Beam reporting with ai capability

Abstract

Methods and apparatus for AI / ML capable beam reporting are disclosed. In one embodiment, a UE comprises: a transceiver; and a processor coupled to the transceiver, where the processor is configured to receive, via the transceiver, a configuration for CSI reporting, where the configuration is associated with a set of measurement resources and a set of prediction resources; and transmitting, via the transceiver, a CSI report, the CSI report comprising a resource type indication field to indicate whether the reported resource is a measurement resource selected from the measurement resource set or a prediction resource selected from the prediction resource set.

Description

Technical Field

[0001] The subject matter disclosed herein generally relates to wireless communication and, more particularly, to methods and apparatuses for beam reporting with AI / ML capabilities. 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 / Device (Mobile Terminal), Transmitter (TX), Receiver (RX), Channel State Information (CSI), Channel State Information Reference Signal (CSI-RS), CSI-RS Resource Indicator (CRI), Reference Signal Received Power (RSRP), Layer 1 Reference Signal Received Power (L1-RSRP), Synchronization Signal (SS), Physical Broadcast Channel (PBCH), SS / PBCH Block (SSB), Primary Synchronization Signal (PSS), Secondary Synchronization Signal (SSS), Machine Learning (ML), Artificial Intelligence (AI), Base Station (BS), Deep Neural Network (DNN), Recurrent Neural Network (RNN), SSB Resource Indicator (SSBRI), Quasi-Co-Location (3GPP) (QCL), 3rd Generation Partnership Project (3GPP), Technical Specification (TS).

[0003] In NR Release 15, the CSI reporting settings configured by the higher layer parameter 'CSI-ReportConfig' are linked to a resource setting for channel measurement, which can have multiple CSI-RS resource sets, and each CSI-RS resource set can include one or more CSI-RS resources. One or more CSI-RS resource sets selected from the resource setting are linked to 'CSI-ReportConfig'. From the perspective of the UE, the CSI-RS resources included in the linked CSI-RS resource sets will be received by the UE for channel measurement.

[0004] The "reportQuantity" of the high-layer parameters included in the 'CSI-ReportConfig' IE configures the CSI quantity (parameters) to be reported by the UE. The parameters can include, but are not limited to, the CSI-RS resource indicator (CRI) and the layer 1 reference signal received power (L1-RSRP) (for example, when "reportQuantity" is set to "cri-RSRP").

[0005] The CRI is used to indicate the CSI-RS resources to derive the corresponding CSI parameters (e.g., L1-RSRP). That is, each CRI is used to indicate one CSI-RS resource among the CSI-RS resources included in the CSI-RS resource set from the link in the resource setting, and the L1-RSRP is measured based on this CSI-RS resource.

[0006] The L1-RSRP for CSI-RS is defined as the linear average of the power contributions (in [W]) of the resource elements of the antenna ports carrying the CSI-RS configured for RSRP measurement within the considered measurement frequency bandwidth in the configured CSI-RS occasion. In other words, one L1-RSRP represents the received power of one CSI-RS resource indicated by the CRI. It can be said that one L1-RSRP corresponds to the CRI.

[0007] In addition to being based on CSI-RS resources, L1-RSRP can also be measured based on SSB (SS / PBCH block) resources. Each SS / PBCH block from which the UE can obtain system information contains a PSS (Primary Synchronization Signal), an SSS (Secondary Synchronization Signal), and a PBCH (Physical Broadcast Channel), each of which is transmitted by the gNB using the same spatial Tx beam. The PSS, SSS, and PBCH together are referred to as a Synchronization Signal Block (SSB). When the'reportQuantity' included in the 'CSI-ReportConfig' IE is set to'ssb-Index-RSRP', the 'CSI-ReportConfig' is linked to a resource setting for channel measurement, which can have multiple SSB resource sets, and each of the multiple SSB resource sets can include one or more SSB resources. One or more SSB resource sets selected from the resource setting are linked to the 'CSI-ReportConfig'. From the UE's perspective, the SSB resources included in the linked SSB resource sets will be received by the UE for channel measurement. The SSBRI is used to indicate the SS / PBCH block resources (which can be referred to as "SSB resources") to derive the corresponding CSI parameters (e.g., L1-RSRP). That is, each SSBRI is used to indicate one SSB resource among the SSB resources included in the linked SSB resource sets in the resource setting, and the L1-RSRP is measured based on this SSB resource. The L1-RSRP of the SSB is defined as the linear average of the power contributions (in [W]) of the resource elements carrying the secondary synchronization signal. One L1-RSRP represents the received power of one SSB resource indicated by the SSBRI. It can be said that one L1-RSRP corresponds to the SSBRI.

[0008] Overall, when the 'CSI-ReportConfig' is linked to a resource setting for channel measurement and the'reportQuantity' is set to 'cri-RSRP' or'ssb-Index-RSRP', the UE will report the CRI or SSBRI and the L1-RSRP (which can be referred to as "L1-RSRP corresponding to the CRI or SSBRI") measured based on the CSI-RS or SSB resources indicated by the CRI or SSBRI. Specifically, the measured L1-RSRP is the received power of the CSI-RS or SSB resources indicated by the CRI or SSBRI. Each CSI-RS resource or SSB resource corresponds to a DL Tx beam.

[0009] Machine Learning (ML) is a method to achieve Artificial Intelligence (AI). In the following descriptions, they are described as AI / ML. In 3GPP NR Release 18, AI / ML-based beam prediction has been studied to enhance system performance and / or reduce beam management complexity and overhead, especially for the case where the base station (BS) and / or UE employ a larger number of beams. A potential use case is to deploy the AI / ML function (which can also be referred to as the "AI / ML inference function") in the UE, and the UE can predict the beams in beam set A based on the measurements of the beams in beam set B, where beam set A includes a larger number of beams and beam set B includes a smaller number of beams. Another potential use case is that the AI / ML function is deployed in the UE, and the UE can, by adopting the AI / ML function, predict the best K (K >= 1) beams for F P (F P >= 1) future instances. The UE shall perform beam prediction based on network configuration (e.g., configuration from the gNB) and report the predicted beams to the gNB.

[0010] The object of the present invention is to enhance beam reporting with AI / ML capabilities. Summary of the Invention

[0011] Methods and apparatuses for beam reporting with AI / ML capabilities are disclosed.

[0012] In one embodiment, the UE includes: a transceiver; and a processor coupled to the transceiver, where the processor is configured to receive, via the transceiver, a configuration for CSI reporting, where the configuration is associated with a measurement resource set and a prediction resource set; and transmit, via the transceiver, a CSI report, the CSI report including a resource type indication field to indicate whether the reported resource is a measurement resource selected from the measurement resource set or a prediction resource selected from the prediction resource set.

[0013] In some embodiments, the configuration is associated with an AI / ML function at least for spatial domain resource prediction. If the resource type indication field indicates that the reported resource is a prediction resource, the reported resource is predicted by the AI / ML function from the prediction resource set; and if the resource type indication field indicates that the reported resource is a measurement resource, the reported resource is the resource with the highest measured L1-RSRP in the measurement resource set. Further, if the resource type indication field indicates that the reported resource is a prediction resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the prediction resource set, and if the resource type indication field indicates that the reported resource is a measurement resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the measurement resource set.

[0014] In some embodiments, the configuration is associated with at least an AI / ML function for time-domain resource prediction response. If the resource type indication field indicates that the reported resource is a predicted resource, the reported resource is a predicted resource predicted by the AI / ML function for each of F future time instances, where F is an integer of 1 or greater; and if the resource type indication field indicates that the reported resource is a measured resource, the reported resource is the resource with the highest measured L1-RSRP in the set of measured resources.

[0015] In some embodiments, the configuration is associated with an AI / ML function capable of outputting predicted resources without predicting the L1-RSRP of the predicted resources. The processor is further configured to receive, via the transceiver, a configuration of a second CSI report associated with a second set of measurement resources. The number of resources configured in the second set of measurement resources may be the same as the number of resources reported in the CSI report. The processor may also be configured to receive, via the transceiver, a control signal triggering the second CSI report within a duration since the CSI report was sent, where the resources configured in the second set of measurement resources are quasi-co-located with the resources reported in the CSI report.

[0016] In some embodiments, the processor is further configured to send, via the transceiver, information about the type of AI / ML function equipped by the UE.

[0017] In some embodiments, the set of measurement resources and the set of predicted resources are the same set of resources.

[0018] In some embodiments, the configuration is also associated with a quantization indication.

[0019] In another embodiment, a method performed at a UE includes: receiving a configuration for a CSI report, where the configuration is associated with a set of measurement resources and a set of predicted resources; and sending a CSI report that includes a resource type indication field to indicate whether the reported resource is a measured resource selected from the set of measurement resources or a predicted resource selected from the set of predicted resources.

[0020] In yet another embodiment, a base station unit includes: a transceiver; and a processor coupled to the transceiver, where the processor is configured to: send, via the transceiver, a configuration for a CSI report, where the configuration is associated with a set of measurement resources and a set of predicted resources; and receive, via the transceiver, a CSI report that includes a resource type indication field to indicate whether the reported resource is a measured resource selected from the set of measurement resources or a predicted resource selected from the set of predicted resources.

[0021] In yet another embodiment, a method performed at a base station unit includes: transmitting a configuration for CSI reporting, where the configuration is associated with a measurement resource set and a prediction resource set; and receiving a CSI report that includes a resource type indication field to indicate whether the reported resource is a measurement resource selected from the measurement resource set or a prediction resource selected from the prediction resource set. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] A more specific description of the embodiments briefly described above will be presented by reference to specific embodiments shown in the drawings. It should be understood that these drawings depict only some embodiments and should not be considered as limiting the scope. The embodiments will be described and explained with additional specificity and detail by using the drawings, in which:

[0023] Figure 1 illustrates the principle of AI / ML-based beam prediction in the spatial domain;

[0024] Figure 2 illustrates a first example of an AI / ML model for temporal beam prediction;

[0025] Figure 3 illustrates a second example of an AI / ML model for temporal beam prediction;

[0026] Figure 4 is a schematic flowchart illustrating an embodiment of a method on the UE side;

[0027] Figure 5 is a schematic flowchart illustrating an embodiment of a method on the network side; and

[0028] Figure 6 is a schematic flowchart illustrating an embodiment of another method on the UE side;

[0029] Figure 7 is a schematic flowchart illustrating an embodiment of another method on the network side; and

[0030] Figure 8 is a schematic block diagram illustrating an apparatus according to one embodiment. DETAILED DESCRIPTION

[0031] As will be appreciated by one of ordinary skill in the art, certain aspects of the embodiments may be embodied as a system, apparatus, method, or program product. Accordingly, the embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects that may generally be referred to herein as a “circuit,” “module,” or “system.” Additionally, the embodiments may take the form of a program product embodied in one or more computer-readable storage devices storing machine-readable code, computer-readable code, and / or program code (hereinafter referred to as “code”). The storage device may be tangible, non-transitory, and / or non-transmissive. The storage device may not embody a signal. In certain embodiments, the storage device merely takes the form of a signal for accessing the code.

[0032] Certain functional units described in this specification may be labeled as “modules” for the purpose of more particularly emphasizing their separate implementation. For example, a module may be implemented as a hardware circuit including a custom very large scale integration (VLSI) circuit or gate array, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. A module may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, and the like.

[0033] A module may also be implemented in code and / or software for execution by various types of processors. The identified code module may include, for example, one or more physical or logical blocks of executable code that may be organized, for example, as an object, procedure, or function. However, the executable files of the identified module need not be physically located together, but may include different instructions stored in different locations that, when logically combined, include the module and implement the stated purpose of the module.

[0034] In fact, a code module may contain a single instruction or many instructions and may even be distributed over several different code segments, different programs, and across several memory devices. Similarly, operational data may be identified and illustrated herein within a module and may be embodied in any suitable form and organized within any suitable type of data structure. The operational data may be collected as a single data set or may be distributed at different locations, including across different computer-readable storage devices. Where a module or a portion of a module is implemented in software, the software portion is stored on one or more computer-readable storage devices.

[0035] Any combination of one or more computer-readable media may be utilized. A computer-readable medium may be a computer-readable storage medium. A computer-readable storage medium may be a storage device that stores code. The storage device may be, by way of example and without limitation, an electronic, magnetic, optical, electromagnetic, infrared, holographic, micro-mechanical, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.

[0036] A non-exhaustive list of more specific examples of storage devices would include the following: an electrical connection having one or more wires, a portable computer disk, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. 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.

[0037] 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 execute entirely on the user's computer, partly on the user's computer as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the last 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).

[0038] References throughout this specification to "one embodiment," "an embodiment," or similar language mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, unless expressly stated otherwise, the phrases "in one embodiment," "in an embodiment," and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment, but mean "one or more but not all embodiments." Unless expressly stated otherwise, the terms "including," "comprising," "having," and variations thereof mean "including but not limited to." Unless expressly stated otherwise, a list of items does not imply that any or all of the items are mutually exclusive. Unless expressly stated otherwise, the terms "a," "an," and "the" also refer to "one or more."

[0039] In addition, the described features, structures, or characteristics of the various embodiments may be combined in any suitable manner. In the following description, numerous 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 practiced without one or more of the specific details or with other methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring any aspect of the embodiments.

[0040] Aspects of different embodiments are described below with reference to the schematic flowcharts and / or schematic block diagrams of methods, apparatuses, systems, and program products according to the embodiments. It will be understood that each block of the schematic flowcharts and / or schematic block diagrams, and combinations of blocks in the schematic flowcharts and / or schematic block diagrams, can be implemented by code. This code can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device create a device for implementing the functions specified in one or more blocks of the schematic flowchart and / or schematic block diagram.

[0041] The code can also be stored in a storage device that can direct a computer, other programmable data processing device, or other device to operate in a particular manner, such that the instructions stored in the storage device produce an article of manufacture that includes instructions for implementing the functions specified in the schematic flowchart and / or one or more blocks of the schematic block diagram.

[0042] The code can 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, such that the code executed on the computer or other programmable device provides a process for implementing the functions specified in the flowchart and / or one or more blocks of the block diagram.

[0043] The schematic flowcharts and / or schematic block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatuses, systems, methods, and program products according to various embodiments. In this regard, each block of the schematic flowcharts and / or schematic block diagrams may represent a module, segment, or portion of code that includes one or more executable instructions for implementing the specified logical function.

[0044] It should also be noted that in some alternative embodiments, the functions recited in the blocks may occur out of the order recited in the figures. For example, depending on the functions involved, two consecutively shown blocks may be executed substantially simultaneously, or the blocks may sometimes be executed in the reverse order. Other steps and methods equivalent in function, logic, or effect to one or more blocks or portions thereof of the illustrated figures may be contemplated.

[0045] Although various arrow types and line types may be employed in the flowcharts and / or block diagrams, they are understood not to limit the scope of the corresponding embodiments. In fact, some arrows or other connectors may be used to merely indicate 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 embodiment. It will also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a system based on dedicated hardware that performs the specified functions or actions, or a combination of dedicated hardware and code.

[0046] The description of the elements in each figure may refer to the elements of the previous figures. In all the figures, the same reference numerals refer to the same elements, including alternative embodiments of the same element.

[0047] Figure 1 The principle of AI / ML-based beam prediction in the spatial domain is illustrated. The AI / ML model may be implemented by a deep neural network (DNN) or a recurrent neural network (RNN). As Figure 1 shown, the AI / ML model that can be used for beam prediction of the AI / ML inference function (which may be abbreviated as "AI / ML function" or referred to as "AI / ML model") is deployed on the UE or network (e.g., gNB) side. The measurement results (e.g., L1-RSRP) based on a measurement beam set including a certain number of beams (e.g., measurement beam set B) are set as the input of the AI / ML model. The measurement beam set consists of measurement beams. Each beam may be represented by a CSI-RS resource or an SSB resource. And the beam index may be represented by a CSI-RS resource index (CRI) or an SSB resource index (SSBRI). Thus, the measurement beam set may be referred to as a measurement resource set. The AI / ML model performs beam prediction of another prediction beam set (e.g., prediction beam set A) (or prediction resource set) based on the input according to the AI / ML inference algorithm, which includes a larger number of beams. Incidentally, the output of the AI / ML model may be the prediction results of any number of beams (e.g., the best 2 beams with corresponding predicted L1-RSRP) included in the prediction beam set A. The best 2 beams mean that the predicted L1-RSRP of the 2 beams is the best (the largest and the second largest) among the predicted L1-RSRP of the beams in the prediction beam set.

[0048] The AI / ML model in the UE for time beam prediction performs beam quality prediction for F (F >= 1) future instances based on the historical measurement results of the measurement beams (e.g., on the latest K (K >= 1) measurement instances) by adopting time-domain correlation. The AI / ML model can be implemented by an RNN (Recurrent Neural Network) or DNN (Deep Neural Network) with a fixed set of weights, which can be updated with the AI / ML model update process. The detailed implementation of the AI / ML model for time beam prediction is not within the scope of this disclosure.

[0049] Figure 2 FIG. illustrates a first example of an AI / ML model for time beam prediction with AI / ML input and AI / ML output. The measurement beam set consists of measurement beams. The predicted beam set consists of beams for prediction. The input to the AI / ML model is the historical (e.g., on the measurement instance) beam measurement results (e.g., L1-RSRP) of the measurement beams within the measurement beam set. The measurement instance is the time instance when the quality of each measurement beam is measured (or obtained). The output from the AI / ML model is the predicted best K (K >= 1) beams among the beams within the predicted beam set on F P (F P >= 1) future instances. The future instance is the time instance after each measurement instance when the beam measurement result is obtained. Each AI / ML model requires a fixed input format (e.g., L1-RSRP of a fixed number of measurement beams), and can output the predicted best K beams (e.g., the best K beams among the beams within the predicted beam set) for each of the F (F <= F P ) future instances. The CSI report configuration for beam prediction configured by the RRC parameter CSI-ReportConfig, i.e., the CSI report setting, should be configured to meet the requirements of the AI / ML model. If the AI / ML model only has the time beam prediction function, the measurement beam set and the predicted beam set should be the same, i.e., both beam sets contain the same beams. If the AI / ML model has both time-domain and spatial-domain beam prediction functions, the measurement beam set and the predicted beam set can contain different beams, e.g., the predicted beam set has a larger number of beams while the measurement beam set has a smaller number of beams.

[0050] Figure 3Illustrates a second example of an AI / ML model for time beam prediction, where in addition to the AI / ML model selection function, multiple AI / ML models (e.g., AI / ML model #1 to AI / ML model #N) are provided. The AI / ML model selection function is used to select (allocate) an AI / ML model from the multiple AI / ML models for a specific beam prediction process. The multiple AI / ML models and the AI / ML model selection function can be collectively referred to as the AI / ML model management function.

[0051] The first embodiment relates to different AI / ML capabilities (e.g., different AI / ML functions).

[0052] As described above, the AI / ML function can be deployed on the UE side and / or the network side (e.g., at the gNB). The AI / ML function deployed at the UE can be referred to as the UE being equipped with the AI / ML function.

[0053] If the AI / ML function is deployed on the network side, regardless of whether the AI / ML function is deployed on the UE side, the network can determine to use the AI / ML function deployed on the network side.

[0054] If one or more AI / ML functions are deployed on the UE side, the UE capabilities on the AI / ML function (e.g., the type of AI / ML function deployed at the UE) can be reported to the network (e.g., the gNB). The AI / ML functions deployed on the UE side can have different types listed as follows:

[0055] (1) An AI / ML function for spatial domain beam prediction (i.e., only for spatial domain beam prediction); and

[0056] (2) An AI / ML function for time domain beam prediction.

[0057] The AI / ML function for time domain beam prediction can be further divided into:

[0058] (2-1) An AI / ML function only for time domain beam prediction (which means it cannot be used for spatial domain beam prediction);

[0059] (2-2) An AI / ML function for both time domain beam prediction and spatial domain beam prediction.

[0060] From another perspective, the AI / ML functions solely for spatial domain beam prediction and the AI / ML functions for both temporal domain beam prediction and spatial domain beam prediction can be collectively referred to as the AI / ML functions for at least spatial domain resource prediction. Similarly, the AI / ML functions solely for temporal domain beam prediction and the AI / ML functions for both temporal domain beam prediction and spatial domain beam prediction can be collectively referred to as the AI / ML functions for at least temporal domain beam prediction.

[0061] For different types of AI / ML functions, the format of the beam report, i.e., the CSI report configured with the high-layer parameter'reportQuantity', is set to 'cri-RSRP' or'ssb-Index-RSRP', which is also different.

[0062] Incidentally, a UE can be equipped with one or more AI / ML functions for the same or different AI / ML functions. This means that the UE can report UE capabilities with one or more AI / ML capabilities (i.e., one or more AI / ML functions of different types). That is to say, the UE reports all types of AI / ML functions equipped (or deployed at the UE) by the UE.

[0063] In addition, different AI / ML models for the same AI / ML function can have different AI / ML outputs, which should be part of the UE AI / ML capability report. For example, one AI / ML model for spatial domain beam prediction can output the predicted top K beams (e.g., by their beam IDs) and their corresponding predicted L1-RSRP, while another AI / ML model for spatial domain beam prediction can only output the predicted top K beams but cannot output their corresponding predicted L1-RSRP. The details of the AI / ML model that only outputs the predicted top K beam IDs will be described in the fourth embodiment.

[0064] The second embodiment relates to the beam report of the AI / ML function deployed on the network side.

[0065] When the AI / ML function is deployed on the network side (e.g., at the gNB), for example, for spatial domain beam prediction, the gNB can configure or trigger the beam measurement and beam report process for the UE to obtain the measurement results regarding the measurement beam set B to provide input to the AI / ML function deployed on the network side.

[0066] For example, the gNB configures or triggers beam measurement and beam reporting procedures, i.e., CSI report settings (or CSI report configurations) configured by CSI-ReportConfig, where the higher layer parameter'reportQuantity' is set to 'cri-RSRP' or'ssb-Index-RSRP' for the UE to report beam reports, i.e., CSI reports containing CRI and the corresponding L1-RSRP. Specifically, the gNB configures CSI-ReportConfig for the UE. The CSI report configuration is associated with a measurement beam set B composed of multiple beams (e.g., 8 beams or 16 beams) for measurement. When the UE receives the CSI report configuration for CSI reporting and the CSI report is triggered, it measures the beams in the measurement beam set B (e.g., the L1-RSRP of the measurement beams), and reports the measurement results (i.e., the measured L1-RSRP of the beams in the measurement beam set B) in the corresponding CSI report. Since the CSI report contains the measurement results of the beams, it can also be referred to as a "beam report". Incidentally, in the following description, L1-RSRP can be abbreviated as RSRP.

[0067] Note that each beam is configured by CSI-RS resources or SSB resources, and the beam ID is represented by CRI or SSBRI. This means that the measurement beam set B can also be referred to as a measurement resource set B composed of multiple CSI-RS or SSB resources, and each CSI-RS resource or SSB resource corresponds to CRI or SSBRI.

[0068] Beam reporting based on differential RSRP specified in 3GPP TS38.214 and TS38.133 can be used. This means that in the CSI report (i.e., beam report) reported by the UE, only the maximum measured RSRP is reported by quantifying it as a 7-bit value in the range [-140, -44] dBm with a 1 dB step, while other measured RSRPs are reported with differential values calculated with a 2 dB step with reference to the maximum measured RSRP and quantified as 4-bit values.

[0069] Table 1 provides the CSI report format of the CSI report according to the second embodiment, where N is the number of beams in the measurement beam set B.

[0070]

[0071] In Table 1, it is assumed that the measurement beam set consists of N beams (e.g., N CSI-RS or SSB resources), and the UE is configured to report the measurement results of all beams in the measurement beam set B. As can be seen from Table 1, the first field is the CRI or SSBRI field indicating the CRI or SSBRI, which indicates the CSI-RS or SSB resource having the maximum measured RSRP among the measured RSRPs of all beams in the measurement beam set B. The bit length of the first field is determined by the number of beams (i.e., CSI-RS resources or SSB resources) included in the measurement beam set B. The second field is the maximum measured RSRP (e.g., quantized to a 7-bit value) corresponding to the CRI or SSBRI indicated in the first field. The differential RSRPs of other CSI-RS resources or SSB resources (e.g., each RSRP is quantized to a 4-bit value) are reported in the following fields in the order of the CRI or SSBRI of the resources (e.g., ascending order). Note that one RSRP corresponding to one CSI-RS or SSB resource having the maximum measured RSRP is included. Thus, differential RSRPs corresponding to the remaining N-1 CSI-RS or SSB resources in the measurement beam set B are included.

[0072] As described above, according to the conventional quantization scheme, the maximum reported RSRP is defined by a 7-bit value in the range [-140, -44] dBm with a 1 dB step, and the differential RSRP is quantized to a 4-bit value, while the differential RSRP is calculated with a 2 dB step with reference to the maximum measured RSRP value, which is the maximum reported RSRP in the same beam report. If the 7-bit RSRP and 4-bit differential RSRP are sufficient to achieve the quantization accuracy of the input for the AI / ML function deployed on the network side, the conventional quantization scheme can be used.

[0073] According to a variant of the second embodiment, a new quantization scheme with higher quantization accuracy is proposed. An indication of the higher quantization accuracy can be included in or associated with the CSI report configuration. Higher quantization accuracy means using more bits in the process of quantizing the L1-RSRP and / or differential L1-RSRP, and / or using a smaller step in calculating the differential L1-RSRP. For example, in the new quantization scheme, the maximum reported L1-RSRP value is defined by an 8-bit value (which is greater than 7 bits) in the range [-140, -44] dBm with a 0.5 dB step, and the differential L1-RSRP is quantized to a 5-bit value or a 6-bit value (which is greater than 4 bits), which is calculated with a 1 dB step or a 0.5 dB step (which is less than 2 dB steps) with reference to the maximum measured L1-RSRP value, which is the maximum reported L1-RSRP in the same beam report.

[0074] An example of a variant of the second embodiment is described. The UE needs to report all 8 configured beams (K included in the measurement beam set BBeams = 8), i.e., the measurement results of 8 CSI-RS resources. According to the UE's measurement of 8 configured beams, the fifth (i.e., the (4, +1)th or the 5th) CSI-RS resource has the maximum measured RSRP. In addition, the UE is instructed to use a higher quantization accuracy. Therefore, the CSI report reported by the UE is shown in Table 2. The bit width of the CSI field is = 3 (where means the smallest integer equal to or greater than x). According to the higher quantization accuracy, the bit width of the RSRP#1 of the CSI-RS resource (i.e., the maximum reported RSRP) is 8. According to the higher quantization accuracy, the bit width of the differential RSRP is 5.

[0075]

[0076] The third embodiment relates to beam reporting of AI / ML functions deployed on the UE side.

[0077] One or more AI / ML functions are deployed in the UE. As described in the first embodiment, each AI / ML function can have a different type. Each type of AI / ML function can be associated with different CSI report configurations for beam reporting (i.e., the CSI report includes beam IDs (i.e., CRI or SSBRI)) and the L1-RSRP of the beam (i.e., CSI-RS or SSB resources), because different types of AI / ML functions can have different inputs and / or different outputs. Each AI / ML function can correspond to one or more AI / ML models. This means that each CSI report configuration can be associated with different types of AI / ML functions or with AI / ML models.

[0078] Generally, the CSI report configuration for beam reporting is associated with two resource sets, for example, including a predicted beam set A for predicting a beam set (i.e., CSI-RS or SSB resource set) by an AI / ML inference function; and including a measured beam set B for measuring a beam set (i.e., CSI-RS or SSB resource set).

[0079] The beams in the predicted beam set A do not have to be explicitly configured in the CSI report configuration. This means that the beams in the predicted beam set A can be pre-configured for the UE as the default beam in the predicted beam set A (i.e., the default predicted beam set A), because the number of beams in the predicted beam set A may be large (e.g., 128 beams) and does not always change. In this case, the CSI report configuration can indicate that the predicted beam set A associated with the CSI report configuration is the default predicted beam set A pre-configured for the UE, without having to explicitly indicate the beams in the predicted beam set A.

[0080] The measurement beam set B configures the UE to measure a beam set, and the measurement results (the measured RSRP of each beam in the measurement beam set B) are used as inputs to the AI / ML function deployed on the UE side. This means that the AI / ML function predicts the RSRP of each beam in the predicted beam set A based on the measured RSRP of each beam in the measurement beam set B. In other words, the UE only needs to measure the beams in the measurement beam set B, and the UE does not need to measure the beams in the predicted beam set A.

[0081] The beam report including the CSI report configuration requires the AI / ML function to match the CSI report configuration of the beam report. However, considering that when configuring or triggering the beam report, the AI / ML function matching the CSI report configuration of the beam report deployed on the UE side may not be available. For example, the AI / ML function can be used by another beam report process. Another example is that due to power saving, the AI / ML function may be inactive. As a whole, the UE may not be able to use the AI / ML function as the beam report configured by the NW.

[0082] In view of the above, the present disclosure proposes that if the AI / ML function matching the CSI report configuration for beam reporting is not available, the UE is required to report a beam report based on the measured beam (i.e., based on the beam selected from the measurement beam set B) (the details of the beam report based on the measured beam will be discussed later).

[0083] To distinguish whether the reported beam in the beam report is a predicted beam selected from the predicted beam set A or a measured beam selected from the measurement beam set B, a 'beam type indication' field is included in the beam report. For example, the 'beam type indication' field has 1 bit to indicate whether the reported beam is a measured beam or a predicted beam.

[0084] Specifically, if the 'beam type indication' field indicates that the reported beam is a measured beam, the AI / ML model is not used while selecting the reported beam from the measurement beam set B. The bit width of the CRI or SSBRI field in the beam report (which indicates the CSI-RS resource or SSB resource representing the beam) is determined by the number of beams (i.e., resources) configured in the measurement beam set B.

[0085] If the 'beam type indication' field indicates that the reported beam is a predicted beam, the AI / ML model is used while selecting the reported beam from the predicted beam set A. The bit width of the CRI or SSBRI field in the beam report is determined by the number of beams (i.e., resources) configured in the predicted beam set A.

[0086] The first sub-embodiment of the third embodiment relates to an AI / ML function deployed on the UE side for spatial domain beam prediction (i.e., only for spatial domain beam prediction, not for temporal domain beam prediction).

[0087] The CSI report configuration for beam reporting of the AI / ML function for spatial domain beam prediction is associated with the measurement beam set B and the prediction beam set A.

[0088] Upon receiving the CSI report configuration for beam reporting associated with the AI / ML function for spatial domain beam prediction and when the beam report is triggered, the UE measures the beams included in the measurement beam set B, provides the measurement results (i.e., the measured RSRP of each beam included in the measurement beam set B), and the prediction beam set A as the input to the AI / ML function for spatial domain beam prediction, predicts the top K (K >= 1) beams from the prediction beam set A (by the AI / ML function for spatial domain beam prediction), and reports the predicted top K beams in the beam report. The top K beams are the K beams in the prediction beam set A with the K largest predicted RSRP.

[0089] If the AI / ML function for spatial domain beam prediction is unavailable, the UE reports the top K measured beams in the beam report. The top K measured beams are the K beams in the measurement beam set B with the K largest measured RSRP.

[0090] The CSI report format according to the first sub - embodiment of the third embodiment is shown in Table 3. In Table 3, K = 4.

[0091]

[0092] In Table 3, if the beam type indication field indicates that the reported beam is a measured beam, the RSRP of the beam corresponding to CRI or SSBRI#1 is the measured RSRP, or if the beam type indication field indicates that the reported beam is a predicted beam, it is the predicted RSRP. Similarly, if the beam type indication field indicates that the reported beam is a measured beam, the differential RSRP of the beam corresponding to CRI or SSBRI#2, 3, or 4 is the differential measured RSRP, or if the beam type indication field indicates that the reported beam is a predicted beam, it is the differential predicted RSRP. The beam reporting based on differential RSRP specified in 3GPP TS38.214 and TS38.133 is adopted in Table 3.

[0093] The second sub - embodiment of the third embodiment relates to the AI / ML functions for both time - domain beam prediction and spatial domain beam prediction deployed on the UE side.

[0094] The CSI report configuration for beam reporting of the AI / ML functions for both time - domain beam prediction and spatial domain beam prediction is associated with the measurement beam set B and the prediction beam set A.

[0095] When the UE receives a CSI report configuration for a beam report associated with AI / ML functions for both time-domain beam prediction and spatial-domain beam prediction and the beam report is triggered, the UE measures the beams included in the measurement beam set B, provides the measurement results (i.e., the measured RSRP of each beam included in the measurement beam set B) and the predicted beam set A as inputs to the AI / ML functions for both time-domain beam prediction and spatial-domain beam prediction, predicts the top K (K >= l) beams from the predicted beam set A for F (K >= l) future time instances, and reports the predicted top K beams for each of the F future time instances in the beam report. The top K beams for each of the F future time instances are the K beams in the predicted beam set A that have the K largest predicted RSRP at each of the F future time instances.

[0096] If the AI / ML functions for both time-domain beam prediction and spatial-domain beam prediction are not available, the UE reports the top K measured beams in the beam report. The top K beams are the K beams in the measurement beam set B that have the K largest measured RSRP.

[0097] Table 4 shows the CSI report format of the second sub-embodiment of the third embodiment when using the AI / ML functions for both time-domain beam prediction and spatial-domain beam prediction. In Table 4, K = 4.

[0098]

[0099] Table 5 shows the CSI report format of the second sub-embodiment of the third embodiment when not using the AI / ML functions for both time-domain beam prediction and spatial-domain beam prediction. In Table 5, K = 4.

[0100]

[0101] In Tables 4 and 5, the "beam type indicator" is set to '1' to indicate that the reported beam is a predicted beam, and is set to '0' to indicate that the reported beam is a measured beam. Apparently, the "beam type indicator" is set to '0' to indicate that the reported beam is a predicted beam, and is set to '1' to indicate that the reported beam is a measured beam.

[0102] The third sub-embodiment of the third embodiment relates to an AI / ML function deployed on the UE side for only time-domain beam prediction (i.e., not for spatial-domain beam prediction).

[0103] The CSI report configuration for beam reporting of the AI / ML function only for time-domain beam prediction is associated with a beam set that serves as both the measurement beam set B and the prediction beam set A. Since the beam reporting of the AI / ML function only for time-domain beam prediction cannot perform spatial-domain beam prediction, the measurement beam set B is the same as the prediction beam set A. This means that the AI / ML function only for time-domain beam prediction makes predictions from the prediction beam set A, which is the same as the measurement beam set B.

[0104] When receiving the CSI report configuration for the beam reporting associated with the AI / ML function only for time-domain beam prediction and the beam reporting is triggered, the UE measures the beams included in the measurement beam set B, provides the measurement results (i.e., the measured RSRP of each beam included in the measurement beam set B) as the input to the AI / ML function only for time-domain beam prediction, predicts the top K (K >= 1) beams from the prediction beam set A (which is the same as the measurement beam set B) for F (F >= 1) future time instances, and reports the predicted top K beams for each of the F future time instances in the beam report. The top K beams for each of the F future time instances are the K beams in the prediction beam set A that have the K largest predicted RSRP at each of the F future time instances.

[0105] If the AI / ML function only for time-domain beam prediction is not available, the UE reports the top K measured beams in the beam report. The top K beams are the K beams in the measurement beam set B that have the K largest measured RSRP.

[0106] When using the AI / ML function only for time-domain beam prediction, the CSI report format according to the third sub-embodiment of the third embodiment is substantially the same as the CSI report format according to the second sub-embodiment of the third embodiment shown in Table 4.

[0107] The only "difference" is that according to the third sub-embodiment of the third embodiment, the prediction beam set A is the same as the measurement beam set B and .

[0108] When not using the AI / ML function only for time-domain beam prediction, the CSI report format according to the third sub-embodiment of the third embodiment is the same as the CSI report format according to the second sub-embodiment of the third embodiment shown in Table 5.

[0109] In the description of the third embodiment, a conventional quantization scheme is used. This means that the maximum reported RSRP is defined by a 7-bit value in the range [-140, -44] dBm with a 1 dB step, and the differential RSRP is quantized to a 4-bit value, where the differential RSRP is calculated with a 2 dB step with reference to the maximum measured RSRP value, which is the maximum reported RSRP in the same beam report.

[0110] On the other hand, the CSI report configuration can also be associated with a higher quantization accuracy indication. Higher quantization accuracy means using more bits in the process of quantizing the L1-RSRP and / or the differential L1-RSRP, and / or using a smaller step in calculating the differential L1-RSRP. For example, in the new quantization scheme, the maximum reported L1-RSRP value can be defined by an 8-bit value (which is greater than 7 bits) in the range [-140, -44] dBm with a 0.5 dB step, and the differential L1-RSRP can be quantized to a 5-bit value or a 6-bit value (which is greater than 4 bits), which can be calculated with a 1 dB step or a 0.5 dB step (which is less than 2 dB steps) with reference to the maximum measured L1-RSRP value, which is the maximum reported RSRP in the same beam report.

[0111] The fourth embodiment relates to multi-level beam measurement.

[0112] In the above-mentioned third embodiment, each AI / ML function (the AI / ML function for spatial domain beam prediction, the AI / ML function for temporal domain beam prediction, and the AI / ML function for both spatial domain beam prediction and temporal domain beam prediction) outputs the IDs of the top K beams and their predicted L1-RSRP. This is referred to as the AI / ML function output type 1.

[0113] For the AI / ML function output type 2, the AI / ML function can only output the IDs of the top K beams (i.e., the top K beams with a higher probability). On the other hand, the AI / ML function cannot predict the L1-RSRP of each of the top K beams. This means that if the AI / ML function has output type 2, it can only report the IDs of the top K beams that have the maximum L1-RSRP with a higher probability. However, from the perspective of network deployment, the L1-RSRP may be more important than which beams are the top K beams that have the maximum L1-RSRP with a higher probability.

[0114] In view of the above, the fourth embodiment proposes that if the AI / ML function has output type 2, it is expected that the gNB triggers subsequent beam measurement and beam reporting processes.

[0115] The first embodiment describes that the UE reports all types of AI / ML functions equipped (or deployed at the UE) by the UE. Considering that each type of AI / ML function may have different output types (output type 1 or output type 2), the type of AI / ML function should include its function (for spatial domain beam prediction, for both temporal domain beam prediction and spatial domain beam prediction, and only for temporal domain beam prediction) and its output type (output type 1, output type 2).

[0116] The UE reports its ability to have an AI / ML function with output type 2 (i.e., the AI / ML function can only output the best K beams with a higher probability). The NW may configure a CSI report configuration for the first beam report of the UE, such as CSI report configuration #1. The CSI report configuration is for an AI / ML model with output type 2 and is associated with a predicted beam set A and a measured beam set B. The first beam report (e.g., CSI report configuration #1) is also associated with another CSI report configuration (e.g., CSI report configuration #2) for a subsequent beam report (e.g., the second beam report). The CSI report configuration #2 should be sent to the UE via RRC signaling, for example. The second beam report should be an aperiodic beam report, which may be triggered by a control signal (e.g., by DCI or MAC CE).

[0117] The CSI report configuration #2 is associated with a second measured beam set. The number of beams (i.e., CSI-RS or SSB resources) in the second measured beam set is the same as the number of reported beam IDs configured for (and reported in) the first beam report.

[0118] A duration or window since the transmission of the first beam report is defined (e.g., starting from the last symbol of the PUSCH or PUCCH carrying the first beam report corresponding to the CSI report configuration #1).

[0119] If the UE receives a control signal (e.g., DCI) within the duration or window to trigger the second beam report corresponding to the CSI report configuration #2, the UE shall assume that the beams configured for the CSI report configuration #2 are quasi-co-located with the beams reported in the first beam report. This means that each beam with an index configured for the CSI report configuration #2 is quasi-co-located with the beam with the same index reported in the first beam report. Two beams being quasi-co-located means that the UE can assume that both beams are transmitted by the same spatial domain filter.

[0120] Otherwise (i.e., if the UE does not receive a control signal within the duration or window, which means the UE receives DCI outside the duration or window), the UE will receive the beams configured for the CSI report configuration #2 with the configured QCL information.

[0121] Figure 4 FIG. is a schematic flowchart illustrating an embodiment of a method 400 according to the present application. In some embodiments, the method 400 is performed by a device such as a remote unit (e.g., UE). In certain embodiments, the method 400 may be performed by a processor that executes program code, such as, for example, a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, an FPGA, etc.

[0122] The method 400 is a method performed at a UE and includes: 402 receiving a configuration for CSI reporting, where the configuration is associated with a measurement resource set and a prediction resource set; and 404 transmitting a CSI report including a resource type indication field to indicate that the reported resource is a measurement resource selected from the measurement resource set or a prediction resource selected from the prediction resource set.

[0123] In some embodiments, the configuration is associated with an AI / ML function for at least spatial domain resource prediction. If the resource type indication field indicates that the reported resource is a prediction resource, the reported resource is predicted by the AI / ML function from the prediction resource set; and if the resource type indication field indicates that the reported resource is a measurement resource, the reported resource is the resource in the measurement resource set with the highest measured L1-RSRP. Further, if the resource type indication field indicates that the reported resource is a prediction resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the prediction resource set, and if the resource type indication field indicates that the reported resource is a measurement resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the measurement resource set.

[0124] In some embodiments, the configuration is associated with an AI / ML function for at least time domain resource prediction. If the resource type indication field indicates that the reported resource is a prediction resource, the reported resource is the prediction resource predicted by the AI / ML function for each of F future time instances, where F is an integer greater than or equal to 1; and if the resource type indication field indicates that the reported resource is a measurement resource, the reported resource is the resource in the measurement resource set with the highest measured L1-RSRP.

[0125] In some embodiments, the configuration is associated with an AI / ML function capable of outputting predicted resources without predicting the L1-RSRP of the predicted resources. The method further includes: receiving a configuration of a second CSI report associated with a second measurement resource set. The number of resources configured in the second measurement resource set may be the same as the number of resources reported in the CSI report. The method may further include receiving a control signal triggering the second CSI report within a duration since the CSI report was sent, wherein the resources configured in the second measurement resource set are quasi co-located with the resources reported in the CSI report.

[0126] In some embodiments, the method further includes sending information about the type of AI / ML function equipped by the UE.

[0127] In some embodiments, the measurement resource set and the predicted resource set are the same resource set.

[0128] In some embodiments, the configuration is further associated with a quantization indication.

[0129] Figure 5 FIG. is a schematic flowchart illustrating an embodiment of a method 500 according to the present application. In some embodiments, the method 500 is performed by a device such as a base station unit. In certain embodiments, the method 500 may be performed by a processor executing program code such as, for example, a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, an FPGA, etc.

[0130] The method 500 may include 502 sending a configuration for a CSI report, wherein the configuration is associated with a measurement resource set and a predicted resource set; and 504 receiving a CSI report including a resource type indication field to indicate whether the reported resource is a measurement resource selected from the measurement resource set or a predicted resource selected from the predicted resource set.

[0131] In some embodiments, the configuration is associated with an AI / ML function at least for spatial domain resource prediction. If the resource type indication field indicates that the reported resource is a predicted resource, the reported resource is predicted by the AI / ML function from the predicted resource set; and if the resource type indication field indicates that the reported resource is a measurement resource, the reported resource is the resource with the highest measured L1-RSRP in the measurement resource set. Further, if the resource type indication field indicates that the reported resource is a predicted resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the predicted resource set, and if the resource type indication field indicates that the reported resource is a measurement resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the measurement resource set.

[0132] In some embodiments, the configuration is associated with an AI / ML function for at least time-domain resource prediction. If the resource type indication field indicates that the reported resource is a predicted resource, the reported resource is a predicted resource predicted by the AI / ML function for each of F future time instances, where F is an integer of 1 or greater; and if the resource type indication field indicates that the reported resource is a measured resource, the reported resource is the resource in the measurement resource set having the highest measured L1-RSRP.

[0133] In some embodiments, the configuration is associated with an AI / ML function capable of outputting predicted resources without predicting the L1-RSRP of the predicted resources. The method further includes a configuration for sending a second CSI report associated with a second measurement resource set. The number of resources configured in the second measurement resource set may be the same as the number of resources reported in the CSI report. The method may further include sending a control signal triggering the second CSI report within a duration since receiving the CSI report, where the resources configured in the second measurement resource set are quasi-co-located with the resources reported in the CSI report.

[0134] In some embodiments, the method further includes receiving information about the type of AI / ML function equipped in the UE.

[0135] In some embodiments, the measurement resource set and the predicted resource set are the same resource set.

[0136] In some embodiments, the configuration is also associated with a quantization indication.

[0137] Figure 6 FIG. 600 is a schematic flowchart illustrating an embodiment of a method 600 according to the present application. In some embodiments, the method 600 is performed by a device such as a remote unit (e.g., a UE). In certain embodiments, the method 600 may be performed by a processor executing program code such as, for example, a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, an FPGA, etc.

[0138] The method 600 is a method performed at a UE and includes: 602 receiving a configuration for a CSI report, where the configuration is associated with a measurement resource set and a quantization indication; and 604 sending a CSI report including a CRI or an SSBRI, where the CRI or the SSBRI indicates a CSI-RS or an SSB resource having the maximum measured L1-RSRP in the measurement resource set and the maximum measured L1-RSRP of the CSI-RS or the SSB resource indicated by the CRI or the SSBRI, and differential L1-RSRP of other resources in the measurement resource set, where the L1-RSRP and the differential L1-RSRP are quantized according to the quantization indication.

[0139] In some embodiments, the quantization indication defines an 8-bit value for the maximum measured L1-RSRP and a 5-bit or 6-bit value for the differential L1-RSRP relative to the maximum measured L1-RSRP, where the 8-bit value represents a range of [-140, -44] dbm with a 0.5 dB step, and the 5-bit or 6-bit value represents a 1 dB step or a 0.5 dB step.

[0140] Figure 7 is a schematic flow chart illustrating an embodiment of method 700 according to the present application. In some embodiments, method 700 is performed by a device such as a base station unit. In certain embodiments, method 700 may be performed by a processor executing program code such as, for example, a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, an FPGA, etc.

[0141] Method 700 may include 702 transmitting a configuration for CSI reporting, where the configuration is associated with a measurement resource set and a quantization indication; and 704 receiving a CSI report including a CSI report that includes one CRI or SSBRI indicating the maximum measured L1-RSRP in the measurement resource set and the CSI-RS or SSB resource of the CSI-RS or SSB resource indicating the maximum measured L1-RSRP, and the differential L1-RSRP of other resources in the measurement resource set, where the L1-RSRP and the differential L1-RSRP are quantized according to the quantization indication.

[0142] In some embodiments, the quantization indication defines an 8-bit value for the maximum measured L1-RSRP and a 5-bit or 6-bit value for the differential L1-RSRP relative to the maximum measured L1-RSRP, where the 8-bit value represents a range of [-140, -44] dbm with a 0.5 dB step, and the 5-bit or 6-bit value represents a 1 dB step or a 0.5 dB step.

[0143] Figure 8 is a schematic block diagram illustrating a device according to an embodiment.

[0144] Reference Figure 8 , the UE (i.e., the remote unit) includes a processor, a memory, and a transceiver. The processor implements Figure 4 or Figure 6 the functions, processes, and / or methods proposed in

[0145] The first UE includes a transceiver; and a processor coupled to the transceiver, wherein the processor is configured to receive, via the transceiver, a configuration for CSI reporting, where the configuration is associated with a measurement resource set and a prediction resource set; and transmit, via the transceiver, a CSI report, the CSI report including a resource type indication field to indicate whether the reported resource is a measurement resource selected from the measurement resource set or a prediction resource selected from the prediction resource set.

[0146] In some embodiments, the configuration is associated with an AI / ML function for at least spatial domain resource prediction. If the resource type indication field indicates that the reported resource is a prediction resource, the reported resource is predicted by the AI / ML function from the prediction resource set; and if the resource type indication field indicates that the reported resource is a measurement resource, the reported resource is the resource in the measurement resource set with the highest measured L1-RSRP. Further, if the resource type indication field indicates that the reported resource is a prediction resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the prediction resource set, and if the resource type indication field indicates that the reported resource is a measurement resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the measurement resource set.

[0147] In some embodiments, the configuration is associated with an AI / ML function for at least time domain resource prediction. If the resource type indication field indicates that the reported resource is a prediction resource, the reported resource is a prediction resource predicted by the AI / ML function for each of F future time instances, where F is an integer greater than or equal to 1; and if the resource type indication field indicates that the reported resource is a measurement resource, the reported resource is the resource in the measurement resource set with the highest measured L1-RSRP.

[0148] In some embodiments, the configuration is associated with an AI / ML function that can output prediction resources without predicting the L1-RSRP of the prediction resources. The processor is further configured to receive, via the transceiver, a configuration for a second CSI report associated with a second measurement resource set. The number of resources configured in the second measurement resource set may be the same as the number of resources reported in the CSI report. The processor may also be configured to receive, via the transceiver, a control signal triggering the second CSI report within a duration since the CSI report was transmitted, where the resources configured in the second measurement resource set are quasi-co-located with the resources reported in the CSI report.

[0149] In some embodiments, the processor is further configured to transmit, via the transceiver, information about the type of AI / ML function equipped by the UE.

[0150] In some embodiments, the measurement resource set and the prediction resource set are the same resource set.

[0151] In some embodiments, the configuration is also associated with a quantization indication.

[0152] A second UE includes a transceiver; and a processor coupled to the transceiver, wherein the processor is configured to receive, via the transceiver, a configuration for CSI reporting, wherein the configuration is associated with a measurement resource set and a quantization indication; and transmit, via the transceiver, a CSI report, the CSI report including one CRI or SSBRI indicating a CSI-RS or SSB resource having a maximum measured L1-RSRP in the measurement resource set and the maximum measured L1-RSRP of the CSI-RS or SSB resource indicated by the one CRI or SSBRI, and differential L1-RSRP of other resources in the measurement resource set, wherein the L1-RSRP and the differential L1-RSRP are quantized according to the quantization indication.

[0153] In some embodiments, the quantization indication defines an 8-bit value for the maximum measured L1-RSRP and a 5-bit value or a 6-bit value for the differential L1-RSRP relative to the maximum measured L1-RSRP, wherein the 8-bit value represents a range of [-140, -44] dbm with a 0.5 dB step, and the 5-bit value or the 6-bit value represents a 1 dB step or a 0.5 dB step.

[0154] The gNB (i.e., the base station unit) includes a processor, a memory, and a transceiver. The processor implements Figure 5 or Figure 7 the functions, procedures, and / or methods proposed in

[0155] A first base station unit includes a transceiver; and a processor coupled to the transceiver, wherein the processor is configured to transmit, via the transceiver, a configuration for CSI reporting, wherein the configuration is associated with a measurement resource set and a prediction resource set; and receive, via the transceiver, a CSI report, the CSI report including a resource type indication field to indicate whether the reported resource is a measurement resource selected from the measurement resource set or a prediction resource selected from the prediction resource set.

[0156] In some embodiments, the configuration is associated with an AI / ML function that is at least used for spatial domain resource prediction. If the resource type indication field indicates that the reported resource is a predicted resource, the reported resource is predicted by the AI / ML function from a set of predicted resources; and if the resource type indication field indicates that the reported resource is a measured resource, the reported resource is the resource in the set of measured resources that has the highest measured L1-RSRP. In addition, if the resource type indication field indicates that the reported resource is a predicted resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the set of predicted resources, and if the resource type indication field indicates that the reported resource is a measured resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the set of measured resources.

[0157] In some embodiments, the configuration is associated with an AI / ML function that is at least used for time domain resource prediction. If the resource type indication field indicates that the reported resource is a predicted resource, the reported resource is the predicted resource predicted by the AI / ML function for each of F future time instances, where F is an integer greater than or equal to 1; and if the resource type indication field indicates that the reported resource is a measured resource, the reported resource is the resource in the set of measured resources that has the highest measured L1-RSRP.

[0158] In some embodiments, the configuration is associated with an AI / ML function that can output predicted resources without predicting the L1-RSRP of the predicted resources. The processor is further configured to send, via a transceiver, a configuration for a second CSI report associated with a second set of measurement resources. The number of resources configured in the second set of measurement resources may be the same as the number of resources reported in the CSI report. The processor may also be configured to send, via the transceiver, a control signal that triggers the second CSI report within a duration since receiving the CSI report, where the resources configured in the second set of measurement resources are quasi co-located with the resources reported in the CSI report.

[0159] In some embodiments, the processor is further configured to receive, via a transceiver, information about the type of AI / ML function equipped by the UE.

[0160] In some embodiments, the set of measurement resources and the set of predicted resources are the same set of resources.

[0161] In some embodiments, the configuration is also associated with a quantization indication.

[0162] The second base station unit includes a transceiver; and a processor coupled to the transceiver, wherein the processor is configured to: transmit, via the transceiver, a configuration for CSI reporting, where the configuration is associated with a measurement resource set and a quantization indication; and receive, via the transceiver, a CSI report, the CSI report including one CRI or SSBRI indicating a CSI-RS or SSB resource having the maximum measured L1-RSRP in the measurement resource set and the maximum measured L1-RSRP of the CSI-RS or SSB resource indicated by the one CRI or SSBRI, and differential L1-RSRP of other resources in the measurement resource set, where the L1-RSRP and the differential L1-RSRP are quantized according to the quantization indication.

[0163] In some embodiments, the quantization indication defines an 8-bit value for the maximum measured L1-RSRP and a 5-bit or 6-bit value for the differential L1-RSRP relative to the maximum measured L1-RSRP, where the 8-bit value represents a range of [-140, -44] dbm with a 0.5 dB step, and the 5-bit or 6-bit value represents a 1 dB step or a 0.5 dB step.

[0164] Layers of the radio interface protocol may be implemented by the processor. A 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 may be implemented as a transmitter for transmitting radio signals and a receiver for receiving radio signals.

[0165] The memory may be located inside or outside the processor and is connected to the processor by various well-known means.

[0166] In the above embodiments, the components and features of the embodiments are combined in a predetermined form. Unless otherwise clearly stated, each component or feature should be understood as an option. Each component or feature may be implemented without being associated with other components or features. In addition, embodiments may be configured by associating some components and / or features. The order of operations described in the embodiments may be changed. Some components or features of any embodiment may be included in another embodiment or replaced with components and features corresponding to another embodiment. Obviously, claims not explicitly recited in the claims are combined to form embodiments or included in new claims.

[0167] Embodiments may be implemented by hardware, firmware, software, or a combination thereof. In the case of an implementation by hardware, according to the hardware implementation, the exemplary embodiments described herein may be implemented by using 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.

[0168] Embodiments may be practiced in other specific forms. The described embodiments are to be considered in all respects only as illustrative and not restrictive. Thus, the scope of the invention is indicated by the appended claims rather than by the foregoing description. All changes that come within the meaning and range of equivalency of the claims are to be embraced within their scope.

Claims

1. A user equipment (UE) comprising: A transceiver; And A processor coupled to the transceiver, wherein the processor is configured to Receive, via the transceiver, a configuration for CSI reporting, wherein the configuration is associated with a measurement resource set and a prediction resource set; and Transmit, via the transceiver, the CSI report, the CSI report including a resource type indication field to indicate whether the reported resource is a measurement resource selected from the measurement resource set or a prediction resource selected from the prediction resource set.

2. The UE according to claim 1, wherein The configuration is associated with an AI / ML function for at least spatial domain resource prediction, If the resource type indication field indicates that the reported resource is a prediction resource, the AI / ML function predicts the reported resource according to the prediction resource set; and If the resource type indication field indicates that the reported resource is a measurement resource, the reported resource is the resource in the measurement resource set with the highest measured L1-RSRP.

3. The UE according to claim 2, wherein, If the resource type indication field indicates that the reported resource is a prediction resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the prediction resource set, and If the resource type indication field indicates that the reported resource is a measurement resource, the bit width of each CRI or SSBRI field in the CSI report is determined by the number of resources configured in the measurement resource set.

4. The UE according to claim 1, wherein, The configuration is associated with an AI / ML function for at least time domain resource prediction, If the resource type indication field indicates that the reported resource is a prediction resource, the reported resource is a prediction resource predicted by the AI / ML function for each of F future time instances, where F is an integer greater than or equal to 1; and If the resource type indication field indicates that the reported resource is a measurement resource, the reported resource is the resource in the measurement resource set with the highest measured L1-RSRP.

5. The UE according to claim 1, wherein, The configuration is associated with an AI / ML function that can output prediction resources without predicting the L1-RSRP of the prediction resources, The processor is further configured to receive, via the transceiver, a configuration for a second CSI report associated with a second measurement resource set.

6. The UE according to claim 1, wherein, The number of resources configured in the second measurement resource set is the same as the number of resources reported in the CSI report.

7. The UE according to claim 5, wherein, The processor is further configured to receive, via the transceiver, a control signal triggering the second CSI report within a duration since the CSI report was transmitted, wherein the resources configured in the second measurement resource set are quasi-co-located with the resources reported in the CSI report.

8. The UE according to claim 1, wherein, The processor is further configured to transmit, via the transceiver, information about the type of the AI / ML function equipped by the UE.

9. The UE according to claim 1, wherein, The measurement resource set and the prediction resource set are the same resource set.

10. The UE according to claim 1, wherein, The configuration is also associated with a quantization indication.

11. A method performed at a user equipment (UE), comprising: receiving a configuration for CSI reporting, wherein the configuration is associated with a measurement resource set and a prediction resource set; and transmitting the CSI report, the CSI report including a resource type indication field to indicate that the reported resource is a measurement resource selected from the measurement resource set or a prediction resource selected from the prediction resource set.

12. A base station unit, comprising: a transceiver; and a processor coupled to the transceiver, wherein the processor is configured to transmit, via the transceiver, a configuration for CSI reporting, wherein the configuration is associated with a measurement resource set and a prediction resource set; and receive, via the transceiver, the CSI report, the CSI report including a resource type indication field to indicate that the reported resource is a measurement resource selected from the measurement resource set or a prediction resource selected from the prediction resource set.

Images