-SCH transport block). The wireless signal may be transmitted through various physical channels (e.g., a PUSCH, a PDSCH). Specifically, the codeword can be converted into a bit sequence scrambled by a scrambler (310). 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 (320). The modulation scheme may include pi / 2-binary phase shift keying (pi / 2-BPSK), m-phase shift keying (m-PSK), m-quadrature amplitude modulation (m-QAM), etc.

[0097] A complex modulation symbol sequence can be mapped to at least one transmission layer by a layer mapper (330). The modulation symbols of each transmission layer can be mapped to corresponding antenna port(s) by a precoder (340). The output z of the precoder (340) can be obtained by multiplying the output y of the layer mapper (330) by an N×M precoding matrix W. Here, N is the number of antenna ports, and M is the number of transmission layers. Here, the precoder (340) can perform precoding after performing transform precoding (e.g., discrete Fourier transform (DFT) transform) on the complex modulation symbols. Additionally, the precoder (340) can perform precoding without performing transform precoding.

[0098] The resource mapper (350) 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 (360) 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 (360) can include an inverse fast Fourier transform (IFFT) module, a cyclic prefix (CP) inserter, a digital-to-analog converter (DAC), a frequency uplink converter, and the like.

[0099] The signal processing process for a received signal in a wireless device may be configured in reverse order of the signal processing process (310 to 360) of FIG. 3. For example, a wireless device (e.g., 200 of FIG. 2) may receive a wireless signal from the outside through an antenna port / transceiver. The received wireless signal may be converted into a baseband signal through a signal restorer. For this purpose, the signal restorer may include a frequency downlink converter, an analog-to-digital converter (ADC), a CP remover, and a fast Fourier transform (FFT) module. Thereafter, the baseband signal may be restored to a codeword through a resource demapper process, a postcoding process, a demodulation process, and a descrambling process. The codeword may be restored to the original information block through decoding. Therefore, a signal processing circuit (not shown) for a received signal may include a signal restorer, a resource demapper, a postcoder, a demodulator, a descrambler, and a decoder.

[0100] Figure 4 illustrates a communication procedure between a terminal and a base station applicable to the present disclosure. Figure 4 illustrates operations of a terminal (410) and a base station (420) transmitting and / or receiving data and operations performed prior thereto.

[0101] Referring to FIG. 4, in step 401, the terminal (410) and the base station (420) perform synchronization. For example, the terminal (410) performs an initial cell search operation. Specifically, the terminal (410) can detect at least one synchronization signal transmitted from the base station (420) according to a predefined rule. Here, the synchronization signal can include multiple synchronization signals classified according to structure or purpose (e.g., primary synchronization signal, secondary synchronization signal). Through this, the terminal (410) can check the boundary of the frame, subframe, slot, and / or symbol of the base station (420) and obtain information about the base station (420) (e.g., cell identifier).

[0102] In step 403, the terminal (410) obtains system information transmitted from the base station (420). The system information is information related to the properties, characteristics, and / or capabilities of the base station (420) required to access the base station (420) and use the service, and may be classified according to the content (e.g., whether it is essential for access), transmission structure (e.g., channel used, whether provided on-demand), etc., and may be classified into, for example, a master information block (MIB) and a system information block (SIB). If necessary, the terminal (410) may transmit a signal requesting system information before receiving the system information. However, the request and provision of the system information may be performed after the random access procedure described below.

[0103] In step 405, the terminal (410) and the base station (420) perform a random access procedure. The terminal (410) may transmit and / or receive at least one message (e.g., a random access preamble, a random access response (RAR) message, etc.) for the random access procedure based on information related to the random access channel of the base station (420) obtained through system information (e.g., channel position, channel structure, supported preamble structure, etc.). For example, the terminal (410) may transmit a preamble (e.g., MSG1) through the random access channel, receive an RAR message (e.g., MSG2), transmit a message (e.g., MSG3) including information related to the terminal (410) (e.g., identification information) to the base station (420) using scheduling information included in the RAR message, and receive a message (e.g., MSG4) for contention resolution and / or connection establishment. As another example, MSG1 and MSG3 may be sent and received as one message, or MSG2 and MSG4 may be sent and received as one message.

[0104] In step 407, the terminal (410) and the base station (420) perform signaling of control information. Here, the control information may be defined in various layers, such as a layer that controls 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), and a layer that handles physical channels (e.g., a physical (PHY) layer). For example, the terminal (410) and the base station (420) may perform at least one of signaling for establishing a connection, signaling for determining settings related to communication, and signaling for indicating allocated resources.

[0105] In step 409, the terminal (410) and the base station (420) transmit and / or receive data. In other words, the terminal (410) and the base station (420) can process, transmit, and / or receive data based on the signaling of the control information. For example, when transmitting data, the terminal (410) or the base station (420) can perform at least one of channel encoding, rate matching, scrambling, constellation mapping, layer mapping, waveform modulation, antenna mapping, and resource mapping on the information bits. Conversely, when receiving data, the terminal (410) or the base station (420) can perform at least one of signal extraction from resources, waveform demodulation for each antenna, signal arrangement considering layer mapping, constellation demapping, descrambling, and channel decoding.

[0106] 6G communication systems and core implementation technologies of 6G systems

[0107] The 5G system defines various operating bands within FR1 (frequency range 1), which covers 410 MHz to 7125 MHz, and FR2 (frequency range 2), which covers 24,250 MHz to 71,000 MHz. Various frequencies are being discussed as operating bands for the subsequent 6G system, and the use of higher frequencies than 5G systems is also being considered for wider bandwidth and higher transmission speeds. One such band is the THz (terahertz) frequency band, which covers approximately 100 GHz to 10 THz. The THz frequency band is a band that has both the transparency of radio waves and the straightness of light waves, and communications using the THz frequency band are expected to play a transitional role from existing radio-centered communications to lightwave-based communications.

[0108] 6G systems utilizing the THz frequency band have the following goals: i) very high data rates per device, ii) a very large number of connected devices, iii) global connectivity, iv) very low latency, v) reduced energy consumption of battery-free IoT devices, vi) ultra-reliable connectivity, and vii) connected intelligence with machine learning capabilities. The vision of the 6G system can be divided into four aspects: “intelligent connectivity,” “deep connectivity,” “holographic connectivity,” and “ubiquitous connectivity,” and the 6G system can be designed to satisfy the requirements as shown in [Table 1] below.

[0109] [Table 1]

[0110]

[0111] At this time, the 6G system may have key factors such as enhanced mobile broadband (eMBB), ultra-reliable low latency communications (URLLC), massive machine type communications (mMTC), AI integrated communication, tactile internet, high throughput, high network capacity, high energy efficiency, low backhaul and access network congestion, and enhanced data security.

[0112] Figure 5 illustrates an example of a communication structure that can be provided in a 6G system applicable to the present disclosure. Referring to Figure 5, a 6G system is expected to have 50 times higher simultaneous wireless communication connectivity than a 5G wireless communication system. URLLC, a key feature of 5G, is expected to become an even more important technology in 6G communications by providing end-to-end latency of less than 1 ms. Furthermore, 6G systems will have significantly superior volumetric spectral efficiency, unlike the frequently used area spectral efficiency. 6G systems can provide extremely long battery life and advanced battery technologies for energy harvesting, so mobile devices in 6G systems may not need to be separately charged.

[0113] As core implementation technologies of the 6G system, technologies such as artificial intelligence (AI), THz (terahertz) communication, optical wireless technology, FSO backhaul network, massive MIMO technology, blockchain, 3D networking, quantum communication, unmanned aerial vehicles, cell-free communication, wireless information and energy transfer (WIET), integration of sensing and communication, integration of access backhaul networks, holographic beamforming, big data analysis, and large intelligent surface (LIS) can be adopted.

[0114] For example, THz communication is a communication that utilizes a spectrum in a frequency band between 0.1 THz and 10 THz with a corresponding wavelength in the range of 0.03 mm to 3 mm as shown in Fig. 6, and can be implemented using circuit elements having a structure as shown in Fig. 7. In addition, optical wireless technology is a technology that generates and modulates THz signals using optical elements, and can be implemented based on devices having structures as shown in Figs. 8, 9, 10, and 11.

[0115] In addition, artificial intelligence can be implemented based on various models such as neural networks and machine learning (machine models). For example, an artificial intelligence model of a neural network structure can be based on the structure of a perceptron as in Fig. 12. Referring to Fig. 12, an artificial neural network can be composed of multiple perceptrons. According to the structure of the perceptron, when an input vector x={x1, x2, ... xd} is input, each component is multiplied by a weight {W1, W2, ... Wd}, and all the results are added, and then the activation function σ(·) is applied. A large artificial neural network structure can be formed by extending the simplified perceptron structure illustrated in Fig. 12, and the input vector can be applied to perceptrons of different dimensions. When perceptrons are stacked, a neural network having an input layer, a hidden layer, and an output layer as in Fig. 13 can be configured.

[0116] Specific embodiments of the present disclosure

[0117] Figure 14 is a diagram illustrating a three-stage communication model applicable to the present disclosure. Referring to Figure 14, the communication model can be explained by dividing it into three stages. Stage 1, from a technical perspective, may be concerned with whether symbols for communication are accurately transmitted, and Shannon's information theory can be viewed as a theory focusing on this technical aspect. On the other hand, Stage 2, from a semantic perspective, may be concerned with how accurately the transmitted symbols convey the correct meaning, and Stage 3, from an effectiveness perspective, may be concerned with how effectively the received meaning influences the correct operation.

[0118] One of the various goals of 6G communications may be to provide services that interconnect humans and machines. Semantic communication, based on the concept of "meaning transfer," can be considered as one of the next-generation wireless communication paradigms for this purpose. For example, conventional communication involves a receiver (e.g., destination) decoding an encoded signal received from a transmitter (e.g., source) into a conventional signal without error. In contrast, semantic communication focuses on the meaning intended to be conveyed through the signal, as people exchange information through the "meaning" of words when communicating.

[0119] For example, semantic communication can be a communication method based on whether the concept related to the message sent by the source is correctly interpreted by the destination. For example, the source can generate a semantic representation based on raw data and transmit it to the destination. The destination can perform communication by evaluating whether the task intended by the source is performed properly using the received semantic representation, rather than with the goal of reducing reconstruction errors. In other words, in semantic communication, communication can be performed based on whether the task is performed properly (i.e., whether the interpretation is correct) at the destination, rather than with the goal of reducing reconstruction errors.

[0120] As a specific example, a source can generate a semantic representation and transmit it to a destination. Here, the source needs to generate the semantic representation by considering the task operations performed at the destination. In other words, the source can operate based on a task-oriented semantic communication system that enables the generation of a semantic representation based on whether the task operations are performed well at the destination. Considering the above, there is a need to introduce useful invariances for the tasks performed at the destination while preserving task-relevant information. For example, to perform semantic communication considering the above, a new layer can be added as a semantic layer that governs the overall operation of semantic representations and messages. For example, the semantic layer can be located at both the source and the destination, reflecting the task-oriented semantic communication system. To perform communication between semantic radars located at each of the source and the destination, a protocol and a series of operation procedures, which are rules between the layers, need to be determined.

[0121] For example, in relation to semantic communication, an approach (or perspective) based on rate distortion may be considered, but this is only one example and may not be limited thereto. Here, when performing lossy compression based on a rate distortion method, the signal compression ratio and loss may have a trade-off relationship. For example, signal loss may refer to the degree of distortion between original data and reconstructed data generated after decoding. In other words, signal loss may be based on the difference between the restored information and the original information.

[0122] Fig. 15 is a diagram showing an encoder and decoder block applicable to the present disclosure. Referring to Fig. 15(a), the input X passes through the encoder (1510) and transmits the result, and the received information is decoded through the decoder (1520) to generate a restored output. Here, the distortion (distortion ) is input X and output Considering the relationship between the input X and the output, it can be as shown in the following mathematical formula 1. For example, input X and output Maximum distortion between (distortion ) is allowed, the transmission rate R can be as shown in the following mathematical expression 2, and the trade-off relationship between the transmission rate and distortion can be expressed as a rate-distortion curve as shown in Fig. 15(b). Here, the achievable region can be determined as the upper region of the rate-distortion curve.

[0123] [Mathematical Formula 1]

[0124]

[0125] [Equation 2]

[0126]

[0127] FIG. 16 is a diagram illustrating an information bottleneck method applicable to the present disclosure. Referring to FIG. 16, the rate-distortion method can be extended to an information bottleneck (IB) approach that solves the problem of operating while maintaining source-related variables when compressing a source through encoding and decoding. The IB method can operate by compressing X while maintaining information about Y, given a joint probability distribution (p(X,Y)) between a random variable X and an observed relevant variable Y. Accordingly, Y can implicitly define what is related to X and what is not, and the above-described problem can be expressed as Equation 3 when a random variable T is given in a compressed representation.

[0128] [Equation 3]

[0129]

[0130] In mathematical expression 3, I(X;T) and I(T;Y) may be mutual information (MI), which is an indicator of how dependent one random variable is on another random variable for X and T and T and Y, respectively. The IB method may be a method that aims to find an optimal tradeoff between minimizing I(X;T), maximizing I(T;Y), and maximizing the compression ratio, and preserving effectiveness information.

[0131] FIG. 17 is a diagram illustrating a task-based semantic communication operation that applies the rate-distortion theory applicable to the present disclosure. Referring to FIG. 17, an input is derived as a semantic representation by an encoder, and the semantic representation can be restored as reconstructed data by a decoder. Thereafter, the reconstructed data can be used as input for an artificial intelligence (AI) task. In other words, the semantic communication of FIG. 17 may be a task-based semantic communication method that performs decoding based on a signal encoded based on the rate-distortion theory and transmitted through a channel to reconstruct data, and uses the reconstructed data as input to a downstream task to obtain the intended output from the source.

[0132] As a specific example, referring to Fig. 17, reconstructed data from input data X To obtain , training can be performed on a JSCC (joint source channel coding) encoder and a JSCC decoder. Here, the JSCC encoder and JSCC decoder can be trained jointly based on the reconstructed data. In addition, separate training can be performed for downstream tasks as the main AI task. For example, the AI ​​task can be added in a pre-trained form, and is not limited to a specific form.

[0133] That is, separate training can be performed for the JSCC encoder and JSCC decoder and the AI ​​task. Then, the two modules can be trained together in a joint manner. The loss function used to train the two modules simultaneously can be as shown in Equation 4 below. In Equation 4, R can be the rate of Equation 2, and λ can be a hyperparameter representing the rate-distortion trade-off. Furthermore, can be the MSE (Mean Squared Error) reconstruction distortion, and can be expressed as in Equation 5 below. In addition, in Equation 4, may be task-related distortions, can be expressed as mathematical formula 6. Here, (X, ) is X and can be the expected value of the related information distortion between the two, and Y can be the label held by the main AI task for learning. Finally, in Equation 4, β can be a hyperparameter representing the trade-off between reconstruction quality and the target downstream task.

[0134] [Equation 4]

[0135]

[0136] [Equation 5]

[0137]

[0138] [Equation 6]

[0139]

[0140] In addition, after performing all learning as described above in Figure 17, a downstream task with a different purpose from the existing one can be added as an extended AI task in an ADD-ON manner to perform a generalization performance evaluation. Here, learning after restructuring the input data can be performed based on a single task of the destination. For example, if the destination considers multiple tasks with different performance purposes, other tasks may not be considered in learning. Considering the above, an operating method that considers multi-tasks may be required in semantic communication, and a method for this is described below.

[0141] Below, we describe methods and procedures for operating in a system capable of semantic communication while considering the multi-task behavior of a destination. For example, the following operations may be semantic level operations, Level B of FIG. 14, and may be performed in cases where two-way communication is performed. However, for convenience of explanation, the following description assumes one-way communication, but is not limited thereto and can be equally applied to two-way communication.

[0142] FIG. 18 is a diagram illustrating a method for performing multi-task-based semantic communication applicable to the present disclosure. Referring to FIG. 18, a source (1810) and a destination (1820) may possess a labeled dataset necessary for learning an AI task. For example, the source (1810) may be an entity transmitting data, such as a terminal, a base station, or other device. Furthermore, the destination (1820) may be an entity receiving data and performing an AI task appropriate for the purpose, such as a terminal, a base station, or other device. In other words, the source (1810) and the destination (1820) may each be entities performing communication, and may not be limited to a specific type of device. For convenience of explanation, the following description will be based on the source (1810) and the destination (1820).

[0143] For example, the source (1810) and the destination (1820) may have a labeled data set required for learning an AI task, and the destination (1820) may perform multiple AI tasks (1831, 1832, 1833, 1834). Here, each of the AI ​​tasks (1831, 1832, 1833, 1834) may operate according to a different purpose. For example, as described above, the data transmitted and reconstructed from the source may be transmitted as input to each of the AI ​​tasks (1831, 1832, 1833, 1834), and each of the AI ​​tasks (1831, 1832, 1833, 1834) may operate according to a different purpose based on the input. For example, AI task 1 (1811) of FIG. 18 is intended for classification, and other AI tasks may perform operations for different purposes, such as semantic segmentation or object detection, rather than performing other classifications. In other words, the destination (1820) may perform multi-task operations, and each task may be performed with a different purpose.

[0144] As a specific example, a source (1810) can encode data X given as input through a JSCC encoder (1811) and transmit the derived latent vector to a destination (1820) through a wireless channel. Here, the latent vector can represent a semantic expression. As an example, the following description is based on a semantic expression for convenience of explanation. However, it is not limited to a specific term, and may be referred to as a latent vector or other name, and is not limited to a specific embodiment.

[0145] For example, data x in Fig. 18 may be an image, but this is just one example for the convenience of explanation and may not be limited thereto. As another example, a semantic expression derived from data x may be transmitted to a destination (1820) via a wireless channel through a quantizer (1812), but may not be limited thereto. The destination (1820) decodes the received semantic expression through a JSCC decoder (1821) and reconstructs the data. (reconstruction data ) can be obtained. After that, the destination (1820) is Each AI task (1831, 1832, 1833, 1834) can be used as input to perform an operation suitable for the purpose of each downstream task and then check the output. Here, the JSCC encoder (1811), the JSCC decoder (1821), and the AI ​​tasks (1831, 1832, 1833, 1834) constituting the source (1810) and the destination (1820) can each configure a neural network model based on the data modality. For example, the neural network may be a deep neural network (DNN) model, but may not be limited thereto. Here, when the destination (1820) has N AI tasks, the combination of operations of the AI ​​tasks in the destination (1820) is -1 can exist. That is, all combinations can be considered, from the case where only one AI task operates to the case where all AI tasks operate simultaneously, based on whether each AI task operates. Therefore, the JSCC encoder (1811) and the JSCC decoder (1821) each have a source and a destination. -1 can be held. Here, as N increases, the number of possible combinations increases exponentially, and the number of held models can also increase. However, the size of each model can be reduced through a model lightweighting method. For example, the size of each model can be reduced by applying at least one of the model lightweighting methods, quantization, pruning, and distillation, to each model during the learning process. However, the above-described method is only one example and may not be limited thereto. The source (1810) and the destination (1820) can hold multiple models by applying the above-described model lightweighting to each DNN model.

[0146] As described above, neural network models for the JSCC encoder (1810) and the JSCC decoder (1820) can be provided in response to possible AI task combinations. Here, learning can first be performed on the DNN models corresponding to the JSCC encoder (1810) and the JSCC decoder (1820) and the DNN models of the AI ​​tasks (1831, 1832, 1833, 1834) possessed by the destination (1820). That is, learning for the DNN models corresponding to the JSCC encoder (1810) and the JSCC decoder (1820) and learning for the AI ​​task can be performed respectively.

[0147] Thereafter, simultaneous learning can be performed based on a joint method for the DNN models of the JSCC encoder (1810), the JSCC decoder (1820), and the AI ​​tasks (1831, 1832, 1833, 1834). Here, the loss function for the learning can be as shown in Equation 7 below, and Equation 7 can consider task-relevant distortion for all tasks held by the destination.

[0148] As a concrete example, in Equation 7, R is a rate given as Equation 2, and k is a combination of AI tasks that can operate at the destination. - It can represent the kth combination out of 1. Also, can be the loss function of the kth combination, can be a hyperparameter to control the distortion required in the kth combination in relation to the rate-distortion tradeoff. Also, is the input data X and the reconstructed data Reconstruction distortion between the two can be represented. For example, reconstruction distortion can be applied to various methods used for data reconstruction and may not be limited to a specific form. For example, MSE reconstruction distortion related to pixel-level error, as in Equation 5 described above, may be used, but may not be limited thereto. In addition, N may be the number of AI tasks supported by the destination (1820).

[0149] [Equation 7]

[0150]

[0151] For example, in Equation 7, R, And the parameters corresponding to N can be set through the configuration of the source (1810) and the destination (1820). Here, can be the true label held by the ith AI task. For example, the mutual information and reconstruction data corresponding to the input data X and Y. Learning can be performed in a way that adjusts the distortion by comparing. Here, can be a hyperparameter for the ith AI task in the kth combination. For example, if the ith AI task is not included in the kth combination, can be set to 0. That is, can be made to reflect the AI ​​task used in the kth combination.

[0152] Based on the above, inference can be performed through the constructed model after learning is performed. FIG. 19 is a diagram illustrating a method of performing an inference operation in semantic communication based on a multi-task applicable to the present disclosure. Referring to FIG. 19, an inference operation can be performed after learning related to multi-task support is performed in semantic communication. For example, the destination (1920) can determine a target AI task and transmit instruction information therefor to the source (1910). That is, the destination (1920) can select an AI task that can obtain a desired purpose as an output from among N AI tasks, and the possible combinations according to each AI task are as described above. It could be.

[0153] As a specific example, in FIG. 19, the input data is an image, and a setting may be performed to obtain the results of semantic segmentation and object detection. Here, an AI task for performing the corresponding operation may be selected. After selecting the AI ​​task, the destination (1920) may transmit the selected AI task information to the source (1910). For example, the destination (1920) may transmit index information corresponding to a selected AI task combination among N AI tasks to the source (1810). For example, in mathematical expression 7, k may correspond to an index. Here, Table 2 below may be an index table according to the target AI combination between the source (1910) and the destination (1920) when N = 3. The destination (1920) may transmit an index based on Table 2 below to the source (1910). The source (1910) may recognize at least one AI task corresponding to the index and determine what operation the destination (1920) performs. However, this is just one example, and it is possible that N is set differently.

[0154] [Table 2]

[0155]

[0156] After that, the source (1910) and the destination (1920) can set the JSCC encoder (1911) and the JSCC decoder (1921). Specifically, the source (1910) and the destination (1920) can set the JSCC encoder (1911) and the JSCC decoder (1921) based on the AI ​​task related information. -The corresponding JSCC encoder (1911) and JSCC decoder (1921) models can be selected from one combination. Thereafter, the source (1910) can encode the input data through the JSCC encoder (1911) to generate a semantic representation and transmit it to the destination (1920). The destination (1920) can obtain reconstructed data by decoding the received semantic representation through the JSCC decoder (1921). Here, the reconstructed data can be transmitted to a set AI task and can perform a task-based operation. As a specific example, in FIG. 19, semantic segmentation and object detection can be performed as an AI task, and accordingly, an output such as that in FIG. 20 can be obtained.

[0157] FIG. 21 is a diagram illustrating an initial setup method for semantic communication applicable to the present disclosure. Referring to FIG. 21, a terminal (2110) may obtain a synchronization signal from a base station (2120) and perform synchronization to establish a connection. For example, the source described above in FIG. 21 may be the terminal (2110) and the destination may be the base station (2120). However, this is merely an example for convenience of explanation, and the same may apply even when the source is the base station (2120) and the destination is the terminal (2110). Furthermore, the same may be applied to two-way communication and is not limited to a specific form.

[0158] Thereafter, the base station (2120) may request terminal capability information from the terminal (2110). Here, the terminal capability information may include various information based on the terminal type. For example, the terminal capability information may include information on whether the terminal has the above-described semantic communication performance capability. That is, the terminal capability information may include semantic communication capability information of the terminal. The terminal (2110) may transmit the terminal capability information to the base station (2120) based on the request from the base station (2120). Here, as an example, the terminal capability information may further include information on the types of raw data that the terminal can generate, collect, or process, the computational capabilities of the device, and may not be limited to a specific form. Thereafter, the base station (2120) may determine whether to perform semantic communication. For example, the base station (2120) may recognize that the terminal (2110) has the capability to perform semantic communication based on the terminal capability information. In addition, the base station (2120) can further consider other acquired information and other parameters to decide whether to perform semantic communication and instruct the terminal whether to perform semantic communication. That is, when the base station (2120) decides to perform communication with the terminal (2110) based on semantic communication, the base station (2120) can transmit information indicating semantic communication to the terminal (2110). Here, the information indicating semantic communication can include semantic communication-related information. Thereafter, the terminal (2110) can store the semantic communication-related information transmitted together with the semantic communication-instruction information. For example, the semantic communication-related information may include the number of AI tasks supported (N), an index table according to the AI ​​task combination, a rate (R), a JSCC encoder / decoder model, whether to use a quantizer, a mini-batch size, a loss function, and a reconstruction distortion ( ) may include at least one of the information. That is, the semantic communication-related information may include information that must be configured to perform learning in consideration of the multi-task described above, and may not be limited to a specific form.

[0159] Additionally, as an example, semantic communication instruction information and semantic communication-related information may be transmitted from the base station (2120) to the terminal (2110) through at least one of a DCI (downlink control information), a MAC (medium access control) CE (control element), and an RRC (radio resource control) message.

[0160] As another example, it may be possible for semantic communication instruction information to be indicated through upper layer signaling, and for semantic communication-related information to be conveyed through DCI.

[0161] That is, the base station (2120) can obtain terminal capability information from the terminal (2110) and, if the above-described semantic communication is possible, transmit semantic communication-related information to the terminal (2110). The terminal (2110) can store the received information and perform the above-described semantic communication.

[0162] FIG. 22 is a diagram showing information transmitted when learning for semantic communication based on multi-task applicable to the present disclosure is performed.

[0163] For example, in Fig. 22, the source may be a terminal (2210) and the destination may be a base station (2220). However, this is only an example for convenience of explanation, and the same may apply when the source is a base station (2220) and the destination is a terminal (2210). In addition, the same may be applied when performing two-way communication, and is not limited to a specific form. Referring to Fig. 22, learning is performed by considering a combination of AI multi-tasks. -1 can be performed. Here, information can be transmitted in each mini-batch when learning is performed. For example, information for forward-pass transmitted from source (2210) to destination (2220) can include the result of JSCC encoder execution. In addition, when including quantizer as described above, execution result information considering the corresponding operation can be included in the information for forward-pass and transmitted to destination (2220). After that, destination (2220) can also transmit information for backward-pass to source (2210). For example, information for backward-pass can include gradient information used for learning. As described above, when learning is performed in source (2210) and destination (2220), each information can be transmitted, and the operation can be performed for each mini-batch by considering the combination of AI multi-tasks. -Can be performed 1 time.

[0164] Figure 23 is a diagram illustrating inference performance of multi-task-based semantic communication applicable to the present disclosure.

[0165] For example, in FIG. 23, the source may be a terminal (2310) and the destination may be a base station (2320). However, this is only an example for the convenience of explanation, and the same may apply even when the source is a base station (2320) and the destination is a terminal (2310). In addition, the same may be applied when performing two-way communication, and is not limited to a specific form. Referring to FIG. 23, the destination (2320) may select a target AI task. The destination (2320) may select a target AI task that suits its purpose by considering the output operation. Thereafter, the destination (2320) may transmit the selected target AI task information to the source (2310). Here, the possible combinations of AI tasks are -1 may be possible, and index information corresponding to a possible combination may be transmitted from the destination (2320) to the source (2310). For example, the index information corresponding to the combination may be as shown in Table 2 described above, but may not be limited thereto.

[0166] Thereafter, the source (2310) and the destination (2320) can each set a JSCC encoder model and a JSCC decoder model corresponding to the index. When input data is given, the source (2310) can encode the input data through the JSCC encoder to generate a semantic representation. For example, when a quantizer is applied as described above, a quantization operation may be performed to generate a semantic representation, but the present invention is not limited thereto. Thereafter, the source (2310) can transmit the semantic representation to the destination (2320). The destination (2320) can decode the semantic representation received through the JSCC decoder and provide the reconstructed data obtained through the decoding as an input to each of the set AI tasks. Thereafter, each of the set AI tasks can be performed to derive an output operation. As described above, learning and inference can be performed when multi-tasks are performed at the destination in a system capable of performing semantic communication.

[0167] That is, learning can be performed on each model by setting up an index table based on a loss function and AI task combination that considers multi-task behavior. Once learning is complete, instruction information based on the target AI task behavior set at the destination is transmitted, and corresponding inference operations can be performed at the source and destination. This allows the destination to obtain the intended output based on each AI task behavior.

[0168] Although the above-described FIGS. 21 to 23 have been described based on the case where the source is a terminal and the destination is a base station, the present invention may not be limited thereto, as described above. For example, the operations of FIGS. 21 to 23 may be performed in consideration of the characteristics of the source and the destination. As a specific example, when the source is a terminal and the destination is a base station as described above, the terminal may obtain control information through RRC signaling or DCI, but when both the source and the destination are terminals, the control information may be obtained through PC5-RRC signaling or SCI (sidelink control information). That is, the source and destination operations are performed as described above, but it may also be possible to perform signaling or operations that are combined and performed according to the characteristics of the source and destination, and the present invention may not be limited to a specific embodiment.

[0169] Figure 24 is a flowchart showing a first node operation method applicable to the present disclosure.

[0170] Referring to FIG. 24, a first node may establish a connection with a second node (S2410). Here, the first node may be a source and the second node may be a destination. As another example, the first node may be a destination and the second node may be a source, and the present invention is not limited to a specific embodiment. After the first node establishes a connection with the second node, the first node may receive a request for first node capability information from the second node (S2420). The first node may transmit the first node capability information to the second node based on the first node capability information request. (S2430) The first node capability information may include information indicating whether the first node supports multi-AI task-based semantic communication. In addition, as an example, the first node capability information may further include at least one of information generated by the first node, information collected by the first node, information on the type of raw data that can be processed, and device computation capability information.

[0171] Here, the first node may refer to the source described above, and the second node may refer to the destination. For example, the first node may be a terminal, and the second node may be a base station. As another example, the first node may be a base station, and the second node may be a terminal. As another example, both the first node and the second node may be terminals, and may refer to each terminal in terminal-to-terminal communication. As another example, the first node may refer to a subject or function that can operate as the source and destination described above, and the second node may not be limited to a specific form.

[0172] After that, the second node can determine whether to perform semantic communication by considering the received first node capability information, and transmit semantic communication instruction information to the first node. (S2440) In addition, the second node can transmit semantic communication-related information to the first node together with the semantic communication instruction information. Here, the semantic communication-related information includes rate (R) information, the number of AI tasks supported (N), an index table according to the combination of AI tasks, JSCC encoder and JSCC decoder model information, information on whether to use a quantizer, mini-batch size information, loss function information, and reconstruction distortion ( ) may include at least one of the information. After that, the first node may perform learning for semantic communication based on the received information to perform learning for at least one model. (S2450) Here, the number of AI task combinations may be determined based on the number of AI tasks supported (N). The number of JSCC encoder and JSCC decoder models may correspond to the number of AI task combinations. In addition, a model for each AI task may be set. Here, when learning is performed based on semantic communication, learning for the JSCC encoder and JSCC decoder models corresponding to the number of AI task combinations may be performed. In addition, learning for each model of each AI task supported individually may be performed. Thereafter, the JSCC encoder and JSCC decoder models and the models for each AI task may be learned together based on a joint method, which may be as shown in Mathematical Expression 7 described above.

[0173] Based on the above, learning for each model based on the multi-AI task can be completed. Thereafter, inference can be performed based on the learned model. Here, the second node can determine a target AI task that matches the output purpose among the multi-AI tasks and transmit the corresponding information to the first node. (S2460) The first node can encode input data through a corresponding JSCC encoder model based on the received target AI task information. Here, as an example, the target AI task information can be set based on an index table corresponding to the number of AI task combinations. As a specific example, when the target AI task information indicates a first index based on the index table, the first node can select a first JSCC encoder model corresponding to the first index, set the JSCC encoder model, encode the input data, and transmit the encoded input data to the second node. For example, the first node can generate a semantic representation through JSCC encoding for input data based on the configured JSCC encoder model and transmit the generated semantic representation to the second node, as described above (S2470). Thereafter, the second node can select the first JSCC decoder model corresponding to the first index to set the JSCC decoder model. The second node can decode the received semantic representation through the configured JSCC decoder model to obtain reconstructed data. The reconstructed data can be provided as an input for each of the configured target AI tasks, and an output can be derived based on the purpose of each of the configured target AI tasks.

[0174] Fig. 25 is a flowchart illustrating a second node operation method applicable to the present disclosure. Referring to Fig. 25, a second node may establish a connection with a first node (S2510). Here, the first node may be a source and the second node may be a destination. As another example, the first node may be a destination and the second node may be a source, and the present invention is not limited to a specific embodiment. After the first node establishes a connection with the second node, the second node may transmit a first node capability information request to the first node (S2520). The first node may transmit the first node capability information to the second node based on the first node capability information request, and the second node may receive the information (S2530). The first node capability information may include information indicating whether the first node supports multi-AI task-based semantic communication. Additionally, as an example, the first node capability information may further include at least one of information generated by the first node, information collected by the first node, information on the type of raw data that can be processed, and device computation capability information.

[0175] Here, the first node may refer to the source described above, and the second node may refer to the destination. For example, the first node may be a terminal, and the second node may be a base station. As another example, the first node may be a base station, and the second node may be a terminal. As another example, both the first node and the second node may be terminals, and may refer to each terminal in terminal-to-terminal communication. As another example, the first node may refer to a subject or function that can operate as the source and destination described above, and the second node may not be limited to a specific form.

[0176] After that, the second node can determine whether to perform semantic communication by considering the received first node capability information, and transmit semantic communication instruction information to the first node. (S2540) In addition, the second node can transmit semantic communication-related information to the first node together with the semantic communication instruction information. Here, the semantic communication-related information includes rate (R) information, the number of AI tasks supported (N), an index table according to the combination of AI tasks, JSCC encoder and JSCC decoder model information, information on whether to use a quantizer, mini-batch size information, loss function information, and reconstruction distortion ( ) may include at least one of the information. After that, the second node may perform learning for semantic communication based on the information transmitted to the first node to perform learning for at least one model. (S2550) Here, the number of AI task combinations may be determined based on the number of AI tasks supported (N). The number of JSCC encoder and JSCC decoder models may correspond to the number of AI task combinations. In addition, a model for each AI task may be set. Here, when learning is performed based on semantic communication, learning for the JSCC encoder and JSCC decoder models corresponding to the number of AI task combinations may be performed. In addition, learning for each model of each AI task supported individually may be performed. Thereafter, the JSCC encoder and JSCC decoder models and the models for each AI task may be learned together based on a joint method, which may be as shown in Mathematical Expression 7 described above.

[0177] Based on the above, learning for each model based on the multi-AI task can be completed. Thereafter, inference can be performed based on the learned model. Here, the second node can determine a target AI task that matches the output purpose among the multi-AI tasks and transmit the corresponding information to the first node. (S2560) The first node can encode input data through a corresponding JSCC encoder model based on the received target AI task information. Here, as an example, the target AI task information can be set based on an index table corresponding to the number of AI task combinations. As a specific example, when the target AI task information indicates a first index based on the index table, the first node can select a first JSCC encoder model corresponding to the first index, set the JSCC encoder model, encode the input data, and transmit the encoded input data to the second node. As an example, the first node can generate a semantic representation through JSCC encoding for the input data based on the set JSCC encoder model and transmit the generated semantic representation to the second node, as described above. Thereafter, the second node can select the first JSCC decoder model corresponding to the first index and set the JSCC decoder model. The second node can obtain reconstructed data by decoding the received semantic expression through the set JSCC decoder model. (S2570) The second node can provide the reconstructed data as input for each set target AI task and derive an output based on the purpose of each set target AI task, as described above. (S2580)

[0178] It is clear that the examples of the proposed methods described above can also be considered as a type of proposed methods, as they can be included as one of the implementation methods of the present disclosure. Furthermore, the proposed methods described above can be implemented independently, but they can also be implemented in the form of a combination (or merge) of some of the proposed methods. Information regarding the applicability of the proposed methods (or information regarding the rules of the proposed methods) can be defined by a rule such that the base station notifies the terminal of the application of the proposed methods through a predefined signal (e.g., a physical layer signal or a higher layer signal).

[0179] The present disclosure may be embodied in other specific forms without departing from the technical ideas and essential features described herein. Therefore, the above detailed description should not be construed as limiting in all respects but rather as illustrative. The scope of the present disclosure should be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present disclosure are intended to be included within the scope of the present disclosure. Furthermore, claims that do not explicitly cite each other in the claims may be combined to form embodiments or incorporated into new claims through post-filing amendments.

[0180] Embodiments of the present disclosure can be applied to various wireless access systems. Examples of various wireless access systems include the 3rd Generation Partnership Project (3GPP) or 3GPP2 systems.

[0181] The embodiments of the present disclosure can be applied not only to the various wireless access systems described above, but also to all technical fields that utilize these various wireless access systems. Furthermore, the proposed method can also be applied to mmWave and THz communication systems utilizing ultra-high frequency bands.

[0182] Additionally, embodiments of the present disclosure can be applied to various applications such as autonomous vehicles and drones.

Claims

1. In a method for operating a first node in a wireless communication system, Step of establishing a connection with a second node; A step of receiving a request for first node capability information from the second node; A step of transmitting first node capability information to the second node based on the first node capability information request; A step of receiving semantic communication instruction information from the second node; A step of performing semantic communication learning based on the received semantic communication instruction information to perform learning for at least one model; A step of receiving target AI (artificial intelligence) task information from the second node; and A step of encoding input data based on a JSCC (joint source channel coding) encoder model corresponding to the target AI task information and transmitting the encoded input data to the second node, A first node operation method, wherein the second node has a multi-AI task based on the semantic communication, and provides reconstructed data generated based on a JSCC decoder model corresponding to the target AI task information as an input to a target AI task set among the multi-AI tasks to derive an output.

2. In paragraph 1, The above first node capability information includes information indicating whether the first node supports multi-AI task-based semantic communication, A first node operation method, wherein the first node capability information further includes at least one of first node creation information, first node collection information, processable raw data type information, and device operation capability information.

3. In paragraph 2, When the second node decides to perform multi-AI task-based semantic communication based on the first node capability information, the semantic communication instruction information is transmitted to the first node. A first node operation method, wherein semantic communication related information is transmitted to the first node together with the above semantic communication instruction information.

4. In paragraph 3, A first node operation method, wherein the above semantic communication-related information includes at least one of rate (R) information, the number of AI tasks supported (N), an index table according to AI task combination, JSCC (joint source channel coding) encoder and JSCC decoder model information, information on whether a quantizer is used, mini-batch size information, loss function information, and reconstruction distortion (D_R) information.

5. In paragraph 4, The number of AI task combinations is determined based on the number of AI tasks (N) supported above, and the JSCC encoder and JSCC decoder models corresponding to the number of AI task combinations and the models of each of the supported AI tasks are set. A first node operation method, wherein when performing the above semantic communication learning, learning for the JSCC encoder and JSCC decoder models corresponding to the number of AI task combinations and learning for each model of the supported AI task are performed individually, and then the JSCC encoder and JSCC decoder models and the models of each of the supported AI tasks are learned together based on a joint method.

6. In paragraph 1, The above target AI task information is set based on an index table corresponding to the number of AI task combinations, If the target AI task information indicates a first index based on the index table, the first node selects a first JSCC encoder model corresponding to the first index and sets the JSCC encoder model, A first node operation method for generating a semantic representation through JSCC encoding of the input data based on the above-described JSCC encoder model and transmitting the generated semantic representation to the second node.

7. In paragraph 6, The second node sets the JSCC decoder model by selecting the first JSCC decoder model corresponding to the first index, A first node operation method for obtaining the reconstructed data by decoding the above-described semantic expression through the above-described set JSCC decoder model.

8. In paragraph 7, A first node operation method, wherein the above-described reconstruction data is provided as an input for each of the set target AI tasks, and the output is derived based on the purpose of each of the set target AI tasks.

9. In a first node in a wireless communication system, Transmitter and receiver; and A processor connected to the above transmitter and receiver is included, The above processor, Establish a connection with the second node, Control the transceiver to receive a first node capability information request from the second node, Control the transceiver to transmit the first node capability information to the second node based on the first node capability information request, Control the transceiver to receive semantic communication instruction information from the second node, Perform semantic communication learning based on the received semantic communication instruction information to learn at least one model, Control the transceiver to receive target AI task information from the second node, Control the transceiver to encode input data based on the JSCC encoder model corresponding to the target AI task information and transmit the encoded data to the second node. The second node is a first node that provides reconstructed data generated based on a JSCC decoder model corresponding to the target AI task information as an input to a target AI task set among the multi-AI tasks based on the semantic communication and derives an output.

10. In a second node operation method in a wireless communication system, Step of establishing a connection with the first node; A step of transmitting a request for first node capability information to the first node; A step of receiving first node capability information from the first node based on the first node capability information request; A step of transmitting semantic communication instruction information to the first node; A step of performing learning for at least one model by performing semantic communication learning; A step of transmitting target AI task information to the first node; A step of generating reconstructed data by receiving encoded input data based on a JSCC encoder model corresponding to the target AI task information; and Including a step of providing the above reconstruction data as input to a target AI task set among the above multi-AI tasks to derive an output, A second node operating method, wherein the second node has multi-AI tasks based on the semantic communication.

11. In paragraph 10, The above first node capability information includes information indicating whether the first node supports multi-AI task-based semantic communication, A second node operating method, wherein the first node capability information further includes at least one of first node creation information, first node collection information, processable raw data type information, and device operation capability information.

12. In paragraph 11, When the second node decides to perform multi-AI task-based semantic communication based on the first node capability information, the semantic communication instruction information is transmitted to the first node. A second node operating method, wherein semantic communication related information is transmitted to the first node together with the above semantic communication instruction information.

13. In paragraph 12, A second node operating method, wherein the above semantic communication-related information includes at least one of rate (R) information, the number of AI tasks supported (N), an index table according to AI task combination, JSCC (joint source channel coding) encoder and JSCC decoder model information, information on whether a quantizer is used, mini-batch size information, loss function information, and reconstruction distortion (D_R) information.

14. In paragraph 13, The number of AI task combinations is determined based on the number of AI tasks (N) supported above, and the JSCC encoder and JSCC decoder models corresponding to the number of AI task combinations and the models of each of the supported AI tasks are set. A second node operation method, wherein when performing the above semantic communication learning, learning for the JSCC encoder and JSCC decoder models corresponding to the number of AI task combinations and learning for each model of the supported AI task are performed individually, and then the JSCC encoder and JSCC decoder models and the models of each of the supported AI tasks are learned together based on a joint method.

15. In paragraph 10, The above target AI task information is set based on an index table corresponding to the number of AI task combinations, If the target AI task information indicates a first index based on the index table, the first node selects a first JSCC encoder model corresponding to the first index and sets the JSCC encoder model, A second node operation method for generating a semantic representation through JSCC encoding of the input data based on the above-described JSCC encoder model and transmitting the generated semantic representation to the second node.

16. In paragraph 15, The second node sets the JSCC decoder model by selecting the first JSCC decoder model corresponding to the first index, A second node operation method for obtaining the reconstructed data by decoding the above-described semantic expression through the above-described set JSCC decoder model.

17. In paragraph 16, A second node operation method, wherein the above-mentioned reconstruction data is provided as an input for each of the set target AI tasks, and the output is derived based on the purpose of each of the set target AI tasks.

18. In a second node in a wireless communication system, Transmitter and receiver; and A processor connected to the above transmitter and receiver is included, The above processor, Establish a connection with the first node, Control the transceiver to transmit a first node capability information request to the first node, Control the transceiver to receive first node capability information from the first node based on the first node capability information request, Controlling the transceiver to transmit semantic communication instruction information to the first node; Perform semantic communication learning to train at least one model, Control the transmitter / receiver to transmit target AI task information to the first node; Controlling the transmitter / receiver to receive encoded input data based on a JSCC encoder model corresponding to the target AI task information, and The above reconstruction data is provided as input to the target AI task set among the above multi-AI tasks to derive an output. The second node is a second node having multi-AI tasks based on the semantic communication.

19. A device comprising at least one memory and at least one processor functionally connected to the at least one memory, At least one processor of the device, Controls the establishment of connections with other devices, Controlling the device to receive a device capability information request from the other device; Controlling the device to transmit device capability information to the other device based on the device capability information request; Controlling the device to receive semantic communication instruction information from the other device; Controlling the device to perform learning for at least one model by performing semantic communication learning based on the received semantic communication instruction information; Controlling the device to receive target AI task information from the other device; Controlling the device to encode input data based on a JSCC encoder model corresponding to the target AI task information and transmit the encoded data to the other device; The other device is a device having a multi-AI task based on the semantic communication, and providing the reconstructed data generated based on the JSCC decoder model corresponding to the target AI task information as an input to a target AI task set among the multi-AI tasks to derive an output.

20. In a non-transitory computer-readable medium storing at least one instruction, comprising at least one instruction executable by the processor, At least one of the above commands causes the device to: Controls the establishment of connections with other devices, Controlling the device to receive a device capability information request from the other device; Controlling the device to transmit device capability information to the other device based on the device capability information request; Controlling the device to receive semantic communication instruction information from the other device; Controlling the device to perform learning for at least one model by performing semantic communication learning based on the received semantic communication instruction information; Controlling the device to receive target AI task information from the other device; Controlling the device to encode input data based on a JSCC encoder model corresponding to the target AI task information and transmit the encoded data to the other device; A computer-readable medium in which the other device has a multi-AI task based on the semantic communication, and provides reconstruction data generated based on a JSCC decoder model corresponding to the target AI task information as an input to a target AI task set among the multi-AI tasks to derive an output.

Images