UE capability report for ai-based CSI reporting

Abstract

A method, system and apparatus are disclosed. A method implemented in a user equipment, UE, (22) that is configured to communicate with a network node (16) includes: generating a UE capability report indicating at least one UE capability for generating an artificial intelligence-, AI, based channel state information, CSI, report; and transmitting the UE capability report to the network node (16).

Description

[0001] UE CAPABILITY REPORT FOR AI-BASED CSI REPORTING

[0002] TECHNICAL FIELD

[0003] The present disclosure relates to wireless communications, and in particular, to artificial intelligence-, Al, based channel state information, CSI, reporting.

[0004] BACKGROUND

[0005] The Third Generation Partnership Project (3GPP) has developed and is developing standards for Fourth Generation (4G) (also referred to as Long Term Evolution (LTE)) and Fifth Generation (5G) (also referred to as New Radio (NR)) wireless communication systems. Such systems provide, among other features, broadband communication between network nodes, such as base stations, and mobile user equipments (UE), as well as communication between network nodes and between UEs. The 3GPP is also developing standards for Sixth Generation (6G) wireless communication networks.

[0006] Channel State Information (CSI) reporting in NR

[0007] In NR, a UE can be configured with one or multiple CSI Report Settings, each configured by a higher layer parameter CSI-ReportConfig. Each CSI-ReportConfig is associated with a bandwidth part (BWP) and includes one or more of the following:

[0008] • a CSI resource configuration for channel measurement

[0009] • a CSI interference measurement (CSLIM) resource configuration for interference measurement

[0010] • reporting configuration type, i.e., aperiodic CSI (on physical uplink shared channel (PUSCH)), periodic CSI (on physical uplink control channel (PUCCH)), or semi-persistent CSI on PUCCH or PUSCH

[0011] • report quantity specifying what is to be reported, such as rank indicator (RI), precoding matrix indicator (PMI), channel quality indicator (CQI)

[0012] • codebook configuration such as type I or type II CSI

[0013] • frequency domain configuration, i.e., subband vs. wideband CQI or PMI, and subband size

[0014] • CQI table to be used

[0015] A UE can be configured with one or multiple CSI resource configurations for channel measurement and one or more CSLIM resources for interference measurement. Each CSI resource configuration for channel measurement can contain one or more nonzero power (NZP) CSI reference signal (CSI-RS) resource sets. For each NZP CSLRSresource set, it can further contain one or more NZP CSI-RS resources. A NZP CSI-RS resource can be periodic, semi-persistent, or aperiodic.

[0016] Similarly, each CSI-IM resource configuration for interference measurement can contain one or more CSI-IM resource sets. For each CSI-IM resource set, it can further contain one or more CSI-IM resources. A CSI-IM resource can be periodic, semi-persistent, or aperiodic.

[0017] CSI reporting types and CSI-RS configuration types

[0018] FIG. 1 illustrates a table in which a summary is provided for the CSI reporting types and CSI-RS configuration types supported in NR.

[0019] LCM operations of AI / ML model and functionality

[0020] A part of artificial intelligence (Al) development and operation is the lifecycle management (LCM) of the Al / machine learning (ML) model (e.g., model training, model deployment, model inference, model monitoring, model updating) and AI / ML functionality.

[0021] In 3GPP AI / ML for NR air interface study item, the LCM procedure is studied for the case that an AI / ML model has a model identifier (ID) with associated information and / or for the case that a given functionality is provided by some AI / ML operations.

[0022] Two types of LCM operations were studied in 3 GPP: functionality -based LCM and model-ID based LCM.

[0023] Functionality refers to an AI / ML-enabled Feature / FG enabled by configuration(s), where configuration(s) is(are) supported based on conditions indicated by UE capability. Correspondingly, functionality-based LCM operates based on, at least, one configuration of an AI / ML-enabled Feature / FG or specific configurations of an AI / ML-enabled Feature / FG. In functionality -based LCM, the network indicates activation / deactivation / fallback / switching of AI / ML functionality via 3GPP signalling (e.g., radio resource control (RRC), medium access control control element (MAC-CE), downlink control information (DCI)). Models may not be identified at the Network, and UE may perform model-level LCM. The network (NW) (e.g., via a network node) may or may not be aware of model -level LCM at the UE. For functionality identification, there may be either one or more than one functionalities defined within an AI / ML-enabled feature, whereby AI / ML-enabled Feature refers to a Feature where AI / ML may be used.

[0024] In model-ID-based LCM, models are identified at the Network, and Network / UE may activate / deactivate / select / switch individual AI / ML models via model ID. A model may be associated with specific configurations / conditions associated with UEcapability of an AI / ML-enabled Feature / FG and additional conditions (e.g., scenarios, sites, and datasets) as determined / identified between the UE-side and NW-side. An AI / ML model identified by a model ID may be logical, and how it maps to physical AI / ML model(s) may be up to implementation.

[0025] NR CSI processing unit (CPU) for computing CSI report

[0026] In NR, the concept of CPU (CSI processing unit) was introduced, where the number of CPUs, denoted as NCPU, is equal to the number of simultaneous CSI calculations supported by the UE. The UE indicates NCPUto the NW as part of the UE capability. When the UE is triggered for a CSI report, a certain number of CPUs, denoted as 0CPU, will be allocated to the UE from the available CPU pool, which will be occupied for a period of time (measured in symbols). If there are not enough CPUs for a given time instance, the newly triggered CSI report does not need to be calculated by the UE.

[0027] The number of occupied CPUs for a given CSI report depends on the content (configured by higher layer parameter ‘ reportQuantity ’), actually the complexity, for calculating it. The followings options are based, e.g., on the current 3GPP NR Technical Specification (TS) 38.214 vl8.6.0 (2025-03):

[0028] - When ‘ reportQuantity ’ is set to ‘none’ and aperiodic TRS (Tracking Reference Signal) is configured, then the TRS is mainly used for time and / or frequency synchronization at the UE, and nothing needs to be reported. In addition, the UE is assumed to have dedicated resources for TRS processing. Therefore, for this case, OCPU= 0.

[0029] - When "reportQuantity ’ is set to beam related parameters, such as ‘cri-RSRP’ (Reference Signal Received Power (RSRP) measured according to CSI Reference Signal Resource Indicator (CRI)), ‘ssb-Index-RSRP’ (RSRP measured according to SSB index), etc., OCPU= 1, since beam related processing is usually not complex.

[0030] - When "reportQuantity ’ is set to non-beam related parameters, such as ‘cri-RLPMLCQF, ‘cri-RI-il’, etc., the CSI report typically occupies as many CPUs as the number of CSLRS resources in the CSLRS resource set for channel measurement.

[0031] - When ‘reportQuantity’ is set to 'cri-RI-PMI-CQI' and with codebookType set to 'typeII-Doppler-rl8' or 'typeII-Doppler-PortSelection-rl8',

[0032] o if the corresponding CSLRS Resource Set for channel measurement is aperiodic and configured with K CSLRS resources, OCPU= 8 for K = 12 and OCPU= Y • K for K < 12, where

[0033]

[0034] E {1, 2, 3} is reported by UE capability indication,o if the corresponding CSI-RS Resource Set for channel measurement is periodic or semi-persistent and configured with a single CSI-RS resource, 0CPU= 4 for 1V4= 1 and 0CPU= max( Y2• 1V4, 4) for 1V4> 1, where the value of 1V4is configured by the higher layer parameter N4, and Y2E {1, 2, 3} is reported by UE capability indication, The period of time (measured by the number of symbols) for which the CPU is occupied for a given CSI report depends on the time domain behavior of the said CSI report, in general:

[0035] - For periodic or semi-persistent CSI report (excluding an initial semi-persistent CSI report on PUSCH after the PDCCH triggering the report and a semi-persistent CSI report on PUSCH configured with the higher layer parameter codebookType set to 'typeII-Doppler-rl8' or 'typeII-Doppler-PortSelection-rl8'), the CPU is occupied from the first symbol of the earliest CSI-RS / CSI-IM / SSB resource for channel or interference measurement, no later than the CSI-RS reference resource, until the last symbol of the configured PUSCH / PUCCH carrying the report. For the example in FIG. 2, one CSI-RS resource is configured to the UE for channel measurement (denoted by the first bar), then T' is the CPU occupancy period for periodic or semi-persistent CSI report.

[0036] - For aperiodic CSI report, the CPU is occupied from the first symbol after the PDCCH triggering the CSI report, until the last symbol of the scheduled PUSCH carrying the report. For the example in FIG. 2, T" is the CPU occupancy period for aperiodic CSI report.

[0037] - An initial semi-persistent CSI report on PUSCH after the PDCCH trigger occupies CPU(s) from the first symbol after the PDCCH until the last symbol of the scheduled PUSCH carrying the report. For the example in FIG. 2, T" is the CPU occupancy period for an initial semi-persistent CSI report.

[0038] - A semi-persistent CSI report on PUSCH configured with the higher layer parameter codebookType set to 'typeII-Doppler-rl8' or 'typeII-Doppler-PortSelection-rl8' occupies CPU(s) from the first symbol of A>-th latest consecutive periodic / semi-persistent CSI-RS occasions no later than CSI reference resource, until the last symbol of the PUSCH carrying the report, where the value of KPE {1,2,4} is indicated by UE capability.

[0039] FIG. 2 is a diagram of an explanation of CPU occupancy period.

[0040] If a CSI-RS resource is referred N times by one or more CSI Reporting Settings not configured with higher layer parameter csi-ReportSubConfigToAddModList, the CSI-RS resource and the CSI-RS ports within the CSI-RS resource are counted N times.For a periodic or semi-persistent CSI-RS resource in a CSI-RS resource set for channel measurement linked to a CSI-ReportConfig configured with the higher layer parameter codebookType set to 'typeII-Doppler-rl8' or 'typeII-Doppler-PortSelection-rl8', the CSI-RS resource and the CSI-RS ports within the CSI-RS resource are counted KPtimes, where the value of KPE {1,2,4} is indicated by UE capability.

[0041] Examples of AI / ML based CSI reporting use cases

[0042] AI / ML based time domain CSI prediction using UE-sided models

[0043] One or more AI / ML models can be trained and deployed at a UE for the Al-based CSI-prediction feature. FIG. 3 is a diagram of an example for the inference procedure for CSI prediction using a UE-sided AI / ML model (e.g., as specified in 3GPP Technical Reference (TR) 38.843 vl8.0.0). For generating the input of CSI prediction model, some further pre-processing on the measured channel may be needed; for the output of the CSI prediction model, some further post-processing may also be applied.

[0044] During model inference, a UE is configured by the network node to measure a set of historical CSI-RSs (e.g., the K CSI-RS measurements in the observation window shown in FIG. 4) and then report a predicted CSI in the scheduled UL slot for one or multiple future time instances (e.g., the A4future tine instances separation in FIG. 4, which is a diagram of signalling for predicted CSI reporting with aperiodic CSI-RS resource) using its AI / ML model. Alternatively, NW (network or network node) may also configure a legacy periodic (P) or semi-persistent (SP) CSI-RS resource for measuring historical CSI and creating model input.

[0045] AI / ML based CSI compression using two-sided models

[0046] FIG. 5 is a diagram of an example for the inference procedure for CSI compression using a two-sided model (e.g., as specified in 3GPP TR 38.843 vl8.0.0). The two-sided model includes of two parts, i.e., an AI / ML-based CSI generation part to generate the CSI feedback information and an AI / ML-based CSI reconstruction part which is used to reconstruct the CSI from the received CSI feedback information. At least for inference, the CSI generation part is located at the UE side, and the CSI reconstruction part is located at the network node side.

[0047] FIG. 6 is a diagram of how an autoencoder (AE) might be used for AI / ML-enhanced CSI reporting in NR, e.g., for CSI compression. The UE measures the channel in the downlink using CSI-RS. The UE estimates the channel for each subcarrier (SC) from each base station TX antenna to each UE RX antenna. The estimate can be viewed as a three-dimensional channel matrix. The 3D channel matrix represents the MIMO channelestimated over several SCs and is input to the encoder. However, there are different architectures where a processed version of the 3D MIMO channel, or a processed subset of the information, e.g., singular vectors of the MIMO channel, is input to the encoder.

[0048] The AE encoder is implemented in the UE, and the AE decoder is implemented in the NW, denoted BS for base station in the figure. The output of the AE encoder (Al compressed CSI information) is reported from the UE to the NW as a CSI report over the uplink. The Al compressed CSI information can be viewed as a learned latent representation of the channel.

[0049] AI / ML based beam management using UE-sided models

[0050] In 3 GPP Release 18 (Rel-18) and earlier releases, the support for measurement of a set of resources (e.g., CSI-RSs or synchronization signal blocks (SSBs)) have been standardized. Where for mmWave beam management, each resource in a set of resources is typically transmitted with a different beam. In 3GPP Release 19 (Rel-19), support has been added to also support UE providing predictions of a set of resources (i.e., a set of beams). The predicted set of resources are denoted the Set A of beams (set A resource set). The predictions are based on UE measurements on a set B of beams (a set B of resources), where the measurements are done using legacy measurement procedures. The Set B of beams could either be a subset of the Set A of beams, or the set A of beams could include different beams compared to the Set B of beams (for example Set A includes narrow beams and Set B includes wide beams).

[0051] FIG. 7 is a diagram of an example of Set A and Set B of beams, where Set B is different from Set A. Set B of beams are wide NW beams and the Set A of beams are the narrow network node beams.

[0052] FIG. 8 is a diagram of an example of Set A and Set B of beams, where Set B is a subset of Set A of beams. Both Set B and Set A of beams are the narrow network node beams.

[0053] If the UE predicts the set A of beam in the same time instance as the measurement of set B, it is denoted as beam management (BM) Case 1 in Rel-19. In addition to BM-Casel, Rel-19 will also support UE-based temporal (BM case 2) beam prediction for a Set A of beams based on measurement results of Set B of beams, where the Set A of beams and Set B of beams can be the same set of beams or different set of beams. That is, for temporal beam prediction, the UE may provide predictions (forecasts) of the set A of beams in a future time instance (e.g. 80ms ahead of last set B measurements). For AI / ML based temporal beam prediction, the measurement results of K (K > 1) latestmeasurement instances during a time window T1 of the Set B beams are used for AI / ML model input.

[0054] The general picture for the Rel-19 support is shown in FIG. 9, which is a diagram of an example of the inference procedure for beam management.

[0055] FIG. 9 provides an example for the inference procedure for beam management for BM-Casel and BM-Case2. Measurements based on Set B of beams are used as model input. Based on model output (e.g., probability of each beam in Set A being the Top-1 beam, predicted Ll-RSRPs (Layer 1 Reference Signal Received Power)), Top-l / N beam(s) among Set A of beams can be predicted and / or potentially with predicted Ll-RSRPs (depending on the labeling). For BM-Case2, the measurements from historic time instance(s) are used as model input for temporal DL beam prediction of beams from Set A The configuration of set A and set B is done via extending the CSI report configuration. The set A (predicted beams) are configured via a new field that indicates that these are the resources to be predicted by the UE (e.g., a NZP-CSI-RS-ResourceSet or a CSI-SSB-ResourceSetld), and another field that indicates the set B resources that are to be measured by the UE (used as input to the model). Additionally, the configuration of an “associated ID” is part of the CSI report configuration. Such associated ID is used by the NW to indicate the NW properties of the NW TX beams that is used to transmit each set of resources. This is used for the UE to first collect measurements and train the beam prediction model. After UE has trained its model, if the UE receives the same associated ID during inference, the UE uses the model during the inference stage. The UE can use the same model since when it received the same associated ID, the UE knows that the NW transmission properties are the same as during its training, hence the model inference outputs are valid.

[0056] AI / ML based CSI-RS overhead reduction using UE-sided models

[0057] FIG. 10 is a diagram of an example of using a UE-sided model to reduce CSLRS overhead reduction for CSI acquisition, e.g., using UE-sided model to obtain channel information for all Ntantenna ports based on measurements on a subset of NRSports. In this example, it is assumed that the NW deploys a massive MIMO antenna array with Nttransmitter chains, i.e., physical antenna ports. For massive MIMO system, the value of is typically very large, hence sounding CSLRS for each of the antenna ports (that is, configuring one CSLRS port for each of the physical antenna ports) will introduce significant overhead and requires a large CSLRS resource. In light of this, an Al model can be used, whose input is channel measurement based on NRSCSLRS ports, which aretransmitted over NRSof the Ntantenna ports or alternatively, each CSI-RS port is transmitted from multiple of the Ntantenna ports, using a multi-antenna precoding vector.. The output of the Al model is then a CSI report associated for all Ntantenna ports. Since NRS< Nt, CSI-RS overhead in the air interface can be reduced.

[0058] For an AI / ML based CSI reporting feature (e.g., CSI prediction using UE-side Al model, CSI compression using two-sided models, beam prediction using UE-side Al model, or CSI-RS overhead reduction with UE-sided AI / ML extrapolation), a UE may use dedicated hardware (e.g., graphics processing unit (GPU), specialized accelerators, memory, etc.) resources to run AI / ML based CSI report related processing, resulting a different CSI processing capability and the CSI processing consumes dedicated resources (referred to as “AI-CPU” herein), or the UE may reuse the legacy hardware resources (referred to as “legacy CPU” herein) that are used for generating legacy non-AI based CSI report to run the AI / ML based CSI reporting related processing. The legacy CPU could also be referred to as non-AI CPU.

[0059] Different UE / chipset vendors or UE releases / versions may choose different hardware design options (i.e., dedicated resource pool or shared resource pool with non-AI based CSI reporting) when implementing the Al based CSI reporting features. In addition, even for the same UE / chipset vendor or the same UE release / version, some Al based CSI reporting features may be implemented using dedicated hardware resources, while some other Al based CSI reporting features (e.g., Al features that require small AI / ML models or share the similar type of matrix operations as for legacy CSI report generation) may be implemented by reusing the hardware resources for legacy non-AI based CSI reporting. Moreover, even within the same feature, the UE might use dedicated Al hardware or reusing the hardware resources for legacy non-AI based CSI reporting based on the received NW configuration. For example, when the NW configures the UE to predict a small set of beams in set A, it could be enabled by using existing non-AI hardware in the UE. In contrast, a larger set of beams to predict, it would need dedicated hardware.

[0060] All the above introduces the uncertainties in CPU (occupied hardware resources) counting and CSI processing timeline for an Al based CSI report, which makes it difficult for the NW to decide whether / when to trigger an Al based CSI report. If the NW triggers a report when the UE has no CPU available, then the UE will ignore the report trigger leading to reduced NW performance, which is a problem.

[0061] SUMMARYHence, for a UE that is capable of one or more Al-based CSI reporting features, a solution is needed to remove the above uncertainties, and to align the CPU usage, CPU counting and processing timeline for an Al-based CSI report between the UE and the NW.

[0062] Some embodiments advantageously provide methods, systems, and apparatuses for Al-based CSI reporting.

[0063] According to an embodiment, a method implemented in a UE is provided, which is configured to communicate with a network node. The method comprises generating a UE capability report indicating at least one UE capability for generating an Al-based CSI report. Further, the method comprises transmitting the UE capability report to the network node.

[0064] According to a further embodiment, a method implemented in a network node is provided, which is configured to communicate with a UE. The method comprises receiving a UE capability report indicating at least one UE capability for generating an AI-based CSI report. Further, the method comprises configuring the UE based on the UE capability report.

[0065] According to a further embodiment, a UE is provided, which is configured to communicate with a network node. The UE is configured to generate a UE capability report indicating at least one UE capability for generating an Al-based CSI report, and to transmit the UE capability report to the network node.

[0066] According to a further embodiment, a UE is provided, which is configured to communicate with a network node. The UE comprises a radio interface and / or processing circuitry configured to generate a UE capability report indicating at least one UE capability for generating an Al-based CSI report, and to transmit the UE capability report to the network node.

[0067] According to a further embodiment, a network node is provided, which is configured to communicate with a UE. The network node is configured to receive a UE capability report indicating at least one UE capability for generating an Al-based CSI report, and to configure the UE based on the UE capability report.

[0068] According to a further embodiment, a network node is provided, which is configured to communicate with a UE. The network node a radio interface and / or processing circuitry configured to receive a UE capability report indicating at least one UE capability for generating an Al-based CSI report, and to configure the UE based on the UE capability report.In some embodiments, the UE capability report includes an indication of a processing unit type for generating the Al-based CSI report.

[0069] In some embodiments, the indication of the processing unit type is indicated as a component of a feature group (FG).

[0070] In some embodiments, a number of occupied processing units for an Al-based CSI report is defined based on the indication of processing unit type.

[0071] In some embodiments, a number of occupied legacy processing units for the AI-based CSI report is zero if the indication of the processing unit type indicates that an Al processing unit is used for generating the Al-based CSI report.

[0072] In some embodiments, the number of occupied legacy processing units for the AI-based CSI report is defined by associated report configuration parameters if the indication of the processing unit type does not indicate that an Al processing unit is used for generating the Al-based CSI report.

[0073] In some embodiments, the associated report configuration parameters include one or more of: report quantity, CSI reference signal resource type, number of CSI reference signal resources, number of prediction time resources.

[0074] In some embodiments, a number of occupied Al processing units for the Al-based CSI report is zero if the indication of the processing unit type indicates that a legacy processing unit is used for generating the Al-based CSI report.

[0075] In some embodiments, the number of occupied Al processing units for the AI-based CSI report is defined by associated report configuration parameters if the indication of the processing unit type does not indicate that a legacy processing unit is used for generating the Al-based CSI report.

[0076] In some embodiments, the associated report configuration parameters include one or more of: report quantity, CSI reference signal resource type, number of CSI reference signal resources, number of prediction time resources.

[0077] In some embodiments, the UE capability report indicates a number of simultaneous CSI calculations using legacy processing unit resources supported by the UE.

[0078] In some embodiments, the UE capability report indicates a number of simultaneous CSI calculations using Al processing unit resources supported by the UE.

[0079] In some embodiments, the UE capability report includes an indication of a number of simultaneous CSI calculations using each of a first type of CPU and a second type of CPU.In some embodiments, a UE capable of an Al-based CSI reporting feature / feature-group indicates the type of processing unit resources (e.g., AI-CPU or legacy CPU) it uses for generating an Al based CSI report associated to an Al based CSI reporting feature / feature-group to the NW.

[0080] In some embodiments, rules are defined for the UE to perform the CPU counting for an Al-based CSI report and to decide whether it may drop the requested Al-based CSI report, depending on the type of processing unit resources used for generating this CSI report.

[0081] Some embodiments include signaling to support a UE indicating the type of processing unit resources (e.g., AI-CPU or legacy CPU) it uses for generating an Al based CSI report associated to an Al based CSI reporting feature / feature-group to the NW (e.g., via network node).

[0082] Some embodiments include enabling the NW (e.g., via network node) to efficiently trigger and configure a CSI report for a UE that is capable of one or more Al based CSI reporting features, and to ensure a consistent UE behavior on handling a CSI report when there is lack of sufficient unoccupied resources for processing the requested CSI report. Some embodiments also allow the UE the implementation flexibility to choose which type of hardware resources (e.g., AI-CPU or legacy CPU) to use for performing computations related to a certain Al-based CSI reporting feature.

[0083] BRIEF DESCRIPTION OF THE DRAWINGS

[0084] A more complete understanding of the present embodiments, and the attendant advantages and features thereof, will be more readily understood by reference to the following detailed description when considered in conjunction with the accompanying drawings wherein:

[0085] FIG. 1 illustrates a table summarizing CSI reporting types and CSI-RS configuration types supported in NR.

[0086] FIG. 2 is a diagram of an explanation of CPU occupancy period;

[0087] FIG. 3 is a diagram of an example for the inference procedure for CSI prediction using a UE-sided AI / ML model;

[0088] FIG. 4, which is a diagram of signalling for predicted CSI reporting with aperiodic CSI-RS resource;

[0089] FIG. 5 is a diagram of an example for the inference procedure for CSI compression using a two-sided model;FIG. 6 is a diagram of how an autoencoder (AE) might be used for AI / ML-enhanced CSI reporting in NR;

[0090] FIG. 7 is a diagram of an example of Set A and Set B of beams, where Set B is different from Set A;

[0091] FIG. 8 is a diagram of an example of Set A and Set B of beams, where Set B is a subset of Set A of beams;

[0092] FIG. 9, which is a diagram of an example of the inference procedure for beam management;

[0093] FIG. 10 is a diagram of an example of using a UE-sided model to reduce CSI-RS overhead reduction for CSI acquisition;

[0094] FIG. 11 is a schematic diagram of an example network architecture illustrating a communication system according to principles disclosed herein;

[0095] FIG. 12 is a block diagram of a network node in communication with a user equipment over a wireless connection according to some embodiments of the present disclosure;

[0096] FIG. 13 is a schematic diagram of another example network architecture illustrating a communication system according to principles disclosed herein;

[0097] FIG. 14 is a flowchart of an example process in a network node according to some embodiments of the present disclosure;

[0098] FIG. 15 is a flowchart of an example process in a user equipment according to some embodiments of the present disclosure; and

[0099] FIG. 16 is a signal diagram according to some embodiments of the present disclosure.

[0100] DETAILED DESCRIPTION

[0101] Before describing in detail example embodiments, it is noted that the embodiments reside primarily in combinations of apparatus components and processing steps related to Al-based CSI reporting. Accordingly, components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

[0102] As used herein, relational terms, such as “first” and “second,” “top” and “bottom,” and the like, may be used solely to distinguish one entity or element from another entity orelement without necessarily requiring or implying any physical or logical relationship or order between such entities or elements. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and / or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0103] In embodiments described herein, the joining term, “in communication with” and the like, may be used to indicate electrical or data communication, which may be accomplished by physical contact, induction, electromagnetic radiation, radio signaling, infrared signaling or optical signaling, for example. One having ordinary skill in the art will appreciate that multiple components may interoperate and modifications and variations are possible of achieving the electrical and data communication.

[0104] In some embodiments described herein, the term “coupled,” “connected,” and the like, may be used herein to indicate a connection, although not necessarily directly, and may include wired and / or wireless connections.

[0105] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and / or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0106] The term “network node” used herein can be any kind of network node comprised in a radio network which may further comprise any of base station (BS), radio base station, base transceiver station (BTS), base station controller (BSC), radio network controller (RNC), g Node B (gNB), evolved Node B (eNB or eNodeB), Node B, multistandard radio (MSR) radio node such as MSR BS, multi-cell / multicast coordination entity (MCE), relay node, donor node controlling relay, radio access point (AP), transmission points, transmission-reception points (TRPs), transmission nodes, Remote Radio Unit(RRU) Remote Radio Head (RRH), a core network node (e.g., mobile management entity (MME), self-organizing network (SON) node, a coordinating node, positioning node, MDT node, etc.), an external node (e.g., 3rd party node, a node external to the current network), nodes in distributed antenna system (DAS), a spectrum access system (SAS) node, an element management system (EMS), etc. The network node may also comprise test equipment. The term “radio node” used herein may be used to also denote a user equipment (UE) such as a wireless device (WD) or a radio network node.

[0107] In some embodiments, the non-limiting terms wireless device (WD) or a user equipment (UE) are used interchangeably. The UE herein can be any type of user equipment capable of communicating with a network node or another UE over radio signals, such as a wireless device (WD). The UE may also be a radio communication device, target device, device to device (D2D) UE, machine type UE or UE capable of machine to machine communication (M2M), low-cost and / or low-complexity UE, a sensor equipped with UE, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, Customer Premises Equipment (CPE), an Internet of Things (loT) device, or a Narrowband loT (NB-IOT) device etc.

[0108] Also, in some embodiments the generic term “radio network node” is used. It can be any kind of a radio network node which may comprise any of base station, radio base station, base transceiver station, base station controller, network controller, RNC, evolved Node B (eNB), Node B, gNB, Multi -cell / multicast Coordination Entity (MCE), relay node, access point, radio access point, Remote Radio Unit (RRU) Remote Radio Head (RRH).

[0109] Note that although terminology from one particular wireless system, such as, for example, 3GPP LTE and / or New Radio (NR) and / or 6G, may be used in this disclosure, this should not be seen as limiting the scope of the disclosure to only the aforementioned system. It is contemplated that other 3GPP systems may make use of the concepts and arrangements disclosed herein. For example, a disclosure relating to NR may also be implementable in a 6G system and / or an LTE system, a disclosure relating to 6G may also be implementable in a NR and / or LTE system, and a disclosure relating to LTE may also be implementable in a NR and / or 6G system. Other wireless systems, including without limitation Wide Band Code Division Multiple Access (WCDMA), Worldwide Interoperability for Microwave Access (WiMax), Ultra Mobile Broadband (UMB) and Global System for Mobile Communications (GSM), may also benefit from exploiting the ideas covered within this disclosure.Note further, that functions described herein as being performed by a user equipment (UE) or a network node may be distributed over a plurality of UEs and / or network nodes. In other words, it is contemplated that the functions of the network node and user equipment described herein are not limited to performance by a single physical device and, in fact, can be distributed among several physical devices.

[0110] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0111] Some embodiments are directed to Al-based CSI reporting.

[0112] Referring to the drawing figures, in which like elements are referred to by like reference numerals, there is shown in FIG. Il a schematic diagram of a communication system 10, according to an embodiment, such as a 3 GPP -type cellular network that may support standards such as LTE and / or NR (5G) and / or 6G, which comprises an access network 12, such as a radio access network, and a core network 14. The core network 14 includes one or more network nodes 15. The access network 12 comprises a plurality of network nodes 16a, 16b, 16c (referred to collectively as network nodes 16), such as NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 18a, 18b, 18c (referred to collectively as coverage areas 18). Each network node 16a, 16b, 16c is connectable to the core network 14 over a wired or wireless connection 20. A first user equipment (UE) 22a located in coverage area 18a is configured to wirelessly connect to, or be paged by, the corresponding network node 16a. A second UE 22b in coverage area 18b is wirelessly connectable to the corresponding network node 16b. While a plurality of UEs 22a, 22b (collectively referred to as user equipments 22) are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole UE is in the coverage area or where a sole UE is connecting to the corresponding network node 16. Note that although only two UEs 22 and three network nodes 16 are shown for convenience, the communication system may include many more UEs 22 and network nodes 16.

[0113] As one example, in certain embodiments, access network 12 may contain some access network nodes 16 that support 3 GPP radio access technologies (RAT), such as LTE or NR, while other access network nodes 16 support (or the same access network nodes 16additionally support) non-3GPP RATs, such as Wi-Fi or a proprietary RAT. As another example, communication system 10 may support multiple generations of related communication standards (e.g., 4G, 5G and 6G 3GPP communication standards) and, as a result, may include an access network 12 and / or a core network 14 that supports multiple different standard generations or may include multiple access networks 12 and / or multiple core networks 14 with individual networks supporting different standards generations.

[0114] Also, it is contemplated that a UE 22 can be in simultaneous communication and / or configured to separately communicate with more than one network node 16 and more than one type of network node 16. For example, a UE 22 can have dual connectivity with a network node 16 that supports LTE and the same or a different network node 16 that supports NR. As an example, UE 22 can be in communication with an eNB for LTEZE-UTRAN, a gNB for NR / NG-RAN (i.e. being configured for multiradio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC) and / or Wi-Fi.

[0115] A network node 16 (eNB or gNB) is configured to include a configuration unit 24 which is configured to perform one or more network node 16 functions described herein, including functions related to Al-based CSI reporting. A user equipment 22 is configured to include a implementation unit 26 which is configured to perform one or more UE 22 functions described herein, including functions related to Al-based CSI reporting.

[0116] Example implementations, in accordance with an embodiment, of the UE 22 and network node 16 discussed in the preceding paragraphs will now be described with reference to FIG. 12.

[0117] The communication system 10 includes a network node 16 provided in a communication system 10 and including hardware 28 enabling it to communicate with the UE 22. The hardware 28 may include a communication interface 29 comprising a radio interface 30 for setting up and maintaining at least a wireless connection 32 with a UE 22 located in a coverage area 18 served by the network node 16. The radio interface 30 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers. The radio interface 30 includes an array of antennas 34 to radiate and receive signal(s) carrying electromagnetic waves.

[0118] In the embodiment shown, the hardware 28 of the network node 16 further includes processing circuitry 36. The processing circuitry 36 may include a processor 38 and a memory 40. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 36 may comprise integratedcircuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 38 may be configured to access (e.g., write to and / or read from) the memory 40, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM (Random Access Memory) and / or ROM (Read-Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read-Only Memory).

[0119] Thus, the network node 16 further has software 42 stored internally in, for example, memory 40, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the network node 16 via an external connection. The software 42 may be executable by the processing circuitry 36. The processing circuitry 36 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by network node 16.

[0120] Processor 38 corresponds to one or more processors 38 for performing network node 16 functions described herein. The memory 40 is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 42 may include instructions that, when executed by the processor 38 and / or processing circuitry 36, causes the processor 38 and / or processing circuitry 36 to perform the processes described herein with respect to network node 16. For example, processing circuitry 36 of the network node 16 may include configuration unit 24 which is configured to perform one or more network node 16 functions described herein, including functions related to Al-based CSI reporting.

[0121] The network node 16 may be composed of multiple distinct network entities (e.g., a NodeB entity and a RNC entity, or a BTS entity and a BSC entity, etc.), which may each have or utilize their own respective physical components. In certain scenarios in which the network node 16 comprises multiple such entities (e.g., BTS and BSC), one or more of the separate entities may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 16 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memories 40 or portions of memory 40 for different RATs) and some components may be reused (e.g., a same antenna may be shared by different RATs). The network node 16 may also include multiple sets of the various illustrated components for different wirelesstechnologies integrated into network node 16, for example GSM, WCDMA, LTE, NR, Wi-Fi (e.g., according to an IEEE 802.11 family standard), Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 16.

[0122] In certain alternative embodiments, network node 16 may be capable of wireless communication but does not include separate radio front-end circuitry, instead, the processing circuitry 36 includes radio front-end circuitry and is connected to the antenna 34. Similarly, in some embodiments, all or some of the RF receivers, transmitters and / or transceivers are part of the radio interface 30. In still other embodiments, the communication interface 29 includes one or more ports or terminals, the radio interface 30, and the RF receiver, transmitter and / or transceiver, and the communication interface 31 communicates with baseband processing circuitry, which is part of a digital unit (not shown).

[0123] The antenna 34 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 34 may be coupled to the radio front-end circuitry in radio interface 30 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 34 is separate from the network node 16 and connectable to the network node 16 through one or more interfaces or ports.

[0124] Network node 15 can include one or more components described above with respect to network node 16, e.g., communication interface 29, radio interface 30, antenna 34, ports, processing circuitry 36, processor 38, memory 40 and software 42. These elements of network node 15 can be arranged such that network node 15 can perform various core network functions. Network node 15 can communicate wirelessly or via a wired connection with network nodes 16 via communication link 59.

[0125] The communication system 10 further includes the UE 22 already referred to. The UE 22 may have hardware 44 that may include a radio interface 46 configured to set up and maintain a wireless connection 32 with a network node 16 serving a coverage area 18 in which the UE 22 is currently located. The radio interface 46 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers. The radio interface 46 includes an array of antennas 48 to radiate and receive signal(s) carrying electromagnetic waves.Communication functions of the radio interface 46 may include cellular communication, Wi-Fi communication (e.g., according to an IEEE 802.11 family standard), LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0126] The hardware 44 of the UE 22 further includes processing circuitry 50. The processing circuitry 50 may include a processor 52 and memory 54. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 50 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 52 may be configured to access (e.g., write to and / or read from) memory 54, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM (Random Access Memory) and / or ROM (Read-Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read-Only Memory).

[0127] Thus, the UE 22 may further comprise software 56, which is stored in, for example, memory 54 at the UE 22, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the UE 22. The software 56 may be executable by the processing circuitry 50. The software 56 may include a client application 58. The client application 58 may be operable to provide a service to a human or non-human user via the UE 22.

[0128] The processing circuitry 50 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by UE 22. The processor 52 corresponds to one or more processors 52 for performing UE 22 functions described herein. The UE 22 includes memory 54 that isconfigured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 56 and / or the client application 58 may include instructions that, when executed by the processor 52 and / or processing circuitry 50, causes the processor 52 and / or processing circuitry 50 to perform the processes described herein with respect to UE 22. For example, the processing circuitry 50 of the user equipment 22 may include implementation unit 26 which is configured to perform one or more UE 22 functions described herein, including functions related to Al-based CSI reporting.

[0129] In some embodiments, the inner workings of the network node 16 and UE 22 may be as shown in FIG. 12 and independently, the surrounding network topology may be that of FIG. 11.

[0130] The wireless connection 32 between the UE 22 and the network node 16 is in accordance with the teachings of the embodiments described throughout this disclosure. More precisely, the teachings of some of these embodiments may improve the data rate, latency, and / or power consumption and thereby provide benefits such as reduced user waiting time, relaxed restriction on file size, better responsiveness, extended battery lifetime, etc. In some embodiments, a measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve.

[0131] Although FIG. 11 and 12 show various “units” such as configuration unit 24 and implementation unit 26 as being within a respective processor, it is contemplated that these units may be implemented such that a portion of the unit is stored in a corresponding memory within the processing circuitry. In other words, the units may be implemented in hardware or in a combination of hardware and software within the processing circuitry.

[0132] FIG. 13 is another example of a communication system 10 according to some embodiments. As used herein, the communication system 10 of FIG. 13 includes multiple access points (APs) 60 (with four example APs 60a, 60b, 60c, and 60d being depicted) and multiple wireless devices, referred to in the context of communication system 10 of FIG.

[0133] 13 as stations (STAs) 62 (referred to individually as STA 62a, STA 62b, STA 62c, STA 62d, and STA 62e). STA 62a is served by AP 60a in a first basic service set (BSS) 64a. STA 60b and STA 60c are served by AP 60b in a second BSS, BSS 64b. STA 62d is served by AP 60c in a third BSS, BSS 64c. STA 62e is served by AP 60d in a fourth BSS, BSS 64d. Stations 62 may be non-AP STAs and correspond to various kinds of wireless devices, for example, user terminals, such as mobile or stationary computing devices like smartphones, laptop computers, desktop computers, tablet computers, gaming devices,head-mounted displays (HMDs) for Augmented Reality (AR) or Virtual Reality (VR), or the like, including UEs 22 that are shown and described with respect to FIG. 11 and 12. In other words, in some embodiment, STA 62 is a UE 22. Further, stations 62 could, for example, correspond to other kinds of equipment like smart home devices, printers, multimedia devices, data storage devices, or the like.

[0134] Each of STAs 62 may connect through a radio link to one of APs 60. For example, depending on location or channel conditions experienced by a given STA 62, the STA may select an appropriate AP and BSS for establishing the radio link. The radio link may be based on one or more orthogonal frequency-division multiplexing (OFDM) carriers from a frequency spectrum that is shared on the basis of a contention-based mechanism, e.g., an unlicensed or license exempt band like 2.4 GHz Industrial, Scientific, and Medical (ISM) band, the 5 GHz band, the 6 GHz band, or the 60 GHz band.

[0135] Each AP 60 may provide data connectivity to STAs 62 connected to a particular AP 60. As illustrated, APs 60 may be connected to a data network 66. In this way, APs 60 may also provide data connectivity between STAs 62 and other entities, e.g., to one or more servers, service providers, data sources, data sinks, user terminals, or the like.

[0136] Accordingly, the radio link established between a given STA 62 and its serving AP 60 may be used for providing various kinds of services to STA 62, e.g., a voice service, a multimedia service, or other data service. Such services may be based on applications that are executed on STA 62 and / or on a device linked to STA 62. By way of example, FIG. 13 illustrates an application service platform 68 provided in data network 66. The application(s) executed on STA 62 and / or on one or more other devices linked to STA 62 may use the radio link for data communication with one or more other STA 62 and / or the application service platform 68, thereby enabling utilization of the corresponding service(s) at STA 62.

[0137] FIG. 14 is a flowchart of an example process in a network node 16 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 36 (including the configuration unit 24), processor 38, and / or radio interface 30. Network node 16 configured to receive a UE capability report indicating at least one UE capability for generating an artificial intelligence-, Al, based channel state information, CSI, report (Block SI 00). Network node 16 is configured to configure the UE based on the UE capability report (Block SI 02).In some embodiments, the UE capability report includes an indication of a processing unit type for generating the Al-based CSI report. The processing unit type may be a CPU (CSI processing unit) type, e.g., a first type of CPU and a second type of CPU, more specifically a legacy CPU and an AI-CPU. The legacy CPU may also be denoted as non- Al CPU.

[0138] In some embodiments, the indication of the processing unit type is indicated as a component of a feature group (FG).

[0139] In some embodiments, a number of occupied processing units for an Al-based CSI report is defined based on the indication of processing unit type.

[0140] In some embodiments, a number of occupied legacy processing units for the AI-based CSI report is zero if the indication of the processing unit type indicates that an Al processing unit is used for generating the Al-based CSI report.

[0141] In some embodiments, the number of occupied legacy processing units for the AI-based CSI report is defined by associated report configuration parameters if the indication of the processing unit type does not indicate that an Al processing unit is used for generating the Al-based CSI report.

[0142] In some embodiments, the associated report configuration parameters include one or more of: report quantity, CSI reference signal resource type, number of CSI reference signal resources, number of prediction time resources.

[0143] In some embodiments, a number of occupied Al processing units for the Al-based CSI report is zero if the indication of the processing unit type indicates that a legacy processing unit is used for generating the Al-based CSI report.

[0144] In some embodiments, the number of occupied Al processing units for the AI-based CSI report is defined by associated report configuration parameters if the indication of the processing unit type does not indicate that a legacy processing unit is used for generating the Al-based CSI report.

[0145] In some embodiments, the associated report configuration parameters include one or more of: report quantity, CSI reference signal resource type, number of CSI reference signal resources, number of prediction time resources.

[0146] In some embodiments, the UE capability report indicates a number of simultaneous CSI calculations using legacy processing unit resources supported by the UE.

[0147] In some embodiments, the UE capability report indicates a number of simultaneous CSI calculations using Al processing unit resources supported by the UE.In some embodiments, the UE capability report includes an indication of a number of simultaneous CSI calculations using each of a first type of CPU, e.g., legacy CPU, and a second type of CPU, e.g., AI-CPU.

[0148] FIG. 15 is a flowchart of an example process in a user equipment 22 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of user equipment 22 such as by one or more of processing circuitry 50 (including the implementation unit 26), processor 52, and / or radio interface 46. User equipment 22 is configured to generate a UE capability report indicating at least one UE capability for generating an artificial intelligence-, Al, based channel state information, CSI, report (Block SI 04). UE 22 is configured to transmit the UE capability report to the network node (Block SI 06).

[0149] In some embodiments, the UE capability report includes an indication of a processing unit type for generating the Al-based CSI report. The processing unit type may be a CPU (CSI processing unit) type, e.g., a first type of CPU and a second type of CPU, more specifically a legacy CPU and an AI-CPU. The legacy CPU may also be denoted as non- Al CPU.

[0150] In some embodiments, the indication of the processing unit type is indicated as a component of a feature group (FG).

[0151] In some embodiments, a number of occupied processing units for an Al-based CSI report is defined based on the indication of processing unit type.

[0152] In some embodiments, a number of occupied legacy processing units for the AI-based CSI report is zero if the indication of the processing unit type indicates that an Al processing unit is used for generating the Al-based CSI report.

[0153] In some embodiments, the number of occupied legacy processing units for the AI-based CSI report is defined by associated report configuration parameters if the indication of the processing unit type does not indicate that an Al processing unit is used for generating the Al-based CSI report.

[0154] In some embodiments, the associated report configuration parameters include one or more of: report quantity, CSI reference signal resource type, number of CSI reference signal resources, number of prediction time resources.

[0155] In some embodiments, a number of occupied Al processing units for the Al-based CSI report is zero if the indication of the processing unit type indicates that a legacy processing unit is used for generating the Al-based CSI report.In some embodiments, the number of occupied Al processing units for the AI-based CSI report is defined by associated report configuration parameters if the indication of the processing unit type does not indicate that a legacy processing unit is used for generating the Al-based CSI report.

[0156] In some embodiments, the associated report configuration parameters include one or more of: report quantity, CSI reference signal resource type, number of CSI reference signal resources, number of prediction time resources.

[0157] In some embodiments, the UE capability report indicates a number of simultaneous CSI calculations using legacy processing unit resources supported by the UE.

[0158] In some embodiments, the UE capability report indicates a number of simultaneous CSI calculations using Al processing unit resources supported by the UE.

[0159] In some embodiments, the UE capability report includes an indication of a number of simultaneous CSI calculations using each of a first type of CPU, e.g., legacy CPU, and a second type of CPU, e.g., AI-CPU.

[0160] Having described the general process flow of arrangements of the disclosure and having provided examples of hardware and software arrangements for implementing the processes and functions of the disclosure, the sections below provide details and examples of arrangements for Al-based CSI reporting.

[0161] One or more network node 16 functions described below may be performed by one or more of processing circuitry 36, processor 38, configuration unit 24, communication interface 29, etc. One or more UE 22 functions described below may be performed by one or more of processing circuitry 50, processor 52, implementation unit 26, radio interface 46, etc.

[0162] FIG. 16 is a signal diagram according to some embodiments of the present disclosure. Signaling like illustrated in FIG. 16 may be used by a UE 22 for indicating the processing unit type for generating an Al based CSI report. In the following, aspects of signaling for UE 22 indicating the processing unit type for generating an Al based CSI report will be explained.

[0163] Although the term legacy CPU is used henceforth, other alternative terminologies may be used, e.g., in 3GPP specifications. The legacy CPU may be defined, e.g., per Section 5.2.1.6 of 3GPP TS 38.214 V18.6.0.

[0164] In addition to the existing legacy CPU, at least one new CPU type is introduced. The UE 22 may indicate to the NW (e.g., via network node 16) support for multiple CPU types, reflecting an implementation of multiple CSI processing engines (Al or non-AI) thatcan be utilized in parallel. These may be numbered and for a given Al feature. The UE 22 can indicate which of the CSI processing engines the UE 22 will use. As an example, it may be so that beam prediction uses Al engine 1 and CSI prediction uses Al engine 2, or it may be so that the UE 22 uses the same engine for both the features. As another example, it may be so that CSI reporting carrying CSI prediction model inference output related information uses Al engine 1, and CSI reporting carrying CSI prediction model performance monitoring results uses Al engine 2. In view of the above, types of CPU considered may include a first type of CPU, corresponding to a legacy CPU, and a second type of CPU, corresponding to an AI-CPU. The legacy CPU may also be denoted as non-AI CPU.

[0165] In at least one embodiment, a UE 22 indicates the type of processing unit it uses for generating an Al based CSI report associated with an Al based CSI reporting feature / feature-group to the NW (e.g., network node 16).

[0166] With reference to FIG. 16, when connecting to the NW (e.g., network node 16), a network node 16 may request UE capabilities (Block S200). A UE capable of an Al based CSI reporting feature may provide its capability related information for this feature / feature-group(s) to the NW (Block S210). Based on this UE 22 capability information, the NW (e.g., network node 16) can provide proper CSI reporting configuration associated to this UE 22 feature / feature-group.

[0167] The processing unit type (e.g., AI-CPU or legacy CPU) used for generating an CSI report associated with the Al based CSI reporting feature can be indicated by the UE 22 as part of this UE 22 capability signaling. A UE 22 may indicate different processing unit types for different Al based CSI reporting features / feature-groups.

[0168] The UE 22 may further indicate the different processing unit types for specific configurations within the feature group. For example, in case of the BM use case, the UE 22 could indicate a specific processing type as a dependency on the NW configuration of the UE 22 inference report. The dependency could include:

[0169] • Number of beams in set A,

[0170] • Number of beams in set B,

[0171] • Number of future time-instances to predict for BM-Case2

[0172] • Time interval between predictions for BM-Case2

[0173] • Specific associated IDs that are configured

[0174] In at least one embodiment, the UE 22 indicates that if more than 32 beams are part of set A, the UE 22 will use AI-CPU, otherwise the legacy CPU. In another example, theUE 22 indicating a list of the associated identities (IDs) that the UE 22 has trained a model in its serving cell, and the UE 22 may require the AI-CPUs or legacy CPUs.

[0175] In at least one embodiment, relating to AI / ML CSI compression using a two-sided model, the UE 22 could indicate a specific processing type as a dependency on the NW (e.g., network node 16) configuration of the UE 22 inference report. The dependency could include the:

[0176] • Number of transmit antenna ports at the NW

[0177] • Bandwidth for which the CSI report should be configured

[0178] • Rank restrictions

[0179] • Rank / layer-related processing options, if this is signalled from the NW. E.g., rank specific, rank common, layer specific, and layer common as defined in TR 38.843

[0180] • AI / ML model input / reporting type, e.g., Raw channel or precoding matrix (as defined, e.g., in 3GPP TR 38.843)

[0181] • Applicable pre-processing, e.g., a group of eigenvector(s) or an eType II- like reporting (as defined, e.g., in 3GPP TR 38.843)

[0182] • Whether the UE 22 is configured to do UE-sided performance monitoring In some embodiments, if the UE 22 is reporting precoding matrix pre-processed using a beam-and-delay reduction similar to legacy PMI reporting (denoted “angular-delay domain, ” and “eType Il-like reporting” , and “Complex-valued full W2 matrix after eType-II processing” in, e.g., 3GPP TR 38.843 V18.0.0 and associated tables), before applying the AI / ML model, then the UE 22 may use legacy CPU, otherwise it may use AI-CPU. In some embodiments, the UE 22 uses ALCPU if it is configured to perform UE-side performance monitoring, since the UE 22 may then need to run additional AI / ML models other than the CSI generation part / encoder, e.g., a CSI reconstruction model at the UE.

[0183] In some embodiments, the indication of processing unit type for the Al-based CSI reporting feature is carried in the part of UE 22 capability report that is related to the Al based CSI reporting feature / feature-group.

[0184] Under certain conditions, a new Al model may be transferred / delivered / loaded to the UE for the Al based CSI reporting feature / feature-group, which uses a different type of processing unit as compared to the one used for the pervious CSI reports generated for this feature / feature-group. Example of such conditions include when the UE 22 connects to a new cell, when the UE 22 moves to a new area / scenario, when the UE 22 state changes(e.g., UE 22 at a low power / energy level, or at high speed), and / or when the NW (e.g., network node 16) antenna configuration changes. If the UE 22 has changed the type of processing unit used for generating a CSI report for an Al-based CSI reporting feature / feature-group, then, the UE 22 may indicate such change to the NW (e.g., network node 16) so that the UE 22 and the NW have the common understanding on the CPU usage, CPU counting, processing timeline for a CSI reporting.

[0185] With further reference to FIG. 16, network node 16 may determine one or more AI / ML configurations to activate based on UE processing unit pools (Block S220).

[0186] Network node 16 may configure UE 22 with one or more AI / ML configuration(s) (Block S230a). The UE 22 and / or network node 16 may increase the count for each processing unit type based on pre-configured rules (Block S240).

[0187] The indication of processing unit type for the Al-based CSI reporting feature may be carried in signaling that indicates / updates the applicable model(s) and / or appliable functionality(ies) for this feature / feature-group to the NW (e.g., network node 16) Block S230b. Examples of the signaling include the RRC signaling carrying the UEAssistancelnformation IE, the RRC signaling carrying the RRCReconfigurationComplete message, and a new MAC signaling that is introduced for providing CSI processing unit type information.

[0188] The UE 22 can update from which pool of CPU resources that a certain inference configuration belongs to after it has been configured by the NW (e.g., network node 16). This could enable the UE 22 to first check in which hardware the feature can fit into, prior to reporting from which pool of CPU resources that is occupied. With this solution, the UE 22 could run more inference operations since it can dynamically allocate the AI-CPU or non- AI-CPU resources based on NW configuration.

[0189] In some embodiments, the indication of the processing unit type for the Al-based CSI reporting feature is indicated as a component of a feature group. In the same feature, information on one or more parameters related to the number of computational resources occupied are provided. For instance, consider the following example, where the following three components are part of a feature group comprising one or more of

[0190] Bl. type of CSI processing unit with candidate values AI-CPU or legacy CPU B2. A parameter Y 1 that is used for identifying the number of occupied processing units when aperiodic CSLRS resources are used as channel measurement resources. For instance, the number of occupied processing units may be defined as Y wherein K is the number of aperiodic resources configured as channel measurement resources.B3. A parameter Y2 that is used for identifying the number of occupied processing units when periodic or semi-persistent CSI-RS resources are used as channel measurement resources. For instance, the number of occupied processing units may be defined as max (K2IV4, 4) wherein 1V4is the number of predicted time occasions.

[0191] In the above embodiment, the parameters provided by components B2 and B3 are used to compute the occupied AI-CPUs when component Bl indicates the processing unit type as AI-CPU. If component B 1 indicates the processing unit type as legacy CPU, the parameters provided by components B2 and B3 are used to compute the occupied legacy CPUs.

[0192] In the following, CSI processing criteria for an Al based CSI report will be described.

[0193] In at least one embodiment, the number of occupied processing units for an AI-based CSI report is defined based on the indication of processing unit type (e.g., AI-CPU or legacy CPU) for the Al-based CSI reporting feature.

[0194] In at least one embodiment, the number of occupied legacy CPU, denoted by OCPU, for an Al-based CSI report associated to an Al based CSI reporting feature is

[0195] • If the processing unit type indication indicates that AI-CPU is used for generating this report, OCPU= 0.

[0196] • Else, the value of OCPUis defined based on the associated report configuration parameters, e.g., reportQuantity, CSI-RS resource type (periodic / semi-persistent / aperiodic CSI-RS), number of CSI-RS resources, and / or number of prediction time occasions etc.

[0197] In at least one embodiment, the number of occupied legacy CPU, denoted by OCPU, for an Al-based CSI report generated by using the type of legacy CPU is defined based on a legacy non-AI based CSI reporting feature.

[0198] For example, denote the number of occupied CPU for a given / reference legacy non-AI based CSI report as OCPU ref, then the number of occupied legacy CPU for the AI-based CSI report, OCPUis a function of OCPU ref which can be written as OCPU= f(OCPUiref). In one example, O

[0199]

[0200] CPU= [a x OCPU ref\, where a is a scalar, if a = 0.5, this means that for a given CSI report, calculating it with Al occupies 50% less CPUs compared to calculating it with non-AI approach. In another example, OCPU=

[0201] \a x OCPU ref + ft , where / 3, for example, can be used to accounting for the resources needed for loading a model. The function (. ), the values

[0202]

[0203] of a, when applicable, is(are) can be specified in 3GPP specifications. The values of a, ft, when applicable can be reported by the UE 22 as part of the UE capability.

[0204] • As an example, for a certain report configuration, the value of 0CPUfor a CSI report carrying the information related to inference output of Al-based CSI prediction using UE-side model is defined to reuse or based on the value specified for the case when ‘reportQuantity’ is set to 'cri-RI-PMI-CQI' and with codebookType set to 'typell-Doppler-rl 8', which is used as the reference for CPU occupancy.

[0205] • As another example, for a certain report configuration, the value of 0CPUfor a CSI report carrying the information related to inference output of Al-based CSI compression feature is defined to reuse or based on the value specified for the case when the ‘reportQuantity’ is set to 'cri-RI-PMI-CQI' the codbookType is set to ‘typell-rl6’, which is used as the reference for CPU occupancy.

[0206] • As yet another example, the value of 0CPUfor a CSI report carrying the information related to inference output of Al-based beam prediction using UE-side model is defined to reuse or based on the value specified for the case when the "reportQuantity set to 'cri-RSRP', 'ssb-Index-RSRP', which is used as the reference for CPU occupancy.

[0207] The information related to inference output of an AI / ML based feature / feature-group may include at least one of the following:

[0208] • The inference output with / without a post-processing (e.g., the predicted CSI generated using the inference output of the CSI prediction model at the UE 22)

[0209] • The quality / accuracy of the inference output (e.g., the quality / accuracy of the predicted CSI generated by the CSI prediction model at the UE 22)

[0210] • Other performance monitoring related results for the AI / ML based feature / feature-group (e.g., whether the CSI prediction model at the UE 22 is functioning properly, the statistics of the performance metric)

[0211] In a dependent embodiment, the number of occupied ALCPU, denoted by OAI-CPU, for an Al-based CSI report associated to an Al based CSI reporting feature is:

[0212] • If the processing unit type indication indicates that legacy CPU is used for generating this report, OAI-CPU= 0.

[0213] • Else, the value of OAI-CPUis defined based on the report configuration parameters, e.g., reportQuantity, CSLRS resource type (periodic / semi-persistent / aperiodic CSLRS), number of CSLRS resources, and / or number of prediction time occasions, etc.

[0214] In at least one embodiment, with the same CSI report configuration, the value of OAI-CPU forafirst Al-based CSI report generated by using the type of ALCPU is differentfrom the value of OCPUfor a second Al-based CSI report generated by using the type of legacy CPU, where the first and the second Al-based CSI report are associated to the same Al-based CSI reporting feature / feature-group.

[0215] In the following, examples of rules for deciding whether to update / drop a requested Al-based CSI report will be described.

[0216] In some embodiments, the UE 22 indicates the following to the NW (e.g., network node 16) as part of UE 22 capability:

[0217] • The number of simultaneous CSI calculations using legacy CPU resources, denoted by NCPU, supported by the UE 22 to the NW.

[0218] • The number of simultaneous CSI calculations using AI-CPU resources, denoted by NAI-CPU, supported by the UE 22 to the NW.

[0219] If a UE 22 supports NCPUsimultaneous CSI calculations it is said to have NCPUlegacy CSI processing units for processing CSI reports (including both legacy non-AI based CSI reports and Al-based CSI reports that are generated using legacy CPUs).

[0220] If a UE 22 supports NAI-CPUsimultaneous CSI calculations it is said to have NAI-CPU Al CSI processing units for processing Al-based CSI reports using Al CPUs. The following rule is defined for the UE to decide whether to update / drop a requested AI-based CSI report:

[0221] If L CPUs are occupied for calculation of CSI reports (including both non-AI and Al based CSI reports using legacy CPUs) in a given OFDM symbol, the UE has NCPU— L unoccupied CPUs. If N CSI reports start occupying their respective CPUs on the same OFDM symbol on which NCPU— L CPUs are unoccupied, where each CSI report n = 0, ... , N — 1 corresponds to 0^, the UE is not required to update the N — M requested CSI reports with lowest priority, where 0 < M < N is the largest value such that L

[0222]

[0223] Y=o OC'PUNCPU ~ h holds.

[0224] If L AI-CPUs are occupied for calculation of Al based CSI reports in a given OFDM symbol, the UE has NCPU— L unoccupied CPUs. If N Al based CSI reports start occupying their respective AI-CPUs on the same OFDM symbol on which NAI-CPU— L AI-CPUs are unoccupied, where each Al based CSI report n = 0, ... , N — 1 corresponds to

[0225]

[0226] OAI-CPU, UE is not required to update the N — M requested Al-based CSI reports with lowest priority, where 0 < M < N is the largest value such that Y

[0227]

[0228] n=o O^-CPU <

[0229] AI-CPU ~ h holds.If the UE 22 has indicated capability to the NW (e.g., network node 16) that it can support a certain feature (e.g. CSI prediction calculations) using both Al and non- Al based processing, the NW may indicate to the UE 22 whether to use Al or non- Al for the feature, using higher layer signaling. The NW may alternatively indicate to the UE 22 using higher layer signalling that it should prioritize the Al based computation (which may have better accuracy in prediction), but the UE can, if the Al CPU is occupied, fallback to non-AI based computation of the feature. The CPU occupation time (i.e. the time from trigger to the CSI report is ready to feed back) for the Al and non-AI based computation may be different, and if the Al based computation has a shorter time, and by indication that the non-AI based calculation is acceptable as a second priority, the UE 22 can still compute the feature report without the Al processing engine, although it will be reported with some larger latency. This may still be acceptable and useful for the NW. Note that this is an example, and the opposite is also possible (that the Al based feature report has a longer latency than the non-AI based). If both Al and non-AI based CPU are occupied, the report is dropped.

[0230] As will be appreciated by one of skill in the art, the concepts described herein may be embodied as a method, data processing system, computer program product and / or computer storage media storing an executable computer program. Accordingly, the concepts described herein may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects all generally referred to herein as a “circuit” or “module.” Any process, step, action and / or functionality described herein may be performed by, and / or associated to, a corresponding module, which may be implemented in software and / or firmware and / or hardware. Furthermore, the disclosure may take the form of a computer program product on a tangible computer usable storage medium having computer program code embodied in the medium that can be executed by a computer. Any suitable tangible computer readable medium may be utilized including hard disks, CD-ROMs, electronic storage devices, optical storage devices, or magnetic storage devices.

[0231] Some embodiments are described herein with reference to flowchart illustrations and / or block diagrams of methods, systems and computer program products. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer (to thereby create a specialpurpose computer), special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0232] These computer program instructions may also be stored in a computer readable memory or storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instruction means which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0233] The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0234] It is to be understood that the functions / acts noted in the blocks may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality / acts involved. Although some of the diagrams include arrows on communication paths to show a primary direction of communication, it is to be understood that communication may occur in the opposite direction to the depicted arrows.

[0235] Computer program code for carrying out operations of the concepts described herein may be written in an object oriented programming language such as Python, Java® or C++. However, the computer program code for carrying out operations of the disclosure may also be written in conventional procedural programming languages, such as the "C" programming language. The program 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. In the latter scenario, the remote computer may be connected to the user's computer through a local area network (LAN) or a wide area network (WAN), or the connection may bemade to an external computer (for example, through the Internet using an Internet Service Provider).

[0236] Many different embodiments have been disclosed herein, in connection with the above description and the drawings. It will be understood that it would be unduly repetitious and obfuscating to literally describe and illustrate every combination and subcombination of these embodiments. Accordingly, all embodiments can be combined in any way and / or combination, and the present specification, including the drawings, shall be construed to constitute a complete written description of all combinations and subcombinations of the embodiments described herein, and of the manner and process of making and using them, and shall support claims to any such combination or subcombination.

[0237] It will be appreciated by persons skilled in the art that the embodiments described herein are not limited to what has been particularly shown and described herein above. In addition, unless mention was made above to the contrary, it should be noted that all of the accompanying drawings are not to scale. A variety of modifications and variations are possible in light of the above teachings.

[0238] In view of the above, example embodiments provided by the present disclosure include:

[0239] Embodiment Al . A method implemented in a user equipment (UE) that is configured to communicate with a network node, the method comprising:

[0240] generating a UE capability report indicating at least one UE capability for generating an artificial intelligence-, Al, based channel state information, CSI, report; and transmitting the UE capability report to the network node.

[0241] Embodiment A2. The method of Embodiment Al, wherein the UE capability report includes an indication of a processing unit type for generating the Al-based CSI report.

[0242] Embodiment A3. The method of Embodiment Al, wherein the UE capability report includes an indication of a number of simultaneous CSI calculations using each of a first type of CSI processing unit, CPU, and a second type of CPU.

[0243] Embodiment Bl. A user equipment (UE) configured to communicate with a network node, the UE configured to, and / or comprising a radio interface and / or processing circuitry configured to:generate a UE capability report indicating at least one UE capability for generating an artificial intelligence-, Al, based channel state information, CSI, report; and transmit the UE capability report to the network node.

[0244] Embodiment B2. The UE of Embodiment Bl, wherein the UE capability report includes an indication of a processing unit type for generating the Al-based CSI report.

[0245] Embodiment B3. The UE of Embodiment B 1 , wherein the UE capability report includes an indication of a number of simultaneous CSI calculations using each of a first type of CSI processing unit, CPU, and a second type of CPU.

[0246] Embodiment Cl . A method implemented in a network node that is configured to communicate with a user equipment, the method comprising:

[0247] receiving a UE capability report indicating at least one UE capability for generating an artificial intelligence-, Al, based channel state information, CSI, report; and configuring the UE based on the UE capability report.

[0248] Embodiment C2. The method of Embodiment Cl, wherein the UE capability report includes an indication of a processing unit type for generating the Al-based CSI report.

[0249] Embodiment C3. The method of Embodiment Cl, wherein the UE capability report includes an indication of a number of simultaneous CSI calculations using each of a first type of CSI processing unit, CPU, and a second type of CPU.

[0250] Embodiment DI . A network node configured to communicate with a user equipment (UE), the network node configured to, and / or comprising a radio interface and / or comprising processing circuitry configured to:

[0251] receive a UE capability report indicating at least one UE capability for generating an artificial intelligence-, Al, based channel state information, CSI, report; and configure the UE based on the UE capability report.Embodiment D2. The network node of Embodiment DI, wherein the UE capability report includes an indication of a processing unit type for generating the AI-based CSI report.

[0252] Embodiment D3. The network node of Embodiment D 1 , wherein the UE capability report includes an indication of a number of simultaneous CSI calculations using each of a first type of CSI processing unit, CPU, and a second type of CPU.

Claims

CLAIMS1. A method implemented in a user equipment, UE, (22) that is configured to communicate with a network node (16), the method comprising:generating a UE capability report indicating at least one UE capability for generating an artificial intelligence-, Al, based channel state information, CSI, report; and transmitting the UE capability report to the network node (16).

2. The method of claim 1, wherein the UE capability report includes an indication of a processing unit type for generating the Al-based CSI report.

3. The method of claim 2, wherein the indication of the processing unit type is indicated as a component of a feature group.

4. The method of claim 2 or 3, wherein a number of occupied processing units for an Al-based CSI report is defined based on the indication of processing unit type.

5. The method of any of claims 2 to 4, wherein a number of occupied legacy processing units for the Al-based CSI report is zero if the indication of the processing unit type indicates that an Al processing unit is used for generating the Al-based CSI report.

6. The method of claim 5, wherein the number of occupied legacy processing units for the Al-based CSI report is defined by associated report configuration parameters if the indication of the processing unit type does not indicate that an Al processing unit is used for generating the Al-based CSI report.

7. The method of claim 6, wherein the associated report configuration parameters include one or more of report quantity, CSI reference signal resource type, number of CSI reference signal resources, number of prediction time resources.

8. The method of any of claims 2 to 7, wherein a number of occupied Al processing units for the Al-based CSI report is zero if the indication of the processing unit type indicates that a legacy processing unit is used for generating the Al-based CSI report.

9. The method of claim 8, wherein the number of occupied Al processing units for the Al-based CSI report is defined by associated report configuration parameters if the indication of the processing unit type does not indicate that a legacy processing unit is used for generating the Al-based CSI report.

10. The method of claim 9, wherein the associated report configuration parameters include one or more of: report quantity, CSI reference signal resource type, number of CSI reference signal resources, number of prediction time resources.

11. The method of any of claims 1 to 10, wherein the UE capability report indicates a number of simultaneous CSI calculations using legacy processing unit resources supported by the UE (22).

12. The method of any of claims 1 to 11, wherein the UE capability report indicates a number of simultaneous CSI calculations using Al processing unit resources supported by the UE (22).

13. The method of any of claims 1 to 12, wherein the UE capability report includes an indication of a number of simultaneous CSI calculations using each of a first type of CSI processing unit, CPU, and a second type of CPU.

14. A user equipment, UE, (22) configured to communicate with a network node (16), the UE (22) being configured to:generate a UE capability report indicating at least one UE capability for generating an artificial intelligence-, Al, based channel state information, CSI, report; and transmit the UE capability report to the network node (16).

15. The UE (22) of claim 14, wherein the UE (22) is configured to perform a method according to any of claims 2 to 13.

16. The UE (22) of claim 14 or 15, comprising a radio interface (46) and / or processing circuitry (50) configured to perform a method according to any of claims 1 to17. A method implemented in a network node (16) that is configured to communicate with a user equipment, UE, (22), the method comprising:receiving a UE capability report indicating at least one UE capability for generating an artificial intelligence-, Al, based channel state information, CSI, report; and configuring the UE (22) based on the UE capability report.

18. The method of claim 17, wherein the UE capability report includes an indication of a processing unit type for generating the Al-based CSI report.

19. The method of claim 18, wherein the indication of the processing unit type is indicated as a component of a feature group.

20. The method of claim 18 or 19, wherein a number of occupied processing units for an Al-based CSI report is defined based on the indication of processing unit type.

21. The method of any of claims 18 to 20, wherein a number of occupied legacy processing units for the Al-based CSI report is zero if the indication of the processing unit type indicates that an Al processing unit is used for generating the AI-based CSI report.

22. The method of claim 21, wherein the number of occupied legacy processing units for the Al-based CSI report is defined by associated report configuration parameters if the indication of the processing unit type does not indicate that an Al processing unit is used for generating the Al-based CSI report.

23. The method of claim 22, wherein the associated report configuration parameters include one or more of report quantity, CSI reference signal resource type, number of CSI reference signal resources, number of prediction time resources.

24. The method of any of claims 18 to 23, wherein a number of occupied Al processing units for the Al-based CSI report is zero if the indication of the processing unit type indicates that a legacy processing unit is used for generating the Al-based CSI report.

25. The method of claim 24, wherein the number of occupied Al processing units for the Al-based CSI report is defined by associated report configuration parameters if the indication of the processing unit type does not indicate that a legacy processing unit is used for generating the Al-based CSI report.

26. The method of claim 25, wherein the associated report configuration parameters include one or more of: report quantity, CSI reference signal resource type, number of CSI reference signal resources, number of prediction time resources.

27. The method of any of claims 17 to 26, wherein the UE capability report indicates a number of simultaneous CSI calculations using legacy processing unit resources supported by the UE (22).

28. The method of any of claims 17 to 27, wherein the UE capability report indicates a number of simultaneous CSI calculations using Al processing unit resources supported by the UE (22).

29. The method of any of claims 17 to 28, wherein the UE capability report includes an indication of a number of simultaneous CSI calculations using each of a first type of CSI processing unit, CPU, and a second type of CPU.

30. A network node (16) configured to communicate with a user equipment, UE, (22), the network node (16) being configured:receive a UE capability report indicating at least one UE capability for generating an artificial intelligence-, Al, based channel state information, CSI, report; and configure the UE (22) based on the UE capability report.

31. The network node (16) of claim 30, wherein the network node (16) is configured to perform a method according to any of claims 18 to 29.

32. The network node (16) of claim 30 or 31, comprising a radio interface (30) and / or processing circuitry (36) configured to perform a method according to any of claims 17 to 29.

Images