Wireless terminal, wireless access network node, information processing system, and methods thereof

Abstract

This wireless terminal receives a reporting configuration of assistance information from a network and transmits the assistance information to the network. The assistance information includes at least one of first information and second information. The first information includes one or more parameters, each of which indicates a correlation or a similarity between a first channel that is estimated on the basis of reception of a first signal beam by the wireless terminal and each of one or more second channels estimated on the basis of reception of one or more second signal beams by the wireless terminal. The second information includes at least one identifier of at least one second signal beam with a corresponding parameter exceeding a threshold that is determined on the basis of the reporting configuration. This contributes to, for example, providing non-proprietary information that is useful for AI / ML-based downlink beam prediction.

Description

Wireless terminal, radio access network node, information processing system, and methods thereof

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

[0002] The 3rd Generation Partnership Project (3GPP®) is discussing the application or introduction of AI or machine learning (ML) to 5G. In particular, network-based AI / ML with User Equipment (UE) involvement and UE-based AI / ML are being considered for 3GPP Release 18 and beyond (see, for example, Non-Patent Documents 1-7).

[0003] AI / ML can be considered for both network internal functions and the air interface (i.e., Uu). Potential use cases of AI / ML for the air interface include Channel State Information (CSI) feedback compression, beam management (BM), and positioning accuracy enhancements (see, for example, Non-Patent Document 1).

[0004] Network-based AI / ML is also referred to as a network-side AI / ML model or network-side model. In network-based AI / ML, the network performs AI / ML inference. AI / ML inference refers to predictions or decisions using or based on a trained AI / ML model. The AI / ML inference function may be located in the Next Generation Radio Access Network (NG-RAN) (e.g., gNB). Alternatively, the AI / ML inference function may be located in a Near-Real-Time (Near-RT) RAN Intelligent Controller (RIC) coupled to the gNB. Training of the AI / ML model may be performed in the NG-RAN. Alternatively, an Operation, Administration, and Maintenance (OAM) server or a non-RT RIC may train the AI / ML model and provide the trained AI / ML model (e.g., trained parameters or an AI / ML application including the trained parameters) to the NG-RAN (e.g., gNB) or Near-RT RIC.

[0005] UE-based AI / ML is also referred to as a UE-side AI / ML model or UE-side model. In UE-based AI / ML, the UE performs AI / ML inference. In UE-based AI / ML, the UE runs an AI model (i.e., a trained machine learning model) and obtains the AI ​​inference results locally. For example, the UE can predict future events or measurements based on past measurements. The UE can feed back the predicted results (e.g., mobility or beam predictions) to the network (e.g., gNB). Training of the AI / ML model for UE-based AI / ML may be performed by the UE or by the network (e.g., gNB, Near-RT RIC, Non-RT RIC, or other OAM server or controller).

[0006] One sub-use case for AI / ML BM involves downlink (DL) beam prediction in both UE-side and network-side models (see, for example, Non-Patent Documents 1-7). DL beam prediction includes spatial-domain beam prediction and temporal beam prediction. Temporal beam prediction may also be referred to as time-domain beam prediction. DL beam prediction includes prediction of DL transmission (Tx) beam, prediction of DL reception (Rx) beam, and prediction of beam pairs of DL Tx beam and DL Rx beam.

[0007] Spatial-domain DL beam prediction is a spatial-domain DL beam prediction of Set A of beams based on measurements of Set B of beams. Spatial-domain DL beam prediction is conveniently called BM-Case 1. Beam Set B is the set of beams whose measurements are taken as inputs to an AI / ML model. In spatial-domain DL beam prediction (i.e., BM-Case 1), Set A is different from Set B (i.e., Set B is not a subset of Set A), or Set B is considered to be a subset of Set A. There are four possible inputs to the AI / ML model for spatial domain DL beam prediction: Layer 1 (L1) Reference Signal Received Power (RSRP) measurements only based on set B; L1-RSRP measurements and assistance information based on set B; Channel Impulse Response (CIR) based on set B; L1-RSRP measurements based on set B and either or both of the corresponding DL Tx beam ID and Rx beam ID.

[0008] Temporal DL beam prediction is a temporal DL beam prediction of Set A of beams based on the historical measurement results of Set B of beams. Temporal DL beam prediction is conveniently called BM-Case 2. Beam Set B is the set of beams whose measurements are taken as inputs to the AI / ML model. In temporal DL beam prediction (i.e., BM-Case 2), Set A is considered to be different from Set B (i.e., Set B is not a subset of Set A), Set B is a subset of Set A (i.e., Set B is not identical to Set A), or Set A and Set B are considered to be the same. The input to the AI / ML model for temporal DL beam prediction is considered to be the measurement results of the K (K≧1) most recent measurement instances, with the following options: - Layer 1 (L1) Reference Signal Received Power (RSRP) measurements only based on set B; - L1-RSRP measurements based on set B and assistance information; - L1-RSRP measurements based on set B and one or both of the corresponding DL Tx beam ID and Rx beam ID.

[0009] As discussed in Non-Patent Documents 3-7, to improve the performance of AI / ML-based spatial-domain and temporal DL beam prediction, additional assistance information can be used as AI / ML input in addition to L1-RSRP measurements based on beam set B. Examples of assistance information include Tx and / or Rx beam shape information (e.g., Tx and / or Rx beam pattern, boresight direction (azimuth and elevation) of Tx and / or Rx beam, 3 dB beam width, etc.), expected Tx and / or Rx beam for the prediction (e.g., expected Tx and / or Rx angle for prediction, Tx and / or Rx beam ID for prediction), UE location information, UE direction information, Tx beam usage information, and UE orientation information.

[0010] However, as described in Non-Patent Documents 1 and 3-7, providing assistance information raises concerns about disclosing proprietary information. Detailed information such as Tx and / or Rx beam shape information is often protected by companies and may not be fully disclosed to the public. Therefore, providing assistance information such as Tx and / or Rx beam shape information may be infeasible due to concerns about disclosing proprietary information to the other side.

[0011] 3GPP TR 38.843 V18.0.0 (2023-12)Qualcomm, "New WID on Artificial Intelligence (AI) / Machine Learning (ML) for NR Air Interface", RP-234039, 3GPP TSG RAN Meeting #102, Edinburgh, Scotland, December 11-15, 2023Huawei, HiSilicon, "Discussion on AI / ML for beam management", R1-2208432, 3GPP TSG-RAN WG1 Meeting #110bis-e, e-Meeting, October 10-19, 2022NVIDIA, "AI and ML for beam management", R1-2306478, 3GPP TSG-RAN WG1 Meeting #114, Toulouse, France, August 21-25, 2023InterDigital, Inc., "Discussion for other aspects on AI / ML for beam management". R1-2306690, 3GPP TSG-RAN WG1 Meeting #114, Toulouse, France, August 21-25, 2023vivo, "Other aspects on AI / ML for beam management", R1-2306743, 3GPP TSG-RAN WG1 Meeting #114, Toulouse, France, August 21-25, 2023ZTE Corporation, "Discussion on other aspects for AI beam management", R1-2306798, 3GPP TSG-RAN WG1 Meeting #114, Toulouse, France, August 21-25, 2023

[0012] The present inventors have investigated AI / ML-based DL beam prediction and found various challenges. One of these challenges relates to providing assistance information. As mentioned above, providing assistance information, such as Tx and / or Rx beam shape information, may raise the issue of disclosure of proprietary information. To address or mitigate this issue, it would be preferable to be able to provide non-proprietary information useful for AI / ML-based DL beam prediction.

[0013] One of the objectives to be achieved by the embodiments disclosed in this specification is to provide an apparatus, a method, and a program that contribute to solving at least one of multiple problems related to AI / ML-based DL beam prediction, including the above-mentioned problem. It should be noted that this objective is only one of multiple objectives to be achieved by the multiple embodiments disclosed in this specification. Other objectives or objectives and novel features will become apparent from the description of this specification or the accompanying drawings.

[0014] A first aspect is directed to a wireless terminal configured to receive an assistance information reporting configuration from a network and transmit the assistance information to the network. The assistance information includes at least one of first information and second information. The first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception of a first signal beam by the wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal. The second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting configuration.

[0015] A second aspect is directed to a method performed by a wireless terminal, the method including receiving an assistance information reporting configuration from a network and transmitting the assistance information to the network. The assistance information includes at least one of first information and second information. The first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception by the wireless terminal of a first signal beam and a respective one of one or more second channels estimated based on reception by the wireless terminal of one or more second signal beams. The second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting configuration.

[0016] A third aspect is directed to a radio access network node configured to transmit an assistance information reporting configuration to a wireless terminal and receive the assistance information from the wireless terminal, the assistance information including at least one of first information and second information, the first information including one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information including at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting configuration.

[0017] A fourth aspect is directed to a method performed by a radio access network node, the method including transmitting an assistance information reporting configuration to a wireless terminal and receiving the assistance information from the wireless terminal. The assistance information includes at least one of first information and second information. The first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception by the wireless terminal of a first signal beam and a respective one of one or more second channels estimated based on reception by the wireless terminal of one or more second signal beams. The second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting configuration.

[0018] A fifth aspect is directed to an information processing system. The information processing system is configured to obtain assistance information. The information processing system is configured to perform beam prediction for a first set of beams by inference using a trained artificial intelligence or machine learning model using measurement results of a second set of beams as input. The information processing system is further configured to select one or more beams from the first set based on the assistance information. The assistance information includes at least one of first information and second information. The first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception by a wireless terminal of a first signal beam and a respective one of one or more second channels estimated based on reception by the wireless terminal of one or more second signal beams. The second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold. The first signal beam and the one or more second signal beams are included in the second set.

[0019] A sixth aspect is directed to a method performed by an information processing system. The method includes the following steps: (a) obtaining assistance information; (b) performing beam prediction for a first set of beams by inference using a trained artificial intelligence or machine learning model using measurements of a second set of beams as input; and (c) selecting one or more beams from the first set based on the assistance information. The assistance information includes at least one of first information and second information. The first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception by a wireless terminal of a first signal beam and a respective one of one or more second channels estimated based on reception by the wireless terminal of one or more second signal beams. The second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold. The first signal beam and the one or more second signal beams are included in the second set.

[0020] A seventh aspect is directed to an information processing system. The information processing system is configured to acquire assistance information. The information processing system is further configured to train, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam prediction for a first set of beams based on measurement results for a second set of beams. The assistance information includes at least one of first information and second information. The first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal. The second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold. The first signal beam is included in the second set. The one or more second signal beams are included in the first set. The second set is a subset of the first set or is different from the first set.

[0021] An eighth aspect is directed to a method performed by an information processing system. The method includes the steps of: (a) acquiring assistance information; and (b) training, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam prediction for a first set of beams based on measurement results for a second set of beams. The assistance information includes at least one of first information and second information. The first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception by a wireless terminal of a first signal beam and a respective one of one or more second channels estimated based on reception by the wireless terminal of one or more second signal beams. The second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold. The first signal beam is included in the second set. The one or more second signal beams are included in the first set. The second set is a subset of the first set or is different from the first set.

[0022] A ninth aspect is directed to an information processing system. The information processing system is configured to acquire assistance information. The information processing system is further configured to train, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam prediction for a first set of beams based on measurement results for a second set of beams. The assistance information includes at least one of first information and second information. The first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal. The second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold. The first signal beam is included in the second set. The one or more second signal beams are included in the second set. Each of the one or more second signal beams is a beam that is transmitted at a different time instance than the first signal beam and with the same beamforming weights applied to the first signal beam.

[0023] A tenth aspect is directed to a method performed by an information processing system. The method includes the steps of: (a) acquiring assistance information; and (b) training, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam predictions for a first set of beams based on measurements of a second set of beams. The assistance information includes at least one of first information and second information. The first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal. The second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold. The first signal beam is included in the second set. The one or more second signal beams are included in the second set. Each of the one or more second signal beams is a beam that is transmitted at a different time instance than the first signal beam and with the same beamforming weights applied to the first signal beam.

[0024] An eleventh aspect is directed to a program, which includes a set of instructions (software code) that, when loaded into a computer, causes the computer to perform the method according to the second, fourth, sixth, eighth, or tenth aspect.

[0025] According to the above-described aspects, it is possible to provide an apparatus, a method, and a program that contribute to solving at least one of a number of problems related to AI / ML-based DL beam prediction, including the problems described above.

[0026]

[0014] Figure 1 illustrates an example configuration of a wireless communication system according to one or more embodiments.

[0015] Figure 2 illustrates an example configuration of a wireless communication system according to one or more embodiments.

[0016] Figure 3 illustrates an example of signaling between a UE and a radio access network node according to one or more embodiments.

[0017] Figure 4 illustrates an example of signaling between a UE and a radio access network node according to one or more embodiments.

[0018] Figure 5 illustrates an example of a format of a CSI-ReportConfig information element according to one or more embodiments.

[0019] Figure 6 illustrates an example of a CSI report according to one or more embodiments.

[0020] Figure 7 illustrates an example of a CSI report according to one or more embodiments.

[0021] Figure 8 illustrates an example of operation of an information processing system according to one or more embodiments.

[0022] Figure 9 illustrates a schematic diagram of example post-processing after DL beam prediction according to one or more embodiments.

[0023] Figure 10 illustrates an example of signaling between a UE and a network according to one or more embodiments.

[0024] Figure 11 illustrates an example of operation of an information processing system according to one or more embodiments.

[0025] Figure 12 illustrates an example of training an AI / ML model for DL ​​beam prediction according to one or more embodiments.

[0026] Figure 13 illustrates an example of signaling between a UE and a network according to one or more embodiments.

[0027] Figure 14 illustrates an example of operation of an information processing system according to one or more embodiments.

[0028] Figure 15 illustrates an example of signaling between a UE and a network according to one or more embodiments. FIG. 1 is a diagram illustrating an example format of a CSI-ReportConfig information element according to one or more embodiments. FIG. 2 is a diagram illustrating an example observation window and a prediction window according to one or more embodiments. FIG. 3 is a block diagram illustrating an example configuration of a UE according to one or more embodiments. FIG. 4 is a block diagram illustrating an example configuration of a radio access network node (e.g., CU, DU) according to one or more embodiments. FIG. 5 is a block diagram illustrating an example configuration of an information processing system according to one or more embodiments.

[0027] Hereinafter, specific embodiments will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and for clarity of explanation, duplicate explanations will be omitted as necessary.

[0028] The multiple embodiments described below may be used independently, or two or more embodiments may be combined as appropriate. These multiple embodiments may have different novel features. Therefore, these multiple embodiments may contribute to achieving different objectives or solving different problems, and may contribute to achieving different effects.

[0029] Each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0030] Although the following embodiments are primarily described for the 3GPP fifth generation mobile communication system (5G system), these embodiments may also be applied to other wireless communication systems that support DL beam prediction, particularly AI / ML-based DL beam prediction.

[0031] As used herein, depending on the context, "if" may be interpreted to mean "when," "while," "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.

[0032] First, the configurations and operations of several network elements common to several embodiments will be described. Fig. 1 shows an example configuration of a wireless communication system related to several 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 dedicated hardware, or as a virtualized function instantiated on an application platform.

[0033] The UE 1 has at least one radio transceiver and is configured to perform wireless communication with the RAN node 2. The UE 1 is connected to the RAN node 2 via an air interface 101. The UE 1 may be referred to by other terms such as a radio terminal, a mobile terminal, a mobile station, or a wireless transmit receive unit (WTRU). The RAN node 2 manages a cell and is configured to perform wireless communication with multiple UEs, including the UE 1, using a cellular communication technology (e.g., an NR Radio Access Technology (RAT)). The RAN node 2 may be referred to by other terms such as a base station, a radio station, or an access point. The UE 1 may be simultaneously connected to multiple RAN nodes, including the RAN node 2, for dual connectivity (DC).

[0034] The RAN node 2 may be a Central Unit (CU) (e.g., gNB-CU) in a cloud RAN (C-RAN) deployment, or a combination of a CU and one or more Distributed Units (DUs) (e.g., gNB-DUs). Furthermore, 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, the RAN node 2 may be a CU-CP or a combination of a CU-CP and a 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.

[0035] Specifically, as shown in Fig. 2, the RAN node 2 may include a CU 201 (e.g., gNB-CU) and one or more DUs 211 and 212 (e.g., gNB-DUs). The CU 201 is a logical node that controls the operation of the DUs 211 and 212. The CU 201 and each of the DUs 211 and 212 may also be referred to as a RAN node. Each of the DUs 211 and 212 is a logical node that hosts the RLC layer and MAC layer of the RAN node 2 and hosts part of the PHY layer of the RAN node 2, i.e., the upper PHY layer. The remaining signal processing of the PHY layer, i.e., the lower PHY layer, is located in Transmission Reception Points (TRPs) 231 to 235.

[0036] One DU may support one or more cells. One cell may be supported by only one DU. In the example of Figure 2, DU 211 is connected to TRPs 231 to 233, while DU 212 is connected to TRPs 234 and 235. TRPs 231 to 233 provide one cell 241, and TRPs 234 and 235 provide separate cells 242 and 243, respectively. In other words, DU 211 provides one cell 241, and TRPs 231 to 233 correspond to cell 241. DU 212 provides multiple cells 242 and 243, and TRPs 234 and 235 correspond to cells 242 and 243, respectively.

[0037] Each of the TRPs 231-235 can communicate with UE 1 using a beam. The TRPs 231-235 may also be called Radio Units (RUs), Remote Radio Heads (RRHs), access points (APs), or distributed antennas. Each TRP is a set of geographically co-located antennas (e.g., an antenna array with one or more antenna elements). Each TRP supports either or both Transmission Point (TP) and Reception Point (RP) functions.

[0038] The RAN node 2 may be connected to a RAN controller 3. The RAN controller 3 may be referred to by other terms, such as a control device or a control system. The RAN controller 3 may be integrated into the RAN node 2 (e.g., gNB). Alternatively, the RAN controller 3 may include one or both of a Non-RT RIC and a Near-RT RIC defined in the O-RAN Alliance technical specifications. In this case, the RAN node 2 may be connected to the RAN controller 3 via one or both of an O1 interface and an E2 interface. Alternatively, the RAN controller 3 may be an OAM server or another controller. In other words, the functions of the RAN controller 3 may be located in the RAN node 2, the Non-RT RIC, the Near-RT RIC, the OAM server, or another controller, or may be distributed across any combination thereof.

[0039] The UE 1 may perform AI / ML inference locally. In other words, the UE 1 may support UE-based AI / ML. UE-based AI / ML is also referred to as a UE-side AI / ML model or a UE-side model. This AI / ML inference may relate to RAN optimization. The UE 1 may run AI inference on a trained artificial intelligence or machine learning (AI / ML) model and take one or more actions according to a prediction or decision based on the AI ​​inference. The AI / ML model may be any model known in the field of machine learning, including deep learning. The AI / ML 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.

[0040] By way of example and not limitation, the prediction or decision based on AI inference by UE1 and one or more actions triggered thereby may relate to beam management (BM) and include DL beam prediction. The one or more actions may include, for example, but not limited to, DL beam selection. The DL beam may include a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam, a Channel State Information (CSI) Reference Signal (CSI-RS) beam, or both. For example, the AI / ML model may output one or more candidate beams for DL ​​beam selection. Additionally or alternatively, the AI / ML model may predict or determine the timing of execution of an action for beam management. The DL beam prediction and selection by UE1 may be performed during a Beam Failure Recovery (BFR) procedure.

[0041] The training of the AI / ML model for AI / ML inference by the UE 1 may be performed by the UE 1 or by the network (e.g., RAN node 2, RAN controller 3, or OAM). The training method may be offline learning, online learning, or a combination thereof.

[0042] Similarly, the network, i.e., the RAN node 2 or the RAN controller 3, or other control system, or any combination thereof, may perform AI / ML inference. In other words, the network may support network-based AI / ML. Network-based AI / ML is also referred to as a network-side AI / ML model or network-side model. This AI / ML inference may relate to RAN optimization. The network may run AI inference on a trained AI / ML model and take one or more actions according to a prediction or decision based on the AI ​​inference. The AI / ML model may be any model known in the field of machine learning, including deep learning. The AI / ML 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.

[0043] By way of example and not limitation, the network-based AI inference-based prediction or decision and one or more actions triggered thereby may relate to beam management and include DL beam prediction. The one or more actions may include, for example and without limitation, DL beam selection. The DL beam may include an SSB beam, a CSI-RS beam, or both. For example, the AI / ML model may output one or more candidate beams for DL ​​beam selection. Additionally or alternatively, the AI / ML model may predict or determine when to perform an action for beam management. The network-based DL beam prediction and selection may be performed to determine the set of CSI-RS beams to be configured (or measured) by UE1.

[0044] Training of an AI / ML model for network-based AI / ML inference may be performed by any information processing system or computer system on the network side, and the training method may be offline learning, online learning, or a combination of these.

[0045] One sub-use case for AI / ML BM involves DL beam prediction in both the UE-side model and the network-side model. DL beam prediction includes spatial domain beam prediction and temporal beam prediction. Temporal beam prediction may also be referred to as time domain beam prediction. DL beam prediction includes DL Tx beam prediction, DL Rx beam prediction, and beam pair prediction of DL Tx beam and DL Rx beam.

[0046] Spatial-domain DL beam prediction is a spatial-domain DL beam prediction of Set A of beams based on measurements of Set B of beams. Spatial-domain DL beam prediction is conveniently called BM-Case 1. Beam Set B is the set of beams whose measurements are taken as inputs to an AI / ML model. In spatial-domain DL beam prediction (i.e., BM-Case 1), Set A is different from Set B (i.e., Set B is not a subset of Set A), or Set B is considered to be a subset of Set A. For example, there are four possible inputs to the AI / ML model for spatial domain DL beam prediction: Layer 1 (L1) Reference Signal Received Power (RSRP) measurements only based on set B; L1-RSRP measurements and assistance information based on set B; Channel Impulse Response (CIR) based on set B; L1-RSRP measurements based on set B and one or both of the corresponding DL Tx beam ID and Rx beam ID.

[0047] Temporal DL beam prediction is a temporal DL beam prediction of Set A of beams based on the historical measurement results of Set B of beams. Temporal DL beam prediction is conveniently called BM-Case 2. Beam Set B is the set of beams whose measurements are taken as inputs to the AI / ML model. In temporal DL beam prediction (i.e., BM-Case 2), Set A is considered to be different from Set B (i.e., Set B is not a subset of Set A), Set B is a subset of Set A (i.e., Set B is not identical to Set A), or Set A and Set B are considered to be the same. For example, the input to the AI / ML model for temporal DL beam prediction may be the measurement results of the K (K≧1) most recent measurement instances, with the following options: - Layer 1 (L1) Reference Signal Received Power (RSRP) measurements only based on set B; - L1-RSRP measurements based on set B and assistance information; - L1-RSRP measurements based on set B and one or both of the corresponding DL Tx beam ID and Rx beam ID.

[0048] <First Embodiment> A configuration example of a wireless communication system according to this embodiment is similar to the configuration example described with reference to Figures 1 and 2. This embodiment provides details of signaling between a UE 1 and a RAN node 2 related to beam management (e.g., AI / ML BM).

[0049] 3 shows an example of signaling between UE1 and RAN node 2. In step 301, RAN node 2 transmits an Assistance Information reporting configuration to UE1. UE1 receives the Assistance Information reporting configuration from the network (e.g., RAN node 2). RAN node 2 may transmit the Assistance Information reporting configuration to UE1 via signaling dedicated to UE1, such as dedicated RRC signaling. The dedicated RRC signaling may be an RRCReconfiguration message. The Assistance Information reporting configuration may specify the type and / or number of elements to be included in the reported Assistance Information. Additionally or alternatively, the Assistance Information reporting configuration may specify a reporting period for the Assistance Information. Additionally or alternatively, the Assistance Information reporting configuration may specify an event that triggers the reporting of the Assistance Information.

[0050] In step 302, UE1 transmits assistance information to RAN node 2 according to the reporting configuration. RAN node 2 receives the reported assistance information from UE1. UE1 may transmit the assistance information to RAN node 2 via Layer 3 (e.g., RRC), Layer 2 (e.g., MAC), or Layer 1 signaling. The Layer 3 signaling may be an RRC message, such as a MeasurementReport message or a UEAssistanceInformation message. Alternatively, the RRC message may be a UEInformationResponse message sent in response to receiving a UEInformationRequest message from RAN node 2. The Layer 2 signaling may be a MAC Control Element (CE). The Layer 1 signaling may be Uplink Control Information (UCI), specifically, UCI carrying a CSI report.

[0051] The assistance information may include or be based on a correlation indicator (CI) between the first signal beam and each of one or more second signal beams. The first signal beam and the one or more second signal beams are DL beams transmitted by the RAN node 2, e.g., one or more TRPs (e.g., TRPs 231 to 233 in FIG. 2 ). The first beam may be a DL reference signal beam, specifically an SSB beam or a CSI-RS beam. Similarly, each second beam may be a DL reference signal beam, specifically an SSB beam or a CSI-RS beam. The assistance information may specifically include at least one of the following first information and second information: The first information includes one or more CIs between the first signal beam and one or more second signal beams. The second information includes at least one identifier of at least one second signal beam whose corresponding CI exceeds a threshold determined based on the reporting configuration (step 301).

[0052] The reporting configuration (step 301) may include information for UE1 to determine whether the first information or the second information needs to be reported. In one example, the reporting configuration may include an information element that specifies whether the first information or the second information needs to be reported. In another example, the reporting configuration may selectively include an information element that requests or indicates the reporting of the first information and another information element that requests or indicates the reporting of the second information. If the reporting configuration includes a setting of a threshold for generating the second information, UE1 may understand that the reporting configuration requests the transmission of the second information.

[0053] Each of the one or more CIs is a parameter indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by UE1 and a respective one of one or more second channels estimated based on reception of one or more second signal beams by UE1. The term CI may be referred to by other terms such as a correlation parameter, a similarity index, or a similarity parameter. The first channel estimated by UE1 may be an effective channel including a propagation channel between a receiver of UE1 and a transmitter (e.g., TRP) of RAN node 2 and beamforming weights applied to the first signal beam at the transmitter of RAN node 2. Similarly, the second channel estimated by UE1 may be an effective channel including a propagation channel between a receiver of UE1 and a transmitter (e.g., TRP) of RAN node 2 and beamforming weights applied to the second signal beam at the transmitter of RAN node 2.

[0054] As an example, CI(ρ) between the mth beam and the nth beam may be calculated according to the following formula: where N ＿ RB is the number of resource blocks, N_UE is the number of receive antennas of UE1, h_(n,n_RB,n_ue) is a channel vector of dimension N_gNB, and N_gNB is the number of transmit antennas of RAN node 2 (e.g., gNB).

[0055] Some examples of combinations of a first signal beam and a second signal beam are shown below. In a first example, the first signal beam and one or more second signal beams are included in a second set of beams (Set B of beams) used as input for beam prediction of a first set of beams (Set A of beams). This beam prediction may be performed by inference using a trained AI / ML model, and the second set of beams (Set B of beams) may be used as input for inference using the trained AI / ML model. The first signal beam may be the best DL reference signal beam having the best radio quality (e.g., L1-RSRP) among multiple DL reference signal beams (e.g., SSB beam or CSI-RS beam) measured by UE1. Meanwhile, one or more second signal beams may be one or more DL reference signal beams included in the multiple DL reference signal beams and different from the best DL reference signal beam (i.e., the first beam). In other words, each CI in the first example may indicate a correlation or similarity between the estimated channel of the best DL reference beam measured by UE1 among multiple DL reference beams and the estimated channels of other DL reference beams included in the multiple DL reference beams. One or more CIs in the first example may be used, for example, for post-processing the results of DL beam prediction, specifically for selecting one or more beams from a first set of beams (Set A) obtained by beam prediction. Details of the use of CIs in post-processing of beam prediction will be described in other embodiments below.

[0056] In a second example, a first signal beam is included in a second set of beams (Set B of beams) used as input for an AI / ML model for spatial-domain beam prediction of a first set of beams (Set A of beams). Meanwhile, one or more second signal beams are included in the first beam set (Set A of beams). The second beam set (Set B of beams) is a subset of the first beam set (Set A of beams) or is different from the first set (Set A of beams). The first signal beam may be the best reference signal beam with the best radio quality (e.g., L1-RSRP) among multiple DL reference signal beams (e.g., SSB beams) measured by UE1. Meanwhile, one or more second signal beams may be one or more DL beams (e.g., CSI-RS beams) each having a beamwidth narrower than the beamwidth of each of the multiple DL reference signal beams (e.g., SSB beams). In other words, each CI in the second example may indicate a correlation or similarity between the estimated channel of the best DL reference beam measured by UE1 among multiple DL reference beams used as input for the spatial-domain beam prediction AI / ML model and the estimated channel of the DL beam to be predicted included in the output of the AI / ML model. One or more CIs in the second example may be used, for example, for training an AI / ML model for spatial-domain DL beam prediction. Details of the use of CIs in training the spatial-domain DL beam prediction AI / ML model are described in other embodiments below.

[0057] In a third example, the first signal beam is included in a second set of beams (Set B of beams) used as input for an AI / ML model for temporal beam prediction of the first set of beams (Set A of beams). One or more second signal beams are also included in the second set of beams (Set B of beams). However, each of the one or more second signal beams is a beam transmitted at a time instance different from that at which the first signal beam is transmitted, with the same beamforming weights applied to the first signal beam. Each of the one or more second signal beams may be transmitted on the same radio resources (e.g., resource elements) as the first signal beam. The first signal beam may be the best reference signal beam with the best radio quality (e.g., L1-RSRP) among multiple DL reference signal beams (e.g., SSB beams or CSI-RS beams) measured by UE1 at a certain time instance. In other words, each CI in the third example may indicate a correlation or similarity between an estimated channel of a best DL reference beam measured by UE1 at a certain time instance among multiple DL reference beams and an estimated channel obtained by UE1 measuring the best DL reference beam at another time instance. One or more CIs in the third example may be used, for example, for training an AI / ML model for temporal DL beam prediction. Details of the use of CIs in training a temporal DL beam prediction AI / ML model are described in other embodiments below.

[0058] The operations of UE 1 and RAN node 2 described with reference to Figure 3 enable UE 1 to provide information including or based on a CI to a network including RAN node 2. The information including or based on a CI is non-proprietary information and may be useful for beam management, particularly DL beam prediction.

[0059] FIG. 4 illustrates an example of signaling between UE1 and RAN node 2. The signaling illustrated in FIG. 4 is a specific example of the signaling illustrated in FIG. 3 and illustrates an example of transmitting assistance information via CSI reporting. In step 401, RAN node 2 transmits CSI reporting configuration to UE1. The CSI reporting configuration may be a CSI-ReportConfig information element (IE) included in an RRCReconfiguration message. The CSI reporting configuration includes configuration for CSI reporting including or based on CI between a first SSB or CSI-RS (SSB / CSR-RS) beam and a second SSB / CSR-RS beam. The CSI reporting configuration may specify a CSI reporting periodicity. Additionally or alternatively, the CSI reporting configuration may specify an event that triggers CSI reporting by UE1.

[0060] In step 402, UE1 transmits a CSI report to RAN node 2 according to the configuration received in step 401. RAN node 2 receives the CSI report from UE1. The CSI report may be transmitted via Layer 1 signaling, specifically UCI. The CSI report includes or is based on CIs between the first SSB / CSR-RS beam and each of one or more second SSB / CSR-RS beams. Details of the one or more CIs are similar to those described with reference to FIG. 3.

[0061] 5 shows an example of the format of the CSI reporting configuration (step 401). The CSI-ReportConfig IE shown in FIG. 5 may include an AIML-reportQuantity field or IE 501. The AIML-reportQuantity field or IE 501 may include a CRI-RSRP-CI field or IE 502 or an RSRP-CI field or IE 503. The CRI-RSRP-CI field or IE 502 is included in the AIML-reportQuantity field or IE 501 when a threshold for CI is configured. The RSRP-CI field or IE 503 is included in the AIML-reportQuantity field or IE 501 when a threshold for CI is not configured. When the AIML-reportQuantity field or IE 501 indicates the CRI-RSRP-CI field or IE 502, the CSI-ReportConfig IE further includes a CI-Threshold field or IE 504. The CI-Threshold field or IE 504 indicates a threshold value for the CI, i.e., a threshold value that is applied to the CI to generate the second information described above. As an example, the CI-Threshold field or IE 504 may be an integer type (505) and represent the magnitude of the threshold as an integer between 0 and 127.

[0062] FIG. 6 shows an example of a CSI report. In the example of FIG. 6, the CSI report 600 includes a CRI or SSBRI #1 (601), an RSRP #1 (602), and one or more CIs #1 to #N-1 (603). The CRI or SSBRI #1 (601) is a CSI-RS Resource Indicator (CRI) that identifies the best CSI-RS beam measured by UE1, or an SSB Resource Indicator (SSBRI) that identifies the best SSB beam measured by UE1. The RSRP #1 (602) is the L1-RSRP of the best CSI-RS or SSB beam. The one or more CIs #1 to #N-1 (603) are CIs between the estimated channel of the best CSI-RS or SSB beam and one or more estimated channels of one or more other CSI-RS or SSB beams. For example, if UE1 measures 16 (N=16) CSI-RS or SSB beams #0 to #15 and the best beam is beam #3, CSI report 600 may indicate 15 CIs between best beam #3 and the remaining beams #0, #1, #2, and #4 to #15.

[0063] The CSI report format of FIG. 6 may be modified as appropriate. For example, CRI or SSBRI #1 (601) may be omitted. Instead, CSI report 600 may include CI fields (603) equal to the number N of CSI-RS or SSB beams measured by the UE. For example, if UE 1 measures 16 (N=16) CSI-RS or SSB beams #0 to #15 and the best beam is beam #3, CSI report 600 may indicate 16 CIs between best beam #3 and all beams #0 to #15. In this case, the size of the CI between best beam #3 and the same best beam #3 is a maximum value (e.g., 1 or 127), so RAN node 2 can recognize from the maximum CI that beam #3 is the best beam measured by the UE.

[0064] FIG. 7 shows an example of a CSI report. In the example of FIG. 7, the CSI report 600 includes CRI or SSBRI #1 (701), RSRP #1 (702), CRI or SSBRI #2 (703), CRI or SSBRI #3 (704), and CRI or SSBRI #4 (705). CRI or SSBRI #1 (701) is a CRI identifying the best CSI-RS beam measured by UE1, or an SSBRI identifying the best SSB beam measured by UE1. RSRP #1 (702) is the L1-RSRP of the best CSI-RS or SSB beam. CRI or SSBRI #2 (703), CRI or SSBRI #3 (704), and CRI or SSBRI #4 (705) each identify a CSI-RS or SSB beam whose CI with the best CSI-RS or SSB beam exceeds a CI threshold specified by the CSI reporting configuration. The number of fields CRI or SSBRI #2 (703), CRI or SSBRI #3 (704), and CRI or SSBRI #4 (705) is not limited to three. The maximum number of these fields is N-1, where N is the total number of CSI-RS or SSB beams measured by UE1. The number of these fields actually included in the CSI report depends on the number of CSI-RS or SSB beams whose CIs exceed the threshold.

[0065] The operation of UE 1 and RAN node 2 described with reference to Figure 4 enables UE 1 to provide information including or based on CI related to SSB / CSI-RS beams to a network including RAN node 2. Information including or based on CI is non-proprietary information and may be useful for beam management, particularly DL beam prediction.

[0066] Second Embodiment A configuration example of a wireless communication system according to this embodiment is similar to the configuration example described with reference to Figures 1 and 2. This embodiment provides details of the use of CIs in post-processing of beam management (e.g., AI / ML BM).

[0067] 8 shows an example of an operation related to AI / ML BM performed by an information processing system. The information processing system includes one or more computers. In a network-side model, the functions of the information processing system may be located in a RAN node 2, a RAN controller 3, or other network elements, or may be distributed among them. In a UE-side model, the functions of the information processing system may be located in a UE 1. Alternatively, the functions of the information processing system may be distributed between a UE 1 and a network.

[0068] In step 801, the information processing system acquires assistance information including or based on a correlation index (CI) between a first and a second signal beam included in a second set of beams (Set B of beams). In a network-side model, the information processing system may acquire the assistance information from UE1 through a report of the assistance information from UE1. The report of the assistance information by UE1 may be the same as the reporting method described in the first embodiment. In a UE-side model, the information processing system in UE1 acquires the assistance information from a radio layer of UE1.

[0069] The details and examples of the CI acquired in step 801 are the same as those described in the first embodiment. In particular, the details and examples of the CI acquired in step 801 are the same as those in the "first example" described in the first embodiment. Specifically, the first signal beam is the best DL reference signal beam having the best radio quality (e.g., L1-RSRP) among multiple DL reference signal beams (e.g., SSB beam or CSI-RS beam) measured by UE1. Meanwhile, the one or more second signal beams are one or more DL reference signal beams included in the multiple DL reference signal beams and different from the best DL reference signal beam (i.e., the first beam). In other words, in the example of FIG. 8 , the CI indicates the correlation or similarity between the estimated channel of the best DL reference beam measured by UE1 among the multiple DL reference beams and the estimated channels of other DL reference beams included in the multiple DL reference beams.

[0070] In step 802, the information processing system performs spatial-domain DL beam prediction for a first set of beams (Set A of beams) by inference using a trained AI / ML model that uses measurement results of a second set of beams (Set B of beams) as input. Input data (i.e., inference input) for the AI / ML model may include, among other data, the best radio quality (e.g., L1-RSRP) of the best DL reference signal beam measured by UE1. In one example, the second set of beams (Set B of beams) may be a set of SSB beams, and the first set of beams predicted by AI / ML inference may be a set of CSI-RS beams. Typically, the beamwidth of each CSI-RS beam is narrower than the beamwidth of each SSB beam.

[0071] In step 803, one or more beams are further selected from the first set of beams (Set A of beams) predicted by AI / ML inference (802) based on the CI-related assistance information obtained in step 801. For example, in step 802, the information processing system determines the top N (e.g., 4) beams predicted to have better reception quality by UE1 through AI / ML inference. Next, in step 803, the information processing system selects the top M (e.g., 2) beams predicted to have better reception quality by UE1 from the N (e.g., 4) beams, where the integer M is smaller than the integer N.

[0072] FIG. 9 illustrates a specific example of post-processing (step 803) after DL beam prediction using AI / ML inference. In the example of FIG. 9, assume that beam B1 is the best beam measured by UE1 and that UE1 provides three CIs, each of which indicates a correlation between the best beam B1 and one of the other beams B0, B2, and B3 (step 801). Furthermore, assume that the information processing system performs AI / ML beam prediction (step 802) and selects four beams A0 to A3 for UE1. Then, in post-processing (step 803), the information processing system selects two more beams, A0 and A1, from the four beams A0 to A3, taking into account the values ​​of the three CIs provided by UE1. For example, the information processing system may determine that beams A0 and A1 are expected to provide higher reception quality at UE1 than beams A2 and A3, based on the fact that the CI value between the best beam B1 and beam B0 is greater than the CI value between the best beam B1 and beam B2.

[0073] Figure 10 provides a detailed example of the operation of the information processing system described with reference to Figures 8 and 9. The example of Figure 10 assumes a network-side model. Therefore, the information processing system is located in network 4 (e.g., RAN node 2, RAN controller 3, or other network element). Furthermore, the example of Figure 10 assumes that network 4 determines the set of CSI-RS beams to be configured in UE1 (or to be measured by UE1) by AI / ML inference using measurement results of the set of SSB beams by UE1 as inference input.

[0074] In step 1001, network 4 transmits a CSI reporting configuration to UE 1. The CSI reporting configuration may be a CSI-ReportConfig IE included in an RRCReconfiguration message. The CSI reporting configuration requests UE 1 to report the best SSB beam and the L1-RSRP of the best SSB. Furthermore, the CSI reporting configuration requests UE 1 to report assistance information including or based on CI between the best SSB beam and other SSB beams.

[0075] In step 1002, network 4, specifically RAN node 2, sweeps (or transmits) multiple SSB beams. UE1 measures the L1-RSRPs of the multiple SSB beams transmitted from RAN node 2 and determines the best SSB beam with the best L1-RSRP. UE1 then calculates the CI between the best SSB beam and each of one or more other SSB beams.

[0076] In step 1003, UE 1 sends a CSI report to network 4, specifically RAN node 2. The CSI report indicates the SSBRI of the best SSB beam and the best L1-RSRP. Furthermore, the CSI report includes one or more CIs (hereinafter referred to as SSB-CIs) between the best SSB beam and each of one or more other SSB beams. Alternatively, the CSI report includes the SSBRIs of one or more SSB beams whose CIs with the best SSB beam exceed a CI threshold specified by the CSI report configuration (1001).

[0077] In step 1004, the network 4 performs AI / ML inference for CSI-RS beam prediction. In step 1005, the network 4 performs post-processing on the output of the AI / ML inference. Specifically, the network 4 further selects one or more CSI-RS beams to be configured for UE1 (or to be measured by UE1) from the set of CSI-RS beams predicted by the AI / ML inference based on CI-related assistance information (i.e., SSB-CIs).

[0078] 8 to 10, the information processing system can further narrow down the predicted beam or the number of beams for UE1 based on the assistance information related to the CI, which contributes to reducing the overhead (e.g., radio resources) required to transmit the predicted beam, e.g., the reference signal beam, to UE1.

[0079] 8 to 10 are based on AI / ML beam prediction. However, post-processing using assistance information can also be applied to other or existing beam predictions that do not rely on AI / ML inference.

[0080] Third Embodiment A configuration example of a wireless communication system according to this embodiment is similar to the configuration example described with reference to Figures 1 and 2. This embodiment provides details of the use of CIs in training an AI / ML model for spatial domain DL beam prediction.

[0081] 8 shows an example of an operation related to AI / ML BM performed by an information processing system. The information processing system includes one or more computers. In a network-side model, the functions of the information processing system may be located in a RAN node 2, a RAN controller 3, or other network elements, or may be distributed among them. In a UE-side model, the functions of the information processing system may be located in a UE 1. Alternatively, the functions of the information processing system may be distributed between a UE 1 and a network.

[0082] In step 1101, the information processing system acquires assistance information including or based on a correlation index (CI) between a first signal beam included in a second set of beams (Set B of beams) and a second signal beam included in a first set of beams (Set A of beams). In a network-side model, the information processing system may acquire the assistance information from UE1 through a report of the assistance information from UE1. The report of the assistance information by UE1 may be the same as the reporting method described in the first embodiment. In a UE-side model, the information processing system in UE1 acquires the assistance information from a radio layer of UE1.

[0083] The details and examples of the CI acquired in step 1101 are the same as those described in the first embodiment. In particular, the details and examples of the CI acquired in step 1101 are the same as those described in the "second example" of the first embodiment. Specifically, the first signal beam is the best DL reference signal beam (e.g., SSB beam) having the best radio quality (e.g., L1-RSRP) among multiple DL reference signal beams (e.g., SSB beam) measured by UE1. Meanwhile, the one or more second signal beams are one or more DL beams (e.g., CSI-RS beams) each having a beamwidth narrower than that of each of the multiple DL reference signal beams (e.g., SSB beams). In other words, in the example of FIG. 11 , the CI indicates the correlation or similarity between the estimated channel of the best DL reference beam measured by UE1 among multiple DL reference beams used as inputs of the spatial-domain beam prediction AI / ML model and the estimated channel of the DL beam to be predicted included in the output of the AI / ML model.

[0084] In step 1102, the information processing system trains an AI / ML model that performs spatial-domain beam prediction of a first set of beams (Set A of beams) from measurement results of a second set of beams (Set B of beams) using training data including CI-related assistance information.

[0085] Figure 12 illustrates an example of training a spatial domain beam prediction AI / ML model (step 1102) using CI-related assistance information. In the example of Figure 12, assume that UE1 measures beams B0-B3 and that beam B1 is the best beam among beams B0-B3 measured by UE1. Furthermore, in the example of Figure 12, UE1 measures beams A0-A1. 15 and beam A5 is measured by UE1, and beam A0 to A 15Assume that UE1 is the best beam in beam set A. UE1 calculates the CI between the best beam B1 in measured beam set B and the best beam A5 in measured beam set A. The information processing system uses the identifier (e.g., SSBRI) of the best beam B1 in beam set B, the L1-RSRP of the best beam B1, the identifier (e.g., CRI) of the best beam A5 in beam set A, and the CI between the best beam B1 and the best beam A5 as training data for the spatial-domain DL beam prediction AI / ML model. The training data may further include other data. In training the AI / ML model, the information processing system adjusts the predicted values ​​of the AI / ML model based on the CI and the measurement results of beam set B so that they approach the actual values ​​of set A. The CI between the best beam B1 and the best beam A5 enables the AI / ML model to exploit or learn the latent relationship between channel conditions and beam performance. This allows the trained AI / ML model to exploit the learned latent relationship between channel conditions and beam performance and perform beam prediction in unknown channel conditions.

[0086] Figure 13 provides a detailed example of the operation of the information processing system described with reference to Figures 11 and 12. The example of Figure 13 assumes a network-side model. Therefore, the information processing system is located in network 4 (e.g., RAN node 2, RAN controller 3, or other network element). Furthermore, the example of Figure 13 assumes that network 4 trains a spatial-domain beam prediction AI / ML model using training data. This training data includes measurements by UE1 of a set of SSB beams (Set B of beams) and a set of CSI-RS beams (Set A of beams) and the CI between the best SSB beam and the best CSI-RS beam calculated by UE1.

[0087] In step 1301, network 4 sends a CSI reporting configuration to UE1. The CSI reporting configuration may be a CSI-ReportConfig IE included in an RRCReconfiguration message. The CSI reporting configuration requests UE1 to report the best SSB beam, the L1-RSRP of the best SSB beam, and the best CSI-RS beam. Furthermore, the CSI reporting configuration requests UE1 to report assistance information including or based on the CI between the best SSB beam and the best CSI-RS beam.

[0088] In step 1302, network 4, specifically RAN node 2, sweeps (or transmits) multiple SSB beams and multiple CSI-RS beams. UE1 measures the L1-RSRP of the multiple SSB beams transmitted from RAN node 2 and determines the best SSB beam with the best L1-RSRP. In addition, UE1 measures the L1-RSRP of the multiple CSI-RS beams transmitted from RAN node 2 and determines the best CSI-RS beam with the best L1-RSRP. Furthermore, UE1 calculates the CI between the best SSB beam and the best CSI-RS beam.

[0089] In step 1303, UE 1 sends a CSI report to network 4, specifically RAN node 2. The CSI report indicates the SSBRI of the best SSB beam, the best L1-RSRP, and the CRI of the best CSI-RS beam. Additionally, the CSI report includes the CI between the best SSB beam and the best CSI-RS beam.

[0090] In step 1304, network 4 trains an AI / ML model for spatial-domain CSI-RS beam prediction. Specifically, network 4 uses the SSBRI of the best SSB beam, the SSB-L1-RSRP of the best SSB beam, the CRI of the best CSI-RS beam, and the CI between the best SSB beam and the best CSI-RS as training data for the spatial-domain CSI-RS beam prediction AI / ML model. The training data may also include other data. In training the AI / ML model, network 4 adjusts the predicted value of the AI / ML model based on the measurement results of the CI and the SSB beam set so that the predicted value of the AI / ML model approaches the actual value of the CSI-RS beam set.

[0091] 11 to 13, the information processing system uses assistance information about CIs for spatial domain DL beam prediction AI / ML training, which is expected to contribute to improving the performance of AI / ML models by training using non-proprietary information.

[0092] <Fourth Embodiment> A configuration example of a wireless communication system according to this embodiment is similar to the configuration example described with reference to Figures 1 and 2. This embodiment provides details of the use of CIs in training an AI / ML model for temporal DL beam prediction.

[0093] 14 shows an example of an operation related to AI / ML BM performed by an information processing system. The information processing system includes one or more computers. In a network-side model, the functions of the information processing system may be located in a RAN node 2, a RAN controller 3, or other network elements, or may be distributed among them. In a UE-side model, the functions of the information processing system may be located in a UE 1. Alternatively, the functions of the information processing system may be distributed between a UE 1 and a network.

[0094] In step 1401, the information processing system acquires assistance information. The assistance information includes or is based on a correlation index (CI) between a first signal beam included in a second set of beams (Set B of beams) and a second signal beam transmitted with the same beamforming weight as that applied to the first signal beam at a time instance different from the time at which the first signal beam is transmitted. In a network-side model, the information processing system may acquire the assistance information from UE1 through a report of the assistance information from UE1. The report of the assistance information by UE1 may be similar to the reporting method described in the first embodiment. In a UE-side model, the information processing system in UE1 acquires the assistance information from a radio layer of UE1.

[0095] The details and specific examples of the CI acquired in step 1401 are the same as those described in the first embodiment. In particular, the details and specific examples of the CI acquired in step 1401 are the same as those in the "third example" described in the first embodiment. Specifically, the first signal beam is the best reference signal beam having the best radio quality (e.g., L1-RSRP) among multiple DL reference signal beams (e.g., SSB beam or CSI-RS beam) measured by UE1 at a certain time instance. In other words, in the example of FIG. 14 , the CI indicates the correlation or similarity between the estimated channel of the best DL reference beam measured by UE1 at a certain time instance among multiple DL reference beams and the estimated channel obtained by UE1 measuring the best DL reference beam at another time instance.

[0096] In step 1402, the information processing system trains an AI / ML model that performs temporal beam prediction of a first set of beams (Set A of beams) from measurement results of a second set of beams (Set B of beams) using training data including CI-related assistance information.

[0097] Training the temporal beam prediction AI / ML model using CI-related assistance information may be performed as follows: Assume that UE1 measures beams B0 to B3 at multiple time instances within an observation window, and beam B1 is the best beam among beams B0 to B3 measured by UE1. Note that UE1 may determine the best beam in beam set B at each time instance within the observation window. Furthermore, if UE1 measures beams A0 to A1 at one or more time instances within the prediction window, 15 and beam A5 is measured by UE1, and beam A0 to A 15 Assume that beam A is the best beam among beam set A. Note that UE1 may determine the best beam in beam set A at each time instance within the prediction window. The prediction window occurs after the observation window. The observation window may also be referred to by other terms such as an observation period, a measurement window, or a measurement period. The prediction window may also be referred to as a prediction period.

[0098] UE1 calculates the CI between the estimated channels at different time instances within the observation window for the best beam B1 of beam set B. The information processing system uses the identifier (e.g., SSBRI) of the best beam B1 of beam set B, the L1-RSRP of the best beam B1, the identifier (e.g., CRI) of the best beam A5 of beam set A, and the calculated CI as training data for the temporal DL beam prediction AI / ML model. The training data may further include other data. In training the AI / ML model, the information processing system adjusts the predicted value of the AI / ML model based on the CI and the measurement results of beam set B so that it approaches the actual value of set A.

[0099] Furthermore, the information processing system can infer the stability and movement of UE1. For example, if the value of CI during the observation window remains 1 or is maintained close to 1, the information processing system can infer that UE1 is stationary. Therefore, the AI / ML model may maintain beam A5 as the predicted beam, simplifying the prediction task. In one example, the information processing system may estimate the movement speed of UE1 from the CI. Specifically, if the best beam selected at consecutive time instances t and t+1 within the observation window is the same beam (e.g., beam B1), and the CI of the best beam between these two time instances is equal to or substantially equal to 1, the information processing system may infer that the movement speed of UE1 is substantially 0 during that period, i.e., that UE1 is stationary. The information processing system may use the fact that UE1's movement speed is 0 as input for training the AI / ML model.

[0100] Figure 15 provides a detailed example of the operation of the information processing system described with reference to Figure 14. The example of Figure 15 assumes a network-side model. Therefore, the information processing system is located in network 4 (e.g., RAN node 2, RAN controller 3, or other network element). Furthermore, the example of Figure 15 assumes that network 4 trains a temporal beam prediction AI / ML model using training data. This training data includes measurement results of a set of SSB beams (Set B of beams) and a set of CSI-RS beams (Set A of beams) by UE1, and one or more CIs between different time instances for the best SSB beam calculated by UE1.

[0101] In step 1501, network 4 transmits a CSI reporting configuration to UE1. The CSI reporting configuration may be a CSI-ReportConfig IE included in an RRCReconfiguration message. The CSI reporting configuration requests UE1 to report the best SSB beam, the L1-RSRP of the best SSB beam, and the best CSI-RS beam. Furthermore, the CSI reporting configuration requests UE1 to report assistance information including or based on one or more CIs between different time instances for the best SSB beam.

[0102] In step 1502, network 4, specifically RAN node 2, sweeps (or transmits) multiple SSB beams during an observation window in the training phase. UE1 measures the L1-RSRP of the multiple SSB beams transmitted from RAN node 2 and determines the best SSB beam with the best L1-RSRP. In addition, UE1 calculates the CI between the estimated channels at different time instances within the observation window for the best SSB beam.

[0103] In step 1503, UE 1 sends a CSI report to network 4, specifically RAN node 2. The CSI report includes the SSBRI of the best SSB beam, the best SSB-L1-RSRP, and the CI for the best SSB beam (SSB-CI).

[0104] In step 1504, UE1 sweeps (or transmits) multiple CSI-RS beams during a prediction window in the training phase. UE1 measures the L1-RSRP of multiple CSI-RS beams transmitted from RAN node 2 and determines the best CSI-RS beam with the best L1-RSRP.

[0105] In step 1505, UE 1 sends a CSI report to network 4, specifically RAN node 2. The CSI report includes the CRI of the best CSI-RS beam.

[0106] In step 1506, network 4 trains an AI / ML model for temporal CSI-RS beam prediction. Specifically, network 4 uses the SSBRI, SSB-L1-RSRP, and SSB-CI of the best SSB beam in the observation window and the CRI of the best CSI-RS beam in the prediction window as training data for the spatial-domain CSI-RS beam prediction AI / ML model. The training data may further include other data. In training the AI / ML model, network 4 adjusts the predicted values ​​of the AI / ML model based on the CI and measurement results of beam set B so that they approach the actual values ​​of set A. Furthermore, network 4 can infer the stability and movement of UE1. For example, if the value of CI during the observation window remains 1 or remains close to 1, network 4 can infer that UE1 is stationary. Therefore, the AI / ML model may retain the best beam obtained in the prediction window as the predicted beam, simplifying the prediction task.

[0107] Figure 16 shows an example of the format of the CSI reporting configuration sent in step 15 of Figure 15. The CSI-ReportConfig IE shown in Figure 16 may include an AIML-reportQuantity field or IE 1601. The AIML-reportQuantity field or IE 1601 may include an Observation-WindowLength field or IE 1602, a Prediction-WindowLength field or IE 1603, and a CI-Length field or IE 1604. As shown in Figure 17, these fields specify the length of the observation window and the length of the prediction window in units of the time length specified in the CI-Length field or IE 1604.

[0108] 14 to 17, the information processing system uses assistance information about CIs for temporal DL beam prediction AI / ML training, which is expected to contribute to improving the performance of AI / ML models by training using non-proprietary information.

[0109] The operations described with reference to Figures 14 to 17 may be modified as follows. The information processing system may use a trained AI / ML model to perform temporal beam prediction of a first set of beams (Set A of beams) (e.g., multiple CSI-RS beams) from measurement results of a second set of beams (Set B of beams) (e.g., multiple SSB beams). Specifically, an input dataset (inference data) input to the trained AI / ML model for inference includes measurement results of reception quality (e.g., L1-RSRP) of a specific beam (e.g., best beam) included in the second set of beams at multiple time instances within an observation window. Furthermore, the input dataset includes CIs between multiple time instances within the observation window for the specific beam included in the second set. The input dataset may further include other data. The information processing system predicts the first set of beams within a prediction window from the input dataset based on measurements of the second set within the observation window.

[0110] Alternatively, an information processing system (e.g., the RAN controller 3 or the RAN node 2) may provide the trained AI / ML model (e.g., the trained parameters or the AI / ML application including the trained parameters) to another information processing system (e.g., the RAN node 2 or the UE 1). In this case, the other information processing system may perform the above-described temporal beam prediction using the provided trained AI / ML model.

[0111] Next, exemplary configurations of the UE 1, the RAN node 2, and the RAN controller 3 related to the above-described embodiments will be described below. FIG. 18 is a block diagram showing an exemplary configuration of the UE 1. The RF transceiver 1801 performs analog RF signal processing for communication with the RAN node 2. The RF transceiver 1801 may include multiple transceivers. The analog RF signal processing performed by the RF transceiver 1801 includes frequency up-conversion, frequency down-conversion, and amplification. The RF transceiver 1801 is coupled to the antenna array 1802 and the baseband processor 1803. The RF transceiver 1801 receives modulation symbol data (or OFDM symbol data) from the baseband processor 1803, generates a transmit RF signal, and provides the transmit RF signal to the antenna array 1802. The RF transceiver 1801 also generates a baseband receive signal based on the receive RF signal received by the antenna array 1802 and provides the baseband receive signal to the baseband processor 1803. The RF transceiver 1801 may include an analog beamformer circuit for beamforming, which may include, for example, multiple phase shifters and multiple power amplifiers.

[0112] The baseband processor 1803 performs digital baseband signal processing (data plane processing) and control plane processing for wireless communications. Digital baseband signal processing includes (a) data compression / decompression, (b) data segmentation / concatenation, (c) transmission format (transmission frame) generation / decomposition, (d) transmission path coding / decoding, (e) modulation (symbol mapping) / demodulation, and (f) generation of OFDM symbol data (baseband OFDM signal) using Inverse Fast Fourier Transform (IFFT). Meanwhile, control plane processing includes communication management for Layer 1 (e.g., transmit 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).

[0113] For example, the digital baseband signal processing by the baseband processor 1803 may include signal processing of a PDCP layer, an RLC layer, a MAC layer, and a PH layer. Also, the control plane processing by the baseband processor 1803 may include processing of a Non-Access Stratum (NAS) protocol, an RRC protocol, MAC CEs, and Downlink Control Information (DCIs).

[0114] The baseband processor 1803 may perform multiple-input multiple-output (MIMO) encoding and precoding for beamforming.

[0115] The baseband processor 1803 may include a modem processor (e.g., a Digital Signal Processor (DSP)) that performs digital baseband signal processing and a protocol stack processor (e.g., a Central Processing Unit (CPU) or a 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 1804, which will be described later.

[0116] The application processor 1804 is also referred to as a CPU, MPU, microprocessor, or processor core. The application processor 1804 may include multiple processors (multiple processor cores). The application processor 1804 executes a system software program (operating system (OS)) and various application programs (e.g., a call application, a web browser, a mailer, a camera operation application, and a music playback application) read from the memory 1806 or other memories, thereby realizing various functions of the UE 1.

[0117] In some implementations, the baseband processor 1803 and the application processor 1804 may be integrated on a single chip, as shown by the dashed line (1805) in Figure 18. In other words, the baseband processor 1803 and the application processor 1804 may be implemented as a single System on Chip (SoC) device 1805. An SoC device may also be called a system Large Scale Integration (LSI) or chipset.

[0118] The memory 1806 is volatile memory, nonvolatile memory, or a combination thereof. The memory 1806 may include multiple physically independent memory devices. The volatile memory may be, for example, static random access memory (SRAM), dynamic RAM (DRAM), or a combination thereof. The nonvolatile memory may be mask read only memory (MROM), electrically erasable programmable ROM (EEPROM), flash memory, a hard disk drive, or any combination thereof. For example, the memory 1806 may include an external memory device accessible from the baseband processor 1803, the application processor 1804, and the SoC 1805. The memory 1806 may also include an internal memory device integrated within the baseband processor 1803, the application processor 1804, or the SoC 1805. Furthermore, the memory 1806 may include memory within a Universal Integrated Circuit Card (UICC).

[0119] The memory 1806 may store one or more software modules (computer programs) 1807 containing instructions and data for processing by the UE 1. In some implementations, the baseband processor 1803 or the application processor 1804 may be configured to read and execute the software modules 1807 from the memory 1806 to perform the processing of the UE 1 described in one or more of the embodiments.

[0120] It should be noted that the control plane processing and operations performed by UE 1 described in the above embodiment can be realized by elements other than RF transceiver 1801 and antenna array 1802, namely, at least one of baseband processor 1803 and application processor 1804, and memory 1806 storing software module 1807.

[0121] FIG. 19 is a block diagram showing an example configuration of a RAN node 2. Referring to FIG. 19, the RAN node 2 includes an RF transceiver 1901, a network interface 1903, a processor 1904, and a memory 1905. The RF transceiver 1901 performs analog RF signal processing for communication with UEs 1. The RF transceiver 1901 may include multiple transceivers. The RF transceiver 1901 is coupled to an antenna array 1902 and a processor 1904. The RF transceiver 1901 receives modulation symbol data from the processor 1904, generates a transmit RF signal, and provides the transmit RF signal to the antenna array 1902. The RF transceiver 1901 also generates a baseband receive signal based on the receive RF signal received by the antenna array 1902 and provides the baseband receive signal to the processor 1904. The RF transceiver 1901 may include an analog beamformer circuit for beamforming. The analog beamformer circuit may include, for example, multiple phase shifters and multiple power amplifiers.

[0122] The network interface 1903 is used to communicate with network nodes (e.g., other RAN nodes, and control and forwarding nodes of the core network), and may include, for example, a network interface card (NIC) compliant with the IEEE 802.3 series.

[0123] The processor 1904 performs digital baseband signal processing (data plane processing) and control plane processing for wireless communication. The processor 1904 may include multiple processors. For example, the processor 1904 may include a modem processor (e.g., a Digital Signal Processor (DSP)) that performs digital baseband signal processing and a protocol stack processor (e.g., a CPU or MPU) that performs control plane processing. The processor 1904 may include a digital beamformer module for beamforming. The digital beamformer module may include a MIMO encoder and a precoder.

[0124] The memory 1905 is configured by a combination of volatile memory and non-volatile memory. The volatile memory is, for example, SRAM or DRAM, or a combination thereof. The non-volatile memory is, for example, MROM, EEPROM, flash memory, or a hard disk drive, or any combination thereof. The memory 1905 may include storage located remotely from the processor 1904. In this case, the processor 1904 may access the memory 1905 via the network interface 1903 or another I / O interface.

[0125] The memory 1905 may store one or more software modules (computer programs) 1906 containing instructions and data for processing by the RAN node 2. In some implementations, the processor 1904 may be configured to read and execute the software modules 1906 from the memory 1905 to perform the processing of the RAN node 2 described in one or more of the embodiments.

[0126] It should be noted that the control plane processing and operations performed by the RAN node 2 described in the above embodiment can be realized by elements other than the RF transceiver 1901 and the antenna array 1902, namely the processor 1904 and the memory 1905 storing the software module 1906.

[0127] Figure 20 is a block diagram showing an example configuration of the RAN controller 3. In the example of Figure 20, the RAN controller 3 is implemented as a computer system. The computer system includes one or more processors 2010, a memory 2020, and a mass storage 2030, which communicate with each other via a bus 2070. The one or more processors 2010 may include, for example, a CPU or a graphics processing unit (GPU), or both. The computer system may also include other devices such as one or more output devices 2040, one or more input devices 2050, and one or more peripherals 2060. The one or more peripherals 2060 may include a modem, a network adapter, or any combination thereof.

[0128] One or both of the memory 2020 and mass storage 2030 may include a computer-readable medium having stored thereon one or more sets of instructions, which may be located partially or completely in memory within the one or more processors 2010. These instructions, when executed in the one or more processors 2010, cause the one or more processors 2010 to provide the functionality of the RAN controller 3 described in the embodiments above.

[0129] As described with reference to Figures 18, 19, and 20, each of the processors included in the UE 1, the RAN node 2, and the RAN controller 3 according to the above-described embodiments can execute one or more programs including instructions for causing a computer to perform the algorithms described with reference to the drawings. The programs include instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The programs may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disk (DVD), Blu-ray disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage, or other magnetic storage device. The programs may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0130] The above-described embodiments are merely examples of application of the technical ideas obtained by the inventors of the present invention. In other words, the technical ideas are not limited to the above-described embodiments, and various modifications are possible.

[0131] For example, some or all of the above embodiments may also be described as, but are not limited to, the following appendices. Some or all of the elements (e.g., configurations and functions) described in appendices directed to devices (e.g., wireless terminals, RAN nodes, information processing systems) may naturally also be described as appendices directed to methods and programs. For example, some or all of the elements described in appendices 2-17, which are dependent on appendices 1-17, may also be described as appendices dependent on appendices 18 and 19, due to the same dependency relationship as appendices 2-17. Similarly, some or all of the elements described in appendices 21-39, which are dependent on appendices 21-39, may also be described as appendices dependent on appendices 40 and 42, due to the same dependency relationship as appendices 21-39. Some or all of the elements described in any appendice may be applicable to various hardware, software, recording means for recording software, systems, and methods.

[0132] (Supplementary Note 1) A wireless terminal comprising: means for receiving a reporting configuration of assistance information from a network; and means for transmitting the assistance information to the network, wherein the assistance information includes at least one of first information and second information, the first information including one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information including at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting configuration. (Supplementary Note 2) The wireless terminal according to Supplementary Note 1, wherein the first signal beam and the one or more second signal beams are included in a second set of multiple beams used as inputs for beam prediction of a first set of multiple beams. (Supplementary Note 3) The wireless terminal according to Supplementary Note 2, wherein the first signal beam is a best reference signal beam having the best wireless quality among a plurality of reference signal beams measured by the wireless terminal, and the one or more second signal beams are one or more reference signal beams included in the plurality of reference signal beams and different from the best reference signal beam. (Supplementary Note 4) The wireless terminal according to Supplementary Note 2 or 3, wherein the assistance information is used in post-processing of a result of the beam prediction. (Supplementary Note 5) The wireless terminal according to Supplementary Note 4, wherein the post-processing includes selecting one or more beams from the first set obtained by the beam prediction. (Supplementary Note 6) The wireless terminal according to any one of Supplements 2 to 4, wherein the beam prediction is performed by inference using a trained artificial intelligence or machine learning model, and the second set is used as input for the inference by the trained artificial intelligence or machine learning model.(Supplementary Note 7) The wireless terminal according to any one of Supplements 1 to 6, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam. (Supplementary Note 8) The wireless terminal according to Supplementary Note 1, wherein the first signal beam is included in a second set of beams used as input of an artificial intelligence or machine learning model for beam prediction of a first set of beams, and the one or more second signal beams are included in the first set, and the second set is a subset of the first set or different from the first set. (Supplementary Note 9) The wireless terminal according to Supplementary Note 8, wherein the first signal beam is a best reference signal beam having best wireless quality among a plurality of reference signal beams measured by the wireless terminal, and the one or more second signal beams are one or more beams each having a beamwidth narrower than the beamwidth of each of the plurality of reference signal beams. (Supplementary Note 10) The wireless terminal according to Supplementary Note 8 or 9, wherein the assistance information is used for training the artificial intelligence or machine learning model. (Supplementary Note 11) The wireless terminal according to any one of Supplements 1 and 8 to 10, wherein the first signal beam is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam, and each of the one or more second signal beams is a Channel State Information (CSI) Reference Signal (CSI-RS) beam.(Supplementary Note 12) The wireless terminal of Supplementary Note 1, wherein the first signal beam is included in a second set of beams used as input of an artificial intelligence or machine learning model for beam prediction of a first set of beams, and the one or more second signal beams are included in the second set, and each of the one or more second signal beams is a beam transmitted at a time instance different from that at which the first signal beam is transmitted, with the same beamforming weight applied to the first signal beam. (Supplementary Note 13) The wireless terminal of Supplementary Note 12, wherein the first signal beam is a best reference signal beam having the best wireless quality among a plurality of reference signal beams measured by the wireless terminal. (Supplementary Note 14) The wireless terminal of Supplementary Note 12 or 13, wherein the assistance information is used for training the artificial intelligence or machine learning model. (Supplementary Note 15) The radio terminal according to any one of Supplements 1 and 12 to 14, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam. (Supplementary Note 16) The radio terminal according to any one of Supplements 1 to 15, wherein the reporting configuration includes information for the radio terminal to determine which of the first information and the second information needs to be reported. (Supplementary Note 17) The radio terminal according to any one of Supplements 1 to 16, wherein the reporting configuration includes information indicating the threshold.(Supplementary Note 18) A method performed by a wireless terminal, comprising: receiving a reporting configuration for assistance information from a network; and transmitting the assistance information to the network; wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; and the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting configuration. (Supplementary Note 19) A program causing a computer to perform a method for a wireless terminal, the method comprising: receiving a reporting setting for assistance information from a network; and transmitting the assistance information to the network; the assistance information including at least one of first information and second information; the first information including one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; and the second information including at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting setting.and receiving the assistance information from the wireless terminal, the assistance information including at least one of first information and second information, the first information including one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information including at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting configuration. (Supplementary Note 21) The radio access network node according to Supplementary Note 20, wherein the first signal beam and the one or more second signal beams are included in a second set of multiple beams used as inputs for beam prediction of a first set of multiple beams. (Supplementary Note 22) The radio access network node according to Supplementary Note 21, wherein the first signal beam is a best reference signal beam having the best radio quality among a plurality of reference signal beams measured by the radio terminal, and the one or more second signal beams are one or more reference signal beams included in the plurality of reference signal beams and different from the best reference signal beam. (Supplementary Note 23) The radio access network node according to Supplementary Note 21 or 22, wherein the assistance information is used in post-processing of a result of the beam prediction. (Supplementary Note 24) The radio access network node according to Supplementary Note 23, wherein the post-processing includes selecting one or more beams from the first set obtained by the beam prediction. (Supplementary Note 25) The radio access network node according to any one of Supplements 21 to 24, wherein the beam prediction is performed by inference using a trained artificial intelligence or machine learning model, and the second set is used as input for the inference by the trained artificial intelligence or machine learning model.(Supplementary Note 26) The radio access network node according to Supplementary Note 25, further comprising means for performing the inference using the artificial intelligence or machine learning model and post-processing a result of the beam prediction using the assistance information. (Supplementary Note 27) The radio access network node according to any one of Supplements 20 to 26, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam. (Supplementary Note 28) The radio access network node according to Supplementary Note 20, wherein the first signal beam is included in a second set of beams used as an input of an artificial intelligence or machine learning model for beam prediction of a first set of beams, and the one or more second signal beams are included in the first set, and the second set is a subset of the first set or different from the first set. (Supplementary Note 29) The radio access network node according to Supplementary Note 28, wherein the first signal beam is a best reference signal beam having the best radio quality among a plurality of reference signal beams measured by the radio terminal, and the one or more second signal beams are one or more beams each having a beamwidth narrower than the beamwidth of each of the plurality of reference signal beams. (Supplementary Note 30) The radio access network node according to Supplementary Note 28 or 29, wherein the assistance information is used for training the artificial intelligence or machine learning model. (Supplementary Note 31) The radio access network node according to Supplementary Note 30, further comprising means for performing the training of the artificial intelligence or machine learning model.(Supplementary Note 32) The radio access network node according to any one of Supplements 20 and 28 to 31, wherein the first signal beam is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam, and each of the one or more second signal beams is a Channel State Information (CSI) Reference Signal (CSI-RS) beam. (Supplementary Note 33) The radio access network node according to Supplementary Note 20, wherein the first signal beam is included in a second set of beams used as an input of an artificial intelligence or machine learning model for beam prediction of a first set of beams, the one or more second signal beams are included in the second set, and each of the one or more second signal beams is a beam transmitted at a time instance different from that at which the first signal beam is transmitted, with the same beamforming weight applied as that applied to the first signal beam. (Supplementary Note 34) The radio access network node according to Supplementary Note 33, wherein the first signal beam is a best reference signal beam having the best radio quality among a plurality of reference signal beams measured by the radio terminal. (Supplementary Note 35) The radio access network node according to Supplementary Note 33 or 34, wherein the assistance information is used for training the artificial intelligence or machine learning model. (Supplementary Note 36) The radio access network node according to Supplementary Note 35, further comprising means for performing the training of the artificial intelligence or machine learning model. (Supplementary Note 37) The radio access network node according to any one of Supplements 20 and 33 to 36, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam.(Supplementary Note 38) The radio access network node according to any one of Supplementary Notes 20 to 37, wherein the reporting configuration includes information for the radio terminal to determine whether the first information or the second information needs to be reported. (Supplementary Note 39) The radio access network node according to any one of Supplementary Notes 20 to 38, wherein the reporting configuration includes information indicating the threshold. (Supplementary Note 40) A method performed by a radio access network node, comprising: transmitting a reporting setting for assistance information to a radio terminal; and receiving the assistance information from the radio terminal, wherein the assistance information includes at least one of first information and second information, wherein the first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the radio terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the radio terminal, and wherein the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting setting. (Supplementary Note 41) A program causing a computer to perform a method for a radio access network node, comprising: transmitting a reporting setting for assistance information to a radio terminal; and receiving the assistance information from the radio terminal, wherein the assistance information includes at least one of first information and second information, the first information including one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the radio terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the radio terminal, and the second information including at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting setting.(Supplementary Note 42) An information processing system comprising: means for acquiring assistance information; means for performing beam prediction for a first set of beams by inference using a trained artificial intelligence or machine learning model using measurement results of a second set of beams as input; and means for selecting one or more beams from the first set based on the assistance information, wherein the assistance information includes at least one of first information and second information, the first information including one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information including at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold, and the first signal beam and the one or more second signal beams are included in the second set. (Supplementary Note 43) The information processing system according to Supplementary Note 42, wherein the first signal beam is a best reference signal beam having the best wireless quality among a plurality of reference signal beams measured by the wireless terminal, and the one or more second signal beams are one or more reference signal beams included in the plurality of reference signal beams and different from the best reference signal beam. (Supplementary Note 44) The information processing system according to Supplementary Note 42 or 43, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam. (Supplementary Note 45) The information processing system according to any one of Supplements 42 to 44, wherein the beam prediction is beam prediction in the spatial domain. (Supplementary Note 46) The information processing system according to any one of Supplements 42 to 45, wherein the information processing system is mounted on the wireless terminal.(Supplementary Note 47) The information processing system according to any one of Supplements 42 to 45, wherein the information processing system is arranged in a radio access network node that communicates with the radio terminal via an air interface. (Supplementary Note 48) The information processing system according to any one of Supplements 42 to 45, wherein the plurality of means provided by the information processing system are arranged in one or more computers in a network connected to the radio access network node that communicates with the radio terminal via an air interface. (Supplementary Note 49) The information processing system according to any one of Supplements 42 to 45, wherein the plurality of means provided by the information processing system are distributed between the radio terminal and a network connected to be able to communicate with the radio terminal via an air interface. (Supplementary Note 50) A method performed by an information processing system, comprising: acquiring assistance information; performing beam prediction for a first set of beams by inference using a trained artificial intelligence or machine learning model using measurement results of a second set of beams as input; and selecting one or more beams from the first set based on the assistance information, wherein the assistance information includes at least one of first information and second information, the first information including one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information including at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold, and the first signal beam and the one or more second signal beams are included in the second set.(Supplementary Note 51) A program causing a computer to perform a method comprising: acquiring assistance information; performing beam prediction for a first set of beams by inference using a trained artificial intelligence or machine learning model using measurement results of a second set of beams as input; and selecting one or more beams from the first set based on the assistance information; wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold; and the first signal beam and the one or more second signal beams are included in the second set. (Supplementary Note 52) An information processing system comprising: means for acquiring assistance information; and means for training, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam prediction for a first set of beams based on measurement results of a second set of beams; wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold; the first signal beam is included in the second set; and the one or more second signal beams are included in the first set; and the second set is a subset of the first set or is different from the first set.(Supplementary Note 53) The information processing system according to Supplementary Note 52, wherein the first signal beam is a best reference signal beam having the best wireless quality among a plurality of reference signal beams measured by the wireless terminal, and the one or more second signal beams are one or more beams each having a beamwidth narrower than the beamwidth of each of the plurality of reference signal beams. (Supplementary Note 54) The information processing system according to Supplementary Note 52 or 53, wherein the first signal beam is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam, and each of the one or more second signal beams is a Channel State Information (CSI) Reference Signal (CSI-RS) beam. (Supplementary Note 55) The information processing system according to any one of Supplements 52 to 54, wherein the beam prediction is beam prediction in the spatial domain. (Supplementary Note 56) A method performed by an information processing system, comprising: acquiring assistance information; and training an artificial intelligence or machine learning model, using training data including the assistance information, that performs beam prediction for a first set of beams based on measurement results of a second set of beams; wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold; the first signal beam is included in the second set; and the one or more second signal beams are included in the first set; and the second set is a subset of the first set or is different from the first set.(Supplementary Note 57) A program causing a computer to perform a method comprising: acquiring assistance information; and training an artificial intelligence or machine learning model, using training data including the assistance information, that performs beam prediction for a first set of beams based on measurement results for a second set of beams; wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold; the first signal beam is included in the second set; the one or more second signal beams are included in the first set; and the second set is a subset of the first set or is different from the first set.(Supplementary Note 58) A system comprising: means for acquiring assistance information; and means for training, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam prediction for a first set of beams based on measurement results of a second set of beams, wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold; the first signal beam is included in the second set; and the one or more second signal beams are included in the second set. An information processing system, wherein each of the one or more second signal beams is a beam transmitted at a different time instance from that at which the first signal beam is transmitted, with the same beamforming weight applied to the first signal beam. (Supplementary Note 59) The information processing system according to Supplementary Note 58, further comprising: means for predicting the first set by inputting an input data set including measurement results of reception quality of multiple beams included in the second set and the one or more parameters into an artificial intelligence or machine learning model trained by the training means. (Supplementary Note 60) The information processing system according to Supplementary Note 58 or 59, wherein the first signal beam is a best reference signal beam having the best wireless quality among multiple reference signal beams measured by the wireless terminal.(Supplementary Note 61) The information processing system described in any one of Supplementary Notes 58 to 60, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam. (Supplementary Note 62) A method is provided for causing a computer to perform a method comprising: acquiring assistance information; and training, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam prediction for a first set of beams based on measurement results for a second set of beams; wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold; the first signal beam is included in the second set; and the one or more second signal beams are included in the second set. A method performed by an information processing system, wherein each of the one or more second signal beams is a beam transmitted at a different time instance than the first signal beam, with the same beamforming weights applied to the first signal beam.(Supplementary Note 63) A method for implementing a ... Program.

[0133] This application claims priority based on Japanese Patent Application No. 2024-020526, filed February 14, 2024, the disclosure of which is incorporated herein in its entirety by reference.

[0134] 1 UE 2 RAN node 3 RAN controller 4 Network 201 CU 211, 212 DU 231-235 TRP 241-243 Cell 1803 Baseband processor 1804 Application processor 1806 Memory 1807 Modules 1904 Processor 1905 Memory 1906 Modules 2010 Processor 2020 Memory 2030 Mass storage

Claims

1. A wireless terminal comprising: means for receiving a reporting setting for assistance information from a network; and means for transmitting the assistance information to the network, wherein the assistance information includes at least one of first information and second information, wherein the first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting setting.

2. The wireless terminal of claim 1, wherein the first signal beam and the one or more second signal beams are included in a second set of beams used as inputs for beam prediction of a first set of beams.

3. The wireless terminal of claim 2, wherein the first signal beam is a best reference signal beam having the best wireless quality among a plurality of reference signal beams measured by the wireless terminal, and the one or more second signal beams are one or more reference signal beams included in the plurality of reference signal beams and different from the best reference signal beam.

4. The wireless terminal according to claim 2 or 3, wherein the assistance information is used in post-processing of the beam prediction results.

5. The wireless terminal of claim 4, wherein said post-processing includes selecting one or more beams from said first set obtained by said beam prediction.

6. A wireless terminal as described in any one of claims 2 to 4, wherein the beam prediction is performed by inference using a trained artificial intelligence or machine learning model, and the second set is used as input for the inference using the trained artificial intelligence or machine learning model.

7. A wireless terminal according to any one of claims 1 to 6, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam.

8. The wireless terminal of claim 1, wherein the first signal beam is included in a second set of beams used as input for an artificial intelligence or machine learning model for beam prediction of a first set of beams, and the one or more second signal beams are included in the first set, and the second set is a subset of the first set or is different from the first set.

9. A wireless terminal as described in claim 8, wherein the first signal beam is the best reference signal beam having the best wireless quality among multiple reference signal beams measured by the wireless terminal, and the one or more second signal beams are one or more beams each having a beamwidth narrower than the beamwidth of each of the multiple reference signal beams.

10. The wireless terminal of claim 8 or 9, wherein the assistance information is used for training the artificial intelligence or machine learning model.

11. A wireless terminal as described in any one of claims 1 and 8 to 10, wherein the first signal beam is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam, and each of the one or more second signal beams is a Channel State Information (CSI) Reference Signal (CSI-RS) beam.

12. The wireless terminal of claim 1, wherein the first signal beam is included in a second set of beams used as input for an artificial intelligence or machine learning model for beam prediction of the first set of beams, the one or more second signal beams are included in the second set, and each of the one or more second signal beams is a beam that is transmitted at a different time instance than the first signal beam, with the same beamforming weights applied as those applied to the first signal beam.

13. The wireless terminal according to claim 12, wherein the first signal beam is a best reference signal beam having the best wireless quality among a plurality of reference signal beams measured by the wireless terminal.

14. The wireless terminal of claim 12 or 13, wherein the assistance information is used for training the artificial intelligence or machine learning model.

15. A wireless terminal as described in any one of claims 1 and 12 to 14, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam.

16. A wireless terminal according to any one of claims 1 to 15, wherein the reporting configuration includes information for the wireless terminal to determine whether the first information or the second information needs to be reported.

17. The wireless terminal according to any one of claims 1 to 16, wherein the reporting configuration includes information indicating the threshold value.

18. A method performed by a wireless terminal, comprising: receiving an assistance information reporting configuration from a network; and transmitting the assistance information to the network, wherein the assistance information includes at least one of first information and second information, wherein the first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting configuration.

19. A program causing a computer to perform a method for a wireless terminal, the method comprising: receiving a reporting setting for assistance information from a network; and transmitting the assistance information to the network, the assistance information including at least one of first information and second information, the first information including one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information including at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting setting.

20. A radio access network node comprising: means for transmitting a reporting setting of assistance information to a wireless terminal; and means for receiving the assistance information from the wireless terminal, wherein the assistance information includes at least one of first information and second information, wherein the first information includes one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting setting.

21. The radio access network node of claim 20, wherein the first signal beam and the one or more second signal beams are included in a second set of beams used as input for beam prediction of a first set of beams.

22. A radio access network node as described in claim 21, wherein the first signal beam is a best reference signal beam having the best radio quality among a plurality of reference signal beams measured by the radio terminal, and the one or more second signal beams are one or more reference signal beams included in the plurality of reference signal beams and different from the best reference signal beam.

23. A radio access network node according to claim 21 or 22, wherein the assistance information is used in post-processing of the beam prediction results.

24. A radio access network node according to claim 23, wherein the post-processing comprises selecting one or more beams from the first set obtained by the beam prediction.

25. A radio access network node according to any one of claims 21 to 24, wherein the beam prediction is performed by inference using a trained artificial intelligence or machine learning model, and the second set is used as input for the inference using the trained artificial intelligence or machine learning model.

26. The radio access network node of claim 25, further comprising means for performing the inference using the artificial intelligence or machine learning model and post-processing the results of the beam prediction using the assistance information.

27. A radio access network node according to any one of claims 20 to 26, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam.

28. A radio access network node as described in claim 20, wherein the first signal beam is included in a second set of beams that is used as input for an artificial intelligence or machine learning model for beam prediction of a first set of beams, and the one or more second signal beams are included in the first set, and the second set is a subset of the first set or is different from the first set.

29. A radio access network node as described in claim 28, wherein the first signal beam is the best reference signal beam having the best radio quality among multiple reference signal beams measured by the radio terminal, and the one or more second signal beams are one or more beams each having a beamwidth narrower than the beamwidth of each of the multiple reference signal beams.

30. A radio access network node according to claim 28 or 29, wherein the assistance information is used for training the artificial intelligence or machine learning model.

31. A radio access network node according to claim 30, further comprising means for performing said training of said artificial intelligence or machine learning model.

32. A radio access network node as claimed in any one of claims 20 and 28 to 31, wherein the first signal beam is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam, and each of the one or more second signal beams is a Channel State Information (CSI) Reference Signal (CSI-RS) beam.

33. The radio access network node of claim 20, wherein the first signal beam is included in a second set of beams used as input for an artificial intelligence or machine learning model for beam prediction of the first set of beams, and the one or more second signal beams are included in the second set, and each of the one or more second signal beams is a beam that is transmitted at a different time instance than the first signal beam, with the same beamforming weights applied as those applied to the first signal beam.

34. The radio access network node according to claim 33, wherein the first signal beam is a best reference signal beam having the best radio quality among a plurality of reference signal beams measured by the radio terminal.

35. A radio access network node according to claim 33 or 34, wherein the assistance information is used for training the artificial intelligence or machine learning model.

36. A radio access network node according to claim 35, further comprising means for performing said training of said artificial intelligence or machine learning model.

37. A radio access network node according to any one of claims 20 and 33 to 36, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam.

38. A radio access network node according to any one of claims 20 to 37, wherein the reporting configuration includes information for the radio terminal to determine whether the first information or the second information needs to be reported.

39. A radio access network node according to any one of claims 20 to 38, wherein the reporting configuration includes information indicating the threshold value.

40. A method performed by a radio access network node, comprising: transmitting an assistance information reporting configuration to a wireless terminal; and receiving the assistance information from the wireless terminal, wherein the assistance information includes at least one of first information and second information, wherein the first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception of a first signal beam by the wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting configuration.

41. A program causing a computer to perform a method for a radio access network node, the method comprising: sending a reporting setting for assistance information to a radio terminal; and receiving the assistance information from the radio terminal, the assistance information including at least one of first information and second information, the first information including one or more parameters each indicating a correlation or similarity between a first channel estimated based on reception of a first signal beam by the radio terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the radio terminal, and the second information including at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a threshold determined based on the reporting setting.

42. An information processing system comprising: means for obtaining assistance information; means for performing beam prediction for a first set of beams by inference using a trained artificial intelligence or machine learning model using measurement results of a second set of beams as input; and means for selecting one or more beams from the first set based on the assistance information, wherein the assistance information includes at least one of first information and second information, the first information including one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception by a wireless terminal of a first signal beam and a respective one of one or more second channels estimated based on reception by the wireless terminal of one or more second signal beams, and the second information including at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold, and the first signal beam and the one or more second signal beams are included in the second set.

43. The information processing system of claim 42, wherein the first signal beam is a best reference signal beam having the best wireless quality among a plurality of reference signal beams measured by the wireless terminal, and the one or more second signal beams are one or more reference signal beams included in the plurality of reference signal beams and different from the best reference signal beam.

44. An information processing system as described in claim 42 or 43, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam.

45. An information processing system according to any one of claims 42 to 44, wherein the beam prediction is a beam prediction in the spatial domain.

46. ​​The information processing system according to any one of claims 42 to 45, wherein the information processing system is installed in the wireless terminal.

47. An information processing system according to any one of claims 42 to 45, wherein the information processing system is located in a radio access network node that communicates with the wireless terminal over an air interface.

48. An information processing system according to any one of claims 42 to 45, wherein the means provided by the information processing system are located in one or more computers in a network connected to a radio access network node that communicates with the wireless terminal over an air interface.

49. An information processing system according to any one of claims 42 to 45, wherein the multiple means provided by the information processing system are distributed between the wireless terminal and a network communicatively connected to the wireless terminal via an air interface.

50. A method performed by an information processing system, comprising: obtaining assistance information; performing beam predictions for a first set of beams by inference using a trained artificial intelligence or machine learning model using measurements of a second set of beams as input; and selecting one or more beams from the first set based on the assistance information, wherein the assistance information includes at least one of first information and second information, wherein the first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception by a wireless terminal of a first signal beam and a respective one of one or more second channels estimated based on reception by the wireless terminal of one or more second signal beams, and the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold, and wherein the first signal beam and the one or more second signal beams are included in the second set.

51. A program causing a computer to perform a method comprising: obtaining assistance information; performing beam predictions for a first set of beams by inference using a trained artificial intelligence or machine learning model using measurement results of a second set of beams as input; and selecting one or more beams from the first set based on the assistance information; wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold; and the first signal beam and the one or more second signal beams are included in the second set.

52. An information processing system comprising: means for acquiring assistance information; and means for training, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam prediction for a first set of beams based on measurement results of a second set of beams, wherein the assistance information includes at least one of first information and second information, wherein the first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold, wherein the first signal beam is included in the second set, and the one or more second signal beams are included in the first set, and the second set is a subset of the first set or is different from the first set.

53. An information processing system as described in claim 52, wherein the first signal beam is the best reference signal beam having the best wireless quality among multiple reference signal beams measured by the wireless terminal, and the one or more second signal beams are one or more beams each having a beamwidth narrower than the beamwidth of each of the multiple reference signal beams.

54. An information processing system as described in claim 52 or 53, wherein the first signal beam is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam, and each of the one or more second signal beams is a Channel State Information (CSI) Reference Signal (CSI-RS) beam.

55. An information processing system according to any one of claims 52 to 54, wherein the beam prediction is a beam prediction in the spatial domain.

56. A method performed by an information processing system, comprising: acquiring assistance information; and training, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam prediction for a first set of beams based on measurement results for a second set of beams, wherein the assistance information includes at least one of first information and second information, wherein the first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal, and the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold, wherein the first signal beam is included in the second set, and the one or more second signal beams are included in the first set, and the second set is a subset of the first set or is different from the first set.

57. A program causing a computer to perform a method comprising: acquiring assistance information; and training, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam prediction for a first set of beams based on measurement results for a second set of beams; wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold; the first signal beam is included in the second set; and the one or more second signal beams are included in the first set; and the second set is a subset of the first set or is different from the first set.

58. A system comprising: means for acquiring assistance information; and means for training, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam prediction for a first set of beams based on measurement results for a second set of beams, wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold; the first signal beam is included in the second set; the one or more second signal beams are included in the second set; and each of the one or more second signal beams is a beam that is transmitted at a different time instance from that at which the first signal beam is transmitted, with the same beamforming weight applied as that applied to the first signal beam. Information processing system.

59. The information processing system of claim 58, further comprising means for predicting the first set by inputting an input data set including measurement results of reception quality of multiple beams included in the second set and the one or more parameters into an artificial intelligence or machine learning model trained by the training means.

60. An information processing system according to claim 58 or 59, wherein the first signal beam is the best reference signal beam having the best wireless quality among a plurality of reference signal beams measured by the wireless terminal.

61. An information processing system as described in any one of claims 58 to 60, wherein each of the first signal beam and the one or more second signal beams is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam or a Channel State Information (CSI) Reference Signal (CSI-RS) beam.

62. A method is provided for causing a computer to perform a method comprising: obtaining assistance information; and training, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam predictions for a first set of beams based on measurements of a second set of beams, wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception by a wireless terminal of a first signal beam and a respective one of one or more second channels estimated based on reception by the wireless terminal of one or more second signal beams; the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold; the first signal beam is included in the second set; and the one or more second signal beams are included in the second set. A method performed by an information processing system, wherein each of the one or more second signal beams is a beam transmitted at a different time instance than the first signal beam, with the same beamforming weights applied to the first signal beam.

63. A program comprising: acquiring assistance information; and training, using training data including the assistance information, an artificial intelligence or machine learning model that performs beam prediction for a first set of beams based on measurement results of a second set of beams, wherein the assistance information includes at least one of first information and second information; the first information includes one or more parameters each indicative of a correlation or similarity between a first channel estimated based on reception of a first signal beam by a wireless terminal and a respective one of one or more second channels estimated based on reception of one or more second signal beams by the wireless terminal; the second information includes at least one identifier of at least one second signal beam for which the corresponding parameter exceeds a predetermined threshold; the first signal beam is included in the second set; the one or more second signal beams are included in the second set; and each of the one or more second signal beams is a beam that is transmitted at a different time instance from that at which the first signal beam is transmitted, with the same beamforming weight applied as that applied to the first signal beam.

Images