Configuration of beam measurement and beam reporting for AI-based beam prediction

Abstract

Methods and apparatus are disclosed. In one embodiment, a UE includes a transceiver; and a processor coupled to the transceiver, where the processor is configured to report, via the transceiver, a set of parameters defining an AI / ML model for beam prediction; and receiving, via the transceiver, a configuration of CSI reporting settings associated with the AI / ML model, where the CSI reporting settings are associated with one CSI resource setting for beam prediction and one CSI resource setting for beam measurement.

Description

Technical Field

[0001] The subject matter disclosed herein relates generally to wireless communications, and more particularly to methods and apparatus for configuration of beam measurements and beam reporting for AI-based beam prediction. Background Art

[0002] The following abbreviations are defined herein, at least some of which are referenced in the following description: New Radio (NR), Very Large Scale Integration (VLSI), Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM or Flash), Compact Disc Read Only Memory (CD-ROM), Local Area Network (LAN), Wide Area Network (WAN), User Equipment (UE), Evolved Node B (eNB), Next Generation Node B (gNB), Uplink (UL), Downlink (DL), Central Processing Unit (CPU), Graphics Processing Unit (GPU), Field Programmable Gate Array (FPGA), Orthogonal Frequency Division Multiplexing (OFDM), Radio Resource Control (RRC), User Entity / Equipment (Mobile Terminal), Transmitter (TX ), receiver (RX), machine learning (ML), artificial intelligence (AI), base station (BS), deep neural network (DNN), recurrent neural network (RNN), reference signal received power (RSRP), layer 1 reference signal received power (L1-RSRP), cyclic prefix (CP), physical downlink control channel (PDCCH), channel state information (CSI), channel state information reference signal (CSI-RS), subcarrier space (SCS), non-zero power (NZP), synchronization signal (SS), physical broadcast channel (PBCH), SS / PBCH block (SSB), medium access control (MAC), control unit (CE), bandwidth part (BWP), quasi co-location (QCL), CSI-RS resource indicator (CRI).

[0003] Machine Learning (MI) is a method to implement Artificial Intelligence (AI). In the following description, they are referred to as AI / ML. Beam prediction based on AI / ML is studied in NR Release 18 to reduce signaling overhead, especially for the case where a larger number of beams are adopted by the base station (BS) and / or UE. A potential use case is that the AI / ML function is deployed in the UE, and the UE is able to predict the beams in beam set A based on the beam measurements in beam set B, where beam set A includes a larger number of beams and beam set B includes a small number of beams.

[0004] The present invention aims to support such AI / ML-based beam prediction. Summary of the invention

[0005] Methods and apparatus for configuration of beam measurements and beam reporting for AI-based beam prediction are disclosed.

[0006] In one embodiment, the UE includes a transceiver; and a processor coupled to the transceiver, wherein the processor is configured to report, via the transceiver, a set of parameters for defining an AI / ML model for beam prediction; and receive, via the transceiver, a configuration of a CSI reporting setting associated with the AI / ML model, wherein the CSI reporting setting is associated with a CSI resource setting for beam prediction and a CSI resource setting for beam measurement.

[0007] In some embodiments, the parameters include: the number of beams configured in a measurement beam set for input to an AI / ML model; the maximum number of beams that can be configured in a prediction beam set for beam prediction; supported measurement beam construction modes; and an indication of whether beam prediction requires additional AI / ML processing time for CSI calculation. Additionally, if the indication indicates that beam prediction requires additional AI / ML processing time for CSI calculation, the parameters also include the additional AI / ML processing time for CSI calculation.

[0008] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the following CSI calculation timing requirements are met: Defined as the next UL symbol with its CP starting after the last symbol of the PDCCH triggering the CSI report containing the beam report corresponding to the AI / ML based beam prediction ends ;as well as Defined as when aperiodic CSI-RS is used for channel measurement for a triggered CSI report containing a beam report corresponding to AI / ML based beam prediction, after the last symbol of the aperiodic CSI-RS time for channel measurement ends, the next UL symbol has its CP start ,in, and is the CSI computation time specified without AI / ML inference, and, if additional AI / ML processing time is required, reported by the UE and , and if no additional AI / ML processing time is required, then and is 0. Optionally, and have the same value.

[0009] In some embodiments, if the measurement beam set indicated in one CSI resource setting for beam measurement is a subset of the prediction beam set indicated in one CSI resource setting for beam prediction, the measurement beam set is configured by a bitmap of the prediction beam set, each bit of the bitmap being Indicates whether the i+1th beam in the predicted beam set is indicated as the measurement beam, i is from 0 to the number of beams in the predicted beam set minus 1, and the number of bits of the bitmap indicating that the i+1th beam in the predicted beam set is indicated as the measurement beam is equal to the number of beams in the measurement beam set. Optionally, the bitmap can be updated by the MAC CE. Further, the AI / ML model associated with the CSI report configuration can be updated by the MAC CE.

[0010] In some embodiments, if a measurement beam set indicated in a CSI resource setting for beam measurement and a prediction beam set indicated in a CSI resource setting for beam prediction are different beam sets, any beam in the prediction beam set is QCL-Type C and QCL-Type D with respect to a beam in the measurement beam set.

[0011] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the predicted beam reported in the beam report is selected from a predicted beam set indicated in a CSI resource setting for beam prediction. In particular, the bit width of the CRI field in the CSI report is determined by the number of beams included in the beam prediction set, where The k+1th entry of the configuration corresponding to the resources in the predicted beam set. In another embodiment, a method performed at a UE includes: reporting a set of parameters for defining an AI / ML model for beam prediction; and receiving a configuration of a CSI reporting setting associated with the AI / ML model, wherein the CSI reporting setting is associated with one CSI resource setting for beam prediction and one CSI resource setting for beam measurement.

[0012] In another embodiment, the base unit includes a transceiver; and a processor coupled to the transceiver, wherein the processor is configured to receive, via the transceiver, a set of parameters for defining an AI / ML model for beam prediction, and to transmit, via the transceiver, a configuration of a CSI report setting associated with the AI / ML model, wherein the CSI report setting is associated with one CSI resource setting for beam prediction and one CSI resource setting for beam measurement.

[0013] In some embodiments, the parameters include: the number of beams configured in the measurement beam set for input to the AI / ML model; the maximum number of beams that can be configured in the prediction beam set for beam prediction; supported measurement beam construction modes; and an indication of whether beam prediction requires additional AI / ML processing time for CSI calculation. Additionally, if the indication indicates that beam prediction requires additional AI / ML processing time for CSI calculation, the parameters also include the additional AI / ML processing time for CSI calculation.

[0014] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the following CSI calculation timing requirements are met: Defined as the next UL symbol with its CP starting after the last symbol of the PDCCH triggering the CSI report containing the beam report corresponding to the AI / ML based beam prediction ends ;as well as Defined as when aperiodic CSI-RS is used for channel measurement for a triggered CSI report containing a beam report corresponding to AI / ML based beam prediction, after the last symbol of the aperiodic CSI-RS time for channel measurement ends, the next UL symbol has its CP start ,in, and is the CSI computation time specified without AI / ML inference, and, if additional AI / ML processing time is required, reported by the UE and , if no additional AI / ML processing time is required, then and is 0. Optionally, and have the same value.

[0015] In some embodiments, if the measurement beam set indicated in one CSI resource setting for beam measurement is a subset of the prediction beam set indicated in one CSI resource setting for beam prediction, the measurement beam set is configured by a bitmap of the prediction beam set, each bit of the bitmap being Indicates whether the i+1th beam in the predicted beam set is indicated as the measurement beam, i is from 0 to the number of beams in the predicted beam set minus 1, and the number of bits of the bitmap indicating that the i+1th beam in the predicted beam set is indicated as the measurement beam is equal to the number of beams in the measurement beam set. Optionally, the bitmap can be updated by the MAC CE. Further, the AI / ML model associated with the CSI report configuration can be updated by the MAC CE.

[0016] In some embodiments, if a measurement beam set indicated in a CSI resource setting for beam measurement and a prediction beam set indicated in a CSI resource setting for beam prediction are different beam sets, any beam in the prediction beam set is QCL-Type C and QCL-Type D with respect to a beam in the measurement beam set.

[0017] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the predicted beam reported in the beam report is selected from a predicted beam set indicated in a CSI resource setting for beam prediction. In particular, the bit width of the CRI field in the CSI report is determined by the number of beams included in the beam prediction set, where The k+1th entry of the configuration corresponding to the resources in the predicted beam set. In another embodiment, a method performed at a base unit includes: receiving a set of parameters for defining an AI / ML model for beam prediction; and transmitting a configuration of a CSI report setting associated with the AI / ML model, wherein the CSI report setting is associated with one CSI resource setting for beam prediction and one CSI resource setting for beam measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The embodiments briefly described above will be described in more detail with reference to specific embodiments shown in the accompanying drawings. Understanding that these drawings depict only some embodiments and are not therefore to be considered limiting in scope, the embodiments will be described and explained with additional specificity and detail through the use of the accompanying drawings, in which:

[0019] Figure 1 The principle of AI / ML-based beam prediction in the spatial domain is shown;

[0020] Figure 2 The two CSI processing time requirements for deployed AI / ML models are shown;

[0021] Figure 3 The supported measurement beam configuration mode 1 is shown;

[0022] Figure 4 The supported measurement beam configuration mode 2 is shown;

[0023] Figure 5 An example of a MAC CE for measuring beam set updates is shown;

[0024] Figure 6 is a schematic flow chart illustrating an embodiment of a method;

[0025] Figure 7is a schematic flow chart illustrating an embodiment of another method; and

[0026] Figure 8 is a schematic block diagram illustrating an apparatus according to an embodiment. DETAILED DESCRIPTION

[0027] As will be appreciated by those skilled in the art, certain aspects of the embodiments may be embodied as a system, apparatus, method, or program product. Thus, the embodiments may take the form of a fully hardware embodiment, a fully software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, which are generally referred to herein as "circuits," "modules," or "systems." In addition, the embodiments may take the form of a program product embodied in one or more computer-readable storage devices that store machine-readable code, computer-readable code, and / or program code, hereinafter referred to as "code." The storage device may be tangible, non-transient, and / or non-transmitting. The storage device may not embody a signal. In a certain embodiment, the storage device employs signals only for accessing the code.

[0028] Certain functional units described in this specification may be labeled as "modules" to more specifically emphasize their independent implementation. For example, a module may be implemented as a hardware circuit that includes a custom very large scale integrated circuit (VLSI) circuit or gate array, an off-the-shelf semiconductor such as a logic chip, a transistor, or other discrete components. A module may also be implemented in a programmable hardware device such as a field programmable gate array, a programmable array logic, a programmable logic device, etc.

[0029] Modules may also be implemented in the form of code and / or software for execution by various types of processors. For example, an identified code module may include one or more physical or logical executable code blocks that may be organized as objects, procedures, or functions. Nevertheless, the executable files of an identified module do not have to be physically located together, but may include different instructions stored in different locations that, when logically combined together, comprise the module and achieve the intended purpose of the module.

[0030] In practice, a code module may contain one or more instructions, and may even be distributed across multiple different code segments, different programs, and multiple storage devices. Similarly, operational data within a module may be identified and described herein, and may be embodied in any suitable form and organized in any suitable type of data structure. Such operational data may be collected as a single data set, or may be distributed in different locations, including different computer-readable storage devices. When a module or some portion of a module is implemented in software, the software portion is stored on one or more computer-readable storage devices.

[0031] Any combination of one or more computer readable media may be used. The computer readable medium may be a computer readable storage medium. The computer readable storage medium may be a storage device storing code. The storage device may be, for example, but not necessarily, an electronic, magnetic, optical, electromagnetic, infrared, holographic, micromechanical or semiconductor system, apparatus or device, or any suitable combination of the foregoing.

[0032] A non-exhaustive list of more specific examples of storage devices include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the context of this document, a computer-readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0033] The code for performing the operations of the embodiments may include any number of lines and may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Python, Ruby, Java, Smalltalk, C++, etc., as well as conventional procedural programming languages ​​such as the "C" programming language, etc., and / or machine languages ​​such as assembly language. The code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0034] Throughout the specification, references to "one embodiment," "an embodiment," or similar language mean that a particular feature, structure, or characteristic associated with the embodiment is included in at least one embodiment. Therefore, the phrases "in one embodiment," "in an embodiment," and similar language appearing throughout the specification may (but do not necessarily) all refer to the same embodiment, but rather mean "one or more but not all embodiments," unless expressly specified otherwise. The terms "comprises," "comprising," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise. Unless expressly specified otherwise, an enumerated list of items does not mean that any or all of the items are mutually exclusive. The terms "a," "an," and "the" also refer to "one or more," unless expressly specified otherwise.

[0035] In addition, the features, structures or characteristics of the various embodiments may be combined in any suitable manner. In the following description, many specific details are provided, such as examples of programming, software modules, user selections, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, etc., to provide a thorough understanding of the embodiments. However, those skilled in the relevant art will recognize that the embodiments may be implemented without one or more of the specific details or using other methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid confusing aspects of the embodiments.

[0036] Various aspects of different embodiments will be described below with reference to the schematic flow charts and / or schematic block diagrams of the methods, devices, systems, and program products according to the embodiments. It will be understood that each box in the schematic flow chart and / or schematic block diagram and the combination of boxes in the schematic flow chart and / or schematic block diagram can be implemented by code. The code can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to generate a machine, so that instructions executed by the processor of the computer or other programmable data processing device create a device for implementing the functions specified in the schematic flow chart and / or schematic block diagram for the box or boxes.

[0037] The code may also be stored in a storage device that can instruct a computer, other programmable data processing device, or other device to operate in a specific manner so that the instructions stored in the storage device produce an article of manufacture, including instructions that implement the functions specified in the schematic flowchart and / or schematic block diagram box or multiple boxes.

[0038] The code may also be loaded onto a computer, other programmable data processing device, or other device, so that a series of operational steps are performed on the computer, other programmable device, or other device to produce a computer-implemented process, so that the code executed on the computer or other programmable device provides a process for implementing the functions specified in the flowchart and / or block diagram box or multiple boxes.

[0039] The schematic flow charts and / or schematic block diagrams in the figure illustrate the architecture, functions and operations that may be implemented according to the devices, systems, methods and program products of various embodiments. In this regard, each box in the schematic flow charts and / or schematic block diagrams may represent a module, a segment or a part of code, which includes one or more executable instructions for implementing the code of the specified logical function.

[0040] It should also be noted that in some alternative implementations, the functions indicated in the blocks may not be in the order shown in the figures. For example, two blocks shown in succession may be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order, depending on the functions involved. Other steps and methods are contemplated that are equivalent in function, logic, or effect to one or more blocks or portions thereof in the figures shown.

[0041] Although various arrow types and line types may be used in flow charts and / or block diagrams, it should be understood that they do not limit the scope of the corresponding embodiments. In fact, some arrows or other connectors may be used to indicate only the logical flow of the depicted embodiments. For example, an arrow may indicate a waiting or monitoring period of unspecified duration between the enumerated steps of the depicted embodiments. It should also be noted that each box in the block diagram and / or flow chart and the combination of boxes in the block diagram and / or flow chart may be implemented by a dedicated hardware system or a combination of dedicated hardware and code that performs a specified function or action.

[0042] The description of an element in each figure may refer to an element in a previous figure. The same numbers in all figures represent the same elements, including alternative embodiments of the same elements.

[0043] Figure 1 The principle of spatial domain beam prediction based on AI / ML is shown. The AI / ML model can be implemented through a deep neural network (DNN) or a recurrent neural network (RNN). Figure 1 As shown, an AI / ML model that can be used for beam prediction based on an AI / ML reasoning function is deployed on the UE or network (e.g., gNB) side. A measurement result (e.g., L1-RSRP) based on a beam measurement set (e.g., beam measurement set B) including a certain number of beams is set as an input to the AI / ML model. According to the AI / ML reasoning algorithm, the AI / ML model performs beam prediction on another beam prediction set (e.g., beam prediction set A) including a larger number of beams based on the input. By the way, the output of the AI / ML model can be a prediction result for any number of beams (e.g., 2 beams) contained in the beam prediction set.

[0044] This disclosure assumes that the AI / ML model 1 is deployed on the UE side.

[0045] The first embodiment relates to UE capabilities related to AL / ML.

[0046] A first sub-embodiment of the first embodiment involves measuring the number of beams in a beam set (eg, AI / ML input) and predicting the number of beams in a beam combination (eg, AI / ML output).

[0047] like Figure 1As shown, the input of the AI / ML model is the measurement results based on the measurement beam set B, and the output of the AI / ML model is the prediction results of any number of beams contained in the prediction beam set A. This means that each AI / ML model has at least two parameters to be defined:

[0048] (1) The number of beams configured in the measurement beam combination, and

[0049] (2) The maximum number of beams that can be configured in the prediction beam set.

[0050] For example, Table 1 shows examples of these two parameters used in different AI / ML models.

[0051]

[0052] Table 1

[0053] This means that when the UE reports or registers an AI / ML model that can be used for beam prediction, the UE shall indicate the number of measurement beams that should be configured in the measurement beam set (e.g. ) to get the input of the AI / ML model, and the maximum number of prediction beams that can be configured in a prediction beam set (for example, ). Therefore, for CSI reports of beam reports related to this AI / ML model, where the UE reports one or more beams that can be used for subsequent transmissions, the measurement beam set should be configured measurement beams, and the number of prediction beams configured in the prediction beam set should be equal to or less than .

[0054] Optionally, when the UE reports (1) the number of beams configured in the measurement beam set and (2) the maximum number of beams configured in the prediction beam set, other auxiliary information that can be set as AI / ML input for this AI / ML model can be additionally reported. For example, UE location information is an example of other auxiliary information that can be set as AI / ML input.

[0055] The second sub-embodiment of the first embodiment relates to CSI processing capabilities taking into account AI / ML model related processes.

[0056] Traditionally (i.e., without AI / ML models), CSI computation time is specified in NR Release 15. Two CSI processing time requirements are defined as follows: Defined as the next UL symbol with its CP starting after the last symbol of the PDCCH triggering the CSI report containing the beam report ends ;as well as Defined as when aperiodic CSI-RS is used for channel measurement for triggered CSI reporting, after the last symbol of the aperiodic CSI-RS time used for channel measurement ends, the next UL symbol has its CP start .

[0057] When an AI / ML model is deployed and used on the UE side for CSI calculation, the AI / ML model requires additional time for AI / ML inference (i.e., the time required from receiving AI / ML input to providing AI / ML output). Figure 2 As shown, the two CSI processing time requirements can be similarly defined as follows: , which is defined as the time after the last symbol of the PDCCH triggering the CSI report containing the beam report ends, and the next UL symbol has its CP starting ;as well as , which is defined as when aperiodic CSI-RS is used for channel measurement for a triggered CSI report containing a beam report corresponding to AI / ML-based beam prediction, after the last symbol of the aperiodic CSI-RS time for channel measurement ends, the next UL symbol has its CP starting .

[0058] Due to the additional time spent on AI reasoning, Greater than and Greater than . It can be assumed that: = + and + ,in, and represents the additional time of AI / ML reasoning for CSI calculation. and The value of is specific to AI / ML inference. This means that when one or more AI / ML models are reported or registered, the and The value of can be reported by the UE. Alternatively, when the AI / ML model is transferred from the gNB to the UE, the and The value of can be configured by the gNB.

[0059] and The number of symbols that can be reported or configured to correspond to different SCSs for each UE or each AI / ML model or each AI / ML type (e.g., AI / ML model for beam management or AI / ML model for CSI compression).

[0060] In some use cases, the AI / ML model for CSI compression may replace traditional CSI compression. In other words, the AI / ML model for CSI compression does not predict beams. This means that the additional AI / ML processing time for CSI calculation is not necessary for the AI / ML model for CSI compression. From another perspective, the additional AI / ML processing time for CSI calculation, i.e., and For AI / ML models used for CSI compression, it can be considered as 0.

[0061] In order to indicate the additional AI / ML processing time for CSI calculation for both the AI / ML model for beam management and the AI / ML model for CSI compression, an indication of whether the additional AI / ML processing time for CSI calculation is necessary can be reported. In addition, if the additional AI / ML processing time for CSI calculation is necessary (e.g., for the AI / ML model for beam management), the additional AI / ML processing time for CSI calculation is further reported, i.e., and On the other hand, if the additional AI / ML processing time for CSI calculation is not necessary (e.g., for an AI / ML model for CSI compression), then the additional AI / ML processing time for CSI calculation does not need to be further reported.

[0062] Optionally, and can have the same value.

[0063] The third sub-embodiment of the first embodiment relates to the supported measurement beam configurations. The supported measurement beam configurations refer to how the beam measurement set is constructed. Two alternative configurations are proposed:

[0064] Alternative 1: The beam measurement set (ie, set B) is a subset of the prediction beam set (ie, set A).

[0065] Alternative 2: The beam measurement set (ie, set B) and the predicted beam set (ie, set A) are different beam sets. For example, set A consists of narrow beams, and set B consists of wide beams.

[0066] Both Alternative 1 and Alternative 2 can be used for beam prediction. One alternative can be referred to as Mode 1, and the other alternative can be referred to as Mode 2. In the following description, Alternative 1 is referred to as Mode 1, and Alternative 2 is referred to as Mode 2.

[0067] Figure 3 An example of supported measurement beam configuration mode 1 is shown. Figure 3 All beams shown belong to prediction beam set A. Beams shown as solid lines belong to measurement beam set B, which is a subset of prediction beam set A. The two beams with grids are the two prediction beams selected from prediction beam set A, ie the two beams with the best quality.

[0068] Figure 4 An example of supported measurement beam construction mode 2 is shown. All narrow beams belong to prediction beam set A. All wide beams belong to measurement beam set B. Prediction beam set A and measurement beam set B include different beams. The two beams with the grid are two prediction beams selected from prediction beam set A, i.e., two beams with the best quality.

[0069] Different modes may correspond to different AI / ML inference algorithms and further be associated with different AI / ML models. Therefore, the UE shall report the required measurement beam configuration (e.g., Mode 1 or Mode 2) for each AI / ML model.

[0070] In general, for each AI / ML model, the following parameters can be reported:

[0071] The number of beams configured in the measurement beam set used as input for the AI / ML model;

[0072] The maximum number of beams that can be configured in the prediction beam set;

[0073] The supported measurement beam configuration modes; and

[0074] An indication of whether beam prediction requires additional AI / ML processing time for CSI calculation, wherein if the indication indicates that beam prediction requires additional AI / ML processing time for CSI calculation, the parameter also includes the additional AI / ML processing time for CSI calculation.

[0075] By the way, the parameters of the AI / ML model can be reported together.

[0076] The second embodiment relates to CSI measurement and reporting configuration for beam prediction.

[0077] The CSI framework based on the CSI report configuration is reused for beam prediction. Specifically, two resource settings are associated with the CSI report configuration (e.g., CSI-ReportConfig), each of the two resource settings is used to configure one or more resource sets for channel or interference measurement, one CSI resource setting is used to measure the beam set configuration and the other CSI resource setting is used to predict the beam configuration. An example of the CSI report configuration (CSI-ReportConfig) according to the second embodiment is as follows:

[0078]

[0079] Corresponding to the CSI resource setting for beam prediction Instructions include An NZP CSI-RS resource set (eg, with nzp-CSI-RS-ResourceSetId) of NZP CSI-RS resources, where each NZP CSI-RS resource corresponds to a beam for prediction.

[0080] Corresponding to the CSI resource setting for beam measurement Instructions include Another NZP CSI-RS resource set (eg, with nzp-CSI-RS-ResourceSetId) of NZP CSI-RS resources, where each NZP CSI-RS resource corresponds to a beam to be measured.

[0081] Indicates the AI / ML model associated with the CSI reporting configuration for beam prediction.

[0082] Can be set to cri-RSRP for beam reporting.

[0083] In the above CSI reporting configuration, and Each of the indications in includes a NZP CSI-RS resource set containing multiple NZP CSI-RS resources. Alternatively, and Any of the may indicate an SSB resource set containing multiple SSB resources. This means that the CSI resource setting configures one or more CSI-RS resource sets or SSB resource sets for channel and / or interference measurement.

[0084] For simplicity, in the following description, it is assumed that and Each indication in includes an NZP CSI-RS resource set containing multiple NZP CSI-RS resources.

[0085] The predicted beam reported in the beam report associated with the CSI report should be from the Therefore, the bit width of the CRI field in the CSI report is determined by the number of beams included in the beam prediction set (for example, by CRI Corresponds to the k+1th entry of the configuration of the NZP CSI-RS resources in the NZP CSI-RS resource set for the predicted beam.

[0086] The third embodiment is directed to configuring or determining the measurement beam set in Mode 1 (ie, the beam measurement set (ie, Set B) is a subset of the prediction beam set (ie, Set A).

[0087] The configuration of the measurement beam set can be a bitmap corresponding to all beams in the prediction beam set. Assume that the prediction beam set includes NZP CSI-RS resources. A bitmap, for example, (n = 0 to -1), that is, , , …, , , is configured for ,in, Can be set to '1' or '0', which corresponds to the (n+1)th NZP CSI-RS resource in the NZP CSI-RS resource set for beam prediction being activated (ie, selected) or deactivated (ie, not selected) for the measurement beam set. The number of sets is equal to , that is, the number of resources included in the beam measurement set.

[0088] For example, the UE is configured with a CSI reporting configuration associated with an AI / ML model for beam prediction. The associated AI / ML model supports mode 1. Further, the number of measurement beams used for AI / ML model input (i.e., the number of beams included in the beam measurement set) is = 16, and the maximum number of beams contained in the prediction beam set ( ) is 128. The gNB configures the CSI report configuration (CSI-ReportConfig) for beam prediction, where the predicted beam set is the same as the one containing (=64, which is less than ) NZP CSI-RS resources—for example, NZP CSI-RS resource #0, NZP CSI-RS resource #1, ..., NZP CSI-RS resource #63—are associated with an NZP CSI-RS resource set.

[0089] In this case, the configuration of the measurement beam set can be a length of 64 (= ) bits to indicate the beams included in the beam measurement set. The number of bits in the 64-bit bitmap that are set to '1' (i.e., indicating the (n+1)th NZP CSI-RS resource in the NZP CSI-RS resource set activated for beam prediction) shall be equal to = 16. For example, if the bitmap indicates 000100010001000100010001000100010001000100010001000100010001, the measurement beam set includes NZP CSI-RS resources #0, #4, #8, #12, #16, #20, #24, #28, #32, #36, #40, #44, #48, #52, #56, and #60.

[0090] If the beams included in the beam measurement set need to be changed, for example, when the scenario changes, the MAC CE can be used to update the beams included in the beam measurement set.

[0091] Figure 5 An example of a MAC CE for measurement beam set update of CSI-ReportConfig is shown.

[0092] exist Figure 5 In the MAC CE, the following fields are included:

[0093] Serving Cell ID (with 5 bits): The Serving Cell ID field indicates the identity of the serving cell to which the MAC CE applies.

[0094] BWP ID (having 2 bits): The BWP ID field indicates the BWP of the cell indicated by the Serving Cell ID field to which this MAC CE applies.

[0095] CSI Report Configuration ID (with 6 bits, assuming that a maximum of 64 CSI report configurations can be configured for the UE in the BWP of the serving cell): The CSI Report Configuration ID field indicates the CSI report configuration whose measurement beam set is updated.

[0096] AI / ML Model ID (with 2 bits, assuming a maximum of 4 AI / ML models registered by the UE): The AI / ML Model ID field indicates the AI / ML model associated with the CSI reporting configuration indicated by the CSI Reporting Configuration ID field.

[0097] : The (i+1)th NZP CSI-RS resource in the NZP CSI-RS resource set indicated for the predicted beam set is activated (i.e., selected) or deactivated (i.e., not selected) for the measurement beam set. indicates that the (i+1)th beam in the prediction beam set is deactivated (i.e., not selected) for the measurement beam and is set to 1 Indicates that the (i+1)th beam in the prediction beam set is activated (ie, selected) for the measurement beam. The number of fields is equal to the number of configured beams contained in the prediction beam set. For example, i = 0 to ,in, is satisfied The minimum integer number of configured beams included in the prediction beam set.

[0098] If the AI / ML Model ID included in the MAC CE changes, the AI / ML model associated with the CSI report configuration indicated by the CSI ReportConfiguration ID field can be updated.

[0099] The fourth embodiment relates to configuring or determining the measurement beam set in mode 2 (the beam measurement set (ie, set B) and the prediction beam set (ie, set A) are different beam sets.

[0100] In mode 2, respectively and Two different sets of NZP CSI-RS resources are configured. When the beams in the measurement beam set are different from the beams in the prediction beam set, any NZP CSI-RS resources in the prediction beam set should be QCLed with the NZP CSI-RS resources or SSB resources in the measurement beam set.

[0101] An example of Mode 2 is that a wide beam (e.g., SSB beam) is used for beam measurement and a narrow beam (e.g., TRS beam) is used for beam prediction, where each TRS within the prediction beam set is aligned with respect to QCL-TypeC and QCL-TypeD with respect to the SSB resource QCL contained in the measurement beam set, where QCL-TypeC: {Doppler shift, average delay}, and QCL-TypeD: {spatial Rx parameters}.

[0102] Figure 6 6 is a schematic flow chart showing an embodiment of a method 600 according to the present application. In some embodiments, the method 600 is performed by an apparatus, such as a remote unit (e.g., a UE). In some embodiments, the method 600 may be performed by a processor that executes program code, such as a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, an FPGA, etc.

[0103] Method 600 is a method performed at a UE, comprising: 602 reporting a set of parameters for defining an AI / ML model for beam prediction; and 604 receiving a configuration of a CSI report setting associated with the AI / ML model, wherein the CSI report setting is associated with a CSI resource setting for beam prediction and a CSI resource setting for beam measurement.

[0104] In some embodiments, the parameters include: the number of beams configured in the measurement beam set for input to the AI / ML model; the maximum number of beams that can be configured in the prediction beam set for beam prediction; supported measurement beam construction modes; and an indication of whether beam prediction requires additional AI / ML processing time for CSI calculation. Additionally, if the indication indicates that beam prediction requires additional AI / ML processing time for CSI calculation, the parameters also include the additional AI / ML processing time for CSI calculation.

[0105] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the following CSI calculation timing requirements are met: Defined as the next UL symbol with its CP starting after the last symbol of the PDCCH triggering the CSI report containing the beam report corresponding to the AI / ML based beam prediction ends ;as well as Defined as when aperiodic CSI-RS is used for channel measurement for a triggered CSI report containing a beam report corresponding to AI / ML based beam prediction, after the last symbol of the aperiodic CSI-RS time for channel measurement ends, the next UL symbol has its CP start ,in, and is the CSI computation time specified without AI / ML inference, and, if additional AI / ML processing time is required, reported by the UE and , and if no additional AI / ML processing time is required, then and is 0. Optionally, and have the same value.

[0106] In some embodiments, if the measurement beam set indicated in one CSI resource setting for beam measurement is a subset of the prediction beam set indicated in one CSI resource setting for beam prediction, the measurement beam set is configured by a bitmap of the prediction beam set, each bit of the bitmap being Indicates whether the (i+1)th beam in the predicted beam set is indicated as the measurement beam, i is from 0 to the number of beams in the predicted beam set minus 1, and the number of bits of the bitmap indicating that the (i+1)th beam in the predicted beam set is indicated as the measurement beam is equal to the number of beams in the measurement beam set. Optionally, the bitmap can be updated by the MAC CE. Further, the AI / ML model associated with the CSI report configuration can be updated by the MAC CE.

[0107] In some embodiments, if a measurement beam set indicated in a CSI resource setting for beam measurement and a prediction beam set indicated in a CSI resource setting for beam prediction are different beam sets, any beam in the prediction beam set is QCL-Type C and QCL-Type D with respect to a beam in the measurement beam set.

[0108] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the predicted beam reported in the beam report is selected from a predicted beam set indicated in a CSI resource setting for beam prediction. In particular, the bit width of the CRI field in the CSI report is determined by the number of beams included in the beam prediction set, where The k+1th entry corresponding to the configuration of resources in the prediction beam set.

[0109] Figure 7 700 is a schematic flow chart showing an embodiment of a method 700 according to the present application. In some embodiments, the method 700 is performed by a device such as a base unit. In some embodiments, the method 700 can be performed by a processor that executes program code, such as a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, an FPGA, etc.

[0110] Method 700 may include 702 receiving a set of parameters for defining an AI / ML model for beam prediction; and 704 transmitting a configuration of a CSI report setting associated with the AI / ML model, wherein the CSI report setting is associated with a CSI resource setting for beam prediction and a CSI resource setting for beam measurement.

[0111] In some embodiments, the parameters include: the number of beams configured in the measurement beam set for input to the AI / ML model; the maximum number of beams that can be configured in the prediction beam set for beam prediction; supported measurement beam construction modes; and an indication of whether beam prediction requires additional AI / ML processing time for CSI calculation. Additionally, if the indication indicates that beam prediction requires additional AI / ML processing time for CSI calculation, the parameters also include the additional AI / ML processing time for CSI calculation.

[0112] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the following CSI calculation timing requirements are met: , which is defined as the next UL symbol with its CP starting after the last symbol of the PDCCH triggering the CSI report containing the beam report corresponding to the AI / ML based beam prediction ends ;as well as , which is defined as when aperiodic CSI-RS is used for channel measurement for a triggered CSI report containing a beam report corresponding to AI / ML-based beam prediction, after the last symbol of the aperiodic CSI-RS time for channel measurement ends, the next UL symbol has its CP starting ,in, and is the CSI computation time specified without AI / ML inference, and, if additional AI / ML processing time is required, reported by the UE and , and if no additional AI / ML processing time is required, then and is 0. Optionally, and have the same value.

[0113] In some embodiments, if the measurement beam set indicated in one CSI resource setting for beam measurement is a subset of the prediction beam set indicated in one CSI resource setting for beam prediction, the measurement beam set is configured by a bitmap of the prediction beam set, each bit of the bitmap being Indicates whether the (i+1)th beam in the predicted beam set is indicated as the measurement beam, i is from 0 to the number of beams in the predicted beam set minus 1, and the number of bits of the bitmap indicating that the (i+1)th beam in the predicted beam set is indicated as the measurement beam is equal to the number of beams in the measurement beam set. Optionally, the bitmap can be updated by the MAC CE. Further, the AI / ML model associated with the CSI report configuration can be updated by the MAC CE.

[0114] In some embodiments, if a measurement beam set indicated in a CSI resource setting for beam measurement and a prediction beam set indicated in a CSI resource setting for beam prediction are different beam sets, any beam in the prediction beam set is QCL-Type C and QCL-Type D with respect to a beam in the measurement beam set.

[0115] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the predicted beam reported in the beam report is selected from a predicted beam set indicated in a CSI resource setting for beam prediction. In particular, the bit width of the CRI field in the CSI report is determined by the number of beams included in the beam prediction set, where The k+1th entry corresponding to the configuration of resources in the prediction beam set.

[0116] Figure 8 is a schematic block diagram illustrating an apparatus according to an embodiment.

[0117] refer to Figure 8 , the UE (ie, remote unit) includes a processor, a memory, and a transceiver. The processor implements Figure 6 The functions, processes and / or methods proposed in.

[0118] The UE includes a transceiver; and a processor coupled to the transceiver, wherein the processor is configured to report, via the transceiver, a set of parameters for defining an AI / ML model for beam prediction; and receive, via the transceiver, a configuration of a CSI report setting associated with the AI / ML model, wherein the CSI report setting is associated with a CSI resource setting for beam prediction and a CSI resource setting for beam measurement.

[0119] In some embodiments, the parameters include: the number of beams configured in the measurement beam set for input to the AI / ML model; the maximum number of beams that can be configured in the prediction beam set for beam prediction; supported measurement beam construction modes; and an indication of whether beam prediction requires additional AI / ML processing time for CSI calculation. Additionally, if the indication indicates that beam prediction requires additional AI / ML processing time for CSI calculation, the parameters also include the additional AI / ML processing time for CSI calculation.

[0120] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the following CSI calculation timing requirements are met: , which is defined as the next UL symbol with its CP starting after the last symbol of the PDCCH triggering the CSI report containing the beam report corresponding to the AI / ML based beam prediction ends ;as well as , which is defined as when aperiodic CSI-RS is used for channel measurement for a triggered CSI report containing a beam report corresponding to AI / ML-based beam prediction, after the last symbol of the aperiodic CSI-RS time for channel measurement ends, the next UL symbol has its CP starting ,in, and is the CSI computation time specified without AI / ML inference, and, if additional AI / ML processing time is required, reported by the UE and , and if no additional AI / ML processing time is required, then and is 0. Optionally, and have the same value.

[0121] In some embodiments, if the measurement beam set indicated in one CSI resource setting for beam measurement is a subset of the prediction beam set indicated in one CSI resource setting for beam prediction, the measurement beam set is configured by a bitmap of the prediction beam set, each bit of the bitmap being Indicates whether the (i+1)th beam in the predicted beam set is indicated as the measurement beam, i is from 0 to the number of beams in the predicted beam set minus 1, and the number of bits of the bitmap indicating that the (i+1)th beam in the predicted beam set is indicated as the measurement beam is equal to the number of beams in the measurement beam set. Optionally, the bitmap can be updated by the MAC CE. Further, the AI / ML model associated with the CSI report configuration can be updated by the MAC CE.

[0122] In some embodiments, if a measurement beam set indicated in a CSI resource setting for beam measurement and a prediction beam set indicated in a CSI resource setting for beam prediction are different beam sets, any beam in the prediction beam set is QCL-Type C and QCL-Type D with respect to a beam in the measurement beam set.

[0123] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the predicted beam reported in the beam report is selected from a predicted beam set indicated in a CSI resource setting for beam prediction. In particular, the bit width of the CRI field in the CSI report is determined by the number of beams included in the beam prediction set, where The k+1th entry corresponding to the configuration of resources in the prediction beam set.

[0124] The gNB (i.e., base unit) includes a processor, memory, and a transceiver. Figure 7 The functions, processes and / or methods proposed in the.

[0125] The basic unit includes a transceiver; and a processor coupled to the transceiver, wherein the processor is configured to receive, via the transceiver, a set of parameters for defining an AI / ML model for beam prediction, and to transmit, via the transceiver, a configuration of a CSI report setting associated with the AI / ML model, wherein the CSI report setting is associated with a CSI resource setting for beam prediction and a CSI resource setting for beam measurement.

[0126] In some embodiments, the parameters include: the number of beams configured in the measurement beam set for input to the AI / ML model; the maximum number of beams that can be configured in the prediction beam set for beam prediction; supported measurement beam construction modes; and an indication of whether beam prediction requires additional AI / ML processing time for CSI calculation. Additionally, if the indication indicates that beam prediction requires additional AI / ML processing time for CSI calculation, the parameters also include the additional AI / ML processing time for CSI calculation.

[0127] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the following CSI calculation timing requirements are met: , which is defined as the next UL symbol with its CP starting after the last symbol of the PDCCH triggering the CSI report containing the beam report corresponding to the AI / ML based beam prediction ends ;as well as , which is defined as when aperiodic CSI-RS is used for channel measurement for a triggered CSI report containing a beam report corresponding to AI / ML-based beam prediction, after the last symbol of the aperiodic CSI-RS time for channel measurement ends, the next UL symbol has its CP starting ,in, and is the CSI computation time specified without AI / ML inference, and, if additional AI / ML processing time is required, reported by the UE and , and if no additional AI / ML processing time is required, then and is 0. Optionally, and have the same value.

[0128] In some embodiments, if the measurement beam set indicated in one CSI resource setting for beam measurement is a subset of the prediction beam set indicated in one CSI resource setting for beam prediction, the measurement beam set is configured by a bitmap of the prediction beam set, each bit of the bitmap being Indicates whether the (i+1)th beam in the predicted beam set is indicated as the measurement beam, i is from 0 to the number of beams in the predicted beam set minus 1, and the number of bits of the bitmap indicating that the (i+1)th beam in the predicted beam set is indicated as the measurement beam is equal to the number of beams in the measurement beam set. Optionally, the bitmap can be updated by the MAC CE. Further, the AI / ML model associated with the CSI report configuration can be updated by the MAC CE.

[0129] In some embodiments, if a measurement beam set indicated in a CSI resource setting for beam measurement and a prediction beam set indicated in a CSI resource setting for beam prediction are different beam sets, any beam in the prediction beam set is QCL-Type C and QCL-Type D with respect to a beam in the measurement beam set.

[0130] In some embodiments, for aperiodic CSI reporting of beam reports associated with an AI / ML model for beam prediction, the predicted beam reported in the beam report is selected from a predicted beam set indicated in a CSI resource setting for beam prediction. In particular, the bit width of the CRI field in the CSI report is determined by the number of beams included in the beam prediction set, where The k+1th entry corresponding to the configuration of resources in the prediction beam set.

[0131] Each layer of the radio interface protocol can be implemented by a processor. The memory is connected to the processor to store various information for driving the processor. The transceiver is connected to the processor to transmit and / or receive radio signals. Needless to say, the transceiver can be implemented as a transmitter to transmit radio signals and a receiver to receive radio signals.

[0132] The memory may be located inside or outside the processor and connected to the processor through various well-known means.

[0133] In the above-described embodiments, the components and features of the embodiments are combined in a predetermined form. Unless otherwise explicitly stated, each component or feature should be considered as an option. Each component or feature can be implemented as not associated with other components or features. In addition, the embodiments can be configured by associating some components and / or features. The order of the operations described in the embodiments can be changed. Some components or features of any embodiment can be included in another embodiment, or replaced with components and features corresponding to another embodiment. Obviously, claims that are not explicitly cited in the claims can be combined to form embodiments or included in new claims.

[0134] The embodiments may be implemented by hardware, firmware, software or a combination thereof. In the case of being implemented by hardware, according to the hardware implementation, the exemplary embodiments described herein may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, etc.

[0135] Embodiments may be practiced in other specific forms. The described embodiments should be considered in all respects to be illustrative only and not restrictive. Therefore, the scope of the present invention is indicated by the appended claims rather than the foregoing description. All changes that fall within the equivalent meaning and scope of the claims should be included within their scope.

Claims

1. A user equipment (UE), comprising: Transceiver; as well as a processor coupled to the transceiver, wherein the processor is configured to reporting, via the transceiver, a set of parameters defining an AI / ML model for beam prediction; and A configuration of a CSI reporting setting associated with the AI / ML model is received via the transceiver, wherein the CSI reporting setting is associated with one CSI resource setting for beam prediction and one CSI resource setting for beam measurement.

2. The UE according to claim 1, wherein: The parameters include: the number of beams configured in the set of measurement beams used as input to the AI / ML model; the maximum number of beams that can be configured in a prediction beam set for beam prediction; The supported measurement beam construction modes; and An indication of whether beam prediction requires additional AI / ML processing time for CSI calculations.

3. The UE according to claim 2, wherein: If the indication indicates that beam prediction requires additional AI / ML processing time for CSI calculation, the parameters also include the additional AI / ML processing time for CSI calculation.

4. The UE according to claim 1, wherein: For aperiodic CSI reporting of beam reports associated with the AI / ML model for beam prediction, the following CSI calculation timing requirements are met: is defined as the next UL symbol having its CP starting after the last symbol of the PDCCH triggering the CSI report containing the beam report corresponding to the AI / ML based beam prediction ends ; as well as Defined as when aperiodic CSI-RS is used for channel measurement for a triggered CSI report containing a beam report corresponding to AI / ML based beam prediction, after the last symbol of the aperiodic CSI-RS time for channel measurement ends, the next UL symbol has its CP start , in, and is the CSI compute time specified without AI / ML inference, and If additional AI / ML processing time is required, it is reported by the UE and , and if no additional AI / ML processing time is required, then and is 0.

5. The UE according to claim 4, wherein: and have the same value.

6. The UE according to claim 1, wherein: If the measurement beam set indicated in the one CSI resource setting for beam measurement is a subset of the prediction beam set indicated in the one CSI resource setting for beam prediction, the measurement beam set is configured by a bitmap of the prediction beam set, each bit of the bitmap being Indicating whether the i+1th beam in the predicted beam set is indicated as the measurement beam, i is from 0 to the number of beams in the predicted beam set minus 1, and the number of bits of the bitmap indicating that the i+1th beam in the predicted beam set is indicated as the measurement beam is equal to the number of beams in the measurement beam set.

7. The UE according to claim 6, wherein: The bitmap can be updated by the MAC CE.

8. The UE according to claim 7, wherein: The AI / ML model associated with the CSI reporting configuration can be updated by the MAC CE.

9. The UE according to claim 1, wherein: If the measurement beam set indicated in the one CSI resource setting for beam measurement and the prediction beam set indicated in the one CSI resource setting for beam prediction are different beam sets, any beam in the prediction beam set is QCL with respect to QCL-Type C and QCL-Type D and a beam QCL in the measurement beam set.

10. The UE according to claim 1, wherein: For aperiodic CSI reporting of beam reports associated with the AI / ML model for beam prediction, the predicted beam reported in the beam report is selected from a set of predicted beams indicated in the one CSI resource setting for beam prediction.

11. The UE according to claim 10, wherein: The bit width of the CRI field in the CSI report is determined by the number of the beams included in the beam prediction set, where CRI k corresponds to the k+1th entry of the configuration of the resources in the prediction beam set, and k 0.

12. A method performed at a user equipment (UE), comprising: Reports the set of parameters used to define the AI / ML model used for beam prediction; as well as Receive a configuration of a CSI reporting setting associated with the AI / ML model, wherein the CSI reporting setting is associated with one CSI resource setting for beam prediction and one CSI resource setting for beam measurement.

13. A basic unit comprising: Transceiver; as well as a processor coupled to the transceiver, wherein the processor is configured to receiving, via the transceiver, a set of parameters for defining an AI / ML model for beam prediction; and Transmitting, via the transceiver, a configuration of a CSI reporting setting associated with the AI / ML model, wherein the CSI reporting setting is associated with one CSI resource setting for beam prediction and one CSI resource setting for beam measurement.

Images