Wireless terminal, wireless access network node, and methods thereof

Abstract

A wireless terminal (1) receives, from a network, control information indicating whether the wireless terminal (1) is permitted to perform a specific action on the basis of an inference result of machine learning-based artificial intelligence. The wireless terminal (1) makes a prediction or a decision by using a trained machine learning model. The wireless terminal (1) performs, if permitted by the received control information, the specific action that has been triggered by the prediction or decision according to the machine learning model. This contributes to, for example, enabling a network (e.g., a radio access network (RAN) node) to conduct control of whether a wireless terminal is permitted to perform an action on the basis of the prediction or decision according to the trained machine learning model.

Description

Technical Field

[0001] The present disclosure relates to a wireless communication network, and more particularly to the application of artificial intelligence (AI) to a wireless communication network.

Background Art

[0002] The 3rd Generation Partnership Project (3GPP (registered trademark)) is discussing the application or introduction of AI or machine learning (ML) to 5G. AI / ML can be considered for both network internal functions and the air interface (i.e., Uu). In 3GPP Release 17, Radio Access Network (RAN) Working Group #3 (RAN3) is discussing network-based AI / ML without User Equipment (UE) participation. Examples of targets here include energy saving, load balancing, and mobility optimization (see, for example, Non-Patent Documents 1 and 2). In network-based AI / ML, the network executes AI / ML inference. AI / ML inference means a prediction or decision based on a trained machine learning model. The AI / ML inference function may be located in the Next Generation Radio Access Network (NG-RAN) (e.g., gNB). The training of the machine learning model may be performed in the NG-RAN. Alternatively, Operation, Administration and Maintenance (OAM) may train the machine learning model and supply the trained machine learning model (i.e., trained parameters) to the NG-RAN (e.g., gNB).

[0003] Furthermore, for 3GPP Release 18, network-based AI / ML involving UE participation and UE-based AI / ML have been proposed (see, for example, Non-Patent Documents 3-5). In UE-based AI / ML, the UE performs AI / ML inference. Potential use cases of AI / ML for the air interface include Channel State Information (CSI) feedback compression, beam management, positioning, Reference signal (RS) overhead reduction, and mobility. In UE-based AI / ML, the UE runs an AI model (i.e., a trained machine learning model) and locally obtains the AI inference result. For example, the UE can predict future events or measurements based on past measurements. The UE can feedback the predicted results (e.g., mobility or beam prediction) to the network (e.g., gNB).

Prior Art Documents

Non-Patent Documents

[0004]

Non-Patent Document 1

Non-Patent Document 2

[0005] The inventor of the present invention has studied UE-based AI / ML and found various problems. One of these problems relates to the execution conditions of UE-based AI / ML. For example, the UE executes some action based on a prediction or decision using a machine learning model. However, if this action of the UE may result in an interaction with the network or affect the performance of the network, it may not be appropriate for the UE to freely perform the action. Alternatively, it may not be appropriate for the UE to freely perform an action triggered by AI inference instead of being triggered by a rule (or criterion or formula) defined in the 3GPP specification. Actions triggered by a rule (or criterion or formula) defined in the 3GPP specification include, for example, sending a measurement report for handover, executing conditional mobility, beam selection, and cell (re)selection.

[0006] One of the objectives to be achieved by the embodiments disclosed in this specification is to provide an apparatus, method, and program that contribute to solving at least one of a plurality of problems related to UE-based AI / ML including the problems described above. It should be noted that this objective is only one of the plurality of objectives to be achieved by the plurality of embodiments disclosed in this specification. Other objectives or problems and novel features will be apparent from the description of this specification or the accompanying drawings.

Means for Solving the Problems

[0007] In a first aspect, a wireless terminal includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to receive from a network control information indicating whether the wireless terminal is permitted to perform a particular action based on an inference result of a machine learning-based artificial intelligence. The at least one processor is configured to make a prediction or a determination using a trained machine learning model. The at least one processor is configured to perform the particular action triggered by the prediction or determination if the control information permits execution of the particular action based on the inference result.

[0008] In a second aspect, a method performed by a wireless terminal includes the following steps: (a) Receiving from a network control information indicating whether the wireless terminal is permitted to perform a particular action based on an inference result of a machine learning-based artificial intelligence, (b) Making a prediction or a determination using a trained machine learning model, and (c) Performing the particular action triggered by the prediction or determination if the control information permits execution of the particular action based on the inference result.

[0009] In a third aspect, a radio access network (RAN) node includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to send to the wireless terminal control information indicating whether the wireless terminal is permitted to perform a particular action based on an inference result of a machine learning-based artificial intelligence. If the control information permits execution of the particular action based on the inference result, the control information causes the wireless terminal to perform the particular action triggered by a prediction or a determination using a trained machine learning model.

[0010] In a fourth aspect, the method performed by the RAN node includes transmitting, to the wireless terminal, control information indicating whether the wireless terminal is permitted to perform a specific action based on an inference result of a machine learning-based artificial intelligence. If the control information permits execution of the specific action based on the inference result, the control information causes the wireless terminal to perform the specific action triggered by a prediction or a determination using a trained machine learning model.

[0011] A fifth aspect is directed to a program. The program includes a set of instructions (software code) for causing a computer to perform the method according to the second or fourth aspect described above when loaded into the computer.

Advantages of the Invention

[0012] According to the above aspect, it is possible to provide an apparatus, a method, and a program that contribute to solving at least one of a plurality of problems related to UE-based AI / ML.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4A

Figure 4B

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Embodiments for Carrying Out the Invention

[0014] Hereinafter, specific embodiments will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are denoted by the same reference numerals, and redundant descriptions are omitted as necessary for clarity of explanation.

[0015] The plurality of embodiments described below can be implemented independently or can be implemented in appropriate combination. These plurality of embodiments have different novel features. Therefore, these plurality of embodiments contribute to solving different objects or problems and contribute to achieving different effects.

[0016] The plurality of embodiments shown below are mainly described with respect to the 3GPP fifth-generation mobile communication system (5G system). However, these embodiments may be applied to other wireless communication systems.

[0017] As used herein, depending on the context, "(if)~then" may be interpreted to mean "when", "at or around the time", "after", "upon", "in response to determining", "in accordance with a determination", or "in response to detecting". These expressions may be interpreted to have the same meaning depending on the context.

[0018] First, the configuration and operation of a plurality of network elements common to a plurality of embodiments are described. FIG. 1 shows a configuration example of a wireless communication system according to a plurality of embodiments. In the example of FIG. 1, the wireless communication system includes a wireless terminal (i.e., UE) 1 and a radio access network (RAN) node (e.g., gNB) 2. Each element (network function) shown in FIG. 1 can be implemented, for example, as a network element on dedicated hardware, as a software instance running on the dedicated hardware, or as a virtualized function instantiated on an application platform.

[0019] UE1 has at least one wireless transceiver and is configured to perform wireless communication with the RAN node 2. UE1 is connected to the RAN node 2 via the air interface 101. The RAN node 2 manages cells and is configured to perform wireless communication with a plurality of UEs including UE1 using cellular communication technology (e.g., NR Radio Access Technology (RAT)). UE1 may be simultaneously connected to a plurality of RAN nodes for Dual Connectivity (DC).

[0020] RAN Node 2 may be a Central Unit (e.g., gNB-CU) in a cloud RAN (C-RAN) deployment, or may be a combination of a CU and one or more Distributed Units (e.g., gNB-DUs). C-RAN is also referred to as CU / DU split. Further, the CU may include a Control Plane (CP) Unit (e.g., gNB-CU-CP) and one or more User Plane (UP) Units (e.g., gNB-CU-UP). Thus, RAN Node 2 may be a CU-CP, or a combination of CU-CP and CU-UP. The CU may be a logical node that hosts the Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP), and Packet Data Convergence Protocol (PDCP) protocols of the gNB (or the RRC and PDCP protocols of the gNB). The DU may be a logical node that hosts the Radio Link Control (RLC), Medium Access Control (MAC), and Physical (PHY) layers of the gNB.

[0021] UE1 may perform AI / ML inferences locally. This AI / ML inference may relate to the optimization of the radio access network. UE1 may execute AI inferences in a trained machine learning model and take one or more actions according to the predictions or decisions based on the AI inferences. The machine learning model may be any model known in the field of machine learning, including deep learning. The machine learning model may be, for example, but not limited to, a neural network model, a support vector machine model, a decision tree model, a random forest model, or a K-nearest neighbor model.

[0022] By way of example and not limitation, predictions or decisions based on AI inferences by UE1 and one or more actions triggered thereby relate to beam management or mobility or both. The one or more actions include, without limitation, at least one of cell reselection, transmission of measurement reports, execution of conditional mobility, and selection of a downlink beam. The downlink beam may be a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam. For example, a machine learning model may output a candidate cell for cell reselection, a target cell or node for handover, a candidate cell or node for conditional mobility, a candidate beam for beam selection, or a prediction result of a UE trajectory. Additionally or alternatively, the machine learning model may predict or determine the execution timing of actions for mobility or beam management.

[0023] Cell reselection may be performed when UE1 is in RRC_IDLE or RRC_INACTIVE.

[0024] Mobility may be performed when UE1 is in RRC_CONNECTED. Mobility in RRC_CONNECTED may be a handover. The handover may be a Dual Active Protocol Stack (DAPS) handover. Additionally or alternatively, mobility in RRC_CONNECTED may be related to various mobilities in DC. Specifically, the mobility may be a change of the primary cell of the Master Cell Group (MCG) in DC, an inter-Master Node (MN) handover in DC, a secondary node change in DC, or an addition or change of the primary cell of the secondary cell group in DC.

[0025] Conditional mobility may be performed when UE1 is in RRC_CONNECTED. Conditional mobility may be a conditional handover. Additionally or alternatively, conditional mobility may be related to various mobilities in DC. Specifically, conditional mobility may be a change of the primary cell of the Master Cell Group (MCG) in DC, an inter-Master Node (MN) handover in DC, a secondary node change in DC, or an addition or change of the primary cell of the secondary cell group in DC.

[0026] The selection of the downlink beam may be performed in the Beam Failure Recovery (BFR) procedure.

[0027] The training of the machine learning model for AI / ML inference by UE1 may be performed by UE1 or by the network (e.g., OAM, RAN Node 2). The method of the training may be offline learning, online learning, or a combination of these.

[0028] Similarly, RAN Node 2 may perform AI / ML inference. This AI / ML inference may relate to the optimization of the radio access network. RAN Node 2 may perform AI inference in the trained machine learning model and perform one or more actions according to the prediction or decision based on the AI inference. The machine learning model may be any model known in the field of machine learning including deep learning. The machine learning model may be, but is not limited to, for example, a neural network model, a support vector machine model, a decision tree model, a random forest model, or a K-nearest neighbor method model.

[0029] By way of example and not limitation, predictions or decisions based on AI inference by the RAN node 2 and one or more actions triggered thereby relate to at least one of energy saving, load balancing, mobility optimization, enhancement of CSI feedback, and enhancement of positioning accuracy. For example, the predictions or decisions of the machine learning model relate to one or both of the energy saving strategy and the mobility strategy. With respect to the mobility strategy, the machine learning model may output the prediction results of the target cell or node for handover, the candidate cell or node for conditional mobility, or the UE trajectory.

[0030] The training of the machine learning model for AI / ML inference by the RAN node 2 may be performed by the RAN node 2 or by the OAM. The method of the training may be offline learning, online learning, or a combination thereof.

[0031] <The first embodiment> The configuration example of the wireless communication system according to this embodiment may be the same as the example shown in FIG. 1. FIG. 2 shows an example of the operations of UE1 and RAN Node 2 for UE-based AI / ML, that is, for UE1 to perform AI inference with a machine learning model. In step 201, RAN Node 2 transmits control information to UE1. The control information may be transmitted via broadcast (e.g., system information). The system information may be any System Information Block. Alternatively, the control information may be transmitted to UE1 via dedicated signaling. The dedicated signaling may be individual RRC signaling, such as an RRC Reconfiguration message, an RRC Reestablishment message, an RRC Resume message, or an RRC Setup message. The control information may be an information element included in the SIB or individual RRC signaling. The name of the information element is not limited, for example, it may be "AI configuration".

[0032] The control information indicates whether UE1 is permitted to perform a specific action based on the inference result of the machine learning-based artificial intelligence. In other words, the control information indicates whether UE1 is permitted to perform a specific action triggered by a prediction or decision using a trained machine learning model. If the control information indicates that it permits this, the control information causes UE1 to perform a specific action triggered by a prediction or decision using a trained machine learning model. RAN Node 2 may transmit the control information (step 201) only when the execution of a specific action based on the AI / ML inference result at UE1 is permitted. In this case, the transmission of the control information can implicitly indicate the permission for the execution of a specific action based on the AI / ML inference result at UE1.

[0033] The term "inference result of machine learning-based artificial intelligence" may be paraphrased as an inference result by artificial intelligence, an estimation result of self-learning (by the UE), an estimation result of self-correction, or an estimation result of optimization (algorithm). The expression "performing a specific action based on the inference result of machine learning-based artificial intelligence" may be paraphrased as applying the inference result of artificial intelligence to a specific action, performing self-optimization (by the UE) for a specific action, or applying optimization (algorithm) to a specific action. The term "optimization of the radio access network" may mean, for example, optimization of the functions or processes of a radio network (e.g., one or more RAN nodes), or optimization of the values or settings of radio parameters set by the radio network for radio terminals (e.g., one or more UEs).

[0034] Specific examples of predictions or decisions based on AI inference by UE1 and one or more actions triggered thereby are as described above. By way of non-limiting example, specific actions triggered by a prediction or decision using a machine learning model in UE1 relate to at least one of beam management, mobility, CSI feedback, and positioning (or location estimation). Specific actions include, but are not limited to, for example, at least one of cell reselection, transmission of a measurement report, execution of conditional mobility, and selection of a downlink beam. Transmission of a measurement report may trigger a decision by the network (e.g., RAN node 2) to initiate mobility (e.g., handover).

[0035] By way of non-limiting example, specific actions relate to CSI feedback. The specific action may be adjustment of the timing (e.g., period) of CSI reporting. Further or alternatively, the specific action may be reducing or compressing the amount of information in the CSI report (e.g., beam information, channel matrix, precoding matrix).

[0036] By way of example and not limitation, a particular action relates to the positioning (or position estimation) of UE1. The particular action may be a correction of the information used for position estimation or a correction to the position estimation result.

[0037] Additionally or alternatively, the particular action may include transmitting to a network (e.g., RAN node 2) assistance information (e.g., UE assistance information) indicating the result of a prediction or decision using a first machine learning model in UE1. The assistance information may be used for training a second machine learning model related to the optimization of the radio access network. The assistance information may be used for inference execution in a second trained machine learning model related to the optimization of the radio access network. The second machine learning model and the second trained machine learning model may be located in RAN node 2 or OAM. Additionally or alternatively, the assistance information may be used for training (e.g., offline reinforcement learning) of the first machine learning model located in UE1.

[0038] Instead of or in addition to performing a particular action based on a predefined rule (or criterion or formula), the control information may indicate whether execution of the particular action based on the AI inference result is permitted. The predefined rule may be a rule predefined in the 3GPP specification. Alternatively, the predefined rule may be a rule preset by a network (e.g., RAN node 2). More specifically, the predefined rule may be a cell reselection rule (or criterion or formula), a measurement reporting rule (or criterion or formula), an execution rule (or criterion or formula) for conditional mobility, or a beam selection rule (or criterion or formula) defined in the 3GPP specification or set by the network. These rules (or criteria or formulas) are generally based on a comparison between cell or beam quality (e.g., Reference Signal Received Power (RSRP)) and a threshold.

[0039] The control information may indicate to UE1 collectively the permission to use machine learning-based artificial intelligence (i.e., UE-based AI / ML) for a plurality of actions including a specific action. Alternatively, the control information may indicate to UE1 individually whether each of the plurality of actions including the above-mentioned specific action is permitted. The control information may indicate an action or a category (or group) of actions for which the application of UE-based AI / ML is permitted. The control information may indicate a function or feature (e.g., mobility, power saving) for which the application of UE-based AI / ML is permitted. The control information may indicate a sub-function or sub-feature (e.g., cell selection, handover, beam management) for which the application of UE-based AI / ML is permitted. The control information may indicate a procedure (e.g., RRC re-establishment, beam failure recovery (BFR)) for which the application of UE-based AI / ML is permitted. The control information may indicate an RRC configuration (e.g., at the level of information elements or fields in Abstract Syntax Notation One (ASN.1)) for which the application of UE-based AI / ML is permitted.

[0040] The control information may indicate the conditions under which the execution of a specific action based on the AI / ML inference result is permitted. In this case, UE1 may perform a specific action triggered by a prediction or decision of a machine learning model (i.e., UE-based AI / ML) only when the indicated conditions are satisfied. The conditions under which the execution of the specific action is permitted may indicate constraints related to at least one of a frequency band, a location, and a time.

[0041] For example, the conditions may indicate the location (e.g., a geographical area, a cell, or a set of cells) where the execution of a specific action based on the AI / ML inference result is permitted. The conditions may indicate the time or period during which the execution of a specific action based on the AI / ML inference result is permitted. The conditions may indicate one or more frequency bands for which the execution of a specific action based on the AI / ML inference result is permitted.

[0042] Further or alternatively, the condition may be that a consistent impairment is detected. For example, the condition may permit UE1 to perform a specific action based on an AI / ML inference result when a predetermined impairment is repeatedly detected in the same or similar situations (e.g., location, cell, cell pair, time, frequency band, time). The predetermined impairment may be, for example, a handover impairment or a beam impairment. The situation may be at least one of location, cell, cell pair, time, frequency band, and time.

[0043] Further or alternatively, the condition may be that UE1 has received a signal indicating a predetermined identifier from a network (e.g., RAN Node 2). The predetermined identifier may be, but is not limited to, for example, a Config Set Number or ID, an AI Set Number or ID, or a Combination Set Number or ID. The predetermined identifier may be set by the network to represent the same or similar situation (e.g., the transmission power of RAN Node 2, antenna tilt, number of downlink beams, or other physical layer settings).

[0044] Figure 3 shows an example of the operation of UE1. In step 301, UE1 receives the above-described control information. In step 302, UE1 makes a prediction or decision using a trained machine learning model. In step 303, if the control information indicates that it permits, UE1 performs a specific action triggered by the prediction or decision based on the machine learning model. In step 303, UE1 may consider the conditions indicated in the control information. As described above, the condition may be a condition for permitting UE1 to perform a specific action based on an AI / ML inference result. In this case, UE1 may perform a specific action triggered by the prediction or decision of the machine learning model (i.e., UE-based AI / ML) only when the indicated condition is satisfied.

[0045] Figure 4A shows an example of the format of control information (steps 201, 301). The Ai-configuration information element (Information Element (IE)) 401 shown in Figure 4A may be transmitted from RAN node 2 to UE1 in an SIB or an individual RRC message. The Ai-configuration IE 401 can include an AI-ML-ConfigList IE 402. The AI-ML-ConfigList IE 402 can include one or more AI-ML-Config IEs 403. Each AI-ML-Config IE 403 can include one or any combination of a targetFeature IE 404, a targetArea IE 405, and a condition IE 406.

[0046] The targetFeature IE 404 may indicate one or more categories (or groups) of actions for which UE-based AI / ML application is permitted. The categories of actions include, for example, one or more of "mobilityConnected", "mobilityIdleInactive", "beamManagement", "energySaving", "rrmMeasurement", "csiFeedback", and "positioningAccuracy".

[0047] If "mobilityConnected" is set in the targetFeature IE404, this indicates that, for example, the application of UE-based AI / ML to the mobility functions performed by the UE1 in the RRC_Connected state is permitted. The application of UE-based AI / ML to the mobility functions in the RRC_Connected state may be an adjustment related to handover or an adjustment related to Conditional Handover (CHO). The adjustment related to handover may be an adjustment of the reporting timing of the measurement report (MR), or an adjustment of the offset value or threshold value of the MR event. The adjustment of the processing related to CHO may be an adjustment of the offset value or threshold value of the CHO execution condition. Further or alternatively, the application of UE-based AI / ML to the mobility functions in the RRC_Connected state may be an adjustment related to the addition or change of the PSCell of Multi-Radio Dual Connectivity (MR-DC), or an adjustment related to Conditional PSCell Addition / Change (CPAC). PSCell is an abbreviation for Primary SCell or Primary Secondary Cell Group (SCG) Cell.

[0048] If "mobilityIdleInactive" is set in targetFeature IE404, this indicates that the application of UE-based AI / ML to the mobility functions performed by UE1, for example, in either or both of the RRC_IDLE state and the RRC_INACTIVE state, is permitted. The application of UE-based AI / ML to the mobility functions in the RRC_IDLE state or the RRC_INACTIVE state may mean adjustments related to cell reselection. The adjustments related to cell reselection may be adjustments to the parameters used in the cell reselection process. For example, this may be an adjustment of an offset value or a threshold value, an adjustment of priorities per frequency or between frequencies, or an adjustment of priorities per network slice or between network slices.

[0049] If "beamManagement" is set in targetFeature IE404, this indicates that the application of UE-based AI / ML to the beam management function by UE1, for example, is permitted. The application of UE-based AI / ML to the beam management function may mean adjustments related to the beam selection of UE1, adjustments related to beam failure detection (BFD), or adjustments related to beam failure recovery (BFR). The adjustments related to beam selection may be adjustments of an offset value or a threshold value of radio quality (e.g., RSRP, Reference Signal Received Quality (RSRQ), Received Signal Strength Indicator (RSSI)), or adjustments of priorities per beam or between beams. The adjustments related to beam failure detection may be adjustments of the threshold value for determining BFD. The adjustments related to beam failure recovery may be adjustments of the beam selection criteria for BFR (e.g., a threshold value or the type of reference signal (RS) (e.g., SSB or CSI-RS)).

[0050] If "energySaving" is set in targetFeature IE404, this indicates that, for example, UE1 is permitted to apply UE-based AI / ML to functions related to power consumption reduction. The application of UE-based AI / ML to functions related to power consumption reduction may be to adjust the timing (e.g., period, target frequency) of measurements of either or both of the serving cell and the neighbour cell so as to lead to (or be expected to lead to) a reduction in power consumption. The said measurement may be either or both of Radio Link Monitoring (RLM) measurements and Radio Resource Management (RRM) measurements.

[0051] If "rrmMeasurement" is set in targetFeature IE404, this indicates that, for example, UE1 is permitted to apply UE-based AI / ML to the RRM measurement function. The application of UE-based AI / ML to the RRM measurement function may be the adjustment of the measurement timing for the aforementioned power consumption reduction. Further or alternatively, this may be the adjustment of the criteria in the frequency of RRM measurements or the relaxation of the assumed target (i.e., RRM relaxation). For example, the threshold for the determination of not-at-cell edge or low-mobility may be adjusted. For example, if UE1 determines itself to be not-at-cell edge or low-mobility, UE1 may be permitted to make the period of RRM measurement longer than normal or reduce the target frequency.

[0052] If "csiFeedback" is set in targetFeature IE404, this indicates, for example, that UE1 is permitted to apply UE-based AI / ML to the CSI feedback function. The application of UE-based AI / ML to the CSI feedback function may be an adjustment of the timing (e.g., period) of CSI reporting to RAN node 2. Additionally or alternatively, the application of UE-based AI / ML to the CSI feedback function may be to reduce or compress the amount of information in the CSI report (e.g., beam information, channel matrix, precoding matrix).

[0053] If "positioningAccuracy" is set in targetFeature IE404, this indicates, for example, that UE1 is permitted to apply UE-based AI / ML to a function related to improving positioning accuracy. The application of UE-based AI / ML to a function related to improving positioning accuracy may mean correcting the information used for position estimation or correcting the position estimation result.

[0054] The targetArea IE405 may indicate one or more areas where the application of UE-based AI / ML is permitted (i.e., functional areas that are permitted targets). The areas may include, for example, one or more of "intraFreq", "interFreq", "intraAndInterFreq", "interRAT", and "any". "intraFreq" means cell reselection or handover within the same frequency band. "interFreq" means cell reselection or handover between different frequency bands. "intraAndInterFreq" means cell reselection or handover within the same frequency band and between different frequency bands. "interRAT" means cell selection or handover between different radio access technologies. "any" means there are no restrictions on the area. Alternatively, it may mean that there are no restrictions on the area if the targetArea IE405 is not included in the AI-ML-Config IE403. Note that the targetArea is defined as targetFunc (targetFunction), targetScope, or applicableTarget, which may each indicate one or more target functions (target functions), one or more scopes (target scopes), or one or more application targets (applicable targets) where the application of UE-based AI / ML is permitted.

[0055] Condition IE406 may indicate a situation where the application of UE-based AI / ML is permitted. For example, the situation may include one or more of "consistentFailure", "predictable", "lowBattery", "gnssAvailable", and "nlos". "ConsistentFailure" means a situation where a given failure has been repeatedly detected in the same or similar situations. "Predictable" means a situation that can be predicted based on history. "LowBattery" means a situation where the remaining power of the battery of UE1 is low. "GnssAvailable" means a situation where it is possible to obtain position information by the Global Navigation Satellite System (GNSS). GNSS may be, for example, any one of the Global Positioning System (GPS), Galileo, and the Global Navigation Satellite System (GLONASS). "Nlos" means that the radio wave environment (or communication environment) of UE1 is a non-line-of-sight (NLOS) environment.

[0056] Figure 4B shows another example of the format of the control information (steps 201, 301). The Ai-configuration Information Element (IE) 421 shown in Figure 4B may be transmitted from the RAN node 2 to UE1 in the SIB or an individual RRC message. The Ai-configuration IE421 can include an AI-ML-ConfigList IE422. The AI-ML-ConfigList IE422 can include one or more AI-ML-Config IEs423. Each AI-ML-Config IE423 can include one or any combination of a mobility IE424, an energySaving IE425, and a positioningAccuracy IE426.

[0057] The mobility IE424 specifies the target function (targetFuncMob IE) and target scope (targetScopeMob IE) related to mobility. The target function may indicate one or more categories (or groups) of actions for which UE-based AI / ML application is permitted. The categories of actions may include, for example, one or more of "mobilityConnected", "mobilityIdleInactive", "beamManagement", and "rrmMeasurement". The target scope may indicate one or more scopes for which UE-based AI / ML application is permitted. The target scope may include, for example, one or more of "intraFreq", "interFreq", "intraAndInterFreq", "interRAT", and "any".

[0058] The energySaving IE425 specifies the target function (targetFuncES IE) and target scope (targetScopeES IE) related to power consumption reduction. The target function may indicate one or more categories (or groups) of actions for which UE-based AI / ML application is permitted. The categories of actions may include, for example, one or more of "rrmMeasurement" and "csiFeedback". The target scope may indicate one or more scopes for which UE-based AI / ML application is permitted. The target scope may include, for example, one or more of "intraFreq", "interFreq", "intraAndInterFreq", "interRAT", "any", "pCell", "sCell", "servCell". "pCell" means the primary cell of carrier aggregation or the MCG or SCG primary cell of DC. "sCell" means the secondary cell of DC or carrier aggregation. "servCell" means the serving cell of UE1.

[0059] The positioningAccuracy IE426 specifies the target function (targetFuncPosi IE) and target scope (targetScopePosi IE) related to positioning accuracy. The target function may indicate one or more categories (or groups) of actions for which the application of UE-based AI / ML is permitted. The categories of actions may include, for example, one or more of "nlosMitigation", "multipathMitigation", "propagationDelayCompensation". "nlosMitigation" means correcting the positioning result (or UL transmission timing) when UE1 is in an NLOS environment. "multipathMitigation" means correcting the positioning result (or UL transmission timing) when UE1 is in a multipath environment. "propagationDelayCompensation" means compensating for the impact of propagation delay (e.g., UL transmission timing). The target scope may indicate one or more scopes for which the application of UE-based AI / ML is permitted. The target scope may include, for example, one or more of "positioning" and "timingAdvance". "positioning" means obtaining position information by the positioning function. "timingAdvance" means calculating the adjustment value (Timing Advance (TA)) of the transmission timing applied by UE1 during uplink transmission. The calculation result of TA by UE1 may be reflected, for example, in the UL transmission timing of UE1 in a Non-Terrestrial Network (NTN), or the calculation result of the TA may be reported from UE1 to RAN node 2.

[0060] According to the operations of UE1 and RAN Node 2 described with reference to FIGS. 2 to 4B, RAN Node 2 can control whether UE1 is permitted to perform an action based on a prediction or determination by UE-based AI / ML. For example, if an action of UE1 triggered by AI inference may result in an interaction with the network or affect the performance of the network, it may not be appropriate for UE1 to freely perform the action. Alternatively, it may not be appropriate for UE1 to freely perform an action triggered by AI inference instead of being triggered by a rule (or criterion or formula) defined in the 3GPP specification. The operations of UE1 and RAN Node 2 described with reference to FIGS. 2 to 4B can contribute to the solution of these problems.

[0061] <Second Embodiment> A configuration example of the wireless communication system according to this embodiment may be the same as the example shown in FIG. 1. FIG. 5 shows an example of the operations of UE1 and RAN Node 2 for UE-based AI / ML, that is, for UE1 to perform AI inference with a machine learning model. In step 501, UE1 transmits an AI interest indication to RAN Node 2. In one example, UE1 may transmit the AI interest indication in the procedure of setting up, resuming, or re-establishing an RRC connection. RAN Node 2 may also request UE1 to transmit the AI interest indication.

[0062] The AI interest indication may indicate to RAN Node 2 that UE1 supports machine learning-based artificial intelligence. The AI interest indication may indicate to RAN Node 2 that UE1 is interested in the execution of UE-based AI / ML. The AI interest indication may indicate to RAN Node 2 that UE1 requests permission for the execution of UE-based AI / ML. The AI interest indication may be included in the UE Capability Information.

[0063] Additionally or alternatively, the AI interest indication may indicate to the RAN node 2 that the UE1 desires to perform a specific action based on the inference result of the machine learning-based artificial intelligence. In other words, the AI interest indication may indicate to the RAN node 2 that the execution of UE-based AI / ML by the UE1 is expected to be beneficial for performance improvement.

[0064] The AI interest indication may indicate the category of AI / ML estimations that the UE1 wishes to execute. In other words, the AI interest indication may indicate the action or category of actions that the UE1 wishes to perform for which the application of UE-based AI / ML is permitted. The AI interest indication may indicate the function or feature (e.g., mobility, power saving) for which the application of UE-based AI / ML is permitted and that the UE1 desires. The AI interest indication may indicate the sub-function or sub-feature (e.g., cell selection, handover, beam management) for which the application of UE-based AI / ML is permitted and that the UE1 desires. The AI interest indication may indicate the procedure (e.g., RRC re-establishment, beam failure recovery (BFR)) for which the application of UE-based AI / ML is permitted and that the UE1 desires. The AI interest indication may indicate the RRC configuration (e.g., the level of information elements or fields in Abstract Syntax Notation One (ASN.1)) for which the application of UE-based AI / ML is permitted and that the UE1 desires.

[0065] The AI interest indication may indicate the magnitude or level of the effect expected by the execution of the AI / ML estimations by the UE1.

[0066] Step 502 is the same as step 201 in FIG. 2. RAN node 2 transmits control information to UE1. Since the details regarding the control information (e.g., transmission method, content) are the same as those described in the first embodiment, the description of the control information is omitted here. RAN node 2 may determine whether to transmit the control information (502) based on the AI interest indication (501). RAN node 2 may determine the content of the control information (502) based on the AI interest indication (501).

[0067] FIG. 6 shows an example of the format of the AI interest indication. The ai-ML-Assistance IE602 shown in FIG. 6 corresponds to the AI interest indication. The ai-ML-Assistance IE602 may be included in the UEAssistanceInformation IE601. The UEAssistanceInformation IE601 may be transmitted to RAN node 2 via an RRC message (e.g., RRC Setup Request, RRC Setup Complete, RRC Resume Request, RRC Resume Complete, RRC Re-establishment Request, RRC Re-establishment Complete). The ai-ML-Assistance IE602 may include the ai-ML-InterestIndication IE603 or 604.

[0068] The ai-ML-InterestIndication IE603 indicates, for example, that UE1 is interested in the execution of UE-based AI / ML. If UE1 desires permission for the execution of UE-based AI / ML, UE1 may include the ai-ML-InterestIndication IE603 in the UEAssistanceInformation IE601.

[0069] On one hand, the ai-ML-InterestIndication IE604 indicates the category of AI / ML estimations that UE1 wants to execute. In other words, the ai-ML-InterestIndication IE604 indicates the action or category of actions that UE1 hopes to be permitted to apply UE-based AI / ML. The category includes, for example, one or more of "mobilityConnected", "mobilityIdleInactive", "beamManagement", "energySaving", "rrmMeasurement", "csiFeedback", and "positioningAccuracy". What each of these means (indicates) may be as described above.

[0070] Figure 7 is a flowchart showing an example of the operation of RAN Node 2. In step 701, RAN Node 2 receives an AI interest indication from UE1. In step 702, RAN Node 2 determines whether UE1 is permitted to perform a specific action based on the inference result of machine learning-based artificial intelligence. In step 703, RAN Node 2 transmits control information to UE1. The control information in step 703 indicates whether UE1 is permitted to perform a specific action based on the inference result of machine learning-based artificial intelligence. Since the details regarding the control information (e.g., transmission method, content) are the same as those described in the first embodiment, the description of the control information is omitted here.

[0071] According to the operations of UE1 and RAN Node 2 described with reference to FIGS. 5 to 7, before transmitting control information (steps 502, 703) for permitting the execution of UE-based AI / ML, RAN Node 2 can receive an AI interest indication (steps 501, 701) from UE1. Thus, for example, based on the AI interest indication received from UE1, RAN Node 2 can determine whether to permit UE1 to execute UE-based AI / ML. Alternatively, based on the AI interest indication received from UE1, RAN Node 2 can determine one or more actions (or categories of actions) for which the application of UE-based AI / ML by UE1 is permitted.

[0072] Subsequently, hereinafter, a configuration example of UE1 and RAN Node 2 according to the above-described multiple embodiments will be described. FIG. 8 is a block diagram showing a configuration example of UE1. A Radio Frequency (RF) transceiver 801 performs analog RF signal processing for communicating with a RAN node. The RF transceiver 801 may include a plurality of transceivers. The analog RF signal processing performed by the RF transceiver 801 includes frequency up-conversion, frequency down-conversion, and amplification. The RF transceiver 801 is coupled to an antenna array 802 and a baseband processor 803. The RF transceiver 801 receives modulation symbol data (or OFDM symbol data) from the baseband processor 803, generates a transmission RF signal, and supplies the transmission RF signal to the antenna array 802. Also, the RF transceiver 801 generates a baseband reception signal based on the reception RF signal received by the antenna array 802 and supplies this to the baseband processor 803. The RF transceiver 801 may include an analog beamformer circuit for beamforming. The analog beamformer circuit includes, for example, a plurality of phase shifters and a plurality of power amplifiers.

[0073] The baseband processor 803 performs digital baseband signal processing (data plane processing) and control plane processing for wireless communication. The digital baseband signal processing includes (a) data compression / decompression, (b) data segmentation / concatenation, (c) generation / decomposition of a transmission format (transmission frame), (d) channel encoding / decoding, (e) modulation (symbol mapping) / demodulation, and (f) generation of OFDM symbol data (baseband OFDM signal) by Inverse Fast Fourier Transform (IFFT), etc. On the other hand, the control plane processing includes communication management of layer 1 (e.g., transmission power control), layer 2 (e.g., radio resource management, and hybrid automatic repeat request (HARQ) processing), and layer 3 (e.g., signaling related to attachment, mobility, and call management).

[0074] For example, the digital baseband signal processing by the baseband processor 803 may include signal processing of the Service Data Adaptation Protocol (SDAP) layer, Packet Data Convergence Protocol (PDCP) layer, Radio Link Control (RLC) layer, Medium Access Control (MAC) layer, and Physical (PHY) layer. Also, the control plane processing by the baseband processor 803 may include processing of the Non-Access Stratum (NAS) protocol, Radio Resource Control (RRC) protocol, MAC Control Elements (CEs), and Downlink Control Information (DCIs).

[0075] The baseband processor 803 may perform Multiple Input Multiple Output (MIMO) encoding and precoding for beamforming.

[0076] The baseband processor 803 may include a modem processor (e.g., Digital Signal Processor (DSP)) that performs digital baseband signal processing and a protocol stack processor (e.g., Central Processing Unit (CPU) or Micro Processing Unit (MPU)) that performs control plane processing. In this case, the protocol stack processor that performs control plane processing may be shared with the application processor 804 described later.

[0077] The application processor 804 is also referred to as a CPU, MPU, microprocessor, or processor core. The application processor 804 may include a plurality of processors (a plurality of processor cores). The application processor 804 realizes various functions of the UE1 by executing a system software program (Operating System (OS)) and various application programs (for example, a call application, a WEB browser, a mailer, a camera operation application, a music playback application) read from the memory 806 or a memory not shown.

[0078] In some implementations, as shown by the dashed line (805) in FIG. 8, the baseband processor 803 and the application processor 804 may be integrated on one chip. In other words, the baseband processor 803 and the application processor 804 may be implemented as one System on Chip (SoC) device 805. The SoC device may also be referred to as a system Large Scale Integration (LSI) or a chipset.

[0079] The memory 806 is a volatile memory, a non-volatile memory, or a combination thereof. The memory 806 may physically include a plurality of independent memory devices. The volatile memory is, for example, Static Random Access Memory (SRAM), Dynamic RAM (DRAM), or a combination thereof. The non-volatile memory is a Mask Read Only Memory (MROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, or a hard disk drive, or any combination thereof. For example, the memory 806 may include an external memory device accessible from the baseband processor 803, the application processor 804, and the SoC 805. The memory 806 may include an embedded memory device integrated within the baseband processor 803, within the application processor 804, or within the SoC 805. Further, the memory 806 may include the memory within a Universal Integrated Circuit Card (UICC).

[0080] The memory 806 may store one or more software modules (computer programs) 807 including instruction groups and data for performing the processing by the UE1 described in the above-described embodiments. In some implementations, the baseband processor 803 or the application processor 804 may be configured to perform the processing of the UE1 described with reference to the drawings in the above-described embodiments by reading and executing the software module 807 from the memory 806.

[0081] Note that the control plane processing and operations performed by the UE1 described in the above-described embodiments can be realized by other elements excluding the RF transceiver 801 and the antenna array 802, that is, at least one of the baseband processor 803 and the application processor 804 and the memory 806 storing the software module 807.

[0082] FIG. 9 is a block diagram showing a configuration example of the RAN node 2 according to the above-described embodiment. Referring to FIG. 9, the RAN node 2 includes a Radio Frequency transceiver 901, a network interface 903, a processor 904, and a memory 905. The RF transceiver 901 performs analog RF signal processing to communicate with UEs including the UE1. The RF transceiver 901 may include a plurality of transceivers. The RF transceiver 901 is coupled to the antenna array 902 and the processor 904. The RF transceiver 901 receives modulation symbol data from the processor 904, generates a transmission RF signal, and supplies the transmission RF signal to the antenna array 902. Also, the RF transceiver 901 generates a baseband reception signal based on the reception RF signal received by the antenna array 902 and supplies this to the processor 904. The RF transceiver 901 may include an analog beamformer circuit for beamforming. The analog beamformer circuit includes, for example, a plurality of phase shifters and a plurality of power amplifiers.

[0083] The network interface 903 is used to communicate with network nodes (e.g., other RAN nodes, as well as control nodes and transfer nodes of the core network). The network interface 903 may include, for example, a network interface card (NIC) compliant with the IEEE 802.3 series.

[0084] Processor 904 performs digital baseband signal processing (data plane processing) and control plane processing for wireless communication. Processor 904 may include a plurality of processors. For example, Processor 904 may include a modem processor (e.g., Digital Signal Processor (DSP)) that performs digital baseband signal processing and a protocol stack processor (e.g., Central Processing Unit (CPU) or Micro Processing Unit (MPU)) that performs control plane processing. Processor 904 may include a digital beamformer module for beamforming. The digital beamformer module may include a Multiple Input Multiple Output (MIMO) encoder and a precoder.

[0085] Memory 905 is composed of a combination of volatile memory and non-volatile memory. The volatile memory is, for example, Static Random Access Memory (SRAM) or Dynamic RAM (DRAM) or a combination thereof. The non-volatile memory is Mask Read Only Memory (MROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, or a hard disk drive, or any combination thereof. Memory 905 may include storage located remotely from Processor 904. In this case, Processor 904 may access Memory 905 via Network Interface 903 or an I / O interface not shown.

[0086] Memory 905 may store one or more software modules (computer programs) 906 containing instruction groups and data for the processing by RAN node 2 described in the above-described multiple embodiments. In some implementations, processor 904 may be configured to perform the processing of RAN node 2 described in the above embodiments by reading and executing the software module 906 from memory 905.

[0087] Note that when RAN node 2 is a CU (e.g., gNB-CU) or a CU-CP (e.g., gNB-CU-CP), RAN node 2 may not include RF transceiver 901 (and antenna array 902).

[0088] As described with reference to FIGS. 8 and 9, each of the processors of UE1 and RAN node 2 according to the above embodiments can execute one or more programs including instruction groups for causing a computer to perform the algorithms described with reference to the drawings. The program includes instruction groups (or software code) for causing the computer to perform one or more functions described in the embodiments when loaded into the computer. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD), or other memory technologies, CD-ROM, digital versatile disk (DVD), Blu-ray (registered trademark) disk, or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage, or other magnetic storage devices. The program may be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0089] <Other Embodiments> The above-described embodiments may be applied to a Non-Terrestrial Network (NTN). The above-described embodiments may also be applied to various new applications such as vehicle-to-everything (V2X), high-speed trains (HSTs), unmanned aerial vehicles (UAVs), uncrewed aerial vehicles (UAVs), and urban air mobility (UAM).

[0090] The above-described embodiments may be applied in a secondary cell group (SCG) in Dual Connectivity (e.g., MR-DC). In this case, RAN Node 2 may be a secondary node (SN). In this case, the SN may directly transmit and receive RRC messages with UE1 using signaling radio bearer (SRB3) in the SCG, or may do so via the master node (MN). Further or alternatively, RAN Node 2 may be a master node (MN) and may play a role in forwarding RRC messages between the SN and UE1.

[0091] RAN Node 2 in the above-described embodiments may be implemented in a C-RAN configuration. For example, RAN Node 2 may include a CU (e.g., gNB-CU) and a DU (e.g., gNB-DU). The CU may determine whether to permit UE1 to perform a specific action based on the inference result of machine learning-based artificial intelligence, and may transmit control information indicating the result of the determination to UE1 (via the DU). Further or alternatively, the DU may determine whether to permit a wireless terminal to perform a specific action based on the inference result of machine learning-based artificial intelligence, transmit control information indicating the result of the determination to the CU, and the CU may transmit it to UE1. Note that depending on the object permitted to UE1, or its type and content, the control by the above-described CU and DU may be selected or combined.

[0092] Furthermore, the above-described embodiments are merely examples regarding the application of the technical idea obtained by the present inventor. That is, the technical idea is not limited to only the above-described embodiments, and it goes without saying that various modifications are possible.

[0093] For example, some or all of the above-described embodiments may be described as follows, but are not limited thereto.

[0094] (Appendix 1) A wireless terminal, comprising at least one memory, and at least one processor coupled to the at least one memory, wherein the at least one processor receives control information from a network indicating whether the wireless terminal is permitted to perform a specific action based on an inference result of a machine learning-based artificial intelligence, makes a prediction or determination using a trained machine learning model, and performs the specific action triggered by the prediction or determination if the control information permits the execution of the specific action based on the inference result. A wireless terminal configured as such. (Appendix 2) The control information indicates whether the execution of the specific action based on the inference result is permitted, instead of or in addition to performing the specific action based on a predefined rule. The wireless terminal according to Appendix 1. (Appendix 3) The predefined rule is a rule predefined in the Third Generation Partnership Project (3GPP) specification or a rule preset by a network. The wireless terminal according to Appendix 2. (Appendix 4) The control information individually indicates whether each of a plurality of actions including the specific action is permitted. The wireless terminal according to any one of Appendices 1 to 3. (Appendix 5) The control information collectively indicates permission to use the machine learning-based artificial intelligence for a plurality of actions including the specific action. The wireless terminal according to any one of Appendices 1 to 3. (Appendix 6) The control information indicates conditions under which execution of a specific action based on the inference result is permitted. The at least one processor is configured to perform the specific action triggered by the prediction or determination only when the conditions are satisfied. The wireless terminal according to any one of Appendices 1 to 5. (Appendix 7) The conditions indicate constraints regarding at least one of a frequency band, a location, and a time. The wireless terminal according to Appendix 6. (Appendix 8) The control information is transmitted by the network when execution of the specific action based on the inference result is permitted. The wireless terminal according to any one of Appendices 1 to 7. (Appendix 9) The at least one processor is configured to notify the network that the wireless terminal supports a machine learning-based artificial intelligence before receiving the control information. The wireless terminal according to any one of Appendices 1 to 8. (Appendix 10) The at least one processor is configured to notify the network that the wireless terminal desires to execute the specific action based on the inference result of the machine learning-based artificial intelligence before receiving the control information. The wireless terminal according to any one of Appendices 1 to 9. (Appendix 11) The specific action relates to beam management or mobility. The wireless terminal according to any one of Appendices 1 to 10. (Appendix 12) The specific action includes at least one of cell reselection, transmission of a measurement report, execution of conditional mobility, and selection of a downlink beam. The wireless terminal according to any one of Appendices 1 to 11. (Appendix 13) The specific action includes transmitting, to the network, assistance information indicating a result of a prediction or determination using the trained machine learning model. The wireless terminal according to any one of Appendices 1 to 12. (Appendix 14) The assistance information is used for training a second machine learning model related to optimization of a radio access network or performing inference in a second trained machine learning model related to optimization of the radio access network. The wireless terminal according to Appendix 13. (Appendix 15) A method performed by a wireless terminal, receiving, from a network, control information indicating whether the wireless terminal is permitted to perform a specific action based on an inference result of a machine learning-based artificial intelligence, performing a prediction or a determination using a trained machine learning model, and performing the specific action triggered by the prediction or the determination if the control information permits execution of the specific action based on the inference result. A method comprising the above steps. (Appendix 16) A program for causing a computer to perform a method for a wireless terminal, wherein the method comprises: receiving, from a network, control information indicating whether the wireless terminal is permitted to perform a specific action based on an inference result of a machine learning-based artificial intelligence, performing a prediction or a determination using a trained machine learning model, and performing the specific action triggered by the prediction or the determination if the control information permits execution of the specific action based on the inference result. A program comprising the above steps. (Appendix 17) At least one memory, At least one processor coupled to the at least one memory and configured to send to the wireless terminal control information indicating whether the wireless terminal is permitted to perform a specific action based on an inference result of a machine learning-based artificial intelligence, comprising, if the control information permits the execution of the specific action based on the inference result, the control information causes the wireless terminal to perform the specific action triggered by a prediction or decision using a trained machine learning model, A wireless access network node. (Appendix 18) The control information indicates whether the execution of the specific action based on the inference result is permitted, instead of or in addition to performing the specific action based on a predefined rule, The wireless access network node according to Appendix 17. (Appendix 19) The predefined rule is a rule predefined in a Third Generation Partnership Project (3GPP) specification or a rule preset by the network, The wireless access network node according to Appendix 18. (Appendix 20) The control information individually indicates whether each of a plurality of actions including the specific action is permitted, The wireless access network node according to any one of Appendices 17 to 19. (Appendix 21) The control information collectively indicates permission to use the machine learning-based artificial intelligence for a plurality of actions including the specific action, The wireless access network node according to any one of Appendices 17 to 19. (Appendix 22) The control information indicates the conditions under which the execution of a specific action based on the inference result is permitted, The control information causes the wireless terminal to perform the specific action triggered by the prediction or determination only when the condition is satisfied. The wireless access network node according to any one of Appendices 17 to 21. (Appendix 23) The condition indicates a constraint related to at least one of a frequency band, a location, and a time. The wireless access network node according to Appendix 22. (Appendix 24) The at least one processor is configured to transmit the control information when execution of the specific action based on the inference result is permitted. The wireless access network node according to any one of Appendices 17 to 23. (Appendix 25) The at least one processor is configured to be notified from the wireless terminal before transmitting the control information that the wireless terminal supports a machine learning-based artificial intelligence. The wireless access network node according to any one of Appendices 17 to 24. (Appendix 26) The at least one processor is configured to be notified from the wireless terminal before transmitting the control information that the wireless terminal desires to execute the specific action based on the inference result of the machine learning-based artificial intelligence. The wireless access network node according to any one of Appendices 17 to 25. (Appendix 27) The specific action relates to beam management or mobility. The wireless access network node according to any one of Appendices 17 to 26. (Appendix 28) The specific action includes at least one of cell reselection, transmission of a measurement report, execution of conditional mobility, and selection of a downlink beam. The wireless access network node according to any one of Appendices 17 to 27. (Appendix 29) The specific action includes transmitting, to the radio access network node, assistance information indicating a result of prediction or determination using the trained machine learning model. The radio access network node according to any one of Appendices 17 to 28. (Appendix 30) The assistance information is used for training a second machine learning model related to optimization of the radio access network or performing inference in the second trained machine learning model related to optimization of the radio access network. The radio access network node according to Appendix 29. (Appendix 31) Comprising transmitting, to the wireless terminal, control information indicating whether the wireless terminal is permitted to perform a specific action based on an inference result of a machine learning-based artificial intelligence. If the control information permits execution of the specific action based on the inference result, the control information causes the wireless terminal to perform the specific action triggered by a prediction or determination using a trained machine learning model. A method performed by a radio access network node. (Appendix 32) A program for causing a computer to perform a method for a radio access network node, The method comprising transmitting, to the wireless terminal, control information indicating whether the wireless terminal is permitted to perform a specific action based on an inference result of a machine learning-based artificial intelligence. If the control information permits execution of the specific action based on the inference result, the control information causes the wireless terminal to perform the specific action triggered by a prediction or determination using a trained machine learning model. Program.

[0095] This application claims priority based on Japanese Patent Application No. 2021-182104 filed on November 8, 2021, and incorporates the entire disclosure thereof herein.

Description of Symbols

[0096] 1 UE 2 RAN Node 803 Baseband Processor 804 Application Processor 806 Memory 807 Modules 904 Processor 905 Memory 906 Modules

Claims

1. A wireless terminal, comprising: means for receiving from a network control information indicating whether the wireless terminal is permitted to perform a specific action based on an inference result of a machine learning-based artificial intelligence; means for performing an inference using a trained machine learning model; means for performing the specific action triggered by the inference if the control information permits execution of the specific action based on the inference result; wherein the specific action includes execution of at least one function of beam management, mobility, or Radio Resource Management (RRM) measurement. A wireless terminal.

2. The control information indicates whether execution of the specific action based on the inference result is permitted, instead of or in addition to performing the specific action based on rules predefined in a Third Generation Partnership Project (3GPP) specification or preset by the network. The wireless terminal according to claim 1.

3. The control information indicates conditions under which execution of a specific action based on the inference result is permitted, and the means for performing the specific action is configured to perform the specific action triggered by the inference only when the conditions are met. The wireless terminal according to claim 1 or 2.

4. The conditions indicate constraints regarding at least one of a frequency band, a location, and a time. The wireless terminal according to claim 3.

5. The wireless terminal further comprises means for notifying the network that the wireless terminal supports a machine learning-based artificial intelligence before receiving the control information. The wireless terminal according to claim 1 or 2.

6. The wireless terminal further comprises means for notifying the network that the wireless terminal desires to execute the specific action based on an inference result of a machine learning-based artificial intelligence before receiving the control information. The wireless terminal according to claim 1 or 2.

7. The specific action includes at least one of cell reselection, transmission of a measurement report for mobility in the wireless terminal, execution of conditional mobility, relaxation of RRM measurement, and selection of a downlink beam. The wireless terminal according to claim 1 or 2.

8. A method performed by a wireless terminal, comprising: Receiving, from a network, control information indicating whether the wireless terminal is permitted to perform a specific action based on an inference result of a machine learning-based artificial intelligence; Performing an inference using a trained machine learning model; and Performing the specific action triggered by the inference if the control information permits execution of the specific action based on the inference result, comprising: The specific action includes execution of at least one function of beam management, mobility, or Radio Resource Management (RRM) measurement, A method.

9. A means for transmitting, to the wireless terminal, control information indicating whether the wireless terminal is permitted to perform a specific action based on an inference result of a machine learning-based artificial intelligence; If the control information permits execution of the specific action based on the inference result, the control information causes the wireless terminal to perform the specific action triggered by an inference using a trained machine learning model, The specific action includes execution of at least one function of beam management, mobility, or Radio Resource Management (RRM) measurement, A radio access network node.

Images