User equipment and operating method thereof

Abstract

A user equipment (UE) supporting a first radio access technology (RAT) network and a second RAT network, the UE comprising: processing circuitry configured to monitor whether a location of the UE has changed from a first location to obtain a monitoring result, and performing a reconnection operation to a first RAT network based on a monitoring result, a network connected to the UE switching from the first RAT network to a second RAT network based on the UE moving to a first location.

Description

[0001] This application is based on and claims the benefit of priority from Korean Patent Application No. 10-2023-0150297 filed on November 2, 2023, Korean Patent Application No. 10-2024-0016222 filed on February 1, 2024, and Korean Patent Application No. 10-2024-0049401 filed on April 12, 2024, in the Korean Intellectual Property Office, the disclosure of each of which is incorporated herein in its entirety by reference. Technical Field

[0002] The inventive concept relates to wireless communications, and more particularly, to a user equipment (UE) supporting multiple radio access technologies (RATs) and an operating method thereof. Background Art

[0003] Recently, UEs for wireless communication may support various RATs such as a third generation (3G) network, a fourth generation (4G) (or Long Term Evolution (LTE)) network, and a fifth generation (5G) network.

[0004] When the UE moves to a specific location while performing communication using a first RAT network, the UE may switch to an available second RAT network because the first RAT network is temporarily unavailable. The UE may perform communication using the second RAT network at the specific location, and also repeatedly perform an operation for returning to the first RAT network (e.g., a reconnection operation to the first RAT network). When the UE continuously stays at the specific location, the operation for returning to the first RAT network may cause excessive power consumption. Summary of the invention

[0005] The inventive concept provides a user equipment (UE) for efficiently performing a reconnection operation to a previously used Radio Access Technology (RAT) network by confirming a change in a user's location in a scenario where the previously used RAT network is switched to a different RAT network due to the user moving to a specific location, and a method of operating the UE.

[0006] According to an aspect of the inventive concept, a UE is provided, the UE supporting a first RAT network and a second RAT network, the UE comprising: a processing circuit system configured to monitor whether a location of the UE has changed from the first location to obtain a monitoring result, a network connected to the UE switching from the first RAT network to the second RAT network based on the UE moving to the first location, and performing a reconnection operation to the first RAT network based on the monitoring result.

[0007] According to an aspect of the inventive concept, there is provided an operation method of a UE, the UE supporting a first RAT network and a second RAT network, the method comprising: switching from the first RAT network to the second RAT network based on the UE moving to a first location, the switching step comprising switching communication from a first base station to a second base station, the first base station being based on the first RAT network, and the second base station being based on the second RAT network; monitoring whether the location of the UE has changed to obtain a monitoring result; and performing a reconnection operation to the first RAT network based on the monitoring result.

[0008] According to one aspect of the inventive concept, a method for operating a UE is provided, the method comprising: performing communication based on a primary radio access technology (RAT) network in a normal state; switching from the primary RAT network to a secondary RAT network based on the UE moving to a first location; transitioning from the normal state to a switching state based on the switching; monitoring whether the UE has left the first location in the switching state to obtain a monitoring result; and determining whether to transition from the switching state to a reconnectable state based on the monitoring result, the reconnectable state being a state for a reconnection operation to the primary RAT network. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Embodiments of the inventive concept will be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings, in which: Figure 1 A wireless communication system according to an embodiment is shown; Figure 2A and Figure 2B is a block diagram illustrating a user equipment (UE) according to an embodiment; Figure 3 shows the status of a UE according to an embodiment; Figure 4 is a flowchart illustrating an operation method of a UE according to an embodiment; FIG. 5A to FIG. 5D It specifically shows Figure 4 Flowchart of operations S110 and S120; Figure 6 It specifically shows Figure 4 Flow chart of operation S130; Figure 7 is a signaling diagram illustrating an operation method between a processor included in a UE and a location change confirmation model executed by the processor according to an embodiment; Figure 8 Show Figure 7 The position change confirms the architecture of the model; Fig. 9A and Fig. 9B shows a monitoring operation using a position change confirmation model according to an embodiment; Fig.10 is a flow chart illustrating a method of training a position change confirmation model according to an embodiment; Fig.11 is a flowchart illustrating an operation method of a UE according to an embodiment; Fig. 12A and Fig. 12B It specifically shows Fig.11 Flowchart of operations S410 and S420; Fig.13 An operation method of a UE according to an embodiment is shown; Fig.14A and Fig. 14B Is used to describe Fig.13 A table of operating methods of a UE; Fig.15 is a signaling diagram illustrating an operation method between a processor included in a UE and a location change confirmation model executed by the processor according to an embodiment; Fig.16 It specifically shows Fig.15 Flowchart of operation S540; and Fig.17 is a conceptual diagram illustrating an Internet of Things (IoT) network system according to an embodiment. DETAILED DESCRIPTION

[0010] Figure 1 A wireless communication system 1 according to an embodiment is shown. The wireless communication system 1 can provide communication services based on a plurality of radio access technology (RAT) networks to a user equipment (UE) 30. For example, the wireless communication system 1 can provide communication services based on at least two types of networks among a third generation (3G) network, a fourth generation (4G) network, a wireless broadband (Wibro) network, a global system for mobile communications (GSM) network, a fifth generation (5G) network, a sixth generation (6G) network, etc.

[0011] In addition, the various functions described below may be implemented or supported by artificial intelligence technology or one or more computer programs, and each of the computer programs is composed of computer-readable program code and executed in a non-transitory computer-readable medium. The terms "application" and "program" indicate one or more computer programs, software components, instruction sets, processes, functions, objects, classes, instances, related data, or some of them suitable for implementing appropriate computer-readable program codes. The term "computer-readable program code" includes all types of computer codes, including source code, object code, and run code. The term "computer-readable medium" includes each type of non-transitory computer-readable medium (such as read-only memory (ROM), random access memory (RAM), hard drive, compact disk (CD), digital video disk (DVD), or any other type of memory) that can be accessed by a computer. "Non-transitory" computer-readable media do not include temporary wired, wireless, optical, or other communication links through which electrical signals or other signals are transmitted. Non-transitory computer-readable media include media in which data is permanently stored and media in which data is stored and later overwritten by other data (such as rewritable optical disks or erasable memory devices).

[0012] The embodiments described below take a hardware-based access method as an example. However, because the embodiments include techniques using both hardware and software, the embodiments do not exclude a software-based access method.

[0013] Reference Figure 1 , the wireless communication system 1 may include a first base station 10, a second base station 20 and / or a UE 30. The base station may generally be referred to as a fixed station that communicates with the UE 30, and may exchange control information and data by communicating with the UE 30. For example, the base station may be variously referred to as a Node B, an evolved Node B (eNB), a next generation Node B (gNB), a sector, a site, a base transceiver system (BTS), an access point (AP), a relay node, a remote radio head (RRH), a radio unit (RU), a small cell, a wireless device, a device, etc.

[0014] The UE 30 may be referred to as a fixed or mobile device, and transmits and receives data and / or control information by communicating with the first base station 10 and / or the second base station 20. For example, the UE 30 may be referred to as a terminal, a terminal device, a mobile station (MS), a mobile terminal (MT), a user terminal (UT), a subscriber station (SS), a wireless communication device, a wireless device, a device, a handheld device, etc.

[0015] The first base station 10 may be connected to a UE 30 within a first coverage area, and provide a communication service based on a first RAT network to the UE 30. The second base station 20 may be connected to a UE 30 within a second coverage area, and provide a communication service based on a second RAT network to the UE 30. In an embodiment, the first base station 10 and the second base station 20 may be physically integrated into one base station, and the integrated base station may be implemented to support a communication service based on the first RAT network and a communication service based on the second RAT network.

[0016] Hereinafter, the first RAT network may correspond to a primary RAT network (e.g., a higher priority RAT network) that is mainly used by the UE 30, and the second RAT network may correspond to a secondary RAT network (e.g., a lower priority RAT network) that is temporarily available in place of the primary RAT network when the primary RAT network is unavailable. For example, the primary RAT network may be configured according to a request of a user of the UE 30, and the secondary RAT network may be configured according to a request of an operator or a user that provides a communication service.

[0017] When the UE 30 moves to a specific location (also referred to herein as the first location) while performing communication based on the first RAT network with the first base station 10 by connecting to the first base station 10, the first RAT network may be unavailable, so that the connection to the first base station 10 is disconnected unintentionally (for example, due to insufficient signal quality and / or strength). The UE 30 may attempt to connect to the second base station 20 in response to the disconnection from the first base station 10, and perform communication based on the second RAT network by connecting to the second base station 20. Since the UE 30 moves to the specific location, the UE 30 may switch the network connected to the UE 30 from the first RAT network to the second RAT network. In the specification, the connection of the UE 30 to the network may be interpreted as the connection of the UE 30 to the base station providing the network. In addition, in the specification, the specific location may be defined as a location that causes a handover from the primary RAT network to the secondary RAT network, or a location where the primary RAT network is unavailable, and the specific location may inclusively represent a specific point or area. The specific location may depend on the type of the primary RAT network. For example, the specific location when the primary RAT network is a 5G network may be different from the specific location when the primary RAT network is a 4G network. As an example to help understand, when the primary RAT network is a 5G network, the specific location may include the inside of an elevator, an emergency staircase inside a building, etc.

[0018] In an embodiment, the UE 30 may include a reconnection control circuit 32. The reconnection control circuit 32 may perform an operation for reconnecting to a previously connected first RAT network from a second RAT network temporarily connected due to the UE 30 moving to a specific location.

[0019] In an embodiment, the reconnection control circuit 32 may monitor a change in the location of the UE 30 from a specific location, and perform a reconnection operation to the first RAT network based on the monitoring result. As a specific example, when it is confirmed that the UE 30 has left the specific location (e.g., when it is confirmed that the UE 30 has moved to a normal location where the first RAT network as the primary RAT network is available), the reconnection control circuit 32 may start a reconnection operation to the first RAT network.

[0020] Reconnection control circuitry 32 may monitor changes in the location of UE 30 from a particular location in various ways.

[0021] For example, the reconnection control circuit 32 may monitor the change of the location of the UE 30 by using a radio frequency (RF) signal received from the second base station 20. As a specific example, the reconnection control circuit 32 may monitor the change of the location of the UE 30 based on the values ​​of a plurality of indicators generated using the RF signal received from the second base station 20. In an embodiment, the plurality of indicators are associated with a second RAT network (e.g., a secondary RAT network), and may include indicators suitable for monitoring the change of the location of the UE 30. For example, the plurality of indicators may include at least one of the following items: a global cell identifier (ID), a physical cell ID, a frequency band, a bandwidth, a received signal received power (RSRP), a reference signal received quality (RSRQ), a received signal strength indicator (RSSI), a signal to interference plus noise ratio (SINR), the number of resource blocks, a channel quality indicator (CQI), a rank indicator (RI), a precoding matrix indicator (PMI), a modulation and coding scheme (MCS), a modulation order, a block error rate (BLER), a transmission power, a Doppler frequency, and / or a delay spread. In the specification, monitoring the change of the position of the UE 30 by using the RF signal may include monitoring the change of the position of the UE 30 based on the baseband signal generated by down-converting the frequency of the RF signal. In addition, in the specification, generating the values ​​of the multiple indicators by using the RF signal may include generating the values ​​of the multiple indicators based on the baseband signal generated by down-converting the frequency of the RF signal.

[0022] As another example, the reconnection control circuit 32 may monitor the change of the position of the UE 30 by using a plurality of sensors included in the UE 30. As a specific example, since the plurality of sensors perform sensing operations related to the movement of the UE 30, the reconnection control circuit 32 may monitor the change of the position of the UE 30 based on a plurality of sensing values ​​generated using the plurality of sensors. For example, the plurality of sensors may include at least one of a gyro (gyro) sensor, an acceleration sensor, a linear acceleration sensor, and / or a geomagnetic sensor. Specifically, the reconnection control circuit 32 may confirm the movement of the UE 30 through the plurality of sensors, and determine whether the position of the UE 30 has changed based on the confirmed movement.

[0023] As another example, the reconnection control circuit 32 may monitor the change in the location of the UE 30 by using the RF signal received from the second base station 20 and a plurality of sensors. As a specific example, the reconnection control circuit 32 may monitor the change in the location of the UE 30 by using the values ​​of a plurality of indicators generated using the RF signal received from the second base station 20 and a plurality of sensing values ​​generated using a plurality of sensors simultaneously (or contemporaneously) or sequentially.

[0024] In an embodiment, the reconnection control circuit 32 may use a location change confirmation model based on a neural network (NN) to monitor the change of the location of the UE 30. For example, the reconnection control circuit 32 may input data including the collected values ​​into the location change confirmation model, and determine whether the UE 30 has left a specific location based on the output of the location change confirmation model. The collected values ​​may include at least one of the values ​​of the above-mentioned multiple indicators and at least one of the above-mentioned multiple sensing values.

[0025] In the specification, the reconnection operation to the first RAT network may be interpreted as a connection operation to a base station providing the first RAT network. That is, the reconnection operation to the first RAT network may include a reconnection operation to the previously connected first base station 10 or a connection operation to a different base station providing the first RAT network. Hereinafter, the reconnection operation to the first RAT network is described based on an example corresponding to the reconnection operation to the previously connected first base station 10.

[0026] In an embodiment, when it is confirmed that the UE 30 has left a specific location, the reconnection control circuit 32 may attempt to reconnect to the first RAT network (e.g., reconnect to the first base station 10) based on the connection history information. For example, the connection history information may include a plurality of pieces of information for connection to the first base station 10 that the UE 30 has previously exchanged with the first base station 10. As a specific example, the connection history information may include information about the first base station 10. In an embodiment, the reconnection control circuit 32 may actively request the first base station 10 to reconnect based on the connection history information. In an embodiment, the reconnection control circuit 32 may provide information required for reconnection (or otherwise used) to the first base station 10, so that the UE 30 can reconnect to the first base station 10 relatively easily.

[0027] The aforementioned operations of the reconnection control circuit 32 may be interpreted as operations of the UE 30 , and the reconnection control circuit 32 may be implemented by software executed by a processor of the UE 30 or hardware in the processor of the UE 30 .

[0028] When the network connected to UE 30 is switched from the primary RAT network to the secondary RAT network due to UE 30 moving to a specific location, UE 30 according to an embodiment can confirm whether UE 30 has left the specific location and then start a reconnection operation to the primary RAT network, thereby minimizing or reducing excessive power consumption.

[0029] The UE 30 according to the embodiment may monitor a change in the location of the UE 30 by using an RF signal based on the secondary RAT network or a plurality of sensors included in the UE 30 , thereby effectively determining whether the UE 30 has left a specific location.

[0030] In addition, the UE 30 according to the embodiment may monitor a change in the location of the UE 30 using the NN-based location change confirmation model, thereby accurately determining whether the UE 30 has left a specific location.

[0031] Figure 2A and Figure 2B is a block diagram showing a UE 100 according to an embodiment.

[0032] Reference Figure 2A , UE 100 may include a processor 110, a transceiver 120, a memory 130 and / or a plurality of antennas 121_1 to 121_x.

[0033] The transceiver 120 may receive an RF signal transmitted from a base station through a plurality of antennas 121_1 to 121_x. The transceiver 120 may down-convert the received RF signal to generate an intermediate frequency signal or a baseband signal. The processor 110 may acquire data by performing processing operations of filtering, decoding and / or digitizing the intermediate frequency signal or the baseband signal, and generate data for communicating with the base station based on the acquired data.

[0034] In addition, the processor 110 may encode, multiplex and / or simulate (e.g., perform digital-to-analog conversion) the generated data to provide an intermediate frequency signal or a baseband signal to the transceiver 120. The transceiver 120 may up-convert the intermediate frequency signal or the baseband signal to transmit the RF signal to the base station through the plurality of antennas 121_1 to 121_x.

[0035] In an embodiment, the processor 110 may include a reconnection control circuit 112, and / or the memory 130 may store a NN-based location change confirmation model 132. The location change confirmation model 132 may be executed by the processor 110 and used to monitor the change of the location of the UE 100 from a specific location. According to an embodiment, the reconnection control circuit 112 may be combined with Figure 1 The reconnection control circuit 32 discussed above is the same or similar.

[0036] When UE 100 moves to the specific location, the connection of UE 100 to the first RAT network may be disconnected, and UE 100 may be temporarily connected to the second RAT network. In this case, processor 110 may perform a reconnection operation to the first RAT network by using reconnection control circuit 112 and location change confirmation model 132.

[0037] In an embodiment, an RF signal based on the second RAT network may be received through the plurality of antennas 121_1 to 121_x and the transceiver 120, and the reconnection control circuit 112 may monitor a change in the location of the UE 100 based on values ​​of a plurality of indicators generated using the RF signal.

[0038] As a specific example, the reconnection control circuit 112 may provide an input including first data or second data generated by filtering the first data to the location change confirmation model 132, and determine whether the UE 100 has left a specific location based on the output of the location change confirmation model 132, the first data being periodically generated during a period of performing communication based on the second RAT network. For example, the first data may include at least one of the values ​​of the above-mentioned multiple indicators, and the second data may include a change between past data of the first data and current data of the first data. The second data may be defined by the following [Equation 1].

[0039] [Equation 1]

[0040] can represent the second data at time k, may represent the first data generated at time k, and may represent the first data generated at time k-1.

[0041] However, since the filtering scheme for the first data based on [Equation 1] is only an example, the present inventive concept is not limited thereto, and the second data may be generated by applying various filtering schemes to the first data.

[0042] In an embodiment, when the output of the location change confirmation model 132 indicates that the UE 100 has left a specific location, the reconnection control circuit 112 may start a reconnection operation to the first RAT network. As a specific example, the reconnection control circuit 112 may generate a signal for reconnecting to the previously connected first base station based on the connection history information stored in the memory 130, and transmit the generated signal to the first base station through the transceiver 120 and the plurality of antennas 121_1 to 121_x.

[0043] In an embodiment, the position change confirmation model 132 may adopt any NN architecture including a multi-layer perceptron (MLP) architecture, a convolutional neural network (CNN) architecture, a regional convolutional neural network (R-CNN) architecture, a region proposal network (RPN) architecture, a recurrent neural network (RNN) architecture, a stacked deep neural network (S-DNN) architecture, a state-space dynamic neural network (S-SDNN) architecture, a deconvolution network architecture, a deep belief network (DBN) architecture, a restricted Boltzmann machine (RBM) architecture, a fully convolutional network architecture, a classification network architecture, a general residual network architecture, a dense network architecture, a hierarchical pyramid network architecture, a transformer architecture, a long short-term memory (LSTM) architecture, and the like.

[0044] In an embodiment, the location change confirmation model 132 may be stored in the memory 130 in a state of being trained offline using previously collected data.

[0045] In an embodiment, the location change confirmation model 132 may be continuously updated by online training using data measured by the UE 100 in real time.

[0046] Reference Figure 2B ,and Figure 2A In contrast, the UE 100 may further include an application processor 140 and / or a plurality of sensors 150 .

[0047] In an embodiment, the plurality of sensors 150 may perform a sensing operation related to the movement of the UE 100. As a specific example, the plurality of sensors 150 may include at least one of a gyro sensor, an acceleration sensor, a linear acceleration sensor, and / or a geomagnetic sensor.

[0048] In an embodiment, the reconnection control circuit 112 may use only the sensed values ​​generated by the plurality of sensors 150, or use the sensed values ​​and a reference signal. Figure 2A The reconnection control circuit 112 may monitor the change of the location of the UE 100 from a specific location by using the values ​​of the multiple indicators described. For example, the reconnection control circuit 112 may receive the sensed values ​​through the application processor 140 connected to the multiple sensors 150. In an embodiment, the reconnection control circuit 112 may receive the sensed values ​​directly from the multiple sensors 150 (e.g., without providing the sensed values ​​to the application processor 140).

[0049] As a specific example, the reconnection control circuit 112 may provide an input including first data or second data generated by filtering the first data to the location change confirmation model 132, and determine whether the UE 100 has left a specific location based on the output of the location change confirmation model 132, the first data being periodically generated during a period in which communication based on the second RAT network is performed. For example, the first data may include at least one of the above-mentioned multiple sensing values, and the second data may include a change between past data of the first data and current data of the first data.

[0050] When the reconnection control circuit 112 monitors the change of the location of the UE 100 by using the values ​​of the above multiple indicators and the above multiple sensing values, the first data input to the location change confirmation model 132 may include at least one of the values ​​of the above multiple indicators and at least one of the above multiple sensing values.

[0051] Figure 3 Shows the status of a UE according to an embodiment.

[0052] Reference Figure 3 , the states of the UE may include a normal state ST1, a switching state ST2, and a reconnectable state ST3.

[0053] First, the UE may perform communication using the first RAT network as a primary RAT network in the normal state ST1. The UE in the normal state ST1 may stay in a normal position.

[0054] When the first condition C1 that the UE moves from a normal position to a specific position is met, the state of the UE may be converted from the normal state ST1 to the switching state ST2. Because the first RAT network is not available in the switching state ST2, the UE may be temporarily connected to the second RAT network as a secondary RAT network. The UE in the switching state ST2 may stay at a specific position. The UE in the switching state ST2 may perform a monitoring operation to determine whether the UE has left the specific position. For example, the UE may monitor the change in the position of the UE based on at least one of "movement of the UE" and "based on a signal of the second RAT network (or a signal received from a second base station providing the second RAT network)". The movement of the UE may be identified by including multiple sensors in the UE.

[0055] When the second condition C2 determining that the UE still stays at the specific location is satisfied, the UE may maintain the switching state ST2 (eg, the UE may suspend the start of the reconnection operation).

[0056] The UE may prevent an operation for reconnecting to the first RAT network in the switching state ST2. That is, the UE may efficiently use power by minimizing or reducing unnecessary operations at a specific location.

[0057] When the third condition C3 for determining that the UE has left the specific location is satisfied (for example, when it is confirmed that the UE has moved to the normal location), the state of the UE may be converted from the switching state ST2 to the reconnectable state ST3. The UE in the reconnectable state ST3 may start a reconnection operation to the first RAT network. For example, the UE in the reconnectable state ST3 may actively request the previously connected first base station to reconnect based on the connection history information.

[0058] When a fourth condition C4 for the UE to reconnect to the first RAT network is satisfied, the state of the UE may transition from the reconnectable state ST3 to the normal state ST1 .

[0059] The UE according to the embodiment may centrally perform a reconnection operation to the primary RAT network in the reconnectable state ST3, and by doing so, the UE may efficiently reconnect to the primary RAT network with less power consumption.

[0060] Figure 4 is a flowchart illustrating a method of operating a UE according to an embodiment.

[0061] Reference Figure 4In operation S100, the connected network may be switched from the first RAT network to the second RAT network according to the UE moving to a specific location. As a specific example, since the first RAT network used as the primary RAT network is unavailable according to the UE moving to the inside of the elevator as the specific location, the UE may be temporarily connected to the second RAT network as the secondary RAT network.

[0062] In operation S110, the UE may monitor a change in the location of the UE from a specific location. As a specific example, the UE may perform a monitoring operation to determine whether the UE has moved from inside the elevator to outside the elevator. The UE may perform a monitoring operation based on at least one of the values ​​of a plurality of indicators generated using an RF signal received from a second base station of a second RAT network and / or a plurality of sensing values ​​generated from a plurality of sensors of the UE. In addition, the UE may use a NN-based location change confirmation model when performing the monitoring operation.

[0063] In operation S120, the UE may perform a reconnection operation to the first RAT network based on the monitoring result of operation S110. As a specific example, if it is determined that the UE continues to stay inside the elevator, the UE may not attempt a reconnection operation to the first RAT network. In addition, if it is determined that the UE has moved from inside the elevator to outside the elevator, the UE may start a reconnection operation to the first RAT network. The UE may reconnect to the first RAT network by performing a reconnection operation to the previously connected first base station based on the connection history information. In an embodiment, if it is difficult for the UE to connect to the first base station in the reconnection operation to the first RAT network, the UE may reconnect to the first RAT network by performing a connection operation to a new base station that provides the first RAT network.

[0064] In operation S130, the UE may perform communication by reconnecting to the first RAT network. According to an embodiment, the UE 100 may generate a first signal (e.g., using a processor of the UE 100), process the first signal to perform one or more of modulation, up-conversion, filtering, amplification, and / or encryption on the first signal (e.g., according to the above combined with Figure 2A 1 to 121_x), and transmits the processed first signal to the first base station via one or more of the multiple antennas 121_1 to 121_x. Additionally or alternatively, the UE 100 may receive a second signal from the first base station via one or more of the multiple antennas 121_1 to 121_x, process the second signal to perform one or more of demodulation, down-conversion, filtering, amplification and / or decryption on the second signal (for example, according to the above combined Figure 2AThe processing described above) and performing further operations based on the processed second signal. For example, the further operations may include one or more of the following: providing the processed second signal to a corresponding application running on the UE 100, storing the processed second signal (for example, storing it in the memory 130), sending a response signal to the first base station, etc.

[0065] FIG. 5A to FIG. 5D It specifically shows Figure 4 Flowchart of operations S110 and S120.

[0066] Reference Figure 5A , in operation S111A, the UE may generate multiple indicator values ​​based on a signal received from the second RAT network. As a specific example, the UE may generate multiple indicator values ​​based on an RF signal received from the second base station during a period in which the UE is temporarily connected to the second base station and performs communication based on the second RAT network. For example, the values ​​of the multiple indicators may include at least one of the following items: global cell ID, physical cell ID, frequency band, bandwidth, RSRP, RSRQ, RSSI, SINR, number of resource blocks, CQI, RI, PMI, MCS, modulation order, BLER, transmission power, Doppler frequency and / or delay spread. As a specific example, the UE may generate a value of an indicator related to the strength of the received signal based on a reference signal included in the received RF signal.

[0067] In operation S112A, the UE may determine whether the UE has left a specific location based on the values ​​of multiple indicators. As a specific example, if a first latent vector indicating a feature of data including the values ​​of multiple indicators is greater than a first threshold previously determined to monitor changes in the location of the UE, the UE may determine that the UE has left the specific location. As another example, the UE may perform calculations based on the values ​​of multiple indicators and a first calculation algorithm, and if the calculation result is greater than the first threshold, it is determined that the UE has left the specific location. However, since this is merely an example, the inventive concept is not limited thereto, and if the first latent vector or the calculation result is less than or equal to the first threshold, the UE may determine that the UE has left the specific location.

[0068] If operation S112A is "No", the UE may perform operation S111A again to newly generate (or update) the values ​​of the multiple indicators, and may perform operation S112A again based on the newly generated (or updated) values ​​of the multiple indicators. That is, the UE may monitor the change of the location of the UE based on the values ​​of the multiple indicators generated periodically until it is confirmed that the UE has left the specific location.

[0069] If operation S112A is "yes", then in operation S121A, the UE may start a reconnection operation to the first RAT network. That is, the UE may perform a reconnection operation to the first RAT network after confirming that the UE has left a specific location.

[0070] Reference Figure 5B In operation S111B, the UE may generate a plurality of sensing values ​​through a plurality of sensors in the second RAT network. As a specific example, the UE may generate a plurality of sensing values ​​by using a plurality of sensors configured to perform sensing operations related to the movement of the UE during a period in which the UE is temporarily connected to the second base station and performs communication based on the second RAT network. For example, the plurality of sensors may include at least one of a gyro sensor, an acceleration sensor, a linear acceleration sensor, and / or a geomagnetic sensor.

[0071] In operation S112B, the UE may determine whether the UE has left a specific location based on multiple sensing values. As a specific example, if a second latent vector indicating a feature of data including multiple sensing values ​​is greater than a second threshold previously determined to monitor a change in the location of the UE, the UE may determine that the UE has left the specific location. As another example, the UE may perform calculations based on multiple sensing values ​​and a second calculation algorithm, and if the calculation result is greater than the second threshold, it is determined that the UE has left the specific location. However, since this is merely an example, the inventive concept is not limited thereto, and if the second latent vector or the calculation result is less than or equal to the second threshold, the UE may determine that the UE has left the specific location.

[0072] If operation S112B is "No", the UE may perform operation S111B again to newly generate (or update) multiple sensing values ​​and may perform operation S112B again based on the newly generated (or updated) multiple sensing values. That is, the UE may monitor the change of the UE's position based on the multiple sensing values ​​generated periodically until it is confirmed that the UE has left the specific location.

[0073] If operation S112B is "yes", then in operation S121B, the UE may start a reconnection operation to the first RAT network.

[0074] Reference Figure 5C In operation S111C, the UE may generate values ​​of multiple indicators based on the signal received from the second RAT network, and generate multiple sensing values ​​through multiple sensors. As a specific example, the UE may generate reference values ​​in a period when the UE is temporarily connected to the second base station and performs communication based on the second RAT network. Figure 5A Describes the values ​​of multiple indicators and references Figure 5B In an embodiment, the UE may generate the values ​​of the multiple indicators and the multiple sensing values ​​in a parallel manner.

[0075] In operation S112C, the UE may determine whether the UE has left a specific location based on the values ​​of multiple indicators and multiple sensing values. In an embodiment, the UE may apply different weights to each of the values ​​of multiple indicators and / or multiple sensing values, and monitor the change of the UE's location based on the values ​​of multiple indicators and / or multiple sensing values ​​to which different weights are applied. In an embodiment, if a third potential vector indicating a feature of data including the values ​​of multiple indicators and multiple sensing values ​​is greater than a third threshold previously determined to monitor the change of the UE's location, the UE may determine that the UE has left a specific location. As another example, the UE may perform calculations based on the values ​​of multiple indicators, multiple sensing values, and a third calculation algorithm, and if the calculation result is greater than the third threshold, it is determined that the UE has left a specific location. However, because this is merely an example, the inventive concept is not limited thereto, and if the third potential vector or the calculation result is less than or equal to the third threshold, the UE may determine that the UE has left a specific location.

[0076] If operation S112C is "No", the UE may perform operation S111C again to newly generate (or update) the values ​​of the multiple indicators and the multiple sensing values ​​and may perform operation S112C again based on the newly generated (or updated) values ​​of the multiple indicators and the newly generated (or updated) multiple sensing values. That is, the UE may monitor the change of the location of the UE based on the values ​​of the multiple indicators generated periodically and the multiple sensing values ​​generated periodically until it is confirmed that the UE has left the specific location.

[0077] If operation S112C is "yes", then in operation S121C, the UE may start a reconnection operation to the first RAT network.

[0078] Reference Figure 5D , at operation S111D, the UE may generate values ​​of a plurality of indicators based on a signal received from the second RAT network.

[0079] In operation S112D, the UE may determine whether the UE has left a specific location based on the values ​​of the plurality of indicators.

[0080] If operation S112D is "No", the UE may perform operation S111D again to newly generate values ​​of the plurality of indicators and may perform operation S112D again based on the newly generated values ​​of the plurality of indicators.

[0081] If operation S112D is “Yes”, then in operation S113D, the UE may generate a plurality of sensing values ​​through a plurality of sensors in the second RAT network.

[0082] In operation S114D, the UE may determine whether the UE has left a specific location based on a plurality of sensing values.

[0083] If operation S114D is "No", the UE may perform operation S111D again to newly generate values ​​of the plurality of indicators and may perform operation S112D again based on the newly generated values ​​of the plurality of indicators.

[0084] If operation S114D is "Yes", then in operation S121D, the UE may start a reconnection operation to the first RAT network.

[0085] That is to say, Figure 5D As shown in , the UE can determine the change of the UE's position twice by sequentially using the values ​​of multiple indicators and multiple sensing values ​​and performing operation S121D only after operations S112D and S114D. By doing so, the UE can more accurately determine whether the UE has left a specific location.

[0086] Figure 6 It specifically shows Figure 4 Flow chart of operation S130.

[0087] Reference Figure 6 , in operation S131, the UE may attempt reconnection to the previously connected first base station based on the connection history information. In an embodiment, the connection history information may include information required (or otherwise used) for reconnection to the first base station among a plurality of pieces of information exchanged in a radio resource control (RRC) signaling operation for connection between the UE and the first base station. In an embodiment, the UE may store the connection history information in a memory (e.g., memory 130) and read the connection history information from the memory when attempting reconnection to the first base station.

[0088] In operation S132 , the UE may perform communication based on the first RAT network by reconnecting to the first base station (eg, based on reconnecting to the first base station, after reconnecting to the first base station, etc.).

[0089] Figure 7 is a signaling diagram illustrating an operation method between a processor 200 included in a UE and a location change confirmation model 210 executed by the processor 200 according to an embodiment. According to an embodiment, the processor 200 may be the same as or similar to the processor 110, and the location change confirmation model 210 may be combined with FIG. 2A to FIG. 2B The position change confirmation model 132 discussed is the same or similar. Figure 7 The operations of the processor 200 and the location change confirmation module 210 in the embodiment may be understood as the operations of the UE (eg, the UE 100).

[0090] Reference Figure 7In operation S200, the processor 200 may switch the connected network from the first RAT network to the second RAT network according to the UE moving to a specific location. In an embodiment, the processor 200 may recognize that the first RAT network is not available at a specific location, disconnect the connection to the first RAT network, and control the connection to the second RAT network. Thereafter, the processor 200 may perform communication based on the second RAT network.

[0091] At operation S210, the processor 200 may determine a trigger for an operation of the location change confirmation model 210. In an embodiment, if the connection to the first RAT network is disconnected due to the UE moving to a specific location, the processor 200 may trigger an operation of the location change confirmation model 210. For example, the operation of the location change confirmation model 210 may include an operation of monitoring a change in the location of the UE from a specific location by using the location change confirmation model 210.

[0092] In operation S220, the processor 200 may send a location change confirmation request to the location change confirmation model 210. In an embodiment, the location change confirmation request may include data generated from the values ​​of multiple indicators related to the second RAT network. In an embodiment, the location change confirmation request may include data generated from multiple sensing values ​​related to the movement of the UE. In addition, in an embodiment, the location change confirmation request may include data generated from the values ​​of multiple indicators and multiple sensing values. That is, the processor 200 may generate data by processing at least one of the values ​​of the multiple indicators and / or the multiple sensing values ​​to be suitable for the location change confirmation model 210, and input the generated data to the location change confirmation model 210.

[0093] In operation S230, the location change confirmation model 210 may generate data indicating whether the location of the UE has changed from a specific location in response to the received location change confirmation request. In an embodiment, the location change confirmation model 210 may receive an input of data included in the location change confirmation request, and output data indicating whether the location of the UE has changed. As a specific example, the location change confirmation model 210 may perform NN calculations for extracting features of the input data and output calculation results. The calculation results may include a probability value that the UE has left the specific location, and if the probability value is greater than a threshold value, it may be determined that the UE has left the specific location.

[0094] In operation S240, the location change confirmation module 210 may send a location change confirmation response including data indicating whether the location of the UE has changed from a specific location to the processor 200. According to an embodiment, the location change confirmation response may include a probability value in the calculation result and / or an indication of whether the probability value is greater than a threshold.

[0095] In operation S250, the processor 200 may determine whether to start a reconnection operation to the first RAT network based on the location change confirmation response. As a specific example, if the data included in the location change confirmation response indicates a location change, the processor 200 may start a reconnection operation to the first RAT network. According to an embodiment, the processor 200 may start a reconnection operation in response to determining that the probability value is greater than a threshold.

[0096] Figure 8 Show Figure 7 The location change confirmation model 210 is shown in FIG. Figure 8 The described architecture of the location change confirmation model 210 can be applied to Figure 2A and Figure 2B The position change confirmation model 132.

[0097] Reference Figure 8 , the position change confirmation model 210 may include multiple levels (e.g., the first level LV1 to the third level LV3). However, the inventive concept is not necessarily limited thereto, and the NN may consist of only one level or two or more levels. In the following, the first level LV1 is described, but this may also be applied to other levels included in the position change confirmation model 210 in substantially the same manner. In an embodiment, the layers L1_2 and L2_2, feature maps FM1_2, FM2_2, and FM3_2, weight map WM2, and pooling window PW2 included in the second level LV2, and the layers L1_3 and L2_3, feature maps FM1_3, FM2_3, and FM3_3, weight map WM3, and pooling window PW3 included in the third level LV3 may be the same or similar to the corresponding structures in the first level LV1, but are not limited thereto. In addition, depending on the circumstances, a portion of the layers in the first level LV1 of the position change confirmation model 210 may be omitted, or other layers may be added to the layers in the first level LV1.

[0098] The first level LV1 may include a plurality of layers (e.g., a first layer L1_1 to an nth layer Ln_1). Such a multi-layered position change confirmation model 210 may be referred to as a deep neural network (DNN) or a deep learning architecture. Each of the first layer L1_1 to the nth layer Ln_1 may be a linear layer or a nonlinear layer, and in an embodiment, at least one linear layer and at least one nonlinear layer may be combined into one layer. For example, the linear layer may include a convolutional layer or a fully connected layer, and the nonlinear layer may include a pooling layer or an activation layer.

[0099] For example, the first layer L1_1 may be a convolutional layer, the second layer L2_1 may be a pooling layer, and the nth layer may be a fully connected layer as an output layer. The position change confirmation model 210 may further include an activation layer and a layer that performs another type of calculation.

[0100] Each of the first layer L1_1 to the nth layer Ln_1 may receive input data or a feature map generated in a previous layer as an input feature map, and generate an output feature map by calculating the input feature map. Here, the feature map indicates data representing various features of the input data. The first feature map FM1_1 to the nth feature map FMn_1 may have, for example, a two-dimensional matrix or a three-dimensional matrix (or referred to as a tensor) form including a plurality of eigenvalues. Each of the first feature map FM1_1 to the nth feature map FMn_1 may have a width W1 (or referred to as a column), a height H1 (or referred to as a row), and a depth D1 corresponding to the x-axis, y-axis, and z-axis on the coordinate system, respectively. Here, the depth D1 may be referred to as the number of channels CH1. Although Figure 8 Three channels CH1 are shown, but the inventive concept is not necessarily limited thereto, and the number of channels CH1 may be 1 or more.

[0101] The first layer L1_1 may generate a second feature map FM2_1 by convolving the first feature map FM1_1 with the weight map WM1. The weight map WM1 may have a two-dimensional matrix or three-dimensional matrix form including a plurality of weight values. The weight map WM1 may be referred to as a kernel. The weight map WM1 may perform filtering of the first feature map FM1_1 and is referred to as a filter or a kernel. The channels of the weight map WM1 may be convolved with the channels of the first feature map FM1_1, respectively. The weight map WM1 moves as a sliding window across the first feature map FM1_1. For each movement, the weights included in the weight map WM1 may be multiplied by all feature values ​​in the area of ​​the first feature map FM1_1 that overlaps with the weight map WM1, respectively, and then added (e.g., the multiplication results are added). Based on the convolution of the first feature map FM1_1 and the weight map WM1, one channel of the second feature map FM2_1 may be generated. Although Figure 8 One weight map WM1 is shown, but multiple weight maps are basically convolved with the first feature map FM1_1 to generate multiple channels of the second feature map FM2_1. In other words, the number of channels of the second feature map FM2_1 may correspond to the number of weight maps.

[0102] The second layer L2_1 may generate a third feature map FM3_1 by changing the spatial size of the second feature map FM2_1 by pooling. Pooling may be referred to as sampling or downsampling. The two-dimensional pooling window PW1 may be moved on the second feature map FM2_1 in units of the size of the pooling window PW1, and the maximum (or highest) value (or average) of the feature values ​​in the area overlapping the pooling window PW1 may be selected. Therefore, the third feature map FM3_1 may be generated by changing the spatial size of the second feature map FM2_1. The number of channels of the third feature map FM3_1 may be the same as (or similar to) the number of channels of the second feature map FM2_1.

[0103] The n-th layer Ln_1 may classify the category CL of the input data by combining the features of the n-th feature map FMn_1. In addition, an identification signal REC corresponding to the category CL may be generated. The n-th layer Ln_1 may be omitted according to circumstances.

[0104] The position change confirmation model 210 may include one or more (e.g., multiple) levels. Each of the multiple levels may receive a feature map generated from data input to the level as an input feature map, and calculate the input feature map to generate an output feature map or a recognition signal REC. In an embodiment, the first level LV1 may receive a feature map generated from the input data as an input feature map. The first layer L1_1 may receive a first feature map FM1_1 generated from the input data. The second level LV2 may receive a feature map generated from the first reconstruction data as an input feature map. The first layer L1_2 may receive a first feature map FM1_2 generated from the first reconstruction data. The third level LV3 may receive a feature map generated from the second reconstruction data as an input feature map. The first layer L1_3 may receive a first feature map FM1_3 generated from the second reconstruction data. The unit of the first reconstruction data may be different from the unit of the second reconstruction data. The widths W1, W2, and W3, the heights H1, H2, and H3, and the depths D1, D2, and D3 of the first feature map FM1_1, the first feature map FM1_2, and the first feature map FM1_3 may be different from each other.

[0105] Multiple levels may be connected to each other in an organized manner. In an embodiment, feature maps output from layers included in each of the multiple levels may be connected to feature maps of different levels in an organized manner. For example, the position change confirmation model 210 may perform calculations to extract features of the third feature map FM3_1 and the first feature map FM1_2 and generate a new feature map. In an embodiment, the nth layer Ln_1 may exist only in one level, and the category CL of the input data is classified by combining features of feature maps of multiple levels.

[0106] In an embodiment, a configuration including a layer of the location change confirmation model 210 , the number of feature maps, and a combination of feature maps may be determined to efficiently determine a change in the location of a user device from a specific location.

[0107] Fig. 9A and Fig. 9B FIG. 2 shows a monitoring operation using the location change confirmation model 210 according to an embodiment. Fig. 9A and Fig. 9B The monitoring operation described using the location change confirmation model 210 can be applied to Figure 2A and Figure 2B The position change confirmation model 132. In addition, although Fig. 9A and Fig. 9BIt is shown that three values ​​are input to the position change confirmation model 210, but since this is only an example, the inventive concept is not limited thereto, and a greater or lesser number of values ​​may be input. Fig. 9A and Fig. 9B It is shown that one value is output from the location change confirmation model 210 , but since this is only an example, the inventive concept is not limited thereto.

[0108] Reference Fig. 9A , data including a first value of the first indicator, a second value of the second indicator, and a third value of the third indicator may be input to the location change confirmation model 210. The location change confirmation model 210 may perform NN-based calculations based on the inputs and output data indicating whether the location of the UE has changed from a specific location. For example, the output of the location change confirmation model 210 may include a probability value of a change in the location of the UE. In an embodiment, the first to third indicators are associated with a secondary RAT network and may be indicators suitable for monitoring changes in the location of the UE. As a specific example, the first to third indicators may indicate the reception strength of a signal based on the secondary RAT network.

[0109] Reference Fig. 9B , data including a first sensing value of the first sensor, a second sensing value of the second sensor, and a third sensing value of the third sensor may be input to the position change confirmation model 210. The position change confirmation model 210 may perform NN-based calculations based on the inputs and output data indicating whether the position of the UE has changed from a specific position. In an embodiment, the first sensor to the third sensor may perform sensing operations related to the movement of the UE.

[0110] and Fig. 9A and Fig. 9B Differently, data including the value of the indicator as well as the sensed value (eg, data including both the value of the indicator and the sensed value) may be input to the position change confirmation model 210 .

[0111] Fig.10 is a flowchart illustrating a method of training a position change confirmation model according to an embodiment.

[0112] Reference Fig.10 In operation S300, offline training for the location change confirmation model may be performed based on previously collected data. In an embodiment, the location change confirmation model may be trained offline based on data previously collected in various environments and stored in a memory of the UE during the UE mass production stage.

[0113] In operation S310, online training for the location change confirmation model may be performed based on data measured in real time by the UE. In an embodiment, the location change confirmation model may be continuously updated by performing online training based on data measured in real time by providing communication services to the user since the UE was sold to the user (e.g., based on data measured by the UE during the life cycle of the UE or since the original activation).

[0114] Fig.11 is a flowchart illustrating a method of operating a UE according to an embodiment.

[0115] Reference Fig.11 , in operation S400, the connected network may be switched from the first RAT network to the second RAT network according to the UE moving to a specific location.

[0116] In operation S410, the UE may identify the type of the specific location. In an embodiment, there may be various types of specific locations where the first RAT network is unavailable, and a value required (or otherwise used) for monitoring a change in the location of the UE may be preset (or optionally, given) according to the type of the specific location.

[0117] In operation S420, the UE may monitor a change in the location of the UE from a specific location based on the type of the identification. In an embodiment, the UE may selectively generate a value of an indicator that matches the type of the identification from among a plurality of indicators associated with the second RAT network, and use the generated value of the indicator for monitoring. In an embodiment, the UE may generate a sensing value by selectively using a sensor that matches the type of the identification from among a plurality of sensors configured to perform sensing operations related to the movement of the UE, and use the generated sensing value for monitoring. In an embodiment, the UE may use indicators and sensors that match the type of the identification from among a plurality of indicators and a plurality of sensors for monitoring.

[0118] In operation S430 , the UE may perform a reconnection operation to the first RAT network based on the monitoring result of operation S420 .

[0119] In operation S440 , the UE may perform communication by reconnecting to the first RAT network (eg, based on reconnecting to the first RAT network, after reconnecting to the first RAT network, etc.).

[0120] Fig. 12A and Fig. 12B It specifically shows Fig.11 Flowchart of operations S420 and S430.

[0121] Reference Fig. 12AIn operation S421A, the UE may select an indicator set corresponding to the identified type. In the specification, the indicator set may be a unit including indicators that are pre-set (or, optionally, given) according to the type of a specific location for monitoring a change in the location of the UE. For example, a first indicator set may correspond to a first specific location of a first type, and a second indicator set may correspond to a second specific location of a second type.

[0122] In operation S422A, the UE may generate a value of the selected indicator set based on a signal received from the second RAT network. As a specific example, the UE may generate a value of an indicator in the selected indicator set based on an RF signal received from the second base station during a period in which the UE is temporarily connected to the second base station and performs communication based on the second RAT network.

[0123] In operation S423A, the UE may determine whether the UE has left a specific location based on the value of the selected indicator set.

[0124] If operation S423A is "No", the UE may perform operation S422A again to newly generate (or update) the value of the selected indicator set, and may perform operation S423A again based on the newly generated (or updated) value.

[0125] If operation S423A is "yes", then in operation S431A, the UE may start a reconnection operation to the first RAT network.

[0126] Reference Fig. 12B In operation S421B, the UE may select a sensor set corresponding to the identified type. In the specification, the sensor set may be a unit including sensors that are pre-set (or, optionally, given) according to the type of a specific location for monitoring a change in the location of the UE. For example, a first sensor set may correspond to a first specific location of a first type, and a second sensor set may correspond to a second specific location of a second type.

[0127] In operation S422B, the UE may generate a sensing value through a sensor included in the selected sensor set in the second RAT network. As a specific example, the UE may generate a sensing value of a sensor included in the selected sensor set during a period in which the UE is temporarily connected to the second base station and performs communication based on the second RAT network.

[0128] In operation S423B, the UE may determine whether the UE has left a specific location based on the sensing value.

[0129] If operation S423B is “No”, the UE may perform operation S422B again to newly generate (or update) a sensing value by using a sensor included in the selected sensor set, and may perform operation S423B again based on the newly generated (or updated) value.

[0130] If operation S423B is "yes", then in operation S431B, the UE may start a reconnection operation to the first RAT network.

[0131] Fig.13 A method of operating a UE according to an embodiment is shown, and Fig.14A and Fig. 14B Is used to describe Fig.13 Table of methods of operating a UE.

[0132] Reference Fig.13 , if the UE moves to any one of the first specific location to the third specific location SP1, SP2, and / or SP3 while performing communication by connecting to the first RAT network, the first RAT network may be unavailable, so that the connection to the first RAT network is disconnected. In addition, in an embodiment, the first specific location SP1 may correspond to the first type, the second specific location SP2 may correspond to the second type, and the third specific location SP3 may correspond to the third type. As described above, the value required (or otherwise used) for monitoring the change of the location of the UE may vary for each of the types of specific locations.

[0133] In an embodiment, when the UE temporarily connects to the second RAT network because the first RAT network is unavailable due to the UE moving to a specific location, the UE may identify the type of the specific location and preselect values ​​required for monitoring (or otherwise used).

[0134] Reference Fig.13 and Fig.14A In the first table TB1, the first indicator set IS_1 may correspond to the first specific position SP1 of the first type T1, the second indicator set IS_2 may correspond to the second specific position SP2 of the second type T2, and the third indicator set IS_3 may correspond to the third specific position SP3 of the third type T3.

[0135] For example, when the UE moves to the first specific position SP1, the UE may identify that the first specific position SP1 is of the first type T1, generate a value of an indicator included in the first indicator set IS_1, and monitor a change in the position of the UE using the generated value.

[0136] For example, when the UE moves to the second specific position SP2, the UE may identify that the second specific position SP2 is of the second type T2, generate a value of an indicator included in the second indicator set IS_2, and monitor a change in the position of the UE using the generated value.

[0137] In addition, for example, when the UE moves to the third specific position SP3, the UE may identify that the third specific position SP3 is of the third type T3, generate a value of an indicator included in the third indicator set IS_3, and monitor a change in the position of the UE using the generated value.

[0138] Reference Fig.13 and Fig. 14B , in the second table TB2 , the first sensor set SS_1 may correspond to the first specific position SP1 of the first type T1 , the second sensor set SS_2 may correspond to the second specific position SP2 of the second type T2 , and the third sensor set SS_3 may correspond to the third specific position SP3 of the third type T3 .

[0139] For example, when the UE moves to the first specific position SP1, the UE may identify that the first specific position SP1 is of the first type T1, generate a sensing value by using a sensor included in the first sensor set SS_1, and monitor a change in the position of the UE using the generated value.

[0140] For example, when the UE moves to the second specific position SP2, the UE may identify that the second specific position SP2 is the second type T2, generate a sensing value by using a sensor included in the second sensor set SS_2, and monitor a change in the position of the UE using the generated value.

[0141] In addition, for example, when the UE moves to the third specific position SP3, the UE may identify that the third specific position SP3 is the third type T3, generate a sensing value by using a sensor included in the third sensor set SS_3, and monitor a change in the position of the UE using the generated value.

[0142] Fig.15 1 is a signaling diagram illustrating an operation method between a processor 300 included in a UE and a location change confirmation model 310 executed by the processor 300 according to an embodiment. According to an embodiment, the processor 300 may be the same as or similar to the processor 110, and the location change confirmation model 310 may be combined with the processor 300. Figure 2A to Figure 2B The position change confirmation model 132 discussed above is the same or similar. According to an embodiment, the processor 300 may be the same or similar to the processor 200, and the position change confirmation model 310 may be combined with Figure 7 The location change confirmation model 210 discussed is the same or similar. Fig.15The operations of the processor 300 and the location change confirmation model 310 in the embodiment may be understood as the operations of the UE (eg, the UE 100 ).

[0143] Reference Fig.15 , at operation S500, the processor 300 may switch a connected network from a first RAT network to a second RAT network according to movement of the UE to a specific location.

[0144] In operation S510, the UE may identify the type of a specific location.

[0145] In operation S520 , the processor 300 may determine a trigger for an operation of the location change confirmation model 310 .

[0146] At operation S530, the processor 300 may send a location change confirmation request to the location change confirmation model 310. In an embodiment, the location change confirmation request may include data generated from a value of an indicator matching the type of the identification among a plurality of indicators related to the second RAT network. In an embodiment, the location change confirmation request may include data generated from a sensed value matching the type of the identification among a plurality of sensed values ​​related to the movement of the UE. In addition, in an embodiment, the location change confirmation request may include data generated from a value matching the type of the identification among a plurality of indicator values ​​and a plurality of sensed values. The location change confirmation request may also include data indicating the type of the identification.

[0147] In operation S540, the location change confirmation model 310 may generate data indicating whether the location of the UE has changed based on the type and input data identifying the specific location in response to the received location change confirmation request.

[0148] In operation S550 , the location change confirmation module 310 may transmit a location change confirmation response including data indicating whether the location of the UE has changed from a specific location to the processor 300 .

[0149] At operation S560, the processor 300 may determine whether to start a reconnection operation to the first RAT network based on the location change confirmation response.

[0150] Fig.16 It specifically shows Fig.15 Flow chart of operation S540.

[0151] Reference Fig.16 In operation S541, the location change confirmation model 310 may select one of a plurality of NN calculation algorithms based on the type of identification of the specific location.

[0152] In operation S542, the location change confirmation model 310 may generate data indicating whether the location of the UE has changed from a specific location based on the selected NN calculation algorithm and the input data.

[0153] In an embodiment, the location change confirmation model 310 may identify which values ​​are included in the input data based on the type of identification and select a NN calculation suitable for the value. The location change confirmation model 310 may perform the NN calculation selected for the input data and output the calculation result. The calculation result may include a probability value that the UE has left a specific location.

[0154] Fig.17 is a conceptual diagram illustrating an Internet of Things (IoT) network system 1000 according to an embodiment.

[0155] Reference Fig.17 , the IoT network system 1000 may include a plurality of IoT devices 1100, 1120, 1140, and 1160, an AP 1200, a gateway 1250, a radio network 1300, and / or a server 1400. IoT may indicate a network between things using wired / wireless communication.

[0156] A plurality of IoT devices 1100, 1120, 1140, and 1160 may be grouped according to their characteristics. For example, a plurality of IoT devices 1100, 1120, 1140, and 1160 may be grouped into a home gadget group 1100, a home appliance / furniture group 1120, an entertainment group 1140, and / or a vehicle group 1160. The IoT devices 1100, 1120, and 1140 may be connected to a communication network or another IoT device via an AP 1200. The AP 1200 may be embedded in one IoT device. The gateway 1250 may change a protocol to connect the AP 1200 to an external radio network. The IoT devices 1100, 1120, and 1140 may be connected to an external communication network via the gateway 1250. The radio network 1300 may include the Internet and / or a public network. The plurality of IoT devices 1100 , 1120 , 1140 , and 1160 may be connected to a server 1400 providing a specific service through the radio network 1300 , and a user may use the specific service through at least one of the plurality of IoT devices 1100 , 1120 , 1140 , and 1160 .

[0157] According to an embodiment, if the connected network switches from the primary RAT network to the secondary RAT network due to the IoT device moving to a specific location, each of the multiple IoT devices 1100, 1120, 1140 and 1160 can monitor the change of the location of the IoT device from the specific location and perform a reconnection operation to the primary RAT network based on the monitoring result.

[0158] Conventional apparatus and methods for managing connections to multiple RAT networks repeatedly attempt to reconnect to a higher priority RAT network in a scenario where a handoff to a lower priority RAT network has been performed (e.g., based on insufficient signal strength / quality of the higher priority RAT network). In doing so, the conventional apparatus and methods continuously measure radio signals corresponding to the higher priority RAT network. These continuous measurements and repeated reconnection attempts result in excessive power consumption.

[0159] However, according to an embodiment, an improved apparatus and method for managing connections to multiple RAT networks is provided. For example, the improved apparatus and method may monitor the location of the UE in a scenario where the UE has switched to a lower priority RAT network. The improved apparatus and method may attempt to reconnect to a higher priority RAT network only in response to determining that the UE has moved to a different location. Since the lack of access to a higher priority RAT network may be due to location-specific characteristics (e.g., channel quality), attempting to reconnect only in response to determining that the UE has moved to a different location may reduce the number of measurements of radio signals of the higher priority RAT network and / or reduce the number of reconnection attempts. In addition, monitoring the location of the UE may consume less power than continuous measurements and repeated reconnection attempts. Therefore, the improved apparatus and method may overcome the deficiencies of conventional apparatus and methods to at least reduce power consumption.

[0160] According to an embodiment, the operations described herein as being performed by the wireless communication system 1, the first base station 10, the second base station 20, the UE 30, the reconnection control circuit 32, the processor 110, the transceiver 120, the reconnection control circuit 112, the application processor 140, the plurality of sensors 150, the processor 200, the processor 300, the IoT network system 1000, each of the plurality of IoT devices 1100, 1120, 1140 and / or 1160, the AP 1200, the gateway 1250 and / or the server 1400 may be performed by a processing circuit system. The term "processing circuit system" as used in the present disclosure may refer to, for example, hardware including a logic circuit; a hardware / software combination (such as a processor running software); or a combination thereof. For example, the processing circuit system may more specifically include, but is not limited to, a central processing unit (CPU), an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a system on a chip (SoC), a programmable logic unit, a microprocessor, an application specific integrated circuit (ASIC), and the like.

[0161] The various operations of the methods described above may be performed by any suitable device capable of performing the operations (such as the processing circuit system discussed above). For example, as described above, the operations of the methods described above may be performed by various hardware and / or software implemented in some form of hardware (e.g., processor, ASIC, etc.).

[0162] The software may include an ordered listing of executable instructions for implementing logical functions and may be implemented in any "processor readable medium" for use by or in conjunction with an instruction execution system, device or apparatus (such as a single-core or multi-core processor or a system including a processor).

[0163] The blocks or operations of the methods or algorithms and / or functions described in conjunction with the embodiments disclosed herein may be implemented directly in hardware, in software modules executed by a processor, or in a combination of both. If implemented in software, the functions may be stored as one or more instructions or codes on or transmitted through a tangible, non-transitory computer-readable medium (e.g., memory 130). The software module may reside in a random access memory (RAM), flash memory, read-only memory (ROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), registers, a hard disk, a removable disk, a CD ROM, or any other form of storage medium known in the art.

[0164] In an embodiment, the processing circuit system may perform a portion of the operations (e.g., operations described herein as being performed by the position change confirmation model 132, the position change confirmation model 210, and / or the position change confirmation model 310) through artificial intelligence and / or machine learning. As an example, the processing circuit system may implement an artificial neural network (e.g., the position change confirmation model 132, the position change confirmation model 210, and / or the position change confirmation model 310), the artificial neural network (e.g., the position change confirmation model 132, the position change confirmation model 210, and / or the position change confirmation model 310) being trained on a set of training data through, for example, a supervised learning model, an unsupervised learning model, and / or a reinforcement learning model, and wherein the processing circuit system may process the feature vector to provide an output based on the training. Such artificial neural networks may utilize various artificial neural network organizations and processing models (such as, convolutional neural networks (CNNs), recurrent neural networks (RNNs) (optionally including long short-term memory (LSTM) units and / or gated recurrent units (GRUs)), stacked deep neural networks (S-DNNs), state-space dynamic neural networks (S-SDNNs), deconvolution networks, deep belief networks (DBNs), and / or restricted Boltzmann machines (RBMs)). Alternatively or additionally, the processing circuit system may include other forms of artificial intelligence and / or machine learning (such as, for example, linear regression and / or logistic regression, statistical clustering, Bayesian classification, decision trees, dimensionality reduction (such as principal component analysis), and expert systems; and / or combinations thereof (including ensembles such as random forests).

[0165] Here, the position change confirmation model (e.g., the position change confirmation model 132, the position change confirmation model 210, and / or the position change confirmation model 310) may have any structure that can be trained, for example, with training data. For example, the position change confirmation model (e.g., the position change confirmation model 132, the position change confirmation model 210, and / or the position change confirmation model 310) may include an artificial neural network, a decision tree, a support vector machine, a Bayesian network, a genetic algorithm, and the like. The position change confirmation model (e.g., the position change confirmation model 132, the position change confirmation model 210, and / or the position change confirmation model 310) is described herein by mainly referring to an artificial neural network, but the embodiment is not limited thereto. Non-limiting examples of artificial neural networks may include convolutional neural networks (CNNs), region-based convolutional neural networks (R-CNNs), region proposal networks (RPNs), recurrent neural networks (RNNs), stacked deep neural networks (S-DNNs), state space dynamic neural networks (S-SDNNs), deconvolution networks, deep belief networks (DBNs), restricted Boltzmann machines (RBMs), full convolutional networks, long short-term memory (LSTM) networks, classification networks, and the like.

[0166] While the inventive concept has been particularly shown and described with reference to embodiments thereof, it will be understood that various changes in form and details may be made therein without departing from the spirit and scope of the appended claims.

Claims

1. A user equipment, the user equipment supporting a first radio access technology network and a second radio access technology network, the user equipment comprising: A processing circuit system is configured to: monitoring whether the location of the user equipment has changed from a first location to obtain a monitoring result, switching a network connected to the user equipment from a first radio access technology network to a second radio access technology network based on the user equipment moving to the first location, and A reconnection operation to the first radio access technology network is performed based on the monitoring result.

2. The user equipment according to claim 1, wherein: The step of monitoring whether the location of the user equipment has changed from the first location comprises determining whether the user equipment has left the first location based on values ​​of a plurality of indicators generated using radio frequency signals received based on a second radio access technology network.

3. The user equipment according to claim 2, wherein: The multiple indicators include at least one of the following items: a global cell identifier, a physical cell identifier, a frequency band, a bandwidth, a received signal received power, a reference signal received quality, a received signal strength indicator, a signal to interference plus noise ratio, a number of resource blocks, a channel quality indicator, a rank indicator, a precoding matrix indicator, a modulation and coding scheme, a modulation order, a block error rate, a transmission power, a Doppler frequency, and a delay spread.

4. The user equipment according to claim 2, further comprising: a plurality of sensors configured to generate a plurality of sensing values ​​by performing sensing operations related to movement of the user equipment, The step of monitoring whether the position of the user equipment has changed from the first position includes: determining whether the user equipment has left the first position based on the multiple sensing values.

5. The user equipment according to claim 4, wherein: The plurality of sensors include at least one of a gyro sensor, an acceleration sensor, a linear acceleration sensor, and a geomagnetic sensor.

6. The user equipment according to claim 2, wherein: The step of performing a reconnection operation comprises initiating a reconnection operation to a first radio access technology network in response to determining that the user equipment has left the first location.

7. The user equipment according to claim 1, further comprising: Memory, storage location change confirmation model, location change confirmation model based on neural network, Among them, the step of monitoring whether the location of the user equipment has changed from the first location includes: providing input to a location change confirmation model run by a processing circuit system, and determining whether the user equipment has left the first location based on the output of the location change confirmation model, the input including first data periodically generated during a period of performing communication based on a second radio access technology network or second data generated by filtering the first data.

8. The user equipment according to claim 7, wherein: The first data includes values ​​of a plurality of indicators generated using a radio frequency signal received based on the second radio access technology network.

9. The user equipment according to claim 7, further comprising: a plurality of sensors configured to generate a plurality of sensing values ​​by performing sensing operations related to movement of the user equipment, The first data includes the plurality of sensing values.

10. The user equipment according to claim 7, wherein: The second data includes a change between past data of the first data and current data of the first data.

11. The user equipment according to claim 1, wherein: The step of performing a reconnection operation includes attempting reconnection to a base station providing the first radio access technology network based on the connection history information.

12. The user equipment according to claim 1, wherein: The step of monitoring whether the location of the user equipment has changed from the first location comprises determining whether the user equipment has left the first location based on a value of an indicator set corresponding to the type of the first location, the value of the indicator set being generated using a radio frequency signal received based on a second radio access technology network.

13. The user equipment according to claim 1, further comprising: a plurality of sensors configured to perform sensing operations related to movement of the user equipment, Among them, the step of monitoring whether the position of the user device has changed from the first position includes: determining whether the user device has left the first position based on a sensing value generated using at least one sensor, the at least one sensor is included in a sensor set corresponding to the type of the first position, and the at least one sensor is among the multiple sensors.

14. A method for operating a user equipment, wherein the user equipment supports a first radio access technology network and a second radio access technology network, the method comprising: Switching from a first radio access technology network to a second radio access technology network based on the user equipment moving to a first location, the step of switching comprising: switching communications from a first base station to a second base station, the first base station being based on the first radio access technology network and the second base station being based on the second radio access technology network; monitoring whether the location of the user equipment has changed to obtain a monitoring result; and A reconnection operation to the first radio access technology network is performed based on the monitoring result.

15. The operating method according to claim 14, wherein: The step of monitoring whether the location of the user equipment has changed comprises determining whether the user equipment has left a first location based on at least one of: movement of the user equipment and a signal received from a second base station.

16. The operating method according to claim 14, wherein: The step of performing a reconnection operation includes: in response to determining that the monitoring result indicates that the user equipment has left the first location, starting a reconnection operation.

17. The operating method according to claim 16, wherein: The step of performing a reconnection operation includes attempting a reconnection to the first base station based on information about a previous connection to the first base station.

18. The operating method according to claim 14, wherein: The step of performing the reconnection operation includes: in response to determining that the monitoring result indicates that the user equipment remains in the first position, pausing the start of the reconnection operation.

19. The operating method according to claim 14, wherein: The step of monitoring whether the location of the user equipment has changed comprises: generating values ​​for a plurality of indicators using a radio frequency signal received from a second base station; providing an input including values ​​of the plurality of indicators to a position change confirmation model, the position change confirmation model being based on a neural network; and A determination is made based on an output of a location change confirmation model as to whether the user equipment has left the first location.

20. A method for operating a user equipment, the method comprising: Performing communication based on a primary radio access technology network in a normal state; switching from a primary radio access technology network to a secondary radio access technology network based on movement of the user equipment to a first location; transitioning from a normal state to a switching state based on the switching; In the switching state, monitoring whether the user equipment has left the first location to obtain a monitoring result; as well as It is determined whether to transition from the handover state to a reconnectable state based on the monitoring result, the reconnectable state being a state for a reconnection operation to the primary radio access technology network.

Images