Method and apparatus for artificial intelligence / machine learning-based beam management in spatial domain

AI/ML-based beam management in the spatial domain addresses ambiguities in CSI report linkages, improving accuracy and consistency, thereby optimizing spectral efficiency and QoS in 5G NR systems.

WO2026235031A1PCT designated stage Publication Date: 2026-11-12SHARP KK
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2026/016591
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-05
Filing Date
2026-04-24
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

Existing wireless communication systems face challenges in beam management, particularly in 5G NR, due to ambiguities in linkage rules for channel state information (CSI) reports, leading to inconsistent implementations and reduced accuracy in beam prediction.

Method used

Implementing AI/ML-based beam management in the spatial domain by defining clear rules for linking CSI reports with reference signal resources, using minimal time offsets, and enhancing UE and BS operations to perform L1-RSRP measurements and transmit accurate CSI reports.

Benefits of technology

This approach improves beam management accuracy and consistency across UEs, optimizing spectral efficiency and QoS by dynamically adjusting beamforming parameters, reducing interference, and enhancing signal quality and reliability in wireless communication systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2026016591_12112026_PF_FP_ABST
    Figure JP2026016591_12112026_PF_FP_ABST
Patent Text Reader

Abstract

A method performed by a UE for AI / ML-based beam management in spatial domain is provided. The method receives a first RRC configuration for configuring first CSI reports, each including a predicted L1-RSRP. The method receives a second RRC configuration for configuring a reference signal resource set including reference signal resources for channel measurement and a second CSI report including at least one RS-PAI. The method determines a linkage between each first CSI report and each of transmission occasions of the reference signal resources based on at least one CSI reference resource for each first CSI report that has a minimal time offset to a corresponding transmission occasion. The method performs L1-RSRP measurements for reference signal resources based on the determined linkage. The method transmits the first CSI reports and the second CSI report, where an index of the first RRC configuration is included in the second RRC configuration.
Need to check novelty before this filing date? Find Prior Art

Description

METHOD AND APPARATUS FOR ARTIFICIAL INTELLIGENCE / MACHINE LEARNING-BASED BEAM MANAGEMENT IN SPATIAL DOMAIN

[0001] The present disclosure is related to wireless communication and, more specifically, to a User Equipment (UE), Base Station (BS), and method for artificial intelligence (AI) / machine learning (ML)-based beam management in spatial domain in the wireless communication networks.

[0002] Various efforts have been made to improve different aspects of wireless communication for the cellular wireless communication systems, such as the 5thGeneration (5G) New Radio (NR), by improving data rate, latency, reliability, and mobility. The 5G NR system is designed to provide flexibility and configurability to optimize network services and types, accommodating various use cases, such as enhanced Mobile Broadband (eMBB), massive Machine-Type Communication (mMTC), and Ultra-Reliable and Low-Latency Communication (URLLC). As the demand for radio access continues to grow, however, there exists a need for further improvements in the next-generation wireless communication systems, such as improvements in a beam management procedure.

[0003] The present disclosure is related to a UE, a BS, and a method for artificial intelligence (AI) / machine learning (ML)-based beam management in spatial domain in the wireless communication networks.

[0004] In a first aspect of the present disclosure, a UE for artificial intelligence (AI) / machine learning (ML)-based beam management in spatial domain is provided. The UE includes at least one processor and at least one non-transitory computer-readable medium that is coupled to the at least one processor and that stores one or more computer-executable instructions. The computer-executable instructions, when executed by the at least one processor, cause the UE to: receive, from a base station (BS), a first radio resource control (RRC) configuration for configuring multiple first channel state information (CSI) reports, each of the multiple first CSI reports including a predicted layer 1 (L1)-reference signal received power (RSRP); receive, from the BS, a second RRC configuration for configuring a reference signal resource set for channel measurement and a second CSI report, the reference signal resource set including multiple reference signal resources and the second CSI report including at least one reference signal-prediction accuracy indicator (RS-PAI); determine a linkage between each of the multiple first CSI reports and each of multiple transmission occasions of the multiple reference signal resources based on at least one CSI reference resource for each of the multiple first CSI reports that has a minimal time offset to a corresponding transmission occasion of the multiple transmission occasions; perform L1-RSRP measurements for the multiple reference signal resources based on the determined linkage; and transmit, to the BS, the multiple first CSI reports and the second CSI report, where an index of the first RRC configuration is included in the second RRC configuration.

[0005] In some implementations of the first aspect, the multiple reference signal resources include multiple channel state information-reference signals (CSI-RSs).

[0006] In some implementations of the first aspect, the multiple reference signal resources include multiple synchronization signal block (SSBs).

[0007] In some implementations of the first aspect, the minimal time offset includes one or more slots.

[0008] In a second aspect of the present disclosure, a method performed by a user equipment (UE) for artificial intelligence (AI) / machine learning (ML)-based beam management in spatial domain is provided. The method includes: receiving, from a base station (BS), a first radio resource control (RRC) configuration for configuring multiple first channel state information (CSI) reports, each of the multiple first CSI reports including a predicted layer 1 (L1)-reference signal received power (RSRP); receiving, from the BS, a second RRC configuration for configuring a reference signal resource set for channel measurement and a second CSI report, the reference signal resource set including multiple reference signal resources and the second CSI report including at least one reference signal-prediction accuracy indicator (RS-PAI); determining a linkage between each of the multiple first CSI reports and each of multiple transmission occasions of the multiple reference signal resources based on at least one CSI reference resource for each of the multiple first CSI reports that has a minimal time offset to a corresponding transmission occasion of the multiple transmission occasions; performing L1-RSRP measurements for the multiple reference signal resources based on the determined linkage; and transmitting, to the BS, the multiple first CSI reports and the second CSI report, where an index of the first RRC configuration is included in the second RRC configuration.

[0009] In a third aspect of the present application, a BS for artificial intelligence (AI) / machine learning (ML)-based beam management in spatial domain is provided. The BS includes at least one processor and at least one non-transitory computer-readable medium that is coupled to the at least one processor and that stores one or more computer-executable instructions. The computer-executable instructions, when executed by the at least one processor, cause the BS to: transmit, to a user equipment (UE), a first radio resource control (RRC) configuration for configuring multiple first channel state information (CSI) reports, each of the multiple first CSI reports including a predicted layer 1 (L1)-reference signal received power (RSRP); and transmit, to the UE, a second RRC configuration for configuring a reference signal resource set for channel measurement and a second CSI report, the reference signal resource set including multiple reference signal resources and the second CSI report including at least one reference signal-prediction accuracy indicator (RS-PAI). The first RRC configuration and the second RRC configuration cause the UE to: determine a linkage between each of the multiple first CSI reports and each of multiple transmission occasions of the multiple reference signal resources based on at least one CSI reference resource for each of the multiple first CSI reports that has a minimal time offset to a corresponding transmission occasion of the multiple transmission occasions; perform L1-RSRP measurements for the multiple reference signal resources based on the determined linkage; and transmit, to the BS, the multiple first CSI reports and the second CSI report, where an index of the first RRC configuration is included in the second RRC configuration.

[0010] Aspects of the present disclosure are best understood from the following detailed disclosure when read with the accompanying drawings. Various features are not drawn to scale. Dimensions of various features may be arbitrarily increased or reduced for clarity of discussion.

[0011] FIG. 1 is a diagram illustrating linkages between inference reports and monitoring reports for BM-Case 1, according to an example implementation of the present disclosure.

[0012] FIG. 2 is a diagram illustrating linkages between inference reports and monitoring reports for BM-Case 2, according to an example implementation of the present disclosure.

[0013] FIG. 3 is a diagram illustrating a functional framework for AI / ML for NR air interface, according to an example implementation of the present disclosure.

[0014] FIG. 4 is a flowchart illustrating a method / process performed by a UE for artificial intelligence (AI) / machine learning (ML)-based beam management in spatial domain, according to an example implementation of the present disclosure.

[0015] FIG. 5 is a block diagram illustrating a node for wireless communication, according to an example implementation of the present disclosure.

[0016] Some of the abbreviations used in the present disclosure include: Abbreviation  Full name 3GPP  3rdGeneration Partnership Project 5G  5thGeneration ACK  Acknowledgment AI  Artificial Intelligence AL  Aggregation level ARFCN  Absolute Radio Frequency Channel Number BFD  Beam Failure Detection BM  Beam Management BWP  Band Width Part CA  Carrier Aggregation CORESET   Control resource set CC  Component Carrier CCE  Control Chanel Element CRC  Cyclic Redundancy Check C-RNTI  Cell Radio Network Temporary Identifier CS-RNTI    Configured Scheduling Radio Network Temporary Identifier CSS  Common Search Space CSI  Channel State Information DC  Dual Connectivity DCI  Downlink Control Information DL  Downlink GC-PDCCH  Group Common Physical Downlink Control Channel HARQ  Hybrid Automatic Repeat Request IE  Information Element IIoT  Industrial Internet of Things LSB  Least Significant Bit LTE  Long Term Evolution L1  Layer 1 L1-RSRP  Layer 1 reference signal received power LMF  Location Management Function MAC  Medium Access Control MCG  Master Cell Group MCS-C-RNTI  Modulation Coding Scheme Cell Radio Network Temporary Identifier mTRP  Multiple Transmission Reception Point MIMO  Multiple-input Multiple-output MSB  Most Significant Bit ML  Machine Learning NACK  Negative Acknowledgment NDI  New Data Indicator NR  New RAT / Radio NW  Network NUL  Normal UL PCI  Physical Cell ID PCell  Primary Cell PSCell  Primary Secondary Cell PBCH  Physical Broadcast Channel PDCCH  Physical Downlink Control Channel PDSCH  Physical Downlink Shared Channel PDU  Protocol Data Unit PHY  Physical PRACH  Physical Random Access Channel PTAG  Primary Timing Advance Group PUCCH  Physical Uplink Control Channel PUSCH  Physical Uplink Shared Channel RA  Random Access RAN  Radio Access Network RAR  Random Access Response Rel  Release RMSI  Remaining Minimum System Information RNTI  Radio Network Temporary Identifier RRC  Radio Resource Control RRM  Radio Resource Measurement RS  Reference Signal RSRP  Reference Signal Received Power RV  Redundancy Version SCell  Secondary Cell SCG  Secondary Cell Group SCS  Subcarrier Spacing SDM  Spatial Division Multiplexing SINR  Signal to Interference plus Noise Ratio SpCell  Special Cell SR  Scheduling Request SRS  Sounding Reference Signal SRI  SRS Resource Indicator SSB  Synchronization Signal Block STAG  Secondary Timing Advance Group STxMP  Simultaneous Transmission on Multiple Panels SUL  Supplementary UL TA  Timing Advance TAG  Timing Advance Group TB  Transport Block TBS  Transport Block Size TCI  Transmission Configuration Indication TPMI  Transmission Precoding Matrix Indicator TR  Technical Report TRP  Transmission Reception Point TS  Technical Specification QCL  Quasi-CoLocation UE  User Equipment UL  Uplink URLLC  Ultra Reliable Low Latency Communication USS  UE-Specific Search Space WG  Working Group WI  Working Item

[0017] The following contains specific information related to implementations of the present disclosure. The drawings and their accompanying detailed disclosure are merely directed to implementations. However, the present disclosure is not limited to these implementations. Other variations and implementations of the present disclosure will be obvious to those skilled in the art.

[0018] Unless noted otherwise, like or corresponding elements among the drawings may be indicated by like or corresponding reference numerals. Moreover, the drawings and illustrations in the present disclosure are generally not to scale and are not intended to correspond to actual relative dimensions.

[0019] For the purposes of consistency and ease of understanding, like features may be identified (although, in some examples, not illustrated) by the same numerals in the drawings. However, the features in different implementations may be different in other respects and may not be narrowly confined to what is illustrated in the drawings.

[0020] References to “one implementation,” “an implementation,” “example implementation,” “various implementations,” “some implementations,” “implementations of the present application,” etc., may indicate that the implementation(s) of the present application so described may include a particular feature, structure, or characteristic, but not every possible implementation of the present application necessarily includes the particular feature, structure, or characteristic. Further, repeated use of the phrase “In some implementations,” or “in an example implementation,” “an implementation,” do not necessarily refer to the same implementation, although they may. Moreover, any use of phrases like “implementations” in connection with “the present application” are never meant to characterize that all implementations of the present application must include the particular feature, structure, or characteristic, and should instead be understood to mean “at least some implementations of the present application” includes the stated particular feature, structure, or characteristic. The term “coupled” is defined as connected, whether directly or indirectly through intervening components, and is not necessarily limited to physical connections. The term “comprising,” when utilized, means “including, but not necessarily limited to”; it specifically indicates open-ended inclusion or membership in the so-described combination, group, series, and the equivalent.

[0021] The expression “at least one of A, B and C” or “at least one of the following: A, B and C” means “only A, or only B, or only C, or any combination of A, B and C.” The terms “system” and “network” may be used interchangeably. The term “and / or” is only an association relationship for describing associated objects and represents that three relationships may exist such that A and / or B may indicate that A exists alone, A and B exist at the same time, or B exists alone. The character “ / ” generally represents that the associated objects are in an “or” relationship.

[0022] For the purposes of explanation and non-limitation, specific details, such as functional entities, techniques, protocols, and standards, are set forth for providing an understanding of the disclosed technology. In other examples, detailed disclosure of well-known methods, technologies, systems, and architectures are omitted so as not to obscure the present disclosure with unnecessary details.

[0023] Persons skilled in the art will immediately recognize that any network function(s) or algorithm(s) disclosed may be implemented by hardware, software, or a combination of software and hardware. Disclosed functions may correspond to modules which may be software, hardware, firmware, or any combination thereof.

[0024] A software implementation may include computer-executable instructions and / or Artificial Intelligence (AI) / Machine Learning (ML) module(s) stored on a computer-readable medium, such as memory or other type of storage devices. One or more microprocessors or general-purpose computers with communication processing capability may be programmed with corresponding computer-executable instructions and perform the disclosed network function(s), AI / ML module(s), or algorithm(s). The AI / ML module(s) may be implemented with a supervised learning approach, a semi-supervised learning approach, an unsupervised learning approach (e.g., Transductive approach and Inductive approach), a federated learning approach, or a reinforcement learning (RL) approach, but the present disclosure is not limited thereto. The computer-executable instructions associated with the AI module(s) and / or the ML module(s) may include but are not limited to, data management instructions (e.g., collection instructions, validation instructions…etc.), model monitoring and management instructions (e.g., NW KPIs monitoring, model input / output monitoring, model selection / switching / update / upload / download, model (de)activation, model identification, functionality selection…etc.), and / or pre-process input instructions.

[0025] The microprocessors or general-purpose computers may include Application-Specific Integrated Circuits (ASICs), programmable logic arrays, Central Processing Units (CPUs), Tensor Processing Units (TPUs), Graphics Processing Units (GPUs), General-purpose computing on GPUs (GPGPU, or less often GPGP), and / or one or more Digital Signal Processors (DSPs). Although some of the disclosed implementations are oriented to software installed and executing on computer hardware, alternative implementations implemented as firmware, as hardware, or as a combination of hardware and software are well within the scope of the present disclosure. The computer-readable media may include computer-storage media and communication media. Computer-storage media may include both volatile (and / or non-volatile media), and removable (and / or non-removable) media implemented in any method or technology for storage of information such as computer-readable instructions related to AI module(s) and / or the ML module(s), data structures, program modules or data. The computer-readable medium may include, but is not limited to, Random Access Memory (RAM), Dynamic Random Access Memory (DRAM), High Bandwidth Memory (HBM), Magnetoresistive Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Resistive Random Access Memory (RRAM), Read-Only Memory (ROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash memory (or other memory technology), Compact Disc Read-Only Memory (CD-ROM) , Digital Versatile Disks (DVD) (or other optical disk storage), magnetic cassettes, magnetic tape, magnetic disk storage (or other magnetic storage devices), or any other equivalent medium capable of storing computer-readable instructions. Computer-storage media may not include a propagated data signal. Communication media may typically embody computer-readable instructions (e.g., computer-readable instructions related to AI module(s) and / or the ML module(s)), data structures, program modules, or other data in a modulated data signal, such as a carrier wave, or other transport mechanisms and include any information delivery media.

[0026] The term “modulated data signal” may mean a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. Communication media may include wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared, and other wireless media. Combinations of any of the previously listed components should also be included within the scope of computer-readable media.

[0027] A radio communication network architecture such as a Long-Term Evolution (LTE) system, an LTE-Advanced (LTE-A) system, an LTE-Advanced Pro system, a 5G NR Radio Access Network (RAN), 5G-Advanced (5G-A) system, or an open radio access network (O-RAN) may typically include at least one base station (BS), at least one UE, and one or more optional network elements that provide connection within a network. The BS and one or more optional network elements enable the UE to access a radio network. Thus, the UE may communicate with the network, such as a Core Network (CN), an Evolved Packet Core (EPC) network, an Evolved Universal Terrestrial RAN (E-UTRAN), a Next-Generation Core (NGC), a 5G Core (5GC), or an internet via a RAN established by one or more BSs and the network elements / functions.

[0028] A UE may include, but is not limited to, a mobile station, a mobile terminal or device, or a user communication radio terminal. The UE may be a portable radio equipment that includes, but is not limited to, a mobile phone, a tablet, a wearable device, a sensor, a vehicle, a virtual reality (VR) device, an augmented (AR) device, an Internet of Things (IoT) device, an unmanned aerial vehicle (UAV), or a Personal Digital Assistant (PDA) with wireless communication capability. The UE may be configured to receive and transmit signals over an air interface to one or more cells in a RAN. In some implementations, the UE may be an AI / ML-enabled device and / or an AI / ML capable device that is equipped with AI module(s) and / or ML module(s).

[0029] The BS may be configured to provide communication services according to at least a Radio Access Technology (RAT) such as Worldwide Interoperability for Microwave Access (WiMAX), Global System for Mobile communications (GSM) that is often referred to as 2G, GSM Enhanced Data rates for GSM Evolution (EDGE) RAN (GERAN), General Packet Radio Service (GPRS), Universal Mobile Telecommunication System (UMTS) that is often referred to as 3G based on basic wideband-code division multiple access (W-CDMA), high-speed packet access (HSPA), LTE, LTE-A, evolved LTE (eLTE) that is LTE connected to 5GC, NR (often referred to as 5G), and / or LTE-A Pro. However, the scope of the present disclosure is not limited to these protocols.

[0030] The BS may include, but is not limited to, a node B (NB) in the UMTS, an evolved node B (eNB) in LTE or LTE-A, a radio network controller (RNC) in UMTS, a BS controller (BSC) in the GSM / GERAN, an ng-eNB in an Evolved Universal Terrestrial Radio Access (E-UTRA) BS in connection with 5GC, a next generation Node B (gNB) in the 5G-RAN, or any other apparatus capable of controlling radio communication and managing radio resources within a cell. The BS may serve one or more UEs via a radio interface. Although the gNB is used as an example in some implementations within the present disclosure, it should be noted that the disclosed implementations may also be applied to other types of base stations. In some implementations, the BS may be an AI / ML-enabled device and / or an AI / ML capable device that is equipped with AI module(s) and / or ML module(s).

[0031] The BS may be operable to provide radio coverage to a specific geographical area using multiple cells forming the RAN. The BS may support the operations of the cells. Each cell may be operable to provide services to at least one UE within its radio coverage.

[0032] Each cell (may often referred to as a serving cell) may provide services to one or more UEs within the cell’s radio coverage, such that each cell schedules the DL (and optionally UL resources) to at least one UE within its radio coverage for DL (and optionally UL packet transmissions from the UE). The BS may communicate with one or more UEs in the radio communication system via the cells.

[0033] A cell may allocate Sidelink (SL) resources for supporting Proximity Service (ProSe), LTE SL services, LTE / NR sidelink communication services, LTE / NR sidelink discovery services, and / or LTE / NR Vehicle-to-Everything (V2X) services. In addition, a cell may allocate DL and / or UL resources for supporting Multicast / Broadcast Service (MBS) services, Non-Terrestrial Networks (NTN) services, positioning services, power serving services and / or Network Energy Saving (NES) services.

[0034] In Multi-RAT Dual Connectivity (MR-DC) cases, the primary cell of a Master Cell Group (MCG) or a Secondary Cell Group (SCG) may be referred to as a Special Cell (SpCell). A Primary Cell (PCell) may include the SpCell of an MCG. A Primary SCG Cell (PSCell) may include the SpCell of an SCG. MCG may include a group of serving cells associated with the Master Node (MN), including the SpCell and optionally one or more Secondary Cells (SCells). An SCG may include a group of serving cells associated with the Secondary Node (SN), including the SpCell and optionally one or more SCells.

[0035] The terms, definitions, and abbreviations as given in the present disclosure may be either imported from existing documentation (e.g., European Telecommunications Standards Institute (ETSI), International Telecommunication Union (ITU), or elsewhere) or newly created by 3GPP experts whenever the need for precise vocabulary is identified.

[0036] As discussed above, the frame structure for NR may support flexible configurations for accommodating various next generation (e.g., 5G) communication requirements, such as Enhanced Mobile Broadband (eMBB), Massive Machine Type Communication (mMTC), and Ultra-Reliable and Low-Latency Communication (URLLC), while fulfilling high reliability, high data rate, and low latency requirements. The Orthogonal Frequency-Division Multiplexing (OFDM) technology in the 3GPP may serve as a baseline for an NR waveform. The scalable OFDM numerology, such as adaptive sub-carrier spacing, channel bandwidth, and Cyclic Prefix (CP), may also be used.

[0037] Two coding schemes may be considered for NR, specifically, Low-Density Parity-Check (LDPC) code and Polar Code. The coding scheme adaption may be configured based on channel conditions and / or service applications.

[0038] At least the DL transmission data, a guard period, and UL transmission data should be included in a transmission time interval (TTI) of a single NR frame. The respective portions of the DL transmission data, the guard period, and the UL transmission data should also be configurable based on, for example, the network dynamics of NR. SL resources may also be provided in an NR frame to support ProSe services or V2X services.

[0039] Any two or more than two of the following paragraphs, (sub)-bullets, points, actions, behaviors, terms, or claims described in the present disclosure may be combined logically, reasonably, and properly to form a specific method.

[0040] Any sentence, paragraph, (sub)-bullet, point, action, behaviors, terms, or claims described in the present disclosure may be implemented independently and separately to form a specific method.

[0041] Dependency, e.g., “based on”, “more specifically”, “preferably”, “in one embodiment”, “in some implementations”, etc., in the present disclosure is just one possible example which would not restrict the specific method.

[0042] In some implementations, all the designs / embodiment / implementations introduced within this disclosure are not limited to be applied for dealing with the problems discussed within this disclosure. For example, the described embodiments may be applied to solve other problems that exist in the RAN of wireless communication systems. In some implementations, all of the numbers listed within the designs / embodiment / implementations introduced within this disclosure are just examples and for illustration, for example, of how the described methods are executed.

[0043] The term “A and / or B” within the present disclosure means “A”, “B”, or “A and B”. The term “A and / or B and / or C” within the present disclosure means “A”, “B”, “C”, “A and B”, “A and C”, “B and C”, or “A and B and C”. The term “A / B” within the present disclosure means “A” or “B”.

[0044] The term “TRP” in the present disclosure may be replaced by the term “beam” or “panel”. The term “overlap” may refer to partial overlap or fully overlap in time domain.

[0045] Examples of some selected terms in the present disclosure are provided as follows.

[0046] DCI: DCI may include downlink control information, and there may be various DCI formats used in a PDCCH. The DCI format may be a predefined format in which the downlink control information may be packed / formed and transmitted in a PDCCH.

[0047] BWP: A subset of the total cell bandwidth of a cell is referred to as a Bandwidth Part (BWP) and a Bandwidth Adaptation (BA) may be achieved by configuring the UE with BWP(s) and instructing the UE which of the configured BWPs is currently the active one. To enable a BA on the PCell, the BS (e.g., a gNB) configures the UE with UL and DL BWP(s). To enable the BA on SCells, when CA is deployed, the BS configures the UE with one or more DL BWPs. It should be noted that there may be no BWP in the UL. For the PCell, the initial BWP is the BWP used for an initial access. For the SCell(s), the initial BWP is the BWP configured for the UE to operate after an SCell activation. The UE may be configured with a first active uplink BWP by a firstActiveUplinkBWP IE. If the first active uplink BWP is configured for an SpCell, the firstActiveUplinkBWP IE field may contain the ID of the UL BWP to be activated upon performing the RRC (re-)configuration. If such a field is absent, the RRC (re-)configuration may not impose a BWP switching. If the first active uplink BWP is configured for an SCell, the firstActiveUplinkBWP IE field may contain the ID of the uplink bandwidth part to be used upon the MAC-activation of an SCell.

[0048] TCI state: A TCI state may include parameters for configuring a QCL relationship between one or more DL reference signals and a target reference signal set. For example, a target reference signal set may include the DMRS ports of a PDSCH, a PDCCH, a PUCCH, or a PUSCH. The reference signals may include UL or DL reference signals. In NR Rel-15 / 16, the TCI state may be used for a DL QCL indication, whereas the spatial relation information may be used for providing the UL spatial transmission filter information for the UL signal(s) or channel(s). A TCI state may include the information similar to the spatial relation information, which may be used for UL transmission. In other words, from the UL perspective, a TCI state may provide the UL beam information that may indicate the relationship between a UL transmission and the DL or UL reference signals (e.g., the CSI-RS, the SSB, the SRS, and the PTRS).

[0049] Beam: The term “beam” may refer to a spatial (domain) filtering. For example, when the UE reports a preferred gNB TX beam, the UE may essentially select a spatial filter used by the gNB. The term “beam information” may be used to provide information about which beam / spatial filter is used / selected.

[0050] In the realm of wireless communication, beam management plays a crucial role in optimizing the performance of communication networks, particularly in the context of emerging technologies such as 5G and beyond. Beam management involves the selection, tracking, and optimization of beams in a beamforming system to ensure efficient and reliable data transmission between base stations and user equipment. Furthermore, AI / ML-driven beam management enhances spectral efficiency by dynamically adjusting beamforming parameters to optimize resource allocation and / or by maximizing throughput per unit of spectrum. It improves coverage by intelligently steering beams towards active users and high-demand areas, thereby ensuring better signal propagation and reduced dead zones. Additionally, AI / ML algorithms mitigate interference, enhance signal quality and reliability, thereby improving overall quality of service (QoS). Through these mechanisms (e.g., AI / ML algorithms), AI / ML-driven beam management optimizes spectrum usage, extends coverage, and enhances QoS, leading to more efficient and reliable wireless communication systems.

[0051] FIG. 1 is a diagram illustrating linkages between inference reports and monitoring reports for BM-Case 1 100, according to an example implementation of the present disclosure. FIG. 2 is a diagram illustrating linkages between inference reports and monitoring reports for BM-Case 2 200, according to an example implementation of the present disclosure.

[0052] In UE-side model-based monitoring (e.g., under Monitoring Type 1 Option 2), performance metrics for monitoring may be calculated by linking measurement results of CSI-RS / SSB resources with corresponding inference reports. For BM-Case 1, the linking criterion may be based on the minimal slot offset (e.g., the minimal offset 102) between the transmission occasion of the CSI-RS / SSB resource used for monitoring and a CSI reference resource for an inference report. For BM-Case 2, the linking criterion may be based on the minimal slot offset (e.g., the minimal offset 202) between the transmission occasion of the CSI-RS / SSB resource used for monitoring and a specific prediction result (e.g., the f-th time instance of the time instance in one inference report), where the specific prediction result (e.g., the value of f) may be configured by the RRC and may be in an inference report. Specifically, the CSI reference resource for the inference report that has the minimal slot offset to the CSI-RS / SSB resource for monitoring transmission occasion may be selected.

[0053] However, an ambiguity may arise when multiple inference reports whose CSI reference resources have the same slot offset to the transmission occasion of the CSI-RS / SSB resource used for monitoring. For example, as illustrated in FIG. 1, an ambiguity may arise when multiple inference reports (e.g., the inference report 104 and the inference report 106) whose CSI reference resources (e.g., the CSI reference resource 108 of the inference report 104 and the CSI reference resource 110 of the inference report 106) have the same slot offset (e.g., the minimal offset 102) to the transmission occasion of the CSI-RS / SSB resource used for monitoring (e.g., the CSI-RS / SSB resource 112). This occurs, for example, when CSI reference resource for one inference report is located in time prior to the monitoring transmission occasion, and another after, but both have identical slot offset magnitudes. In such cases, it may be unclear whether (1) both inference reports should be considered in the metric calculation, or (2) only one inference report should be selected and linked, in which case the linking rule (e.g., preferring the earlier or later CSI reference resource) must be explicitly defined. As illustrated in FIG. 2, an ambiguity may arise when multiple inference reports (e.g., the inference report 204 and the inference report 206) whose predicted results (e.g., the predicted result 208 of the inference report 204 and the predicted result 210 of the inference report 206) have the same slot offset (e.g., the minimal offset 202) to the transmission occasion of the CSI-RS / SSB resource used for monitoring (e.g., the CSI-RS / SSB resource 212).

[0054] This lack of clarity may lead to inconsistent implementations across UEs or vendors and may affect the accuracy or interpretability of the monitoring metric. Therefore, it may be necessary to define clear rules or constraints for resolving slot offset equivalence behavior in inference report linkage for calculation of the beam prediction accuracy.

[0055] Functional framework for AI / ML for NR air interface

[0056] FIG. 3 is a diagram illustrating a functional framework 300 for AI / ML for NR air interface, according to an example implementation of the present disclosure.

[0057] Data collection 302 may be a function that provides input data to the model training function 304, management function 306, and inference function 308.

[0058] Training data 312: Data needed as input for the AI / ML model training function 304.

[0059] Monitoring data 314: Data needed as input for the management function 306 of AI / ML models or AI / ML functionalities.

[0060] Inference data 316: Data needed as input for the AI / ML inference function 306.

[0061] Model training 304 may be a function that performs AI / ML model training, validation, and testing which may generate model performance metrics used as part of the model testing procedure. The model training function 304 may also be responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on training data 312 delivered by a data collection function 302, if required.

[0062] Trained / updated model 318: In case of having a model storage function 310, this may be used to deliver trained, validated, and tested AI / ML models to the model storage function 310, or to deliver an updated version of a model to the model storage function 310.

[0063] Management 306 may be a function that oversees the operation (e.g., selection / (de)activation / switching / fallback) and monitoring (e.g., performance) of AI / ML models or AI / ML functionalities. This function may also be responsible for making decisions to ensure the proper inference operation based on data (e.g., the monitoring data 314 and the inference output 320) received from the data collection function 314 and the inference function 308.

[0064] Management instruction 322: Information needed as input to manage the inference function 308. Concerning information may include selection / (de)activation / switching of AI / ML models or AI / ML-based functionalities, fallback to non-AI / ML operation (e.g., not relying on inference process), and so on.

[0065] Model transfer / delivery request 324: Used to request model(s) to the model storage function 310.

[0066] Performance feedback / retraining request 326: Information needed as input for the model training function 304 (e.g., for model (re)training or updating purposes).

[0067] Inference 308 may be a function that provides outputs from the process of applying AI / ML models or AI / ML functionalities, using the data that is provided by the data collection function 302 (e.g., the inference data 316) as an input. The inference function 308 may also be responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on inference data 316 delivered by a data collection function 302, if required.

[0068] Inference output 320: Data used by the management function 306 to monitor the performance of AI / ML models or AI / ML functionalities.

[0069] Model storage 310 may be a function responsible for storing trained / updated models that can be used to perform the inference function 308.

[0070] Model transfer / delivery 328: Used to deliver an AI / ML model to the inference function 308.

[0071] L1 measurement and report

[0072] A UE may perform and report measurement (e.g., L1 measurement or L3 measurement) based on the received configuration and / or indication. L1 measurements may be further classified into the L1 intra-frequency measurement or the L1 inter-frequency measurement. In some implementations, the L1 intra-frequency measurement and the L1 inter-frequency measurement may be based on the L1-RSRP through measuring the SSB (e.g., the SS-RSRP) or the CSI-RS (e.g., the CSI-RSRP). In some implementations, the L1 intra-frequency measurement and the L1 inter-frequency measurement may be based on the L1-SINR through measuring the SSB (e.g., the SS-SINR) or the CSI-RS (e.g., the CSI-SINR). In some implementations, the L1 intra-frequency measurement and the L1 inter-frequency measurement may be based on the L1-RSRQ through measuring the SSB (e.g., the SS-RSRQ) or the CSI-RS (e.g., the CSI-RSRQ).

[0073] In some implementations, the L1 measurement report may include one or more PCIs (e.g., PCIs of the candidate cells, the PCI of the source cell, the PCI of the serving cell, or the PCI of the target cell). In some implementations, the L1 measurement report may include one or more RS IDs.

[0074] In some implementations, the L1 measurement report as UCI transmitted on the PUCCH or the PUSCH may be considered as the result of measurement from the UE’s perspective. In some implementations, the L1 measurement report type may include the periodic report on the PUCCH, the semi-persistent report on the PUCCH or the PUSCH, and the aperiodic report on the PUSCH. In some implementations, the L1 measurement report may be transmitted on a MAC CE.

[0075] CSI measurement configuration

[0076] The CSI measurement configuration may include setting parameters that configure how CSI measurements are performed and reported by the UE. The CSI measurement configuration may configure a list of non-zero power CSI-RS resources for channel measurement, a list of CSI-RS resources for interference management, and a list of SSB resources for CSI measurement and reporting. In some implementation, the CSI measurement configuration may be associated with the CSI report configuration. In some implementations, when the CSI resources in the CSI resource set is configured for beam measurement, the corresponding CSI report may only contain the CRI, the SSBRI, the L1-RSRP, and / or the L1-SINR for each measurement result based on the configured CSI-RS resources, and one CSI-RS resource or one SSB may correspond to one L1-RSRP, one L1-SINR, or one L1-RSRQ value.

[0077] CSI report content

[0078] In some implementations, the CSI report may include the Channel Quality Indicator (CQI), the Precoding Matrix Indicator (PMI), the CSI-RS resource indicator (CRI), the SS / PBCH block resource indicator (SSBRI), the Layer Indicator (LI), the Rank Indicator (RI), the Capability Index, the L1-RSRP, the L1-SINR, or / and the L1-RSRQ. In some implementations, the report may contain top K value among a set of measurement results by measuring the CSI-RS resource or the SSB.

[0079] CSI reference resource

[0080] The CSI reference resource for a serving cell may be defined as follows.

[0081] In the frequency domain, the CSI reference resource may be defined by the group of downlink physical resource blocks corresponding to the band to which the derived CSI relates.

[0082] In the time domain, the CSI reference resource for a CSI reporting in uplink slot n’ may be defined by a single downlink slot Ns. The single downlink slot Nsmay be defined by the following equation: Ns= n - nCSI_ref- K_offset* (2uDL / 2uK_offset),

[0083] where K_offsetmay be a parameter configured by the higher layer, and uK_offsetmay be the subcarrier spacing configuration for K_offsetwith a value of 0 for frequency range 1 and for FR2-NTN.

[0084] n may be defined by the following equation:

[0085] where floor(x) denotes the greatest integer less than or equal to x.

[0086] uDLand uULmay be the subcarrier spacing configurations for DL and UL, respectively.

[0087] ,NCAslot, offsetand uoffsetmay be determined by the higher layer configured ca-SlotOffset for the cells transmitting the uplink and downlink, as specified in the 3GPP TS 38.211.

[0088] For periodic and semi-persistent CSI reporting:

[0089] (a) if a single CSI-RS / SSB resource is configured for channel measurement, nCSI_ref may be the smallest value greater than or equal to 4 * 2uDL, such that it corresponds to a valid downlink slot, or

[0090] (b) if multiple CSI-RS / SSB resources are configured for channel measurement, nCSI_ref may be the smallest value greater than or equal to 5 * 2uDL, such that it corresponds to a valid downlink slot.

[0091] For aperiodic CSI reporting, if the UE is indicated by the DCI to report CSI in the same slot as the CSI request, nCSI_ref is such that the reference resource is in the same valid downlink slot as the corresponding CSI request. Otherwise, nCSI_ref may be the smallest value greater than or equal to Y. Y may defined by the following equation:

[0092] such that slot n- nCSI_ref corresponds to a valid downlink slot. Z’ may correspond to the delay requirement as specified in the 3GPP TS 38.214.

[0093] When periodic or semi-persistent CSI-RS / CSI-IM or SSB is used for channel / interference measurements, the UE may not expect to measure channel / interference on the CSI-RS / CSI-IM / SSB whose last OFDM symbol is received up to Z' symbols before transmission time of the first OFDM symbol of the aperiodic CSI reporting.

[0094] Cell term

[0095] In some implementations, a cell in the present disclosure may refer to a PCell, a PSCell, a SpCell, an SCell, a candidate cell, a target cell, a neighbour cell, a serving cell, and / or a source cell.

[0096] Performance monitoring

[0097] Type 1 performance monitoring: The configuration and signaling may be initiated by the network (e.g., the gNB) to instruct the user equipment (UE) to perform certain measurements or report specific performance metrics. Depending on the monitoring option, the UE may either transmit measurement results and inference results to the network (Option 1: network-side monitoring) or locally calculate performance metrics and optionally report results or events back to the network (Option 2: UE-assisted monitoring).

[0098] Type 2 performance monitoring: The UE may take a more proactive role by initiating performance monitoring through signaling (e.g., indication, request, or reporting) toward the gNB. This type may involve the UE making decisions regarding model selection, activation, deactivation, or fallback based on performance evaluations.

[0099] Several potential scenarios for AI / ML-based beam management (BM) may include the following (A) and (B).

[0100] (A) BM case 1: Spatial-domain downlink beam prediction for Set A of beams may be based on measurement results of Set B of beams. This case may include at least one of the following aspects (a)-(d).

[0101] (a) AI / ML model training and inference may be performed at NW side,

[0102] (b) AI / ML model training and inference may be performed at UE side,

[0103] (c) Set A and Set B may be different, and

[0104] (d) Set B may be a subset of Set A.

[0105] (B) BM case 2: Temporal Downlink beam prediction for Set A of beams may be based on the historical measurement results of Set B of beams. This case may include at least one of the following aspects (a)-(e).

[0106] (a) AI / ML model training and inference may be performed at NW side,

[0107] (b) AI / ML model training and inference may be performed at UE side,

[0108] (c) Set A and Set B may be different,

[0109] (d) Set B may be a subset of Set A, and

[0110] (e) Set A and Set B may be the same.

[0111] In some implementations, the user equipment (UE) may receive, from a base station (BS) or a network (NW), a first radio resource control (RRC) configuration for configuring channel state information (CSI) report related information. The first RRC configuration may configure multiple first CSI reports including predicted L1-RSRP values (e.g., with the reportQuantity IE set to ‘p-cri-RSRP-r19’ and / or ‘p-ssb-index-RSRP-r19’) and prediction reference signal (RS) indication (e.g., with the reportQuantity IE set to ‘p-cri-r19’ and / or ‘p-ssb-index-r19’), which may be generated from CSI-RS (e.g., a type of reference signal) resources and / or synchronization signal block (SSB) (e.g., a type of reference signal) resources in the corresponding one or more CSI resource sets of the resource setting given by the resourcesForSetB IE (e.g., a resource set ID for reference signal (RS) prediction). In some implementations, the prediction RS indication may correspond to the reference resources (e.g., the CSI-RS and / or the SSB) in the corresponding CSI resource set of the resource setting given by the resourcesForSetA IE (e.g., a resource set ID for channel measurement).

[0112] In some implementations, the UE may receive, from the BS or the NW, a second RRC configuration. The second RRC configuration may configure a CSI-RS resource set for channel measurement, and the resource set may include multiple CSI-RS and / or synchronization signal block (SSB) resources. The second RRC configuration may further configure a second CSI report including at least one reference signal prediction accuracy indicator (RS-PAI) (e.g., with the reportQuantity IE set to ‘rspai-r19’). In some implementations, the CSI-RS resource set for channel measurement may refer to the CSI-RS resource set for RS-PAI.

[0113] In some implementations, the UE may determine multiple CSI reference resources for the corresponding first CSI reports.

[0114] In some implementations, the UE may determine a linkage (e.g., each of the multiple first CSI reports may be linked to each transmission occasion of the multiple CSI-RS / SSB resources configured by the second RRC configuration) based on some specific rules. For example, a CSI report including predicted L1-RSRP values and prediction RS indication may be linked to a transmission occasion of the multiple reference resources (e.g., CSI-RS or SSB) for channel measurement (e.g., RS-PAI) having a minimal time offset to a transmission occasion of one of the multiple CSI-RS / SSB resources. In some implementations, the ID of the first RRC configuration may be configured / included in the second RRC configuration or an RRC configuration for RS-PAI. In some implementations, the ID of the second RRC configuration may be configured / included in the first RRC configuration.

[0115] In some implementations, the UE may calculate the RS-PAI based on the determined linkage, where the RS-PAI may quantify the accuracy of a beam prediction result reported in a CSI report by including the predicted L1-RSRP value in the at least one of the multiple first CSI reports to the at least one measurement result (e.g., L1-RSRP value) of the linked CSI-RS / SSB transmission occasion(s).

[0116] In some implementations, the UE may transmit the multiple first CSI reports and the second CSI report including the RS-PAI to the BS or the NW via uplink signaling (e.g., the PUCCH or the PUSCH).

[0117] In some implementations, when more than one CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine the linkage based on a CSI reference resource that is no later than the transmission occasion of one of the multiple CSI-RS / SSB resources (e.g., the corresponding CSI-RS / SSB resource). In some implementations, the occurrence of multiple minimal time offsets may result from the situation where, relative to the transmission occasion of the CSI-RS / SSB resource for RS-PAI, some CSI reference resources corresponding to the multiple first CSI reports may be located prior to the transmission occasion, while others may be located after it, with both having identical absolute time offsets. In some implementations, the time offset may refer to a slot offset or a time interval.

[0118] In some implementations, the user equipment (UE) may receive, from a base station (BS) or a network (NW), a first radio resource control (RRC) configuration for configuring channel state information (CSI) report related information. The first RRC configuration may configure multiple first CSI reports including predicted L1-RSRP values (e.g., with the reportQuantity IE set to ‘p-cri-RSRP-r19’ and / or ‘p-ssb-index-RSRP-r19’) and prediction reference signal (RS) indication (e.g., with the reportQuantity IE set to ‘p-cri-r19’ and / or ‘p-ssb-index-r19’), which may be generated from CSI-RS (e.g., a type of reference signal) resources and / or synchronization signal block (SSB) (e.g., a type of reference signal) resources in the corresponding CSI resource set of the resource setting given by the resourcesForSetB IE (e.g., a resource set ID for reference signal (RS) prediction). In some implementations, the prediction RS indication may correspond to the reference resources (e.g., the CSI-RS and / or the SSB) in the corresponding CSI resource set of the resource setting given by the resourcesForSetA IE (e.g., a resource set ID for channel measurement).

[0119] In some implementations, the UE may receive an RRC parameter in the first RRC configuration or an RRC configuration other than the first RRC configuration for configuring a specific time instance of at least one time instance of predicted L1-RSRP in a corresponding CSI report of the multiple first CSI reports. In some implementations, each of the multiple first CSI reports may include at least one predicted L1-RSRP and the time instance of the at least one predicted L1-RSRP. In some implementations, each of the multiple first CSI reports may include at least one predicted L1-RSRP and the time instance of the at least one predicted L1-RSRP, and may further include a prediction RS indication that is configured by an RRC parameter. In some implementations, the configured specific time instance may be used to link the predicted L1-RSRP to the measured L1-RSRP based on the CSI-RS / SSB resource for RS-PAI to calculate RS-PAI in the second CSI report.

[0120] In some implementations, the UE may receive, from the BS or the NW, a second RRC configuration. The second RRC configuration may configure a CSI-RS resource set for channel measurement, the resource set may include multiple CSI-RS and / or synchronization signal block (SSB) resources. The second RRC configuration may further configure a second CSI report cincluding at least one reference signal prediction accuracy indicator (RS-PAI) (e.g., with the reportQuantity IE set to ‘rspai-r19’). In some implementations, the CSI-RS resource set for channel measurement may refer to the CSI-RS resource set for RS-PAI.

[0121] In some implementations, the UE may determine a linkage (e.g., each of the multiple first CSI reports may be linked to each transmission occasion of the multiple CSI-RS / SSB resources configured by the second RRC configuration) based on some specific rules. For example, a CSI report including predicted L1-RSRP values and prediction RS indication may be linked to a transmission occasion of the multiple reference resources (e.g., the CSI-RS or the SSB) for channel measurement (e.g., the RS-PAI) having a minimal time offset to a specific time instance of predicted L1-RSRP (e.g., the f-th time instance) of one of the multiple first CSI reports. In some implementations, the ID of the first RRC configuration may be configured / included in the second RRC configuration or an RRC configuration for RS-PAI. In some implementations, the ID of the second RRC configuration may be configured / included in the first RRC configuration.

[0122] In some implementations, the UE may calculate the RS-PAI based on the determined linkage, where the RS-PAI may quantify the accuracy of a beam prediction result reported in the second CSI report by including the predicted L1-RSRP value in the at least one of multiple CSI reports to the at least one measurement result (e.g., L1-RSRP value) of the linked CSI-RS / SSB transmission occasion(s).

[0123] In some implementations, the UE may transmit the multiple first CSI reports and the second CSI report including the RS-PAI to the BS or the NW via uplink signaling (e.g., the PUCCH or the PUSCH).

[0124] In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine the linkage based on the specific time instance of predicted L1-RSRP that is no later than the transmission occasion of the CSI-RS / SSB resource (e.g., the corresponding CSI-RS / SSB resource). In some implementations, the occurrence of multiple minimal time offsets may result from the situation where, relative to the transmission occasion of the CSI-RS / SSB resource for RS-PAI, some specific time instance of predicted L1-RSRP corresponding to the multiple first CSI reports may be located prior to the transmission occasion, while others may be located after it, with both having identical absolute time offsets. In some implementations, the time offset may refer to a slot offset or a time interval.

[0125] For BM Case 1

[0126] In some implementations, when more than one CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the CSI-RS / SSB resources, the UE may determine the linkage by selecting a CSI reference resource of one of the multiple first CSI reports that is earlier than the transmission occasion of one of the multiple CSI-RS / SSB resources for RS-PAI.

[0127] In some implementations, when more than one CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine the linkage by selecting a CSI reference resource of one of the multiple first CSI reports that is later than the transmission occasion of one of the multiple CSI-RS / SSB resources for RS-PAI.

[0128] In some implementations, when more than one CSI reference resources of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may randomly select one CSI reference resource from the more than one CSI reference resource of the one of the multiple first CSI report having equal minimal time offsets for linkage. In other words, it is up to UE implementation to select one CSI reference resource of the one of the multiple first CSI reports.

[0129] In some implementations, when more than one CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine the linkage based on a rule configured by RRC signaling, where the rule may specify whether to prefer earlier, later, or random linkage selection.

[0130] In some implementations, when more than one CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine that a CSI reference resource of one of the multiple first CSI reports that includes a higher L1-RSRP value is linked to the transmission occasion of the multiple CSI-RS / SSB resource. In some implementations, the maximum L1-RSRP value in the CSI report associated with the selected CSI reference resource is greater than the maximum L1-RSRP value in the other CSI report associated with the selected CSI reference resource.

[0131] In some implementations, when more than one CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine a CSI reference resource of one of the multiple first CSI reports based on the evaluation of prediction quality indicators, such as the associated CSI report with the lowest differential L1-RSRP value between the predicted L1-RSRP value and L1-RSRP value of CSI-RS / SSB resource for RS-PAI.

[0132] In some implementations, when more than CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may delay the determination of the linkage and may wait for additional transmission occasions of CSI-RS / SSB resources before the transmission of the second CSI report until a maximum threshold value is reached. The maximum threshold value may be configured by an RRC parameter and may ensure that the CSI reference resource of the first CSI report with predicted L1-RSRP and the first CSI report are earlier than the CSI reference resource of the second CSI report with RS-PAI.

[0133] In some implementations, when more than one CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may select the CSI reference signal of one of the multiple first CSI reports as the linkage, where the one of the multiple first CSI reports may be temporally closest to the transmission occasion of the CSI-RS / SSB resource in the time domain, and the one of the multiple first CSI reports may be located before the transmission occasion of the CSI-RS / SSB resource. In some implementations, when more than one CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may select the CSI reference signal of one of the multiple first CSI reports as the linkage, where the one of the multiple first CSI reports may be temporally closest to the transmission occasion of the CSI-RS / SSB resource in the time domain, and the one of the multiple first CSI reports may be located after the transmission occasion of the CSI-RS / SSB resource. In some implementations, when more than one CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may select the CSI reference signal of one of the multiple first CSI reports as the linkage, where the one of the multiple first CSI reports may be the one whose absolute time difference to the transmission occasion of the CSI-RS / SSB resource is minimal.

[0134] In some implementations, when more than one CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine that all the CSI reports associated with the CSI reference resource with equivalent minimal time offset is linked to the transmission occasion of one of the CSI-RS / SSB resources.

[0135] In some implementations, the UE may not expect that more than one CSI reference resource of one of the multiple first CSI reports has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources.

[0136] For BM Case 2

[0137] In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine the linkage by selecting a specific time instance of predicted L1-RSRP that is earlier than the transmission occasion of the CSI-RS / SSB resource for RS-PAI.

[0138] In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine the linkage by selecting a specific time instance of predicted L1-RSRP that is later than the transmission occasion of the CSI-RS / SSB resource for RS-PAI.

[0139] In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may randomly select one specific time instance of predicted L1-RSRP of one of the multiple first CSI reports from more than one specific time instance having equal minimal time offsets for linkage. In other words, it is up to UE implementation to select one specific time instance of predicted L1-RSRP corresponding to one of the multiple first CSI reports.

[0140] In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine the linkage based on a rule configured by RRC signaling (e.g., an RRC parameter), where the rule may specify whether to prefer earlier, later, or random linkage selection.

[0141] In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine that a CSI report including a specific time instance of predicted L1-RSRP having a higher L1-RSRP value than the other CSI report including a specific time instance of predicted L1-RSRRP is linked to the transmission occasion of the CSI-RS / SSB resource. In some implementations, the maximum L1-RSRP value in the CSI report including the specific time instance of predicted L1-RSRP may be greater than the maximum L1-RSRP value in the other CSI report including the specific time instance of predicted L1-RSRP.

[0142] In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine a specific time instance of predicted L1-RSRP based on the evaluation of prediction quality indicators, such as the corresponding predicted L1-RSRP with the lowest differential L1-RSRP value between the predicted L1-RSRP value and L1-RSRP value of CSI-RS / SSB resource for RS-PAI.

[0143] In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may delay the determination of the linkage and may wait for additional transmission occasions of CSI-RS / SSB resources before the transmission of the second CSI report until a maximum threshold value is reached. The maximum threshold value may be configured by an RRC parameter and may ensure that the specific time instance of predicted L1-RSRP (e.g., N f-th time instances) and the first CSI report are earlier than the CSI reference resource of the second CSI report with RS-PAI.

[0144] In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may select a CSI report including the specific time instance of predicted L1-RSRP that is temporally closest to the transmission occasion of one of the multiple CSI-RS / SSB resources in the time domain as the linkage, where the CSI report may be located before the transmission occasion of one of the multiple CSI-RS / SSB resources. In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may select a CSI report including the specific time instance of predicted L1-RSRP that is temporally closest to the transmission occasion of one of the multiple CSI-RS / SSB resources in the time domain as the linkage, where the CSI report may be located after the transmission occasion of one of the multiple CSI-RS / SSB resources. In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may select a CSI report including the specific time instance of predicted L1-RSRP that is temporally closest to the transmission occasion of one of the multiple CSI-RS / SSB resources in the time domain as the linkage, where the CSI report may be the one whose absolute time difference to the transmission occasion of the multiple CSI-RS / SSB resources is minimal.

[0145] In some implementations, when more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources, the UE may determine that all the CSI reports including the specific time instance of predicted L1-RSRP with equivalent minimal time offset is linked to the transmission occasion of one of the CSI-RS / SSB resources.

[0146] In some implementations, the UE may not expect that more than one specific time instance of predicted L1-RSRP (e.g., N f-th time instances) has the same minimal time offset to the transmission occasion of one of the multiple CSI-RS / SSB resources.

[0147] FIG. 4 is a flowchart illustrating a method / process 400 performed by a UE for artificial intelligence (AI) / machine learning (ML)-based beam management in spatial domain, according to an example implementation of the present disclosure.

[0148] In the action 402, the process 400 may start by receiving, from a base station (BS), a first radio resource control (RRC) configuration for configuring multiple first channel state information (CSI) reports, each of the multiple first CSI reports may include a predicted layer 1 (L1)-reference signal received power (RSRP).

[0149] In the action 404, the process 400 may receive, from the BS, a second RRC configuration for configuring a reference signal resource set for channel measurement and a second CSI report, the reference signal resource set may include multiple reference signal resources and the second CSI report may include at least one reference signal-prediction accuracy indicator (RS-PAI).

[0150] In the action 406, the process 400 may determine a linkage between each of the multiple first CSI reports and each of multiple transmission occasions of the multiple reference signal resources based on at least one CSI reference resource for each of the multiple first CSI reports that has a minimal time offset to a corresponding transmission occasion of the multiple transmission occasions.

[0151] In the action 408, the process 400 may perform L1-RSRP measurements for the multiple reference signal resources based on the determined linkage.

[0152] In the action 410, the process 400 may transmit, to the BS, the multiple first CSI reports and the second CSI report, where an index of the first RRC configuration may be included in the second RRC configuration. The process 400 may then end.

[0153] In some implementations, the multiple reference signal resources may include multiple channel state information-reference signals (CSI-RSs). In some implementations, the multiple reference signal resources may include multiple synchronization signal block (SSBs). In some implementations, the minimal time offset may include one or more slots.

[0154] The steps / actions shown in FIG. 4 should not be construed as necessarily order dependent. The order in which the process is described is not intended to be construed as a limitation. Moreover, some of the actions shown in FIG. 4 may be omitted in some implementations and one or more actions shown in FIG. 4 may be combined.

[0155] The technical problem addressed by the method illustrated in FIG. 4 is how to efficiently and accurately associate AI / ML-predicted L1-RSRP CSI reports with actual downlink reference signal transmission occasions in the spatial domain, particularly when the UE needs to perform L1-RSRP measurements on the reference signal resources based on the predicted results, while maintaining a clear linkage between the predicted CSI reports and the corresponding transmission occasions without introducing excessive signaling overhead. The advantageous technical effect achieved by the method illustrated in FIG. 4 is that it enables the UE to determine a precise linkage between each predicted CSI report and the corresponding transmission occasion of the reference signal resources based on the minimal time offset, and further allows the index of the first RRC configuration to be included in the second RRC configuration. This approach reduces signaling overhead, improves the accuracy of L1-RSRP measurements on the actual reference signal resources, and enhances the reliability of AI / ML-based beam management in the spatial domain by ensuring consistent and efficient association between predicted beam information and measured reference signals.

[0156] FIG. 5 is a block diagram illustrating a node 500 for wireless communication in accordance with various aspects of the present disclosure. As illustrated in FIG. 5, a node 500 may include a transceiver 520, a processor 528, a memory 534, one or more presentation components 538, and at least one antenna 536. The node 500 may also include a radio frequency (RF) spectrum band module, a BS communications module, a network communications module, and a system communications management module, Input / Output (I / O) ports, I / O components, and a power supply (not illustrated in FIG. 5).

[0157] Each of the components may directly or indirectly communicate with each other over one or more buses 540. The node 500 may be a UE or a BS that performs various functions disclosed with reference to FIGS. 1 through 4.

[0158] The transceiver 520 has a transmitter 522 (e.g., transmitting / transmission circuitry) and a receiver 524 (e.g., receiving / reception circuitry) and may be configured to transmit and / or receive time and / or frequency resource partitioning information. The transceiver 520 may be configured to transmit in different types of subframes and slots including, but not limited to, usable, non-usable, and flexibly usable subframes and slot formats. The transceiver 520 may be configured to receive data and control channels.

[0159] The node 500 may include a variety of computer-readable media. Computer-readable media may be any available media that may be accessed by the node 500 and include volatile (and / or non-volatile) media and removable (and / or non-removable) media.

[0160] The computer-readable media may include computer-storage media and communication media. Computer-storage media may include both volatile (and / or non-volatile media), and removable (and / or non-removable) media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, Artificial Intelligence (AI) / Machine Learning (ML) module(s), or data.

[0161] Computer-storage media may include RAM, DRAM, HBM, MRAM, FRAM, PRAM, ROM, EPROM, EEPROM, flash memory (or other memory technology), CD-ROM, Digital Versatile Disks (DVD) (or other optical disk storage), magnetic cassettes, magnetic tape, magnetic disk storage (or other magnetic storage devices), etc. Computer-storage media may not include a propagated data signal. Communication media may typically embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave, or other transport mechanisms and include any information delivery media.

[0162] The term “modulated data signal” may mean a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. Communication media may include wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above listed components should also be included within the scope of computer-readable media.

[0163] The memory 534 may include computer-storage media in the form of volatile and / or non-volatile memory. The memory 534 may be removable, non-removable, or a combination thereof. Example memory may include solid-state memory, hard drives, optical-disc drives, etc. As illustrated in FIG. 5, the memory 534 may store a computer-readable and / or computer-executable instructions 532 (e.g., software codes) that are configured to, when executed, cause the processor 528 to perform various functions disclosed herein, for example, with reference to FIGS. 1 through 4. Alternatively, the instructions 532 may not be directly executable by the processor 528 but may be configured to cause the node 500 (e.g., when compiled and executed) to perform various functions disclosed herein. The AI / ML module(s) may be implemented with a supervised learning approach or an unsupervised learning approach (e.g., Transductive approach and Inductive approach).

[0164] The processor 528 (e.g., having processing circuitry) may include an intelligent hardware device, e.g., a Central Processing Unit (CPU), a microcontroller, an ASIC, etc. The processor 528 may include memory. The processor 528 may process the data 530 and the instructions 532 received from the memory 534, and information transmitted and received via the transceiver 520, the baseband communications module, and / or the network communications module. The processor 528 may also process information to send to the transceiver 520 for transmission via the antenna 536 to the network communications module for transmission to a CN.

[0165] One or more presentation components 538 may present data indications to a person or another device. Examples of presentation components 538 may include a display device, a speaker, a printing component, a vibrating component, etc.

[0166] In view of the present disclosure, it is obvious that various techniques may be used for implementing the disclosed concepts without departing from the scope of those concepts. Moreover, while the concepts have been disclosed with specific reference to certain implementations, a person of ordinary skill in the art may recognize that changes may be made in form and detail without departing from the scope of those concepts. As such, the disclosed implementations are to be considered in all respects as illustrative and not restrictive. It should also be understood that the present disclosure is not limited to the particular implementations disclosed and many rearrangements, modifications, and substitutions are possible without departing from the scope of the present disclosure.

Claims

1. A user equipment (UE) for artificial intelligence (AI) / machine learning (ML)-based beam management in spatial domain, the UE comprising:   at least one processor; and   at least one non-transitory computer-readable medium coupled to the at least one processor and storing one or more computer-executable instructions that, when executed by the at least one processor, cause the UE to:     receive, from a base station (BS), a first radio resource control (RRC) configuration for configuring a plurality of first channel state information (CSI) reports, each of the plurality of first CSI reports comprising a predicted layer 1 (L1)-reference signal received power (RSRP);     receive, from the BS, a second RRC configuration for configuring a reference signal resource set for channel measurement and a second CSI report, the reference signal resource set comprising a plurality of reference signal resources and the second CSI report comprising at least one reference signal-prediction accuracy indicator (RS-PAI);     determine a linkage between each of the plurality of first CSI reports and each of a plurality of transmission occasions of the plurality of reference signal resources based on at least one CSI reference resource for each of the plurality of first CSI reports that has a minimal time offset to a corresponding transmission occasion of the plurality of transmission occasions;     perform L1-RSRP measurements for the plurality of reference signal resources based on the determined linkage; and     transmit, to the BS, the plurality of first CSI reports and the second CSI report,       wherein an index of the first RRC configuration is included in the second RRC configuration.

2. The UE of claim 1, wherein the plurality of reference signal resources comprises a plurality of channel state information-reference signals (CSI-RSs).

3. The UE of claim 1, wherein the plurality of reference signal resources comprises a plurality of synchronization signal block (SSBs).

4. The UE of claim 1, wherein the minimal time offset comprises one or more slots.

5. A method performed by a user equipment (UE) for artificial intelligence (AI) / machine learning (ML)-based beam management in spatial domain, the method comprising:   receiving, from a base station (BS), a first radio resource control (RRC) configuration for configuring a plurality of first channel state information (CSI) reports, each of the plurality of first CSI reports comprising a predicted layer 1 (L1)-reference signal received power (RSRP);   receiving, from the BS, a second RRC configuration for configuring a reference signal resource set for channel measurement and a second CSI report, the reference signal resource set comprising a plurality of reference signal resources and the second CSI report comprising at least one reference signal-prediction accuracy indicator (RS-PAI);   determining a linkage between each of the plurality of first CSI reports and each of a plurality of transmission occasions of the plurality of reference signal resources based on at least one CSI reference resource for each of the plurality of first CSI reports that has a minimal time offset to a corresponding transmission occasion of the plurality of transmission occasions;   performing L1-RSRP measurements for the plurality of reference signal resources based on the determined linkage; and   transmitting, to the BS, the plurality of first CSI reports and the second CSI report,     wherein an index of the first RRC configuration is included in the second RRC configuration.

6. A base station (BS) for artificial intelligence (AI) / machine learning (ML)-based beam management in spatial domain, the BS comprising:   at least one processor; and   at least one non-transitory computer-readable medium coupled to the at least one processor and storing one or more computer-executable instructions that, when executed by the at least one processor, cause the BS to:     transmit, to a user equipment (UE), a first radio resource control (RRC) configuration for configuring a plurality of first channel state information (CSI) reports, each of the plurality of first CSI reports comprising a predicted layer 1 (L1)-reference signal received power (RSRP); and     transmit, to the UE, a second RRC configuration for configuring a reference signal resource set for channel measurement and a second CSI report, the reference signal resource set comprising a plurality of reference signal resources and the second CSI report comprising at least one reference signal-prediction accuracy indicator (RS-PAI), wherein the first RRC configuration and the second RRC configuration cause the UE to:       determine a linkage between each of the plurality of first CSI reports and each of a plurality of transmission occasions of the plurality of reference signal resources based on at least one CSI reference resource for each of the plurality of first CSI reports that has a minimal time offset to a corresponding transmission occasion of the plurality of transmission occasions;       perform L1-RSRP measurements for the plurality of reference signal resources based on the determined linkage; and       transmit, to the BS, the plurality of first CSI reports and the second CSI report,         wherein an index of the first RRC configuration is included in the second RRC configuration.

7. The BS of claim 6, wherein the plurality of reference signal resources comprises a plurality of channel state information-reference signals (CSI-RSs).

8. The BS of claim 6, wherein the plurality of reference signal resources comprises a plurality of synchronization signal block (SSBs).

9. The BS of claim 6, wherein the minimal time offset comprises one or more slots.