Method and apparatus for adjusting ranging area using ultra-wideband communication signal

Abstract

The invention discloses a method for an electronic device to adjust a door distance measurement area. A method according to the present disclosure may comprise the steps of: acquiring LOS probability data based on a DL-TDoA signal received from at least one UWB anchor point by using a trained first convolutional neural network (CNN) model; obtaining an average LOS probability based on the LOS probability data; determining whether the electronic device exists in the LOS environment based on the average LOS probability; maintaining the initially established door access area if the electronic device is present in the LOS environment; and if the electronic device is present in the LOS environment, adjusting the gate access area according to a value of the average LOS probability. Here, the door access area may be an area where the electronic device and the door device initiate DS-TWR ranging for the transaction.

Description

Technical Field

[0001] The present disclosure relates to methods and apparatus for adjusting a ranging area using an ultra-wideband (UWB) signal. Background Art

[0002] The Internet is evolving from a human-centric connected network where humans create and consume information to an Internet of Things (IoT) network where information is transmitted and processed between things or other distributed components. Another emerging technology is the Internet of Everything (IoE), which is a combination of big data processing technology and IoT technology through, for example, connections to cloud servers. Implementing IoT requires technical elements such as sensing technology, wired / wireless communication and network infrastructure, service interfaces, and security technology. Recent ongoing research on object-to-object connectivity focuses on technologies for sensor networking, machine-to-machine (M2M), or machine-type communications (MTC).

[0003] In the IoT environment, intelligent Internet technology (IT) services can be provided that collect and analyze data generated by connected objects to create new value for human life. IoT can have various applications such as smart homes, smart buildings, smart cities, smart cars or connected cars, smart grids, healthcare, or smart appliance industries or advanced medical services through the transformation or integration of conventional information technology (IT) technologies and various industries. Summary of the invention

[0004] Technical issues The present disclosure provides a method and apparatus for adjusting a door access zone using a UWB signal.

[0005] In addition, the present disclosure provides a method 2 and an apparatus for adjusting a gate area using a UWB signal.

[0006] Solution to the problem According to various embodiments of the present disclosure, a method for using UWB communication by an electronic device may include: obtaining LOS probability data using a trained first convolutional neural network (CNN) model based on a DL-TDoA signal received from at least one UWB anchor point; obtaining an average LOS probability based on the LOS probability data; determining whether the electronic device is in a LOS environment based on the average LOS probability; maintaining an initially set door access area when the electronic device is in the LOS environment; and adjusting the door access area according to the value of the average LOS probability when the electronic device is in the LOS environment. The door access area may be an area where the electronic device initiates DS-TWR ranging for a transaction with a door device.

[0007] According to various embodiments of the present disclosure, an electronic device using UWB communication may include a transceiver and a controller connected to the transceiver. The controller may be configured to: obtain LOS probability data using a trained first convolutional neural network (CNN) model based on a DL-TDoA signal received from at least one UWB anchor point; obtain an average LOS probability based on the LOS probability data; determine whether the electronic device is in a LOS environment based on the average LOS probability; maintain an initially set door access area when the electronic device is in the LOS environment; and adjust the door access area according to the value of the average LOS probability when the electronic device is in the LOS environment. The door access area may be an area where the electronic device initiates DS-TWR ranging for a transaction with a door device. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 is a block diagram schematically illustrating an electronic device.

[0009] Figure 2a An example architecture of a UWB device according to an embodiment of the present disclosure is shown.

[0010] Figure 2b An example configuration of a framework of a UWB device according to an embodiment of the present disclosure is shown.

[0011] Figure 3a An example of UWB CIR data according to an embodiment of the present disclosure is shown.

[0012] Figure 3b An example of valid UWB CIR data according to an embodiment of the present disclosure is shown.

[0013] Figure 3c An example of LOS signals and NLOS signals classified using UWB CIR data according to an embodiment of the present disclosure is shown.

[0014] Figure 4 A DS-TWR according to an embodiment of the present disclosure is shown.

[0015] Figure 5 A DL-TDoA according to an embodiment of the present disclosure is shown.

[0016] Figure 6 The training process and distribution process of LOS / NLOS signal classification using UWB channel impulse response data according to an embodiment of the present disclosure are shown.

[0017] Figure 7 A configuration of a user equipment for LOS / NLOS classification according to an embodiment of the present disclosure is shown.

[0018] Figure 8 The training process of posture classification based on LOS / NLOS signal classification using UWB channel impulse response data according to an embodiment of the present disclosure is shown.

[0019] Fig. 9 The distribution process of posture classification based on LOS / NLOS signal classification using UWB channel impulse response data according to an embodiment of the present disclosure is shown.

[0020] Fig.10 A configuration of a user equipment for pose classification using LOS / NLOS classification according to an embodiment of the present disclosure is shown.

[0021] Fig.11 An example architecture of a system for providing a UWB-based gate service according to an embodiment of the present disclosure is shown.

[0022] Fig.12 An example operation scenario of a gate system according to an embodiment of the present disclosure is shown.

[0023] Fig.13 The intelligent door service process of the door system according to the embodiment of the present disclosure is shown.

[0024] Fig.14 A door environment according to an embodiment of the present disclosure is shown.

[0025] Fig.15 The problem occurring in a door environment according to an embodiment of the present disclosure is exemplarily illustrated.

[0026] Fig.16a A method for setting an adaptive door access zone in a door environment according to an embodiment of the present disclosure is shown.

[0027] Fig.16b An example of a door access area expanded according to an adaptive door access area setting method in a door environment according to an embodiment of the present disclosure is shown.

[0028] Fig.17 A door access area ratio according to LOS probability according to an embodiment of the present disclosure is shown.

[0029] Fig.18a and Fig.18b A method for setting a maximum expandable area for setting an adaptive door access area in a door environment according to an embodiment of the present disclosure is shown.

[0030] Fig.19aA method for setting an adaptive door access area using a maximum expandable area in a door environment according to an embodiment of the present disclosure is shown.

[0031] Fig.19b An example of a door access area expanded according to an adaptive door access area setting method in a door environment according to an embodiment of the present disclosure is shown.

[0032] Fig.20a A method for setting an adaptive door access area using a maximum expandable area in a door environment according to an embodiment of the present disclosure is shown.

[0033] Fig.20b An example of a door access area expanded according to an adaptive door access area setting method in a door environment according to an embodiment of the present disclosure is shown.

[0034] Fig.21 A method for setting an adaptive gate area according to an embodiment of the present disclosure is shown.

[0035] Fig. 22 An example of a door area set according to an adaptive door area setting method in a door environment according to an embodiment of the present disclosure is shown.

[0036] Fig.23 is a view showing a structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] Hereinafter, embodiments of the present disclosure are described in detail with reference to the accompanying drawings.

[0038] When describing the embodiments, descriptions of technologies known in the art that are not directly related to the present invention are omitted. This is used to further clarify the main points of the present disclosure without making it unclear.

[0039] For the same reason, some elements may be exaggerated or schematically shown. The size of each element does not necessarily reflect the actual size of the element. In the entire drawings, the same reference numerals are used to refer to the same elements.

[0040] The advantages, effects and features of the present disclosure and the methods for achieving these advantages and features can be understood by the embodiments described below in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed herein, and various changes can be made thereto. The embodiments disclosed herein are only provided to inform those of ordinary skill in the art of the categories disclosed herein. The present invention is limited only by the appended claims. Throughout the specification, the same reference numerals represent the same elements.

[0041] It should be understood that the combination of the blocks and flowcharts in each flowchart can be performed by computer program instructions. Since the computer program instructions can be equipped in a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, the instructions executed by the processor of the computer or other programmable data processing device generate components for performing the functions described in conjunction with (one or more) blocks of each flowchart. Since the computer program instructions can be stored in a computer-usable or computer-readable memory, which can be directed to a computer or other programmable data processing device to implement functions in a specified manner, the instructions stored in the computer-usable or computer-readable memory can produce a product including instruction components for performing the functions described in conjunction with the blocks in each flowchart. Since the computer program instructions can be equipped in a computer or other programmable data processing device, the instructions that generate the process run by the computer as a series of operating steps are executed on the computer or other programmable data processing device, and the operating computer or other programmable data processing device can provide steps for running the functions described in conjunction with (one or more) blocks in each flowchart.

[0042] In addition, each box can represent a module, a fragment or a portion of a code including one or more executable instructions for running a specified (one or more) logical function. In addition, it should also be noted that in some alternative embodiments, the functions mentioned in the box can occur in different orders. For example, two boxes shown in succession can be executed substantially simultaneously or in reverse order according to the corresponding functions.

[0043] As used herein, the term "unit" refers to a software element or a hardware element, such as a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC). The unit plays a specific role. However, the "unit" is not limited to software or hardware. The "unit" can be configured in a storage medium that can be addressed or can be configured to run one or more processors. Therefore, as an example, the "unit" includes the following elements: such as software elements, object-oriented software elements, class elements, and task elements, processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcodes, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided in the components and "units" can be combined into a smaller number of components and "units", or further divided into additional components and "units". In addition, the components and "units" can be implemented as running one or more CPUs in a device or a secure multimedia card. According to an embodiment of the present disclosure, the "···unit" can include one or more processors.

[0044] As used herein, the term "terminal" or "device" may also be referred to as a mobile station (MS), a user equipment (UE), a user terminal (UT), a terminal, a wireless terminal, an access terminal (AT), a user unit, a subscriber station (SS), a wireless device, a wireless communication device, a wireless transmission / reception unit (WTRU), a mobile node or a mobile device, or may be referred to by other terms. Various embodiments of the terminal may include a cellular phone, a smart phone with wireless communication capabilities, a personal digital assistant (PDA) with wireless communication capabilities, a wireless modem, a portable computer with wireless communication capabilities, a capture / recording / shooting / photography device (such as a digital camera) with wireless communication capabilities, a game console with wireless communication capabilities, a music storage and playback home appliance with wireless communication capabilities, an Internet home appliance capable of wireless Internet access and browsing, or a portable unit or terminal integrating a combination of these capabilities. Further, the terminal may include a machine-to-machine (M2M) terminal and a machine type communication (MTC) terminal / device, but is not limited thereto. In the present disclosure, a terminal may be referred to as an electronic device or simply a device.

[0045] The working principle of the present disclosure is described below in conjunction with the accompanying drawings. When describing the embodiments of the present disclosure, when it is determined that the subject matter of the present disclosure is unnecessarily obscure, the detailed description of known functions or configurations can be skipped. The terms used herein are defined under the premise of considering the functions in the present disclosure, and can be replaced with other terms according to the intention or practice of the user or operator. Therefore, the terms should be defined based on the overall disclosure.

[0046] Hereinafter, embodiments of the present invention are described in detail with reference to the accompanying drawings. In addition, although a communication system using UWB is described in conjunction with an embodiment of the present invention, as an example, the embodiments of the present invention may also be applied to other communication systems having similar technical backgrounds or features. For example, a communication system using Bluetooth or ZigBee may be included in an embodiment of the present invention. In addition, the embodiments of the present invention may be modified without significantly departing from the scope of the present invention, and such modifications may be applicable to other communication systems, as determined by a person of ordinary skill in the art.

[0047] When it is determined that the subject matter of the present invention will be unclear, the detailed description of known technologies or functions can be skipped. The terms used herein are defined under the premise of considering the functions in the present disclosure, and can be replaced with other terms according to the intention or practice of the user or operator. Therefore, the terms should be defined based on the overall disclosure.

[0048] Generally speaking, wireless sensor network technology is mainly divided into wireless local area network (WLAN) technology and wireless personal area network (WPAN) technology according to the recognition distance. In this case, WLAN is a technology based on IEEE 802.11, which enables access to the backbone network within a radius of about 100m. WPAN is a technology based on IEEE802.15 including Bluetooth, ZigBee and ultra-wideband (UWB). A wireless network that implements this wireless network technology may include multiple electronic devices.

[0049] According to the definition of the Federal Communications Commission (FCC), UWB can refer to wireless communication technology that uses a bandwidth of 500 MHz or more or a bandwidth corresponding to more than 20% of the center frequency. UWB can refer to the frequency band itself to which UWB communication is applied. UWB can achieve secure and accurate ranging between devices. Therefore, UWB achieves relative position estimation based on the distance between two devices, or achieves accurate position estimation of a device based on the distance from a fixed device (whose position is known).

[0050] The terms used herein are provided for a better understanding of the present disclosure and may be changed without departing from the technical principles of the present disclosure.

[0051] An "application specific file (ADF)" may be, for example, a data structure within an application data structure that may carry an application or application specific data.

[0052] An "application protocol data unit (APDU)" may be a command and response used when communicating with an application data structure in a UWB device.

[0053] “Application specific data” may be, for example, a file structure having a root level and an application level, the application level including UWB slave information and UWB session data required for a UWB session.

[0054] A "Controller" may be a ranging device that defines and controls ranging control messages (RCMs) (or control messages). A controller may define and control ranging characteristics by sending control messages.

[0055] A "controlee" may be a ranging device that uses ranging parameters in an RCM (or control message) received from a controller. A controlee may use the same ranging features as those configured by a control message from a controller.

[0056] Unlike "static STS", "dynamic scrambled timestamp sequence (STS) mode" may be an operation mode in which STS is not repeated during a ranging session. In this mode, STS may be managed by the ranging device, and the ranging session key generating STS may be managed by the security component.

[0057] An "applet" may be, for example, a small program that runs on a secure component and includes UWB parameters and service data. The applet may be a FiRa applet.

[0058] A “ranging device” may be a device capable of performing UWB ranging. In the present disclosure, the ranging device may be an enhanced ranging device (ERDEV) or a FiRa device defined in IEEE 802.15.4z. The ranging device may be referred to as a UWB device.

[0059] A "UWB-enabled Application" may be an application for UWB services. For example, a UWB-enabled application may be an application that uses a framework API to configure an OOB connector, security services, and / or UWB services for a UWB session. A "UWB-enabled application" may be abbreviated as an application or a UWB application. A UWB-enabled application may be a FiRa-enabled application.

[0060] A "Framework" may be a component that provides profile access, standalone-UWB configuration and / or notification. A "Framework" may be a collection of logical software components including, for example, a profile manager, an OOB connector, security services and / or UWB services. A Framework may be a FiRa Framework.

[0061] An "OOB Connector" may be a software component for establishing an out-of-band (OOB) connection (eg, a BLE connection) between ranging devices. The OOB Connector may be a FiRa OOB Connector.

[0062] A "Profile" may be a collection of previously defined UWB and OOB configuration parameters. A profile may be a FiRa profile.

[0063] A "Profile Manager" may be a software component that implements profiles available on a ranging device. The Profile Manager may be a FiRa Profile Manager.

[0064] A "Service" can be an implementation of a use case that provides a service to an end user.

[0065] A "Smart Ranging Device" may be a ranging device that may implement an optional framework API. A Smart Ranging Device may be a FiRa Smart Device.

[0066] A "Global Private File (GDF)" may be the root level of application-specific data that includes data needed to establish a USB session.

[0067] A "Framework API" may be an API used by UWB-enabled applications to communicate with the framework.

[0068] An “Initiator” may be a ranging device that initiates a ranging exchange. The initiator may initiate a ranging exchange by sending a first RFRAME (ranging exchange message).

[0069] An "object identifier (OID)" may be an identifier of an ADF in an application data structure.

[0070] "Out-of-band (OOB)" may be data communications that do not use UWB as the underlying wireless technology.

[0071] A "Ranging Data Set (RDS)" may be data required to establish a UWB session when confidentiality, authenticity, and integrity need to be protected (eg, UWB session key, session ID, etc.).

[0072] A "responder" may be a ranging device that responds to an initiator in a ranging exchange. A responder may respond to a ranging exchange message received from an initiator.

[0073] "STS" may be an encryption sequence used to improve the integrity and accuracy of the ranging measurement timestamp. The STS may be generated based on the ranging session key.

[0074] A "secure channel" may be a data channel that is protected from eavesdropping and tampering.

[0075] A “Secure component” may be an entity with a defined security level (eg, a secure element (SE) or a trusted execution environment (TEE)) that interacts with the UWBS for the purpose of providing RDS to the UWBS, for example, when using dynamic STS.

[0076] “SE” may be a tamper-resistant secure hardware component that may be used as a secure component in a ranging device.

[0077] "Secure ranging" can be STS-based ranging generated through strong cryptographic operations.

[0078] A “Secure Service” may be a software component used to interact with a secure component (such as a secure element or TEE).

[0079] A "Service Applet" may be a small program on a secure component that handles service-specific transactions.

[0080] “Service Data” may be data defined by a service provider that needs to be transmitted between two ranging devices to implement a service.

[0081] A "Service Provider" can be an entity that defines and provides the hardware and software required to deliver a specific service to end users.

[0082] "Static STS mode" is an operating mode in which the STS is repeated during a session and does not need to be managed by the security component.

[0083] A "Secure UWB Service (SUS) applet" may be an applet on the SE that communicates with the applet to retrieve data needed to implement a secure UWB session with other ranging devices. The SUS applet may transmit the corresponding data (information) to the UWBS.

[0084] A "UWB Service" may be a software component that provides access to the UWB S.

[0085] A "UWB Session" may be a period of time from when a controller and a controlled device start communicating via UWB until the communication stops. A UWB Session may include ranging, data transmission, or both ranging and data transmission.

[0086] “UWB Session ID” may be an ID (eg, a 32-bit integer) that is shared between the controller and the controlled device and identifies a UWB session.

[0087] A "UWB session key" may be a key for protecting a UWB session. The UWB session key may be used to generate an STS. The UWB session key may be a UWB ranging session key (URSK) and may be abbreviated as a session key.

[0088] A "UWB subsystem (UWBS)" may be a hardware component that implements the UWB PHY and MAC layer specifications. The UWBS may have an interface to the framework and an interface to the security component to search for RDS.

[0089] A "UWB message" may be a message including a payload IE sent by a UWB device (e.g., ERDEV). A UWB message may be a message such as, for example, a ranging initiation message (RIM), a ranging response message (RRM), a ranging final message (RFM), a control message (CM), a measurement report message (MRM), a ranging result report message (RRRM), a control update message (CUM), or a one-way ranging (OWR) message. If desired, multiple messages may be combined into one message.

[0090] "OWR" may be a ranging scheme that uses messages transmitted unidirectionally between a ranging device and one or more other ranging devices. OWR may be used to measure time difference of arrival (TDoA). Additionally, OWR may be used to measure AoA at the receiving end instead of measuring TDoA. In this case, a pair of advertising end and observing end may be used.

[0091] "TWR" may be a ranging scheme that can estimate the relative distance between two devices by measuring the time of flight (ToF) by exchanging ranging messages between the two devices. The TWR scheme may be one of a double-sided two-way ranging (DS-TWR) and a single-sided two-way ranging (SS-TWR). SS-TWR may be a process for performing ranging through one round-trip time measurement. For example, SS-TWR may include a RIM transmission operation from an initiator to a responder, and an RRM transmission operation from a responder to an initiator. DS-TWR may be a process for performing ranging through two round-trip time measurements. For example, DS-TWR may include a RIM transmission operation from an initiator to a responder, an RRM transmission operation from a responder to an initiator, and an RFM transmission operation from an initiator to a responder. Through the ranging exchange, the time of flight (ToF) can be calculated, and the distance between the two devices can be estimated. At the same time, during the TWR process, the measured AoA information (e.g., AoA azimuth result, AoA elevation result) may be transmitted to another ranging device through RRRM or other messages. In the present disclosure, TWR may also be referred to as UWB TWR.

[0092] "DL-TDoA" may be referred to as downlink time difference of arrival (DL-TDo A), reverse TDoA, and its default operation may be used for a user equipment (UE) (Tag device) to eavesdrop on messages of an anchor device when multiple anchor devices broadcast or exchange messages. DL-TDoA may be classified as a type of one-way ranging like uplink TDoA. A UE performing a DL-TDoA operation may eavesdrop on messages sent by two anchor devices to calculate a time difference of arrival (TDoA) proportional to the difference in distance between each anchor device and the UE. The UE may calculate the relative distance to the anchor device by using TDoA utilizing several pairs of anchor devices, and use it for positioning. The operation of an anchor device for DL-TDoA may be similar to that of a bilateral two-way ranging (DS-TWR) defined in IEEE 802.15.4z, and may also include other useful time information so that the UE may calculate the TDoA. In the present disclosure, DL-TDoA may be referred to as DL-TDoA positioning.

[0093] Anchor devices may be referred to as anchors, UWB anchors, or UWB anchor devices, and may be UWB devices deployed at a specific location to provide positioning services. For example, anchor devices may be UWB devices installed by a service provider on a wall, ceiling, structure, etc. in a room to provide indoor positioning services. Anchor devices may be divided into initiator anchors and responder anchors according to the order and role of sending messages.

[0094] "Initiator anchor" may be referred to as an initiator UWB anchor, an initiator anchor device, etc., and may announce the start of a particular ranging round. The initiator anchor may schedule a ranging slot for a responder anchor operating in the same ranging round to respond. The initiation message of the initiator anchor may be referred to as an initiator downlink TDoA message (DTM) or a poll message. The initiation message of the initiator anchor may include a send timestamp. The initiator anchor may additionally send an end message after receiving a response from the responder anchor. The end message of the initiator anchor may be referred to as a final DTM or a final message. The end message may include the time of a reply to a message sent by the responder anchor. The end message may include a send timestamp.

[0095] A "responder anchor" may also be referred to as a responder UWB anchor, a responder UWB anchor device, a responder anchor device, etc. A responder anchor may be a UWB anchor that responds to an initiation message of an initiator anchor. The message to which the responder anchor responds may include the time of the reply to the initiation message. The message to which the responder anchor responds may be referred to as a responder DTM or a response message. The response message of the responder anchor may include a sending timestamp.

[0096] "Cluster" may refer to a group of UWB anchors covering a specific area. A cluster may consist of an initiator UWB anchor and a responder UWB anchor that responds to it. For 2D positioning, one initiator UWB anchor and at least three responder UWB anchors are typically required, while for 3D positioning, one initiator UWB anchor and at least four responder UWB anchors are required. If the initiator UWB anchor and the responder UWB anchor can be accurately time-synchronized through a separate wired / wireless connection, one initiator UWB anchor and two responder UWB anchors are required for 2D positioning, while one initiator UWB anchor and three responder UWB anchors are required for 3D positioning. Unless otherwise specified, it is assumed that there is no separate device between the UWB anchors for wired / wireless time synchronization. A cluster area may be a space formed by the UWB anchors that constitute the cluster. In order to support positioning services for a wide area, multiple clusters may be configured to provide positioning services to UEs. A cluster may be referred to as a cell. The operations of a cluster can be understood as the operations of the anchor points belonging to the cluster.

[0097] Figure 1 is a block diagram schematically illustrating an electronic device.

[0098] refer to Figure 1, the electronic device 101 in the network environment 100 may communicate with the electronic device 102 via the first network 198 (e.g., a short-range wireless communication network), or communicate with the electronic device 104 or the server 108 via the second network 199 (e.g., a long-range wireless communication network). According to an embodiment, the electronic device 101 may communicate with the electronic device 104 via the server 108. According to an embodiment, the electronic device 101 may include a processor 120, a memory 130, an input module 150, a sound output module 155, a display module 160, an audio module 170, a sensor module 176, an interface 177, a connection terminal 178, a haptic module 179, a camera module 180, a power management module 188, a battery 189, a communication module 190, a user identification module (SIM) 196, or an antenna module 197. In an embodiment, at least one of the above components (e.g., the connection terminal 178) may be omitted from the electronic device 101, or one or more other components may be added to the electronic device 101. According to an embodiment, some of the above-described components (eg, the sensor module 176 , the camera module 180 , or the antenna module 197 ) may be integrated into a single integrated component (eg, the display module 160 ).

[0099] The processor 120 may run, for example, software (e.g., program 140) to control at least one other component (e.g., hardware component or software component) of the electronic device 101 connected to the processor 120, and may perform various data processing or calculations. According to one embodiment, as at least part of the data processing or calculation, the processor 120 may store a command or data received from another component (e.g., sensor module 176 or communication module 190) in the volatile memory 132, process the command or data stored in the volatile memory 132, and store the resultant data in the non-volatile memory 134. According to an embodiment, the processor 120 may include a main processor 121 (e.g., a central processing unit (CPU) or an application processor (AP)) or an auxiliary processor 123 (e.g., a graphics processing unit (GPU), a neural processing unit (NPU), an image signal processor (ISP), a sensor hub processor, or a communication processor (CP)) that is independent of or combined with the main processor 121 in operation. For example, when 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 dedicated to a specified function. The auxiliary processor 123 may be implemented separately from the main processor 121, or as part of the main processor 121.

[0100] When the main processor 121 is in an inactive (e.g., sleep) state, the auxiliary processor 123 (rather than the main processor 121) may control at least some of the functions or states related to at least one component among the components of the electronic device 101 (e.g., display module 160, sensor module 176, or communication module 190), or when the main processor 121 is in an active state (e.g., running an application), the auxiliary processor 123 may control at least some of the functions or states related to at least one component among the components of the electronic device 101 (e.g., display module 160, sensor module 176, or communication module 190) together with the main processor 121. According to an embodiment, the auxiliary processor 123 (e.g., an image signal processor or a communication processor) may be implemented as part of another component (e.g., camera module 180 or communication module 190) that is functionally related to the auxiliary processor 123. According to an embodiment, the auxiliary processor 123 (e.g., a neural processing unit) may include a hardware structure dedicated to artificial intelligence model processing. The artificial intelligence model may be generated through machine learning. For example, such learning can be performed by the electronic device 101 where the artificial intelligence is executed or via a separate server (e.g., server 108). The learning algorithm may include, but is not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, for example. The artificial intelligence model may include multiple artificial neural network layers. The 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), or a deep Q network or a combination of two or more thereof, but is not limited thereto. Additionally or optionally, the artificial intelligence model may include a software structure in addition to a hardware structure.

[0101] The memory 130 may store various data used by at least one component of the electronic device 101 (e.g., the processor 120 or the sensor module 176). The various data may include, for example, software (e.g., the program 140) and input data or output data for commands related thereto. The memory 130 may include a volatile memory 132 or a non-volatile memory 134.

[0102] The program 140 may be stored as software in the memory 130 , and may include, for example, an operating system (OS) 142 , middleware 144 , or applications 146 .

[0103] The input module 150 may receive commands or data to be used by other components (e.g., the processor 120) of the electronic device 101 from outside the electronic device 101 (e.g., a 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).

[0104] The sound output module 155 can output sound signals 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 playing multimedia or playing records. The receiver may be used to receive incoming calls. Depending on the embodiment, the receiver may be implemented as a separate part from the speaker, or as part of the speaker.

[0105] The display module 160 can visually provide information to the outside of the electronic device 101 (e.g., a user). The display module 160 may include, for example, a display, a holographic device, or a projector, and a control circuit for controlling a corresponding one of the display, the holographic device, and the projector. According to an embodiment, the display module 160 may include a touch sensor configured to detect a touch or a pressure sensor configured to measure the strength of a force generated by a touch.

[0106] The audio module 170 may convert sound into an electrical signal, or vice versa. According to an embodiment, the audio module 170 may obtain sound via the input module 150, or output sound via the sound output module 155 or an earphone of an external electronic device (e.g., electronic device 102) directly (e.g., wired) or wirelessly connected to the electronic device 101.

[0107] The sensor module 176 may detect an operating state (e.g., power or temperature) of the electronic device 101 or an environmental state (e.g., a user's state) outside the electronic device 101, and then generate an electrical signal or data value corresponding to the detected state. According to an embodiment, the sensor module 176 may include, for example, a gesture sensor, a gyro sensor, an atmospheric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an infrared (IR) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illumination sensor.

[0108] The interface 177 may support one or more specific protocols to be used to connect the electronic device 101 directly (e.g., wired) or wirelessly to an external electronic device (e.g., the electronic device 102). According to an embodiment, the interface 177 may include, for example, a high-definition multimedia interface (HDMI), a universal serial bus (USB) interface, a secure digital (SD) card interface, or an audio interface.

[0109] The connection end 178 may include a connector, wherein the electronic device 101 may be physically connected to an external electronic device (e.g., the electronic device 102) via the connector. According to an embodiment, the connection end 178 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0110] The haptic module 179 may convert the electric signal into mechanical stimulation (eg, vibration or motion) or electric stimulation that can be recognized by the user via his sense of touch or kinesthetic sense. According to an embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electric stimulator.

[0111] The camera module 180 may capture still images or moving images. According to an embodiment, the camera module 180 may include one or more lenses, an image sensor, an image signal processor, or a flash.

[0112] The power management module 188 may manage power supply to the electronic device 101. According to an embodiment, the power management module 188 may be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0113] The battery 189 may power at least one component of the electronic device 101. According to an embodiment, the battery 189 may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0114] The communication module 190 may support establishing a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device 101 and an external electronic device (e.g., electronic device 102, electronic device 104, or server 108), and perform communication via the established communication channel. The communication module 190 may include one or more communication processors capable of operating independently from the processor 120 (e.g., an application processor (AP)) and support direct (e.g., wired) communication or wireless communication. According to an embodiment, the communication module 190 may include a wireless communication module 192 (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module 194 (e.g., a local area network (LAN) communication module or a power line communication (PLC) module). A corresponding one of these communication modules may communicate via a first network 198 (e.g., a short-range communication network such as Bluetooth TM ), Wireless Fidelity (Wi-Fi) Direct, or Infrared Data Association (IrDA)) or a second network 199 (e.g., a long-distance communication network such as a traditional cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a local area network (LAN) or a wide area network (WAN)))) to communicate with an external electronic device. These various types of communication modules may be implemented as a single component (e.g., a single chip), or these various types of communication modules may be implemented as multiple components (e.g., multiple chips) separated from each other. The wireless communication module 192 may identify and authenticate the electronic device 101 in a communication network (such as a first network 198 or a second network 199) using user information (e.g., an International Mobile Subscriber Identity (IMSI)) stored in the user identification module 196.

[0115] The wireless communication module 192 can support 5G networks after 4G networks and next-generation communication technologies (e.g., new radio (NR) access technologies). NR access technologies can support enhanced mobile broadband (eMBB), massive machine type communications (mMTC), or ultra-reliable low-latency communications (URLLC). The wireless communication module 192 can support high-frequency bands (e.g., millimeter wave bands) to achieve, for example, high data transmission rates. The wireless communication module 192 can support various technologies for ensuring performance on high-frequency bands, such as, for example, beamforming, massive multiple-input multiple-output (massive MIMO), full-dimensional MIMO (FD-MIMO), array antennas, analog beamforming, or massive antennas. The wireless communication module 192 can support various requirements specified in the electronic device 101, an external electronic device (e.g., an electronic device 104), or a network system (e.g., a second network 199). According to an embodiment, the wireless communication module 192 may support a peak data rate for implementing eMBB (e.g., 20 Gbps or greater), loss coverage for implementing mMTC (e.g., 164 dB or less), or U-plane delay for implementing URLLC (e.g., 0.5 ms or less for each of the downlink (DL) and uplink (UL), or 1 ms or less for a round trip).

[0116] The antenna module 197 may transmit a signal or power to the outside (e.g., an external electronic device) or receive a signal or power from the outside (e.g., an external electronic device). According to an embodiment, the antenna module 197 may include an antenna including a radiator formed by a conductor or a conductive pattern formed on a substrate (e.g., a printed circuit board (PCB)). According to an embodiment, the antenna module 197 may include a plurality of antennas (e.g., an antenna array). In this case, at least one antenna suitable for a communication scheme used in a communication network (such as the first network 198 or the second network 199) may be selected from the plurality of antennas by, for example, the communication module 190. A signal or power may then be transmitted or received between the communication module 190 and the external electronic device via the selected at least one antenna. According to an embodiment, components other than the radiator (e.g., a radio frequency integrated circuit (RFIC)) may be further formed as part of the antenna module 197.

[0117] According to various embodiments, the antenna module 197 may form a millimeter wave antenna module. According to an embodiment, the millimeter wave antenna module may include a printed circuit board, a radio frequency integrated circuit (RFIC), and a plurality of antennas (e.g., array antennas), wherein the RFIC is disposed on a first surface (e.g., bottom surface) of the printed circuit board, or adjacent to the first surface and capable of supporting a designated high frequency band (e.g., millimeter wave band), and the plurality of antennas are disposed on a second surface (e.g., top surface or side surface) of the printed circuit board, or adjacent to the second surface and capable of transmitting or receiving signals of the designated high frequency band.

[0118] At least some of the above components may be connected to each other via an inter-peripheral communication scheme (e.g., a bus, a general purpose input output (GPIO), a serial peripheral interface (SPI), or a mobile industry processor interface (MIPI)) and communicatively transfer signals (e.g., commands or data) therebetween.

[0119] According to an embodiment, instructions or data may be sent or received between the electronic device 101 and the external electronic device 104 via a server 108 connected to the second network 199. The external electronic device 102 or the electronic device 104 may each be a device of the same type as the electronic device 101, or a device of a different type from the electronic device 101. According to an embodiment, all or some operations to be run on the electronic device 101 may be run on one or more of the external electronic device 102, the external electronic device 104, or the server 108. For example, if the electronic device 101 should automatically perform a function or service or should perform a function or service in response to a request from a user or another device, the electronic device 101 may request the one or more external electronic devices to perform at least part of the function or service instead of running the function or service, or the electronic device 101 may request the one or more external electronic devices to perform at least part of the function or service in addition to running the function or service. The one or more external electronic devices that receive the request may perform the requested at least part of the function or service, or perform another function or another 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 at least a partial reply to the request with or without further processing the result. To this end, cloud computing technology, distributed computing technology, mobile edge computing (MEC) technology, or client-server computing technology, for example, 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 an embodiment, the external electronic device 104 or the server 108 may be included in the second network 199. The electronic device 101 may be applied to intelligent services (e.g., smart homes, smart cities, smart cars, or healthcare) based on 5G communication technology or IoT-related technologies.

[0120] The electronic device according to various embodiments of the present disclosure may be one of various types of electronic devices. The electronic device may include, for example, a portable communication device (e.g., a smart phone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a household appliance. According to an embodiment of the present disclosure, the electronic device is not limited to those electronic devices described above.

[0121] It should be understood that the various embodiments of the present disclosure and the terms used therein are not intended to limit the technical features set forth herein to specific embodiments, but include various changes, equivalent forms or replacement forms for the corresponding embodiments. For the description of the accompanying drawings, similar reference numerals may be used to refer to similar or related elements. It will be understood that the nouns in the singular form corresponding to the term may include one or more things unless the relevant context clearly indicates otherwise. As used herein, each of the phrases such as "A or B", "at least one of A and B", "at least one of A or B", "A, B or C", "at least one of A, B and C" and "at least one of A, B or C" may include all possible combinations of items listed together with the corresponding one of the multiple phrases. As used herein, terms such as "1st" and "2nd" or "first" and "second" may be used to simply distinguish the corresponding component from another component, and do not limit the component in other aspects (e.g., importance or order). It will be understood that if an element (e.g., a first element) is referred to as being “coupled with another element (e.g., the second element)”, “coupled to another element (e.g., the second element)”, “connected with another element (e.g., the second element)”, or “connected to another element (e.g., the second element)” with or without the terms “operably” or “communicatively” being used, it means that the element may be directly (e.g., wired) connected to the other element, wirelessly connected to the other element, or connected to the other element via a third element.

[0122] As used herein, the term "module" may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with other terms (e.g., "logic," "logic block," "part," or "circuit"). A module may be a single integrated component adapted to perform one or more functions or a minimum unit or part of the single integrated component. For example, according to an embodiment, a module may be implemented in the form of an application specific integrated circuit (ASIC).

[0123] The various embodiments described herein may be implemented as software (e.g., program 140) including one or more instructions stored in a storage medium (e.g., internal memory 136 or external memory 138) that can be read by a machine (e.g., electronic device 101). For example, under the control of a processor, a processor (e.g., processor 120) of the machine (e.g., electronic device 101) may call at least one of the one or more instructions stored in the storage medium and execute the at least one instruction with or without the use of one or more other components. This enables the machine to operate to perform at least one function according to the at least one instruction called. The one or more instructions may include code generated by a compiler or code that can be run by an interpreter. A machine-readable storage medium may be provided in the form of a non-transitory storage medium. Among them, the term "non-transitory" only means that the storage medium is a tangible device and does not include signals (e.g., electromagnetic waves), but the term does not distinguish between data being semi-permanently stored in the storage medium and data being temporarily stored in the storage medium.

[0124] According to an embodiment, the method according to various embodiments of the present disclosure may be included and provided in a computer program product. The computer program product may be traded between a seller and a buyer as a commodity. The computer program product may be released in the form of a machine-readable storage medium (e.g., a compact disk read-only memory (CD-ROM)), or may be downloaded via an application store (e.g., Play Store TM ) The computer program product may be published (e.g., downloaded or uploaded) online, or the computer program product may be distributed (e.g., downloaded or uploaded) directly between two user devices (e.g., smart phones). If published online, at least part of the computer program product may be temporarily generated, or at least part of the computer program product may be at least temporarily stored in a machine-readable storage medium (such as a memory of a manufacturer's server, a server of an application store, or a forwarding server).

[0125] According to various embodiments, each of the above-mentioned components (e.g., a module or a program) may include a single entity or multiple entities. Some of the multiple entities may be detachably arranged in different components. According to various embodiments, one or more of the above-mentioned components may be omitted, or one or more other components may be added. Alternatively or additionally, multiple components (e.g., a module or a program) may be integrated into a single component. In this case, according to various embodiments, the integrated component may still perform the one or more functions of each of the multiple components in the same or similar manner as a corresponding one of the multiple components performing one or more functions before integration. According to various embodiments, the operations performed by a module, a program or another component may be performed sequentially, in parallel, repeatedly or in a heuristic manner, or one or more of the operations may be run or omitted in a different order, or one or more other operations may be added.

[0126] Figure 2a An example architecture of a UWB device according to an embodiment of the present disclosure is shown.

[0127] In the present disclosure, the UWB device 200 may be an electronic device that supports UWB communication. For example, the UWB device 200 may be Figure 1 An example of an electronic device 101.

[0128] The UWB device 200 may be, for example, a ranging device supporting UWB ranging. In an embodiment, the ranging device may be an enhanced ranging device (ERDEV) or a FiRa device.

[0129] exist Figure 2a In the embodiment of the present invention, the UWB device 200 can interact with other UWB devices through a UWB session.

[0130] The UWB device 200 may implement a first interface (interface #1) as an interface between the UWB-enabled application 210 and the framework 220, and the first interface enables the UWB-enabled application 110 on the UWB device 200 to use the UWB capability of the UWB device 200 in a predetermined manner. In an embodiment, the first interface may be a framework API or a proprietary interface, but is not limited thereto.

[0131] The UWB device 200 may implement a second interface (Interface #2) as an interface between the UWB framework 210 and the UWB subsystem (UWBS, 230). In an embodiment, the second interface may be a UWB command interface (UCI) or a proprietary interface, but is not limited thereto.

[0132] refer to Figure 2a, the UWB device 200 may include a UWB-enabled application 210, a framework (UWB framework) 220, and / or a UWBS 230 including a UWB MAC layer and a UWB physical layer. Depending on the embodiment, some entities may not be included in the UWB device, or additional entities (eg, a security layer) may be further included.

[0133] The UWB-enabled application 210 may trigger the establishment of a UWB session by the UWBS 230 via the first interface. The UWB-enabled application 210 may use one of the previously defined profiles (a profile). For example, the UWB-enabled application 210 may use one of the profiles defined in FiRa or a custom profile. The UWB-enabled application 210 may use the first interface to handle related events, such as service discovery, ranging notification, and / or error status.

[0134] The framework 220 may provide access to configuration files, stand-alone-UWB configurations, and / or notifications. The framework 220 may support at least one of the following functions: functions for UWB ranging and transaction execution, functions for providing an interface to an application and the UWBS 230, or functions for estimating the location of the device 200. The framework 220 may be a set of software components. As described above, the UWB-enabled application 210 may interface with the framework 220 via a first interface, and the framework 220 may interface with the UWBS 230 via a second interface.

[0135] Meanwhile, in the present disclosure, the application 210 and / or framework 220 with UWB function may be implemented by an application processor (AP) (or processor). Therefore, in the present disclosure, the operation of the application 210 and / or framework 220 supporting UWB may be understood as being performed by the AP (or processor). In the present disclosure, the framework may be referred to as an AP or a processor.

[0136] UWBS 230 may be a hardware component including a UWB MAC layer and a UWB physical layer. UWBS 230 may perform UWB session management and may communicate with a UWBS of another UWB device. UWBS 230 may interface with framework 120 via a second interface and may obtain security data from a security component. In an embodiment, framework (or application processor) 220 may send a command to UWBS 230 via UCI, and UWBS 230 may send a response to the command to framework 220. UWBS 230 may transmit a notification to framework 120 via UCI.

[0137] Figure 2b An example configuration of a framework of a UWB device according to an embodiment of the present disclosure is shown.

[0138] Figure 2b A UWB device can be Figure 2a Examples of UWB devices.

[0139] refer to Figure 2b , the framework 220 may include, for example, software components such as a profile manager 221 , an OOB connector 222 , a security service 223 , and / or a UWB service 224 .

[0140] The profile manager 221 may be used to manage profiles available on UWB devices. A profile may be a set of parameters required to establish communication between UWB devices. For example, a profile may include parameters indicating which OOB secure channel to use, UWB / OOB configuration parameters, parameters indicating whether the use of a specific security component is mandatory, and / or parameters related to the file structure of an ADF. The UWB-enabled application 210 may communicate with the profile manager 221 via a first interface (e.g., a framework (API)).

[0141] The OOB connector 222 may be used to establish an OOB connection with another device. The OOB connector 222 may process an OOB procedure including a discovery procedure and / or a connection procedure. The OOB component (eg, a BLE component) 250 may be connected to the OOB connector 222 .

[0142] The security service 223 may function to interface with the security component 240 (such as SE or TEE).

[0143] The UWB service 224 may perform a role of managing the UWBS 230. The UWB service 224 may provide access from the profile manager 321 to the UWBS 230 by implementing a second interface.

[0144] The present disclosure provides a method for performing posture detection by an electronic device using a UWB signal. The UWB signal may be a UWB signal for DL-TDoA ranging (OWR) or a UWB signal for DS-TWR ranging. In the present disclosure, the posture may be, for example, a posture related to a position where a user is holding a user device (e.g., handheld) or a user is placing a user device (e.g., back pocket / front pocket).

[0145] The present disclosure provides a method in which an electronic device receives a UWB signal to obtain UWB channel impulse response (CIR) data, and classifies whether the UWB signal is a line of sight (LOS) signal or a non-LOS (NLOS) signal based on the UWB CIR data. For the classification of LOS signals or NLOS signals, a convolutional neural network (CNN) algorithm (model) can be used. Therefore, the electronic device of the present disclosure can have high classification accuracy by classifying data with time series characteristics using a CNN model. Valid CIR data with noise removed from UWB CIR data can be used as input data to a CNN model for classification of LOS signals or NLOS signals. Therefore, the classification accuracy of LOS / NLOS signals and the classification accuracy of posture can be improved.

[0146] The present disclosure provides a method for an electronic device to perform posture classification using a classification result of a LOS signal or a NLOS signal (signal classification result) and sensing data. Data (IMU data) of an inertial measurement unit (IMU) sensor can be used as sensing data. Two CNN models (e.g., two parallel CNN models) different from the CNN model used for classification of LOS / NLOS signals can be used to perform posture classification using the signal classification result and sensing data. One of the two CNN models can be trained using the IMU data (first training data) associated with the LOS signal, and the other CNN model can be trained using the IMU data (second training data) associated with the NLOS signal. As described above, a separate CNN model can be used to classify data with different characteristics, thereby improving classification accuracy.

[0147] The present disclosure provides a method for an electronic device to filter the prediction data output from each CNN model before the final LOS / NLOS signal classification and the final posture classification. For filtering, a moving average filter can be used. Therefore, the classification accuracy of the LOS / NLOS signal and the classification accuracy of the posture can be improved.

[0148] The present disclosure provides a method that can use classified LOS / NLOS signals and / or classified postures by various applications of user devices. For example, the classification method of the present disclosure can be used in applications of tagless doors (smart doors), digital car key applications, or point of service (POS) applications. Applications can use accurately classified LOS / NLOS signals and / or classified postures to appropriately provide specific services or functions / parameters associated with specific services.

[0149] In an embodiment, an application may use accurately classified LOS / NLOS signals to perform adaptive ranging frequency adjustment for power saving. For example, an application may set a maximum sleep duration by using adaptive ranging frequency adjustment of classified LOS / NLOS signals.

[0150] In an embodiment, an application may improve the accuracy of position estimation by selectively using only LOS signals through accurate LOS / NLOS signal classification.

[0151] In an embodiment, applications may set adaptive access boundaries through accurate classification of LOS / NLOS signals and posture.

[0152] Figure 3a An example of UWB CIR data according to an embodiment of the present disclosure is shown.

[0153] The UWB channel impulse response CIR can be obtained by receiving a UWB signal. For example, when a UWB signal for DL-TDoA or a UWB signal for DS-TWR is received, the electronic device can obtain UWB CIR data based on the received signal. In the present disclosure, UWB CIR can be abbreviated as CIR.

[0154] According to an embodiment, the electronic device may obtain UWB CIR data using a correlation value between an impulse function and a received UWB signal.

[0155] An example of UWB CIR data obtained based on a UWB signal can be as follows Figure 3a As shown. Figure 3a As shown, for example, 1016 CIR values ​​may be output. Each CIR value may be, for example, a value obtained or measured based on each UWB signal including a UWB message (e.g., an initiation message RIM or a final message RFM) from an initiator (e.g., a smart door) received by a responder (e.g., a user device) during a DS-TWR process. Alternatively, each CIR value may be, for example, a value obtained or measured based on each UWB signal including a UWB message (DTM) from a UWB anchor point (e.g., an initiation message or a final message from an initiator anchor point or a response message from a responder anchor point) received by a user device (tag device) during a DL-TDoA process.

[0156] refer to Figure 3a , an amplitude peak may occur after a particular CIR index (eg, CIR index 750).

[0157] Figure 3b An example of valid UWB CIR data according to an embodiment of the present disclosure is shown.

[0158] In the present disclosure, the effective UWB CIR may refer to a CIR having a meaningful value among CIRs. In other words, the effective UWB CIR may be a CIR obtained or measured by an actual signal other than noise. In the present disclosure, the effective UWB CIR may be referred to as an effective CIR (eCIR).

[0159] According to an embodiment, the electronic device may regard the CIR value before the peak value occurs as noise, and regard n CIR values ​​starting from the peak value as eCIR.

[0160] According to an embodiment, the electronic device may determine n CIRs according to a CIR index obtained by subtracting a margin value from a CIR index where a peak occurs. For example, when a peak occurs at CIR index 750 and the margin value is set to 5 (margin=5), and n is set to 200 (n=200), the electronic device may identify CIRs from CIR index 745 to CIR index 945 as eCIRs. Therefore, CIRs may be classified into signals and noises, and examples of such classification may be as follows: Figure 3b shown.

[0161] When eCIR is classified from the obtained CIR and only the eCIR is used as input data to the CNN model for classification of LOS / NLOS signals, inaccurate noise can be removed to improve the accuracy of classification.

[0162] Furthermore, when eCIR is classified from the obtained CIR and used, the delay of exchanging CIR data can be optimized.

[0163] Furthermore, when eCIR is classified from the obtained CIR and used, an input matrix may be optimized to enhance processing efficiency of the terminal.

[0164] Figure 3c An example of LOS signals and NLOS signals classified using UWB CIR data according to an embodiment of the present disclosure is shown.

[0165] As described above, the CIR value used for classification of LOS signal / NLOS signal may be an eCIR value. Figure 3c As shown, n (eg, 200) eCIR values ​​may be used for classification of LOS / NLOS signals.

[0166] Meanwhile, CIR values ​​(eCIR values) of the LOS signal and the NLOS signal may have different characteristics from each other.

[0167] For example, the LOS signal may have at least one of the following characteristics.

[0168] -The peak value of CIR is higher than the peak value of NLOS signal -CIR value drops quickly to the noise level after the peak - A small number of peaks, such as one or two peaks For example, the NLOS signal may have at least one of the following characteristics.

[0169] -The peak value of CIR is lower than the peak value of LOS signal - After the peak, the CIR value takes a long time to drop to the noise level -Multiple peaks due to multipath signals Due to the characteristic difference between the CIR values ​​of the LOS signal and the NLOS signal, the measured CIR data (eCIR data) can be used to classify whether the corresponding signal is a LOS signal or a NLOS signal.

[0170] According to an embodiment, the electronic device may use a deep learning algorithm to classify whether the corresponding signal is a LOS signal or a NLOS signal using the CIR data (eCIR data) of the corresponding signal. For example, the electronic device may use a CNN model (CNN algorithm) to perform classification of LOS / NLOS signals. Figures 4 to 11 Describe the method of using CNN model to classify LOS / NLOS signals.

[0171] Hereinafter, for convenience of description, it is assumed that four cases for generating data used for classification of LOS / NLOS signals and / or pose classification are classified as follows.

[0172] (1) Handheld (LOS) situation (handheld (LOS) posture): The user holds the electronic device with his hand (handheld) and does not cover the UWB antenna of the electronic device.

[0173] (2) Hand-held NLOS situation (handheld (NLOS) posture): The user holds the electronic device with his hand and covers the UWB antenna of the electronic device.

[0174] (3) Front pocket (LOS) situation (front pocket (LOS) posture): The electronic device is in the user's front pocket, ensuring the LOS signal situation.

[0175] (4) Back-pocket (NLOS) situation (Back-pocket (NLOS) posture): The electronic device is in the user’s back pocket and the signal is blocked due to the body effect.

[0176] A large amount of data for the above four situations (e.g., UWB CIR data and / or IMU sensor data) may be collected as training data for various environments (e.g., an environment in which a user's electronic device (user device) moves toward (approaches) an initiator (e.g., an initiator for DS-TWR or an initiator anchor for DL-TDoA) for UWB ranging). The collected training data may be used to train each CNN model. However, the embodiment is not limited thereto, and according to the embodiment, data from other environments and / or other situations may be collected and used to train the CNN model.

[0177] First, refer to Figure 4 and Figure 5 , describes examples of environments (scenarios) where LOS / NLOS classification can be applied, e.g. Figure 4 DS-TWR and Figure 5 A large amount of data collected in advance in the DS-TWR scenario and / or DL-TDoA scenario to be described below can be used in the training process of the CNN model, and the real-time collected data can be used in the testing process of the CNN model.

[0178] Figure 4 A DS-TWR scenario according to an embodiment of the present disclosure is shown.

[0179] refer to Figure 4 , DS-TWR may be performed between the first electronic device 410 and the second electronic device 420 .

[0180] exist Figure 4 In the embodiment of , for the convenience of description, it is assumed that the first electronic device 410 (e.g., smart door) acts as a controller / initiator of DS-TWR, and the second electronic device 420 (e.g., user device) as an electronic device of the user acts as a controlled / responder of DS-TWR, but the present disclosure is not limited thereto. In this case, it is assumed that the second electronic device 420 is close to the first electronic device 410 as the initiator.

[0181] In an embodiment, the first electronic device 410 may be, for example, a UWB-based door (UWB smart door), and the second electronic device 420 may be an electronic device of a user (eg, a smart phone of the user).

[0182] refer to Figure 4In one ranging cycle (one ranging measurement cycle), the first electronic device 410 as an initiator may initiate a DS-TWR ranging process by sending a ranging initiation message RIM, the second electronic device 420 as a responder may send a ranging response message RRM as a response message to the RIM to the first electronic device 410, and the first electronic device 410 may send a ranging final message RFM to the second electronic device 420, the ranging final message RFM being a response message to the RRM. One ranging measurement cycle for such a DS-TWR may be repeatedly (e.g., periodically) performed.

[0183] According to an embodiment, the RIM may include a transmission timestamp indicating a transmission time of the RIM. In an embodiment, the RRM may include a transmission timestamp indicating a transmission time of the RRM and response time information indicating a time between a reception time of the RIM and the transmission time of the RRM. In an embodiment, the RFM may include a transmission timestamp indicating a transmission time of the RFM and response time information indicating a time between a reception time of the RRM and the transmission time of the RFM.

[0184] According to an embodiment, the second electronic device 420 may obtain a CIR value for each UWB signal including a received TWR message (eg, RFM). The obtained CIR data may be used for classification of LOS / NLOS signals.

[0185] In an embodiment, the second electronic device 420 may obtain the sensing data of the IMU sensor together with the CIR data. In an embodiment, the acquisition period of the IMU sensor data may be different from (e.g., smaller than) the acquisition period of the CIR data. In this case, in order to input the IMU sensor data corresponding to the CIR data as input to the CNN model, a sorting operation may need to be performed.

[0186] Figure 5 A DL-TDoA scenario according to an embodiment of the present disclosure is shown.

[0187] exist Figure 5 In the embodiment of the present invention, for ease of description, a DL-TDoA environment including four UWB anchor points 510, 520-1, 520-2, and 520-3 and one user's electronic device (user device) 530 is assumed, but the number of UWB anchor points and user devices is not limited thereto. In this case, it is assumed that one initiator anchor point (initiator UWB anchor point) 510 and three responder anchor points (responder UWB anchor points) 520-1, 520-2, and 520-3 are used for DL-TDoA. In addition, it is assumed that the user device 530 is close to the initiator anchor point 510 as the initiator. However, the embodiment is not limited thereto.

[0188] refer to Figure 5 , in one ranging cycle (one ranging measurement cycle), the initiator anchor point 510 as the initiator may initiate the DL-TDoA ranging process by sending an initiation message (polling DTM), the responder anchor points 520-1, 520-2 and 520-3 as the responders may each send a response message (response DTM) to the initiator anchor point 510, and the initiator anchor point 510 may send a final message (final DTM) as a response message of the response message to each of the responder anchor points 520-1, 520-2 and 520-3.

[0189] In an embodiment, the polling DTM may further include a sending timestamp indicating the time when the polling DTM is sent. The polling DTM may further include a round index of the current ranging round and a block index of the current ranging block of the sending polling DTM. The polling DTM may further include location information about the UWB anchor point sending the polling DTM.

[0190] In an embodiment, each response DTM may include response time information indicating the time between the time when the polling DTM is received and the time when the corresponding response DTM is sent. Each response DTM may include a sending time (sending timestamp) indicating the time when the response DTM is sent. Each response DTM may also include a round index of the current ranging round in which the corresponding response DTM is sent and a block index of the current ranging block. Each response DTM may also include location information about the UWB anchor point that sends the corresponding response DTM.

[0191] In an embodiment, the final DTM may include a response time indicating the time between the time each response DTM is received and the time the final DTM is sent. In other words, the final DTM may include a list of response times, and the list may include a response time indicating the time between the time each response DTM is received and the time the final DTM is sent. The final DTM may include a send time (send timestamp) indicating the time the final DTM is sent. The final DTM may also include a round index of the current ranging round in which the final DTM is sent and a block index of the current ranging block.

[0192] The user device 530 may receive the initiation message, the response message, and the final message, calculate the TDoA value between the initiator anchor point 510 and each responder anchor point 520-1, 520-2, and 520-3, and estimate its own position using the TDoA value and the known position of the anchor point. In an embodiment, information about the position of the anchor point may be transmitted through UWB in-band communication (e.g., DTM message) or through UWB out-of-band communication (e.g., BLE communication).

[0193] In an embodiment, the user equipment 530 may obtain a CIR value for each UWB signal including the received DMT (eg, final DTM). The obtained CIR data may be used for classification of LOS / NLOS signals.

[0194] In an embodiment, the user device 530 may obtain the sensing data of the IMU sensor together with the CIR data. In an embodiment, the acquisition period of the IMU sensor data may be different from (e.g., smaller than) the acquisition period of the CIR data. In this case, in order to input the IMU sensor data corresponding to the CIR data as input to the CNN model, a sorting operation may need to be performed.

[0195] Figure 6 A process of LOS / NLOS signal classification using UWB channel impulse response data according to an embodiment of the present disclosure is shown.

[0196] exist Figure 6 In the embodiment of the present invention, for ease of description, it is assumed that the training process 610 is performed on the remote server, and the testing process / implementation process 620 is performed on the user device. However, the embodiment is not limited thereto. For example, if the user device is a device with high computing power, the training process can also be performed on the user device.

[0197] First, refer to Figure 6 Describe the training process 610. In the present disclosure, the training process may be a process for using pre-collected training data (e.g., Figure 4 / Figure 5 The model for LOS / NLOS classification can be trained using pre-collected training data in the environment (scene) of the present invention. The model disclosed in the present invention can be a CNN-based model.

[0198] In the training process 610, the remote server (server) may collect input data (611). For example, the server may collect CIR data (eg, eCIR data including n eCIR values) as input data for training.

[0199] The server may perform CIR normalization processing on the collected input data (612). For example, the server may normalize the collected input data to between 0 and 1. However, the CIR normalization of operation 612 may be omitted as an optional operation.

[0200] The server may input the CIR normalized data or the CIR unnormalized data as input data to the CNN model, and may perform processing for LOS / NLOS classification using the CNN model (613). The CNN model may classify the input data into values ​​of multiple output labels. For example, the CNN model may output the input data as a probability value corresponding to a LOS signal (e.g., label 1) and a probability value corresponding to a NLOS signal (e.g., label 2).

[0201] Tables 1 and 2 below show examples of characteristics (architecture) and hyperparameters of a CNN model for LOS / NLOS classification.

[0202] [Table 1]

[0203] [Table 2]

[0204] The server may obtain the prediction value output from the CNN model (614). In an embodiment, the prediction value may include a prediction probability value (e.g., a first prediction value) for a label (e.g., label 1) corresponding to the LOS signal and a prediction probability value (e.g., a second prediction value) for a label (e.g., label 2) corresponding to the NLOS signal.

[0205] The server may obtain an actual value (ground truth value) of a corresponding signal (signal corresponding to the input data) (615). In an embodiment, the actual value may include an actual value of a tag (e.g., tag 1) corresponding to the LOS signal and / or an actual value of a tag (e.g., tag 2) corresponding to the NLOS signal.

[0206] The server may calculate a loss function (616) based on an error between the predicted value of operation 614 and the actual value of operation 615. In an embodiment, the server may calculate an overall error based on an error between the predicted value and the actual value of the LOS signal and an error between the predicted value and the actual value of the NLOS signal.

[0207] The server can back-propagate the calculated loss function to update the parameters of the CNN model in a direction that reduces the error. The updated parameters can be used in the CNN model for processing the next input data (e.g., the next n eCIR values).

[0208] The server may perform the above training process 610 for each of all collected input data sets (e.g., each input data set includes n eCIR values), continuously updating the parameters of the CNN model (CNN parameters) in the direction of reducing the error. The user device may obtain or download the trained CNN parameters. In addition, the user device may download information about whether normalization is used. In addition, the user device may download the standard deviation associated with the CNN model.

[0209] In the following, reference Figure 6 Describe the test procedure process / implementation process 620. In the present disclosure, the test process may be a process for testing a model trained using actual data (e.g., real-time data), and the implementation process may be a process for actually implementing LOS / NOS classification using a model trained using actual data (e.g., real-time data).

[0210] In the testing process / implementation process 620, the user device may collect real-time input data (621). For example, the user device may collect multiple CIR values ​​(e.g., eCIR values) as input data in real time, and process the input data to divide them into a preset number of lengths (sizes) (e.g., length n). In an embodiment, the length n may be the same as the length n used for training.

[0211] The user equipment may perform CIR normalization on the collected input data (622). For example, the user equipment may normalize the collected input data to be between 0 and 1. However, the CIR normalization in operation 622 may be omitted as an optional operation.

[0212] The user device may input the CIR normalized data or the CIR unnormalized data as input data to the CNN model, and may perform processing for LOS / NLOS classification using the CNN model (623). The CNN model of the user device may process the input data using the CNN parameters obtained through the training process 610. The CNN model may classify the input data into values ​​of multiple output labels. For example, the CNN model may output the input data as a probability value corresponding to a LOS signal (e.g., label 1) and a probability value corresponding to a NLOS signal (e.g., label 2).

[0213] The user device may obtain prediction data (real-time prediction data) output from the CNN model (624). In an embodiment, the prediction data output from the CNN model may include a prediction value (first prediction value) for the first eCIR data (the first n eCIR data in the real-time input data), a prediction value (second prediction value) for the second eCIR data (the second n eCIR data in the real-time input data), ..., a prediction value (nth prediction value) for the nth eCIR data (the nth eCIR data in the real-time input data). In an embodiment, for the corresponding eCIR data, each prediction value may include a prediction probability value corresponding to a label of a LOS signal (e.g., label 1) and / or a prediction probability value corresponding to a label of a NLOS signal (e.g., label 2).

[0214] The user device may filter the predicted values ​​(prediction data) using a filter (e.g., a low pass filter (LPF) or a sliding average filter) (625). In an embodiment, the sliding average filter may have a window length parameter as a hyperparameter indicating the length of a window used to calculate the average value of the data. The user device may filter the prediction data using the sliding average filter with the window length parameter. For example, the user device may filter the prediction data by replacing each data point in the prediction data with the average value of as many data points as specified by the window_length that includes the corresponding data point.

[0215] The user device may use the filtered data to obtain an output label for the real-time input data (626). The user device may ultimately use the filtered data to determine whether the output label of the signal corresponding to the real-time input data is a label corresponding to the LOS signal (e.g., label 1) or a label corresponding to the NLOS signal (e.g., label 2). Therefore, the user device may perform a final classification of whether the corresponding signal is a LOS signal or a NLOS signal. Therefore, the classification accuracy of the LOS / NLOS signal may be improved by providing filtering using a sliding average filter for the predicted data output from the CNN model before the final LOS / NLOS signal classification.

[0216] Table 3 below shows a comparison of the accuracy of LOS / NLOS classification when an LPF filter (eg, a sliding average filter) is used and when it is not used under the same conditions.

[0217] [Table 3]

[0218] Figure 7 A configuration of a user equipment for LOS / NLOS classification according to an embodiment of the present disclosure is shown.

[0219] Figure 7 The user equipment 700 may be a device that performs Figure 6 An example of a user device for a testing procedure / implementation procedure 620 .

[0220] refer to Figure 7 , the user equipment 700 may include a UWB antenna 710, a CIR collector 720, a machine learning unit 730, a classification processing unit 740, a central control unit 750 and / or a storage unit 750. The classification processor 740 may include an effective CIR generator 741, a normalizer 742 and a sliding average filter 743.

[0221] According to an embodiment, some of the above components may be omitted, or additional components may be further included. According to an embodiment, two or more of the above components may be combined into one component. According to an embodiment, all or some of the above components may be implemented by at least one processor (or controller). For example, components other than the UWB antenna 710 and the storage unit 750 may be implemented by at least one processor (or controller).

[0222] The UWB antenna 710 may transmit / receive UWB signals. In an embodiment, the UWB antenna 710 may receive at least one UWB signal for UWB ranging from another electronic device. For example, the UWB antenna 710 may receive at least one UWB signal for DS-TWR or at least one UWB signal for DL-TDoA.

[0223] The CIR collector 720 may collect CIR data from at least one UWB signal received through the UWB antenna 710. The CIR collector 720 may transmit the collected CIR data to the effective CIR generator (informative CIR generator) 741. The collected CIR data may include a plurality of CIR values.

[0224] The effective CIR generator 741 may generate effective CIR data from the collected CIR data. The effective CIR generator 741 may send the generated effective CIR data to the normalizer 742, or may directly send the generated effective CIR data to the machine learning unit 730. The effective CIR data may include a plurality of effective CIR values ​​and may be processed by the machine learning unit 730 in a preset number of units (e.g., n units).

[0225] The normalizer 742 may normalize the value of the effective CIR (eCIR) data. For example, the normalizer 742 may normalize the value of the effective CIR data to a value between 0 and 1. The normalizer 742 may have optional components. For example, even if the normalizer 742 is not included in the user equipment 700, or is included in the user equipment 700, the processing of the normalizer 742 may be omitted.

[0226] The machine learning unit 730 can generate prediction data using the input valid CIR data. According to an embodiment, the machine learning unit 730 can generate prediction data using a CNN model. In an embodiment, the CNN parameters of the CNN model can be downloaded from a server that has pre-performed a training process. Therefore, the machine learning unit 730 can use an optimized CNN model.

[0227] In an embodiment, the machine learning unit 730 may perform processing in units of a preset number of eCIRs (e.g., n eCIRs) (eCIR sets) to output each prediction value for the corresponding eCIR set. For example, the prediction data may include a first prediction value (first prediction value) for the first n eCIRs (first eCIR set), a prediction value (second prediction value) for the next n eCIRs (second eCIR set), ..., a prediction value (nth prediction value) for the nth CIR (nth eCIR set). For the corresponding eCIR set, each prediction value may include a prediction probability value corresponding to LOS and a prediction probability value corresponding to NLOS.

[0228] The machine learning unit 730 may transmit the prediction data to the central controller 750 and / or the sliding average filter 743 .

[0229] The central controller 750 may transmit the received prediction data to the storage unit 730. The storage unit 730 may store the received prediction data and transmit the stored prediction data to the sliding average filter 743.

[0230] The sliding average filter 743 can use the prediction data (e.g., current prediction data) received from the machine learning unit 730 and the prediction data (e.g., previous prediction data) received from the storage unit 760 to calculate an average value based on a preset window length parameter, and use the average value to filter the prediction data. The filtered prediction data can be used for final classification as a LOS signal or a NLOS signal. The filtered prediction data can be used by various applications.

[0231] Figure 8 A training process for pose classification based on LOS / NLOS signal classification using UWB channel impulse response data according to an embodiment of the present disclosure is shown.

[0232] exist Figure 8 In the embodiment of , for ease of description, it is assumed that the training process 810 is performed on the remote server. However, the embodiment is not limited thereto. For example, if the user device is a device with high computing power, the training process can also be performed on the user device.

[0233] First, refer to Figure 8 Describe the training process 800. In the present disclosure, the training process can be a method for using pre-collected training data (e.g., Figure 4 / Figure 5 The process of training a model for pose classification using pre-collected training data in an environment (scene). The model disclosed in the present invention may be a CNN-based model.

[0234] In the training process 800, a remote server (server) may collect input data (801). For example, the server may collect CIR data (eg, eCIR data including n eCIR values) as input data for training.

[0235] The server may perform CIR normalization on the collected input data (802). For example, the server may normalize the collected input data between 0 and 1. However, the CIR normalization of operation 802 may be omitted as an optional operation.

[0236] The server may input CIR normalized data or CIR unnormalized data as input data to the first CNN model, and may perform processing for LOS / NLOS classification using the first CNN model (803). The first CNN model may classify the input data into values ​​of multiple output labels. For example, the CNN model may output the input data as a probability value corresponding to a LOS signal (e.g., label a) and a probability value corresponding to a NLOS signal (e.g., label b). In the present disclosure, the first CNN model refers to a CNN model for LOS / NLOS classification.

[0237] The server may obtain a prediction value (a first prediction value or first prediction information) output from the first CNN model (804). In an embodiment, the first prediction value may include a prediction probability value corresponding to a label of the LOS signal (e.g., label a) and / or a prediction probability value corresponding to a label of the NLOS signal (e.g., label b).

[0238] The server may obtain an actual value (ground truth value) of the corresponding signal (first actual value or first actual information) (805). In an embodiment, the first actual value may include an actual value of a label (e.g., label a) corresponding to the LOS signal and / or an actual value of a label (e.g., label b) corresponding to the NLOS signal.

[0239] The server may calculate a loss function (loss and gradient calculation) (806) based on the error (or loss) between the predicted value of operation 804 and the actual value of operation 805. In an embodiment, the server may calculate an overall error based on the error between the predicted value and the actual value of the LOS signal and the error between the predicted value and the actual value of the NLOS signal.

[0240] The server may back-propagate the calculated loss function to update the parameters of the first CNN model in a direction that reduces the error. The updated parameters may be used in the first CNN model for processing the next input data (eg, the next n eCIR values).

[0241] The server may perform the above training process 800 for each of all collected eCIR sets (e.g., each eCIR set includes n eCIR values), continuously updating the parameters of the first CNN model (CNN parameters) in a direction that reduces the error. The user device may obtain or download the CNN parameters for the trained first CNN model. In addition, the user device may download information about whether normalization is used. In addition, the user device may download a standard deviation associated with the first CNN model.

[0242] The server may determine whether the signal corresponding to the eCIR set is classified as a LOS signal or a NLOS signal based on the predicted value of the eCIR set. For example, when the predicted probability value corresponding to the LOS signal in the predicted value of the eCIR set is greater than the predicted probability value corresponding to the NLOS signal, the server may determine that the signal corresponding to the eCIR set is classified as a LOS signal. For another example, when the predicted probability value corresponding to the NLOS signal in the predicted value of the corresponding eCIR set is greater than the predicted probability value corresponding to the LOS signal, the server may determine that the signal corresponding to the eCIR set is classified as a NLOS signal.

[0243] When the signal corresponding to the eCIR set is classified as a LOS signal, the server can perform a classification process for pose detection based on the second CNN model. Alternatively, when the signal corresponding to the eCIR set is classified as a NLOS signal, the server can perform a classification process for pose detection based on the third CNN model. In the present disclosure, the second CNN model refers to a CNN model for pose classification trained using IMU sensor data associated with LOS signals. In the present disclosure, the third CNN model refers to a CNN model for pose classification trained using IMU sensor data associated with NLOS signals.

[0244] Tables 4 and 5 below show examples of characteristics (architecture) and hyperparameters of CNN models (second CNN model / third CNN model) for pose classification.

[0245] [Table 4]

[0246] [Table 5]

[0247] The server may collect sensor input data (e.g., IMU data) (807). The sensor input data may be sensor input data associated with the LOS signal (first sensor input data) or sensor input data associated with the NLOS signal (second sensor input data). For example, sensor data collected in the above-mentioned environment when the UWB antenna is not covered or placed in the front pocket may be sensor input data associated with the LOS signal (first sensor input data), and sensor data collected in the above-mentioned environment when the UWB antenna is covered or placed in the back pocket may be sensor input data associated with the NLOS signal (second sensor input data).

[0248] In an embodiment, the sensor input data may include IMU values ​​for m timestpes (m time series IMU values).

[0249] The server may perform sorting to input sensor input data corresponding to the input data input to the first CNN model into the second CNN model or the third CNN model (808). For example, the server may perform sorting to input sensor input data collected during the same period as the period during which the input data including the n eCIR values ​​are collected into the second CNN model or the third CNN model.

[0250] When the signal is classified as a LOS signal, the server may input the sorted first sensor input data (first sensor input sequence) as input data for training a second CNN model, and may use the second CNN model to perform processing for posture classification (809). For example, the second CNN model may use the input data to predict whether the posture for the sensor input data is a first posture (e.g., handheld) or a second posture (e.g., front pocket). The server may obtain a prediction value (a second prediction value or second prediction information) output from the second CNN model (810). In an embodiment, for the first sensor input data associated with LOS, the prediction value may include a prediction probability value of a label (e.g., label 1) corresponding to the first posture (e.g., handheld (LOS)) and a prediction probability value of a label (e.g., label 2) corresponding to the second posture (e.g., front pocket (LOS)).

[0251] When the signal is classified as an NLOS signal, the server may input the sorted second sensor input data (second sensor input sequence) as input data for training a third CNN model, and may use the third CNN model to perform processing for pose classification (811). For example, the third CNN model may use the input data to predict whether the pose of the sensor input data is a third pose (e.g., handheld (NLOS)) or a fourth pose (e.g., back pocket (NLOS)). The server may obtain a prediction value (a second prediction value or second prediction information) output from the third CNN model (812). In an embodiment, for the second sensor input data associated with LOS, the prediction value may include a prediction probability value of a label (e.g., label 3) corresponding to the third pose (e.g., handheld (NLOS)) and a prediction probability value of a label (e.g., label 4) corresponding to the fourth pose (e.g., back pocket (NLOS)).

[0252] The server may obtain an actual value (actual value) of the corresponding posture (second actual value or second actual information) (813). In an embodiment, the second actual value may include an actual value of a label (e.g., label 1) corresponding to the first posture, an actual value of a label (e.g., label 2) corresponding to the second posture, an actual value of a label (e.g., label 3) corresponding to the third posture, and / or an actual value of a label (e.g., label 4) corresponding to the fourth posture.

[0253] The server may calculate a loss function based on an error (or loss) between the second predicted value of operation 810 and the second actual value of operation 813 , and / or based on an error (or loss) between the third predicted value of operation 812 and the second actual value of operation 813 ( 814 ).

[0254] The server may back-propagate the calculated loss function and update the parameters of the corresponding CNN model (the second CNN model or the third CNN model) in the direction of reducing the error. For example, the server may update the parameters of the second CNN model by back-propagating the loss function obtained based on the second predicted value of operation 810 and the second actual value of operation 813. Alternatively, the server may update the parameters of the third CNN model by back-propagating the loss function obtained based on the third predicted value of operation 812 and the second actual value of operation 813. In this way, the server may update the parameters of the corresponding CNN model in the direction of reducing the error using the back-propagation method.

[0255] The updated parameters can be used in the corresponding CNN model to process the next input data (eg, the next m IMU sensing values).

[0256] The server may perform the above training process 800 on all collected IMU sensor data sets (e.g., each IMU sensor data set includes m IMU sensing values) to continuously update the parameters (CNN parameters) of the second CNN model and the third CNN model in the direction of reducing the error. The user device may obtain or download the trained CNN parameters of the second CNN model and the third CNN model.

[0257] Fig. 9 The process of performing posture classification by a user equipment based on LOS / NLOS signal classification using UWB channel impulse response data according to an embodiment of the present disclosure is shown.

[0258] exist Fig. 9 In the embodiment of , for ease of description, it is assumed that the test process / implementation process 900 is performed on the user device. In the present disclosure, the test process may be a process for testing a model trained using actual data (e.g., real-time data), and the implementation process may be a process for actually implementing LOS / NOS classification using a model trained using actual data (e.g., real-time data).

[0259] First, refer to Fig. 9 ,refer to Fig. 9 Describe the testing process / implementation process 900.

[0260] In the testing process / implementation process 900, the user equipment may collect input data (901). For example, the user equipment may collect multiple CIR values ​​(e.g., eCIR values) in real time as input data, and process the input data to divide them into a preset number of lengths (sizes) (e.g., length n). In an embodiment, the length n may be the same as the length n used for training.

[0261] The user equipment may perform CIR normalization on the collected input data (902). For example, the user equipment may normalize the collected input data to between 0 and 1. However, the CIR normalization in operation 902 may be omitted as an optional operation.

[0262] The user equipment may input CIR normalized data or CIR unnormalized data as input data to the first CNN model, and may use the first CNN model to perform processing for LOS / NLOS classification (903). The first CNN model may classify the input data into values ​​of multiple output labels. For example, the CNN model may output the input data as a probability value corresponding to a LOS signal (e.g., label a) and a probability value corresponding to a NLOS signal (e.g., label b). In the present disclosure, the first CNN model refers to a CNN model for LOS / NLOS classification.

[0263] The user device may obtain a prediction value (a first prediction value or first prediction information) output from the first CNN model (904). In an embodiment, the first prediction value may include a prediction probability value corresponding to a label of the LOS signal (e.g., label a) and / or a prediction probability value corresponding to a label of the NLOS signal (e.g., label b).

[0264] The user device may perform the above LOS / NLOS classification process on each of all collected eCIR sets (eg, each eCIR set includes n eCIR values). The user device may perform filtering (905) on the prediction data (first prediction data) including each prediction value obtained from the first CNN model using a sliding average filter.

[0265] The user equipment may determine whether the signal corresponding to the eCIR set is classified as a LOS signal or a NLOS signal based on the predicted value of the eCIR set. For example, when the predicted probability value corresponding to the LOS signal in the predicted value for the eCIR set is greater than the predicted probability value corresponding to the NLOS signal, the user equipment may determine that the signal corresponding to the eCIR set is classified as a LOS signal. For another example, when the predicted probability value corresponding to the NLOS signal in the predicted value for the corresponding eCIR set is greater than the predicted probability value corresponding to the LOS signal, the user equipment may determine that the signal corresponding to the eCIR set is classified as a NLOS signal.

[0266] When the signal corresponding to the eCIR set is classified as a LOS signal, the user device can perform a classification process for posture detection based on the second CNN model. Alternatively, when the signal corresponding to the eCIR set is classified as a NLOS signal, the user device can perform a classification process for posture detection based on the third CNN model. In the present disclosure, the second CNN model refers to a CNN model for posture classification trained using IMU sensor data associated with LOS signals. In the present disclosure, the third CNN model refers to a CNN model for posture classification trained using IMU sensor data associated with NLOS signals.

[0267] The user device may collect sensor input data (906). The sensor input data may be sensor input data associated with the LOS signal (first sensor input data) or sensor input data associated with the NLOS signal (second sensor input data). In an embodiment, the sensor input data may include IMU values ​​of m time strings.

[0268] The user device may perform sorting to input sensor input data corresponding to the input data input to the first CNN model to the second CNN model or the third CNN model (907). For example, the user device may perform sorting to input sensor input data collected during the same period as the period during which input data including n eCIR values ​​are collected into the second CNN model or the third CNN model.

[0269] When the signal is classified as a LOS signal, the user device may input the sorted sensor input data (first sensor input sequence) as input data to the second CNN model, and may use the second CNN model to perform processing for posture classification (908). For example, the second CNN model may use the input data to predict whether the posture of the sensor input data is a first posture (e.g., handheld (LOS)) or a second posture (e.g., front pocket (LOS)). The user device may obtain a prediction value (a second prediction value or second prediction information) output from the second CNN model (909). In an embodiment, for the first sensor input data associated with LOS, the prediction value may include a prediction probability value of a label (e.g., label 1) corresponding to the first posture (e.g., handheld (LOS)) and a prediction probability value of a label (e.g., label 2) corresponding to the second posture (e.g., front pocket (LOS)).

[0270] When the signal is classified as an NLOS signal, the server may input the sorted sensor input data (second sensor input sequence) as input data for training a third CNN model, and may use the third CNN model to perform processing for posture classification (910). For example, the third CNN model may use the input data to predict whether the posture of the sensor input data is a third posture (e.g., handheld (NLOS)) or a fourth posture (e.g., back pocket (NLOS)). The user device may obtain a prediction value (a second prediction value or second prediction information) output from the third CNN model (911). In an embodiment, for the second sensor input data associated with NLOS, the prediction value may include a prediction probability value of a label (e.g., label 3) corresponding to the third posture (e.g., handheld (NLOS)) and a prediction probability value of a label (e.g., label 4) corresponding to the fourth posture (e.g., front pocket (NLOS)).

[0271] The user device may perform the above-described pose classification process on each of all collected IMU sensor data sets (e.g., each IMU sensor data set includes m IMU sensing values). The user device may perform filtering (912) on the prediction data (second prediction data) including each prediction value obtained from the second CNN model or the prediction data (third prediction data) including each prediction value obtained from the third CNN model using a sliding average filter. Thus, the classification accuracy of the LOS / NLOS signal and pose may be improved by providing filtering using a sliding average filter for the prediction data output from each CNN model before the final LOS / NLOS signal classification and the final pose classification.

[0272] The user device may use the filtered first prediction data and the filtered second prediction data to determine a pose. For example, the filtered first prediction data and the filtered second prediction data may be used to determine whether the pose is a first pose (e.g., a hand (LOS) pose) or a second pose (e.g., a front (LOS) pose).

[0273] Alternatively, the user device may use the filtered first prediction data and the filtered third prediction data to determine the pose. For example, the filtered first prediction data and the filtered third prediction data may be used to determine whether the pose is a third pose (e.g., a hand (NLOS) pose) or a fourth pose (e.g., a back (NLOS) pose).

[0274] Fig.10 A configuration of a user equipment for performing pose classification using LOS / NLOS classification according to an embodiment of the present disclosure is shown.

[0275] Fig.10 The user device 1000 may be a device that performs Fig. 9 An example of a testing process / user device implementing process 900.

[0276] refer to Fig.10 , the user equipment 1000 may include an IMU sensor 1010, a sensor data collector 1020, a UWB antenna 1030, a CIR collector 1040, a machine learning unit 1050, a classification processor 1060, a central controller 1070 and / or a storage unit 1080. The classification processor 1060 may include an effective CIR generator 1061, a normalizer 1062, a sliding average filter 1063 and / or a sequence generator 1064.

[0277] According to an embodiment, some of the above components may be omitted, or additional components may be further included. According to an embodiment, two or more of the above components may be combined into one component. According to an embodiment, all or some of the above components may be implemented by at least one processor. For example, components other than the IMU sensor 1010, the UWB antenna 1030, and the storage unit 1080 may be implemented by at least one processor (or controller).

[0278] The IMU sensor 1010 can sense the surrounding environment. In an embodiment, the IMU sensor 1010 can be a sensor capable of measuring a specific force, an angular rate, and / or an orientation of a body using a combination of an accelerometer, a gyroscope, and / or a magnetometer. The IMU sensor 1010 can transmit the sensed data to the sensor data collector 1020.

[0279] The sensor data collector 1020 may transmit the collected sensor data to the sequence generator 1064 .

[0280] The sequence generator 1064 may perform sorting to input sensor input data corresponding to the input data input to the first CNN model to the second CNN model or the third CNN model. For example, the sequence generator 1064 may perform sorting to input sensor input data collected during the same period as the period during which the input data including the n eCIR values ​​are collected to the second CNN model or the third CNN model.

[0281] The UWB antenna 1030 may transmit / receive UWB signals. In an embodiment, the UWB antenna 1030 may receive at least one UWB signal for UWB ranging from another electronic device. For example, the UWB antenna 1030 may receive at least one UWB signal for DS-TWR or at least one UWB signal for DL-TDoA.

[0282] The CIR collector 1040 may collect CIR data from at least one UWB signal received through the UWB antenna 1030. The CIR collector 1040 may transmit the collected CIR data to the effective CIR generator 1061. The collected CIR data may include a plurality of CIR values.

[0283] The effective CIR generator 1061 may generate effective CIR data based on the collected CIR data. The effective CIR generator 1061 may transmit the generated effective CIR data to the normalizer 1062, or may transmit the generated effective CIR data directly to the machine learning unit 1050. The effective CIR data may include a plurality of effective CIR values ​​and may be processed by the machine learning unit 1050 in a preset number of units (e.g., n units).

[0284] The normalizer 1062 may normalize the value of the effective CIR (eCIR) data. For example, the normalizer 1062 may normalize the value of the effective CIR data to a value between 0 and 1. The normalizer 1062 may have optional components. For example, whether the normalizer 1062 is not included in the user equipment 1000 or is included in the user equipment 1000, the processing of the normalizer 1062 may be omitted.

[0285] The machine learning unit 1050 may generate prediction data using input data. In an embodiment, the machine learning unit 730 may generate at least one prediction data using at least one CNN model, and may download CNN parameters of each CNN model from a server that has previously performed a training process.

[0286] According to an embodiment, the machine learning unit 1050 may use a first CNN model to generate first prediction data for LOS / NLOS classification based on the input valid CIR data. In an embodiment, the first CNN model may perform processing in units of a preset number of eCIRs (e.g., n eCIRs) (eCIR sets) to output each prediction value for the corresponding eCIR set. For example, the first prediction data may include a first prediction value (first prediction value) for the first n eCIRs (first eCIR set), a prediction value (second prediction value) for the next n eCIRs (second eCIR set), ..., a prediction value (nth prediction value) for the nth n eCIRs (neCIR set). For the corresponding eCIR set, each prediction value may include a prediction probability value corresponding to LOS and a prediction probability value corresponding to NLOS.

[0287] According to an embodiment, the machine learning unit 1050 may use a second CNN model to generate second prediction data for classification of a posture associated with LOS based on the input sensor data. In an embodiment, the second CNN model may perform processing in units of a preset number of sensing values ​​(e.g., m sensing values) (sensor data set) to output a prediction value for each corresponding sensing data set. For example, the second prediction data may include a prediction value (first prediction value) for the first m sensing values ​​(first sensing data set), a prediction value (second prediction value) for the next m sensing values ​​(second sensing data set), ..., a prediction value (nth prediction value) for the nth m sensing values ​​(nth sensing data set). For the corresponding sensing data set, each prediction value may include a prediction probability value associated with LOS corresponding to the first posture and a prediction probability value corresponding to the second posture.

[0288] According to an embodiment, the machine learning unit 1050 may use a third CNN model to generate third prediction data for classification of a pose associated with NLOS based on input sensor data. In an embodiment, the third CNN model may perform processing in units of a preset number of sensing values ​​(e.g., m sensing values) (sensor data set) to output a prediction value for each corresponding sensing data set. For example, the third prediction data may include a prediction value (first prediction value) for the first m sensing values ​​(first sensing data set), a prediction value (second prediction value) for the next m sensing values ​​(second sensing data set), ..., a prediction value (nth prediction value) for the nth m sensing values ​​(nth sensing data set). For the corresponding sensing data set, each prediction value may include a prediction probability value corresponding to the first pose and a prediction probability value corresponding to the second pose associated with NLOS.

[0289] The machine learning unit 1050 may transmit the prediction data (eg, the first prediction data, the second prediction data, and / or the third prediction data) to the central controller 1070 and / or the sliding average filter 1064 .

[0290] The central controller 1070 may transmit the received prediction data to the storage unit 1080. The storage unit 1080 may store the received prediction data and transmit the stored prediction data to the sliding average filter 1064.

[0291] The sliding average filter 1064 may filter each prediction data. The filtered prediction data may be used for final pose classification. The filtered prediction data may be used by various applications. In an embodiment, the application may provide different services or service-related parameters (e.g., thresholds) based on the pose classified based on the filtered prediction data.

[0292] Fig.11 An example architecture of a system providing a UWB-based gate service according to an embodiment of the present disclosure is shown.

[0293] In the present disclosure, the UWB-based gate service may be referred to as a gate service or a smart gate service (SGS), and a system providing the UWB-based gate service may be referred to as a gate system or a smart gate system.

[0294] refer to Fig.11 , the gate system may include a mobile device (user equipment) 1110 , a smart station 1120 and / or an SGS operator server.

[0295] (1) The mobile device 1110 may include an SGS application 1111, a framework (U-pass framework) 1112, a BLE component (subsystem) 1113, an SGS applet 1114, and / or a UWB component (subsystem) 1115. In an embodiment, the SGS application 1111, the U-pass framework 1112, the BLE component 1113, the SGS applet 1114, and / or the UWB component 1115 of the mobile device 1110 may be examples of the framework of the UWB device, the application with UWB function, the applet, the OOB component, and the UWB component described above in conjunction with, for example, FIG. 2 , respectively.

[0296] The U-pass framework 1112 may support at least one of the following functions.

[0297] -Estimating the location of the mobile device during a Downlink-TDoA (D-TDoA) round.

[0298] -Implementation procedures for performing UWB ranging and transactions.

[0299] - Provides a set of APIs for SGS operator applications (SGS applications) and provides an interface between the framework and UWB components.

[0300] - UWB communication is triggered when a BLE broadcast is received from a smart station (component).

[0301] The SGS application can support at least one of the following functions.

[0302] - Provides anchor point and UWB block structure deployment information when requested by the framework.

[0303] - Provide the framework with the AID of the SGS applet and the version of the SGS applet protocol.

[0304] - Communication with the SGS operator server to initiate service application installation, station specific information retrieval (eg anchor map) and token retrieval or update processing.

[0305] The SGS applet can support at least one of the following functions.

[0306] -Hosted on a secure component (e.g., SE or TEE) that is able to communicate over the UWB interface.

[0307] - Implement the transaction protocol for the gate service.

[0308] -Support APDU commands.

[0309] The BLE component 1113 may be used to receive at least one BLE message from a smart station when the mobile device enters the service area of ​​the door system.

[0310] The UWB component 1115 may be used to estimate the location of the mobile device, for example, via D-TDoA, and / or may be used to communicate with a specific gate to perform UWB ranging and transactions.

[0311] (2) The smart station 1120 may include at least one BLE anchor point 1121 , at least one TDoA anchor point (UWB anchor point) 1122 , and / or at least one door (door device) 1123 .

[0312] The BLE anchor point 1121 may be used to provide general site information about the mobile device and notify the mobile device that it is entering the service area of ​​the door system.

[0313] In an embodiment, the BLE anchor 1121 may support a role as a GAP broadcaster, a role as a GATT server, and / or broadcast advertising physical channel PDUs.

[0314] A TDoA anchor point (UWB anchor point) 1122 may be deployed in the service area of ​​the door system. The TDoA anchor point (UWB anchor point) 1122 may broadcast a UWB message at a specific time. Mobile devices may use this UWB message to estimate their location.

[0315] The door device 1123 may include at least one UWB component (subsystem) and / or a security authentication module. The UWB component may be a combination of the above Figure 1 Examples of UWB subsystems described in .

[0316] The UWB component can be used to communicate with the mobile device for door access and door ranging to identify whether the mobile device is within the valid range to perform the transaction process and pass through the door.

[0317] In an embodiment, the UWB component may support at least one of the following features.

[0318] -Execute DS-TWR - Perform gate connection and gate ranging -Provide an interface to the security authentication module The security authentication module can be used to verify whether the mobile device is authenticated to use the door system.

[0319] In an embodiment, the security authentication module may support at least one of the following features.

[0320] - Provides interface to UWB components -Communication capability via UWB interface - Ability to sync with SGS operator servers (3) The SGS operator server 1130 can manage the entire door system. To this end, the SGS operator server can communicate with the mobile device and the smart station.

[0321] Fig.12 An example operation scenario of a door system according to an embodiment of the present disclosure is shown.

[0322] Fig.12 The door system can be Fig.11 Example of a door system.

[0323] refer to Fig.12 In operation 1, when a mobile device (or a user carrying a mobile device) enters the BLE area of ​​the door system, the mobile device may receive a BLE broadcast message (data packet) from at least one BLE anchor point of the smart station. The at least one BLE anchor point may be located in the BLE area.

[0324] In operation 2, upon receiving the BLE broadcast message, a preparation process for the door system may be performed. In other words, the door system may be prepared. In an embodiment, the preparation process may be activated by the UWB component of the mobile device, and the preparation process is used to obtain authentication related information and / or UWB related information from the SGS operator server.

[0325] In operation 3, when the mobile device enters the location estimation area, the mobile device may estimate its location to determine the closest gate it will pass through. In an embodiment, the mobile device may receive a TDoA message from at least one TDoA anchor point of the smart station and use the D-TDoA scheme to estimate its location. The mobile device's application (SGS application) may provide or use the location of the gate(s).

[0326] In operation 4, the mobile device may select the closest door. In an embodiment, the mobile device may select the closest door based on the estimation result of the location of the mobile device and the location of the door(s).

[0327] In operation 5, the mobile device may perform a process for UWB ranging with the selected gate. After selecting the closest gate, the mobile device may participate in competition in a specific time slot to perform UWB ranging with the gate. The gate may be informed of the time slot (contention cycle) that may participate in the competition through UWB messages. If the mobile device obtains an opportunity to transmit, the gate may be used to perform UWB ranging and service agreements (transactions). After verifying appropriate authentication or payment capabilities through the exchange of messages and UWB ranging, the user may pass through the gate.

[0328] Fig.13 The intelligent door service process of the door system according to the embodiment of the present disclosure is shown.

[0329] Fig.13 The door system can be Fig.11 Example of a door system.

[0330] refer to Fig.13 , a smart door service process can be performed between a smart station including at least one door device and at least one mobile device.

[0331] The smart door service process may include a smart door service initiation phase (phase 1), a door discovery and location estimation phase using D-TDoA (phase 2), a door access phase for UWB slot reservation (phase 3), and / or a transaction phase through UWB (phase 4). If the transaction (transaction phase) according to the smart door service process is completed, the specific door may be opened. Therefore, the user may enter or exit the specific door.

[0332] In an embodiment, the smart door service initiation phase may include, for example Fig.12 Operations 1 and 2.

[0333] In an embodiment, the door discovery and position estimation phase may include e.g. Fig.12 Operation 3.

[0334] In an embodiment, the gate access phase for UWB time slot reservation may include, for example Fig.12 The gate access operation (participation in competition) of operation 4 and operation 5. During the gate access phase (process), the mobile device can participate in competition to occupy the time slot for data communication. If the mobile device obtains a specific time slot, the gate and the mobile device can exchange data for the service agreement.

[0335] In an embodiment, the transaction phases over UWB may include, for example Fig.12 Operation 5 is a UWB ranging and service protocol (transaction) operation. In an embodiment, the service protocol may require multiple, for example, ranging blocks to complete the message exchange process. For example, in order to complete the message exchange process for each gate, multiple ranging rounds may be required, and since one round for a corresponding gate can be assigned to one block, the service protocol may require multiple blocks to complete the message exchange process.

[0336] The present disclosure provides a method for performing posture detection by an electronic device using a UWB signal. The UWB signal may be a UWB signal for DL-TDoA ranging (OWR) or a UWB signal for DS-TWR ranging. In the present disclosure, the posture may be, for example, a posture related to a position where a user is holding a user device (e.g., handheld) or a position where a user is placing a user device (e.g., back pocket / front pocket).

[0337] The present disclosure provides a method in which an electronic device receives a UWB signal to obtain UWB channel impulse response (CIR) data, and classifies whether the UWB signal is a line of sight (LOS) signal or a non-LOS (NLOS) signal based on the UWB CIR data. In order to classify LOS signals or NLOS signals, a convolutional neural network (CNN) algorithm (model) can be used. Therefore, the electronic device of the present invention can have high classification accuracy by classifying data with time series characteristics using a CNN model. The effective CIR data from which noise is removed from the UWB CIR data can be used as input data to the CNN model for classification of LOS signals or NLOS signals. Therefore, the classification accuracy of LOS / NLOS signals and the classification accuracy of posture can be improved.

[0338] The present disclosure provides a method for an electronic device to perform posture classification using a classification result of a LOS signal or a NLOS signal (signal classification result) and sensing data. Data (IMU data) of an inertial measurement unit (IMU) sensor can be used as sensing data. Two CNN models (e.g., two parallel CNN models) different from the CNN model used for classification of LOS / NLOS signals can be used to perform posture classification using the signal classification result and sensing data. One of the two CNN models can be trained using the IMU data (first training data) associated with the LOS signal, and the other CNN model can be trained using the IMU data (second training data) associated with the NLOS signal. As described above, a separate CNN model can be used to classify data with different characteristics, thereby improving classification accuracy.

[0339] The present disclosure provides a method for an electronic device to filter the prediction data output from each CNN model before the final LOS / NLOS signal classification and the final posture classification. For filtering, a sliding average filter can be used. Therefore, the classification accuracy of the LOS / NLOS signal and the classification accuracy of the posture can be improved.

[0340] The present disclosure provides a method that can use classified LOS / NLOS signals and / or classified postures by various applications of a user device. For example, the classification method of the present disclosure can be used in an application for a tagless door (smart door), a digital car key application, or a point of service (POS) application. The application can use the accurately classified LOS / NLOS signals and / or the classified postures to appropriately provide specific services or functions / parameters associated with specific services.

[0341] In an embodiment, an application may use accurately classified LOS / NLOS signals to perform adaptive ranging frequency adjustment for power saving. For example, an application may set a maximum sleep duration by using adaptive ranging frequency adjustment of classified LOS / NLOS signals.

[0342] In an embodiment, an application may improve the accuracy of position estimation by selectively using only LOS signals through accurate LOS / NLOS signal classification.

[0343] In an embodiment, the application may set adaptive access boundaries through accurate classification of LOS / NLOS signals and / or posture.

[0344] In the following, various embodiments are described in which a user device sets an adaptive access boundary in a gate environment by classification of LOS / NLOS signals and / or postures. For example, the user device may adaptively set (or adjust) a gate ranging area (e.g., a gate access area and / or a gate area) in a gate environment by classification of LOS / NLOS signals and / or postures.

[0345] First, refer to Fig.14 A door environment to which the present disclosure can be applied is exemplarily described.

[0346] Fig.14 A door environment according to an embodiment of the present disclosure is shown.

[0347] refer to Fig.14 , the gate environment may include a plurality of UWB anchor points (eg, six UWB anchor points 1411 to 1416 ) for DL-TDoA, at least one user device 1420 supporting UWB communication, and / or at least one gate device 1430 supporting UWB communication.

[0348] The door environment can be divided into door access area A GA , Door Area A G and the remaining area. The remaining area may include the location estimation area (e.g., Fig.12 In the present disclosure, an area including a gate access area and a gate area may be referred to as a gate ranging area (e.g., Fig.12 door ranging area).

[0349] In the present disclosure, the gate access area may be an area where DS-TWR for transactions between a user device and a gate device is initiated. When a user device (or user) is located in the gate access area, DS-TWR for transactions between the user device and the gate device may be initiated.

[0350] In the present disclosure, a door zone may be an area where a door device may open a door for a corresponding user based on the result of a transaction through DS-TWR. When a user device (or user) is located in the door zone, the door device may open the door based on the result of a transaction with the user device through DS-TWR.

[0351] Fig.15 The problem occurring in a door environment according to an embodiment of the present disclosure is exemplarily illustrated.

[0352] Fig.15 The door environment can be e.g. Fig.14 door environment.

[0353] Fig.15 Part (a) of FIG. 5 shows a problem that occurs when DL-TDoA is performed (DL-TDo A problem).

[0354] refer to Fig.15 In part (a), although the actual user (or user device) 1421 is located in the gate access area, due to low position accuracy such as in the NLOS environment, the user device 1420 may identify itself as being located in the gate access area A. GA In this case, even if the actual user (or user device) 1421 is located in the gate access area, the user device 1421 only performs DL-TDoA positioning and may not initiate DS-TWR with the gate device for transaction. Therefore, the opening of the gate may be delayed.

[0355] The DL-TDoA problem can be solved by extending the gate access area according to the NLOS condition.

[0356] Fig.15 Part (b) shows a problem that occurs when DS-TWR is performed (DS-TWR problem).

[0357] refer to Fig.15 In part (b), although the actual user (or user device) 1421 is located in the gate area, the user device 1420 may identify itself as being located in the gate access area A. G 1420 is outside the door (e.g., located in a door access area). Even if the location identified by the user device 1420 is accurate, this may occur when the actual location of the user and the location identified by the user device are different, such as when the user device 1420 is in the user's back pocket. Alternatively, this may occur when the location identified by the user device 1420 is inaccurate, for example, when the location identified by the user device 1420 is measured to be farther away from the door than the actual location due to the NLOS environment, such as when the user device 1420 is in the user's back pocket. In this case, the door may not open at the correct time, but may open too early, or may open too late.

[0358] The DS-TWR problem can be solved by adjusting the margin (or length) of the gate area according to the pose of the user equipment.

[0359] Hereinafter, various embodiments for solving the above-mentioned DL-TDoA problem and DS-TWR problem are exemplarily described.

[0360] Fig.16a A method for setting an adaptive door access zone in a door environment according to an embodiment of the present disclosure is shown. Fig.16b An example of a door access area expanded according to an adaptive door access area setting method in a door environment according to an embodiment of the present disclosure is shown. Fig.17 A door access area ratio according to LOS probability according to an embodiment of the present disclosure is shown.

[0361] Fig.16a / Fig.16b The door environment can be e.g. Fig.14 door environment.

[0362] The user equipment may obtain the LOS probability of the UWB signal for DL-TDoA (DL-TDoA signal) received from each UWB anchor point. Here, the LOS probability refers to the probability that the corresponding UWB signal is a LOS signal. The LOS probability may be expressed as p(LOS). In an embodiment, the user equipment may use a pre-trained LOS / NLOS classification model (e.g., Figure 7 / Figure 8 The CNN-based LOS / NLOS classification model (CNN model) obtains the LOS probability (LOS probability data) of the UWB signal (DL-TDoA signal) for each UWB anchor point.

[0363] The following table 6 shows the Fig.14 An example of the LOS probability (LOS probability data) of each UWB anchor point obtained in a gate environment.

[0364] [Table 6]

[0365] Referring to Table 6, for example, the LOS probability of the UWB signal of the first UWB anchor point 1411 is 0.42, and the LOS probability of the UWB signal of the second UWB anchor point 1412 is 0.51.

[0366] The user equipment may determine a LOS-related state (condition) based on the obtained LOS probabilities. In an embodiment, the user equipment may calculate an average of the obtained LOS probabilities (average LOS probability (average p(LOS), ) (1620), and determine whether the user equipment is in the LOS environment (whether the user equipment is in the LOS state) based on the calculated average LOS probability (1630). For example, when the calculated average value of the LOS probability is greater than a preset first threshold value (e.g., 0.5), the user equipment can determine that the state (or environment) is the LOS state (or LOS environment). When the calculated average value of the LOS probability is not greater than the preset first threshold value (e.g., 0.5), the user equipment can determine that the state (or environment) is the NLOS state (or NLOS environment).

[0367] When it is recognized that the user equipment is in the LOS state (or LOS environment), the user equipment may maintain the initially set door access area ( 1640 ).

[0368] When it is recognized that the user equipment is in the NLOS state (or NLOS environment), the user equipment may adjust the initially set door access area based on the average value of the LOS probability (average LOS probability value) ( ​​1650 ).

[0369] For example, Fig.17 As shown, it can be assumed that the door access area is different from the initially set door access area (e.g., Fig.16b The door access area ratio x of the door access area 1601) can be expanded to a preset maximum value of the door access area ratio x (e.g., 1.3). Here, x represents the door access area ratio. In this case, when the value of the average LOS probability is less than the second threshold value (e.g., 0.1), the user equipment can expand the door access area to the maximum value of the door access area ratio x (e.g., 1.3), (i.e., add the door access area initially set 0.3 expansion area (for example, Fig.16b When the value of the average LOS probability is greater than the second threshold (e.g., 0.1) and less than the first threshold (e.g., 0.5), the user device may linearly expand the door access area, e.g., Fig.17 For example, based on Fig.17 The gate access area ratio x is determined by the value of the linear function of the average LOS probability.

[0370] In an embodiment, the user device may extend the door access area in the direction of entering the door, such as Fig.16b In other words, Fig.16b As shown, an extension area 1602 for the door access area may be added in the direction of entry to the door.

[0371] In an embodiment, the user device may transmit information about the adjusted gate access area to the gate device. The gate device may perform DS-TWR with the user device based on the corresponding information.

[0372] At the same time, there may be limitations in extending the door access area in the door entry direction. For example, there may be a situation where the area cannot be extended in the door entry direction according to the actual building structure. Therefore, it is necessary to consider extending the door access area in the extendable direction using map information about the door installation space (door environment).

[0373] In an embodiment, the user device may communicate with the smart station via OOB communication (eg, BLE communication) and / or in-band communication when initially entering (eg, when initially entering the smart station). Fig.12 Get information about the extended area.

[0374] In an embodiment, the information about the expansion area may include: information about the maximum value of the door access area ratio x and / or information about at least one maximum expandable area (e.g., the number of maximum expandable areas, or the position and / or size of each expandable area). In an embodiment, upon initial entry, the information about the expansion area may be received together with the information about the initially set door access area. The information about the door access area may include information about the position and / or size of the initially set door access area.

[0375] Fig.18a and Fig.18b A method for setting a maximum expandable area in a door environment to set an adaptive door access area according to an embodiment of the present disclosure is shown.

[0376] Fig.18a and Fig.18b The door environment can be e.g. Fig.14 door environment.

[0377] exist Fig.18a and Fig.18b In the case of an embodiment of the present invention, map information (eg, indoor map) may be used to set the door access area. Fig.18a and Fig.18b In the case of the embodiment, the range of the door access area to be extended can be set differently according to the shape of the map of the area in which the door is installed.

[0378] exist Fig.18a In the embodiment of FIG. 1 , it is assumed that an initial door access area 1801a and maximum expandable areas 1802a-1 and 1802a-2 of the door access area are initially set.

[0379] refer to Fig.18a , in such Fig.18aIn the map form shown, the door access area can be expanded to the left and right of the initial door access area 1801a. The maximum expandable area that can be expanded to the left can be the same as the first maximum expandable area 1802a-1, and the maximum expandable area that can be expanded to the right can be the same as the second maximum expandable area 1802a-2.

[0380] ]exist Fig.18b In the embodiment of , it is assumed that initial door access areas 1801b-1 and 1801b-2 and maximum expandable areas of the door access areas 1802b-1, 1802b-1, 1802b-3 and 1802b-4 are initially set.

[0381] refer to Fig.18b , in such Fig.18b In the map form shown, the door access area can be expanded to the top / bottom / left / right of the initial door access areas 1801b-1 and 1801b-2. The maximum expandable area that can be expanded to the right can be the same as the first maximum expandable area 1802b-1, the maximum expandable area that can be expanded to the left can be the same as the second maximum expandable area 1802b-1, and the maximum expandable area that can be expanded upward (or downward) can be the same as the third maximum expandable area 1802b-3 and the fourth maximum expandable area 1802b-4.

[0382] The maximum expandable area may be preset. For example, a server (eg, a backend server) connected to the door may preset the maximum expandable area based on map information. In an embodiment, the setting of the maximum expandable area may be an output of image processing using the map information as input.

[0383] Information about the set maximum expandable area may be transmitted to the user device. The user device may obtain information about the maximum expandable area as information about the expansion area at the time of initial entry (e.g., when initially entering the smart station) through OOB communication (e.g., BLE communication) and / or in-band communication. In an embodiment, at the time of initial entry, the information about the expansion area may be received together with information about the initially set door access area.

[0384] Fig.19a A method for setting an adaptive door access area using a maximum expandable area in a door environment according to an embodiment of the present disclosure is shown. Fig.19b An example of a door access area expanded according to an adaptive door access area setting method in a door environment according to an embodiment of the present disclosure is shown.

[0385] Fig.19a / Fig.19b The door environment can be e.g. Fig.14 door environment.

[0386] For ease of description, assume that the maximum expandable area of ​​FIG. 19 is, for example, Fig.18b The maximum expandable area is, but is not limited to, Fig.18a The maximum expandable area can be used in the embodiment of Figure 19.

[0387] In an embodiment, for setting Fig.19a The adaptive gate access area method can be e.g. Fig.16a In this case, for example, Fig.16a Operations 1610 to 1630 are performed after Fig.19a For a description of the corresponding operations, please refer to Fig.16a Description.

[0388] exist Fig.19a / Fig.19b In the case of the embodiment of the present invention, the same expansion ratio a can be used to determine the expansion degree of each area. In order to determine the expansion ratio a, it is first necessary to determine the door access area ratio x and the entire expansion area.

[0389] refer to Fig.19a , the user equipment may determine the gate access area ratio x based on the value of the average LOS probability (1910). The method for determining the gate access area ratio x may follow the method described in FIG. 16 / Fig.17 The method described in the examples.

[0390] The user equipment may determine a total extension area EA based on the gate access area ratio ( 1920 ).

[0391] In an embodiment, the total extension area EA may be determined by Equation 1 below.

[0392] [Equation 1]

[0393] Here, x represents the gate access area ratio, and A GA Indicates the initially set door access area.

[0394] The user equipment can be based on the total expansion area EA and the total maximum expandable area BA t The expansion area a (1930) is determined.

[0395] In an embodiment, the extension area a may be determined by Equation 2 below.

[0396] [Equation 2] a=EA / BA t Here, BA tcorresponds to the sum of the boundary areas BA corresponding to the maximum expandable area, and as Fig.19b As shown, when three maximum expandable areas are set for the door access area, it can be expressed as shown in the following equation 3.

[0397] [Equation 3] BA t =BA 1 +BA 2 +BA 3 Here, BA 1 represents a boundary area corresponding to the first maximum expandable area (eg, the first maximum expandable area 1802 b - 1 ), BA 2 represents a boundary area corresponding to the second largest expandable area (eg, the second largest expandable area 1802 b - 2 ), and BA 3 Indicates a boundary area corresponding to the third maximum expandable area (eg, the third maximum expandable area 1802 b - 2 ).

[0398] The user equipment may arrange each expansion area according to the expansion ratio (1940).

[0399] In an embodiment, each expansion area according to the expansion ratio a may be determined by Equation 4 below.

[0400] [Equation 4]

[0401] like Fig.19b As shown, each determined extension area may be set within a corresponding boundary area.

[0402] Therefore, in Fig.19a / Fig.19b In the case of the embodiment of the present invention, the door access area can be adaptively expanded according to the ratio of each area. Fig.16b Compared with the embodiment of Fig.19b In the case of the embodiments, the door access area can be extended in various directions and / or forms.

[0403] In an embodiment, the user device may transmit information about the adjusted gate access area to the gate device. The gate device may perform DS-TWR with the user device based on the corresponding information.

[0404] Fig.20a A method for setting an adaptive door access area using a maximum expandable area in a door environment according to an embodiment of the present disclosure is shown. Fig.20b An example of a door access area expanded according to an adaptive door access area setting method in a door environment according to an embodiment of the present disclosure is shown.

[0405] Fig.20a / Fig.20b The door environment can be e.g. Fig.14 door environment.

[0406] For ease of description, assume Fig.20a / Fig.20b The maximum expandable area is, for example, Fig.18b The maximum expandable area is, but is not limited to, Fig.20a / Fig.20b In the embodiments, you can use Fig.18a The maximum expandable area.

[0407] exist Fig.20a / Fig.20b In the case of an embodiment, with Fig.19a / Fig.19b Different embodiments may further use different reset ratios for each expandable area (boundary area). In an embodiment, the reset ratio may be determined by considering the floating headcount ratio of the corresponding area. In an embodiment, the floating headcount ratio may be determined by path tracking of the user based on DL-TDoA. To this end, the user device may record the path immediately before passing through the gate and transmit information about the path to the gate device.

[0408] In an embodiment, for setting Fig.20a The adaptive gate access area method can be e.g. Fig.16a An example of operation 1650. For example, after arranging each expansion area, Fig.20a Adaptive door access area setting method. For example, Fig.20a The adaptive door access area setting method can be based on Fig.19a The adaptive door access area setting method of the present invention is a reset method performed after arranging each extended area. The description of the arrangement operation of each extended area can be referred to Fig.19a Description.

[0409] refer to Fig.20a , the user equipment may determine a reset ratio (2010) of each expansion area (or boundary area) according to each floating population ratio.

[0410] To determine the reset ratio , the floating headcount ratio of each boundary area should be determined first. The floating headcount ratio can be determined by a server (e.g., a backend server) connected to the gate device based on information about the path transmitted from a plurality of user devices. Therefore, information about the floating headcount ratio of each boundary area thus determined can be transmitted to the user device together with information about the maximum expandable area corresponding to the boundary area. For example, upon initial entry (e.g., upon initial entry to the site), the user device can obtain information about the floating headcount ratio of each boundary area and information about the maximum expandable area through OOB communication (e.g., BLE communication) and / or in-band communication.

[0411] In an embodiment, the reset ratio of each boundary area It can be determined by the following equation 5.

[0412] [Equation 5]

[0413] here, represents a reset ratio of a first boundary area (eg, a boundary area corresponding to the first maximum expandable area 1802 b - 1 ), represents a reset ratio of a second boundary area (eg, a boundary area corresponding to the second maximum expandable area 1802 b - 2 ), and Indicates a reset ratio of a third boundary area (eg, a boundary area corresponding to the third maximum expandable area 1802 b - 2 ).

[0414] EA 1 Indicates the current expansion area of ​​the first boundary area, EA 2 represents the current extension area of ​​the second boundary area, and EA 3 represents the current extension area of ​​the third boundary area. Fig.19a method to determine (or arrange) the corresponding extension area.

[0415] u1 represents the floating population ratio of the first boundary area, u2 represents the floating population ratio of the second boundary area, and u3 represents the floating population ratio of the third boundary area. The total floating population ratio can be expressed as ut=u1+u2+u3.

[0416] The user equipment may reset each expansion area based on each reset ratio (2020).

[0417] In an embodiment, an expansion area (new expansion area) reset according to the determined reset ratio may be determined by Equation 6 below.

[0418] [Equation 6]

[0419] Here, EA 1,new Indicates the new extension area of ​​the first boundary area, EA 2,new represents the new expansion area of ​​the second boundary area, while EA 3,new Indicates the new extension area of ​​the third boundary area.

[0420] Each extension area thus reset can be in e.g. Fig.20b For example, Fig.20b As shown, the new extension area EA of the second boundary area with the highest floating population ratio can be 2,new Reset to an expansion area larger than the existing expansion area, and the new expansion area EA of the first boundary area with an intermediate floating population ratio can be 1,new Reset to an expansion area with the existing expansion area maintained and the third boundary area with the lowest floating number ratio can be a new expansion area EA 1,new Reset to a smaller extent than the existing extent.

[0421] By setting different weights of the expansion areas in consideration of the floating number of people ratio, for example, an expansion area corresponding to a corresponding environment (eg, a multi-user environment) may be adaptively provided.

[0422] The user device may transmit information about the adjusted (or reset) gate access area to the gate device. The gate device may perform DS-TWR with the user device based on the corresponding information.

[0423] Fig.21 A method for setting an adaptive gate area according to an embodiment of the present disclosure is shown. Fig. 22 An example of a door area set according to an adaptive door area setting method in a door environment according to an embodiment of the present disclosure is shown.

[0424] Fig.21 and Fig. 22 The door environment can be e.g. Fig.14 door environment.

[0425] As described above, the position (or posture) of the user device affects the time when the door device opens the door. For example, depending on the posture of the user device, the door may be opened too early or too late. Therefore, it is necessary to consider a method of opening the door at an appropriate time by adaptively adjusting the door area according to the posture of the user device.

[0426] refer to Fig.21 , the user device can use the IMU data received from the gate device and the UWB signal for DS-TWR to classify the pose of the user device. The user device can use a pre-trained pose classification model (e.g., based on Fig. 9 / Fig.10The CNN pose model (CNN model) uses the IMU data and the UWB signal for DS-TWR (UWB TWR data) to classify the pose of the user device (2110).

[0427] The posture thus classified may be one of the above-mentioned hand-held (LOS) posture, hand-held (NLOS) posture, front-of-bag (LOS) posture, or back-of-bag (NLOS) posture, but is not limited thereto.

[0428] The user device may adjust the gate area based on the classified pose (2120). For example, the user device may adjust the margin (eg, length) of the gate area based on the classified pose.

[0429] For example, Fig. 22 As shown in part (a) of FIG. 2 , when the classified posture is the first posture in which the user device is located in front of the user (e.g., a handheld (LOS) posture or a handheld (NLOS) posture), the user device may adjust the length h of the gate area according to the classified posture by the actual position error hpose. For example, the user device may adjust the length of the gate area by the actual position error (hpose=-20).

[0430] For example, Fig. 22 As shown in part (b) of , when the classified posture is a second posture (eg, a front pocket (LOS) posture) in which the user device is located at a position close to the user, the user device may maintain the length h of the gate area.

[0431] For example, Fig. 22 As shown in part (c) of , when the classified posture is the third posture (e.g., the back pocket (NLOS) posture) in which the user device is located behind the user, the user device may adjust the length h of the door area by the actual position error hpose according to the classified posture. For example, the user device may adjust the length of the door area by the actual position error (hpose=+30) as much as the thickness of the user's body.

[0432] The user device may transmit information about the adjusted door area to the door device. The door device may open the door at an appropriate time by performing DS-TWR for a transaction with the user device based on the corresponding information.

[0433] Through adaptive adjustment of the door area, the door can be opened at the appropriate time.

[0434] Above Figures 14 to 22 The embodiments can be combined without contradicting each other.

[0435] Fig.23 2 is a diagram illustrating a structure of an electronic device according to an embodiment of the present invention.

[0436] exist Fig.23 In the embodiment of the present invention, the electronic device may be a user's electronic device (user device) or a server.

[0437] refer to Fig.23 , the electronic device may include a transceiver 2310, a controller 2320, and a storage unit 2330. In the present disclosure, the controller may be defined as a circuit, an application specific integrated circuit, or at least one processor.

[0438] The transceiver 2310 may send and receive signals to and from other network entities. The transceiver 2310 may send / receive data for debugging.

[0439] According to an embodiment, the controller 2320 may control the overall operation of the electronic device. For example, the controller 2320 may control the inter-block signal flow to perform the operation according to the above flowchart. Specifically, the controller 2320 may control the above reference Figures 1 to 22 Describe the operation of an electronic device.

[0440] The storage unit 2330 may store at least one of information transmitted / received via the transceiver 2310 and information generated via the controller 2320. For example, the storage unit 2330 may store the above reference Figures 1 to 22 Describes the information and data necessary for adaptive zone adjustment.

[0441] In the above specific embodiments, the components included in the present disclosure are expressed in singular or plural form, depending on the specific embodiment proposed. However, the choice of singular and plural forms is to adapt to the context suggested by the convenience of description, and the present disclosure is not limited to singular and plural components. As used herein, the singular forms "a", "an" and "the" are also intended to include plural forms, unless the context clearly indicates otherwise.

[0442] Although specific embodiments of the present invention have been described above, various changes may be made thereto without departing from the scope of the present invention. Therefore, the scope of the present disclosure should not be limited to the above embodiments, but should be defined by the appended claims and their equivalents.

Claims

1. A method for utilizing UWB communication by an electronic device, the method comprising: Obtaining LOS probability data using a trained first convolutional neural network (CNN) model based on a DL-TDoA signal received from at least one UWB anchor point; obtaining an average LOS probability based on the LOS probability data; Based on the average LOS probability, determining whether the electronic device is in a LOS environment; maintaining an initially set door access area while the electronic device is in the LOS environment; and In the case where the electronic device is in the LOS environment, adjusting the door access area according to the value of the average LOS probability, The gate access area is an area in which the electronic device initiates DS-TWR ranging for a transaction with the gate device.

2. The method according to claim 1, wherein: Adjusting the door access area includes: determining an expansion ratio based on the average LOS probability; and At least one expansion area is set based on the expansion ratio, wherein each expansion area is set in a maximum expandable area corresponding to the corresponding expansion area.

3. The method according to claim 2, wherein: Determining the expansion ratio includes: determining a door access area ratio based on the value of the average LOS probability; and The expansion ratio is determined based on the door access area ratio.

4. The method according to claim 2, further comprising: determining a reset ratio for each expansion area based on the information about the floating headcount ratio; as well as Based on the reset ratio, the at least one expansion region is reset.

5. The method according to claim 4, wherein: The information about the floating headcount ratio is generated based on path information transmitted from electronic devices of a plurality of users.

6. The method according to claim 1, further comprising: Based on the UWB TWR data and the IMU data received from the gate device, classify the posture of the electronic device using a pre-trained second CNN model; as well as A door area is adjusted based on the classified posture, wherein the door area is an area in which the door device opens a door according to a result of the transaction.

7. An electronic device using UWB communication, the electronic device comprising: Transceiver; as well as a controller connected to the transceiver, wherein the controller is configured to: Obtaining LOS probability data using a trained first convolutional neural network (CNN) model based on a DL-TDoA signal received from at least one UWB anchor point; obtaining an average LOS probability based on the LOS probability data; Based on the average LOS probability, determining whether the electronic device is in a LOS environment; maintaining an initially set door access area while the electronic device is in the LOS environment; and In the case where the electronic device is in the LOS environment, adjusting the door access area according to the value of the average LOS probability, and The gate access area is an area in which the electronic device initiates DS-TWR ranging for a transaction with the gate device.

8. The electronic device according to claim 7, wherein: The controller is configured to: determining an expansion ratio based on the average LOS probability; and At least one expansion area is set based on the expansion ratio, wherein each expansion area is set in a maximum expandable area corresponding to the corresponding expansion area.

9. The electronic device according to claim 8, wherein: The controller is configured to: determining a door access area ratio based on the value of the average LOS probability; and The expansion ratio is determined based on the door access area ratio.

10. The electronic device according to claim 8, wherein: The controller is configured to: determining a reset ratio for each expansion area based on the information about the floating headcount ratio; and Based on the reset ratio, the at least one expansion region is reset.

11. The electronic device according to claim 10, wherein: The information about the floating headcount ratio is generated based on path information transmitted from electronic devices of a plurality of users.

12. The electronic device according to claim 7, wherein: The controller is configured to: Based on the UWB TWR data and the IMU data received from the gate device, classifying the posture of the electronic device using a pre-trained second CNN model; and A door area is adjusted based on the classified posture, wherein the door area is an area in which the door device opens a door according to a result of the transaction.

Images