Method and apparatus for anomaly detection in wireless environment

Abstract

The present disclosure relates to a 5G or 6G communication system for supporting a data transmission rate higher than that of a 4G communication system such as LTE. This operation method of a first electronic device for performing wireless communication may comprise the steps of: collecting feature values of features for at least one wireless channel used by the first electronic device during communication; generating pre-processed feature values by using the feature values of the features; generating correlation coefficient weights of the features, the weights reflecting the influence between the features, on the basis of the pre-processed feature values; generating training data by using the pre-processed feature values and the correlation coefficient weights; training an unsupervised learning model by using the training data; and performing monitoring and anomaly detection on the at least one wireless channel in real time by using the model.

Description

Method and device for anomaly detection in a wireless environment

[0001] The present disclosure relates to a method and apparatus for detecting anomalies in a wireless environment.

[0002] Looking back at the evolution of wireless communication through successive generations, technologies have been developed primarily for human-oriented services, such as voice, multimedia, and data. Following the commercialization of 5G (5th-generation) communication systems, connected devices, which have been increasing explosively, are expected to be connected to communication networks. Examples of networked objects include vehicles, robots, drones, home appliances, displays, smart sensors installed in various infrastructures, construction machinery, and factory equipment. Mobile devices are expected to evolve into various form factors, such as augmented reality glasses, virtual reality headsets, and holographic devices. In the 6G (6th-generation) era, efforts are underway to develop improved 6G communication systems to connect hundreds of billions of devices and objects to provide diverse services. For this reason, 6G communication systems are being referred to as "beyond 5G" systems.

[0003] In the 6G communication system predicted to be realized around 2030, the maximum transmission speed is tera (i.e., 1,000 gigabit) bps, and the wireless latency is 100 microseconds (μsec). In other words, compared to the 5G communication system, the transmission speed in the 6G communication system is 50 times faster, and the wireless latency is reduced to one-tenth.

[0004] To achieve such high data transmission speeds and ultra-low latency, 6G communication systems are being considered for implementation in the terahertz band (e.g., the 95 GHz to 3 terahertz (3 THz) band). In the terahertz band, due to more severe path loss and atmospheric absorption compared to the millimeter wave (mmWave) band introduced in 5G, the importance of technology capable of guaranteeing signal reach, or coverage, is expected to increase. As key technologies to ensure coverage, radio frequency (RF) devices, antennas, new waveforms that offer better coverage than orthogonal frequency division multiplexing (OFDM), beamforming, and multi-antenna transmission technologies such as massive multiple-input and multiple-output (massive MIMO), full-dimensional MIMO (FD-MIMO), array antennas, and large-scale antennas must be developed. In addition, new technologies such as metamaterial-based lenses and antennas, high-dimensional spatial multiplexing technology using orbital angular momentum (OAM), and reconfigurable intelligent surface (RIS) are being discussed to improve coverage of terahertz band signals.

[0005] In addition, to improve frequency efficiency and system network, development is underway in 6G communication systems for full duplex technology, in which uplink and downlink simultaneously utilize the same frequency resources at the same time; network technology that integrates satellites and HAPS (high-altitude platform stations); network structure innovation technology that supports mobile base stations and enables network operation optimization and automation; dynamic spectrum sharing technology through collision avoidance based on spectrum usage prediction; AI-based communication technology that utilizes AI (artificial intelligence) from the design stage and internalizes end-to-end AI support functions to realize system optimization; and next-generation distributed computing technology that realizes services of complexity exceeding the limits of terminal computing capabilities by utilizing ultra-high performance communication and computing resources (mobile edge computing (MEC), cloud, etc.). In addition, attempts are continuing to further strengthen connectivity between devices, further optimize networks, promote the softwareization of network entities, and increase the openness of wireless communication through the design of new protocols to be used in 6G communication systems, the implementation of hardware-based security environments, the development of mechanisms for the safe utilization of data, and the development of technologies regarding privacy maintenance methods.

[0006] Due to the research and development of such 6G communication systems, it is expected that a new dimension of hyper-connected experience will become possible through the hyper-connectivity of 6G communication systems, which encompasses not only connections between objects but also connections between people and objects. Specifically, it is projected that 6G communication systems will enable the provision of services such as truly immersive extended reality (truly immersive XR), high-fidelity mobile holograms, and digital replicas. Furthermore, services such as remote surgery, industrial automation, and emergency response, which are provided through 6G communication systems with enhanced security and reliability, will be applied in various fields including industry, healthcare, automotive, and home appliances.

[0007] The present disclosure provides a method and apparatus for detecting anomalies in a high wireless environment.

[0008] A method of operation of a first electronic device for performing wireless communication according to an embodiment of the present disclosure for achieving the above objective may include: collecting feature values ​​of features for at least one wireless channel used by the first electronic device during communication; generating preprocessed feature values ​​using the feature values ​​of the features; generating correlation coefficient weights of the features reflecting the influence between the features based on the preprocessed feature values; generating training data using the preprocessed feature values ​​and the correlation coefficient weights; training an unsupervised learning model using the training data; and performing real-time monitoring and anomaly detection for the at least one wireless channel using the model.

[0009] A method of operation of a second electronic device for performing wireless communication according to one embodiment of the present disclosure for achieving the above objective may include the steps of receiving feature values ​​of features for at least one wireless channel from a first electronic device, generating at least one data frame for said at least one wireless channel using said feature values ​​of said features, and transmitting said at least one data frame to said first electronic device.

[0010] A first electronic device for performing wireless communication according to one embodiment of the present disclosure for achieving the above objective includes a transceiver and a control unit, wherein the control unit may be configured to collect feature values ​​of features for at least one wireless channel used by the first electronic device during communication, generate preprocessed feature values ​​using the feature values ​​of the features, generate correlation coefficient weights of the features reflecting the influence between the features based on the preprocessed feature values, generate training data using the preprocessed at least one feature information and the at least one correlation coefficient weights, train an unsupervised learning model using the training data, and perform real-time monitoring and anomaly detection for the at least one wireless channel using the model.

[0011] A second electronic device for performing wireless communication according to one embodiment of the present disclosure for achieving the above objective comprises a transceiver and a control unit, wherein the control unit may be configured to receive feature values ​​of features for at least one wireless channel from a first electronic device, generate at least one data frame for the at least one wireless channel using the feature values ​​of the features, and transmit the at least one data frame to the first electronic device.

[0012] According to one embodiment of the present disclosure, the present disclosure may include a method for adjusting the weights of features for wireless communication. The method for adjusting the weights of features in wireless communication may be for efficient data transmission and quality control. The method for adjusting the weights of features may automatically adjust the weights of features participating in learning based on collected data. The present disclosure may set weights that can dynamically adapt according to the network environment. The method for adjusting the weights of features may include a method for determining correlation coefficients between features to set more optimized weights. The method for adjusting the weights of features may include a method for efficiently analyzing data by setting optimized weights. The method for adjusting the weights of features may include a method for monitoring the wireless environment by efficiently analyzing data.

[0013] FIG. 1 is a block diagram of an electronic device in a network environment according to one embodiment of the present disclosure.

[0014] FIG. 2a is a block diagram illustrating an example of an anomaly detection method according to one embodiment of the present disclosure.

[0015] FIG. 2b is a block diagram illustrating an anomaly detection invention according to one embodiment of the present disclosure.

[0016] FIG. 3 is a flowchart illustrating a model learning method according to one embodiment of the present disclosure.

[0017] FIG. 4 is a conceptual diagram illustrating an example of an ideal value according to an embodiment of the present disclosure.

[0018] FIG. 5 is a block diagram illustrating a model inference method according to one embodiment of the present disclosure.

[0019] FIG. 6 is a conceptual diagram illustrating a learning weight according to one embodiment of the present disclosure.

[0020] FIG. 7 is a flowchart illustrating a learning method using a feature that is used as learning data in a device according to one embodiment of the present disclosure.

[0021] FIG. 8 is a flowchart illustrating a monitoring method according to one embodiment of the present disclosure.

[0022] FIG. 9 is a block diagram illustrating a method for transmitting features used as training data according to one embodiment of the present disclosure.

[0023] FIG. 10 is a conceptual diagram illustrating a method for preprocessing data according to one embodiment of the present disclosure.

[0024] FIG. 11 is a conceptual diagram illustrating a model evaluation method according to one embodiment of the present disclosure.

[0025] FIG. 12 is a block diagram illustrating the structure of a first electronic device according to one embodiment of the present disclosure.

[0026] FIG. 13 is a block diagram illustrating the structure of a second electronic device according to one embodiment of the present disclosure.

[0027] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0028] In describing the embodiments, technical details that are well known in the technical field to which this disclosure belongs and are not directly related to this disclosure are omitted. This is intended to convey the essence of this disclosure more clearly without obscuring it by omitting unnecessary explanations.

[0029] For the same reason, some components in the attached drawings have been exaggerated, omitted, or schematically depicted. Additionally, the size of each component does not entirely reflect its actual dimensions. Identical or corresponding components in each drawing have been assigned the same reference numbers.

[0030] The advantages and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below but may be implemented in various different forms. The embodiments of the present disclosure are provided merely to make the present disclosure complete and to fully inform those skilled in the art of the scope of the disclosure, and the present disclosure is defined only by the scope of the claims. Throughout the specification, like reference numerals refer to like components.

[0031] At this point, it will be understood that each block of the process flow diagrams and combinations of the flow diagrams can be executed by computer program instructions. Since these computer program instructions can be loaded into the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, the instructions executed through the processor of the computer or other programmable data processing equipment create means to perform the functions described in the flow diagram block(s). Since these computer program instructions can also be stored in computer-available or computer-readable memory that can be directed toward the computer or other programmable data processing equipment to implement the function in a specific way, the instructions stored in computer-available or computer-readable memory can also produce a manufactured item containing means of instruction to perform the function described in the flow diagram block(s). Since computer program instructions can be loaded onto a computer or other programmable data processing equipment, instructions that execute a computer or other programmable data processing equipment by performing a series of operation steps on the computer or other programmable data processing equipment to create a process executed by the computer may also provide steps for executing the functions described in the flowchart block(s).

[0032] Additionally, each block may represent a module, segment, or part of code containing one or more executable instructions for executing a specific logical function(s). It should also be noted that in some alternative execution examples, the functions mentioned in the blocks may occur out of order. For instance, two blocks described in succession may actually be executed substantially simultaneously, or the blocks may be executed in reverse order depending on the corresponding function.

[0033] In this disclosure, the term “part” as used refers to a software or hardware component, such as a Field Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC), and the “part” performs certain roles. However, the “part” is not limited to software or hardware. The “part” may be configured to reside in an addressable storage medium or may be configured to run one or more processors. Accordingly, according to some embodiments, the “part” includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and “parts” may be combined into a smaller number of components and “parts” or further separated into additional components and “parts.” In addition, the components and 'parts' may be implemented to utilize one or more CPUs within the device or secure multimedia card. Furthermore, according to some embodiments, the 'parts' may include one or more processors.

[0034] The operating principles of the present disclosure will be described in detail below with reference to the attached drawings. In describing the present disclosure below, specific descriptions of related known functions or configurations will be omitted if it is determined that such detailed descriptions would unnecessarily obscure the essence of the present disclosure. Furthermore, the terms described below are defined in consideration of their functions in the present disclosure, and these may vary depending on the intentions or practices of the user or operator. Therefore, their definitions should be based on the content throughout this specification.

[0035] Each of the station (STA), transmitting device, receiving device, and electronic device used in this disclosure may be referred to as a terminal, mobile station (MS), user equipment (UE), user terminal (UT), wireless terminal, access terminal (AT), terminal, subscriber unit, subscriber station (SS), wireless device, wireless communication device, wireless transmit / receive unit (WTRU), mobile node, mobile, or other terms. Each of the station, transmitting device, receiving device, and electronic device may include a cellular telephone, a smartphone with wireless communication capabilities, a personal digital assistant (PDA) with wireless communication capabilities, a wireless modem, a portable computer with wireless communication capabilities, a shooting device such as a digital camera with wireless communication capabilities, a gaming device with wireless communication capabilities, a music storage and playback device with wireless communication capabilities, an internet consumer device capable of wireless internet access and browsing, as well as portable units or terminals integrating combinations of such capabilities. Additionally, each of the station, transmitting device, receiving device, and electronic device may include, but is not limited to, a Machine-to-Machine (M2M) terminal or a Machine-Type Communication (MTC) terminal / device. In this disclosure, each of the station, transmitting device, receiving device, and electronic device may simply be referred to as a device.

[0036] In this disclosure, "Wireless Local Area Network (WLAN)" and "Wi-Fi" may be used interchangeably. For convenience of explanation, this disclosure describes a WLAN system comprising at least one Access Point (AP) and at least one Station (STA); however, the embodiments of this disclosure are applicable to other WLAN systems, such as, for example, multiple WLANs, peer-to-peer (or independent basic service set) systems, Wi-Fi Direct systems, and / or hotspots.

[0037] FIG. 1 is a block diagram of an electronic device in a network environment according to one embodiment of the present disclosure.

[0038] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) through a first network (198) (e.g., a short-range wireless communication network) or with at least one of an electronic device (104) or a server (108) through a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) through a server (108). According to one embodiment, the electronic device (101) may include a processor (120), memory (130), input module (150), sound output module (155), display module (160), audio module (170), sensor module (176), interface (177), connection terminal (178), haptic module (179), camera module (180), power management module (188), battery (189), communication module (190), subscriber identification module (196), or antenna module (197). In some embodiments, at least one of these components (e.g., connection terminal (178)) may be omitted from the electronic device (101), or one or more other components may be added. In some embodiments, some of these components (e.g., sensor module (176), camera module (180), or antenna module (197)) may be integrated into a single component (e.g., display module (160)).

[0039] The processor (120) can control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) by executing software (e.g., a program (140)), and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (120) can store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in volatile memory (132), process the commands or data stored in volatile memory (132), and store the resulting data in non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) that can operate independently or together with it (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, if the electronic device (101) includes a main processor (121) and an auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a designated function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as part thereof.

[0040] The auxiliary processor (123) may control at least some of the functions or states associated with at least one component of the electronic device (101) (e.g., display module (160), sensor module (176), or communication module (190)) on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. According to one embodiment, the auxiliary processor (123) (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module (180) or communication module (190)). According to one embodiment, the auxiliary processor (123) (e.g., neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or through a separate server (e.g., server (108)). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include a plurality of artificial neural network layers.An artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0041] The memory (130) can store various data used by at least one component of the electronic device (101) (e.g., processor (120) or sensor module (176)). The data may include, for example, input data or output data for software (e.g., program (140)) and related commands. The memory (130) may include volatile memory (132) or non-volatile memory (134).

[0042] The program (140) may be stored as software in memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0043] The input module (150) can receive commands or data to be used for a component of the electronic device (101) (e.g., processor (120)) from outside the electronic device (101) (e.g., user). The input module (150) may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0044] The sound output module (155) can output a sound signal to the outside of the electronic device (101). The sound output module (155) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback. The receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part thereof.

[0045] The display module (160) can visually provide information to an external (e.g., user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling said device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of the force generated by said touch.

[0046] The audio module (170) can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150) or output sound through the sound output module (155) or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphones) connected directly or wirelessly to the electronic device (101).

[0047] The sensor module (176) can detect the operating state of the electronic device (101) (e.g., power or temperature) or the external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) may include, for example, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0048] The interface (177) may support one or more specified protocols that can be used for the electronic device (101) to be connected directly or wirelessly to an external electronic device (e.g., electronic device (102)). According to one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0049] The connection terminal (178) may include a connector through which the electronic device (101) can be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0050] The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that can be perceived by the user through tactile or kinesthetic senses. According to one embodiment, the haptic module (179) may include, for example, a motor, a piezoelectric element, or an electric stimulation device.

[0051] The camera module (180) can capture still images and video. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0052] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0053] The battery (189) can supply power to at least one component of the electronic device (101). According to one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0054] The communication module (190) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may include one or more communication processors that operate independently of the processor (120) (e.g., application processor) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (194) (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device (104) through a first network (198) (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (199) (e.g., a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can identify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module (196).

[0055] The wireless communication module (192) can support 5G networks and next-generation communication technologies following 4G networks, for example, new radio access technology. NR access technology can support high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and connection of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low-latency communications (URLLC)). The wireless communication module (192) can support a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate, for example. The wireless communication module (192) can support various technologies for securing performance in the high-frequency band, such as beamforming, massive MIMO (multiple-input and multiple-output), full-dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large-scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), external electronic device (e.g., electronic device (104)), or network system (e.g., second network (199)). According to one embodiment, the wireless communication module (192) can support a Peak data rate (e.g., 20 Gbps or more) for realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mMTC, or U-plane latency (e.g., downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less) for realizing URLLC.

[0056] An antenna module (197) can transmit a signal or power to or from an external source (e.g., an external electronic device). According to one embodiment, the antenna module (197) may include an antenna comprising a radiator made of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as a first network (198) or a second network (199), may be selected from the plurality of antennas, for example, by a communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, other components (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module (197).

[0057] According to one embodiment, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to a first surface (e.g., bottom surface) of the printed circuit board and capable of supporting a specified high frequency band (e.g., mmWave band), and a plurality of antennas (e.g., array antennas) disposed on or adjacent to a second surface (e.g., top surface or side surface) of the printed circuit board and capable of transmitting or receiving a signal of the specified high frequency band.

[0058] At least some of the above components can be connected to each other via a communication method between peripheral devices (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)) and exchange signals (e.g., commands or data) with each other.

[0059] According to one embodiment, commands or data may be transmitted or received between an electronic device (101) and an external electronic device (104) through a server (108) connected to a second network (199). Each of the external electronic devices (102, or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations performed on the electronic device (101) may be performed on one or more of the external electronic devices (102, 104, or 108). For example, if the electronic device (101) needs to perform a function or service automatically or in response to a request from a user or another device, the electronic device (101) may request one or more external electronic devices to perform at least part of the function or service instead of performing the function or service itself or additionally. One or more external electronic devices that receive the above request may execute at least part of the requested function or service, or additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may provide the result as is or additionally processed as at least part of the response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device (101) may provide ultra-low latency services using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server using machine learning and / or neural networks. According to one embodiment, the external electronic device (104) or the server (108) may be included within a second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0060] An electronic device according to one embodiment disclosed in this document may be of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. The electronic device according to the embodiment of this document is not limited to the aforementioned devices.

[0061] A wireless network management system can detect and manage signal quality by adopting a fixed monitoring method. The wireless network management system can monitor signal quality based on fixed criteria for interference detection. The wireless network management system can detect only outliers that exceed a specific threshold. Outliers exceeding a specific threshold may be referred to as point anomalies.

[0062] A wireless network management system can be implemented using a post-analysis-centric approach. The wireless network management system can collect data after a network anomaly occurs. The wireless network management system can be operated by analyzing problems after a network anomaly occurs.

[0063] Anomalies in wireless networks can generally be difficult to reproduce. Since anomalies themselves are often rare, post-event handling methods may struggle to guarantee an effective response. Resolving the problem after interference occurs can take a significant amount of time and may require substantial costs and resources.

[0064] Interference with wireless signals can be caused by various factors. For example, interference can occur due to external factors such as other wireless devices or buildings. It can be difficult for wireless network management systems to analyze and respond to interference in real time. In other words, fixed monitoring methods may have limitations in analyzing and responding to various factors in real time.

[0065] Variables in wireless environments can exhibit varying degrees of variability. An integrated and adaptive approach may be necessary to effectively analyze and manage these diverse variables. Therefore, methods based on fixed criteria or post-hoc analysis fail to reflect the dynamic and complex characteristics of wireless environments, which can lead to difficulties in real-time signal interference detection and response.

[0066] The present disclosure proposes a method for adaptively and high-dimensionally learning the wireless link quality of a WLAN to solve the problem of real-time response to interference. At least one of an electronic device, a server, user equipment (UE), a terminal, a network entity, an access point (AP), and a base station can accurately calculate the quality of the network link through a network management system. At least one of the electronic device, the server, the UE, the terminal, the network entity, the AP, and the base station can detect abnormal conditions in real time through a network management system. The server may include a cloud server. By detecting abnormal conditions in real time, the limitations of a post-processing-oriented approach can be overcome, and a rapid response to various interference factors occurring in real time can be achieved.

[0067] In the present disclosure, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may adjust the weights of features for wireless communication. The method of adjusting the weights of features in wireless communication may be for efficient data transmission and quality control. The method of adjusting the weights of features may automatically adjust the weights of features participating in learning based on collected data. In the present disclosure, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may set weights that can dynamically adapt according to the network environment. The method of adjusting the weights of features may analyze data and identify correlations between features to derive more optimized weights.

[0068] The method of adjusting variable weights enables anomaly detection utilizing unsupervised learning. This method assigns weights based on the correlation between variables (e.g., features) for anomaly detection. By adjusting variable weights, it is possible to detect data anomalies while simultaneously identifying the importance of specific variables. Therefore, it allows for the efficient detection of various abnormal states that may occur in the network.

[0069] In the present disclosure, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station can perform real-time anomaly detection per link. To evaluate the data transmission quality of a link in real time, a link model can receive test data collected in real time. The link model may be a model learned based on the previous data transmission state of the link. The link model may include a model used to perform real-time anomaly detection. The link model may include a link-specific unsupervised learning model used to perform real-time anomaly detection. The link model can perform real-time evaluation through learning. The learned link model can evaluate new data to derive an evaluation score for the data transmission quality of a given link. A network operator can detect and respond to anomalies in a link in real time.

[0070] In the present disclosure, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may perform a high-dimensional link quality analysis method. Various features may be incorporated into the learning process to analyze the link quality of a wireless local area network (WLAN) more precisely. The high-dimensional link quality analysis method may evaluate link quality by considering the combination and interaction of multiple variables, rather than relying on a single variable. The high-dimensional link quality analysis method may comprehensively analyze the quality of the link and improve network performance.

[0071] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can learn patterns of a wireless channel through a network management system. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can calculate link quality in real time through a network management system. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can detect and improve anomalies through a network management system.

[0072] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may include at least one of a feature-based weighted learning procedure, an interference detection procedure through pattern change, or a real-time wireless environment monitoring procedure.

[0073] The feature-based weighted learning procedure may include a procedure for evaluating the importance of variables appearing in wireless transmission. In other words, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station may evaluate the importance of variables appearing in wireless transmission. The feature-based weighted learning procedure may include a procedure for adjusting the weights of variables with high variability. The feature-based weighted learning procedure may include a procedure for extracting meaningful information in a model learning procedure by adjusting the weights. In other words, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station may extract meaningful information in a model learning procedure by adjusting the weights of variables with high variability.

[0074] The interference detection procedure through pattern change may include a procedure for comparing a wireless environment pattern learned through variables with the current environment state. The interference detection procedure through pattern change may include a procedure for detecting anomalies by comparing a learned wireless environment pattern with the current environment state. In other words, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may detect anomalies by comparing a wireless environment pattern learned through variables with the current environment state.

[0075] The real-time wireless environment monitoring procedure may include a procedure for monitoring various performance indicators of the wireless environment in real time. The real-time wireless environment monitoring procedure may include a procedure for evaluating the network through real-time monitoring. In other words, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station may evaluate the current network through continuous monitoring of various performance indicators of the wireless environment. The performance indicators of the wireless environment may include at least one of RSSI (received signal strength indicator), SNR (signal to noise ratio), PDR (packet delivery ratio), throughput, packet loss rate, channel utilization, retransmission rate, latency, or time-series data.

[0076] FIG. 2a is a block diagram illustrating an example of an anomaly detection method according to one embodiment of the present disclosure.

[0077] Referring to Fig. 2a, the method of adjusting the weights of variables can perform anomaly detection using unsupervised learning. The method of adjusting the weights of variables can assign weights based on the correlation between variables (e.g., features) regarding anomaly detection. The method of adjusting the weights of variables can detect anomalies in the data while simultaneously identifying the importance of specific variables. Therefore, various abnormal states that may occur in the network can be efficiently detected.

[0078] The present disclosure can perform real-time anomaly detection per link. To evaluate the data transmission quality of a link in real time, a link model may receive test data collected in real time. The link model may be a model trained based on the previous data transmission state of the link. The link model can perform real-time evaluation through training. The trained link model can evaluate new data to derive an evaluation score for the data transmission quality of a given link. A network operator can detect and respond to anomalies in a link in real time.

[0079] The present disclosure can perform a high-dimensional link quality analysis method. To analyze the link quality of a wireless local area network (WLAN) more precisely, various features can be incorporated into the learning process. The high-dimensional link quality analysis method can evaluate link quality by considering the combination and interaction of multiple variables, rather than relying on a single variable. The high-dimensional link quality analysis method can comprehensively analyze link quality and improve network performance.

[0080] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform at least one of a preprocessing procedure, an end-to-end procedure, a learning procedure, an inference procedure, or a scoring procedure.

[0081] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may receive input data and perform a data preprocessing procedure (202). Data preprocessing may refer to the process of converting data into a form suitable for a model in machine learning and data analysis. Data preprocessing may be performed to improve data quality and enhance model performance. According to one embodiment, data preprocessing may include at least one of data cleaning, data transformation, data encoding, data sampling, feature selection and engineering, and dimensionality reduction.

[0082] The input data may include a time series (201). At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may perform an end-to-end procedure (203). In other words, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station may perform a procedure using a model that outputs what is received as input to a neural network. The end-to-end procedure may include at least one of a learning procedure (204), an inference procedure (204), or a scoring procedure (205). At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may output labels (206). The labels may include a time series. In other words, the output labels produced by the UE, terminal, or base station through an artificial intelligence model may include time series data indicating detected anomalies.

[0083] FIG. 2b is a block diagram illustrating an anomaly detection invention according to one embodiment of the present disclosure.

[0084] Referring to FIG. 2b, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station can collect link quality-related data (210). The link quality-related data may include time-series data. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform a data preprocessing procedure (220). In other words, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform data preprocessing through the link quality-related data. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform a learning and / or inference procedure through an unsupervised learning model (230). The unsupervised learning model can receive the preprocessed data as input. The unsupervised learning model can perform a learning and / or inference procedure using the preprocessed data. Unsupervised learning may be a machine learning method that finds patterns in a state where there are no labels (or correct answers) in the data. Unsupervised learning can be used to analyze the structure of data and find hidden patterns, relationships, or groups, and can be utilized primarily for tasks such as data exploration, preprocessing, clustering, and dimensionality reduction.

[0085] At least one of the electronic device, server, UE, terminal, network entity, AP, and base station may perform a model evaluation procedure to determine whether the model learned through training data has been well learned (240). The model evaluation procedure may include a method for evaluating the degree of model learning. At least one of the electronic device, server, UE, terminal, network entity, AP, and base station may perform a real-time monitoring procedure (250). In other words, at least one of the electronic device, server, UE, terminal, network entity, AP, and base station may perform a real-time monitoring procedure for a channel using the model. At least one of the electronic device, server, UE, terminal, network entity, AP, and base station may perform an anomaly detection procedure (260). In other words, at least one of the electronic device, server, UE, terminal, network entity, AP, and base station may perform an anomaly detection procedure using the real-time monitoring procedure.

[0086] The data preprocessing procedure may include a procedure for calculating input weights based on correlation coefficients. At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may calculate input weights based on correlation coefficients to resolve uncertainty caused by training data.

[0087] [Mathematical Formula 1]

[0088]

[0089] Is It may include feature values ​​for. Is It may include feature values ​​for. is a characteristic It can mean the average value of. Is It can mean the average value of. Is It can mean the standard deviation. Is It can mean the standard deviation. and Each can mean a characteristic.

[0090] [Mathematical Formula 2]

[0091]

[0092] can mean the correlation coefficient weight. can represent the correlation coefficient value. The data for resetting can be expressed as in Equation 3.

[0093] [Mathematical Formula 3]

[0094]

[0095] The input may include training data. The input may include data for resetting. can mean preprocessed data. It may include link quality-related data. It may include correlation coefficient weights.

[0096] FIG. 3 is a flowchart illustrating a model learning method according to one embodiment of the present disclosure.

[0097] Referring to FIG. 3, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may start pre-learning (310). Pre-learning may mean a procedure in which the first electronic device collects and / or learns parameters regarding the wireless channel environment with a second electronic device connected to the same AP. Pre-learning may include a procedure in which at least one of the electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station collects data and / or produces learning data. At least one of the electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may derive feature values ​​to be used for model learning (320). In other words, at least one of the electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may calculate feature values ​​used for learning the model of the wireless environment for a certain period of time.

[0098] At least one of the electronic device, server, UE, terminal, network entity, AP, and base station can perform preprocessing and assign learning weights to each variable (330). In other words, at least one of the electronic device, server, UE, terminal, network entity, AP, and base station can perform a preprocessing procedure for each variable. At least one of the electronic device, server, UE, terminal, network entity, AP, and base station can assign learning weights to each variable.

[0099] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can train an unsupervised learning model using collected features (340). In other words, an unsupervised learning model can be trained using collected features.

[0100] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform real-time monitoring and anomaly detection (350). In other words, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform real-time monitoring of the channel using a model. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform anomaly detection of the channel using a model.

[0101] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can detect at least one of a point anomaly, a collective anomaly, or a contextual anomaly through an anomaly detection procedure.

[0102] FIG. 4 is a conceptual diagram illustrating an example of an ideal value according to an embodiment of the present disclosure.

[0103] Referring to FIG. 4, FIG. 4(a) may include a point anomaly. A point anomaly may refer to an outlier at a specific point. A point anomaly may refer to an outlier occurring in a single data point. FIG. 4(b) may include a collective anomaly. A collective anomaly may refer to an outlier among two or more related data points. A collective anomaly may include an outlier considered abnormal data when data points in a dataset cluster into a specific group. FIG. 4(c) may include a contextual anomaly. A contextual anomaly may include an outlier appearing in a continuous change pattern. A contextual anomaly may include an outlier regarding a result that differs from the expected change when considering the context.

[0104] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may perform prior learning to detect outliers. Outliers may include at least one of point anomalies, collective anomalies, or contextual anomalies.

[0105] FIG. 5 is a block diagram illustrating a model inference method according to one embodiment of the present disclosure.

[0106] Referring to FIG. 5, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may receive a training input value or a test input value. The terminal (510) may include a home appliance. In other words, the terminal may include at least one of a training input value or a test input value. The training input value may include data input values ​​necessary for training a model included in the terminal or base station. The training input value It can be referred to as. The test input values ​​may include data input values ​​necessary for testing the trained model. The test input values ​​are It can be referred to as. Training input values ​​may include training input data. Test input values ​​may include test input data.

[0107] At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may include a model. The model included in the terminal or base station has learning input values ​​( Can receive ). The model included in the terminal or base station outputs the value ( Can receive ). Learning input value at the transmitting side ( ) is the output value at the receiving end ( It can be expressed as ). In other words, the output value ( ) is the input value after being transmitted through the wireless channel environment ( It can mean ). The terminal or base station input value ( ) and output value( A model (520) can be inferred based on ). The model (520) may include a model of a wireless channel environment described by a probability distribution through unsupervised learning. A terminal or base station can infer a new test input value ( ) can predict the output value after experiencing the wireless channel environment. At least one of the electronic device, server, UE, terminal, network entity, AP, and base station has a test input value ( Predicted output value through model (520) using ) ) can generate. The terminal or base station can generate the actual output value and the predicted output value ( Anomaly detection can be performed by comparing ). Wireless environment inference can be expressed as Equation 4.

[0108] [Mathematical Formula 4]

[0109]

[0110] At least one of the electronic device, server, UE, terminal, network entity, AP, and base station is a learning input value ( ) and output value( The model (520) can be inferred through ). The model (520) may be referred to as a channel model. The terminal or base station uses the model to obtain the predicted output value ( ) can infer. In other words, the terminal or base station gives the test input value ( to the inferred model ) can be transmitted. The inferred model (520) is a test input value ( Predicted output value using ) ) can generate. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can generate an actual output value and a predicted output value for a channel ( Anomaly detection can be performed by comparing ).

[0111] At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may be connected to a cloud server. The cloud server may transmit data for training a model. The cloud server may store data for training a model. The cloud server may transmit data for training a model to a terminal or a base station.

[0112] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can receive data transmitted by a cloud server. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can derive features to be used for learning a wireless environment model. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can derive features for a certain period of time. In other words, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform data collection regarding features for a certain period of time. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can collect data regarding transmission features of link quality. In other words, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station can collect data indicating link quality during the process of data transmission. The link quality indicated during the process of data transmission may be for the uplink or downlink. Data representing link quality during data transmission may refer to data having characteristics that vary over time. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may select the characteristics that vary over time. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may select and collect the characteristics that vary over time. The characteristics that vary over time may include time-series data.At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may include at least one of RSSI (received signal strength indication), SNR (signal noise ratio), PDR (packet delivery ratio), throughput, packet loss rate, channel utilization, retransmission rate, latency, or time series data.

[0113] RSSI can be expressed in units of dBm. SNR can be expressed in units of dB. Throughput can be expressed in units of Mbps. Packet loss rate can be expressed in units of %. Channel utilization can be expressed in units of %. Retransmission rate can be expressed in units of %. Latency can be expressed in units of ms.

[0114] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform a preprocessing procedure for each feature. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can assign learning weights to each feature. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can remove outliers from input data using 6-Sigma. Input data may include data that can be utilized in the preprocessing procedure. In other words, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station can identify outliers during the data preprocessing process. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can remove the identified outliers. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can utilize 6-Sigma (statistical technique) to remove the identified outliers. 6-Sigma or 6-Sigma statistical technique may refer to a method for detecting outliers when it is assumed that the data follows a normal distribution based on the mean (μ) and standard deviation (σ) of the data distribution.

[0115] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may preprocess data using Min-Max normalization to match the range between input data. The method of preprocessing data is not limited to the Min-Max normalization method. For example, if the RSSI value is -30dBm to -99dBm, the preprocessed RSSI value may be 0 to 1.

[0116] At least one of the electronic device, server, UE, terminal, network entity, AP, and base station has a learning weight for the feature value ( ) can be assigned. Learning weights( ) may include learning weights that reflect the correlation coefficients between features. In other words, at least one of the electronic device, server, UE, terminal, network entity, AP, and base station has learning weights that reflect the correlation coefficients between feature values ​​( ) can be assigned to the feature value.

[0117] FIG. 6 is a conceptual diagram illustrating a learning weight according to one embodiment of the present disclosure.

[0118] Referring to FIG. 6, the features may include at least one of RSSI, SNR, PDR, throughput feature a, or feature b. Feature a may be referred to as variable a. Feature b may be referred to as variable b.

[0119] The higher the absolute value of the correlation coefficient of a feature value, the more biased the results of the learning may be. The correlation coefficient of a feature value can indicate biased results in the learning. For example, the correlation coefficient between RSSI and PDR may be higher than the correlation coefficient between RSSI and SNR. The absolute value of the correlation coefficient between RSSI and PDR may be 0.33. The absolute value of the correlation coefficient between RSSI and SNR may be 0.31. The total correlation coefficient of RSSI may refer to the sum of the absolute values ​​of the correlation coefficients for SNR, throughput, feature a, and feature b. For example, in Figure 6, the total correlation coefficient of RSSI may be 1.28, which is 0.31 (absolute value of the correlation coefficient between RSSI and SNR) + 0.33 (absolute value of the correlation coefficient between RSSI and throughput) + 0.58 (absolute value of the correlation coefficient between RSSI and feature a) + 0.06 (absolute value of the correlation coefficient between RSSI and feature b). As another example, the overall correlation coefficient of feature b in Fig. 6 may be 0.496.

[0120] When using RSSI and PDR feature values, the model may exhibit biased learning results.

[0121] The correlation coefficients between features may differ. Features may have correlation coefficients with each other. When there are multiple feature values, learning weights may be assigned based on the sum of the absolute values ​​of the correlation coefficients of the feature values. The sum of the absolute values ​​of the correlation coefficients of the feature values ​​may represent the sum of the total correlation coefficients. For example, the sum of the absolute values ​​of the correlation coefficients of the feature values ​​in Fig. 6 may be 5.476.

[0122] The correlation coefficient can be calculated using the Pearson method or the Spearman method. The method for calculating the correlation coefficient is not limited to the Pearson or Spearman methods.

[0123] It can be expressed as in mathematical formula 1. Is and It can mean the correlation coefficient. Is and It can mean the covariance of. Is It can mean the standard deviation. Is It can mean the standard deviation. and Each can mean a characteristic. Is It may include feature values ​​for. Is It may include feature values ​​for. is a characteristic It can mean the average value of. Is It can mean the average value of.

[0124] The learning weight can be expressed through the above mathematical formula 2.

[0125] can mean learning weights or correlation coefficient weights. can mean the correlation coefficient or the correlation coefficient value.

[0126] In one embodiment, the learning weight of a feature may mean the value obtained by dividing the sum of the correlation coefficients of the feature by the sum of the total correlation coefficients. For example, the learning weight of RSSI may be 1.28 / 5.476. The sum of the correlation coefficients of RSSI may be 1.28. The sum of the total correlation coefficients may be 5.476.

[0127] FIG. 7 is a flowchart illustrating a learning method using a feature that is used as learning data in a device according to one embodiment of the present disclosure.

[0128] Referring to FIG. 7, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station can perform model training using collected features. The model may include an unsupervised learning model.

[0129] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can transmit preprocessed data to a model. The preprocessed data may include data in which feature values ​​have been preprocessed. The preprocessed data may include feature values ​​to which learning weights have been assigned. The model can receive a dataset of preprocessed feature values ​​(720). The model may include an artificial intelligence model. The model may include an unsupervised learning model.

[0130] The model can perform training on a default channel through the dataset. The default channel may include a 2.4 GHz channel and / or a 5 GHz channel. The model can perform training on a candidate channel through the dataset. The candidate channel may include a 2.4 GHz channel and / or a 5 GHz channel. The model can perform model training on a link-by-link basis for the default channel and / or candidate channel (730).

[0131] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may perform a model evaluation (740). When evaluating the model, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station may determine that the model evaluation is pass. When evaluating the model, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station may determine that the model evaluation is fail. If the terminal or base station determines that the model evaluation is pass, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station may terminate the model training. If the terminal or base station determines that the model evaluation is fail, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station may readjust the hyper-parameters of the model (750).

[0132] After readjusting the hyper-parameters, at least one of the electronic device, server, UE, terminal, network entity, AP, and base station can transmit the preprocessed data to the model.

[0133] FIG. 8 is a flowchart illustrating a monitoring method according to one embodiment of the present disclosure.

[0134] Referring to FIG. 8, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform real-time monitoring (810). At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can determine whether new pattern learning is required (820). In other words, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station can determine whether new patterns of feature values ​​for a channel need to be learned. If at least one of an electronic device, server, UE, terminal, network entity, AP, and base station determines that new pattern learning is required, it can reset the learning. If at least one of an electronic device, server, UE, terminal, network entity, AP, and base station identifies a new pattern during the real-time monitoring process, it can determine whether learning for the new pattern is required. If a terminal or base station determines that learning for the new pattern is required, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station can reset the learning. In other words, if a terminal or base station determines that learning about a new pattern is necessary, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may re-perform the learning procedure. If a terminal or base station determines that learning about a new pattern is necessary, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may reset the learning data. When at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station resets the learning data, it may perform a learning procedure. The learning procedure may include a procedure for learning using features collected in a model.The learning procedure may include at least one of a procedure for deriving variable values, a procedure for preprocessing and assigning learning weights, or a procedure for learning using variables collected in the model. Variables may be referred to as features or feature values.

[0135] At least one of the electronic device, server, UE, terminal, network entity, AP, and base station may determine that it is not a new pattern learning. If the terminal or base station determines that it is not a new pattern learning, at least one of the electronic device, server, UE, terminal, network entity, AP, and base station may perform anomaly detection (820). If the terminal or base station determines that it is not a new pattern learning, at least one of the electronic device, server, UE, terminal, network entity, AP, and base station may determine that the new pattern is an anomaly. If the terminal or base station determines that it is not a new pattern learning, at least one of the electronic device, server, UE, terminal, network entity, AP, and base station may perform a reconnection attempt procedure.

[0136] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can evaluate anomaly detection (850). At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can evaluate a detected anomaly or anomaly. If the anomaly detection evaluation fails, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station can change the channel to a candidate channel (860). At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform real-time monitoring by changing to a candidate channel.

[0137] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can evaluate anomaly detection. If the anomaly detection evaluation passes, at least one of the electronic device, server, UE, terminal, network entity, AP, and base station can perform a real-time monitoring procedure. In other words, if at least one of the electronic device, server, UE, terminal, network entity, AP, and base station performs an anomaly detection evaluation and no anomalies are detected, real-time monitoring can be performed. At least one of the electronic device, server, UE, terminal, network entity, AP, and base station can evaluate anomaly detection through reconnection.

[0138] FIG. 9 is a block diagram illustrating a method for transmitting features used as training data according to one embodiment of the present disclosure.

[0139] Referring to FIG. 9, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may perform data collection on a monitoring link. The monitoring link may include a link that the terminal or base station monitors. The data may include at least one of RSSI, SNR, PDR, throughput, packet loss rate, channel utilization, retransmission rate, latency, or time-series data. The terminal or base station may collect data on a default channel and / or a candidate channel. At least one of the electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may transmit the collected data to a cloud server. The data may include features or feature values.

[0140] The features are It can be represented as. can mean a feature or a feature value. can mean the collection time. can mean the number of features. The matrix of is at least one It may include. The cloud server is It can generate a matrix of. The cloud server is The matrix can generate a data frame for the link. For example, a cloud server Data frames for Link 1, Link 2, and Link 3 can be generated using the matrix. Link 1, Link 2, and Link 3 may each represent channel links over time. Link 1, Link 2, and Link 3 may each represent different links across channels. Link 1, Link 2, and Link 3 may represent the same link.

[0141] FIG. 10 is a conceptual diagram illustrating a method for preprocessing data according to one embodiment of the present disclosure.

[0142] Referring to FIG. 10, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may receive data for training from a cloud server. At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may perform a data preprocessing (min-max normalization) procedure for training. At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may apply weights to the preprocessed data. At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may apply weights to the preprocessed data. At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station may input the weighted data into a model as training data.

[0143] Data for learning may refer to collected data. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may receive the collected data transmitted by the cloud server in the form of a data frame (1010). At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may preprocess the data frame (1010). At least one of an electronic device, server, UE, terminal, network entity, AP, and base station may perform data preprocessing using Equation 5.

[0144] [Mathematical Formula 5]

[0145]

[0146] can mean a preprocessed value. can refer to the value in the data frame that is subject to preprocessing. can refer to feature values ​​in a data frame that are subject to preprocessing. can mean the minimum feature value in a data frame. can refer to the maximum feature value in a data frame. The minimum feature value can refer to the smallest value among the feature values ​​in a data frame. The maximum feature value can refer to the largest value among the feature values ​​in a data frame.

[0147] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can calculate correlation coefficient weights using preprocessed data. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can calculate correlation coefficients using Equation 1.

[0148] Is It may include feature values ​​for. Is It may include feature values ​​for. is a characteristic It can mean the average value of. Is It can mean the average value of. Is It can mean the standard deviation. Is It can mean the standard deviation. and Each can represent a characteristic. For example, regarding RSSI It could be 0.6614. In other words, the average of the RSSI could be 0.6614. Regarding SNR It could be 0.724. In other words, the average of the SNR could be 0.724. For example, the correlation coefficient between RSSI and SNR It can be as follows.

[0149]

[0150] Correlation coefficient between RSSI and SNR It can be -0.86225. Correlation coefficient between SNR and PDR It can be -0.0122. Correlation coefficient between PDR and RSSI It could be 0.00438.

[0151] In the case where at least one of an electronic device, server, UE, terminal, network entity, AP, and base station has multiple correlation coefficients, the weight can be obtained through the sum of the correlation coefficients of the i-th feature. In other words, the i-th feature may have correlations with multiple features. The correlation coefficient of the i-th feature can be calculated through the sum of the correlation coefficients with multiple features. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can calculate the weight of the i-th feature through the sum of the correlation coefficients of the i-th feature. The sum of the correlation coefficients of the i-th feature can be expressed as Equation 6.

[0152] [Mathematical Formula 6]

[0153]

[0154] can represent the sum of the correlation coefficients of the i-th feature. n can represent a natural number. k can represent an integer.

[0155] At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station can generate a correlation coefficient weight using a correlation coefficient value. The correlation coefficient weight is It may be referred to as. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can generate correlation coefficient weights using Equation 7.

[0156] [Mathematical Formula 7]

[0157]

[0158] can mean the input weight of the i-th feature. The input weight may include correlation coefficient weights. can mean the value for the sum of the correlation coefficients of the i-th feature. It can be referred to as the correlation coefficient or the sum of correlation coefficients. For example, the correlation coefficient weight of RSSI can be 0.00372. The correlation coefficient weight of SNR can be 0.26319. The correlation coefficient weight of PDR can be 0.733086.

[0159] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can reshape the preprocessed data. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can reshape the preprocessed data for dimensionality reduction. The data for reshape may include the preprocessed data. The preprocessed data may be referred to as the normalized input.

[0160] The preprocessed input value may include the preprocessed input value of the i-th feature. The preprocessed input value is It can be represented as follows. The data for resetting can be referred to as the resetting input. The resetting input consists of the preprocessed input and the correlation coefficient weights ( It can be calculated by multiplying by ). The data for reset can be expressed as in mathematical formula 3.

[0161] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can apply a correlation coefficient weight by multiplying the preprocessed input value by the correlation coefficient weight.

[0162] FIG. 11 is a conceptual diagram illustrating a model evaluation method according to one embodiment of the present disclosure.

[0163] Referring to FIG. 11, at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station can transmit input data to a model. The model can learn from the input data transmitted by the terminal or the base station. At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station can evaluate the learned model. At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station can perform model validation evaluation using TaPR (Time-Series Aware Precision and Recall) scoring. At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station can use TaPR (Time-Series Aware Precision and Recall) scoring as a test score. At least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station can perform model validation evaluation using an F1 score. At least one of the electronic device, server, UE, terminal, network entity, AP, and base station can use the F1 score as a test score.

[0164] Time-Series Aware Precision (TaP) indicates whether prediction results can detect anomalies without false positives. Time-Series Aware Recall (TaR) indicates whether various attack ranges can be identified. In other words, Time-Series Aware Recall (TaR) indicates whether various anomalies can be detected.

[0165] The F1 score may represent the evaluation score based on the precision and recall of the test. The F1 score can be expressed as shown in Equation 8.

[0166] [Mathematical Formula 8]

[0167]

[0168] F1 Score can refer to the F1 score. Recall can refer to recall rate. Precision can refer to precision.

[0169] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform model evaluation through TaPR. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can determine model evaluation through Table 1.

[0170] [Table 1]

[0171]

[0172] a can represent an index range in which anomalies appear. In other words, when an anomaly is detected, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station may have the same value of a.

[0173] may mean the result predicted by the terminal or base station through Method 1. It can have high TaP (precision) and high TaR (recall).

[0174] may mean the result predicted by the terminal or base station through Method 2. It may have high TaP (precision) and low TaR (recall). Method 2 may have a short detection time and a short failure alarm.

[0175] may mean the result predicted by the terminal or base station through method 3. It may have low TaP (precision) and high TaR (recall). Method 3 may have a long detection time and a long failure alarm.

[0176] may mean the result predicted by the terminal or base station through method 4. It may have low TaP (precision) and low TaR (recall).

[0177] At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform anomaly detection. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform anomaly detection using a trained model. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can perform anomaly detection during real-time monitoring. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can attempt channel reconnection when an anomaly is detected. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can resume monitoring after the reconnection attempt. At least one of an electronic device, server, UE, terminal, network entity, AP, and base station can change the channel to a candidate channel when an anomaly is detected. For example, at least one of an electronic device, server, UE, terminal, network entity, AP, and base station can change to a candidate channel by band if an anomaly is detected for a long period of time. A long duration anomaly may mean an anomaly occurring for 3000ms or longer. If at least one of an electronic device, server, UE, terminal, network entity, AP, and base station detects a long duration anomaly, Channel 6 in the 2.4GHz band may be changed to Channel 11. If at least one of an electronic device, server, UE, terminal, network entity, AP, and base station detects a long duration anomaly, Channel 36 in the 5GHz band may be changed to Channel 44.

[0178] FIG. 12 is a block diagram illustrating the structure of a first electronic device according to one embodiment of the present disclosure.

[0179] Referring to FIG. 12, the first electronic device of FIG. 12 may be implemented as a base station and a terminal, electronic device, or base station illustrated in FIG. 1 to FIG. 11.

[0180] Referring to FIG. 12, the first electronic device (1201) may include a transceiver (1202), a processor (1203), and a memory (1204). The first electronic device (1201) may include at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station. In the present disclosure, the control unit may be defined as a circuit or an application-specific integrated circuit or at least one processor.

[0181] The transceiver (1202) can transmit and receive signals with an external electronic device.

[0182] The processor (1203) can control the overall operation of the electronic device according to the embodiment proposed in the present disclosure. For example, the processor (1203) can control the signal flow between each block to perform operations according to the flowchart described above. Specifically, the processor (1203) can control the operation of the first electronic device illustrated in FIGS. 1 to 11, for example.

[0183] The memory (1204) can store at least one of the information transmitted and received through the transceiver (1202) and the information generated through the processor (1203).

[0184] FIG. 13 is a block diagram illustrating the structure of a second electronic device according to one embodiment of the present disclosure. The second electronic device of FIG. 13 may be implemented as a terminal, electronic device, or base station shown in FIG. 1 to FIG. 11.

[0185] Referring to FIG. 13, the second electronic device (1301) may include a transceiver (1302), a processor (1303), and a memory (1304). The second electronic device (1301) may include at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, and a base station. In the present disclosure, the processor may be defined as a circuit or an application-specific integrated circuit or at least one processor.

[0186] The transceiver (1302) can transmit and receive signals with an external electronic device.

[0187] The processor (1303) can control the overall operation of the electronic device according to the embodiment proposed in the present disclosure. For example, the processor (1303) can control the signal flow between each block to perform operations according to the flowchart described above. Specifically, the processor (1303) can control, for example, the base station or electronic device illustrated in FIGS. 1 to 11.

[0188] The memory (1304) can store at least one of the information transmitted and received through the transceiver (1302) and the information generated through the processor (1320).

[0189] It should be noted that the system configuration diagrams, method example diagrams, device configuration diagrams, etc., illustrated in FIGS. 1 to 13 above are not intended to limit the scope of the rights of the present disclosure. That is, all configurations or operations described in FIGS. 1 to 13 above should not be interpreted as essential components for the implementation of the present disclosure, and may be implemented within a scope that does not impair the essence of the present disclosure even if only some components are included.

[0190] A method of operation of a first electronic device for performing wireless communication may include: collecting at least one feature information for at least one wireless channel used by the first electronic device during communication; generating at least one preprocessed feature information using the at least one feature information; generating at least one correlation coefficient weight reflecting the influence between feature information using the at least one preprocessed feature information; generating training data using the at least one preprocessed feature information and the at least one correlation coefficient weight; training an unsupervised learning model using the training data; and performing real-time monitoring and anomaly detection for the at least one wireless channel using the model.

[0191] The first electronic device may include at least one of a server, a UE (user equipment), a terminal, a network entity, an AP (access point), or a base station.

[0192] The above at least one correlation coefficient weight can be generated using a correlation coefficient representing the relationship between feature information.

[0193] The above at least one feature information may include at least one of RSSI (received signal strength indication), SNR (signal noise ratio), PDR (packet delivery ratio), throughput, packet loss rate, channel utilization, retransmission rate, latency, or time series data.

[0194] The method of the first electronic device may include the step of transmitting the at least one feature information to a cloud server, and the step of receiving a data frame containing the at least one feature information from the cloud server.

[0195] The method of the first electronic device may include the step of calculating an evaluation score using recall or precision for the model with respect to the at least one wireless channel.

[0196] The step of performing real-time monitoring and anomaly detection for at least one wireless channel using the above model may include: performing the monitoring using the above model; determining whether learning is required for a new pattern detected through the monitoring; performing anomaly detection for the new pattern and reconnecting the channel; and evaluating the anomaly detection and changing it to a candidate channel.

[0197] A method of operation of a second electronic device performing wireless communication may include the steps of receiving at least one feature information for at least one wireless channel from a first electronic device, generating at least one data frame for the at least one wireless channel using the at least one feature information, and transmitting the at least one data frame to the first electronic device.

[0198] The second electronic device may include at least one of a server, a UE (user equipment), a terminal, a network entity, an AP (access point), or a base station.

[0199] The method of the second electronic device may include the steps of: generating at least one preprocessed feature information using at least one feature information; generating at least one correlation coefficient weight reflecting the influence between feature information using at least one preprocessed feature information; and generating training data using at least one preprocessed feature information and the correlation coefficient weight.

[0200] A first electronic device for performing wireless communication includes a transceiver and a control unit, and the control unit may be configured to collect at least one feature information for at least one wireless channel used by the first electronic device for communication, generate at least one preprocessed feature information using the at least one feature information, generate at least one correlation coefficient weight reflecting the influence between feature information using the at least one preprocessed feature information, generate training data using the at least one preprocessed feature information and the at least one correlation coefficient weight, train an unsupervised learning model using the training data, and perform real-time monitoring and anomaly detection for the at least one wireless channel using the model.

[0201] The first electronic device may include at least one of a server, a UE (user equipment), a terminal, a network entity, an AP (access point), or a base station.

[0202] The above at least one correlation coefficient weight can be generated using a correlation coefficient representing the relationship between feature information.

[0203] The above at least one feature information may include at least one of RSSI (received signal strength indication), SNR (signal noise ratio), PDR (packet delivery ratio), throughput, packet loss rate, channel utilization, retransmission rate, latency, or time series data.

[0204] The control unit can transmit the at least one feature information to a cloud server and receive a data frame containing the at least one feature information from the cloud server.

[0205] The control unit above may be configured to calculate an evaluation score for the model using recall or precision for at least one wireless channel.

[0206] The control unit may be configured to perform the monitoring using the model, determine whether learning is required for a new pattern detected through the monitoring, perform anomaly detection for the new pattern to reconnect the channel, and evaluate the anomaly detection to change it to a candidate channel.

[0207] A second electronic device for performing wireless communication includes a transceiver and a control unit, wherein the control unit may be configured to receive at least one feature information for at least one wireless channel from a first electronic device, generate at least one data frame for at least one wireless channel using the at least one feature information, and transmit the at least one data frame to the first electronic device.

[0208] The second electronic device may include at least one of a server, a UE (user equipment), a terminal, a network entity, an AP (access point), or a base station.

[0209] The control unit may be configured to generate at least one preprocessed feature information using at least one feature information, generate at least one correlation coefficient weight reflecting the influence between feature information using at least one preprocessed feature information, and generate training data using at least one preprocessed feature information and the correlation coefficient weight.

[0210] Methods according to the claims or embodiments described in the specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

[0211] When implemented in software, a computer-readable storage medium may be provided for storing one or more programs (software modules). One or more programs stored in the computer-readable storage medium are configured for execution by one or more processors within an electronic device. One or more programs may include instructions that cause the electronic device to execute methods according to the claims or embodiments described in the specification of this disclosure.

[0212] Such programs (software modules, software) may be stored in random access memory, non-volatile memory including flash memory, ROM (Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), magnetic disc storage devices, CD-ROM (Compact Disc-ROM), Digital Versatile Discs (DVDs), or other forms of optical storage devices, magnetic cassettes. Alternatively, they may be stored in memory composed of some or all of these. Additionally, each constituent memory may include multiple units.

[0213] Additionally, the program may be stored on an attachable storage device accessible via a communication network such as the Internet, Intranet, Local Area Network (LAN), Wide LAN (WLAN), or Storage Area Network (SAN), or a combination thereof. Such a storage device may be connected to a device performing an embodiment of the present disclosure through an external port. Additionally, a separate storage device on a communication network may be connected to a device performing an embodiment of the present disclosure.

[0214] In the specific embodiments of the present disclosure described above, the components included in the present disclosure are expressed in a singular or plural form according to the specific embodiments presented. However, the singular or plural expression is selected to suit the situation presented for convenience of explanation, and the present disclosure is not limited to singular or plural components; even if a component is expressed in the plural form, it may be composed in the singular form, and even if a component is expressed in the singular form, it may be composed in the plural form.

Claims

1. A method performed by a first electronic device that performs wireless communication, A step of collecting feature values ​​of features for at least one wireless channel used by the first electronic device for communication; A step of generating preprocessed feature values ​​using the feature values ​​of the above features; A step of generating correlation coefficient weights of the features that reflect the influence between the features based on the preprocessed feature values; A step of generating training data using the above-mentioned preprocessed feature values ​​and the above-mentioned correlation coefficient weights; A step of training an unsupervised learning model using the above training data; and A method comprising the step of performing real-time monitoring and anomaly detection of at least one wireless channel using the above model.

2. In Paragraph 1, The above-mentioned first electronic device is at least one of a server, a UE (user equipment), a terminal, a network entity, an AP (access point), or a base station.

3. In paragraph 1, the at least one correlation coefficient weight is A method generated using correlation coefficients representing the relationships between features.

4. In paragraph 1, the above features are, A method comprising at least two of RSSI (received signal strength indication), SNR (signal noise ratio), PDR (packet delivery ratio), throughput, packet loss rate, channel utilization, retransmission rate, latency, or time series data.

5. In Paragraph 1, The step of transmitting at least one of the above features to a cloud server; and A method further comprising the step of receiving a data frame including at least one feature from the cloud server.

6. In Paragraph 1, A method further comprising the step of calculating an evaluation score using recall or precision for the above model for at least one wireless channel.

7. In Paragraph 1, The step of performing real-time monitoring and anomaly detection for at least one wireless channel using the above model is: A step of performing the monitoring using the above model; A step of determining whether learning is required for new patterns detected through the above monitoring; A step of performing anomaly detection on the new pattern and performing reconnection of the channel; A method comprising the step of evaluating the above anomaly detection and changing to a candidate channel.

8. In a method of operation performed by a second electronic device that performs wireless communication, A step of receiving feature values ​​of features for at least one wireless channel from a first electronic device; A step of generating at least one data frame for at least one wireless channel using the feature values ​​of the above features; and A method comprising the step of transmitting at least one data frame to the first electronic device.

9. In Paragraph 8, The method wherein the second electronic device is at least one of a server, a UE (user equipment), a terminal, a network entity, an AP (access point), or a base station.

10. In Paragraph 8, The method of the second electronic device above is, A step of generating preprocessed feature values ​​using the feature values ​​of the above features; A step of generating correlation coefficient weights of the features that reflect the influence between the features based on the preprocessed feature values; A method comprising the step of generating training data using the above-mentioned preprocessed feature values ​​and the above-mentioned correlation coefficient weights.

11. In a first electronic device that performs wireless communication, Transmitter / receiver; and It includes a control unit, and the control unit, The first electronic device collects feature values ​​of features for at least one wireless channel used for communication, and Generate preprocessed feature values ​​using the feature values ​​of the above features, and Based on the above preprocessed feature values, correlation coefficient weights of the features are generated to reflect the influence between the features, and Training data is generated using the above-mentioned preprocessed at least one feature information and the above-mentioned at least one correlation coefficient weight, and Using the above training data, an unsupervised learning model is trained, and A first electronic device configured to perform real-time monitoring and anomaly detection of at least one wireless channel using the above model.

12. In Paragraph 11, The first electronic device is at least one of a server, a UE (user equipment), a terminal, a network entity, an AP (access point), or a base station.

13. In paragraph 11, the above at least one correlation coefficient weight is A first electronic device generated using a correlation coefficient representing the relationship between features.

14. In Paragraph 11, the above features are, A first electronic device comprising at least two of RSSI (received signal strength indication), SNR (signal noise ratio), PDR (packet delivery ratio), throughput, packet loss rate, channel utilization, retransmission rate, latency, or time series data.

15. In a second electronic device that performs wireless communication, Transmitter / receiver; and It includes a control unit, and the control unit, Receiving feature values ​​of features for at least one wireless channel from a first electronic device, and Using the feature values ​​of the above features, at least one data frame for the at least one wireless channel is generated, and A second electronic device configured to transmit at least one data frame to the first electronic device.

Images