Method for semantic communication in wireless communication system, and apparatus therefor

Abstract

A method performed by a first wireless device, according to one embodiment of the present specification, comprises the steps of: determining a first node related to error checking and correction of semantic information; transmitting first information to a second wireless device; and receiving second information including ACK or NACK related to reception of the semantic information from the second wireless device. The first information includes the semantic information and the first node. Whether an error occurs is determined on the basis of whether second nodes based on semantic information received by the second wireless device are descendant nodes of the first node received by the second wireless device.

Description

Method and device for semantic communication in a wireless communication system

[0001] The present invention relates to a method and a device for semantic communication in a wireless communication system.

[0002] Mobile communication systems were developed to provide voice services while ensuring user activity. However, they have expanded beyond voice to include data services. Currently, explosive growth in traffic is leading to resource shortages and users are demanding faster services, necessitating a more advanced mobile communication system.

[0003] Next-generation mobile communication systems must support explosive data traffic growth, dramatically increasing data rates per user, a vastly increased number of connected devices, ultra-low end-to-end latency, and high energy efficiency. To achieve these goals, various technologies are being studied, including dual connectivity, massive multiple input multiple output (MIMO), in-band full duplex, non-orthogonal multiple access (NOMA), super wideband support, and device networking.

[0004] Meanwhile, the following technical considerations are essential in semantic communication systems. To ensure the reliability of communication between a source and a destination, a semantic error correction technique is essential. Semantic error correction refers to correcting semantic errors in signals received by the destination. The limitations of semantic communication based on existing semantic error correction techniques are as follows.

[0005] Existing semantic error correction techniques struggle to accurately assess the severity of semantic errors. Furthermore, they face limitations: the system must operate under the assumption that discovered / detected semantic errors are completely corrected.

[0006] The purpose of this specification is to propose a method to overcome the limitations of semantic error correction-based communication described above.

[0007] The technical problems to be achieved in this specification are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which this specification pertains from the description below.

[0008] A method performed by a first wireless device in a wireless communication system according to one embodiment of the present disclosure comprises the steps of determining a first node related to error checking and correction of semantic information, transmitting first information to a second wireless device, and receiving second information including an ACK or NACK related to reception of the semantic information from the second wireless device.

[0009] The first information includes the semantic information and the first node. The first node is determined as the ancestor node with the highest level among the ancestor nodes that have second nodes based on the semantic information as descendant nodes in the semantic tree.

[0010] Based on whether an error has occurred in the semantic information received by the second wireless device and / or whether an error has been corrected, the second information includes the ACK or the NACK.

[0011] Whether the above error occurs is determined based on whether the second nodes based on the semantic information received by the second wireless device are descendant nodes of the first node received by the second wireless device.

[0012] It is characterized in that a corrected first node and a corrected second node are determined based on the determination that the above error has occurred.

[0013] Based on the second nodes received by the second wireless device being the descendent nodes, it can be determined that the error did not occur.

[0014] It may be determined that the error has occurred based on at least one of the second nodes received by the second wireless device being not the descendent node.

[0015] A corrected first node can be determined based on which of the above errors is determined to have occurred.

[0016] A corrected second node can be determined based on the corrected first node.

[0017] The above corrected first node may be one of the first candidate nodes having the same level as the first node in the semantic tree.

[0018] Among the first candidate nodes, the first candidate node that has the largest number of second nodes as descendant nodes can be determined as the corrected first node.

[0019] Second candidate nodes can be determined based on the above-mentioned corrected first node.

[0020] i) the remaining second nodes excluding at least one second node among the second nodes and ii) the ancestor node with the highest level among the ancestor nodes having the specific nodes as descendant nodes is the corrected first node: the specific nodes can be determined as the second candidate nodes.

[0021] Among the second candidate nodes, the second candidate node with the highest similarity can be determined as the corrected second node.

[0022] The above similarity may include a similarity calculated based on each of the at least one second node and the second candidate nodes.

[0023] Each similarity may represent the similarity between the first node and each second candidate node in the semantic tree.

[0024] The above similarity may include a similarity calculated for each of the first sub-trees. Each similarity may represent a similarity between each of the first sub-trees and the second sub-tree.

[0025] Each first sub-tree may include i) the corrected first node, ii) one of the second candidate nodes, and iii) the remaining second nodes.

[0026] The second sub-tree may include i) the first node and ii) the second nodes.

[0027] Based on the determination that the above error did not occur, the second information may include the ACK.

[0028] i) based on the determination that the error has occurred, and ii) based on the correction of the error: the second information may include the ACK.

[0029] i) based on the determination that the above error has occurred and ii) based on the fact that the above error cannot be corrected: the second information may include the NACK.

[0030] Information about the above semantic tree can be shared in advance between the first wireless device and the second wireless device.

[0031] The level of a specific node in the above semantic tree may be related to the distance from the specific node to the root of the semantic tree.

[0032] The above first information may further include a level for each of the second nodes.

[0033] A first wireless device operating in a wireless communication system according to another embodiment of the present disclosure includes one or more transceivers, one or more processors, and one or more memories connected to the one or more processors and storing instructions.

[0034] The instructions are characterized in that, based on being executed by the one or more processors, the one or more processors are set to perform all steps of any one of the methods.

[0035] A device according to another embodiment of the present disclosure comprises one or more memories and one or more processors functionally connected to the one or more memories.

[0036] Said one or more memories are characterized in that they store instructions that cause said one or more processors to perform all steps of any one of said methods based on what is executed by said one or more processors.

[0037] In another embodiment of the present disclosure, one or more non-transitory computer-readable media store instructions, the instructions being executable by one or more processors, characterized in that they cause the one or more processors to perform all steps of any one of the methods.

[0038] In another embodiment of the present disclosure, a method performed by a second wireless device in a wireless communication system comprises the steps of receiving first information from a first wireless device, determining whether an error has occurred in the semantic information based on a first node, and transmitting second information including an ACK or NACK related to reception of the semantic information to the first wireless device.

[0039] The first information includes semantic information and a first node related to error checking of the semantic information.

[0040] The occurrence of the above error is characterized in that it is determined based on whether the second nodes based on the semantic information in the semantic tree are descendant nodes of the first node.

[0041] A second wireless device operating in a wireless communication system according to another embodiment of the present disclosure includes one or more transceivers, one or more processors, and one or more memories coupled to the one or more processors and storing instructions.

[0042] The instructions are characterized in that they are executed by the one or more processors, and the one or more processors are set to perform all steps of the method.

[0043] According to the embodiments of this specification, the detection accuracy of semantic errors and the accuracy of correcting semantic errors that occur can be improved. Therefore, semantic communication that is robust to semantic errors can be supported, thereby enhancing the reliability of semantic communication.

[0044] Furthermore, semantic error correction based on the embodiments of this specification is performed based on a semantic tree. This semantic tree-based semantic error correction technique can be applied to all data types capable of constructing a semantic tree. Therefore, the semantic error correction described above can be universally applied to various semantic communication systems.

[0045] The effects that can be obtained from this specification are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the technical field to which this specification belongs from the description below.

[0046] The accompanying drawings are intended to aid understanding of the present specification and may provide embodiments of the present specification along with detailed descriptions. However, the technical features of the present specification 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.

[0047] Figure 1 is a drawing showing an example of a communication system applicable to this specification.

[0048] Figure 2 is a drawing showing an example of a wireless device applicable to this specification.

[0049] FIG. 3 is a diagram illustrating a method for processing a transmission signal applicable to the present specification.

[0050] FIG. 4 is a drawing showing another example of a wireless device applicable to this specification.

[0051] FIG. 5 is a drawing showing an example of a mobile device applicable to this specification.

[0052] Figure 6 is a diagram showing physical channels applicable to this specification and a signal transmission method using them.

[0053] Figure 7 is a diagram showing an example of a perceptron structure.

[0054] Figure 8 is a diagram showing an example of a multilayer perceptron structure.

[0055] Figure 9 is a diagram showing an example of a deep neural network.

[0056] Figure 10 is a diagram showing an example of a convolutional neural network.

[0057] Figure 11 is a diagram showing an example of a filter operation in a convolutional neural network.

[0058] Figure 12 shows an example of a neural network structure in which a recurrent loop exists.

[0059] Figure 13 shows an example of the operating structure of a recurrent neural network.

[0060] Figure 14 is a diagram illustrating a level-based communication model to which the embodiment proposed in this specification can be applied.

[0061] Figure 15 is a diagram illustrating a semantic error.

[0062] Figure 16 illustrates a DNN-based semantic error check technique.

[0063] Figure 17 illustrates a semantic encoder and a semantic decoder.

[0064] Figure 18 illustrates a structure for DNN-based semantic error check.

[0065] Figure 19 illustrates a technique for correcting semantic errors.

[0066] Figure 20 illustrates the layer characteristics of a semantic tree.

[0067] Figure 21 illustrates a semantic tree of WordNet-based words.

[0068] Figure 22 shows a generalized example of a semantic tree.

[0069] Figure 23 illustrates SRC node creation and level information for semantic error correction according to an embodiment of the present specification.

[0070] Figure 24 illustrates a semantic tree in a Destination according to an embodiment of the present specification.

[0071] Figure 25 illustrates a correction to an SRC node according to an embodiment of the present specification.

[0072] Figure 26 illustrates a set of candidates for a semantic information node according to an embodiment of the present specification.

[0073] Figure 27 illustrates semantic similarity based on WordNet.

[0074] Fig. 28 illustrates a sub-graph for semantic similarity comparison according to an embodiment of the present specification.

[0075] FIG. 29 illustrates semantic error correction for a semantic information node according to an embodiment of the present specification.

[0076] Figure 30 is an example of a signaling procedure according to an embodiment of the present specification.

[0077] Figure 31 is another example of a signaling procedure according to an embodiment of the present specification.

[0078] Figure 32 is another example of a signaling procedure according to an embodiment of the present specification.

[0079] FIG. 33 is a flowchart illustrating a method performed by a first wireless device according to one embodiment of the present specification.

[0080] FIG. 34 is a flowchart illustrating a method performed by a second wireless device according to another embodiment of the present specification.

[0081] The following embodiments combine the components and features of this specification 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 this specification. The order of operations described in the embodiments of this specification 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.

[0082] In the description of the drawings, procedures or steps that may obscure the gist of the present specification are not described, and procedures or steps that can be understood by a person skilled in the art are also not described.

[0083] Throughout the specification, when a part is said to "comprising" (or including) a certain component, this does not mean that other components are excluded, but rather that other components can be included, unless specifically stated otherwise. 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 this specification (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.

[0084] The embodiments of this specification have been described with a 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.

[0085] 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.

[0086] Additionally, in the embodiments of the present specification, 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).

[0087] 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.

[0088] Embodiments of the present specification 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 5G (5th generation) NR (New Radio) system and 3GPP2 system, and in particular, embodiments of the present specification 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.

[0089] Furthermore, the embodiments of this specification may be applied to other wireless access systems and are not limited to the aforementioned systems. For example, they may also be applicable to systems implemented after the 3GPP 5G NR system, and are not limited to a specific system.

[0090] That is, obvious steps or parts not described in the embodiments of this specification may be explained by reference to the above documents. In addition, all terms disclosed in this specification may be explained by the above standard documents.

[0091] Hereinafter, preferred embodiments according to the present specification 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 specification and is not intended to represent the only embodiments in which the technical components of the present specification may be implemented.

[0092] Additionally, specific terms used in the embodiments of this specification are provided to aid in understanding of this specification, and the use of these specific terms may be changed to other forms without departing from the technical spirit of this specification.

[0093] 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).

[0094] In order to make the following description clear, the following description is based on a 3GPP communication system (e.g., LTE, NR, etc.), but the technical idea of ​​the present invention 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.

[0095] For background information, terms, abbreviations, etc. used in this specification, reference may be made to standard documents published prior to the invention of the present invention. For example, reference may be made to the 36.xxx and 38.xxx standard documents.

[0096] Communication systems applicable to this specification

[0097] Although not limited thereto, the various descriptions, functions, procedures, proposals, methods and / or operational flowcharts disclosed herein may be applied to various fields requiring wireless communication / connectivity (e.g., 5G) between devices.

[0098] 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.

[0099] FIG. 1 is a diagram illustrating an example of a communication system applicable to the present specification. Referring to FIG. 1, a communication system (100) applicable to the present specification includes a wireless device, a base station, and a network. Here, a wireless device refers to a device that performs communication using a wireless access technology (e.g., 5G NR, LTE) 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.

[0100] 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) network, etc. 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). In addition, IoT devices (100f) (e.g., sensors) can communicate directly with other IoT devices (e.g., sensors) or other wireless devices (100a to 100f).

[0101] 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 (e.g., 5G NR) such as uplink / downlink communication (150a), sidelink communication (150b) (or D2D communication), and communication between base stations (150c) (e.g., relay, IAB (integrated access backhaul)). Through 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, at least some of the various configuration information setting processes for transmitting / receiving wireless signals, various signal processing processes (e.g., channel encoding / decoding, modulation / demodulation, resource mapping / demapping, etc.), and resource allocation processes may be performed based on various proposals of this specification.

[0102] Communication systems applicable to this specification

[0103] FIG. 2 is a diagram illustrating an example of a wireless device applicable to this specification.

[0104] Referring to FIG. 2, the first wireless device (200a) and the second wireless device (200b) can transmit and receive wireless signals via various wireless access technologies (e.g., LTE, NR). Here, {the first wireless device (200a), the second wireless device (200b)} can correspond to {the wireless device (100x), the base station (120)} and / or {the wireless device (100x), the wireless device (100x)} of FIG. 1.

[0105] A first wireless device (200a) includes one or more processors (202a) and one or more memories (204a), and may further include one or more transceivers (206a) and / or one or more antennas (208a). The processor (202a) controls the memories (204a) and / or the transceivers (206a), and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed herein. For example, the processor (202a) may process information in the memory (204a) to generate first information / signals, and then transmit a wireless signal including the first information / signals via the transceivers (206a). In addition, the processor (202a) may receive a wireless signal including second information / signals via the transceivers (206a), and then store information obtained from signal processing of the second information / signals in the memory (204a). The memory (204a) may be connected to the processor (202a) and may store various information related to the operation of the processor (202a). For example, the memory (204a) may perform some or all of the processes controlled by the processor (202a), or may store software code including instructions for performing the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed herein. Here, the processor (202a) and the memory (204a) may be part of a communication modem / circuit / chip designed to implement wireless communication technology (e.g., LTE, NR). The transceiver (206a) may be connected to the processor (202a) and may transmit and / or receive wireless signals via one or more antennas (208a). The transceiver (206a) may include a transmitter and / or a receiver. The transceiver (206a) may be used interchangeably with an RF (radio frequency) unit. In this specification, wireless device may also mean a communication modem / circuit / chip.

[0106] The second wireless device (200b) includes one or more processors (202b), one or more memories (204b), and may further include one or more transceivers (206b) and / or one or more antennas (208b). The processor (202b) controls the memories (204b) and / or the transceivers (206b), and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed herein. For example, the processor (202b) may process information in the memory (204b) to generate third information / signals, and then transmit a wireless signal including the third information / signals via the transceivers (206b). In addition, the processor (202b) may receive a wireless signal including fourth information / signals via the transceivers (206b), and then store information obtained from signal processing of the fourth information / signals in the memory (204b). The memory (204b) may be connected to the processor (202b) and may store various information related to the operation of the processor (202b). For example, the memory (204b) may perform some or all of the processes controlled by the processor (202b), or may store software code including instructions for performing the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed herein. Here, the processor (202b) and the memory (204b) may be part of a communication modem / circuit / chip designed to implement wireless communication technology (e.g., LTE, NR). The transceiver (206b) may be connected to the processor (202b) and may transmit and / or receive wireless signals via one or more antennas (208b). The transceiver (206b) may include a transmitter and / or a receiver. The transceiver (206b) may be used interchangeably with an RF unit. In this specification, wireless device may also mean a communication modem / circuit / chip.

[0107] Hereinafter, hardware elements of the wireless device (200a, 200b) will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors (202a, 202b). For example, one or more processors (202a, 202b) may implement one or more layers (e.g., functional layers 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)). One or more processors (202a, 202b) may generate one or more Protocol Data Units (PDUs) and / or one or more Service Data Units (SDUs) according to the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed herein. One or more processors (202a, 202b) may generate messages, control information, data or information according to the descriptions, functions, procedures, proposals, methods and / or operational flowcharts disclosed herein. One or more processors (202a, 202b) may generate signals (e.g., baseband signals) including PDUs, SDUs, messages, control information, data or information according to the functions, procedures, proposals and / or methods disclosed herein and provide the signals to one or more transceivers (206a, 206b). One or more processors (202a, 202b) may receive signals (e.g., baseband signals) from one or more transceivers (206a, 206b) and obtain PDUs, SDUs, messages, control information, data or information according to the descriptions, functions, procedures, proposals, methods and / or operational flowcharts disclosed herein.

[0108] One or more processors (202a, 202b) may be referred to as a controller, a microcontroller, a microprocessor, or a microcomputer. One or more processors (202a, 202b) may be implemented by hardware, firmware, software, or a combination thereof. For example, one or more application specific integrated circuits (ASICs), one or more digital signal processors (DSPs), one or more digital signal processing devices (DSPDs), one or more programmable logic devices (PLDs), or one or more field programmable gate arrays (FPGAs) may be included in one or more processors (202a, 202b). The descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed herein may be implemented using firmware or software, and the firmware or software may be implemented to include modules, procedures, functions, etc. The descriptions, functions, procedures, suggestions, methods and / or operation flowcharts disclosed in this specification may be implemented using firmware or software configured to perform one or more processors (202a, 202b) or stored in one or more memories (204a, 204b) and executed by one or more processors (202a, 202b). The descriptions, functions, procedures, suggestions, methods and / or operation flowcharts disclosed in this specification may be implemented using firmware or software in the form of codes, instructions and / or sets of instructions.

[0109] One or more memories (204a, 204b) may be coupled to one or more processors (202a, 202b) and may store various forms of data, signals, messages, information, programs, codes, instructions, and / or commands. The one or more memories (204a, 204b) may be configured as read only memory (ROM), random access memory (RAM), erasable programmable read only memory (EPROM), flash memory, hard drives, registers, cache memory, computer readable storage media, and / or combinations thereof. The one or more memories (204a, 204b) may be located internally and / or externally to the one or more processors (202a, 202b). Additionally, the one or more memories (204a, 204b) may be coupled to the one or more processors (202a, 202b) via various technologies, such as wired or wireless connections.

[0110] One or more transceivers (206a, 206b) can transmit user data, control information, wireless signals / channels, etc., as mentioned in the methods and / or flowcharts of this specification, to one or more other devices. One or more transceivers (206a, 206b) can receive user data, control information, wireless signals / channels, etc., as mentioned in the descriptions, functions, procedures, proposals, methods and / or flowcharts of this specification, from one or more other devices. For example, one or more transceivers (206a, 206b) can be coupled to one or more processors (202a, 202b) and can transmit and receive wireless signals. For example, one or more processors (202a, 202b) can control one or more transceivers (206a, 206b) to transmit user data, control information, or wireless signals to one or more other devices. Additionally, one or more processors (202a, 202b) may control one or more transceivers (206a, 206b) to receive user data, control information, or wireless signals from one or more other devices. Additionally, one or more transceivers (206a, 206b) may be coupled to one or more antennas (208a, 208b), and one or more transceivers (206a, 206b) may be configured to transmit and receive user data, control information, wireless signals / channels, or the like, as referred to in the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed herein, via one or more antennas (208a, 208b). In the present specification, one or more antennas may be multiple physical antennas or multiple logical antennas (e.g., antenna ports). One or more transceivers (206a, 206b) can convert received user data, control information, wireless signals / channels, etc. from RF band signals to baseband signals in order to process the received user data, control information, wireless signals / channels, etc. using one or more processors (202a, 202b).One or more transceivers (206a, 206b) may convert user data, control information, wireless signals / channels, etc. processed by one or more processors (202a, 202b) from baseband signals to RF band signals. For this purpose, one or more transceivers (206a, 206b) may include an (analog) oscillator and / or filter.

[0111] FIG. 3 is a diagram illustrating a method for processing a transmission signal applied to the present specification. 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 processors (202a, 202b) and / or the transceivers (206a, 206b) of FIG. 2. Furthermore, as an example, the hardware elements of FIG. 3 may be implemented in the processors (202a, 202b) and / or the transceivers (206a, 206b) of FIG. 2. For example, blocks 310 to 350 may be implemented in the processor (202a, 202b) of FIG. 2, and block 360 may be implemented in the transceiver (206a, 206b) of FIG. 2, and are not limited to the above-described embodiments.

[0112] 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) of FIG. 6. 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.

[0113] A complex modulation symbol sequence can be mapped to one or more transmission layers by a layer mapper (330). The modulation symbols of each transmission layer can be mapped to the corresponding antenna port(s) by a precoder (340) (precoding). 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. In addition, the precoder (340) can perform precoding without performing transform precoding.

[0114] 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.

[0115] The signal processing process for receiving signals in a wireless device can be configured in reverse order of the signal processing process (310-360) of FIG. 3. For example, a wireless device (e.g., 200a, 200b of FIG. 2) can receive wireless signals from the outside through an antenna port / transceiver. The received wireless signals can be converted into baseband signals through a signal restorer. For this purpose, the signal restorer can include a frequency downlink converter, an analog-to-digital converter (ADC), a CP remover, and a fast Fourier transform (FFT) module. Thereafter, the baseband signal can be restored to a codeword through a resource demapper process, a postcoding process, a demodulation process, and a descrambling process. The codewords can be restored to the original information blocks through decoding. Accordingly, a signal processing circuit (not shown) for a received signal may include a signal restorer, a resource de-mapper, a postcoder, a demodulator, a de-scrambler, and a decoder.

[0116] Wireless device structure applicable to this specification

[0117] FIG. 4 is a diagram illustrating another example of a wireless device to which the present specification applies.

[0118] Referring to FIG. 4, the wireless device (400) corresponds to the wireless devices (200a, 200b) of FIG. 2 and may be composed of various elements, components, units, and / or modules. For example, the wireless device (400) may include a communication unit (410), a control unit (420), a memory unit (430), and additional elements (440). The communication unit may include a communication circuit (412) and a transceiver(s) (414). For example, the communication circuit (412) may include one or more processors (202a, 202b) and / or one or more memories (204a, 204b) of FIG. 2. For example, the transceiver(s) (414) may include one or more transceivers (206a, 206b) and / or one or more antennas (208a, 208b) of FIG. 2. The control unit (420) is electrically connected to the communication unit (410), the memory unit (430), and the additional elements (440) and controls the overall operation of the wireless device. For example, the control unit (420) may control the electrical / mechanical operation of the wireless device based on the program / code / command / information stored in the memory unit (430). In addition, the control unit (420) may transmit information stored in the memory unit (430) to an external device (e.g., another communication device) via a wireless / wired interface through the communication unit (410), or store information received from an external device (e.g., another communication device) via a wireless / wired interface in the memory unit (430).

[0119] The additional element (440) may be configured in various ways depending on the type of the wireless device. For example, the additional element (440) may include at least one of a power unit / battery, an input / output unit, a driving unit, and a computing unit. Although not limited thereto, the wireless device (400) may be implemented in the form of a robot (Fig. 1, 100a), a vehicle (Fig. 1, 100b-1, 100b-2), an XR device (Fig. 1, 100c), a portable device (Fig. 1, 100d), a home appliance (Fig. 1, 100e), an IoT device (Fig. 1, 100f), a digital broadcasting terminal, a hologram device, a public safety device, an MTC device, a medical device, a fintech device (or a financial device), a security device, a climate / environmental device, an AI server / device (Fig. 1, 140), a base station (Fig. 1, 120), a network node, etc. Wireless devices may be mobile or stationary depending on the use / service.

[0120] In FIG. 4, various elements, components, units / parts, and / or modules within the wireless device (400) may be entirely interconnected via a wired interface, or at least some may be wirelessly connected via a communication unit (410). For example, within the wireless device (400), the control unit (420) and the communication unit (410) may be wired, and the control unit (420) and a first unit (e.g., 430, 440) may be wirelessly connected via the communication unit (410). In addition, each element, component, unit / part, and / or module within the wireless device (400) may further include one or more elements. For example, the control unit (420) may be composed of a set of one or more processors. For example, the control unit (420) may be composed of a set of a communication control processor, an application processor, an electronic control unit (ECU), a graphics processing processor, a memory control processor, etc. As another example, the memory unit (430) may be composed of RAM, DRAM (dynamic RAM), ROM, flash memory, volatile memory, non-volatile memory, and / or a combination thereof.

[0121] Mobile devices to which this specification applies

[0122] FIG. 5 is a drawing illustrating an example of a mobile device to which the present specification applies.

[0123] Figure 5 illustrates an example of a mobile device applicable to the present specification. The mobile device may include a smartphone, a smart pad, a wearable device (e.g., a smart watch, smart glasses), or a portable computer (e.g., a laptop, etc.). The mobile device may be referred to as a mobile station (MS), a user terminal (UT), a mobile subscriber station (MSS), a subscriber station (SS), an advanced mobile station (AMS), or a wireless terminal (WT).

[0124] Referring to FIG. 5, the portable device (500) may include an antenna unit (508), a communication unit (510), a control unit (520), a memory unit (530), a power supply unit (540a), an interface unit (540b), and an input / output unit (540c). The antenna unit (508) may be configured as a part of the communication unit (510). Blocks 510 to 530 / 540a to 540c correspond to blocks 410 to 430 / 440 of FIG. 4, respectively.

[0125] The communication unit (510) can transmit and receive signals (e.g., data, control signals, etc.) with other wireless devices and base stations. The control unit (520) can control components of the portable device (500) to perform various operations. The control unit (520) can include an AP (application processor). The memory unit (530) can store data / parameters / programs / codes / commands required for operating the portable device (500). In addition, the memory unit (530) can store input / output data / information, etc. The power supply unit (540a) supplies power to the portable device (500) and can include a wired / wireless charging circuit, a battery, etc. The interface unit (540b) can support connection between the portable device (500) and other external devices. The interface unit (540b) can include various ports (e.g., audio input / output ports, video input / output ports) for connection with external devices. The input / output unit (540c) can input or output video information / signals, audio information / signals, data, and / or information input from a user. The input / output unit (540c) may include a camera, a microphone, a user input unit, a display unit (540d), a speaker, and / or a haptic module.

[0126] For example, in the case of data communication, the input / output unit (540c) obtains information / signals (e.g., touch, text, voice, image, video) input by the user, and the obtained information / signals can be stored in the memory unit (530). The communication unit (510) can convert the information / signals stored in the memory into wireless signals, and transmit the converted wireless signals directly to other wireless devices or to a base station. In addition, the communication unit (510) can receive wireless signals from other wireless devices or base stations, and then restore the received wireless signals to the original information / signals. The restored information / signals can be stored in the memory unit (530) and then output in various forms (e.g., text, voice, image, video, haptic) through the input / output unit (540c).

[0127] Physical channels and general signal transmission

[0128] FIG. 6 is a diagram illustrating physical channels applicable to this specification and a signal transmission method using them.

[0129] When a terminal is powered on again from a powered-off state or newly enters a cell, it performs an initial cell search operation, such as synchronizing with the base station, in step S611. To this end, the terminal receives a primary synchronization channel (P-SCH) and a secondary synchronization channel (S-SCH) from the base station to synchronize with the base station and obtain information such as the cell ID.

[0130] After that, the terminal can obtain broadcast information within the cell by receiving a physical broadcast channel (PBCH) signal from the base station. Meanwhile, the terminal can check the downlink channel status by receiving a downlink reference signal (DL RS) in the initial cell search phase. After completing the initial cell search, the terminal can obtain more specific system information by receiving a physical downlink control channel (PDCCH) and a physical downlink shared channel (PDSCH) based on the physical downlink control channel information in step S612.

[0131] Thereafter, the terminal may perform a random access procedure such as steps S613 to S616 to complete connection to the base station. To this end, the terminal may transmit a preamble through a physical random access channel (PRACH) (S613) and receive a random access response (RAR) for the preamble through a physical downlink control channel and a physical downlink shared channel corresponding thereto (S614). The terminal may transmit a physical uplink shared channel (PUSCH) using scheduling information in the RAR (S615) and perform a contention resolution procedure such as receiving a physical downlink control channel signal and a physical downlink shared channel signal corresponding thereto (S616).

[0132] A terminal that has performed the procedure described above can then perform reception of a physical downlink control channel signal and / or a physical downlink shared channel signal (S617) and transmission of a physical uplink shared channel (PUSCH) signal and / or a physical uplink control channel (PUCCH) signal (S618) as a general uplink / downlink signal transmission procedure.

[0133] Control information transmitted from a terminal to a base station is collectively referred to as uplink control information (UCI). UCI includes hybrid automatic repeat and request acknowledgment / negative ACK (HARQ-ACK / NACK), scheduling request (SR), channel quality indication (CQI), precoding matrix indication (PMI), rank indication (RI), and beam indication (BI) information. UCI is generally transmitted periodically through PUCCH, but depending on the embodiment (e.g., when control information and traffic data must be transmitted simultaneously), it may be transmitted through PUSCH. In addition, the terminal may transmit UCI aperiodically through PUSCH upon request / instruction from the network.

[0134] 6G communication system

[0135] The 6G (wireless communication) system aims to achieve (i) very high data rates per device, (ii) a very large number of connected devices, (iii) global connectivity, (iv) very low latency, (v) low energy consumption for battery-free IoT devices, (vi) ultra-reliable connectivity, and (vii) connected intelligence with machine learning capabilities. The vision of the 6G system can be divided into four aspects: "intelligent connectivity," "deep connectivity," "holographic connectivity," and "ubiquitous connectivity," and the 6G system can satisfy the requirements as shown in Table 1 below. In other words, Table 1 is a table showing the requirements of the 6G system.

[0136]

[0137] 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.

[0138] Core implementation technology of 6G systems

[0139] Artificial Intelligence

[0140] The most crucial and newly introduced technology for 6G systems is AI. 4G systems did not involve AI. 5G systems will support partial or very limited AI. However, 6G systems will fully support AI for automation. Advances in machine learning will create more intelligent networks for real-time communications in 6G. Incorporating AI into communications can streamline and improve real-time data transmission. AI can use numerous analyses to determine how complex target tasks should be performed. In other words, AI can increase efficiency and reduce processing delays.

[0141] Time-consuming tasks such as handover, network selection, and resource scheduling can be performed instantly using AI. AI can also play a crucial role in machine-to-machine (M2M), machine-to-human, and human-to-machine communications. Furthermore, AI can facilitate rapid communication in brain-computer interfaces (BCIs). AI-based communication systems can be supported by metamaterials, intelligent structures, intelligent networks, intelligent devices, intelligent cognitive radios, self-sustaining wireless networks, and machine learning.

[0142] Recent attempts to integrate AI into wireless communication systems have focused on the application layer, network layer, and especially deep learning in wireless resource management and allocation. However, this research is increasingly evolving to the MAC layer and physical layer, with attempts to combine deep learning with wireless transmission, particularly at the physical layer. AI-based physical layer transmission refers to the application of AI-based signal processing and communication mechanisms, rather than traditional communication frameworks, in the fundamental signal processing and communication mechanisms. For example, this may include deep learning-based channel coding and decoding, deep learning-based signal estimation and detection, deep learning-based MIMO mechanisms, and AI-based resource scheduling and allocation.

[0143] Machine learning can be used for channel estimation and channel tracking, as well as for power allocation and interference cancellation in the physical layer of the downlink (DL). Furthermore, machine learning can be used for antenna selection, power control, and symbol detection in MIMO systems.

[0144] Below, we will look at machine learning in more detail.

[0145] Machine learning refers to a series of operations that train machines to perform tasks that humans can or cannot perform. Machine learning requires data and a learning model. Data learning methods in machine learning can be broadly categorized into three types: supervised learning, unsupervised learning, and reinforcement learning.

[0146] Neural network training aims to minimize output errors. It involves repeatedly inputting training data into a neural network, calculating the neural network output and target error for the training data, and backpropagating the neural network error from the output layer to the input layer to update the weights of each node in the neural network to reduce the error.

[0147] Supervised learning uses labeled training data, while unsupervised learning may not have labeled training data. For example, in the case of supervised learning for data classification, the training data may be data in which each training data category is labeled. Labeled training data is input to a neural network, and the error can be calculated by comparing the output (categories) of the neural network with the training data labels. The calculated error is backpropagated through the neural network in the backward direction (i.e., from the output layer to the input layer), and the connection weights of each node in each layer of the neural network can be updated through backpropagation. The amount of change in the connection weights of each updated node can be determined by the learning rate. The neural network's calculation of the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle. For example, in the early stages of training a neural network, a high learning rate can be used to quickly allow the network to achieve a certain level of performance, thereby increasing efficiency. In the later stages of training, a low learning rate can be used to increase accuracy.

[0148] Learning methods may vary depending on the characteristics of the data. For example, if the goal is to accurately predict data transmitted by a transmitter in a communication system, supervised learning is preferable to unsupervised learning or reinforcement learning.

[0149] The learning model corresponds to the human brain, and the most basic linear model can be thought of, but the machine learning paradigm that uses highly complex neural network structures, such as artificial neural networks, as learning models is called deep learning.

[0150] The neural network cores used in learning methods are mainly divided into deep neural networks (DNN), convolutional deep neural networks (CNN), and recurrent boltzmann machines (RNN).

[0151] An artificial neural network is an example of a network of multiple perceptrons.

[0152] Referring to Fig. 7, when an input vector x=(x1,x2,...,xd) is input, the entire process of multiplying each component by a weight (W1,W2,...,Wd), adding up all the results, and then applying the activation function σ() is called a perceptron. A large-scale artificial neural network structure can extend the simplified perceptron structure illustrated in Fig. 7 to apply the input vector to perceptrons of different dimensions. For convenience of explanation, input values ​​or output values ​​are called nodes.

[0153] Meanwhile, the perceptron structure illustrated in Fig. 7 can be explained as consisting of a total of three layers based on input and output values. An artificial neural network in which there are H perceptrons of dimension (d+1) between the 1st layer and the 2nd layer, and K perceptrons of dimension (H+1) between the 2nd layer and the 3rd layer can be expressed as in Fig. 8.

[0154] The layer where the input vector is located is called the input layer, the layer where the final output value is located is called the output layer, and all layers located between the input layer and the output layer are called hidden layers. The example in Fig. 8 shows three layers, but when counting the number of layers in an actual artificial neural network, the input layer is excluded, so it can be viewed as a total of two layers. An artificial neural network is composed of perceptrons, which are basic blocks, connected in two dimensions.

[0155] The aforementioned input, hidden, and output layers can be applied jointly not only to multilayer perceptrons but also to various artificial neural network structures, such as CNNs and RNNs, which will be described later. The greater the number of hidden layers, the deeper the artificial neural network. The machine learning paradigm that uses sufficiently deep artificial neural networks as learning models is called deep learning. Furthermore, the artificial neural network used for deep learning is called a deep neural network (DNN).

[0156] The deep neural network illustrated in Figure 9 is a multilayer perceptron consisting of eight hidden layers and eight output layers. The multilayer perceptron structure is referred to as a fully-connected neural network. In a fully-connected neural network, there is no connection between nodes located in the same layer, and there is a connection only between nodes located in adjacent layers. DNN has a fully-connected neural network structure and is composed of a combination of multiple hidden layers and activation functions, and can be usefully applied to identify correlation characteristics between inputs and outputs. Here, the correlation characteristic can mean the joint probability of inputs and outputs. Figure 9 is a diagram illustrating an example of a deep neural network.

[0157] Meanwhile, depending on how multiple perceptrons are connected to each other, various artificial neural network structures different from the aforementioned DNN can be formed.

[0158] In DNN, nodes within a single layer are arranged vertically in a one-dimensional manner. However, Fig. 10 can assume a case where nodes are arranged two-dimensionally, with w nodes in width and h nodes in height (the convolutional neural network structure of Fig. 10). In this case, since a weight is added to each connection in the connection process from one input node to the hidden layer, a total of h×w weights must be considered. Since there are h×w nodes in the input layer, a total of h2w2 weights are required between two adjacent layers.

[0159] Figure 10 is a diagram showing an example of a convolutional neural network.

[0160] The convolutional neural network of Fig. 10 has a problem in that the number of weights increases exponentially according to the number of connections. Therefore, instead of considering the connections of all modes between adjacent layers, it assumes that there are small filters, and performs weighted sum and activation function operations on the overlapping portions of the filters, as in Fig. 10.

[0161] Each filter has a weight corresponding to its size, and weight learning can be performed to extract and output a specific feature on the image as a factor. In Fig. 10, a 3×3 filter is applied to the upper left 3×3 region of the input layer, and the output value resulting from performing weighted sum and activation function operations on the corresponding node is stored in z22.

[0162] The above filter performs weighted sum and activation function operations while moving horizontally and vertically at a certain interval while scanning the input layer, and places the output value at the current filter location. This operation method is similar to the convolution operation for images in the field of computer vision, so a deep neural network with this structure is called a convolutional neural network (CNN), and the hidden layer generated as a result of the convolution operation is called a convolutional layer. In addition, a neural network with multiple convolutional layers is called a deep convolutional neural network (DCNN).

[0163] Figure 11 is a diagram showing an example of a filter operation in a convolutional neural network.

[0164] In the convolutional layer, the number of weights can be reduced by calculating a weighted sum that includes only the nodes located in the area covered by the filter, starting from the node where the current filter is located. This allows a single filter to focus on features within a local area. Accordingly, CNNs can be effectively applied to image data processing where physical distance in a two-dimensional area is an important criterion for judgment. Meanwhile, CNNs can apply multiple filters immediately before the convolutional layer, and can generate multiple output results through the convolution operation of each filter.

[0165] Meanwhile, depending on the data properties, there may be data for which sequence characteristics are important. Considering the length variability and chronological relationship of such sequence data, a structure that applies a method of inputting one element of the data sequence at each timestep and inputting the output vector (hidden vector) of the hidden layer output at a specific timestep together with the immediately following element in the sequence is called a recurrent neural network structure.

[0166] Referring to Figure 12, a recurrent neural network (RNN) is a structure that inputs elements (x1(t), x2(t), ,..., xd(t)) of a data sequence at a time point t into a fully connected neural network, and then inputs the hidden vectors (z1(t-1), z2(t-1),..., zH(t-1)) of the immediately preceding time point t-1 together and applies a weighted sum and activation function. The reason for transmitting the hidden vector to the next time point in this way is because the information in the input vectors of the preceding time points is considered to be accumulated in the hidden vector of the current time point.

[0167] Figure 12 shows an example of a neural network structure in which a recurrent loop exists.

[0168] Referring to Figure 12, the recurrent neural network operates in a predetermined order of time for the input data sequence.

[0169] When the input vector (x1(t), x2(t), ,..., xd(t)) at time point 1 is input to the recurrent neural network, the hidden vector (z1(1), z2(1),..., zH(1)) is input together with the input vector (x1(2), x2(2),..., xd(2)) at time point 2, and the vector (z1(2), z2(2),..., zH(2)) of the hidden layer is determined through a weighted sum and an activation function. This process is repeatedly performed until time points 2, 3, ,,, T.

[0170] Figure 13 shows an example of the operating structure of a recurrent neural network.

[0171] Meanwhile, when multiple hidden layers are placed within a recurrent neural network, it is called a deep recurrent neural network (DRNN). Recurrent neural networks are designed to be useful for processing sequence data (e.g., natural language processing).

[0172] It is a neural network core used in a learning manner, and includes various deep learning techniques such as DNN, CNN, RNN, Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), and Deep Q-Network, and can be applied to fields such as computer vision, speech recognition, natural language processing, and speech / signal processing.

[0173] The symbols / abbreviations / terms used in this specification are as follows.

[0174] - CRC: Cyclic Redundancy Check

[0175] - DL: Deep Learning

[0176] - DNN: Deep Neural Network

[0177] - GAN: Generative Adversarial Network

[0178] - GD: Gradient Descent

[0179] - MSE: Mean Squared Error

[0180] - SR: Semantic Representation

[0181] : set of real numbers

[0182] : set of natural numbers

[0183] Below, technical issues related to the embodiments proposed in this specification are examined with reference to FIG. 14.

[0184] Figure 14 is a diagram illustrating a level-based communication model to which the embodiment proposed in this specification can be applied.

[0185] Referring to Figure 14, the communication model can be defined at three levels (A to C).

[0186] Level A concerns how accurately symbols (technical messages) can be transmitted between a transmitter and a receiver. This can be considered when the communication model is understood from a technical perspective.

[0187] Level B concerns how accurately the symbols transmitted between a transmitter and a receiver convey meaning. This can be considered when the communication model is understood from a semantic perspective.

[0188] Level C concerns how effectively the meaning received at the destination contributes to subsequent actions. This can be considered when the communication model is understood in terms of effectiveness.

[0189] Not all Level A to Level C perspectives are considered in the design of a communication model and may vary depending on the implementation method.

[0190] For example, a communication model focused on Level A, such as a communication model based on prior art, can be considered. Another example could be a communication model that considers not only Level A but also Level B (and Level C) for supporting semantic communication. In such a communication model, the transmitter and receiver could be referred to as a semantic transmitter and a semantic receiver, and semantic noise could be additionally considered.

[0191] Below, we describe in detail the considerations related to graph neural networks.

[0192] One of the many goals of 6G communications is to enable a variety of new services that interconnect people and machines with varying levels of intelligence. This requires consideration not only of existing technical issues (e.g., Figure 14A), but also of semantic issues (e.g., Figure 14B). Semantic communication is described in detail below, using human-to-human communication as an example.

[0193] Words used to exchange information (word information) are associated with "meaning." Upon hearing a speaker's words, a listener can interpret the meaning or concept expressed by the speaker's words. Linking this to the communication model in Figure 14, to support semantic communication, the concepts associated with the message sent from the source must be correctly interpreted at the destination.

[0194] Using data provided to the Source or collected raw data, the Source can generate a semantic representation (SR). The Source can then transmit this SR to the Destination. At this point, the approach required to ensure that the interpretation and reasoning are correct, rather than simply reducing reconstruction errors during the process of reconstructing the SR received by the Destination back into raw data, is crucial.

[0195] Specifically, in the process of restoring the SR received by the Destination back to the original raw data, access is required to determine whether the downstream task performed by the Destination is performed according to the intention conveyed by the Source using the received SR.

[0196] When performing inference operations, a destination utilizes its own background knowledge. To achieve this, the background knowledge contained in the data transmitted from the source must be reflected in the destination's background knowledge.

[0197] In order to perform semantic communication, it is important for the Source to properly create an SR containing semantic information about the data to be transmitted and transmit it to the Destination, and for the Destination to accurately interpret the semantic information contained in the received SR.

[0198] When conducting semantic communication over a noisy communication channel, the message received at the destination may contain errors due to channel noise or a mismatch in the receiver's background knowledge. These errors can occur at the technical level (level A in Figure 14) or the semantic level (level B in Figure 14). At this time, since the technical level's ultimate goal is to preserve the syntactic structure of the transmitted and received messages, a technical error can be defined as a syntactic difference between the transmitted and received messages.

[0199] In contrast, the semantic level does not aim for syntactic preservation of the transmitted and received messages. The ultimate goal at the semantic level is to reason similarly between the semantics contained in the transmitted message and the semantics contained in the received message. Therefore, a semantic error can be defined as a semantic difference between the meaning of a transmitted message and a received message. For example, in Source, "Monday" tuesday wednesday thursday The sentence "Friday" was sent and the destination received " Saturday It can be assumed that the sentence "Sunday" is received. Since the same semantics can be obtained based on background knowledge about the day of the week, it can be seen that semantic similarity is maintained. However, in terms of syntactic preservation, it can be interpreted that a technical error has occurred because a syntactic difference has occurred. Another example of a semantic error is described in detail below with reference to FIG. 15.

[0200] Figure 15 is a diagram illustrating a semantic error.

[0201] Referring to Figure 15, suppose that the Source uses sound (e.g., a voice) to convey the word "copy machine" to the Destination. Since the pronunciation of "p" is very similar to the pronunciation of "ff," a semantic error could occur: The Destination might misinterpret the Source's pronunciation of the word "copy machine" as the word "coffee machine." This would be considered a semantic error regarding the intended word.

[0202] To prevent this semantic error, the source could send the word "Xerox" as a message instead of "copy machine." This would prevent the "p" sound from being misinterpreted as "ff," thus preventing the semantic error.

[0203] When performing semantic communication in this manner, semantic errors can cause semantic mismatches between the Source and Destination. To ensure reliable semantic communication, the Destination can perform a semantic error check to detect the aforementioned semantic mismatches. If a semantic error is detected, the Destination can correct the semantic error and request retransmission from the Source, thereby obtaining the exact semantic information the Source intended to send.

[0204] Recently, deep neural network (DNN) semantic encoding / decoding methods for semantic communication have been actively studied. Research is underway to extend classical information theory, such as the definition of semantic entropy and semantic mutual information, to semantic information theory.

[0205] Furthermore, research has been conducted on defining loss functions based on information-theoretic metrics such as broad semantic entropy and channel capacity, and building semantic encoders / decoders using DNNs based on these loss functions. Along with the design of these DNN-based semantic encoders / decoders, research is also being conducted on techniques for detecting semantic errors. In particular, semantic error detection in semantic communication, unlike conventional technical communication, does not primarily aim to find syntactic differences. Therefore, a new semantic error check technique, different from the cyclic redundancy check (CRC) technique used in conventional technical communication, is required. The semantic error check technique will now be examined in detail with reference to Figures 16 to 19.

[0206] Figure 16 illustrates a DNN-based semantic error check technique.

[0207] The semantic error checking techniques proposed to date are DNN-based techniques, as illustrated in Fig. 16. Specifically, referring to Fig. 16, "CRC32 Encoder" and "CRC32 Decoder" are replaced by "Sim32 Encoder" and "Sim32 Decoder," respectively. "Source&Channel Encoder" and "Source&Channel Decoder" are replaced by DNN-based Semantic Encoder and Semantic Decoder (e.g., Fig. 17), respectively.

[0208] Figure 17 illustrates a semantic encoder and a semantic decoder.

[0209] The overall structure specifically expressing Fig. 16 is as shown in Fig. 18.

[0210] Figure 18 illustrates a structure for DNN-based semantic error check.

[0211] The operating principle of semantic error check is as follows: First, the message to be sent from the Source Input them into "Sim32 Encoder" and "Semantic Encoder" respectively to get "32-bit header" ( ) and transmission bits ( ) is obtained. The Source transmits the "32-bit header" along with the transmission bits to the Destination. The Destination receives the "32-bit header" ( ) is removed. The destination inputs the received bit-stream with the "32-bit header" removed to the "Semantic Decoder". Get . Destination is class It inputs "Sim32 Decoder" together, and if the result value of "Sim32 Decoder" is greater than 0.5, it outputs ACK 1, and if the result value is less than or equal to 0.5, it outputs ACK 0. At this time, ACK 1 is an ack that a semantic error did not occur, and ACK 0 is an ack that a semantic error occurred.

[0212] In order to train “Sim32 Encoder” and “Sim32 Decoder”, it is assumed that “Semantic Encoder” and “Semantic Decoder” have been trained. In other words, “Semantic Encoder” and “Semantic Decoder” are trained first, and then “Sim32 Encoder” and “Sim32 Decoder” are trained. In the training process, and Since all are known values, similarity can be obtained using BERT. BERT is a model pre-trained using more than 1 billion words and sentences. Based on BERT, semantic information of sentences can be extracted. If sentence semantic transmission is the main target, based on BERT, and The similarity of can be calculated. and similarity value of Learning can be performed based on this. Then, we proceed with learning for “Sim32 Encoder” and “Sim32 Decoder” with label 1. If so, it can be learned with label 0.

[0213] Therefore, the "32-bit header" received based on the DNN ( ) and message restored through "Semantic Decoder" Semantic errors can be checked based on semantic similarity with . This operation is different from the operation of checking only bit errors in the bit sequence performed in the existing classical CRC.

[0214] The above-described technique only obtains information on whether a semantic error has occurred in the received data using the received "32-bit header", and cannot perform a correction process for semantic errors.

[0215] Techniques for correcting semantic errors are also being studied based on DNNs. Referring to Figure 19 below, we examine techniques for correcting semantic errors.

[0216] Figure 19 illustrates a technique for correcting semantic errors.

[0217] Specifically, Fig. 19 shows the process of performing correction of semantic errors (or semantic distortions) based on a Generative Adversarial Network (GAN).

[0218] Referring to Figure 19, a "correction network" is trained with a structure similar to a GAN so that a feature map in which an error has occurred can be corrected through the "correction network." By inputting an error feature map and an error mask into the "correction network," a restored feature map with the error occurring at the location of the error mask can be generated.

[0219] The GAN-based error correction technique described in Figure 19 can correct semantic errors in received feature maps. However, it has the limitation of lacking an additional verification process to verify that the correction has been performed properly. In other words, it assumes that the restored feature map has perfectly corrected the semantic errors. Accordingly, data from the restored feature map is used directly for downstream tasks (image reconstruction in Figure 19).

[0220] The restored feature map obtained through the correction network may contain additional semantic errors. This technique has a limitation in that it cannot detect or correct these additional errors. Therefore, improvements are needed. The following examples may be considered in this regard.

[0221] To address the limitations of semantic error detection techniques, the following actions can be performed: The Source can create a semantic redundancy check node based on the semantic tree. The Source can transmit the semantic information node and the semantic redundancy check node from the Source to the Destination. Based on the above actions, semantic errors can be detected.

[0222] The above semantic tree can be constructed to satisfy the following properties.

[0223] - Every parent node contains the semantics of all its child nodes.

[0224] - The bit sequence from the MSB of the node label of the child node to the length of the node label of the parent node is identical to the node label of its parent node.

[0225] - Node labels of nodes at the same level have the same length.

[0226] - As the distance between nodes increases, semantic similarity decreases.

[0227] The semantic tree constructed as above can be constructed to satisfy the layer characteristics of Fig. 20.

[0228] Figure 20 illustrates the layer characteristics of a semantic tree. As an example of a semantic tree satisfying the properties of Figure 20, WordNet, constructed using the hierarchical structure of words, can be drawn as shown in Figure 21.

[0229] Figure 21 illustrates a semantic tree of WordNet-based words. The semantic tree of Figure 21 can be generalized and expressed as shown in Figure 22.

[0230] Figure 22 shows a generalized example of a semantic tree.

[0231] Referring to Figure 22, Source is a semantic information node , , It can be assumed that there is a case where one wants to transmit. Here, the node with the highest level among the common ancestor nodes of all semantic information nodes is can be selected as a semantic redundancy check (SRC) node.

[0232] The SRC node generated in this way is transmitted from the source to the destination, along with the semantic information node. The destination can use the received SRC node to check for semantic errors in the received semantic information nodes. At this time, it is verified whether all semantic information nodes are descendants of the SRC node.

[0233] Specifically, if all semantic information nodes are descendants of the SRC node, the Destination can determine that no semantic error has occurred and transmit an ACK signal to the Source. Otherwise (i.e., if at least one semantic information node is not a descendant of the SRC node), the Destination can determine that a semantic error has occurred and transmit a NACK signal to the Source.

[0234] As described above, using the semantic tree, it is possible to determine whether a semantic error has occurred in the semantic information nodes received by the destination.

[0235] In this specification, we propose a technique for correcting semantic errors when semantic errors occur in semantic information nodes received from a destination using a semantic tree.

[0236] In particular, we propose a 2-step technique that can efficiently correct semantic errors by additionally transmitting semantic information nodes and level information of SRC nodes from the Source to the Destination.

[0237] In Step 1 of the proposed technique, semantic error correction is performed on SRC nodes. In Step 2, semantic error correction is performed on semantic information nodes based on the corrected SRC nodes.

[0238] The definitions of terms that can be used in the semantic tree are as follows:

[0239] Node: A structure containing data

[0240] Root: The node at the top of the tree

[0241] Edge: A relationship that indicates the connection status between nodes.

[0242] Child (Child node): A node that exists at a lower level of the tree.

[0243] Parent (Parent node): A node that has child nodes

[0244] Leaf (Leaf node): A node that has no children

[0245] Sibling nodes: child nodes with the same parent

[0246] Ancestor: Node(s) corresponding to the parent(s) of the parent node from the child node

[0247] Descendant: Node(s) that correspond to the child(ies) of a specific parent node

[0248] Degree (of node): Number of children of the node

[0249] Degree of tree: The largest degree value among the nodes in the tree

[0250] Distance: The shortest path connecting two nodes on the tree.

[0251] Level: distance from node to root

[0252] Width: The number of nodes at a given level

[0253] Breadth: Total number of leaf nodes

[0254] Forest: A set of one or more non-overlapping trees

[0255] Size of tree: Number of nodes in the tree

[0256] 1) Semantic Redundancy Check Node Generation & Level Information Transmission

[0257] When the Source transmits semantic information to the Destination, it also transmits information about the semantic redundancy check (SRC) node. This is to enable the Destination to perform semantic error checking.

[0258] For example, the SRC node can be created as follows.

[0259] The Source selects a node from the semantic tree corresponding to the semantic information to be transmitted. If the Source wishes to transmit M pieces of semantic information, the corresponding M nodes can be selected from the semantic tree.

[0260] Source finds all ancestors of the selected M semantic information node(s).

[0261] Source finds all nodes that have all semantic information nodes as descendants among the ancestors of each obtained semantic information node. In other words, Source finds all ancestors that all semantic information nodes have in common.

[0262] Source selects the node with the highest level among the above ancestor(s) as the SRC node.

[0263] The SRC node obtained as described above is transmitted along with semantic information. That is, the Source transmits the SRC node and semantic information to the Destination. Level information may also be transmitted at this time.

[0264] In one embodiment, to perform a semantic error correction technique, the Source may also obtain level information for a semantic information node and transmit it to the Destination. For example, the Source may transmit an SRC node, level information, and semantic information to the Destination. This will be described in detail below with reference to FIG. 23.

[0265] Figure 23 illustrates SRC node creation and level information for semantic error correction according to an embodiment of the present specification.

[0266] Specifically, Figure 23 illustrates semantic information nodes, SRC nodes, and level information for each semantic information node.

[0267] The Source transmits i) semantic information, ii) SRC node information, and iii) level information of each node to the Destination.

[0268] Specifically, Source is i) semantic information nodes ( , , ), ii) SRC node( ) and iii) transmits level information (4, 4, 4) for each of the above semantic information nodes to the destination.

[0269] 2) Semantic Error Detection

[0270] To perform highly reliable semantic communication, the destination must first check whether semantic information received from the source contains semantic errors. The following actions can be performed to check for semantic errors. Specifically, the destination can check for semantic errors by verifying whether all semantic information nodes are descendants of the SRC node. For example, if all semantic information nodes are descendants of the SRC node, it can be determined that no semantic error has occurred. For example, if at least one of the semantic information nodes is not a descendant of the SRC node, it can be determined that a semantic error has occurred.

[0271] Additionally, according to an embodiment of the present specification, level information for semantic information nodes is transmitted together with the semantic information nodes. The destination can determine that a semantic error has occurred if the level values ​​for the received semantic information nodes differ from the received level information.

[0272] The detection / inspection of semantic errors is specifically described with reference to FIG. 24 below.

[0273] Figure 24 illustrates a semantic tree at a Destination according to an embodiment of the present specification. It is assumed that the information transmitted by the Source in Figure 24 is the same as that in Figure 23.

[0274] Specifically, as in Fig. 23, it is assumed that the Source transmits the following information to the Destination.

[0275] i) semantic information nodes ( , , ),

[0276] ii) SRC node( )

[0277] iii) Level information (4, 4, 4) for each of the above semantic information nodes

[0278] Figure 24 illustrates a semantic tree when the Destination receives the information i) to iii) below from the Source.

[0279] i) semantic information nodes ( , , ),

[0280] ii) SRC node( )

[0281] iii) Level information (4, 4, 4) for each of the above semantic information nodes

[0282] Destination can check for semantic errors based on the following two methods:

[0283] For example, the Destination can check whether all semantic information nodes are descendants of the SRC node. In the case of Fig. 24, among the semantic information nodes, node is SRC node( ) is not a descendant node of Destination. Therefore, Destination can determine that a semantic error has occurred.

[0284] For example, the destination can determine whether a semantic error has occurred based on the received level information. Specifically, the received level information (4, 4, 4) indicates that the level of all semantic information nodes is 4 (e.g., =4). Among the received semantic information nodes, The node level is 2 (e.g. =2). Received level information ( =4) and the received semantic information node( node) level information (e.g. =2) does not match, Destination can be judged to have a semantic error.

[0285] 3) Semantic Error Correction

[0286] As described above, if a semantic error is determined to have occurred after checking for semantic errors, semantic error correction must be performed to restore the original semantic information. Below, we will examine a method for correcting semantic errors based on the semantic information nodes received from the destination, the SRC node, and the level information of each semantic information node. Since label information is transmitted and received through the SRC node, the destination can obtain level information using the label length information.

[0287] The semantic error correction technique proposed in this specification proceeds in two steps. In Step 1, semantic error correction is performed on SRC nodes. In Step 2, semantic error correction is performed on semantic information nodes.

[0288] - Step 1: SRC Node Correction

[0289] To perform corrections on SRC nodes, received semantic information nodes are utilized. For convenience of explanation, the following description assumes that semantic information nodes, SRC nodes, and level information are received, as shown in Figure 24.

[0290] The level information for the received SRC node is 2. The SRC node must be selected from among the nodes at level 2. Therefore, the destination finds the node with the largest number of descendants of the received semantic information nodes among the nodes at level 2 in the semantic tree. Based on the number of semantic information nodes belonging to the descendants of the selected node, the destination can determine the selected node as the corrected SRC node.

[0291] The number of received semantic information nodes Assuming this is the case, the following actions can be performed:

[0292] For example, the number of semantic information nodes that are descendants of the selected node is If the number of semantic information nodes that are descendants of the selected node does not exceed a certain number, the Destination can transmit a NACK signal to the Source. That is, if the number of semantic information nodes that are descendants of the selected node does not exceed a certain number ( ) is less than the received semantic information node and SRC node, the Destination can determine that a semantic error that cannot be corrected has occurred. In this case, the Destination can no longer perform semantic error correction and transmit a NACK signal to the Source. The value can be a value defined / set between Source and Destination in advance.

[0293] For example, the number of semantic information nodes that are descendants of the selected node is If it is greater than or equal to , the destination determines the node as a corrected SRC node. The correction for such an SRC node is explained with reference to Figure 25.

[0294] Figure 25 illustrates a correction to an SRC node according to an embodiment of the present specification.

[0295] Referring to Figure 25, among the nodes with level 2, contains two of the received semantic information nodes. That is, among the nodes with level 2, the node with the largest number of semantic information nodes as descendants is It is a node. Destination is Corrects the node to an SRC node. In other words, the SRC node is In node It can be corrected with node.

[0296] At this time, information related to whether semantic error correction is performed for the SRC node (e.g., the ratio α described above, and / or At least one of them) can be transmitted to the Destination.

[0297] For example, Source is a specific threshold can be transmitted from the Source to the Destination. Based on the above specific threshold, the Destination can determine whether to perform semantic error correction for the SRC node. can be transmitted instead of a specific ratio α.

[0298] The number of semantic information nodes that are descendants of the node searched / selected according to the above method If it is equal to or greater than , the destination can determine that node as a SRC node with a normally corrected semantic error. For example, in Fig. 25 If =2, the node can be selected as an SRC node. Destination performs step 2. For example, If =3, there is no level 2 node with a number of descendant semantic information nodes greater than 3. The destination terminates the semantic correction procedure and sends a NACK signal to the source.

[0299] For example, the maximum number of hops between a semantic information node and an SRC node can be defined / set between Source / Destination. Destination calculates the number of hops between the received semantic information node and the SRC node.

[0300] Destination is the calculated hop count is the maximum hop count above. If it exceeds , it can be determined that a semantic error that cannot be corrected has occurred in the received semantic information node and SRC node. Therefore, the destination does not perform any further correction techniques and sends a NACK signal to the source.

[0301] For example, in Fig. 25 If =2, the distance between all semantic information nodes and SRC nodes is Because it is smaller, we continue to perform the semantic error correction technique. However, if If =1, then in Fig. 25 Since there is a semantic information node with a larger number of hops, semantic error correction is no longer performed and a NACK signal is sent to the Source.

[0302] - Step 2: Semantic Information Node Correction

[0303] If a correction is performed on the SRC node (e.g., the Destination is When a node is selected as a corrected SRC node), semantic error correction is performed on semantic information nodes.

[0304] Destination selects the semantic information node where semantic error correction will be performed. In Fig. 25 Since the node is not included as a descendant of the SRC node and the level value is different from the received level value, correction is performed for the semantic information node.

[0305] Candidate node(s) are generated based on the received level information for semantic error correction. In Fig. 25. The level information for is 4, so The candidates for correction are and It becomes a child node of .

[0306] Here The reason why the child node of is not selected as a candidate is because there is an SRC node mismatch. Specifically, If semantic error correction is performed, the SRC node is regenerated using semantic information nodes. This has to come out. In other words, cast When it is corrected as a child node of , the SRC node is re-created / determined based on this. . Therefore, an SRC node mismatch occurs.

[0307] After the correction of semantic information nodes is completed and an SRC node is created using the semantic information nodes, all nodes that can create a node identical to the corrected SRC node are designated as candidates for erroneous semantic information nodes. Among the candidates for semantic information nodes designated in this way, the node with the highest semantic similarity with the originally received semantic information node is selected as the corrected semantic information node.

[0308] The correction process of the semantic information node for Fig. 25 is described in detail with reference to Fig. 26.

[0309] Figure 26 illustrates a set of candidates for a semantic information node according to an embodiment of the present specification.

[0310] Referring to Figure 26, the nodes of level 4 that can regenerate the corrected SRC node are set as candidates. At this time, the possible candidates are node and Assuming node, Destination is for those two nodes Semantic similarity with nodes can be calculated. Various existing methods can be utilized to calculate semantic similarity. Three examples of methods for calculating semantic similarity are described below.

[0311] In one embodiment, the destination can find the similarity between nodes in the semantic tree. Two nodes class similarity about can be calculated by the following mathematical formula 1.

[0312]

[0313] Here, Silver node is the probability of occurrence refers to the node with the highest level among the common ancestors of two nodes. Destination can calculate the semantic similarity between nodes using mathematical equation 1. Alternatively, a previously shared semantic similarity table (e.g., Figure 27) can be utilized for a given semantic tree. Figure 27 illustrates semantic similarity based on WordNet.

[0314] In one embodiment, Destination can calculate the similarity of subgraphs based on the belief propagation (BP) algorithm. Applying the algorithm shown in Figure 26 can calculate the similarity for a subgraph (or subtree) as shown in Figure 28.

[0315] Figure 28 illustrates a subgraph for semantic similarity comparison according to an embodiment of the present specification. Specifically, Figure 28 illustrates a subgraph-based graph similarity measurement.

[0316] Referring to Figure 28, Destination is and By comparing, it can be determined that the sub-graph with a higher similarity value is the sub-graph with the corrected semantic information node.

[0317] While the BP algorithm can be used, subgraph similarity can also be measured using a transformer-based deep neural network. For example, similarity for a subgraph like that in Figure 28 can be calculated based on the following mathematical expression (2).

[0318]

[0319] Mathematical expression 2 represents the transformer-based similarity measurement value. Silver graph It is a transformer-based graph processing DNN. It means the embedding function to be used as input. Using this similarity metric, the destination is and By comparing, a sub-graph having a higher similarity value can be determined as a sub-graph having a corrected semantic information node. The corrected semantic information node determined based on the similarity described above is described below with reference to FIG. 29.

[0320] FIG. 29 illustrates semantic error correction for a semantic information node according to an embodiment of the present specification.

[0321] If semantic error correction is performed on a semantic information node using the similarity measurement method described above in the example of Fig. 26, a corrected semantic information node can be determined as in Fig. 29.

[0322] Referring to Fig. 29, Corrected semantic information node for can be decided by , , The SRC node generated based on , and the corresponding node is identical to the corrected SRC node. That is, no SRC node mismatch occurs. The creation of the SRC node (whether there is an SRC node mismatch) is confirmed and the correction procedure is terminated. If the semantic error correction for the semantic information node is successful, the destination sends an ACK signal to the source.

[0323] The Source may not send level information for a semantic information node. If the Destination does not receive level information for a semantic information node, semantic error correction can be performed as follows.

[0324] The destination can determine the lowest level node(s) among the nodes that can create a corrected SRC node using the corrected semantic information node as a candidate group for semantic error correction. The destination can obtain similarity based on the candidate group. The destination can perform semantic error correction for the semantic information node based on the similarity. For example, in Fig. 26 and can be determined as a candidate for the corrected semantic information node.

[0325] When semantic error correction is performed as described above, it can be seen that semantic error correction has been performed to a level that allows the task to be performed at the destination, rather than performing perfect semantic error correction. Furthermore, by not transmitting or receiving level information for semantic information nodes, transmission and reception resources can be conserved.

[0326] Below, a signaling procedure based on the above-described embodiments is specifically described with reference to FIGS. 30 to 32.

[0327] 4) Signaling Procedure

[0328] The general signaling procedure for the technology proposed in this specification is as shown in Figure 30 below.

[0329] Figure 30 is an example of a signaling procedure according to an embodiment of the present specification.

[0330] In S3010, semantic communication initialization is performed. For example, at least one of information about the semantic tree, information related to the detection of semantic errors, and / or information related to the correction of semantic errors may be shared between the Source and the Destination.

[0331] As a specific example, the Source may transmit to the Destination at least one of information about the semantic tree, information related to the detection of semantic errors, and / or information related to the correction of semantic errors. As another example, at least one of the information about the semantic tree, information related to the detection of semantic errors, and / or information related to the correction of semantic errors may be predefined with the same value(s) when implementing the Source and the Destination.

[0332] In S3020, the Source generates semantic information to be transmitted to the Destination.

[0333] In S3030, the Source selects semantic information node(s) for the above semantic information and creates an SRC node. Additionally, the Source obtains a level value for each semantic information node.

[0334] In S3040, the Source transmits the Semantic information node, the SRC node, and the level value of each semantic information node to the Destination.

[0335] In S3050, Destination performs semantic error check based on semantic tree.

[0336] If no semantic error is found, the Destination transmits an ACK signal to the Source (S3060).

[0337] If it is determined that a semantic error has occurred (S3070), the destination performs SRC node correction using the level information of each node and performs correction for the semantic information node (S3071).

[0338] When semantic error correction is completed, the Destination transmits an ACK signal to the Source. If semantic error correction is not completed, the Destination transmits a NACK signal to the Source (S3072).

[0339] If the Source does not transmit level information about the semantic information node to the Destination, the signaling procedure is as shown in Figure 31.

[0340] Figure 31 is another example of a signaling procedure according to an embodiment of the present specification.

[0341] S3110 to S3172 of Fig. 31 correspond to S3010 to S3072 of Fig. 30, and thus, duplicate descriptions are omitted. That is, in S3140, the remaining information (semantic information and SRC node) excluding the level information is transmitted from the Source to the Destination.

[0342] Source to Destination , The signaling procedure for transmitting additional information such as level information is as follows: Figure 32

[0343] Figure 32 is another example of a signaling procedure according to an embodiment of the present specification.

[0344] S3210 to S3272 of FIG. 32 correspond to S3010 to S3072 of FIG. 30, and duplicate descriptions are omitted.

[0345] In S3140, Source contains additional information (Add: level information, attribute value, etc.) in addition to semantic information and SRC node. , , ) can be transmitted together.

[0346] For example, threshold and / or max hop count If restrictions apply, the Source is created after the SRC node is created. and / or The value can be calculated / determined. The Source is the Destination along with the semantic information node, SRC node, and level information. and / or can be transmitted.

[0347] Destination is , When performing semantic error correction using , the procedure can be stopped early as described above. That is, , If the conditions based on this are not satisfied, the Destination may stop semantic error correction and send a NACK signal.

[0348] Also, the values ​​promised by Source and Destination in advance It can be used as a value. Depending on the communication environment, from the Source You can set the value and send it to the destination along with the semantic information node and SRC node as additional information.

[0349] Additionally, when the BP algorithm is used for semantic error correction for semantic information nodes, the Source can transmit attribute values ​​for the semantic information nodes and SRC nodes to the Destination. The Destination can additionally calculate sub-tree similarity based on the received attribute values ​​for semantic error correction for the semantic information nodes using the BP algorithm. The Destination can correct semantic errors in the semantic information nodes using the calculated sub-tree similarity.

[0350] The following effects are derived from the above-described examples.

[0351] To achieve reliable semantic communication, it is essential to detect whether semantic errors have occurred in the signals received at the destination and, if so, to correct them. The technology proposed in this specification enables correction of semantic errors that may occur in semantic communication situations, thereby enabling reliable semantic communication.

[0352] In particular, the semantic tree-based semantic error correction technology proposed in this specification can generate the values ​​and level information of SRC nodes and semantic information nodes through the characteristics of the semantic tree, thereby performing semantic error correction at the destination. This semantic tree-based semantic error correction technology can be applied to all data types that can constitute a semantic tree. In other words, the semantic error correction technology based on this specification has high utility in that it can be universally applied to various semantic communication systems.

[0353] In terms of implementation, the operations according to the embodiments described above (e.g., operations related to detection and correction of semantic errors) can be processed by the devices of FIGS. 1 to 5 described above (e.g., processors (202a, 202b) of FIG. 2).

[0354] In addition, the operations (e.g., operations related to detection and correction of semantic errors) according to the above-described embodiments may be stored in a memory (e.g., 204a, 204b of FIG. 2) in the form of instructions / programs (e.g., instructions, executable codes) for driving at least one processor (e.g., processors (202a, 202b) of FIG. 2).

[0355] In this specification, "semantic" can be interpreted as the meaning intended to be conveyed from the Source to the Destination. As described in FIG. 14, semantic communication can be related to Level B (and Level C). For example, if the semantic information transmitted from the Source to the Destination is accurately conveyed without error, it can mean that the meaning intended by the Source has been accurately conveyed to the Destination.

[0356] The embodiments described below are specifically described with reference to FIGS. 33 and 34 in terms of the operation of wireless devices (e.g., the first wireless device (200a) and the second wireless device (200b) of FIG. 2). The methods described below are distinguished merely for the convenience of explanation, and it goes without saying that some components of one method may be substituted for some components of another method or may be applied in combination with each other.

[0357] FIG. 33 is a flowchart illustrating a method performed by a first wireless device according to one embodiment of the present specification.

[0358] Referring to FIG. 33, a method performed by a first wireless device in one embodiment of the present specification includes a step of determining a first node related to error checking of semantic information (S3310), a step of transmitting first information including semantic information and the first node (S3320), and a step of receiving second information including an ACK or NACK related to reception of semantic information (S3330).

[0359] Hereinafter, the first wireless device may mean a source in semantic communication, and the second wireless device may mean a destination in semantic communication.

[0360] In S3310, the first wireless device determines a first node (e.g., an SRC node) related to error checking and correction of semantic information. For example, S3310 may be based on S3030 of FIG. 30, S3130 of FIG. 31, or S3230 of FIG. 32.

[0361] The first node may be determined as the ancestor node with the highest level among the ancestor nodes that have second nodes (e.g., semantic information nodes) based on the semantic information as descendant nodes in the semantic tree.

[0362] In one embodiment, information about the semantic tree may be shared in advance between the first wireless device and the second wireless device.

[0363] In one embodiment, the level of a specific node in the semantic tree may be related to the distance from the specific node to the root of the semantic tree. The first information may further include a level for each of the second nodes.

[0364] In S3320, the first wireless device transmits first information to the second wireless device. The first information may include the semantic information and the first node. For example, S3320 may be based on S3040 of FIG. 30 , S3140 of FIG. 31 , or S3240 of FIG. 32 .

[0365] In S3330, the first wireless device receives second information including an ACK or NACK related to the reception of the semantic information from the second wireless device. For example, S3330 may be based on S3060 / S3070 of FIG. 30, S3160 / S3170 of FIG. 31, or S3260 / S3270 of FIG. 32.

[0366] Based on whether an error has occurred in the semantic information received by the second wireless device and / or whether an error has been corrected, the second information may include the ACK or the NACK.

[0367] For example, based on a determination that the error did not occur, the second information may include the ACK.

[0368] For example, based on i) it was determined that the error occurred, and ii) the error was corrected: the second information may include the ACK.

[0369] For example, based on i) it being determined that the error has occurred, and ii) the error cannot be corrected: the second information may include the NACK.

[0370] In one embodiment, whether the error has occurred can be determined based on whether the second nodes, based on semantic information received by the second wireless device, are descendant nodes of the first node received by the second wireless device. Based on the determination that the error has occurred, a corrected first node and a corrected second node can be determined.

[0371] For example, it may be determined that the error did not occur based on the second nodes received by the second wireless device being the descendent nodes.

[0372] For example, it may be determined that the error has occurred based on at least one of the second nodes received by the second wireless device being not the descendent node.

[0373] If an error is determined to have occurred, the SRC node correction and semantic information node correction described above may be performed. This is described in detail below.

[0374] The corrected first node may be determined based on the determination that the above error has occurred. The corrected second node may be determined based on the corrected first node.

[0375] The corrected first node (e.g., corrected SRC node) may be one of the first candidate nodes having the same level as the first node in the semantic tree. Among the first candidate nodes, the first candidate node having the largest number of second nodes as descendant nodes may be determined as the corrected first node.

[0376] Second candidate nodes can be determined based on the above-mentioned corrected first node.

[0377] Second candidate nodes may refer to nodes without the aforementioned SRC node mismatch. Among the second candidate nodes, a corrected second node (e.g., a corrected semantic information node) may be determined based on similarity. This will be described in detail below.

[0378] Specifically, based on the fact that i) the remaining second nodes excluding at least one second node among the second nodes and ii) the ancestor node having the specific nodes as descendant nodes has the highest level ancestor node as the corrected first node: the specific nodes can be determined as the second candidate nodes.

[0379] Among the second candidate nodes, the second candidate node with the highest similarity can be determined as the corrected second node.

[0380] For example, the similarity (e.g., mathematical expression 1) may include a similarity calculated based on the at least one second node and each of the second candidate nodes. Each similarity may represent a similarity between the first node and each of the second candidate nodes in the semantic tree.

[0381] For example, the similarity may refer to the similarity between subtrees (subgraphs). The similarity may include a similarity calculated for each of the first subtrees. Each similarity may represent the similarity between each of the first subtrees and the second subtree.

[0382] Each first sub-tree (e.g., Fig. 28) , ) may include i) the corrected first node, ii) one of the second candidate nodes, and iii) the remaining second nodes.

[0383] The second sub-tree (e.g., Fig. 28) ) may include i) the first node and ii) the second nodes.

[0384] The operations based on S3310 to S3330 described above can be implemented by the device of FIG. 2. For example, the first wireless device (200a) can control one or more transceivers (206a) and / or one or more memories (204a) to perform the operations based on S3310 to S3330.

[0385] The embodiments described below are specifically described in terms of the operation of the second wireless device.

[0386] S3410 to S3430 described below correspond to S3310 to S3330 described in FIG. 33. Considering the above correspondence, redundant descriptions are omitted. That is, the detailed description of the operation of the second wireless device described below may be replaced with the description / example of FIG. 33 corresponding to the corresponding operation.

[0387] For example, the description / example based on S3310 to S3320 of FIG. 33 may be applied to the operation of a second wireless device based on S3410.

[0388] For example, the description / example based on S3330 of FIG. 33 may be applied to the operation of a second wireless device based on S3420 and S3430.

[0389] FIG. 34 is a flowchart illustrating a method performed by a second wireless device according to another embodiment of the present specification.

[0390] Referring to FIG. 34, a method performed by a second wireless device in another embodiment of the present specification includes a step of receiving first information including semantic information and a first node (S3410), a step of determining whether an error has occurred in the semantic information based on the first node (S3420), and a step of transmitting second information including an ACK or NACK related to the reception of the semantic information (S3430).

[0391] In S3410, the second wireless device receives first information from the first wireless device. The first information may include semantic information and a first node related to error checking of the semantic information. For example, S3410 may be based on S3040 of FIG. 30 , S3140 of FIG. 31 , or S3240 of FIG. 32 .

[0392] At S3420, the second wireless device determines whether an error has occurred in the semantic information based on the first node. For example, S3420 may be based on S3050 of FIG. 30, S3150 of FIG. 31, or S3250 of FIG. 32.

[0393] In one embodiment, whether the error has occurred can be determined based on whether the second nodes based on the semantic information in the semantic tree are descendant nodes of the first node.

[0394] In S3430, the second wireless device transmits second information including an ACK or NACK related to reception of the semantic information to the first wireless device. For example, S3430 may be based on S3060 / S3070 of FIG. 30, S3160 / S3170 of FIG. 31, or S3260 / S3270 of FIG. 32.

[0395] The operations based on S3410 to S3430 described above can be implemented by the device of FIG. 2. For example, the second wireless device (200b) can control one or more transceivers (206b) and / or one or more memories (204b) to perform the operations based on S3410 to S3430.

[0396] Here, the wireless communication technology implemented in the wireless device (200a, 200b) of the present specification may include not only LTE, NR, and 6G, but also Narrowband Internet of Things for low-power communication. At this time, for example, NB-IoT technology may be an example of LPWAN (Low Power Wide Area Network) technology, and may be implemented with standards such as LTE Cat NB1 and / or LTE Cat NB2, and is not limited to the above-described names. Additionally or alternatively, the wireless communication technology implemented in the wireless device (200a, 200b) of the present specification may perform communication based on LTE-M technology. At this time, for example, LTE-M technology may be an example of LPWAN technology, and may be called by various names such as eMTC (enhanced Machine Type Communication). For example, LTE-M technology can be implemented by at least one of various standards such as 1) LTE CAT 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-Bandwidth Limited), 5) LTE-MTC, 6) LTE Machine Type Communication, and / or 7) LTE M, and is not limited to the above-described names. Additionally or alternatively, the wireless communication technology implemented in the wireless device (200a, 200b) of the present specification can include at least one of ZigBee, Bluetooth, and Low Power Wide Area Network (LPWAN) considering low-power communication, and is not limited to the above-described names. For example, ZigBee technology can create personal area networks (PAN) related to small / low-power digital communication based on various standards such as IEEE 802.15.4, and can be called by various names.

[0397] The embodiments described above are combinations of the components and features of the present disclosure in a predetermined form. Each component or feature should be considered optional unless explicitly stated otherwise. Each component or feature may be implemented without being combined with other components or features. Furthermore, it is also possible to combine some components and / or features to form an embodiment 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. It is self-evident that claims that do not have an explicit citation relationship in the patent claims may be combined to form an embodiment or may be incorporated as a new claim through a post-application amendment.

[0398] Embodiments according to the present specification may be implemented by various means, for example, hardware, firmware, software, or a combination thereof. In the case of hardware implementation, an embodiment of the present invention may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, etc.

[0399] When implemented via firmware or software, an embodiment of the present specification may be implemented in the form of a module, procedure, function, or the like that performs the functions or operations described above. The software code may be stored in memory and executed by a processor. The memory may be located within or external to the processor and may exchange data with the processor via various known means.

[0400] It will be apparent to those skilled in the art that this specification may be embodied in other specific forms without departing from the essential characteristics thereof. Therefore, the foregoing detailed description should not be construed in any way as limiting but rather as illustrative. The scope of this specification should be determined by a reasonable interpretation of the appended claims, and all changes within the scope of equivalents herein are intended to be included within the scope of this specification.

Claims

1. A method performed by a first wireless device in a wireless communication system, A step of determining a first node related to error checking and correction of semantic information; A step of transmitting first information to a second wireless device, the first information including the semantic information and the first node; and A step of receiving second information including an ACK or NACK related to reception of the semantic information from the second wireless device; The first node is determined as the ancestor node with the highest level among the ancestor nodes that have second nodes based on the semantic information as descendant nodes in the semantic tree. Based on whether an error has occurred in the semantic information received by the second wireless device and / or whether an error has been corrected, the second information includes the ACK or the NACK, Whether the above error occurs or not, It is determined based on whether the second nodes based on the semantic information received by the second wireless device are descendant nodes of the first node received by the second wireless device, A method characterized in that a corrected first node and a corrected second node are determined based on the determination that the above error has occurred.

2. In paragraph 1, A method characterized in that it is determined that the error has not occurred based on the second nodes received by the second wireless device being the descendent nodes.

3. In paragraph 1, A method characterized in that the error is determined to have occurred based on at least one of the second nodes received by the second wireless device being not the descendent node.

4. In paragraph 3, The corrected first node is determined based on the determination that the above error has occurred, A method characterized in that the corrected second node is determined based on the corrected first node.

5. In paragraph 4, The above corrected first node is one of the first candidate nodes having the same level as the first node in the semantic tree, A method characterized in that the first candidate node having the largest number of second nodes as descendant nodes among the first candidate nodes is determined as the corrected first node.

6. In paragraph 5, Second candidate nodes are determined based on the above-mentioned corrected first node, i) the remaining second nodes excluding at least one second node among the second nodes and ii) the ancestor node with the highest level among the ancestor nodes having specific nodes as descendant nodes is the corrected first node: the specific nodes are determined as the second candidate nodes, A method characterized in that the second candidate node having the highest similarity among the second candidate nodes is determined as the corrected second node.

7. In paragraph 6, The above similarity includes a similarity calculated based on each of the at least one second node and the second candidate nodes, A method characterized in that each similarity represents the similarity between the first node and each second candidate node in the semantic tree.

8. In paragraph 6, The above similarity includes the similarity calculated for each of the first sub-trees, Each similarity represents the similarity between the first sub-tree and the second sub-tree, Each first sub-tree comprises i) the corrected first node, ii) one of the second candidate nodes, and iii) the remaining second nodes, A method characterized in that the second sub-tree comprises i) the first node and ii) the second nodes.

9. In paragraph 1, A method characterized in that the second information includes the ACK, based on the determination that the above error did not occur.

10. In paragraph 1, i) based on the determination that the error has occurred, and ii) based on the correction of the error: a method characterized in that the second information includes the ACK.

11. In paragraph 1, A method characterized in that: the second information includes the NACK, wherein: i) it is determined that the error has occurred, and ii) the error cannot be corrected.

12. In paragraph 1, A method characterized in that information about the semantic tree is shared in advance between the first wireless device and the second wireless device.

13. In paragraph 1, A method characterized in that the level of a specific node in the semantic tree is related to the distance from the specific node to the root of the semantic tree.

14. In paragraph 13, A method characterized in that the first information further includes a level for each of the second nodes.

15. In a first wireless device operating in a wireless communication system, One or more transmitters and receivers; one or more processors; and One or more memories connected to said one or more processors and storing instructions, A first wireless device, characterized in that the instructions, based on being executed by the one or more processors, set the one or more processors to perform all steps of the method according to any one of claims 1 to 14.

16. In a device comprising one or more memories and one or more processors functionally connected to the one or more memories, A device characterized in that said one or more memories store instructions that cause said one or more processors to perform all steps of a method according to any one of claims 1 to 14, based on execution by said one or more processors.

17. In one or more non-transitory computer-readable media storing instructions, One or more non-transitory computer-readable media characterized in that the instructions executable by one or more processors cause the one or more processors to perform all steps of the method according to any one of claims 1 to 14.

18. In a method performed by a second wireless device in a wireless communication system, A step of receiving first information from a first wireless device, the first information including semantic information and a first node related to error checking and correction of the semantic information; A step of determining whether an error has occurred in the semantic information based on the first node; and A step of transmitting second information including an ACK or NACK related to reception of the semantic information to the first wireless device; Whether the above error occurs or not, In the semantic tree, it is determined based on whether the second nodes based on the semantic information are descendant nodes of the first node, A method characterized in that a corrected first node and a corrected second node are determined based on the determination that the above error has occurred.

19. In a second wireless device operating in a wireless communication system, One or more transmitters and receivers; one or more processors; and One or more memories connected to said one or more processors and storing instructions, A second wireless device characterized in that the instructions are set to cause the one or more processors to perform all steps of the method according to claim 18, based on the instructions being executed by the one or more processors.

Images