Terminal

Abstract

This terminal comprises: a control unit that determines whether the estimation accuracy of a learning model is less than a first threshold value; and a transmission unit that, when the estimation accuracy is less than the first threshold value, transmits that the learning model has become unavailable.

Description

Terminal

[0001] The present disclosure relates to a terminal that utilizes a learning model.

[0002] The 3rd Generation Partnership Project (3GPP) is developing specifications for the 5th generation mobile communication system (5G, also known as New Radio (NR) or Next Generation (NG)), and is also developing specifications for the next generation of mobile communication systems, known as Beyond 5G, 5G Evolution, or 6G.

[0003] 3GPP Release 18 discusses the introduction of Artificial Intelligence (AI) / Machine Learning (ML). AI / ML models (hereinafter referred to as learning models) are downloaded from base stations (gNodeB, gNB) and applied to terminals (User Equipment, UE). Applying learning models is expected to improve performance in areas such as Channel State Information (CSI) feedback, beam management (BM), positioning, mobility, network slicing, and Quality of Experience (QoE).

[0004] There are two types of learning model downloads: reactive model transfer / delivery, which is performed in response to changes in the environment surrounding the UE (e.g., scenario, settings, and location of use), and proactive model transfer / delivery, which is performed in advance. In the latter case, the learning model to be applied is switched from multiple learning models downloaded in advance in response to changes in the environment surrounding the UE (Non-Patent Document 1).

[0005] “Report of 3GPP TSG RAN WG2 meeting #123”, 3GPP TSG-RAN WG2 Meeting #123, 3GPP, August 21-25, 2023

[0006] In proactive model transfer / delivery, a UE may recognize changes in its surrounding environment and determine that the downloaded learning model no longer satisfies the applicability conditions, and report this to the gNB. However, for example, if the change is small, the learning model may not necessarily no longer satisfy the applicability conditions. Reporting every time the environment surrounding the UE changes leaves room for improvement in terms of resource utilization efficiency.

[0007] Therefore, the present disclosure has been made in consideration of such circumstances, and aims to provide a terminal that can report at an appropriate time that a learning model no longer satisfies the application conditions, so as to reduce waste of resources.

[0008] One aspect of the disclosure is a terminal that includes a control unit (estimation accuracy determination unit 260) that determines whether the estimation accuracy of a learning model is below a first threshold, and a transmission unit (transmission / reception unit 210) that transmits information indicating that the learning model is no longer applicable when the estimation accuracy is below the first threshold.

[0009] FIG. 1 is a diagram showing an overall schematic configuration of a wireless communication system. FIG. 2 is a diagram showing a frequency range used in the wireless communication system. FIG. 3 is a diagram showing an example configuration of a wireless frame, subframe, slot, and symbol used in the wireless communication system. FIG. 4 is a functional block diagram of a terminal. FIG. 5 is a functional block diagram of a base station. FIG. 6 is a sequence diagram related to reporting whether a learning model can be applied. FIG. 7 is a sequence diagram related to requesting a learning model. FIG. 8 is a sequence diagram related to determining whether a learning model can be applied in a terminal. FIG. 9 is a sequence diagram related to determining whether a learning model can be applied in a base station. FIG. 10 is a sequence diagram related to disabling or switching a learning model in a terminal. FIG. 11 is a diagram showing an example hardware configuration of a base station and a terminal. FIG. 12 is a diagram showing an example configuration of a vehicle.

[0010] Hereinafter, embodiments will be described with reference to the drawings. Note that the same or similar reference numerals are used to designate the same functions or configurations, and descriptions thereof will be omitted as appropriate.

[0011] (1) Overall Schematic Configuration of Wireless Communication System The wireless communication system 10 shown in Fig. 1 is a wireless communication system conforming to a method called 5G. Alternatively, the wireless communication system 10 may be a wireless communication system conforming to a method called Beyond 5G, 5G Evolution, or 6G.

[0012] The wireless communication system 10 can support Massive Multiple-Input Multiple-Output (Massive MIMO), which generates more directional beams by controlling wireless signals transmitted from multiple antenna elements, Carrier Aggregation (CA), which uses multiple component carriers (CCs) as a bundle, and Dual Connectivity (DC), which enables simultaneous communication with two base stations.

[0013] As shown in FIG. 1 , the wireless communication system 10 includes a base station (gNodeB, gNB) 100 connected to a Next Generation-Radio Access Network (NG-RAN) 20, and a terminal (User Equipment, UE) 200 that performs wireless communication with the gNB 100. The NG-RAN 20 is connected to a core network (CN) (not shown). The CN is configured by a network function (NF) such as an access and mobility management function (AMF). Note that the specific configuration of the wireless communication system 10, for example, the number of gNBs 100 and UEs 200, is not limited to the example shown in FIG. 1 . Furthermore, the NG-RAN 20 and the CN may be simply referred to as a "network," and may or may not be considered to be included in the wireless communication system 10.

[0014] The gNB100 may be a base station in a Centralized-Radio Access Network (C-RAN) configuration having a distributed unit (DU) having a function for connecting to the UE200 and a central unit (CU) having a function for connecting to the network. In this case, the gNB100 may be referred to as a DU or a CU. When the gNB100 is a DU, it may be referred to as a gNB-DU, an Integrated Access and Backhaul (IAB) node, a wireless communication node, etc. Similarly, when the gNB100 is a CU, it may be referred to as a gNB-CU, an IAB donor, etc.

[0015] The wireless communication system 10 may also support multiple frequency ranges (FR). That is, as shown in Fig. 2, the wireless communication system 10 may support the following FRs: FR1: 410 MHz to 7.125 GHz FR2-1: 24.25 GHz to 52.6 GHz FR2-2: Over 52.6 GHz to 71 GHz

[0016] In FR1, a subcarrier spacing (SCS) of 15, 30, or 60 kHz and a bandwidth (BW) of 5 to 100 MHz may be used, while in FR2-1, an SCS of 60 or 120 kHz (including 240 kHz) and a BW of 50 to 400 MHz may be used.

[0017] In FR2-2, to avoid an increase in phase noise, Cyclic Prefix-Orthogonal Frequency Division Multiplexing (CP-OFDM) or Discrete Fourier Transform-Spread-Orthogonal Frequency Division Multiplexing (DFT-S-OFDM) with a larger SCS may be applied.

[0018] 3, one slot in the wireless communication system 10 is composed of 14 symbols. If this configuration is maintained, the larger (wider) the SCS, the shorter the symbol period (and slot period). Note that the SCS is not limited to the frequencies shown in FIG. 3 and may be, for example, 480 kHz, 960 kHz, or other frequencies.

[0019] Furthermore, the number of symbols constituting one slot does not necessarily have to be 14, but may be, for example, 28 or 56. Furthermore, the number of slots per subframe may differ depending on the SCS.

[0020] (2) Functional Block Configuration of Wireless Communication System (2.1) Functional Block Configuration of Terminal As shown in FIG. 4, the UE 200 includes a transceiver unit 210, a message generator 220, a model memory unit 230, a model determination unit 240, a model request unit 250, an estimation accuracy determination unit 260, and a control unit 270.

[0021] The transceiver 210 transmits and receives radio signals to and from the gNB 100. The transceiver 210 may be configured with a transmitter that transmits radio signals to the gNB 100 and a receiver that receives radio signals from the gNB 100. "Send" may be interpreted as "report," "notify," etc. Furthermore, "receive" may be interpreted as "set," "instruct," etc. The radio signal includes, for example, a message or a Measurement Report (MR) generated by the message generator 220. As will be described later, the message or MR may include information that the learning model is inapplicable (or has become inapplicable). That is, the transceiver 210 can transmit information that the learning model is inapplicable (or has become inapplicable).

[0022] Here, the determination that the learning model is no longer applicable is made by the estimation accuracy determination unit 260 (described later) based on a threshold value (described later). That is, the transmitting / receiving unit 210 can transmit a message that the learning model is no longer applicable when the estimation accuracy of the learning model falls below a first threshold. Furthermore, the transmitting / receiving unit 210 can transmit a message that the learning model is no longer applicable when the number of times the estimation accuracy of the learning model falls below the first threshold exceeds a second threshold. Alternatively, the transmitting / receiving unit 210 can transmit a message that the learning model is no longer applicable when a timer (described later) expires without the estimation accuracy of the learning model returning to or above the first threshold during a period measured by the timer.

[0023] Furthermore, as will be described later, the message or MR may include the reason why the learning model is inapplicable (or the reason why it has become inapplicable) and a request for a necessary learning model. That is, the transceiver 210 can transmit the reason why the learning model is inapplicable. Furthermore, the transceiver 210 can transmit a request for a necessary learning model based on this reason.

[0024] The message generation unit 220 generates a message or MR to be transmitted to the gNB 100. The message may be, for example, RRCReconfigurationComplete, UEAssistanceInfo, RRCSetupComplete, RRCResumeComplete, etc. Furthermore, the message in this embodiment may be understood to include not only a Radio Resource Control (RRC) message but also a Medium Access Control Control Element (MAC CE) or Downlink Control Information (DCI). The message or MR in this embodiment may include content related to the learning model, such as a determination result or a determination reason by the model determination unit 240, a proposal / request by the model request unit 250, and a determination result or estimation accuracy by the estimation accuracy determination unit 260. Details will be described in the section on operation examples.

[0025] The model storage unit 230 stores a learning model that the UE 200 (control unit 270) applies to itself and uses. The learning model may be pre-installed at the time of shipment, or may be installed after being received (downloaded) from the gNB 100, as described below. The learning model optimizes processes related to, for example, Channel State Information (CSI) feedback, beam management (BM), positioning, mobility, network slicing, and QoE.

[0026] The model determination unit 240 determines whether or not the learning model applied by the UE 200 (control unit 270) satisfies the application conditions (hereinafter also referred to as applicability). The applicability of the learning model is determined based on, for example, the environment surrounding the UE 200, the specifications of the UE 200, etc. (hereinafter also simply referred to as the environment surrounding the UE 200). The environment surrounding the UE 200 is, for example, the UE movement speed, the channel model (e.g., urban macrocell (UMa) / urban microcell (UMi)), the inter-site distance (ISD), the frequency, the BWP, the antenna port layout, and the size of the learning model.

[0027] If the learning model is applicable, the model determination unit 240 includes this information in the above-mentioned message or MR. Also, if the learning model is not applicable, the model determination unit 240 includes this information in the above-mentioned message or MR. Furthermore, if the learning model is not applicable, the model determination unit 240 can include the reason (cause) why the learning model is not applicable in the above-mentioned message or MR.

[0028] The model determination unit 240 may continuously monitor the application conditions of the learning model (e.g., the UE movement speed), and when it detects that the learning model is not applicable, it may include a message to that effect in the message or MR.

[0029] The model request unit 250 includes in the message or MR a proposal / request for a learning model that satisfies the application conditions (hereinafter also referred to as a required learning model). The proposal / request for the required learning model may be interpreted as information related to the environment surrounding the UE. In this case, it is sufficient that the gNB 100 that receives the message or MR can determine the required learning model based on the information related to the environment surrounding the UE that is included in the message or MR.

[0030] The estimation accuracy determination unit 260 determines whether the estimation accuracy of the learning model is below a predetermined threshold (first threshold). That is, when the estimation accuracy of the learning model is below the first threshold, the estimation accuracy determination unit 260 determines that the learning model is no longer applicable. Here, the first threshold is, for example, an estimation accuracy of 90%. Note that the estimation accuracy determination unit 260 may be interpreted as corresponding to the "control unit" in the claims.

[0031] The estimation accuracy determination unit 260 may also determine that the learning model is inapplicable based on other criteria. For example, the estimation accuracy determination unit 260 may count the number of times the estimation accuracy of the learning model falls below a first threshold and determine that the learning model is inapplicable when this number exceeds a predetermined threshold (second threshold). Here, the second threshold is, for example, a positive integer greater than or equal to 2. Alternatively, the estimation accuracy determination unit 260 may start a timer that measures a predetermined period when the estimation accuracy of the learning model falls below the first threshold and determine that the learning model is inapplicable when the timer expires without the estimation accuracy of the learning model returning to or above the first threshold.

[0032] Regardless of the determination criterion, the estimation accuracy determination unit 260 includes in the above-mentioned message or MR that the learning model has become inapplicable. Alternatively, the estimation accuracy determination unit 260 may include in the above-mentioned message or MR the estimation accuracy of the learning model itself. In this case, the gNB 100 may determine that the learning model has become inapplicable.

[0033] Furthermore, estimation accuracy determination unit 260 can estimate the reason why the learning model is inapplicable. The reason why the learning model is inapplicable may be estimated based on a change in the environment surrounding UE 200 (or a change in the setting parameters of UE 200 in accordance with the change in the environment). In this case, estimation accuracy determination unit 260 may include the reason why the learning model is inapplicable in the above-mentioned message or MR.

[0034] The determination by the estimation accuracy determination unit 260 may be performed intermittently at predetermined intervals or continuously, similar to the model determination unit 240. The estimation accuracy determination unit 260 continues to monitor the estimation accuracy of the learning model, and when it detects that the learning model is not applicable based on the above-mentioned threshold, it may include a message or MR to that effect.

[0035] The control unit 270 controls the UE 200. The control unit 270 controls the operations of the transmission / reception unit 210, the message generation unit 220, the model storage unit 230, the model determination unit 240, the model request unit 250, and the estimation accuracy determination unit 260, for example.

[0036] The control unit 270 applies and uses the learning model that satisfies the above-described application conditions. Note that application may be interpreted as activation, switch (from the currently applied learning model), etc. By using the learning model, the UE 200 can optimize processing related to Channel State Information (CSI) feedback, beam management (BM), positioning, mobility, network slicing, QoE, etc.

[0037] Specifically, the UE 200 can reduce overhead and improve the accuracy of CSI feedback by using a learning model related to CSI feedback. Also, the UE 200 can estimate a high-quality beam at its own future position by using a learning model related to BM. Alternatively, the UE 200 can accurately estimate its own future position by using a learning model related to positioning.

[0038] The control unit 270 can deactivate a learning model that does not satisfy the application conditions or that no longer satisfies the application conditions. The control unit 270 can also pre-set a learning model that will not be deactivated even if it no longer satisfies the application conditions. As a result, the control unit 270 excludes the pre-set learning model from the learning models to be deactivated, so there is no risk of all learning models stored in the model storage unit 230 being deactivated.

[0039] (2.2) Functional block configuration of base station As shown in FIG. 5, the gNB 100 includes a transceiver unit 110, a message generator unit 120, a model memory unit 130, an estimation accuracy determination unit 160, and a control unit 170.

[0040] The transceiver 110 transmits and receives radio signals to and from the UE 200. The transceiver 110 may be configured as a transmitter that transmits radio signals to the UE 200 or another gNB 100, and a receiver that receives radio signals from the UE 200 or another gNB 100. "Send" may be interpreted as "configure," "instruct," or the like. "Receive" may be interpreted as "reported," "notified," or the like. The radio signals include, for example, a message generated by the message generator 120.

[0041] The message generating unit 120 generates a message to be transmitted to the UE 200. The message may be, for example, an RRCReconfiguration message. The message in this embodiment may be understood to include not only a Radio Resource Control (RRC) message but also a Medium Access Control Element (MAC CE) or Downlink Control Information (DCI). The message in this embodiment may include a learning model stored in the model storage unit 130, setting information related to the learning model, and an instruction to switch / enable / disable the learning model based on the determination result by the estimation accuracy determining unit 160. Details will be described in the section on operation examples.

[0042] The model storage unit 130 stores a learning model that the UE 200 (control unit 270) applies to itself and uses. The learning model optimizes processes related to, for example, Channel State Information (CSI) feedback, beam management (BM), positioning, mobility, network slicing, and QoE.

[0043] The estimation accuracy determination unit 160 determines whether the estimation accuracy of the learning model is below a predetermined threshold (first threshold). That is, when the estimation accuracy of the learning model is below the first threshold, the estimation accuracy determination unit 160 determines that the learning model is no longer applicable.

[0044] The estimation accuracy determination unit 160 may also determine that the learning model has become inapplicable based on other determination criteria. For example, the estimation accuracy determination unit 160 may count the number of times the estimation accuracy of the learning model falls below a first threshold, and determine that the learning model has become inapplicable when this number exceeds a predetermined threshold (second threshold). Alternatively, the estimation accuracy determination unit 160 may start a timer that measures a predetermined period when the estimation accuracy of the learning model falls below the first threshold, and determine that the learning model has become inapplicable when this timer expires without the estimation accuracy of the learning model returning to or above the first threshold.

[0045] Furthermore, the estimation accuracy determination unit 160 can estimate the reason why the learning model is no longer applicable. The reason why the learning model is no longer applicable may be estimated based on a change in the AI ​​inference value transmitted from the UE 200, etc.

[0046] Note that the determination by estimation accuracy determination unit 160 may be performed intermittently at predetermined intervals or continuously, similarly to estimation accuracy determination unit 260. Estimation accuracy determination unit 160 continues to monitor the estimation accuracy of the learning model, and when detecting that it is inapplicable based on the above-mentioned threshold, may include a notice to that effect in the above-mentioned message or MR. Note that in this case, the estimation accuracy of the learning model (AI inference value) is assumed to be transmitted from UE 200 intermittently or continuously.

[0047] The control unit 170 controls the gNB 100. The control unit 170 controls the operations of the transmission / reception unit 110, the message generation unit 120, the model storage unit 130, and the estimation accuracy determination unit 160, for example.

[0048] The control unit 170 can instruct the UE 200 which learning model the UE 200 should apply. Note that application may be interpreted as activation, switch (from the currently applied learning model), or the like. Similarly, the control unit 170 can instruct the UE 200 which learning model to deactivate. These instructions may be realized by being included in the above-mentioned message and transmitted.

[0049] The control unit 170 can include in the above-mentioned message the learning model stored in the model storage unit 130. In particular, the control unit 170 can include in the above-mentioned message the learning model required by the UE 200 based on a request from the model request unit 250 of the UE 200 or based on the reason why the learning model determined by the estimation accuracy determination unit 160 is not applicable.

[0050] The control unit 170 can set in advance a learning model that will not be invalidated even if the application conditions are no longer satisfied. Specifically, the learning model that will not be invalidated (hereinafter also referred to as a default learning model or a learning model that will be made absolutely active) and its identification information (e.g., AI model ID) can be included in the above-mentioned message. As a result, the control unit 170 excludes the previously set learning model from the learning models to be invalidated, so there is no risk of all learning models stored in the model storage unit 230 of the UE 200 being invalidated.

[0051] (3) Operation of the Wireless Communication System (3.1) Issues (3.1.1) Issue 1 UE 200 may not satisfy the application conditions of a learning model pre-stored in itself due to the setting parameters of UE 200 or the environment surrounding UE 200. If UE 200 does not satisfy the application conditions of the learning model, there is a risk that the learning model cannot be used, and there is also a risk that the learning model may be used with low estimation accuracy.

[0052] (3.1.2) Issue 2: Due to changes in the UE200's configuration parameters or the environment surrounding the UE200, a learning model that once satisfied the application conditions may no longer satisfy the application conditions. In such a case, the UE200 may recognize the change in its surrounding environment and determine that the downloaded learning model no longer satisfies the application conditions, and report this to the gNB. However, for example, if the change is small, the learning model may not necessarily no longer satisfy the application conditions. Reporting every time the environment surrounding the UE changes leaves room for improvement in terms of resource utilization efficiency.

[0053] (3.1.3) Problem 3: When a learning model pre-stored in UE 200 does not satisfy the application conditions, UE 200 may invalidate the learning model. However, if all learning models pre-stored in UE 200 are invalidated, there is a risk that functions related to the learning models in UE 200 may stop.

[0054] (3.2) Operational Examples (3.2.1) Operational Example 1 As shown in Fig. 6, the UE 200 receives an RRCReconfiguration message from the gNB 100. The RRCReconfiguration message may include one or more learning models, may include identification information for the learning models (e.g., AI model ID), and may further include mapping information linking information related to an environment in which the learning models can be used (or are preferably used) (e.g., scenario, setting, location of use).

[0055] UE200 may determine whether the learning model included in the RRCReconfiguration message satisfies the application conditions, and may report the following information to gNB100 via the RRCReconfigurationComplete message.

[0056] - Applicability of the learning model (application complete / incomplete) * Applicability of the learning model (application complete / incomplete) may be reported using a single bit indicating either applicable / application complete or not applicable. - Reasons why the learning model does not meet the application conditions (e.g., UE movement speed, channel model (e.g., UMa / UMi), ISD, frequency, BWP, antenna port layout (layout), learning model size) - Proposal / request for a required learning model (e.g., compatible with UE movement speed of 120 km / h, compatible with UMi channel model, compatible with 500 m ISD, compatible with 2 GHz frequency, compatible with 100 MHz BWP, compatible with 4x4 antenna port layout, compatible with size of 100 Mbytes or less) * The required learning model may be interpreted as information related to the environment surrounding the UE. The same applies to the following explanation.

[0057] Furthermore, as shown in Fig. 7, the UE 200 may propose / request the necessary training model via a UEAssistanceInfo message or another UL message instead of the RRCReconfigurationComplete message, such as an RRCSetupComplete message or an RRCResumeComplete message.

[0058] As described above, when the UE 200 does not satisfy the application conditions of the learning model pre-stored in itself, the UE 200 can report this to the gNB 100. Furthermore, the UE 200 can report to the gNB 100 not only that the application conditions are not satisfied, but also the reason and the required learning model.

[0059] (3.2.2) Operation Example 2 (3.2.2.1) Operation Example 2-1 The UE 200 may report to the gNB 100 that the application conditions of the learning model are no longer satisfied by an event-based trigger. Note that the setting related to the event-based trigger may be performed via, for example, an RRCReconfiguration message. Furthermore, the UE 200 may disable the learning model that no longer satisfies the application conditions.

[0060] Specifically, UE200 may report to gNB100 that the conditions for applying the learning model are no longer met when the estimation accuracy of the learning model (e.g., the accuracy (or confidence score) of the AI ​​inference value) falls below a predetermined threshold (first threshold). Also, UE200 may report to gNB100 that the conditions for applying the learning model are no longer met when the number of times the estimation accuracy of the learning model falls below the predetermined threshold (first threshold) exceeds a predetermined number (second threshold).

[0061] Alternatively, UE200 may start a timer when the estimation accuracy of the learning model falls below a predetermined threshold (first threshold), or when the number of times the estimation accuracy of the learning model falls below the predetermined threshold (first threshold) exceeds a predetermined number (second threshold). UE200 may report to gNB100 that the application conditions for the learning model are no longer satisfied when the estimation accuracy of the learning model does not become equal to or greater than the predetermined threshold (first threshold) before the timer expires. Note that UE200 may stop the timer when the estimation accuracy of the learning model becomes equal to or greater than the predetermined threshold (first threshold) before the timer expires.

[0062] Alternatively, when UE200 recognizes that the environment surrounding UE200 has changed, UE200 may report to gNB100 that the application conditions of the learning model are no longer satisfied. Such recognition may be performed, for example, by a change in the configuration parameters of UE200. In this case, UE200 may report the reason why the learning model no longer satisfies the application conditions (e.g., UE movement speed, channel model (e.g., UMa / UMi), ISD, frequency, BWP, antenna port layout, size of the learning model) as in Operation Example 1. Note that UE200 may explain a more specific reason, such as a change in UE movement speed from 60 km / h to 120 km / h.

[0063] Furthermore, UE200 may propose / request the necessary learning model (e.g., compatible with UE movement speed of 120 km / h, compatible with UMi channel model, compatible with ISD of 500 m, compatible with 2 GHz frequency, compatible with 100 MHz BWP, compatible with 4x4 antenna port arrangement, compatible with size of 100 Mbytes or less).

[0064] Operation example 2-1 will be described with reference to FIG. 8 . As in operation example 1, UE 200 receives the learning model via an RRCReconfiguration message, and further reports to gNB 100 that the learning model satisfies the application conditions. Thereafter, UE 200 monitors whether the application conditions of the learning model are satisfied, and when it detects that the application conditions of the learning model are no longer satisfied, it reports this to gNB 100. Specifically, it reports that the application conditions of the learning model are no longer satisfied via a Measurement report. Furthermore, UE 200 may also report the reason why the application conditions of the learning model are no longer satisfied (for example, because the UE movement speed is no longer appropriate) at the same time as this report, and may further propose / request a required learning model (for example, a learning model corresponding to a UE movement speed of 120 km / h).

[0065] In response to the report from the UE 200, the gNB 100 may transmit an RRCReconfiguration message or a MAC CE. The RRCReconfiguration message or the MAC CE may include an instruction to switch the learning model, an instruction to disable the learning model that no longer satisfies the application conditions (and an instruction to enable the learning model that satisfies the application conditions), or a new learning model.

[0066] (3.2.2.2) Operation Example 2-2 The gNB100 may determine, instead of the UE200, that the application conditions of the learning model are no longer satisfied. The determination by the gNB100 may be based on a threshold and / or a timer, as in Operation Example 2-1, and a description thereof will be omitted here. As shown in FIG. 9 , the UE200 may report that the learning model received from the gNB100 satisfies the application conditions, and then report to the gNB100 an estimated value (AI inference value in the figure) output using the learning model. The estimated value may be reported at predetermined intervals or dynamically based on an instruction from the gNB100.

[0067] The gNB100 may monitor whether the application conditions of the learning model are satisfied based on the received estimated value of the learning model. When the gNB100 detects that the application conditions of the learning model are no longer satisfied, it may transmit an RRCReconfiguration message or a MAC CE, as in Operation Example 2-1. The RRCReconfiguration message or the MAC CE may include an instruction to switch the learning model, an instruction to disable the learning model that no longer satisfies the application conditions (and an instruction to enable the learning model that satisfies the application conditions), or a new learning model.

[0068] (3.2.2.3) Operation Example 2-3 Operation example 2-3 is a modified example of the switching of the learning model in operation examples 2-1 and 2-2. Specifically, operation example 2-3 is an operation example in which the UE 200 autonomously switches the learning model, which was performed by instruction from the gNB 100 in operation examples 2-1 and 2-2. Operation example 2-3 will be described below with reference to FIG. 10.

[0069] Before the UE 200 autonomously switches the learning model, specific learning model switching conditions are set in advance by the gNB 100. This pre-setting may be performed, for example, via the RRC Reconfiguration message shown in Fig. 10, but is not limited to this, and may be performed before or after that. Below, an example will be described in which the learning model switching conditions are set at the same time as the setting of three learning models via the RRC Reconfiguration message.

[0070] UE 200 receives learning models A, B, and C via the RCReconfiguration message. Learning model A corresponds to a UE movement speed of 30 km / h, learning model B corresponds to a UE movement speed of 60 km / h, and learning model C corresponds to a UE movement speed of 120 km / h. The learning model switching condition may be, for example, starting a timer when the UE movement speed exceeds a predetermined threshold, and ensuring that the UE movement speed does not fall below the predetermined threshold before the timer expires.

[0071] Specifically, when UE200 uses learning model A, a timer is started when the UE moving speed exceeds 60 km / h. If the UE moving speed does not fall below 60 km / h before the timer expires, UE200 determines that the learning model switching condition is met (detection of failure to meet the applicability condition of AI model in the figure). UE200 disables learning model A and switches to learning model B (deactivating the AI ​​model and switching to another applicable AI model in the figure).

[0072] Furthermore, the UE 200 may report to the gNB 100 via an RRC message or MAC CE that the learning model has been autonomously switched or disabled (and another learning model has been enabled). Also, if there is no appropriate learning model, the UE 200 may propose / request a required learning model to the gNB 100.

[0073] Note that the switching conditions related to the UE movement speed in the description of operation example 2-3 are just examples, and may be replaced with switching conditions related to the channel model (e.g., UMa / UMi), ISD, frequency, BWP, antenna port layout, and learning model size.

[0074] (3.2.3) Operation Example 3 Operation example 3 is a variation of operation example 2 (2-1, 2-2, 2-3) that imposes restrictions on disabling the learning model. That is, UE200 may activate at least one learning model regardless of an instruction from gNB100 or a learning model switching condition. Such a learning model may be set in advance as a default learning model. The default learning model may be, for example, a general-purpose learning model. If all learning models do not satisfy the application conditions, UE200 may fall back to the default learning model regardless of an instruction from gNB100 or a learning model switching condition.

[0075] The default learning model may be referred to as a common AI model or a reference AI model. The common AI model may include sub-common AI models for each use case. The sub-common AI model may be, for example, a common AI model for beam management, a common AI model for CSI prediction, or a common AI model for positioning. The common AI model or sub-common AI model may be transmitted from a gNB 100 forming a source cell to a gNB 100 forming a target cell, for example, during handover. This allows the gNB 100 forming the target cell to inherit the learning model without having to re-download it from an OAM (Operations, Administration, and Maintenance) that handles network maintenance and management functions, thereby enabling the gNB 100 to quickly use AI / ML functions.

[0076] If all learning models do not satisfy the application conditions, UE200 may report this to gNB100. Furthermore, UE200 may propose / request a default learning model (a learning model that is always enabled) to gNB100. In response to the proposal / request from UE200, gNB100 may set the default learning model (a learning model that is always enabled) and identification information (e.g., AI model ID) of the learning model in UE200.

[0077] The default learning model may be set in advance when the UE 200 is shipped, may be set in advance by a user of the UE 200, or may be set in advance from the gNB 100. When set from the gNB 100, the default learning model and identification information (e.g., AI model ID) of the learning model may be set, for example, via RRCReconfiguration. Alternatively, when there is only one learning model left that satisfies the application conditions, the UE 200 may always activate the learning model as the default learning model.

[0078] (4) Other Embodiments The contents of the present invention have been described above in accordance with the embodiments, but it will be obvious to those skilled in the art that the present invention is not limited to these descriptions and that various modifications and improvements are possible.

[0079] In the above disclosure, the proposal / request of the UE 200 may be executed based on the validity period set in the learning model, thereby enabling more efficient utilization of communication resources.

[0080] In the above disclosure, the learning model is intended to optimize processes related to Channel State Information (CSI) feedback, beam management (BM), positioning, mobility, network slicing, QoE, etc., but is not limited thereto. For example, the learning model may be intended to suppress call losses, radio link failures (RLFs), and minimization of unnecessary handovers (HOs) of the UE 200, in other words, to optimize the mobility of the UE 200.

[0081] In the above disclosure, the term "learning model" may be replaced with another term meaning a similar model, such as an AI / ML model.

[0082] In the above disclosure, the learning model is set or transmitted by the gNB 100, but this is not limited thereto. The learning model may be set or transmitted by another configuration on the network side.

[0083] The above-described operation examples may be combined and applied in a composite manner, as long as no contradiction occurs.

[0084] In the above disclosure, configure, activate, update, indicate, enable, specify, and select may be interchangeable. Similarly, link, associate, correspond, and map may be interchangeable, and allocate, assign, monitor, and map may be interchangeable.

[0085] Furthermore, specific, dedicated, UE-specific, and UE-dedicated may be interchangeable. Similarly, common, shared, group-common, UE-common, and UE-shared may be interchangeable.

[0086] The block diagrams (FIGS. 4 and 5) used to explain the above-described embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may be realized by combining software with the single device or multiple devices.

[0087] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, election, establishment, comparison, assumption, expectation, regard, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how each is implemented.

[0088] Furthermore, the above-described gNB 100 and UE 200 (the devices) may function as a computer that performs processing of the wireless communication method of the present disclosure. Figure 11 is a diagram showing an example of the hardware configuration of the devices. As shown in Figure 11, the devices may be configured as a computer including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0089] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the apparatus may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0090] Each functional block of the device (FIGS. 4 and 5) is realized by any hardware element of the computer device or a combination of the hardware elements.

[0091] In addition, each function of the device is realized by loading specified software (programs) onto hardware such as processor 1001 and memory 1002, causing processor 1001 to perform calculations, control communication via communication device 1004, and control at least one of reading and writing data in memory 1002 and storage 1003.

[0092] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control unit, an arithmetic unit, and registers.

[0093] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. Furthermore, the various processes described above may be executed by a single processor 1001, or may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

[0094] The memory 1002 is a computer-readable recording medium and may be configured by at least one of, for example, a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 may store a program (program code), a software module, etc., capable of executing a method according to an embodiment of the present disclosure.

[0095] Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a Compact Disc ROM (CD-ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned recording medium may be, for example, a database, a server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0096] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0097] The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize, for example, at least one of Frequency Division Duplex (FDD) and Time Division Duplex (TDD).

[0098] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0099] Furthermore, each device such as the processor 1001 and the memory 1002 is connected to a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0100] Furthermore, the device may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0101] Furthermore, the notification of information is not limited to the aspects / embodiments described in the present disclosure, and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI), Uplink Control Information (UCI)), higher layer signaling (e.g., RRC signaling, Medium Access Control (MAC) signaling), broadcast information (Master Information Block (MIB), System Information Block (SIB)), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0102] Each aspect / embodiment described in the present disclosure may be applied to at least one of a system using Long Term Evolution (LTE), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, a 4th generation mobile communication system (4G), a 5th generation mobile communication system (5G), Future Radio Access (FRA), New Radio (NR), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), or other suitable system, and a next-generation system enhanced based on these. Furthermore, a combination of multiple systems (e.g., a combination of at least one of LTE and LTE-A and 5G) may also be applied.

[0103] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0104] In the present disclosure, a specific operation described as being performed by a base station may be performed by its upper node in some cases. In a network consisting of one or more network nodes having a base station, it is clear that various operations performed for communication with a terminal may be performed by at least one of the base station and another network node other than the base station (for example, an MME or an S-GW, etc., but are not limited to these). Although the above example illustrates a case where there is one other network node other than the base station, a combination of multiple other network nodes (for example, an MME and an S-GW) may also be used.

[0105] Information, signals (information, etc.) may be output from a higher layer (or a lower layer) to a lower layer (or a higher layer), or may be input / output via multiple network nodes.

[0106] The input and output information may be stored in a specific location (for example, a memory) or may be managed using a management table. The input and output information may be overwritten, updated, or added. The output information may be deleted. The input information may be transmitted to another device.

[0107] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0108] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0109] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0110] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0111] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0112] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0113] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0114] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or other corresponding information. For example, a radio resource may be indicated by an index.

[0115] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0116] In this disclosure, terms such as "base station (BS)," "radio base station," "fixed station," "NodeB," "eNodeB (eNB)," "gNodeB (gNB)," "access point," "transmission point," "reception point," "transmission / reception point," "cell," "sector," "cell group," "carrier," and "component carrier" may be used interchangeably. Base stations may also be referred to by terms such as macrocell, small cell, femtocell, and picocell.

[0117] A base station can accommodate one or more (e.g., three) cells (also called sectors). When a base station accommodates multiple cells, the overall coverage area of ​​the base station can be divided into multiple smaller areas, and each smaller area can be provided with communication services by a base station subsystem (e.g., a small indoor base station (Remote Radio Head: RRH)).

[0118] The terms "cell" or "sector" refer to part or all of the coverage area of ​​a base station and / or base station subsystem that provides communication services within that coverage area.

[0119] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," etc. may be used interchangeably.

[0120] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0121] At least one of the base station and the mobile station may be referred to as a transmitting device, a receiving device, a communication device, etc. At least one of the base station and the mobile station may be a device mounted on a mobile object, the mobile object itself, etc. The mobile object may be a vehicle (e.g., a car, an airplane, etc.), an unmanned mobile object (e.g., a drone, an autonomous vehicle, etc.), or a robot (manned or unmanned). At least one of the base station and the mobile station may also include devices that do not necessarily move during communication operations. For example, at least one of the base station and the mobile station may be an Internet of Things (IoT) device such as a sensor.

[0122] Furthermore, a base station in the present disclosure may be read as a mobile station (user terminal, the same applies hereinafter). For example, the aspects / embodiments of the present disclosure may be applied to a configuration in which communication between a base station and a mobile station is replaced with communication between multiple mobile stations (which may be called, for example, Device-to-Device (D2D) or Vehicle-to-Everything (V2X)). In this case, the mobile station may be configured to have the functions of a base station. Furthermore, terms such as "uplink" and "downlink" may be read as terms corresponding to terminal-to-terminal communication (for example, "side"). For example, terms such as an uplink channel and a downlink channel may be read as a side channel.

[0123] Similarly, a mobile station in the present disclosure may be interpreted as a base station, in which case the base station may have the functions of a mobile station.

[0124] A radio frame may be made up of one or more frames in the time domain, each of which may be called a subframe.

[0125] A subframe may further be composed of one or more slots in the time domain, and may have a fixed time length (e.g., 1 ms) that is independent of numerology.

[0126] Numerology may be communication parameters that apply to the transmission and / or reception of a signal or channel, such as subcarrier spacing (SCS), bandwidth, symbol length, cyclic prefix length, transmission time interval (TTI), number of symbols per TTI, radio frame structure, specific filtering operations performed by the transceiver in the frequency domain, and specific windowing operations performed by the transceiver in the time domain.

[0127] A slot may consist of one or more symbols in the time domain (such as Orthogonal Frequency Division Multiplexing (OFDM) symbols, Single Carrier Frequency Division Multiple Access (SC-FDMA) symbols, etc.) A slot may be a time unit based on numerology.

[0128] A slot may include multiple minislots. Each minislot may consist of one or multiple symbols in the time domain. A minislot may also be called a subslot. A minislot may consist of fewer symbols than a slot. A PDSCH (or PUSCH) transmitted in a time unit larger than a minislot may be called PDSCH (or PUSCH) mapping type A. A PDSCH (or PUSCH) transmitted using a minislot may be called PDSCH (or PUSCH) mapping type B.

[0129] The radio frame, subframe, slot, minislot, and symbol all represent time units for transmitting signals, and may be referred to by other names corresponding to the radio frame, subframe, slot, minislot, and symbol.

[0130] For example, one subframe may be referred to as a transmission time interval (TTI), multiple consecutive subframes may be referred to as a TTI, or one slot or one minislot may be referred to as a TTI. That is, at least one of the subframe and the TTI may be a subframe (1 ms) in existing LTE, a period shorter than 1 ms (e.g., 1-13 symbols), or a period longer than 1 ms. Note that the unit representing the TTI may be referred to as a slot, minislot, etc. instead of a subframe.

[0131] Here, TTI refers to, for example, the smallest time unit for scheduling in wireless communication. For example, in an LTE system, a base station schedules each user terminal to allocate radio resources (such as frequency bandwidth and transmission power that can be used by each user terminal) in TTI units. Note that the definition of TTI is not limited to this.

[0132] The TTI may be a transmission time unit for a channel-encoded data packet (transport block), a code block, a code word, etc., or may be a processing unit for scheduling, link adaptation, etc. When a TTI is given, the time interval (e.g., the number of symbols) to which a transport block, a code block, a code word, etc. is actually mapped may be shorter than the TTI.

[0133] In addition, when one slot or one minislot is called a TTI, one or more TTIs (i.e., one or more slots or one or more minislots) may be the minimum time unit for scheduling. Furthermore, the number of slots (minislots) constituting the minimum time unit for scheduling may be controlled.

[0134] A TTI having a time length of 1 ms may be called a regular TTI (TTI in LTE Rel. 8-12), normal TTI, long TTI, regular subframe, normal subframe, long subframe, slot, etc. A TTI shorter than a regular TTI may be called a shortened TTI, short TTI, partial or fractional TTI, shortened subframe, short subframe, minislot, subslot, slot, etc.

[0135] In addition, a long TTI (e.g., a normal TTI, a subframe, etc.) may be interpreted as a TTI having a time length of more than 1 ms, and a short TTI (e.g., a shortened TTI, etc.) may be interpreted as a TTI having a TTI length shorter than the TTI length of a long TTI and equal to or greater than 1 ms.

[0136] A resource block (RB) is a resource allocation unit in the time domain and the frequency domain, and may include one or more consecutive subcarriers in the frequency domain. The number of subcarriers included in an RB may be the same regardless of numerology, for example, 12. The number of subcarriers included in an RB may be determined based on numerology.

[0137] The time domain of an RB may include one or more symbols and may have a length of one slot, one minislot, one subframe, or one TTI. One TTI, one subframe, etc. may each be composed of one or more resource blocks.

[0138] Note that one or more RBs may also be called a physical resource block (PRB), a sub-carrier group (SCG), a resource element group (REG), a PRB pair, an RB pair, etc.

[0139] Furthermore, a resource block may be composed of one or more resource elements (REs). For example, one RE may be a radio resource region of one subcarrier and one symbol.

[0140] A Bandwidth Part (BWP) (which may also be referred to as a fractional bandwidth) may represent a subset of contiguous common resource blocks (RBs) for a given numerology on a given carrier, where the common RBs may be identified by their index relative to a common reference point of the carrier. PRBs may be defined in a given BWP and numbered within that BWP.

[0141] The BWP may include a BWP for UL (UL BWP) and a BWP for DL ​​(DL BWP). One or more BWPs may be configured for a UE within one carrier.

[0142] At least one of the configured BWPs may be active, and the UE may not expect to transmit or receive a given signal / channel outside the active BWP. Note that the terms "cell," "carrier," etc. in this disclosure may be read as "BWP."

[0143] The above-described structures of radio frames, subframes, slots, minislots, symbols, etc. are merely examples. For example, the number of subframes included in a radio frame, the number of slots per subframe or radio frame, the number of minislots included in a slot, the number of symbols and RBs included in a slot or minislot, the number of subcarriers included in an RB, the number of symbols in a TTI, the symbol length, the cyclic prefix (CP) length, etc. may be variously changed.

[0144] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0145] The reference signal may also be abbreviated as Reference Signal (RS) and may be called a pilot depending on the applicable standard.

[0146] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0147] The "means" in the configuration of each of the above devices may be replaced with "part," "circuit," "device," etc.

[0148] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed therein or that the first element must precede the second element in some way.

[0149] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0150] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0151] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like, all of which are considered to be "determining." "Determining" and "determining" may also include resolving, selecting, choosing, establishing, comparing, and the like, all of which are considered to be "determining." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Also, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0152] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0153] 12 shows an example of the configuration of a vehicle 2001. As shown in Fig. 12, the vehicle 2001 includes a drive unit 2002, a steering unit 2003, an accelerator pedal 2004, a brake pedal 2005, a shift lever 2006, left and right front wheels 2007, left and right rear wheels 2008, an axle 2009, an electronic control unit 2010, various sensors 2021 to 2029, an information service unit 2012, and a communication module 2013.

[0154] The drive unit 2002 is composed of, for example, an engine, a motor, or a hybrid of an engine and a motor.

[0155] The steering unit 2003 includes at least a steering wheel (also called a handle) and is configured to steer at least one of the front wheels and the rear wheels based on the operation of the steering wheel operated by the user.

[0156] The electronic control unit 2010 is composed of a microprocessor 2031, a memory (ROM, RAM) 2032, and a communication port (IO port) 2033. Signals are input to the electronic control unit 2010 from various sensors 2021 to 2027 provided in the vehicle. The electronic control unit 2010 may also be called an ECU (Electronic Control Unit).

[0157] The signals from the various sensors 2021 to 2028 include a current signal from a current sensor 2021 that senses the current of the motor, a rotation speed signal of the front and rear wheels obtained by a rotation speed sensor 2022, an air pressure signal of the front and rear wheels obtained by an air pressure sensor 2023, a vehicle speed signal obtained by a vehicle speed sensor 2024, an acceleration signal obtained by an acceleration sensor 2025, an accelerator pedal depression amount signal obtained by an accelerator pedal sensor 2029, a brake pedal depression amount signal obtained by a brake pedal sensor 2026, a shift lever operation signal obtained by a shift lever sensor 2027, and a detection signal for detecting obstacles, vehicles, pedestrians, etc. obtained by an object detection sensor 2028.

[0158] The information service unit 2012 is composed of various devices, such as a car navigation system, an audio system, speakers, a television, and a radio, for providing various types of information such as driving information, traffic information, and entertainment information, and one or more ECUs for controlling these devices. The information service unit 2012 uses information obtained from external devices via the communication module 2013, etc., to provide various types of multimedia information and multimedia services to the occupants of the vehicle 1.

[0159] The driving assistance system unit 2030 is composed of various devices that provide functions for preventing accidents and reducing the driver's driving burden, such as millimeter-wave radar, LiDAR (Light Detection and Ranging), cameras, positioning locators (e.g., GNSS, etc.), map information (e.g., high-definition (HD) maps, autonomous vehicle (AV) maps, etc.), gyro systems (e.g., IMU (Inertial Measurement Unit), INS (Inertial Navigation System), etc.), AI (Artificial Intelligence) chips, and AI processors, as well as one or more ECUs that control these devices. The driving assistance system unit 2030 also transmits and receives various information via the communication module 2013 to realize driving assistance functions or autonomous driving functions.

[0160] The communication module 2013 can communicate with the microprocessor 2031 and components of the vehicle 1 via the communication port. For example, the communication module 2013 transmits and receives data via the communication port 2033 to and from a driving unit 2002, a steering unit 2003, an accelerator pedal 2004, a brake pedal 2005, a shift lever 2006, left and right front wheels 2007, left and right rear wheels 2008, an axle 2009, a microprocessor 2031 and memory (ROM, RAM) 2032 in the electronic control unit 2010, and sensors 2021 to 2028, which are provided in the vehicle 2001.

[0161] The communication module 2013 is a communication device that can be controlled by the microprocessor 2031 of the electronic control unit 2010 and can communicate with an external device. For example, it transmits and receives various information to and from the external device via wireless communication. The communication module 2013 may be located either inside or outside the electronic control unit 2010. The external device may be, for example, a base station, a mobile station, or the like.

[0162] The communication module 2013 transmits, via wireless communication to an external device, a current signal from the current sensor that is input to the electronic control unit 2010. The communication module 2013 also transmits, via wireless communication to an external device, the rotation speed signals of the front and rear wheels acquired by a rotation speed sensor 2022, the air pressure signals of the front and rear wheels acquired by an air pressure sensor 2023, the vehicle speed signal acquired by a vehicle speed sensor 2024, the acceleration signal acquired by an acceleration sensor 2025, the accelerator pedal depression amount signal acquired by an accelerator pedal sensor 2029, the brake pedal depression amount signal acquired by a brake pedal sensor 2026, the shift lever operation signal acquired by a shift lever sensor 2027, and the detection signals for detecting obstacles, vehicles, pedestrians, etc. acquired by an object detection sensor 2028, all of which are input to the electronic control unit 2010.

[0163] The communication module 2013 receives various information (traffic information, traffic signal information, vehicle distance information, etc.) transmitted from external devices and displays it on an information service unit 2012 provided in the vehicle. The communication module 2013 also stores the various information received from the external devices in a memory 2032 that can be used by the microprocessor 2031. Based on the information stored in the memory 2032, the microprocessor 2031 may control the drive unit 2002, steering unit 2003, accelerator pedal 2004, brake pedal 2005, shift lever 2006, left and right front wheels 2007, left and right rear wheels 2008, axle 2009, sensors 2021 to 2028, and the like provided in the vehicle 2001.

[0164] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0165] (Additional Note) The above disclosure may be expressed as follows.

[0166] The first feature is a terminal that includes a control unit that determines whether the estimation accuracy of a learning model is below a first threshold, and a transmission unit that transmits information that the learning model is no longer applicable when the estimation accuracy is below the first threshold.

[0167] A second feature is that, in the first feature, the control unit counts the number of times the estimation accuracy falls below the first threshold, and the transmission unit transmits a message that the learning model is no longer applicable when the number of times exceeds a second threshold.

[0168] A third feature is that, in the terminal of the first feature, the control unit starts a timer that measures a period when the estimation accuracy falls below the first threshold, and the transmission unit transmits a signal that the learning model is no longer applicable when the timer expires without the estimation accuracy returning to or above the first threshold during the period.

[0169] A fourth feature is a terminal in which, in any of the first to third features, the control unit disables the learning model that has become inapplicable, except for a learning model that has been set in advance.

[0170] A fifth feature is a terminal in which, in any of the first to fourth features, the control unit estimates the reason why the learning model became inapplicable, and the transmission unit transmits the reason.

[0171] A sixth feature is the terminal according to the fifth feature, wherein the transmission unit transmits a request for a required learning model based on the reason.

[0172] 10 Wireless communication system 20 NG-RAN 100 gNB 110 Transceiver 120 Message generator 130 Model memory 160 Estimation accuracy determination unit 170 Control unit 200 UE 210 Transceiver 220 Message generator 230 Model memory 240 Model determination unit 250 Model request unit 260 Estimation accuracy determination unit 270 Control unit 1001 Processor 1002 Memory 1003 Storage 1004 Communication device 1005 Input device 1006 Output device 1007 Bus 2001 Vehicle 2002 Drive unit 2003 Steering unit 2004 Accelerator pedal 2005 Brake pedal 2006 Shift lever 2007 Left and right front wheels 2008 Left and right rear wheels 2009 Axle 2010 Electronic control unit 2012 Information service unit 2013 Communication module 2021 Current sensor 2022 RPM sensor 2023 Air pressure sensor 2024 Vehicle speed sensor 2025 Acceleration sensor 2026 Brake pedal sensor 2027 Shift lever sensor 2028 Object detection sensor 2029 Accelerator pedal sensor 2030 Driving assistance system unit 2031 Microprocessor 2032 Memory (ROM, RAM) 2033 Communication port

Claims

1. A terminal comprising: a control unit that determines whether the estimation accuracy of a learning model is below a first threshold; and a transmission unit that transmits a message indicating that the learning model is no longer applicable if the estimation accuracy is below the first threshold.

2. The terminal according to claim 1, wherein the control unit counts the number of times the estimation accuracy falls below the first threshold, and the transmission unit transmits a message indicating that the learning model is no longer applicable when the number of times exceeds a second threshold.

3. The terminal described in claim 1, wherein the control unit starts a timer that measures a period when the estimation accuracy falls below the first threshold, and the transmission unit transmits a message that the learning model is no longer applicable if the timer expires without the estimation accuracy returning to or above the first threshold during the period.

4. The terminal according to claim 1, wherein the control unit disables the learning models that have become inapplicable, except for a previously set learning model.

5. The terminal according to claim 1, wherein the control unit estimates a reason why the learning model is inapplicable, and the transmission unit transmits the reason.

6. The terminal according to claim 5, wherein the transmission unit transmits a request for a required learning model based on the reason.

Images