Mechanisms for beam prediction

Abstract

Example embodiments of the present disclosure relate to mechanisms for beam prediction. A first apparatus receives, from a second apparatus, a configuration for a group-based beam report. The configuration includes first information regarding a first set of beams for measurements associated with a first TRP and a second set of beams for measurements associated with a second TRP, and second information regarding a third set of beams for predictions associated with the first TRP and a fourth set of beams for predictions associated with the second TRP. The first apparatus performs measurements of the first set of beams and the second set of beams. The first apparatus determines, using an AI / ML model, one or more predicted uplink beam pairs based on measurement results of the measurements. The first apparatus transmits, to the second apparatus, a report associated with the one or more predicted uplink beam pairs.

Description

Cross-references to related applications

[0001] This application claims priority and benefit to U.S. Provisional Application No. 63 / 733567, filed December 13, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] Various exemplary embodiments of this disclosure generally relate to the telecommunications field, and more particularly to methods, apparatuses, devices, and computer-readable storage media for beam prediction. Background Technology

[0003] Due to the tremendous success of artificial intelligence (AI) / machine learning (ML) technologies, AI / ML research projects have been discussed in the 3rd Generation Partnership Project (3GPP), which can refer to user equipment (UE) side models and network (NW) side models. For example, AI / ML-based beam prediction can be performed. Summary of the Invention

[0004] In a first aspect of this disclosure, a first apparatus is provided. The first apparatus includes: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus to: receive a configuration for a group-based beam report from a second apparatus, wherein the configuration includes first information and second information, the first information relating to a first beam set for measurements associated with a first transmit receive point (TRP) and a second beam set for measurements associated with a second TRP, the second information relating to a third beam set for predictions associated with the first TRP and a fourth beam set for predictions associated with the second TRP, and the configuration further includes at least one associated identifier. At least one associated identifier includes at least one of the following: antenna configuration of a first TRP, antenna configuration of a second TRP, or path loss reference for uplink transmission; performing a first measurement on a first beam set and a second measurement on a second beam set; determining one or more predicted uplink beam pairs using an artificial intelligence / machine learning (AI / ML) model based on the measurement results of the first and second measurements, each predicted uplink beam pair including a first beam from a third beam set and a second beam from a fourth beam set; and transmitting a report associated with one or more predicted uplink beam pairs to a second device.

[0005] In a second aspect of this disclosure, a second apparatus is provided. The second apparatus includes: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus to: transmit to a first apparatus a configuration for group-based beam reports, wherein the configuration includes first information and second information, the first information relating to a first beam set for measurements associated with a first transmit receiving point (TRP) and a second beam set for measurements associated with a second TRP, the second information relating to a predicted third beam set associated with the first TRP and a predicted fourth beam set associated with the second TRP, and the configuration further includes at least one associated identifier, the at least one associated identifier including at least one of: an antenna configuration of the first TRP, an antenna configuration of the second TRP, or a path loss reference for uplink transmission; and receive from the first apparatus a report associated with one or more predicted uplink beam pairs, wherein the one or more predicted uplink beam pairs are determined using an artificial intelligence / machine learning (AI / ML) model, each predicted uplink beam pair including a first beam from the third beam set and a second beam from the fourth beam set.

[0006] In a third aspect of this disclosure, an apparatus is provided. The apparatus includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to: determine an input to an artificial intelligence / machine learning (AI / ML) model for predicting uplink beam pairs; determine an output of the AI / ML model for predicting uplink beam pairs by applying the input to the AI / ML model for predicting uplink beam pairs; and determine one or more predicted uplink beam pairs based on the output of the AI / ML model for predicting uplink beam pairs, each predicted uplink beam pair including a first beam for a first transmit receiver point (TRP) and a second beam for a second TRP.

[0007] In a fourth aspect of this disclosure, a method is provided. The method includes: receiving, at a first device, a configuration of receiving a group-based beam report from a second device, wherein the configuration includes first information and second information, the first information relating to a first beam set for measurements associated with a first transmit receiving point (TRP) and a second beam set for measurements associated with a second TRP, the second information relating to a predicted third beam set associated with the first TRP and a predicted fourth beam set associated with the second TRP, and the configuration further including at least one associated identifier, the at least one associated identifier including at least one of: an antenna configuration of the first TRP, an antenna configuration of the second TRP, or a path loss reference for uplink transmission; performing a first measurement on the first beam set and a second measurement on the second beam set; determining one or more predicted uplink beam pairs using an artificial intelligence / machine learning (AI / ML) model based on the measurement results of the first and second measurements, each predicted uplink beam pair including a first beam from the third beam set and a second beam from the fourth beam set; and transmitting a report associated with the predicted one or more uplink beam pairs to the second device.

[0008] In a fifth aspect of this disclosure, a method is provided. The method includes: transmitting, from a second device to a first device, a configuration for group-based beam reports, wherein the configuration includes first information and second information, the first information relating to a first beam set for measurements associated with a first transmit receiving point (TRP) and a second beam set for measurements associated with a second TRP, the second information relating to a predicted third beam set associated with the first TRP and a predicted fourth beam set associated with the second TRP, and the configuration further including at least one associated identifier, the at least one associated identifier including at least one of: an antenna configuration of the first TRP, an antenna configuration of the second TRP, or a path loss reference for uplink transmission; and receiving from the first device a report associated with one or more predicted uplink beam pairs, wherein the one or more predicted uplink beam pairs are determined using an artificial intelligence / machine learning (AI / ML) model, each predicted uplink beam pair including a first beam from the third beam set and a second beam from the fourth beam set.

[0009] In a sixth aspect of this disclosure, a method is provided. The method includes: determining input to an artificial intelligence / machine learning (AI / ML) model for predicting uplink beam pairs; determining an output of the AI / ML model for predicting uplink beam pairs by applying the input to the AI / ML model for predicting uplink beam pairs; and determining one or more predicted uplink beam pairs based on the output of the AI / ML model for predicting uplink beam pairs, each predicted uplink beam pair including a first beam for a first transmit receiving point (TRP) and a second beam for a second TRP.

[0010] In a seventh aspect of this disclosure, a first device is provided. The first device includes: components for receiving a configuration for a group-based beam report from a second device, wherein the configuration includes first information and second information, the first information relating to a first beam set for measurements associated with a first transmit receiving point (TRP) and a second beam set for measurements associated with a second TRP, and the second information relating to a predicted third beam set associated with the first TRP and a predicted fourth beam set associated with the second TRP; components for performing a first measurement on the first beam set and a second measurement on the second beam set, and the configuration further includes at least one associated identifier, the at least one associated identifier including at least one of the following: antenna configuration of the first TRP, antenna configuration of the second TRP, or path loss reference for uplink transmission; components for determining one or more predicted uplink beam pairs using an artificial intelligence / machine learning (AI / ML) model based on the measurement results of the first and second measurements, each predicted uplink beam pair including a first beam from the third beam set and a second beam from the fourth beam set; and components for transmitting a report associated with one or more predicted uplink beam pairs to the second device.

[0011] In an eighth aspect of this disclosure, a second apparatus is provided. The second apparatus includes: means for transmitting a configuration for group-based beam reports to a first apparatus, wherein the configuration includes first information and second information, the first information relating to a first beam set for measurements associated with a first transmit receiving point (TRP) and a second beam set for measurements associated with a second TRP, the second information relating to a predicted third beam set associated with the first TRP and a predicted fourth beam set associated with the second TRP, and the configuration further including at least one associated identifier, the at least one associated identifier including at least one of: an antenna configuration of the first TRP, an antenna configuration of the second TRP, or a path loss reference for uplink transmission; and means for receiving reports from the first apparatus associated with one or more predicted uplink beam pairs, wherein the one or more predicted uplink beam pairs are determined using an artificial intelligence / machine learning (AI / ML) model, each predicted uplink beam pair including a first beam from the third beam set and a second beam from the fourth beam set.

[0012] In a ninth aspect of this disclosure, an apparatus is provided. The apparatus includes: means for determining input to an artificial intelligence / machine learning (AI / ML) model for predicting uplink beam pairs; means for determining an output of the AI / ML model for predicting uplink beam pairs by applying the input to the AI / ML model; and means for determining one or more predicted uplink beam pairs based on the output of the AI / ML model, each predicted uplink beam pair including a first beam for a first transmit receiver point (TRP) and a second beam for a second TRP.

[0013] In a tenth aspect of this disclosure, a computer-readable medium is provided. The computer-readable medium includes instructions stored thereon for causing a device to perform at least the method according to any one of the fourth, fifth, or sixth aspects.

[0014] It should be understood that the summary portion is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0015] Some exemplary embodiments will now be described with reference to the accompanying drawings, in which: Figure 1 An example communication environment in which example embodiments of the present disclosure may be implemented is shown; Figure 2 A schematic diagram of multiple transmit receiver points (TRP) operation is shown; Figure 3 Signaling diagrams for beam prediction according to some example embodiments of the present disclosure are shown; Figure 4 Schematic diagrams show different combinations of two panels for simultaneous transmission and simultaneous reception; Figure 5 A schematic diagram of an AI / ML model for spatial domain beampair prediction is shown, according to some example embodiments of the present disclosure; Figure 6 Signaling flows for beam prediction according to some example embodiments of this disclosure are shown; Figure 7 A flowchart is shown illustrating a method implemented at a first device according to some exemplary embodiments of the present disclosure; Figure 8 A flowchart is shown illustrating a method implemented at a second device according to some example embodiments of the present disclosure; Figure 9 A flowchart is shown illustrating a method implemented at an apparatus according to some example embodiments of the present disclosure; Figure 10 A simplified block diagram of a device suitable for implementing example embodiments of the present disclosure is shown; and Figure 11 A block diagram of an example computer-readable medium according to some example embodiments of the present disclosure is shown.

[0016] Throughout the accompanying drawings, the same or similar reference numerals denote the same or similar elements. Detailed Implementation

[0017] The principles of this disclosure will now be described with reference to some exemplary embodiments. It should be understood that these embodiments are described for illustrative purposes only and to assist those skilled in the art in understanding and implementing this disclosure, and are not intended to imply any limitation on the scope of this disclosure. The embodiments described herein can be implemented in various ways other than those described below.

[0018] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0019] References to "an embodiment," "embodiment," "example embodiment," etc., in this disclosure indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment includes that particular feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Moreover, when a particular feature, structure, or characteristic is described in connection with an embodiment, whether explicitly described or not, it is believed that its influence on such feature, structure, or characteristic in conjunction with other embodiments is within the knowledge of those skilled in the art.

[0020] It should be understood that although the terms “first,” “second,” etc., may be used before the noun(s) herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another, and they do not restrict the order of the noun(s). For example, without departing from the scope of the exemplary embodiments, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0021] As used herein, “at least one of the following: ” and “at least one of ” and similar expressions, wherein the list of two or more elements is connected by “and” or “or”, means at least any one of these elements, or at least any two or more of these elements, or at least all of these elements.

[0022] As used herein, unless explicitly stated otherwise, the execution step “in response to A” does not indicate that the step is performed immediately after “A” occurs, but may include one or more intermediate steps.

[0023] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments. As used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It will also be understood that the terms “comprising,” “including,” “having,” “possessing,” “containing,” and / or “covering,” as used herein, specify the presence of the stated features, elements, and / or components, but do not exclude the presence or addition of one or more other features, elements, components, and / or combinations thereof.

[0024] As used in this disclosure, the term "circuit" may refer to one or more or all of the following: (a) Hardware circuit implementation only (e.g., implemented with purely analog and / or digital circuits), and (b) Combinations of hardware circuitry and software, such as (if applicable): (i) A combination of (multiple) analog and / or digital hardware circuits and software / firmware, and (ii) Any part of a hardware processor(s) having software (including (multiple) digital signal processors, software, and (multiple) memories, which work together to enable a device (such as a mobile phone or server) to perform various functions), and (c) The operation requires software (e.g., firmware) for the operation of (multiple) hardware circuits and / or (multiple) processors, such as (multiple) microprocessors or parts thereof, but the software may be absent when the operation does not require the software.

[0025] This definition of "circuit" applies to all use of the term in this application (including in any claim). As another example, as used in this application, the term "circuit" also covers only hardware circuitry, or a processor (or multiple processors), or portions of hardware circuitry or processors and their accompanying software and / or firmware implementations. For example, where applicable to a particular claim element, the term "circuit" also covers baseband integrated circuits or processor integrated circuits for mobile devices or similar integrated circuits in servers, cellular network devices, or other computing or network devices.

[0026] As used herein, the term "communication network" refers to a network that conforms to any suitable communication standard, such as New Radio (NR), Long Term Evolution (LTE), LTE-A Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), Narrowband Internet of Things (NB-IoT), etc. Furthermore, communication between terminal devices and network devices in a communication network can be performed according to any suitable generated communication protocol, including but not limited to: first-generation (1G), second-generation (2G), 2.5G, 2.75G, third-generation (3G), fourth-generation (4G), 4.5G, fifth-generation (5G), 5.5G, sixth-generation (6G) communication protocols and / or any other currently known or to be developed in the future. Embodiments of this disclosure can be applied to a variety of communication systems. Given the rapid development in communications, there will naturally be future types of communication technologies and systems that can implement this disclosure. The scope of this disclosure should not be limited to the aforementioned systems only.

[0027] As used herein, the term "network device" refers to a node in a communications network through which terminal devices access the network and receive services. Depending on the terminology and technology applied, a network device can refer to a base station (BS) or access point (AP), such as a Node B (NodeB or NB), an evolved Node B (eNodeB or eNB), an NR NB (also known as a gNB), a Remote Radio Unit (RRU), a Radio Head (RH), a Remote Radio Head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low-power node (such as a femtosecond or picosecond), a non-terrestrial network (NTN) or non-terrestrial network device (such as satellite network device, low Earth orbit (LEO) satellite, and geostationary Earth orbit (GEO) satellite), an aircraft network device, etc. In some example embodiments, the Radio Access Network (RAN) split architecture includes a centralized unit (CU) and a distributed unit (DU) at the IAB master node. The IAB node includes a mobile terminal (IAB-MT) portion (behaving similarly to a UE facing a parent node) and a DU portion of the IAB node (behaving similarly to a base station facing a next-hop IAB node).

[0028] The term "terminal device" refers to any terminal device capable of wireless communication. As an example and not a limitation, a terminal device may also be referred to as a communication device, user equipment (UE), user station (SS), portable user station, mobile station (MS), or access terminal (AT). Terminal devices can include, but are not limited to, mobile phones, cellular phones, smartphones, Voice over IP (VoIP) phones, wireless local loop phones, tablets, wearable terminal devices, personal digital assistants (PDAs), portable computers, desktop computers, image capture terminal devices (such as digital cameras), gaming terminal devices, music storage and playback devices, in-vehicle wireless terminal devices, wireless endpoints, mobile stations, laptop embedded devices (LEEs), laptop devices (LMEs), USB dongles, smart devices, wireless client devices (CPEs), Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in the context of industrial and / or automated processing chains), consumer electronic devices, devices operating on commercial and / or industrial wireless networks, etc. The terminal device may also correspond to the mobile terminal (MT) portion of an IAB node (e.g., a relay node). In the following description, the terms "terminal device," "communication device," "terminal," "user equipment," and "UE" are used interchangeably.

[0029] As used herein, the terms “resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” can refer to any resource used to perform communication (e.g., communication between a terminal device and a network device), such as resources in the time domain, resources in the frequency domain, resources in the spatial domain, resources in the code domain, or any other combination of time, frequency, spatial, and / or code domain resources for implementing communication. In the following, unless explicitly stated otherwise, resources in both the frequency and time domains will be used as examples of transmission resources used to describe some exemplary embodiments of this disclosure. Note that the exemplary embodiments of this disclosure are equally applicable to other resources in other domains. As used herein, the term “transmitter receiving point (TRP)” can refer to a device / entity that transmits and receives radio signals. It refers to a component of a wireless network capable of both transmitting and receiving signals, which may be part of a base station or access point. In the context of 5G and advanced wireless systems, a TRP can involve multiple antenna elements arranged in an array to facilitate the transmission and reception of radio waves for communication purposes. TRPs play a crucial role in ensuring the coverage, capacity, and overall performance of a wireless network.

[0030] Figure 1 An example communication environment 100 in which exemplary embodiments of the present disclosure may be implemented is shown. In communication environment 100, multiple communication devices, including terminal device 110 and network device 120 (e.g., network devices 120-1 and 120-2, collectively referred to as "network device 120"), can communicate with each other. Figure 1 In the example, terminal device 110 can be a UE, and network devices 120-1 and 120-2 can be base stations.

[0031] It should be understood that Figure 1 The number of devices and their connections shown are for illustrative purposes only and do not imply any limitation. Communication environment 100 may include any suitable number of devices configured to implement the exemplary embodiments of this disclosure. Although not shown, it should be understood that one or more additional devices may be located in the serving cell of terminal device 110, and one or more additional cells may be deployed in communication environment 100. Note that although shown as a network device, network device 120 may be another device besides a network device. Although shown as a terminal device, terminal device 110 may be another device besides a terminal device.

[0032] In the following description, for illustrative purposes, some example embodiments are depicted in which terminal device 110 operates as a UE and network device 120 operates as a base station. However, in some example embodiments, the operations described in connection with the terminal device can be implemented at the network device or other devices, and the operations described in connection with the network device can be implemented at the terminal device or other devices.

[0033] In some example embodiments, the transmission direction from network device 120 to terminal device 110 is referred to as the downlink (DL), and the transmission direction from terminal device 110 to network device 120 is referred to as the uplink (UL). In the DL, network device 120 is a transmitting (TX) device (or transmitter), and terminal device 110 is a receiving (RX) device (or receiver). In the UL, terminal device 110 is a TX device (or transmitter), and network device 120 is an RX device (or receiver).

[0034] Communication in communication environment 100 can be implemented according to any suitable communication protocol(s), including but not limited to cellular communication protocols, wireless local area network communication protocols (such as IEEE 802.11), and / or any other currently known or to be developed in the future. Furthermore, communication can utilize any suitable wireless communication technology, including but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), Multiple Input Multiple Output (MIMO), Orthogonal Frequency Division Multiple Access (OFDM), Discrete Fourier Transform Extended OFDM (DFT-s-OFDM), and / or any other currently known or to be developed in the future.

[0035] As described above, AI / ML-based beam prediction is introduced. For example, AI / ML can be used for beam management. AI / ML-based beam management can include using AI / ML models to predict (multiple) optimal beams based on a finite set of measurements. Two sub-use cases for beam prediction can exist: spatial domain prediction and temporal domain prediction. In the spatial domain prediction sub-use case, beam prediction can be based on a finite set of measurements that does not contain any historical information. In the temporal domain prediction sub-use case, future beam prediction can be based on a finite set of measurements that includes historical information.

[0036] Furthermore, measurements and predictions can be based on two sets of beams: Set A, on which the predictions will be performed on the complete set of beams, and Set B, on which measurements of the beam sets are input into an AI / ML model (e.g., Layer 1 Reference Signal Received Power (L1-RSRP), etc.). Set B can be different from Set A (spatial and temporal predictions) or a subset of Set A (spatial and temporal predictions), or Set B can be the same as Set A (temporal predictions).

[0037] Version 19 (Rel-19) of the work item (WI) for AI / ML on the NR air interface based on AI / ML technology has been approved. For example, it supports the following aspects: (1) a general AI / ML framework for single-sided AI / ML models: signaling and protocol aspects of lifecycle management (LCM) to implement function and model (if appropriate) selection, activation, deactivation, switching, and fallback; (multiple) necessary signaling / mechanisms for LCM to facilitate model training, inference, performance monitoring, and data collection for both UE-side and NW-side models; signaling mechanisms applicable to functions / models; and (2) beam management - DL transmit (Tx) beam prediction for both UE-side and NW-side models, covering: spatial domain DL Tx beam prediction of beam Set A based on measurement results of beam Set B (“BM-Case 1”); temporal DL prediction of beam Set A based on historical measurement results of beam Set B. Tx beam prediction (“BM-Case 2”); specifying the necessary signaling / mechanisms to facilitate LCM operation specific to beam management use cases, if any; enabling methods to ensure consistency between training and inference regarding NW-side additional conditions (if identified) for inference at the UE. Furthermore, research objectives with corresponding checkpoints may include the necessity and details of model identification concepts and processes in the context of LCM; over-the-top (OTT) of core network (CN) / operation, administration and maintenance (OAM) / UE-side model training data: identifying the corresponding UE data collection for the FS_NR_AIML_Air research use case; and analyzing the UE data collection mechanisms identified during the FS_NR_AIML_Air research and the implications and limitations of each method; and model delivery / transmission, considering whether standardized solutions for delivery / transmission of (multiple) AI / ML models need to be considered, given that the identified solutions were identified at least during the FS_NR_AIML_Air research.

[0038] Furthermore, group-based beam reporting is proposed. Group-based beam reporting has been supported since NR Rel-15 and is further optimized in Rel-17 to support multi-TRP operation. The features of group-based beam reporting are summarized below: - Rel-15 group-based beam reporting allows the UE to report two beams that can be received simultaneously by the UE. The UE is unaware whether the two beams come from the same TRP or different TRPs.

[0039] - Rel-15 reports are valid for L1-RSRP or L1-Signal-to-Interference-plus-Noise Ratio (SINR) reports (with CSI-ReportConfig with reportQuantity set to 'CSI-RS Resource Indicator (cri)-RSRP', 'Synchronization Signal Block (ssb)-Index-RSRP', 'cri-RSRP-Capability[Set]Index', 'ssb-Index-RSRP-Capability[Set]Index', 'cri-SINR', 'ssb-Index-SINR', 'cri-SINR-Capability[Set]Index', or 'ssb-Index-SINR-Capability[Set]Index').

[0040] - Rel-17 group-based beam reporting allows a UE to report two groups of CSI-RS resource indicators (CRIs) or synchronization signal (SS) / physical broadcast channel (PBCH) block resource indicators (SSBRIs), selecting a channel state information (CSI-RS) or synchronization signal (SS) / physical broadcast channel (PBCH) block (SSB) from each of the two CSI resource sets configured for reporting, where the CSI-RS and / or SSB resources of each group can be received by the UE simultaneously. Here, the UE is aware of the beam-to-TRP association, and the beams reported in the beam group originate from different TRPs.

[0041] - Support Rel-17 group-based beam reporting (r17) by configuring two CSI resource sets for the UE. Otherwise, the number of configured CSI-RS resource sets is limited to one.

[0042] - Rel-17 reports are valid for L1-RSRP reports (with CSI-ReportConfig having reportQuantity set to 'cri-RSRP', 'ssb-Index-RSRP', 'cri-RSRP-Capability[Set]Index', or 'ssb-Index-RSRP-Capability[Set]Index').

[0043] In some cases, the UE is configured with CSI-ReportConfig, which has a higher-layer parameter reportQuantity set to 'cri-RSRP', 'ssb-Index-RSRP', 'cri-RSRP-Index', or 'ssb-Index-RSRP-Index'. Specifically, if the UE is configured with a higher-layer parameter groupBasedBeamReporting-v18 set to UL Only, the UE does not need to update measurements for more than 64 CSI-RS and / or SSB resources, and the UE should report in a single report instance nrofReportedGroups-r18 (if configured) two groups of CRIs or SSBRIs selected from each of the two CSI resource sets for the reporting settings, where the CSI-RS and / or SSB resources of each group can be applied to simultaneous transmission by the UE with spatial filters, which is limited by the UE's capabilities. In summary, for UL-only mode: each group consists of two CRIs or SSBRIs, where a CSI-RS or SSB is selected from each of the two CSI resource sets; the CSI-RS and / or SSB resources of each group can be used for simultaneous transmission with the spatial filter.

[0044] In frequency ranges (FR) 2 or FR3 (high-frequency portion, such as 10 GHz to 20 GHz), to support multi-TRP (m-TRP) operation, the UE can use multiple panels because beams can be received from different panels, thus facilitating simultaneous reception. For example... Figure 2As shown, not all beams are suitable for joint transmission toward UE 210. UE 210 can be configured with panels 1, 2, and 3. UE 210 can receive signals from beams P1 and P2 of TRP 220-1 using panel 1, and from beams Q1 and Q2 of TRP 220-2. When signals are received at the same panel (i.e., panel 1), UE 210 may not be able to simultaneously receive signals from beams Q3 and P1 (or #P2). In other words, there are not many opportunities in FR2 or FR3 (high frequency) where, unless the UE has different panels, the UE will be able to receive signals from two TRPs simultaneously, and therefore the benefit of scheduling transmissions for the network on two beams is questionable. This is addressed in Rel-17 group-based beam reporting, where beams are divided into two sets and reporting can be made for beam groups. However, the beams used by each TRP should follow beam refinement individually, and beam pairs (beam groups) can be reported after this beam refinement phase for each TRP. Each TRP must transmit a large number of reference signals, such as SSBs and CSI-RS, which leads to overhead issues because each beam is associated with a different SSB or CSI-RS resource.

[0045] Beam pair prediction can help reduce the frequency of measurement reporting because the UE can report the predicted output from a small set of measured beams; therefore, the NW does not need to configure the UE to report the complete set of beam measurements to the NW. During the training and inference phases, consistency between the AI / ML training and inference phases needs to be ensured. For example, in UL-only mode, when the predicted beam pair corresponds to two CRIs or SSBRIs of measurements from two CSI resource sets, there is a question of how to ensure the UE is likely in good channel condition, where the two CRIs or SSBRIs correspond to simultaneous UL transmissions. For UEs configured with the higher-layer parameter groupBasedBeamReporting-v18 set to UL-only, how the UE can select the optimal combination of panels remains open, where the optimal combination of panels can determine the simultaneous Tx corresponding to the CSI-RS or SSB from each of the two CSI resource sets for the reporting settings.

[0046] According to some example embodiments of this disclosure, a solution for beam prediction is provided. The terminal device measures a low number of beams corresponding to multiple UE panels. The terminal device then uses an AI / ML model with the measurement results as input to determine the optimal simultaneously transmitted beam pair. In this way, the terminal device does not need to report the complete set of beam measurements to the network device, thereby reducing overhead.

[0047] The exemplary embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0048] refer to Figure 3 This illustrates the signaling flow for beam prediction according to some example embodiments of this disclosure. For discussion purposes, reference will be made to... Figure 1 Discuss signaling flow 300, for example, by using terminal device 110 and network device 320. Network device 320 can be network device 120-1 or network device 120-2.

[0049] Terminal device 110 can transmit (3005) capability information to network device 320. That is, network device 320 can receive (3005) capability information from terminal device 110. The capability information can instruct terminal device 110 to support group-based beam reporting with uplink-only mode.

[0050] Network device 320 transmits (3010) a configuration for group-based beam reporting to terminal device 110. That is, terminal device 110 receives (3010) a configuration for group-based beam reporting from network device 320. For example, terminal device 110 may receive a CSI-report configuration to enable group-based beam reporting based on prediction.

[0051] The configuration includes first information regarding a first set of beams for measurements associated with a first TRP and a second set of beams for measurements associated with a second TRP. For example, the configuration may indicate a set of beams for measurements for the first TRP (e.g., Set B1) and another set of beams for measurements for the second TRP (e.g., Set B2). The configuration also includes second information regarding a third set of beams for predictions associated with the first TRP and a fourth set of beams for predictions associated with the second TRP. For example, the configuration may indicate a set of beams for predictions for the first TRP (e.g., Set A1) and another set of beams for predictions for the second TRP (e.g., Set A2). In some example embodiments, the first set of beams is a subset of the third set of beams. For example, Set B1 may be a subset of Set A1. Alternatively or additionally, the second set of beams is a subset of the fourth set of beams. For example, Set B2 may be a subset of Set A2.

[0052] In some example embodiments, to ensure consistency between training and inference of the UE-side model, associated identification information for the first / second / third / fourth beam sets is introduced during the training and inference phases. For example, the first information includes at least one of the following: codebooks for the first and second beam sets, beam shapes for the first and second beam sets, or the quality of the first and second beam sets. Furthermore, the second information includes at least one of the following: codebooks for the third and fourth beam sets, beam shapes for the third and fourth beam sets, or the quality of the third and fourth beam sets. In some other example embodiments, this configuration may also include one or more of the following: antenna configuration for the first TRP, antenna configuration for the second TRP, or path loss reference for uplink transmission. For example, information in the configuration that can be implicitly constructed using the associated ID includes: SetA1 / SetA2 / SetB1 / SetB2 codebook beams, SetA1 / SetA2 / SetB1 / SetB2 beam shapes, TRP antenna configuration, the quality of the DL Tx beam pairs used for UE-side beam prediction, and path loss reference for UL transmission. These can be considered as a condition for the UE to determine the Sounding Reference Signal (SRS) resource, where the path loss reference can be indicated by the structure or other information within the NW and associated ID. In some example embodiments, the beam shape may include narrow or wide beams. In some other example embodiments, the quality of the DL Tx beam pairs may include RSRP or Quality of Service (QoS).

[0053] In some example embodiments, network device 320 may transmit (3015) path loss reference information for uplink transmission to terminal device 110. That is, terminal device 110 may receive (3015) path loss reference information for uplink transmission from network device 320. For example, the path loss reference information may be transmitted via Radio Resource Control (RRC) signaling. Alternatively, the path loss reference information may be transmitted in a Media Access Control (MAC) control element (CE).

[0054] Network device 320 may transmit (3020) reference signals to terminal device 110. For example, terminal device 110 may receive (3020) measurement reference signals for Set B1 from a first TRP and for Set B2 from a second TRP. In some example embodiments, the measurement reference signals may include SSB. In some other example embodiments, the measurement reference signals may include CSI reference signals.

[0055] In some example embodiments, if terminal device 110 has the capability to (i) use two panels for simultaneous transmission and (ii) use two panels for simultaneous reception, wherein each UE panel has more than one antenna, then terminal device 110 needs to perform an assumption check / assumption determination to select the optimal combination corresponding to simultaneous transmission (Tx) of UL only. See below for reference. Figure 4 Describe example embodiments for determining the assumptions. In some example embodiments, the CSI-RS and / or SSB resources of each measurement RS resource set can be applied to simultaneous transmission with spatial filters (UL mode only).

[0056] Figure 4 Examples are shown of different combinations for simultaneous transmission with two antenna panels corresponding to TRP 400-1 and TRP 400-2, and different combinations for simultaneous reception with two antenna panels corresponding to TRP 400-1 and TRP 400-2. TRP 400-1 may be implemented at network device 120-1, and TRP 400-2 may be implemented at network device 120-2. In some example embodiments, terminal device 110 may determine N different combinations defining simultaneous transmission with two panels, where N is an integer and can be any suitable value. In some other example embodiments, terminal device 110 may determine Q different combinations defining simultaneous reception with two panels, where Q is an integer and can be any suitable value. Figure 4 As shown, combination 411 of two panels 401 and 402 and combination 421 of two panels 402 and 404 are used for simultaneous transmission. Combination 412 of two panels 401 and 404 and combination 422 of two panels 402 and 403 are used for simultaneous reception.

[0057] When terminal device 110 is configured with UL-only mode, it can use the following steps to determine hypotheses by using model training or inference for UL TX beams used for simultaneous multi-panel transmission.

[0058] Terminal device 110 may be assumed to be pre-configured with UL SRS resources, which have one or more UL SRS resource sets associated with different TRPs and using 'beam management'. Furthermore, terminal device 110 may be assumed to be pre-configured with UL power control values, such as the nominal RX power at panel 401 at each TRP.

[0059] Terminal device 110 can perform DL L1-RSRP measurements associated with different antenna panels from different TRPs 400-1 and 400-2 in different time instances, without being limited to simultaneous reception from different TRPs with different antenna panels. That is, terminal device 110 performs model training / inference for UL TX beampair prediction with UL-only mode independently of the UE's simultaneous multi-panel reception capability.

[0060] Terminal device 110 may use all or a selection of (where the selection may be based on N optimal L1-RSRP values ​​associated with different antenna panels, specific ground panels, or all antenna panels) measured L1-RSRP values ​​of SSB / NZP-CSI-RS resources (associated with SSB and / or non-zero power (NZP)-CSI-RS resources) as downlink path loss reference resources for determining “virtual” UL power control values ​​for pre-configured UL SRS resources. Here, “virtual” refers to the power control values ​​that the terminal device can use for UL SRS resources associated with different SRS resource sets when performing UL TX beam prediction for simultaneous multi-panel transmission.

[0061] Additionally, terminal device 110 can determine (3025) combinations of multiple receiving panels. For example, terminal device 110 can apply its simultaneous multi-panel transmission limitation to antenna panel selection for TX beam prediction (e.g., there are a total of four TX antenna panels, but only two of them can be used for simultaneous transmission). For example, terminal device 110 can determine combination 411 or combination 421. In some example embodiments, by utilizing the optimal combination of receiving panels, beam scanning processes (such as P1, P2, and P3) can ensure that terminal device 110 can use the best / optimal beam with respect to the best panel for UL-only mode.

[0062] Terminal device 110 can determine (3030) the uplink power control value for the uplink sounding reference signal resources. For example, when determining the “virtual” power control value, terminal device 110 can consider hardware implementation limitations affecting simultaneous multi-panel transmission, such as the implemented transmitter power amplifier (PA) architecture (i.e., whether one or more power amplifiers are associated with different TX antenna panels) and the TX power level of the PA. That is, for the uplink power control value, the amount of TX power budget available for each UL SRS resource set or across all UL SRS resource sets and resources can be considered.

[0063] Return to reference Figure 3Terminal device 110 performs (3035) a first measurement on the first beam set and a second measurement on the second beam set. For example, terminal device 110 can measure the RSRP of reference signals from the first beam set and the second beam set. As an example, terminal device 110 can measure the downlink L1-RSRP of at least two SSB / CSI-RS resource sets (Set B1 and Set B2).

[0064] In some example embodiments, terminal device 110 may determine (3040) one or more beam pairs for simultaneous transmission. For example, terminal device 110 may determine the first M beam pairs. Alternatively or additionally, terminal device 110 may determine the beam index of one or more beam pairs for simultaneous transmission.

[0065] Terminal device 110 can determine (3045) the inputs to the AI / ML model for uplink beampair prediction. In some example embodiments, DL beampair measurements (such as DL L1-RSRPs for Set B1 and Set B2) can be determined as inputs to the AI / ML model simultaneously. In some example embodiments, beam measurements that do not correspond to the RSRP of Set B1 for the first TRP are, for example, CRI_x1, CRI_xN, etc., and beam measurements that do not correspond to the RSRP of Set B2 for the second TRP are, for example, CRI_y4, CRI_y6, ..., CRI_yM. The two UL TX beampairs can be identified by terminal device 110 based on beam measurements (e.g., beampair, beam index).

[0066] In some example embodiments, the input to the AI / ML model may include UL SRS measurements based on UL L1-RSRP for one or more specific UL Tx antenna panels from a first TRP and a second TRP. For example, the first and second TRPs may perform UL SRS measurements and obtain UL SRS L1-RSRP values ​​corresponding to the UL SRS measurements. The first and second TRPs may then send the UL SRS L1-RSRP measurements to the terminal device 110. For SRS resources, the power control factor for SRS is considered as a condition when NW triggers SRS transmission.

[0067] In some example embodiments, the input to the AI / ML model may include DL measurements only. For example, the input to the AI / ML model may include a first downlink measurement result for a first beam set of measurements associated with a first TRP and a second downlink measurement result for a second beam set of measurements associated with a second TRP. As an example, at least beam-level measurements in the downlink (NON-simultaneous DL beampair measurements) are used at the model input, i.e., the DL L1-RSRP of SetB1 and the DL L1-RSRP of SetB2. Alternatively, the input to the AI / ML model may include beampair information for the first TRP and the second TRP, as well as the corresponding measurements. For example, the input to the AI / ML model may include at least beampair information and the corresponding measurements, such as, for non-simultaneous reception at terminal device 110, N optimal beampairs from two SSB resources or CSI-RS resources of two resource sets (Set B1 and Set B2) and the corresponding DL L1-RSRPs.

[0068] In some other example embodiments, the input to the AI / ML model may include DL measurements and UL measurements. For example, the input to the AI / ML model may include a first downlink measurement result for a first beam set of measurements associated with a first TRP and a second downlink measurement result for a second beam set of measurements associated with a second TRP, as well as a first uplink measurement result associated with the first TRP and a second uplink measurement result associated with the second TRP. In some example embodiments, the input to the AI / ML model may include at least beam-level measurements in the downlink (non-simultaneous DL beam pair measurements), wherein the non-simultaneous downlink measurements include DL L1-RSRP values ​​associated with SSB / NZP-CSI-RS resource pairs from two different TRPs (e.g., SSB / NZP-CSI-RS resources of Set B1 (corresponding to the first TRP) and SSB / NZP-CSI-RS resources of Set B2 (corresponding to the second TRP). Alternatively, the input to the AI / ML model may include at least beam-level measurements in the uplink, where the uplink measurements consist of UL L1-RSRP values ​​(measured by two gNB / TRPs) associated with UL SRS resource pairs, which are spatial quasi-co-located (QCL) type D, configured to match SSB and / or NZP-CSI-RS resource pairs as input values ​​for model training / inference for UL TX beam prediction. Alternatively, the input to the AI / ML model may include beam pair information for the first TRP and the second TRP, along with the corresponding measurements. For example, the input to the AI / ML model may include at least beam pair information and corresponding measurements, such as, for simultaneous reception at terminal device 110, N optimal beam pairs from two SSB or CSI-RS sets (Set B1 and Set B2) and their corresponding UL L1-RSRPs.

[0069] In some other example embodiments, the input to the AI / ML model may include UL-only measurements. For example, the input to the AI / ML model may include a first uplink measurement associated with a first TRP and a second uplink measurement associated with a second TRP. For example, the input to the AI / ML model may include at least beam-level measurements in the uplink, where the uplink measurements include UL L1-RSRP values ​​(measured by two gNB / TRPs) associated with a UL SRS resource pair, which is a spatial QCL-type D configured to match the used SSB and / or NZP-CSI-RS resource pair. In some example embodiments, the input to the AI / ML model may include beam pair information for the first TRP and the second TRP, and the corresponding measurements. For example, the input to the AI / ML model may include at least beam pair information and the corresponding measurements, such as, for non-simultaneous reception at terminal device 110, N optimal beam pairs from two SSB or CSI-RS sets (Set B1 and Set B2) and their corresponding UL L1-RSRPs.

[0070] In addition, the input to the AI / ML model may include additional information. For example, the additional information may include one or more receiver panel IDs. The additional information may also include the location of the terminal device 110.

[0071] Terminal device 110 can determine the output of the AI / ML model (3048) by applying the input of the AI / ML model. In some example embodiments, the output of the AI / ML model may include identification information of one or more predicted beam pairs. Alternatively or additionally, the output of the AI / ML model may include the RSRP of one or more predicted beam pairs. In other example embodiments, the output of the AI / ML model may also include probability values ​​of one or more predicted beam pairs.

[0072] In some example embodiments, the AI / ML model can be a convolutional neural network (CNN) model. For example, assuming SetB1 and Set B2 have an equal number of beams (N beams), the first layer of the neural network (NN) can take inputs including beam measurements such as: UL L1-RSRP values ​​(measured by two gNBs (such as network devices 120-1 and 120-2) / TRP) associated with UL SRS pairs having SSB and / or NZP-CSI-RS resource pairs; and CRI and RSRP measurements for each beam set (Set B1 and Set B2) on the CSI-RS resources and the identified best beam pair (e.g., (xi, yj) (i, j selected from (i = 1, ..., N), where N is the number of beams in SetB1 and Set B2)). The next layer of the CNN model can be a convolutional layer that extracts features from the input dataset. Then, activation layers can later add activation functions to the previous layer, where the activation function can be a rectified linear unit (RELU), hyperbolic tangent (Tanh), etc. CNN models can include pooling and flattening layers, where pooling layers can be used to reduce the volume, while flattening layers are used to map to a one-dimensional vector. The next layer can be a fully connected layer, and the last layer can be a softmax function to obtain a probability distribution over the set of model outputs. These probabilities can then be ranked, for example. Alternatively, the AI / ML model can be a deep reinforcement learning model.

[0073] Alternatively, the AI / ML model can be a feedforward neural network. Assuming Set B1 and Set B2 have an equal number of beams (N beams), the first layer of the neural network (NN) can take inputs including CRI and RSRP measurements (such as beam measurements) for each set of beams (Set B1 and Set B2) on the CSI-RS resources and the identified best beam pair (e.g., (xi, yj) (i, j selected from (i=1, ..., N), where N is the number of beams in Set B1 and Set B2)). The next layer is a block of neural networks (NN), where each NN block has multiple neurons. Each NN block can include fully connected layers, and the final layer can be a Softmax function to obtain the probability distribution over the set of model outputs. These probabilities can then be ranked, for example.

[0074] As another example, an AI / ML model can be a Long Short-Term Memory (LSTM) model. An LSTM architecture can have three parts: a forget gate, an input gate, and an output gate. In the first layer, assuming Set B1 and Set B2 have an equal number of beams (N beams), the forget gate can take an input (such as beam measurements) including the ULL1-RSRP value (measured by two gNB / TRPs) associated with UL SRS pairs having SSB and / or ZP-CSI-RS resource pairs; and CRI and RSRP measurements, which are for each set of beams (Set B1 and Set B2) for CSI-RS resources and the identified best beam pairs (e.g., (xi, yj) (i, j are selected from (i=1, ..., N), where N is the number of beams in Set B1 and Set B2)). The input at time instance t can be represented as Within the forgetting gate, it has a hidden state, in which... The equation for the forget gate represents the hidden state of a previous time instance. ),in This represents the weight matrix associated with the forget gate. This represents the cascading of the input and the hidden states of previous time instances. It's a deviation from the forgetting gate, and It is the sigmoid activation function. It can be included in the input gate. and activation function As shown below: )and ),in , These are the weight matrix and bias vector of the input gate, respectively. Then, the previous state can be obtained at time t ( Multiply by the forget gate, then include ,in It means according to the following Element-wise multiplication. In the output gate, ),in and These are the weight matrix and bias vector of the output gates. Then, the last function can be a softmax function to obtain the probability distribution over the set of model outputs. These probabilities can then be ranked, for example.

[0075] Figure 5A schematic diagram of an AI / ML model for spatial domain beampair prediction is shown according to some example embodiments of the present disclosure. For example, the output 530 of the AI / ML model 510 is obtained by applying input 520 to the AI / ML model 510. In some example embodiments, the AI / ML model 510 may be implemented using a CNN or a feedforward neural network. Alternatively, the AI / ML model 510 may be implemented using an LSTM model. In some other example embodiments, the AI / ML model may be a deep reinforcement learning model.

[0076] In some example embodiments, input 520 may include beam measurements for Set B1 and beam measurements for Set B2. The beam measurements for Set B1 include L1-RSRP_beam_x1 (and / or CRI_beam_x1), ..., L1-RSRP_beam_xN (and / or CRI_beam_xN), and the beam measurements for Set B2 include L1-RSRP_beam_y1 (and / or CRI_beam_y1), ..., L1-RSRP_beam_yN (and / or CRI_beam_yN). Alternatively or additionally, input 520 may include the top N best UL Tx beam pairs for simultaneous beam pair measurements (Set B1 to Set A1) and (Set B2 to Set A2), which may include, for example, the L1-RSRP (and / or the CRI of the UL Tx beam pair (xi, yj)), ..., the L1-RSRP (and / or the CRI of the Tx UL beam pair (xl, yN)). In some other example embodiments, input 520 may include UL SRS measurements from a first TRP (Set B1) including UL L1-RSRP_beam_x1 (and / or CRI_beam_x1), ..., UL L1-RSRP_beam_xN (and / or CRI_beam_xN), and from a second TRP (Set B2) including UL L1-RSRP_beam_y1 (and / or CRI_beam_y1), ..., UL L1-RSRP_beam_yN (and / or CRI_beam_yN). Input 520 may include UE panel IDs, such as Panel ID_M1, ..., Panel ID_MN. Note that input 520 may include any combination of the above inputs.

[0077] The output 530 of the AI / ML model 510 may include the predicted top K Tx beam pair IDs of the best UL from two CSI-RS sets (Set A1 and Set A2), for example, {predicted CRI_x1(PCRI_x1), predicted CRI_y2(PCRI_y2)}, ..., {predicted CRI_xN(PCRI_xN), predicted CRI_yN+1(PCRI_yN+1)}. The default value of K can be 1. Alternatively, the output 530 of the AI / ML model 510 may include the predicted UL RSRP of the top K beam pairs (beam pair IDs) of the best Tx from Set A1 and Set A2, for example, {predicted RSRP_x1 (PRSRP_x1), predicted RSRP_y2 (PRSRP_y2)}, ..., {predicted RSRP_xN (PRSRP_xN), predicted RSRP_yN+1 (PRSRP_yN+1)}. Furthermore, the output 530 of the AI / ML model 510 may include the probability values ​​of the top K beam pairs (beam pair IDs) of the best Tx from Set A1 and Set A2.

[0078] In some example implementations, the input and output of the AI / ML model reside in the same spatial domain. For instance, for time-domain UL Tx beampup prediction, the input and output can be the same as in the spatial domain, but the input can be historical measurements, and the predicted output can be in multiple future time instances. The input to the AI / ML model can be historical measurement data. For example, for UL SRS measurements, the historical data of the measurements may include UL SRS measurements based on historical L1-RSRP from Set B1 of the first TRP (e.g., {UL SRS L1-RSRP_beam_x1 (and / or CRI_beam_x1), ..., UL SRS L1-RSRP_beam_xN (and / or CRI_beam_xN)} from time tM, tM-1, ... t) and UL SRS measurements based on historical L1-RSRP from Set B2 of the second TRP (e.g., {UL SRS L1-RSRP_beam_y1 (and / or CRI_beam_y1), ..., UL SRS L1-RSRP_beam_yM (and / or CRI_beam_yM)} from time tM, tM-1, ... t).

[0079] In some other example embodiments, for other input parameters, they are the same as those for spatial domain UL Tx beampup prediction, but the inputs can be from historical measurements (e.g., from time tM, tM-1, ..., t). The model for time-domain UL Tx beampup prediction can be, for example, a transformer model, LSTM, autoencoder-decoder, etc.

[0080] Based on the measurement results of the first and second measurements, terminal device 110 uses an AI / ML model to determine (3050) one or more predicted uplink beam pairs. Each predicted uplink beam pair includes a first beam from a third beam set and a second beam from a fourth beam set. In some example embodiments, the predicted uplink beam pair may include at least one first beam from the third beam set and at least one second beam from the fourth beam set. For example, the predicted uplink beam pair may be, for instance, the first two predicted uplink beam pairs of a first TRP and the first two predicted uplink beam pairs of a second TRP.

[0081] Terminal device 110 transmits (3055) a report associated with one or more predicted uplink beam pairs to network device 120. That is, network device 120 may receive (3055) a report associated with one or more predicted uplink beam pairs. In some example embodiments, the report may include identification information for one or more predicted beam pairs. Alternatively or additionally, the report may include reference signal received power for one or more predicted beam pairs.

[0082] In some example embodiments, based on the measured DL L1-RSRP and the uplink power value associated with pre-configured UL SRS resources, terminal device 110 predicts the UL TX beam for simultaneous multi-panel transmission and reports the corresponding DL SSB and / or NZP-CSI-RS resources and downlink L1-RSRP values ​​associated with different TRPs. Alternatively, based on the measured DL L1-RSRP of SSB and / or NZP-CSI-RS resources at different TRPs, the indicated / configured UL L1-RSRP measured by UL SRS, and the uplink power value associated with pre-configured UL SRS resources, terminal device 110 predicts the UL TX beam for simultaneous multi-panel transmission and reports the corresponding DL SSB and / or NZP-CSI-RS resources and downlink L1-RSRP values ​​associated with different TRPs.

[0083] refer to Figure 6 This illustrates the signaling flow for beam prediction according to some example embodiments of this disclosure. For discussion purposes, reference will be made to... Figure 1The signaling flow 600 is discussed, for example, through the use of terminal device 110 and TRPs 620-1 and 620-2. TRP 620-1 can be implemented at network device 120-1, and TRP 620-2 can be implemented at network device 120-2. Terminal device 110 may include prediction model 611, measurement entity 612, UL entity 613, and DL entity 614.

[0084] Terminal device 110 can send (6005) capability indications to NW (with UL-only group-based beam reports), such as to TRP 620-1. TRP 620-1 can utilize group-based beam reports to configure (6010) CSI-ReportConfig and indicate to terminal device 110 the RS sets (Set B1 / B2) and (Set A1 / A2) for AI / ML UL Tx beam pairs (with structure-associated IDs in the NZP-CSI-RS-ResourceSet for measurements and the NZP-CSI-RS-ResourceSet for predictions). Optionally, if the path loss reference is not in the associated IDs, TRP 620-1 can send (6015) path loss references in RRC / MAC-CE.

[0085] Terminal device 110 can determine (6020) the use of the predictive model of CSI-ReporConfig. TRP 620-1 can use Set B1 to transmit (6025) the measured RS, and TRP 620-2 can use Set B2 to transmit (6030) the measured RS.

[0086] Terminal device 110 can determine (6035) the assumptions for simultaneous transmission (UL only). Terminal device 110 can also select the optimal combination of two panels for simultaneous transmission (UL only).

[0087] Terminal device 110 can perform beam measurements of (6040) RS SetB1 and SetB2. Terminal device 110 can determine the beam pairs used for simultaneous transmission (UL only).

[0088] Terminal device 110 can determine (6045) the input for beam measurement (e.g., the first M beam pairs and / or beam indices + DL L1-RSRP + UL SRS L1-RSRP). Terminal device 110 can perform (6050) UL group-based beam prediction (e.g., using the first M beam pairs and / or beam indices, as well as DL L1-RSRP and UL SRS L1-RSRP). Terminal device 110 can report (6055 and 6060) the predicted UL first K beam pair IDs (and / or predicted UL first K beam pair L1-RSRPs) to TRP 620-1 and / or TRP 620-2. The predicted UL first K beam pair IDs (and / or predicted UL first K beam pair L1-RSRPs) can be included in the CSI report.

[0089] Figure 7 A flowchart illustrating an example method 700 implemented at a first device according to some example embodiments of the present disclosure is shown. For example, method 700 can be implemented in... Figure 1 The terminal devices are implemented in 110 locations.

[0090] At block 710, the first device receives a configuration for group-based beam reports from the second device. This configuration includes first and second information: the first information pertains to a first beam set for measurements associated with a first transmit-receive point (TRP) and a second beam set for measurements associated with a second TRP; the second information pertains to a third beam set for predictions associated with the first TRP and a fourth beam set for predictions associated with the second TRP.

[0091] At frame 720, the first device performs a first measurement on the first beam set and a second measurement on the second beam set.

[0092] At box 730, the first device uses an artificial intelligence / machine learning (AI / ML) model to determine one or more predicted uplink beam pairs based on the measurement results of the first and second measurements. Each predicted uplink beam pair includes a first beam from a third beam set and a second beam from a fourth beam set.

[0093] At frame 740, the first device transmits a report to the second device that is associated with one or more predicted uplink beam pairs.

[0094] In some example embodiments, the report includes at least one of the following: identification information of one or more predicted beam pairs, or reference signal received power of one or more predicted beam pairs.

[0095] In some example embodiments, the first information includes at least one of the following: the codebook of the first beam set and the second beam set, the beam shape of the first beam set and the second beam set, or the quality of the first beam set and the second beam set, and wherein the second information includes at least one of the following: the codebook of the third beam set and the fourth beam set, the beam shape of the third beam set and the fourth beam set, or the quality of the third beam set and the fourth beam set.

[0096] In some example embodiments, the configuration also includes at least one associated identifier, which includes at least one of the following: antenna configuration of the first TRP, antenna configuration of the second TRP, or path loss reference for uplink transmission.

[0097] In some example embodiments, the inputs to the AI / ML model include at least one of the following: the measurement results of the first measurement and the second measurement, the identifier of the receiving panel of the first device, the location of the first device, the uplink probe reference signal measurement for the transmission panel from the first TRP, the uplink probe reference signal measurement for the transmission panel from the second TRP, or the uplink power control value.

[0098] In some example embodiments, method 700 further includes receiving path loss reference information for uplink transmission from the second device.

[0099] In some example embodiments, the path loss reference information for uplink transmission is received from the radio resource control configuration or media access control control element.

[0100] In some example embodiments, method 700 further includes: determining an uplink power control value for uplink probe reference signal resources.

[0101] In some example embodiments, method 700 further includes: determining a combination of multiple receiving panels for simultaneous transmission.

[0102] In some example embodiments, method 700 further includes: determining one or more beam pairs for simultaneous transmission.

[0103] In some example embodiments, the first beam set is a subset of the third beam set, and the second beam set is a subset of the fourth beam set.

[0104] In some example embodiments, the first device is a terminal device, and the second device is a network device.

[0105] Figure 8 A flowchart illustrating an example method 800 implemented at a second device according to some example embodiments of the present disclosure is shown. For example, method 800 can be implemented in... Figure 1Implemented at network device 120 (such as network device 120-1 and / or network device 120-2).

[0106] At block 810, the second device transmits a configuration for group-based beam reports to the first device. This configuration includes first and second information: the first information pertains to a first beam set for measurements associated with a first transmit-receive point (TRP) and a second beam set for measurements associated with a second TRP; the second information pertains to a third beam set for predictions associated with the first TRP and a fourth beam set for predictions associated with the second TRP.

[0107] At box 820, the second device receives a report from the first device associated with one or more predicted uplink beam pairs. The one or more predicted uplink beam pairs are determined using an artificial intelligence / machine learning (AI / ML) model, and each predicted uplink beam pair includes a first beam from a third beam set and a second beam from a fourth beam set.

[0108] In some example embodiments, the report includes at least one of the following: identification information of one or more predicted beam pairs, or reference signal received power of one or more predicted beam pairs.

[0109] In some example embodiments, the first information includes at least one of the following: the codebook of the first beam set and the second beam set, the beam shape of the first beam set and the second beam set, or the quality of the first beam set and the second beam set, and wherein the second information includes at least one of the following: the codebook of the third beam set and the fourth beam set, the beam shape of the third beam set and the fourth beam set, or the quality of the third beam set and the fourth beam set.

[0110] In some example embodiments, the configuration also includes at least one associated identifier, which includes at least one of the following: antenna configuration of the first TRP, antenna configuration of the second TRP, or path loss reference for uplink transmission.

[0111] In some example embodiments, method 800 further includes transmitting path loss reference information for uplink transmission to the first device.

[0112] In some example embodiments, the path loss reference information for uplink transmission is transmitted in the radio resource control configuration or media access control control element.

[0113] In some example embodiments, the first beam set is a subset of the third beam set, and the second beam set is a subset of the fourth beam set.

[0114] In some example embodiments, the first device is a terminal device, and the second device is a network device.

[0115] Figure 9 A flowchart illustrating an example method 900 implemented at a device according to some example embodiments of the present disclosure is shown. For example, method 900 can be implemented at a device. Figure 1 Implemented at terminal device 110 and / or network device 120 (such as network device 120-1 and / or network device 120-2).

[0116] At box 910, the device determines the input to the predicted artificial intelligence / machine learning (AI / ML) model for the uplink beam pair.

[0117] At box 920, the device determines the output of the AI / ML model for uplink beampair prediction by applying the input to the AI / ML model for uplink beampair prediction.

[0118] At box 930, the device determines one or more predicted uplink beam pairs based on the output of an AI / ML model for predicting uplink beam pairs, each predicted uplink beam pair including a first beam for a first transmit receiver point (TRP) and a second beam for a second TRP.

[0119] In some example embodiments, the input to the AI / ML model includes at least one of the following: a first downlink measurement result for a first beam set of measurements associated with a first TRP and a second downlink measurement result for a second beam set of measurements associated with a second TRP, a first uplink measurement result associated with a first TRP and a second uplink measurement result associated with a second TRP, or beam pair information for the first TRP and the second TRP and the corresponding measurements.

[0120] In some example embodiments, the input to the AI / ML model also includes at least one of the following: the identifier of the receiving panel of the terminal device, the location of the terminal device, or the uplink power control value.

[0121] In some example embodiments, the output of the AI / ML model includes at least one of the following: identification information of one or more predicted beam pairs, or reference signal received power of one or more predicted beam pairs.

[0122] In some example implementations, the output of the AI / ML model also includes probability values ​​for one or more predicted beam pairs.

[0123] In some example implementations, the input and output of the AI / ML model are in the same spatial domain.

[0124] In some example implementations, the input to the AI / ML model is historical measurement data.

[0125] In some example embodiments, method 900 further includes: determining an uplink power control value for uplink probe reference signal resources.

[0126] In some example embodiments, the device is pre-configured with uplink sounding reference resources, which have one or more sets of uplink sounding reference resources for beam management associated with different transmit receiving points.

[0127] In some example embodiments, the pre-configured uplink sounding reference signal resources are configured with uplink power control values.

[0128] In some example embodiments, method 900 further includes applying simultaneous multi-panel transmission constraints to antenna panel selection for uplink beampair prediction.

[0129] In some example embodiments, the device is a terminal device or a network device.

[0130] In some example embodiments, the device is a terminal device that functions as a user device.

[0131] Note, reference Figures 3 to 9 The described exemplary embodiments can be implemented individually or in any suitable combination. For example, exemplary embodiments described with reference to one accompanying drawing can be combined. Alternatively or additionally, exemplary embodiments described with reference to different accompanying drawings can be combined.

[0132] In some example embodiments, a first means capable of performing any of the methods in method 700 (e.g., Figure 1 The terminal device 110 may include components for performing the corresponding operations of method 700. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit or software module. The first device may be implemented as or included in... Figure 1 In terminal device 110.

[0133] In some example embodiments, the first device includes: components for receiving configurations for group-based beam reports from a second device, wherein the configuration includes first and second information, the first information relating to a first beam set for measurements associated with a first transmit receiving point (TRP) and a second beam set for measurements associated with a second TRP, the second information relating to a predicted third beam set associated with the first TRP and a predicted fourth beam set associated with the second TRP, and the configuration further includes at least one associated identifier, the at least one associated identifier including at least one of: antenna configuration of the first TRP, antenna configuration of the second TRP, or path loss reference for uplink transmission; components for performing a first measurement on the first beam set and a second measurement on the second beam set; components for determining one or more predicted uplink beam pairs using an artificial intelligence / machine learning (AI / ML) model based on the measurement results of the first and second measurements, each predicted uplink beam pair including a first beam from the third beam set and a second beam from the fourth beam set; and components for transmitting reports associated with one or more predicted uplink beam pairs to the second device.

[0134] In some example embodiments, the report includes at least one of the following: identification information of one or more predicted beam pairs, or reference signal received power of one or more predicted beam pairs.

[0135] In some example embodiments, the first information includes at least one of the following: the codebook of the first beam set and the second beam set, the beam shape of the first beam set and the second beam set, or the quality of the first beam set and the second beam set, and wherein the second information includes at least one of the following: the codebook of the third beam set and the fourth beam set, the beam shape of the third beam set and the fourth beam set, or the quality of the third beam set and the fourth beam set.

[0136] In some example embodiments, the inputs to the AI / ML model include at least one of the following: the measurement results of the first measurement and the second measurement, the identifier of the receiving panel of the first device, the location of the first device, the uplink probe reference signal measurement for the transmission panel from the first TRP, the uplink probe reference signal measurement for the transmission panel from the second TRP, or the uplink power control value.

[0137] In some example embodiments, the first device further includes a component for receiving path loss reference information for uplink transmission from the second device.

[0138] In some example embodiments, the first device further includes a component for determining an uplink power control value for uplink probe reference signal resources.

[0139] In some example embodiments, the first device further includes a component for determining a combination of multiple receiving panels for simultaneous transmission.

[0140] In some example embodiments, the first device further includes a component for determining one or more beam pairs for simultaneous transmission.

[0141] In some example embodiments, the first beam set is a subset of the third beam set, and the second beam set is a subset of the fourth beam set.

[0142] In some example embodiments, the first device is a terminal device, and the second device is a network device.

[0143] In some example embodiments, a second means capable of performing any of the methods in method 800 (e.g., Figure 1 The network device 120 in the process may include components for performing the corresponding operations of method 800. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit or software module. The second device may be implemented as or included in... Figure 1 Among the network devices in 120.

[0144] In some example embodiments, the second device includes: components for transmitting a configuration for group-based beam reports to the first device, wherein the configuration includes first information and second information, the first information relating to a first beam set for measurements associated with a first transmit receiving point (TRP) and a second beam set for measurements associated with a second TRP, the second information relating to a predicted third beam set associated with the first TRP and a predicted fourth beam set associated with the second TRP, and the configuration further includes at least one associated identifier, the at least one associated identifier including at least one of: antenna configuration of the first TRP, antenna configuration of the second TRP, or path loss reference for uplink transmission; and components for receiving reports from the first device associated with one or more predicted uplink beam pairs, wherein the one or more predicted uplink beam pairs are determined using an artificial intelligence / machine learning (AI / ML) model, each predicted uplink beam pair including a first beam from the third beam set and a second beam from the fourth beam set.

[0145] In some example embodiments, the report includes at least one of the following: identification information of one or more predicted beam pairs, or reference signal received power of one or more predicted beam pairs.

[0146] In some example embodiments, the first information includes at least one of the following: the codebook of the first beam set and the second beam set, the beam shape of the first beam set and the second beam set, or the quality of the first beam set and the second beam set, and wherein the second information includes at least one of the following: the codebook of the third beam set and the fourth beam set, the beam shape of the third beam set and the fourth beam set, or the quality of the third beam set and the fourth beam set.

[0147] In some example embodiments, the second device further includes a component for transmitting path loss reference information for uplink transmission to the first device.

[0148] In some example embodiments, the first beam set is a subset of the third beam set, and the second beam set is a subset of the fourth beam set.

[0149] In some example embodiments, the first device is a terminal device, and the second device is a network device.

[0150] In some example embodiments, the apparatus capable of performing any method 900 (e.g., Figure 1 The terminal device 110 and / or network device 120 may include components for performing the corresponding operations of method 900. These components can be implemented in any suitable form. For example, the components can be implemented in a circuit or software module. The device can be implemented as or included in... Figure 1 In the terminal device 110 and / or network device 120.

[0151] In some example embodiments, the apparatus includes: means for determining input to an artificial intelligence / machine learning (AI / ML) model for predicting uplink beam pairs; means for determining output of the AI / ML model for predicting uplink beam pairs by applying the input to the AI / ML model for predicting uplink beam pairs; and means for determining one or more predicted uplink beam pairs based on the output of the AI / ML model for predicting uplink beam pairs, each predicted uplink beam pair including a first beam for a first transmit receiver point (TRP) and a second beam for a second TRP.

[0152] In some example embodiments, the input to the AI / ML model includes at least one of the following: a first downlink measurement result for a first beam set of measurements associated with a first TRP and a second downlink measurement result for a second beam set of measurements associated with a second TRP, a first uplink measurement result associated with a first TRP and a second uplink measurement result associated with a second TRP, or beam pair information for the first TRP and the second TRP and the corresponding measurements.

[0153] In some example embodiments, the input to the AI / ML model also includes at least one of the following: the identifier of the receiving panel of the terminal device, the location of the terminal device, or the uplink power control value.

[0154] In some example embodiments, the output of the AI / ML model includes at least one of the following: identification information of one or more predicted beam pairs, or reference signal received power of one or more predicted beam pairs.

[0155] In some example implementations, the output of the AI / ML model also includes probability values ​​for one or more predicted beam pairs.

[0156] In some example implementations, the input and output of the AI / ML model are in the same spatial domain.

[0157] In some example implementations, the input to the AI / ML model is historical measurement data.

[0158] In some example embodiments, the apparatus also includes components for determining uplink power control values ​​for uplink probe reference signal resources.

[0159] In some example embodiments, the device is pre-configured with uplink sounding reference resources, which have one or more sets of uplink sounding reference resources for beam management associated with different transmit receiving points.

[0160] In some example embodiments, the pre-configured uplink sounding reference signal resources are configured with uplink power control values.

[0161] In some example embodiments, the device also includes components for applying simultaneous multi-panel transmission limits to antenna panel selection for uplink beampair prediction.

[0162] In some example embodiments, the device is a terminal device or a network device.

[0163] In some example embodiments, the device is a terminal device that functions as a user device.

[0164] Figure 10 This is a simplified block diagram of a device 1000 suitable for implementing exemplary embodiments of the present disclosure. The device 1000 can be provided to implement a communication device, for example, as... Figure 1 The terminal device 110 or network device 120 shown. As shown, device 1000 includes one or more processors 1010, one or more memories 1020 coupled to processor 1010, and one or more communication modules 1040 coupled to processor 1010.

[0165] Communication module 1040 is used for bidirectional communication. Communication module 1040 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interface can represent any interface necessary for communication with other network elements. In some example embodiments, communication module 1040 may include at least one antenna.

[0166] As a non-limiting example, processor 1010 can be any type suitable for a local technology network and can include one or more of the following: general-purpose computer, special-purpose computer, microprocessor, digital signal processor (DSP), and processor based on a multi-core processor architecture. Device 1000 can have multiple processors, such as application-specific integrated circuit chips that are time-dependent on a clock synchronized with the main processor.

[0167] Memory 1020 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 1024, electrically programmable read-only memory (EPROM), flash memory, hard disk, miniature optical disc (CD), digital video disc (DVD), optical disc, laser disc, and other magnetic and / or optical storage. Examples of volatile memories include, but are not limited to, random access memory (RAM) 1022 and other volatile memories that will not be retained when power is lost.

[0168] Computer program 1030 includes computer-executable instructions that are executed by an associated processor 1010. The instructions of program 1030 may include instructions for performing operations / actions of some example embodiments of this disclosure. Program 1030 may be stored in memory (e.g., ROM 1024). Processor 1010 can perform any suitable actions and processes by loading program 1030 into RAM 1022.

[0169] The exemplary embodiments of this disclosure can be implemented by means of program 1030, so that device 1000 can execute as referenced. Figures 2 to 9 Any process discussed in this disclosure. Exemplary embodiments of this disclosure may also be implemented by hardware or a combination of software and hardware.

[0170] In some example embodiments, program 1030 may be tangibly contained in a computer-readable medium, which may be included in device 1000 (e.g., in memory 1020) or in other storage devices accessible to device 1000. Device 1000 may load program 1030 from the computer-readable medium into RAM 1022 for execution. In some example embodiments, the computer-readable medium may include any type of non-transitory storage medium, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. The term "non-transitory" as used herein refers to a limitation on the medium itself (i.e., tangible, not tactile) rather than a limitation on data storage persistence (e.g., RAM vs. ROM).

[0171] Figure 11 An example of a computer-readable medium 1100 is shown, which may be in the form of a CD, DVD, or other optical storage disc. The computer-readable medium 1100 has a program 1030 stored thereon.

[0172] Generally, the various embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of this disclosure are shown and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof, as non-limiting examples.

[0173] Some exemplary embodiments of this disclosure also provide at least one computer program product tangibly stored on a computer-readable medium (such as a non-transitory computer-readable medium). The computer program product includes computer-executable instructions (such as those included in a program module) that execute in a device on a target physical or virtual processor to perform any of the methods described above. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc., that perform a particular task or implement a particular abstract data type. In various embodiments, the functionality of a program module can be combined or split among program modules as needed. The machine-executable instructions for a program module can execute in a local device or a distributed device. In a distributed device, the program module can reside in both local storage media and remote storage media.

[0174] Program code used to perform the methods of this disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that, when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a stand-alone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0175] In the context of this disclosure, computer program code or related data may be carried by any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, etc.

[0176] Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable media can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination thereof. More specific examples of computer-readable storage media include electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable optical disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0177] Furthermore, although the operations are described in a specific order, this should not be construed as requiring that such operations be performed in the specific order shown or sequentially, or that all the operations shown be performed in order to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be considered as limiting the scope of this disclosure, but rather as a description of features that may be specific to particular embodiments. Unless explicitly stated otherwise, certain features described in the context of a single embodiment may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated otherwise, the various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0178] Although this disclosure has been described in language specific to structural features and / or methodological actions, it should be understood that the disclosure as defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as exemplary forms of implementing the claims.

[0179] Furthermore, the various implementations of this disclosure can be described with reference to the following terms, and their features can be combined in any reasonable manner.

[0180] Clause 1. A first means for communication, comprising: at least one processor; and at least one memory storing instructions, which, when executed by the at least one processor, cause the first means to: receive a configuration for a group-based beam report from a second means, wherein the configuration includes first information and second information, the first information relating to a first beam set for measurements associated with a first transmit receive point (TRP) and a second beam set for measurements associated with a second TRP, the second information relating to a third beam set for predictions associated with the first TRP and a fourth beam set for predictions associated with the second TRP, and the configuration further comprising at least one associated The at least one associated identifier includes at least one of the following: the antenna configuration of the first TRP, the antenna configuration of the second TRP, or a path loss reference for uplink transmission; performing a first measurement on the first beam set and a second measurement on the second beam set; based on the measurement results of the first and second measurements, using an artificial intelligence / machine learning (AI / ML) model to determine one or more predicted uplink beam pairs, each predicted uplink beam pair including a first beam from the third beam set and a second beam from the fourth beam set; and transmitting a report associated with the one or more predicted uplink beam pairs to the second device.

[0181] Clause 2. The first apparatus according to Clause 1, wherein the report includes at least one of the following: identification information of the one or more predicted beam pairs, or reference signal received power of the one or more predicted beam pairs.

[0182] Clause 3. The first apparatus according to Clause 1, wherein the first information includes at least one of the following: the codebooks of the first beam set and the second beam set, the beam shape of the first beam set and the second beam set, or the quality of the first beam set and the second beam set, and wherein the second information includes at least one of the following: the codebooks of the third beam set and the fourth beam set, the beam shape of the third beam set and the fourth beam set, or the quality of the third beam set and the fourth beam set.

[0183] Clause 4. The first device according to Clause 1, wherein the input of the AI / ML model includes at least one of the following: the measurement results of the first measurement and the second measurement, an identifier of the receiving panel of the first device, the location of the first device, an uplink probe reference signal measurement for the transmission panel from the first TRP, an uplink probe reference signal measurement for the transmission panel from the second TRP, or an uplink power control value.

[0184] Clause 5. The first apparatus according to Clause 1, wherein the first apparatus is configured to: receive from the second apparatus information for the path loss reference for the uplink transmission.

[0185] Clause 6. The first apparatus according to Clause 5, wherein the information for the path loss reference for the uplink transmission is received from a radio resource control configuration or media access control control element.

[0186] Clause 7. The first means according to Clause 1, wherein the first means is configured to: determine an uplink power control value for uplink sounding reference signal resources.

[0187] Clause 8. The first apparatus according to Clause 1, wherein the first apparatus is configured to: determine a combination of a plurality of receiving panels for simultaneous transmission.

[0188] Clause 9. The first means according to Clause 1, wherein the first means is configured to: determine one or more beam pairs for simultaneous transmission.

[0189] Clause 10. The first apparatus according to Clause 1, wherein the first beam set is a subset of the third beam set, and the second beam set is a subset of the fourth beam set.

[0190] Clause 11. A method for communication, comprising: receiving, at a first device, a configuration of receiving a group-based beam report from a second device, wherein the configuration includes first information and second information, the first information relating to a first beam set for measurements associated with a first transmit receiving point (TRP) and a second beam set for measurements associated with a second TRP, the second information relating to a predicted third beam set associated with the first TRP and a predicted fourth beam set associated with the second TRP, and the configuration further comprising at least one associated identifier, the at least one associated identifier including at least one of: an antenna configuration of the first TRP, an antenna configuration of the second TRP, or a path loss reference for uplink transmission; performing a first measurement on the first beam set and a second measurement on the second beam set; determining one or more predicted uplink beam pairs using an artificial intelligence / machine learning (AI / ML) model based on the measurement results of the first and second measurements, each predicted uplink beam pair including a first beam from the third beam set and a second beam from the fourth beam set; and transmitting to the second device a report associated with the predicted one or more uplink beam pairs.

Claims

1. A first device for communication, comprising: At least one processor; as well as At least one memory, the at least one memory storing instructions, the instructions, when executed by the at least one processor, cause the first device to: The second device receives a configuration for group-based beam reports, wherein the configuration includes first information and second information, the first information relating to a first beam set for measurements associated with a first transmit receive point (TRP) and a second beam set for measurements associated with a second TRP, the second information relating to a third beam set for predictions associated with the first TRP and a fourth beam set for predictions associated with the second TRP, and the configuration further includes at least one associated identifier, the at least one associated identifier including at least one of the following: antenna configuration of the first TRP, antenna configuration of the second TRP, or path loss reference for uplink transmission; Perform a first measurement on the first beam set and a second measurement on the second beam set; Based on the measurement results of the first and second measurements, an artificial intelligence / machine learning (AI / ML) model is used to determine one or more predicted uplink beam pairs, each predicted uplink beam pair including a first beam from the third beam set and a second beam from the fourth beam set; as well as The report associated with the one or more predicted uplink beam pairs is transmitted to the second device.

2. The first apparatus according to claim 1, wherein the report comprises at least one of the following: The identification information of the one or more predicted beam pairs, or The reference signal received power of the one or more predicted beam pairs.

3. The first apparatus according to claim 1, wherein the first information includes at least one of the following: the codebooks of the first beam set and the second beam set, the beam shapes of the first beam set and the second beam set, or the quality of the first beam set and the second beam set, and The second information includes at least one of the following: the codebook of the third beam set and the fourth beam set, the beam shape of the third beam set and the fourth beam set, or the quality of the third beam set and the fourth beam set.

4. The first apparatus according to claim 1, wherein the input to the AI / ML model includes at least one of the following: The measurement results of the first measurement and the second measurement, The markings on the receiving panel of the first device, The position of the first device. Uplink probe reference signal measurement from the first TRP for the transmission panel. Uplink probe reference signal measurement from the second TRP for the transmission panel, or Uplink power control value.

5. The first device according to claim 1, wherein the first device is configured to: Receive information from the second device regarding the path loss reference for the uplink transmission.

6. The first apparatus of claim 5, wherein the information for the path loss reference for the uplink transmission is received from a radio resource control configuration or a media access control control element.

7. The first device according to claim 1, wherein the first device is configured to: Determine the uplink power control value for the uplink probe reference signal resources.

8. The first device according to claim 1, wherein the first device is configured to: Determine the combination of multiple receiving panels for simultaneous transmission.

9. The first device according to claim 1, wherein the first device is configured to: Determine one or more beam pairs for simultaneous transmission.

10. The first apparatus of claim 1, wherein the first beam set is a subset of the third beam set, and the second beam set is a subset of the fourth beam set.

Images