WO2025030535A1

WO2025030535A1 - Devices and methods for communication

Info

Publication number: WO2025030535A1
Application number: PCT/CN2023/112374
Authority: WO
Inventors: Peng Guan; Zhen He; Gang Wang
Original assignee: NEC Corp
Current assignee: NEC Corp
Priority date: 2023-08-10
Filing date: 2023-08-10
Publication date: 2025-02-13
Anticipated expiration: 2026-02-10

Abstract

Embodiments of the present disclosure provide a solution for configuring and transmitting the channel state information (CSI) feedback. In a solution, the terminal device receives a CSI report configuration associated with a plurality of sub-configurations from a network device, where the plurality of sub-configurations comprise at least one of the following: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with CSI for the second usage. Then, the terminal device transmits to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.

Description

DEVICES AND METHODS FOR COMMUNICATION

FIELDS

Example embodiments of the present disclosure generally relate to the field of communication techniques and in particular, to devices and methods for configuring and transmitting the channel state information (CSI) feedback.

BACKGROUND

Generally speaking, during the communication between the terminal device and the network device, the terminal device needs to report CSI feedback to the network device, such that the network device may understand the network condition and make a more proper subsequent schedule. Further, as communication networks and services increase in size, complexity, and number of users, operations in the communication networks may become increasingly more complicated. In order to improve the communication performance, artificial intelligence (AI) /machine learning (ML) technology is proposed to be used in the wireless communication network.

Due to the diversity of the model (s) , the complexity of the CSI configuration is increased accordingly. Thus, how to well support AI/ML-based CSI reporting without increasing the number of CSI report configurations is desirable to be further discussed.

SUMMARY

In general, embodiments of the present disclosure provide for a solution for configuring and transmitting the CSI feedback.

In a first aspect, there is provided a terminal device comprising: a processor configured to cause the terminal device to: receive, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations, wherein the plurality of sub-configurations comprise at least one of the following: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with CSI for the second usage; and transmit to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.

In a second aspect, there is provided a terminal device comprising: a processor configured to cause the terminal device to: receive, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations; and transmit to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, wherein at least one of the following is associated with an identity of a sub-configuration: a CSI processing time, the number of CSI processing units (CPUs) , or a CSI report priority.

In a third aspect, there is provided a network device comprising: a processor configured to cause the network device to: transmit, to the terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations, wherein the plurality of sub-configurations comprise at least one of the following: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with the second usage; and receive from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.

In a fourth aspect, there is provided a network device comprising: a processor configured to cause the network device to: transmit, to a terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations; receive from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, wherein at least one of the following is associated with an identity of a sub-configuration: a CSI processing time, the number of CSI processing units (CPUs) , or a CSI report priority.

In a fifth aspect, there is provided a communication method performed by a terminal device. The method comprises: receiving, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations, wherein the plurality of sub-configurations comprise at least one of the following: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with CSI for the second usage; and transmitting to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.

In a sixth aspect, there is provided a communication method performed by a terminal device. The method comprises: receiving, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations; transmitting to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, wherein at least one of the following is associated with an identity of a sub-configuration: a CSI processing time, the number of CSI processing units (CPUs) , or a CSI report priority.

In a seventh aspect, there is provided a communication method performed by a network device. The method comprises: transmitting, to the terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations, wherein the plurality of sub-configurations comprise at least one of the following: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with the second usage; and receiving from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.

In an eighth aspect, there is provided a communication method performed by a network device. The method comprises: transmitting, to a terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations; receiving from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, wherein at least one of the following is associated with an identity of a sub-configuration: a CSI processing time, the number of CSI processing units (CPUs) , or a CSI report priority.

In a ninth aspect, there is provided a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to carry out the method according to the fifth, sixth, seventh, or eighth aspect.

Other features of the present disclosure will become easily comprehensible through the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

Through the more detailed description of some example embodiments of the present disclosure in the accompanying drawings, the above and other objects, features and advantages of the present disclosure will become more apparent, wherein:

FIG. 1 illustrates example communication environment in which example embodiments of the present disclosure can be implemented;

FIG. 2 illustrates a signaling flow of communication in accordance with some embodiments of the present disclosure;

FIG. 3A to FIG. 3C illustrate examples of sub-configuration mapping;

FIG. 4 illustrates a flowchart of a method implemented at a terminal device according to some example embodiments of the present disclosure;

FIG. 5 illustrates a flowchart of a method implemented at a terminal device according to some example embodiments of the present disclosure;

FIG. 6 illustrates a flowchart of a method implemented at a network device according to some example embodiments of the present disclosure;

FIG. 7 illustrates a flowchart of a method implemented at a network device according to some example embodiments of the present disclosure; and

FIG. 8 illustrates a simplified block diagram of an apparatus that is suitable for implementing example embodiments of the present disclosure.

Throughout the drawings, the same or similar reference numerals represent the same or similar element.

DETAILED DESCRIPTION

Principle of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein can be implemented in various manners other than the ones described below.

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

As used herein, the term ‘terminal device’ refers to any device having wireless or wired communication capabilities. Examples of the terminal device include, but not limited to, user equipment (UE) , personal computers, desktops, mobile phones, cellular phones, smart phones, personal digital assistants (PDAs) , portable computers, tablets, wearable devices, internet of things (IoT) devices, Ultra-reliable and Low Latency Communications (URLLC) devices, Internet of Everything (IoE) devices, machine type communication (MTC) devices, devices on vehicle for V2X communication where X means pedestrian, vehicle, or infrastructure/network, devices for Integrated Access and Backhaul (IAB) , Space borne vehicles or Air borne vehicles in Non-terrestrial networks (NTN) including Satellites and High Altitude Platforms (HAPs) encompassing Unmanned Aircraft Systems (UAS) , eXtended Reality (XR) devices including different types of realities such as Augmented Reality (AR) , Mixed Reality (MR) and Virtual Reality (VR) , the unmanned aerial vehicle (UAV) commonly known as a drone which is an aircraft without any human pilot, devices on high speed train (HST) , or image capture devices such as digital cameras, sensors, gaming devices, music storage and playback appliances, or Internet appliances enabling wireless or wired Internet access and browsing and the like. The ‘terminal device’ can further has ‘multicast/broadcast’ feature, to support public safety and mission critical, V2X applications, transparent IPv4/IPv6 multicast delivery, IPTV, smart TV, radio services, software delivery over wireless, group communications and IoT applications. It may also incorporate one or multiple Subscriber Identity Module (SIM) as known as Multi-SIM. The term “terminal device” can be used interchangeably with a UE, a mobile station, a subscriber station, a mobile terminal, a user terminal or a wireless device.

The term “network device” refers to a device which is capable of providing or hosting a cell or coverage where terminal devices can communicate. Examples of a network device include, but not limited to, a Node B (NodeB or NB) , an evolved NodeB (eNodeB or eNB) , a next generation NodeB (gNB) , a transmission reception point (TRP) , a remote radio unit (RRU) , a radio head (RH) , a remote radio head (RRH) , an IAB node, a low power node such as a femto node, a pico node, a reconfigurable intelligent surface (RIS) , and the like.

The terminal device or the network device may have Artificial intelligence (AI) or Machine learning capability. It generally includes a model which has been trained from numerous collected data for a specific function, and can be used to predict some information.

The terminal or the network device may work on several frequency ranges, e.g., FR1 (e.g., 450 MHz to 6000 MHz) , FR2 (e.g., 24.25GHz to 52.6GHz) , frequency band larger than 100 GHz as well as Tera Hertz (THz) . It can further work on licensed/unlicensed/shared spectrum. The terminal device may have more than one connection with the network devices under Multi-Radio Dual Connectivity (MR-DC) application scenario. The terminal device or the network device can work on full duplex, flexible duplex and cross division duplex modes.

The embodiments of the present disclosure may be performed in test equipment, e.g., signal generator, signal analyzer, spectrum analyzer, network analyzer, test terminal device, test network device, channel emulator. In some embodiments, the terminal device may be connected with a first network device and a second network device. One of the first network device and the second network device may be a master node and the other one may be a secondary node. The first network device and the second network device may use different radio access technologies (RATs) . In some embodiments, the first network device may be a first RAT device and the second network device may be a second RAT device. In some embodiments, the first RAT device is eNB and the second RAT device is gNB. Information related with different RATs may be transmitted to the terminal device from at least one of the first network device or the second network device. In some embodiments, first information may be transmitted to the terminal device from the first network device and second information may be transmitted to the terminal device from the second network device directly or via the first network device. In some embodiments, information related with configuration for the terminal device configured by the second network device may be transmitted from the second network device via the first network device. Information related with reconfiguration for the terminal device configured by the second network device may be transmitted to the terminal device from the second network device directly or via the first network device.

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. The term ‘includes’ and its variants are to be read as open terms that mean ‘includes, but is not limited to. ’ The term ‘based on’ is to be read as ‘at least in part based on. ’ The term ‘one embodiment’ and ‘an embodiment’ are to be read as ‘at least one embodiment. ’ The term ‘another embodiment’ is to be read as ‘at least one other embodiment. ’ The terms ‘first, ’ ‘second, ’ and the like may refer to different or same objects. Other definitions, explicit and implicit, may be included below.

In some examples, values, procedures, or apparatus are referred to as ‘best, ’ ‘lowest, ’ ‘highest, ’ ‘minimum, ’ ‘maximum, ’ or the like. It will be appreciated that such descriptions are intended to indicate that a selection among many used functional alternatives can be made, and such selections need not be better, smaller, higher, or otherwise preferable to other selections.

As used herein, the term “resource, ” “transmission resource, ” “uplink resource, ” or “downlink resource” may refer to any resource for performing a communication, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

Sub-configuration of one CSI report is introduced to support multiple CSI (caused by spatial/power domain adaption) without further increasing the maximum number of CSI report configurations.

In order to improve the communication performance, AI/ML technology is proposed to be used in the wireless communication network. In this event, AI/ML-based CSI report enhancement and beam management (BM) enhancement may also utilize multiple CSI (for model training, model inference, model monitoring, and so on) .

In some embodiments, for each CSI report, the resources for measurement are configured in hierarchical structure, including ResourceConfig, resource set and resource, wherein ReportConfig is linked to one or multiple ResouceConfig, ResourceConfig is linked to one or multiple resource sets via ResourceSetList, ResourceSet contains information of one or multiple Resources via ResourceList and Resource is the minimum unit for physical layer configuration.

In some embodiments, CSI may comprise at least one of Channel Quality Indicator (CQI) , precoding matrix indicator (PMI) , CSI-RS resource indicator (CRI) , SS/PBCH Block Resource indicator (SSBRI) , layer indicator (LI) , rank indicator (RI) , layer 1 (L1) -reference signal receiving power (RSRP) , L1-signal to noise plus interference power ratio (SINR) , or CapabilityIndex (which refers to an index of UE’s capability) .

For CQI, PMI, CRI, SSBRI, LI, RI, L1-RSRP, L1-SINR, CapabilityIndex, a UE may be configured by higher layers with N≥1 CSI-ReportConfig Reporting Settings, M≥1 CSI-ResourceConfig Resource Settings, and one or two list (s) of trigger states (given by the higher layer parameters CSI-AperiodicTriggerStateList and CSI-SemiPersistentOnPUSCH-TriggerStateList) . Each trigger state in CSI-AperiodicTriggerStateList contains a list of associated CSI-ReportConfigs indicating the Resource Set IDs for channel and optionally for interference. Each trigger state in CSI-SemiPersistentOnPUSCH-TriggerStateList contains one associated CSI-ReportConfig.

In some embodiments, support configurability of (non-zero power) NZP CSI-RS resource (s) for channel measurement within one resource setting corresponding to more than one spatial adaptation patterns with at least one of the following:

a resource set with multiple resources is configured within a resource setting, where each resource is associated with only one spatial adaptation pattern; Further, one or more CSI-RS resources from a CSI-RS resource set for channel measurement can be associated with the same sub-configuration provided in a CSI report configuration, and Resources in the resource set for channel measurement have the same number of antenna ports;

for a resource configured in a resource set within a resource setting, the resource can be associated with more than one spatial adaptation patterns. Further, one or more resources may be configured in the resource set for channel measurement. Further, all CSI-RS resource (s) (which can be one or more) in the CSI-RS resource set for channel measurement are associated with each sub-configuration provided in a CSI report configuration, i.e., each CSI-RS resource is associated with all the sub-configurations or resources in the resource set for channel measurement have the same number of antenna ports.

In some embodiments, for spatial domain adaptation, in case of multiple CSI (s) where each CSI corresponds to a spatial adaptation pattern, gNB may indicate to UE which CSI (s) the UE shall report, the UE may select which CSI (s) are reported, and multiple CSI (s) may be reported in a joint CSI report.

In some embodiments, for a CSI report configuration with L sub-configuration (s) , support a framework that enables a UE to report CSI (s) in one reporting instance where the CSI(s) are associated with N sub-configuration (s) from L (where 1≤N≤L) and each CSI corresponds to one sub-configuration. For discussion purpose, N=1 refers to single-CSI while N>1 refers to multi-CSI. For semi-persistent/aperiodic CSI reporting, support gNB trigger/indicate/activate report of N≤L CSIs where N>=1. In some embodiments, the maximum value of N and L may be subject to UE capability.

In some embodiments, for periodic CSI reporting, at least the case of N=L is supported, where N>=1.

In some embodiments, for CSI feedback with CSI overhead/report payload reduction, further study whether/how to report a common value and/or a differential and/or joint coded value across same CSI quantity of different sub-configurations/adaptation patterns, at least for the following: CSI-RS resource indicator (CRI) , rank indicator (RI) , precoding matrix indicator (PMI) , channel quality indicator (CQI) , layer 1 (L1) -reference signal receiving power (RSRP) , or other (new) report quantity.

In some embodiments, for spatial domain network energy saving (NES) , when UE reports CSIs corresponding to one or more sub-configurations provided in a CSI report configuration, it is supported to report CSI for each indicated sub-configuration, according to report quantity configuration.

As for NES and AI/ML-based CSI report scenario, supporting to include multiple sub-configurations in one CSI report configuration may bring a plurality of advantages, such as, avoiding increasing the number of CSI report configurations, enable both normal mode (non-NES node /non-AI mode) and enhanced mode (NES node/AI-based mode) .

In addition, multi-CSI report and sub-configuration of one CSI report configuration, provides some possibilities to configure report and resources in a more dynamic way that one CSI resource setting (or, represented as CSI ResourceConfig) /resource set/resource may be associated with one or more time/spatial domain pattern.

It has been agreed that CSI compressing (spatial-frequency domain CSI compression using two-sided AI model) and time domain CSI prediction are representative sub use cases for AI/ML CSI report enhancement. Further, it is noted that all pre-processing/post-processing, quantization/de-quantization are within the scope of the use case of spatial-frequency domain CSI compression.

Further, in CSI prediction using UE-side model use case, data collection procedure mainly includes RS configuration, measurement and report configuration, which reuse as much as possible what is defined for UE side use cases.

For AI/ML-based beam management, it has been agreed to support below BM-Case1 and BM-Case2:

BM-Case1: Spatial-domain downlink beam prediction for Set A of beams based on measurement results of Set B of beams.

BM-Case2: Temporal downlink beam prediction for Set A of beams based on the historic measurement results of Set B of beams.

Further, for BM-Case1 and BM-Case2, beams in above Set A and Set B may be in the same frequency range (FR) .

In case of BM-Case2, the following alternatives for the predicted beams may be supported: downlink transmitting (TX) beam prediction, downlink receiving (RX) beam prediction, beam pair prediction (a beam pair consists of a downlink TX beam and a corresponding downlink RX beam) .

Regarding the sub-use cases of BM-Case1 and BM-Case2, the following alternatives for AI/ML output may be supported: TX and/or RX Beam identity (ies) ID (s) and/or the predicted layer 1 (L1) -reference signal receiving power (RSRP) of the N predicted downlink TX and/or RX beams, e.g., N predicted beams can be the top-N predicted beams; TX and/or RX beam ID (s) of the N predicted downlink TX and/or TX beams and other information (e.g., probability for the beam to be the best beam, the associated confidence, beam application time/dwelling time, predicted beam failure) , where N predicted beams may be the top-N predicted beams; TX and/or RX Beam angle (s) and/or the predicted L1-RSRP of the N predicted DL TX and/or RX beams, where N predicted beams can be the top-N predicted beams.

As discussed above, the AI/ML for CSI/BM is used to improve the CSI/BM performance, in particular, for those agreed sub cases, some advantages of using AI/ML might be: reduce report overhead; reduce RS overhead; reduce measurement complexity; reduce signaling overhead and latency.

In general, AI/ML based operation needs to be designed in a way that consuming less than non-AI traditional CSI/BM, for example, without further increase the maximum number of CSI report configurations. However, it is difficult to achieve. One reason is that there are different AI/ML model management stages, for example, Model training, Model inference, Model monitoring, and the required data collections for the different AI/ML model management stages are different, which means different CSI report may be needed for different stages, even for one AI/ML model. Another reason is that in some cases, multiple CSI are needed for different AI/ML models for one functionality. A further reason is that in some cases, both AI/ML and non-AI based method are needed, for example, to compare the performance, to validate the model, to monitor the model performance. Therefore, to support AI/ML using legacy CSI framework, it is evitable to have more CSI report configurations.

According to the example embodiments of the present discourse, a solution for configuring and reporting multiple CSI for Artificial Intelligence (AI) /machine learning (ML) based (AI/ML-based) CSI report enhancement and beam management enhancement has been proposed. In particular, multiple CSI may be obtained according to multiple sub-configurations of one CSI report.

Specifically, in the solution, the terminal device receives a CSI report configuration associated with a plurality of sub-configurations from a network device, where the plurality of sub-configurations comprise at least one of the following: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with CSI for the second usage. Then, the terminal device transmits to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.

In this way, the concept of sub-configuration is applied to the procedure of AI/ML-based CSI reporting, and thus the diversity of AL/ML model is satisfied without increasing the number of CSI report configurations.

For better descriptions, some terms used herein are listed as below:

AI/ML Model: refers to a data driven algorithm that applies AI/ML techniques to generate a set of outputs based on a set of inputs;

AI/ML model delivery: refers to a generic term referring to delivery of an AI/ML model from one entity to another entity in any manner. Note: An entity could mean a network node/function (e.g., gNB, LMF, etc. ) , UE, proprietary server, and so on;

AI/ML model Inference: refers to a process of using a trained AI/ML model to produce a set of outputs based on a set of inputs;

AI/ML model testing: refers to a subprocess of training, to evaluate the performance of a final AI/ML model using a dataset different from one used for model training and validation. Differently from AI/ML model validation, testing does not assume subsequent tuning of the model;

AI/ML model training: refers to a process to train an AI/ML Model [by learning the input/output relationship] in a data driven manner and obtain the trained AI/ML Model for inference;

AI/ML model transfer: refers to delivery of an AI/ML model over the air interface in a manner that is not transparent to 3GPP signalling, either parameters of a model structure known at the receiving end or a new model with parameters. Delivery may contain a full model or a partial model;

AI/ML model validation: refers to a subprocess of training, to evaluate the quality of an AI/ML model using a dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for model training;

Data collection: refers to a process of collecting data by the network nodes, management entity, or UE for the purpose of AI/ML model training, data analytics and inference;

Federated learning /federated training: refers to a machine learning technique that trains an AI/ML model across multiple decentralized edge nodes (e.g., UEs, gNBs) each performing local model training using local data samples. The technique requires multiple interactions of the model, but no exchange of local data samples;

Functionality identification: refers to a process/method of identifying an AI/ML functionality for the common understanding between the network and the UE. Note: Information regarding the AI/ML functionality may be shared during functionality identification. Where AI/ML functionality resides depends on the specific use cases and sub use cases;

Model activation: refers to enable an AI/ML model for a specific AI/ML-enabled feature;

Model deactivation: refers to disable an AI/ML model for a specific AI/ML-enabled feature;

Model download: refers to transfer a Model from the network to UE;

Model identification: refers to a process/method of identifying an AI/ML model for the common understanding between the network and the UE. Note: The process/method of model identification may or may not be applicable;

Information regarding the AI/ML model may be shared during model identification;

Model monitoring: refers to a procedure that monitors the inference performance of the AI/ML model;

Model parameter update: refers to a process of updating the model parameters of a model;

Model selection: refers to a process of selecting an AI/ML model for activation among multiple models for the same AI/ML enabled feature. Note: Model selection may or may not be carried out simultaneously with model activation;

Model switching: refers to deactivating a currently active AI/ML model and activating a different AI/ML model for a specific AI/ML-enabled feature;

Model update: refers to a process of updating the model parameters and/or model structure of a model;

Model upload: refers to transfer a Model from UE to the network;

Network-side (AI/ML) model: refers to an AI/ML Model whose inference is performed entirely at the network;

Offline field data: refers to the data collected from field and used for offline training of the AI/ML model;

Offline training: refers to an AI/ML training process where the model is trained based on collected dataset, and where the trained model is later used or delivered for inference. Note: This definition only serves as a guidance. There may be cases that may not exactly conform to this definition but could still be categorized as offline training by commonly accepted conventions;

Online field data: refers to the data collected from field and used for online training of the AI/ML model;

Online training: refers to an AI/ML training process where the model being used for inference) is (typically continuously) trained in (near) real-time with the arrival of new training samples. Note: the notion of (near) real-time and non real-time are context-dependent and is relative to the inference time-scale. Note: This definition only serves as a guidance. There may be cases that may not exactly conform to this definition but could still be categorized as online training by commonly accepted conventions. Note: Fine-tuning/re-training may be done via online or offline training. (This note could be removed when we define the term fine-tuning) ;

Reinforcement Learning (RL) : refers to a process of training an AI/ML model from input (a.k.a. state) and a feedback signal (a.k.a. reward) resulting from the model’s output (a.k.a. action) in an environment the model is interacting with;

Semi-supervised learning A process of training a model with a mix of labelled data and unlabelled data;

Supervised learning: refers to a process of training a model from input and its corresponding labels;

Two-sided (AI/ML) model: refers to a paired AI/ML Model (s) over which joint inference is performed, where joint inference comprises AI/ML Inference whose inference is performed jointly across the UE and the network, i.e., the first part of inference is firstly performed by UE and then the remaining part is performed by gNB, or vice versa;

UE-side (AI/ML) model: refers to an AI/ML Model whose inference is performed entirely at the UE;

Unsupervised learning: refers to a process of training a model without labelled data;

Proprietary-format models ML models of vendor-/device-specific proprietary format, from 3GPP perspective. They are not mutually recognizable across vendors and hide model design information from other vendors when shared. Note: An example is a device-specific binary executable format;

Open-format models: refers to ML models of specified format that are mutually recognizable across vendors and allow interoperability, from 3GPP perspective. They are mutually recognizable between vendors and do not hide model design information from other vendors when shared;

reportConfigType: refers to time domain behavior of reporting configuration;

reportFreqConfiguration: refers to reporting configuration in the frequency domain;

reportQuantity: refers to the CSI related quantities to report.

In the present disclosure,

terms of “ML model” , “AI model” , “ML function” , “AI function” and “algorithm” may be used interchangeably.

terms of “ID” , “index” , “indicator” and “identifier” may be used interchangeably.

terms of “model” “functionality” and “model/functionality” may be used interchangeably.

terms of “Model” , “Model set” and “Model Group” may be used interchangeably.

terms of “Functionality” , “Functionality Group” and “Functionality Set” may be used interchangeably.

terms “precoder” , “precoding” , “precoding matrix” , “beam” , “spatial relation information” , “spatial relation info” , “precoding information” , “precoding information and number of layers” , “precoding matrix indicator (PMI) ” , “precoding matrix indicator” , “transmission precoding matrix indication” , “precoding matrix indication” , “transmission configuration indication state (TCI state) ” , “UL TCI state” , “joint TCI state” , “transmission configuration indicator” , “quasi co-location (QCL) ” , “quasi-co-location” , “QCL parameter” , “QCL assumption” , “QCL relationship” and “spatial relation” may be used interchangeably.

reference signal (RS) resource, RS resource set, antenna port, antenna port group, beam, beam group. In this regard, the terms (and their equivalent expressions) “panel” , “panel type” , “set of antenna port (s) ” , “antenna element (s) ” , “antenna array (s) ” may be used interchangeably.

terms of “network, NW” may be replaced by “Operation Administration and Maintenance, OAM” , “server” , “Access and Mobility Management Function (AMF) /Location Management Function (LMF) ” and other suitable network entity.

terms of “CSI” , “CSI report” , “CSI sub-report” , “CSI field” may be used interchangeably.

terms of “ResourceConfig” and “resource setting” may be used interchangeably.

terms of “multiple CSI” , “multi-CSI” and “CSIs” may be used interchangeably.

It is noted that when the term “a set of” is used, it may mean one or more elements/items, which may be replaced by terms of “at least one” , “a group of” or “a list of” . For example, “a set of Xs” means “at least one X” or “one or more Xs” .

As used herein, a model may be equivalent to at least one of the following: an AI/ML model, a ML model, an AI model, a data-driven, a data processing model, an algorithm, a functionality, a procedure, a process, an entity, a function, a feature, a feature group, a model identifier (ID) , an ID, a functionality ID, a configuration ID, a scenario ID, a site ID, or a dataset ID. As a result, the above terms may be used interchangeably.

In some embodiments, the model may be represented by or associated with a channel, a resource, a resource set, a reference signal (RS) resource, a RS resource set, a RS port, a set of RS ports, a RS port ID, or a set of RS port IDs.

In some embodiments, the model may comprise a set of weights values that may be learned during training, for example for a specific architecture or configuration, where a set of weights values may also be called a parameter set.

In some embodiments, an input of the ML model (i.e., AI input) may refer to the input of a model and indicate data inputted into the model, which may be equivalent to data.

In some embodiments, an output of ML model (i.e., AI output) may refers to the output of a model and indicate result (s) outputted by the model, which is equivalent to label/data.

In the present disclosure, a CSI report configuration associated with a plurality of sub-configurations may refer to: the CSI report configuration comprises a plurality of sub-configurations, or the CSI report configuration comprises a plurality of values of parameters (or a plurality of value groups/sets of parameter groups/sets) . In other word, each sub- configuration may be represented as an independent configuration, or be represented as a value of one parameter (or a value group/set of one parameter group/set) .

In the present disclosure, there are associations between the sub-configurations and CSIs. In view of this, the discussions about the sub-configurations may be adaptively to the CSIs, for example, selection/activation/deactivation of sub-configurations may be replaced by selection/activation/deactivation CSIs. Merely for brevity, some similar contents are omitted herein.

Principles and implementations of the present disclosure will be described in detail below with reference to the figures.

Example environment

FIG. 1 illustrates a schematic diagram of an example communication environment 100 in which example embodiments of the present disclosure can be implemented. In the communication environment 100, a plurality of communication devices, including a terminal device 110 and a network device 120, can communicate with each other.

Further, multiple input multiple output (MIMO) is supported in the communication environment 100, such that the network device 120 and the terminal device 110 may communicate with each other via different beams to enable a directional communication.

In the example of FIG. 1, in some embodiments, the terminal device 110 may include a terminal device and the network device 120 may include a network device serving the terminal device. In this specific example embodiment, a link from the terminal device 110 to the network device 120 is referred to as uplink, while a link from the network device 120 to the terminal device 110 is referred to as a downlink.

In downlink, the network device 120 is a transmitting (TX) device (or a transmitter) and the terminal device 110 is a receiving (RX) device (or a receiver) , and the network device 120 may transmit downlink transmission to the terminal device 110 via one or more beams. As illustrated in FIG. 1, the network device 120 transmits downlink transmission to the terminal device 110 via the one or more of beams 140-1, 140-2 and 140-3. For purpose of discussion, the beams 140-1 to 140-3 are collectively or individually referred to as beam 140.

Correspondingly, in uplink, the network device 120 is an RX device (or a receiver) and the terminal device 110 is a TX device (or a transmitter) , and the terminal device 110 may transmit uplink transmission to the network device 120 via one or more beams. As illustrated in FIG. 1, the terminal device 110 transmits uplink transmission to the network device 120 via the beams 130-1 to 130-3. For purpose of discussion, the beams 130-1 to 130-3 are collectively or individually referred to as beam 130.

In some embodiments, one or more models may be deployed at the terminal device 110 and/or the network device 120. As illustrated in FIG. 1, the model 115 may be deployed at the terminal device 110. Alternatively, or in addition, the model 125 may be deployed at the terminal device 110. In case that both model 115 and model 125 are deployed, the model 115 and model 125 may be operated collaboratively with each other.

It is to be understood that the number of devices and their connections shown in FIG. 1 are only for the purpose of illustration without suggesting any limitation. The communication environment 100 may include any suitable number of devices configured to implementing example embodiments of the present disclosure.

In some embodiments, the terminal device 110 and the network device 120 may communicate with each other via a channel such as a wireless communication channel on an air interface (e.g., Uu interface) . The wireless communication channel may comprise a physical uplink control channel (PUCCH) , a physical uplink shared channel (PUSCH) , a physical random-access channel (PRACH) , a physical downlink control channel (PDCCH) , a physical downlink shared channel (PDSCH) and a physical broadcast channel (PBCH) . Of course, any other suitable channels are also feasible.

The communications in the communication environment 100 may conform to any suitable standards including, but not limited to, Global System for Mobile Communications (GSM) , Long Term Evolution (LTE) , LTE-Evolution, LTE-Advanced (LTE-A) , New Radio (NR) , Wideband Code Division Multiple Access (WCDMA) , Code Division Multiple Access (CDMA) , GSM EDGE Radio Access Network (GERAN) , Machine Type Communication (MTC) and the like. The embodiments of the present disclosure may be performed according to any generation communication protocols either currently known or to be developed in the future. Examples of the communication protocols include, but not limited to, the first generation (1G) , the second generation (2G) , 2.5G, 2.75G, the third generation (3G) , the fourth generation (4G) , 4.5G, the fifth generation (5G) communication protocols, 5.5G, 5G-Advanced networks, or the sixth generation (6G) networks.

Example processes

It is to be understood that the operations at the terminal device 110 and the network device 120 should be coordinated. In other words, the network device 120 and the terminal device 110 should have common understanding about configurations, parameters and so on. Such common understanding may be implemented by any suitable interactions between the network device 120 and the terminal device 110 or both the network device 120 and the terminal device 110 applying the same rule/policy. In the following, although some operations are described from a perspective of the terminal device 110, it is to be understood that the corresponding operations should be performed by the network device 120. Similarly, although some operations are described from a perspective of the network device 120, it is to be understood that the corresponding operations should be performed by the terminal device 110. Merely for brevity, some of the same or similar contents are omitted here.

Reference is made to FIG. 2, which illustrates a signaling flow 200 of communication in accordance with some embodiments of the present disclosure. For the purposes of discussion, the signaling flow 200 will be discussed with reference to FIG. 1, for example, by using the terminal device 110 and the network device 120.

In the following, non-AI CSI will be used as an example of the CSI for a first usage, and AI-based CSI will be used as the CSI for a second usage.

In operation the terminal device 110 receives 215 a CSI report configuration (via such as, RRC signaling) from a network device 120, where the CSI report configuration is associated with a plurality of sub-configurations. Optionally, the terminal device 110 may receive 245 a message (such as, DCI message, MAC CE) used for triggering a CSI report. Then, the terminal device 110 transmits 255 to at least one CSI report the network device 120, where at least one CSI report comprises CSI determined based on one or more of the plurality of sub-configurations.

In the following, more detail about the CSI report configuration and the plurality of sub-configurations will be discussed. For example, sub-configurations may be applied jointly (simultaneously) or sequentially, each sub-configuration may be associated with a different AI/ML model management stage of a different AI/ML model and so on.

In some embodiments, a subset of the plurality of sub-configurations support to be activated jointly. In some embodiments, the plurality of sub-configurations corresponding to a plurality of CSIs, a subset of the plurality of CSIs support to be comprised in one CSI report or comprised in more than one CSI report within a time window.

In some embodiments, the report configuration may further indicate at least one of the following:

first information about the subset of the plurality of sub-configurations, or

second information about subset of the plurality of CSIs.

In some embodiments, one CSI report configuration (i.e., one CSI-ReportConfig, or parameters for one CSI-ReportConfig) may correspond to one CSI-ReportConfigId.

Assuming L sub-configurations are associated with one CSI report configuration, and for CSI, where N and L is integer and 1<=N<=L. In this event,

among CSI, there could be N_s simultaneous CSI, where N_s<=N, where “simultaneous” implies that N_s CSI in one CSI report, or in CSI reports within a short time window.

among L sub-configurations, there could be L_s joint sub-configurations, where L_s<=L, where “joint” implies L_s sub-configurations are applied together or within a short time window.

In some embodiments, information on simultaneous CSI and/or joint sub-configurations may be provided by explicit signaling, i.e., first information about the subset of the plurality of sub-configurations and second information about subset of the plurality of CSIs.

In some embodiments, for each sub-configuration or for each CSI, the following information may be provided: reportQuantity, reportConfigType, reportFreqConfiguration.

In some embodiments, for each sub-configuration or for each CSI corresponding to the CSI report configuration, the following information may be provided: antenna (port) number of a first dimension N₁, antenna (port) number of a second dimension N₂ for single-panel and antenna (port) number of a first dimension N₁, antenna (port) number of a second dimension N₂, number of panels Ng for multi-panel, port subset indication, rank restriction, codebook subset restriction, supported codebook types for PMI (type I/II, compressed CSI) , raw channel, codebookConfig and so on.

In some embodiments, a value of the first parameter of antenna port configuration may be represented as N₁. For example, N₁ may be a positive integer. For example, N₁ may be one of {2, 3, 4, 6, 8, 12, 16} . In some embodiments, a value of the second parameter of antenna port configuration may be represented as N₂. For example, N₂ may be a positive integer. For example, N₂ may be one of {1, 2, 3, 4} . In some embodiments, the first parameter of antenna port configuration and the second parameter of antenna port configuration may be configured in one higher layer parameter.

In some embodiments, the number of antenna ports in one antenna port group or for one CSI-RS resource may be determined based on the first parameter of antenna port configuration and a second parameter of antenna port configuration. In some embodiments, the number of antenna ports in one antenna port group or for one CSI-RS resource may be P=N₁·N₂·2.

In some embodiments, for beam report, information about nrofReportedGroups, nrofReportedRS may be provided.

In addition, each sub-configuration may be assigned with respective time related information, e.g., a time duration, a cycle length or a timer.

In some embodiments, for each CSI report, the resources for measurement are configured in hierarchical structure, specifically,

ReportConfig may be linked to one or multiple ResouceConfig. By introducing sub-configuration, one more layer may be added to the hierarchical structure of legacy CSI report framework, e.g., ReportConfig is linked to one or multiple Sub-configuration, e.g., a list of SubConfigurationId; Sub-configuration may be linked to one or multiple ResouceConfig;

ResourceConfig may be linked to one or multiple resource sets via ResourceSetList;

ResourceSet may contain information of one or multiple Resources via ResourceList

Resource may be the minimum unit for physical layer configuration;

One or more Resource from a ResourceSet may be associated with the same or different CSI report (s) /sub-configuration (s) ; In addition, each CSI-RS resource may be associated with all the CSI report (s) /sub-configurations;

One or more ResourceSet from ResourceSetList may be associated with the same or different CSI report (s) /sub-configuration (s) ; In addition, each ResourceSet is associated with all the CSI report (s) /sub-configurations;

Resource in the ResourceSet may have the same or different number of antenna ports; In addition, depending on associated CSI report (s) /sub-configuration (s) ;

ResourceSet from ResourceSetList may have the same or different number of resources; In addition, depending on associated CSI report (s) /sub-configuration (s) ;

An example IE with SubConfigurationId is illustrated as below.

In some embodiments, for each Resource, or ResourceSet, or ResouceConfig, the Codebook configuration information may be provided as below:

Codebook configuration for Type-1 codebook or Type-2 codebook or compressed CSI codebook may include codebook subset restriction. Network may configure one of codebookConfig, codebookConfig-r16 or codebookConfig-r17 or codebookConfig-r18 to a UE.

In some embodiment, the same codebook type for PMI (type I/II, compressed CSI) may be applied for all corresponding resource, resource set, or ResourceConfig. In some embodiment, the same codebook subset restriction is applied for all corresponding resource, resource set, or ResourceConfig.

In some example, NrofCodebookConfigList may equal the same value as the number of resources in the corresponding resource set. In some example, the resource set is for multiple TRP coherent joint transmission. In some other example, NrofCodebookConfigList may equal the same value as the number of resource sets in the corresponding ResourceConfig. First entry in NrofCodebookConfigList corresponds to first entry in nzp-CSI-RSResources of that NZP-CSI-RS-ResourceSet, second entry in NrofCodebookConfigList corresponds to second entry in nzp-CSI-RS-Resources, and so on. If some resources are not configured with CodebookConfig, the corresponding value could be “null” .

In some example, NrofCodebookConfigList may equal the same value as the number of selected TRPs. In some example, the selected TRPs are corresponding to the selected resources in the corresponding resource set. In some example, the resource set is for multiple TRP coherent joint transmission. First entry in NrofCodebookConfigList corresponds to first TRP, second entry in NrofCodebookConfigList corresponds to second TRP, and so on.

In some example, NrofCodebookConfigList may be smaller than the number of resources in the corresponding resource set. If some resources are not configured with CodebookConfig, there is no codebook subset restrictions. In addition, a bitmap can be configured for indicating the resources not with CodebookConfig, for example, a bitmap 1101 can be configured for a resource set with 4 resources and the third resource is not provided with CodebookConfig.

In some example, NrofCodebookConfigList may equal the value of MaxNrofCodebookConfigList which may be based on UE capability reporting.

In some embodiments, the CSI report configuration may further comprise a main configuration, and wherein if a configuration parameter is absent in a sub-configuration, determine a first value of the configuration parameter to be a second value of a corresponding configuration parameter comprised in main configuration.

As one embodiment, the corresponding CSI report configuration may also provide a main configuration, e.g., which may be configured via the legacy RRC IE.

If the main configuration is configured, for sub-configurations, if some parameters (e.g., carrier, component carrier (CC) , bandwidth part (BWP) , cell information) are not provided, the value may be inherited from the main configuration. Accordingly, for some parameters (such as, time domain behavior) provided in both main configuration and sub-configuration, the value may be overwritten by the sub-configuration.

In some embodiments, the plurality of sub-configurations comprise at least one of the following: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage.

In some embodiments, the plurality of sub-configurations comprise at least one of the following: the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with CSI for the second usage.

In some embodiments, the CSI report configuration may be associated with at least one of the following: an AI model or an AI functionality, and wherein the second sub-configuration and the third sub-configuration are associated with at least one of the following:

two different management stages,

two different types of CSI, or

two different AI models.

In some embodiments, the sub-configuration may comprise at least one of the following:

a first parameter indicating a usage of the sub-configuration, or

a second parameter indicating a model identity associated with the sub-configuration.

That is, the CSI report configuration comprise more than one AI/ML-based sub-configurations. Some details are further discussed as below.

In some embodiments, the terminal device 110 may be provided with multiple CSI report sub-configurations for one CSI report configuration. Additionally, each sub-configuration may be associated with a different AI/ML model management stage of a different AI/ML model. In this way, multiple CSI report for AI/ML without increasing the required number of CSI report configurations is achieved.

Assume that there are L sub-configurations associated with one CSI report configuration, and the L sub-configurations may be associated with one same AI/ML model. Alternatively, or in addition, in some embodiments, each sub-configuration may be associated with one or more AI/ML model management stages, e.g., model training, model monitoring, model inference and so on.

Alternatively, in some embodiments, different sub-configurations associated with the same AI/ML model management stages can be additionally associated with different types of CSI, for example, CSI as Model inputs, CSI as Model outputs, CSI as Ground truth, and so on. Additionally, information on associated AI/ML model management stages of each sub-configuration can be provided by explicit signaling, e.g., “usage” , which may be configured with value, i.e., a first parameter.

Alternatively, in some embodiments, different sub-configurations configured with the same “usage” can be associated as joint sub-configuration for simultaneous multiple CSI, for example, as one sample for model training, as one instance of model monitoring, and so on.

As one example, L sub-configurations associated with one CSI report configuration may be associated with one same AI/ML functionality, but with K different AI/ML models, where K<=N<=L. Further, for each AI/ML model, the number of sub-configurations may be denoted as L_k, k = 1, …, K.

Alternatively, in some embodiments, each sub-configuration may be associated with one or more AI/ML model management stages of one or more AI/ML models, e.g., model training for first model, model monitoring for first model, model inference for first model, and so on.

Additionally, in some embodiments, associated AI/ML model of each sub-configuration may be provided by explicit signaling, e.g., model ID, i.e., the second parameter.

Merely for better understanding, reference is now made to FIG. 3A to 3B, which illustrate examples of sub-configuration mapping 300A, 300B and 300C. In FIG. 3A, each sub-configuration may be associated with one or more AI/ML model management stages, in FIG. 3B, different sub-configurations associated with the same AI/ML model management stages can be additionally associated with different types of CSI, and in FIG. 3C, each sub-configuration may be associated with one or more AI/ML model management stages of one or more AI/ML models.

In some circumstance, AI/ML model based operations may not outperform the legacy operations and NW/UE may need to switch back to non-AI based method. The non-AI based method shall be configured together with the AI/ML model based operations as a fall back option. At least for CSI/BM use cases, as discussed above, the association between CSI report sub configurations and the AI/ML model and/or different LCM stages of an AI/ML model LCM can be established. In addition, a dedicated CSI report sub configuration can be configured for the fall back operation, together with other CSI report sub configurations for AI/ML, sharing the same CSI-ReportConfigId.

In some embodiments, at least for CSI/BM use cases, support fallback configuration as one CSI report sub configuration.

In some embodiments, one of the plurality of sub-configurations may be configured as a default sub-configuration or a fallback sub-configuration.

In some embodiments, any of the fallback sub-configuration or the default sub-configuration is configured to be one of the following: the first sub-configuration, or a sub-configuration with the lowest or highest identity.

As one example, a dedicate sub-configuration may be provided as non-AI sub-configuration, which may be used as a fallback configuration, or a default configuration when the associated AI/ML model is not functional, or a ground truth data collection when model monitoring is performed.

In some embodiments, this sub-configuration may be assigned with a fixed ID, e.g., sub-configuration ID ‘0’ . Further, in some embodiments, the association between AI and non-AI CSI report is then provided by the same CSI report configuration (and different sub-configurations) .

In addition, if the corresponding CSI report configuration provides a main configuration, e.g., via the legacy RRC IE, the non-AI configuration, or the default configuration may be the main configuration.

According to different use cases, the sub-configurations and CSIs may be different, and the plurality of sub-configurations may be associated with the same or different CSI reference signal (RS) resources, which will be discussed as below.

In some embodiments, the CSI determined based on one or more of the plurality of sub-configurations may be multi-CSI, and the multi-CSI comprises at least two of the following:

first CSI comprising raw channel,

second CSI comprising compressed CSI, or

third CSI comprising codebook-based CSI.

In some embodiments, in case of model training data collection, the multi-CSI comprises: the first CSI or third CSI which is used as model input, and the second CSI which is used as model output.

In some embodiments, in case of model monitoring, the multi-CSI comprises: the second CSI which is used for inference, the first CSI or third CSI which is used for collecting ground truth data.

In some embodiments, in case of model switching or model selection, the multi-CSI comprises: different second CSIs corresponding to different AI models.

As one example, the multiple CSI needed to support AI/ML based CSI compression include:

first type of CSI, such as associated with raw channel, which may be used as AI/ML model input. It may be Precoding matrix in spatial-frequency domain, or represented using angular-delay domain projection. It may also be Explicit channel matrix (i.e., full Tx * Rx MIMO channel) in spatial-frequency domain or in angular-delay domain. Further, the first type of CSI may be configured with “usage = ground truth data collection” , “usage = model training input data collection” and son on;

second type of CSI, which can be compressed CSI or generated CSI based on AI/ML model output. Further, the second type of CSI may be configured with “usage = model inference” , “usage = model training output data collection” and so on;

third type of CSI, which may be the legacy codebook based CSI, including CRI, RI, type I or type II PMI, CQI and so on. Further, the third type of CSI may be configured with “usage = ground truth data collection” , “usage = model training input data collection” .

In some embodiments, simultaneous multiple CSI needed to support AI/ML based CSI compression may be:

as for model training data collection, model input may be first type of CSI, or third type of CSI, model output may be second type of CSI;

as for model monitoring, inference based on model output may be: second type of CSI, and ground truth may be obtained based on: first type of CSI, or third type of CSI;

as for model switching/selection, different compressed CSI (second type) based on the model output of different AI/ML models.

It should be understood that data collection is needed for different LCM stages, for example, model training, model inference and model monitoring. For different representative sub use cases, studies are needed to identify whether the legacy CSI/BM/positioning framework can be sufficient for each sub use case respectively. A hierarchical structure could be useful to link the AI/ML framework and the legacy CSI/BM/positioning framework. Multiple alternatives can be considered and it is needed to study their pros and cons in terms of complexity, flexibility, requirement on UE capability, latency, as well as the spec impact. Take CSI report as an example, one method (a) is to configure one legacy CSI ReportConfig for each stage of LCM of an AI/ML model. The other method (b) is to use RRC to reconfigure the target AI/ML model and LCM stage for a CSI ReportConfig.

As a general principle, compared to legacy non-AI based method, AI/ML based method shall not increase signaling overhead and the number of CSI report configurations, i.e., CSI-ReportConfig, which is restricted to a maximum number based on UE capability. Configuration (a) above would require a large number of CSI report configurations, for different AI/ML models, and for different LCM stages even for a same AI/ML model, while method in (b) may trigger frequent RRC reconfigurations.

In view of the above, at least for CSI/BM use cases, compared to legacy CSI report, AI/ML based method shall not increase signaling overhead and the number of CSI report configurations.

To meeting those challenges, sub configuration for a CSI-ReportConfig can be considered, which is introduced in NR during Rel-18 NES discussion to support dynamic spatial pattern and transmit power of a same resource. To integrate AI/ML CSI/BM use case and CSI report framework with sub configurations, the association between sub configurations and AI/ML models and/or different LCM stages of an AI/ML model can be established and configured via one CSI-ReportConfigId. The signalling for CSI report configurations/sub configurations activation/deactivation can be used as the signalling for selecting AI/ML models or switching LCM stages.

The sub configuration based method will not increase the total number of required CSI-ReportConfig and it will not trigger frequent RRC reconfiguration. Thus, in some embodiments, at least for CSI/BM use cases, study sub configuration based method to control the total number of required CSI-ReportConfig.

To assess the accuracy performance, comparisons between AI/ML inference output and the ‘ground truth’ are needed. However, one reasonable assumption is that a reduced version of reference signals and correspondingly a reduced version of measurement and reports will be applied during the model inference stage, which may cause difficulties to obtain the ‘ground truth’ . As a starting point, it is needed to study whether and how the legacy CSI framework, BM framework and positioning framework can be used for ground truth data collection. At least for CSI/BM use cases, the association between CSI report sub configurations and the AI/ML model and/or different LCM stages of an AI/ML model LCM can be established. In addition, a dedicated CSI report sub configuration can be configured for ground truth data collection during the model monitoring stage, together with other CSI report sub configurations for other different LCM stages, sharing the same CSI-ReportConfigId.

In some embodiments, at least for CSI/BM use cases, support ground truth data collection as one CSI report sub configuration.

In some embodiments, the CSI RS resource configuration with sub-configuration, and the CSI RS resources/resource sets may the same for all sub-configurations.

In some embodiments, the CSI determined based on one or more of the plurality of sub-configurations is multi-CSI, and the multi-CSI comprises at least two of the following:

first CSI comprising historical CSI,

second CSI comprising predicted CSI, or

third CSI comprising codebook-based CSI.

In some embodiments, in case of model monitoring, the multi-CSI comprises: the second CSI which is used for inference, the third CSI which is used for collecting ground truth data. In some embodiments, in case of model switching or model selection, the multi-CSI comprises: different second CSIs corresponding to different AI models.

In some embodiments, multiple CSI needed to support AI/ML based time domain CSI prediction include:

first type of CSI, such as associated with historical CSI, which may be used as AI/ML model input. Further, the first type of CSI may be configured with “usage = model training input data collection” , “usage = model inference” ;

second type of CSI, which may be predicted CSI for future time instance based on AI/ML model output. Further, the second type of CSI may be configured with “usage = model inference” , “usage = model training output data collection” ;

third type of CSI, which may be the legacy codebook based CSI, including CRI, RI, type I or type II PMI, CQI; Further, the third type of CSI may be configured with “usage = ground truth data collection” , “usage = model training input data collection” .

In some embodiments, simultaneous multiple CSI needed to support AI/ML based time domain CSI prediction may be:

as for model training data collection, the model input may be: first type of CSI, or third type of CSI, the model output may be second type of CSI;

as for model monitoring, inference based on model output may be” second type of CSI, and ground truth may be obtained based on: third type of CSI;

as for model switching/selection, different predicted CSI (second type) based on the model output may be of different AI/ML models.

In some embodiments, the CSI RS resources/resource sets may the same for all sub-configurations.

In some embodiments, the CSI determined based on one or more of the plurality of sub-configurations is a multi-beam report, and the multi-beam report comprises at least two of the following:

a first beam report comprising measurement results corresponding to a first beam set,

a second beam report comprising predicted beam, or

a third beam report comprising measurement results corresponding to a second beam set.

In some embodiments, in case of model training data collection, the multi-beam report comprises: the first beam report which is used as model input, and the second beam report or third beam report which is used as model output.

In some embodiments, in case of model monitoring, the multi-beam report comprises: the second beam report which is used for inference, the third beam report which is used for collecting ground truth data.

In some embodiments, in case of model switching or model selection, the multi-beam report comprises: different second beam reports corresponding to different AI models.

As one example, the multiple CSI (for BM case, it may also be multiple beam report) needed to support AI/ML based spatial domain beam prediction include:

first type of beam report, set B measurement results, which may be used as AI/ML model input, the first type of beam report may be configured with “usage = model training input data collection” , “usage = model inference” ;

second type of beam report, predicted beam or other prediction results, which may be AI/ML model output. The second type of beam report may be configured with “usage = model inference” , “usage = model training output data collection” ;

third type of beam report, set A measurement results, which may be used as AI/ML model output. The third type of beam report may be configured with “usage = ground truth data collection” , “usage = model training output data collection” .

In some embodiments, simultaneous multiple CSI (for BM case, it also may be simultaneous multiple beam report) needed to support AI/ML based spatial domain beam prediction include:

as for model training, model input may be first type of beam report, model output may be the second type of beam report, or third type of beam report;

as for model monitoring, inference based on model output may be second type of beam report, and ground truth may be obtained based on: third type of beam report;

as for model switching/selection, different predicted beam (second type) based on the model output of different AI/ML models.

In some embodiments, CSI RS (for BM case, it can also be BM RS) resource configuration with sub-configuration may be the same for all sub-configurations. Alternatively, in some embodiments, different BM RS resource for set A and set B may be associated with one sub-configuration, which implies varying set B pattern.

Alternatively, in some embodiments, different BM RS resource for set A and set B may be associated with one sub-configuration.

a first beam report comprising historical measurement results corresponding to a first beam set,

a second beam report comprising predicted beam,

a third beam report comprising historical measurement results corresponding to a second beam set, or

a fourth beam report comprising measurement results corresponding to the first beam set or the second beam set.

In some embodiments, in case of model monitoring, the multi-beam report comprises: the second beam report which is used for inference, the fourth beam report which is used for collecting ground truth data.

As one example, in some embodiments, multiple CSI (for BM case, it can also be multiple beam report) needed to support AI/ML based time domain beam prediction include:

first type of beam report, historical set B measurement results, the first type of beam report may be configured with “usage = model training input data collection” , “usage =model inference” ;

second type of beam report, which can be predicted beam for future time instance based on AI/ML model output, the second type of beam report may be configured with “usage = model inference” , “usage = model training output data collection” ;

third type of beam report, historical set A measurement results, which can be used as AI/ML model output, the third type of beam report may be configured with “usage =model training output data collection” ;

forth type of beam report, set B or set A measurement results, which can be used for non-AI/ML, the forth type of beam report may be configured with “usage = ground truth data collection” .

In some embodiments, simultaneous multiple CSI (for BM case, it can also be simultaneous multiple beam report) needed to support AI/ML based time domain beam prediction include:

As for model training, model input may be first type of beam report, model output may be Second type of beam report, or third type of beam report.

As for model monitoring, inference based on model output may be second type of beam report, ground truth may be forth type of beam report.

As for model switching/selection, different predicted beam (second type) based on the model output of different AI/ML models; Further, as for model switching/selection, data may be based on model outputs of different AI/ML models and/or measurement results.

In some embodiments, CSI RS (for BM case, it can also be BM RS) resource configuration with sub-configuration (i.e., BM RS resources/resource sets) may the same for all sub-configurations. Alternatively, different BM RS resource for set B can be associated with one sub-configuration, which implies varying set B pattern. Alternatively, different BM RS resource for set A and set B may be associated with one sub-configuration.

For multiple CSI and/or multiple sub-configurations, configured by one CSI report configuration, since different CSI and/or sub-configurations are intended to collect data for different stages, it is not necessary to always perform all sub-configurations and to report all CSI. Activation/deactivation of some CSI report or some sub-configurations are needed.

In some embodiments, the terminal device 110 may activate or deactivate 230 one or more of the plurality of sub-configurations. That is, some CSIs or some sub-configurations may be activated/deactivated. In this way, signaling overhead/latency may be reduced and UE processing complexity may be reduced.

In some embodiments, the terminal device 110 may keep valid 220 of the CSI report configuration regardless of a deactivation of a sub-configuration of the plurality of sub-configurations.

As one example, the corresponding CSI report configuration is still valid (e.g., not released) even [some of] CSI report/sub-configurations are deactivated.

In some embodiments, during a period from receiving the CSI report configuration and the first activation of at least one sub-configuration, the terminal device 110 may, validate one of the following:

none of the plurality of sub-configurations,

all the plurality of sub-configurations, or

a default sub-configuration of the plurality of sub-configurations.

As one example, after initial configuration, and before the first activation, the terminal device 110 may perform according to one of the following: none of the sub-configurations; all of the sub-configurations; default configuration, e.g., the sub-configuration with lowest configuration ID, the non-AI sub-configuration, the main configuration, and so on. In this example, “initial configuration” means the signaling of the corresponding CSI report configuration containing multiple CSI and/or sub-configurations is received, acknowledged, or applied, by the UE, “after” may refer to right after, or a time duration after, and “first activation” means, for the first time after initial configuration, at least one sub-configuration activation signaling is received, acknowledged, or applied, by the UE, in addition, it also means that a sub-configuration is activated implicitly.

In some embodiments, implicit activation/deactivation of some CSI reports or sub- configurations may be supported. In some embodiments, the terminal device 110 may activate or deactivate one or more of the plurality of sub-configurations based on at least one activation/deactivation condition associated with an artificial intelligence (AI) model.

Specifically, the terminal device 110 may activate and/or deactivate some CSI reports or sub-configurations adaptively based on AI/ML model condition/additional conditions/UE internal conditions without explicit signaling.

In some embodiments, adaptive/implicit activation/deactivation may be implemented as UE capability or controlled by the network. As illustrated in FIG. 2, in some embodiments, the terminal device 110 may receive 210, from the network device 120, a first indication used for enabling or disabling an adaptive activation or deactivation of sub-configuration. Alternatively, or in addition, in some embodiments, the terminal device 110 may transmit 205, to the network device, a second indication used for indicating whether the adaptive activation or deactivation of sub-configuration is supported by the terminal device 110.

In some embodiments, the terminal device 110 may determine at least one association between at least one sub-configuration and at least one activation/deactivation condition.

In some embodiments, the association is defined as default configuration, configured by the network device 120 or reported by the terminal device 110.

Additionally, in some embodiments, the terminal device 110 may report the selection result to the network device 120.

In order to better understand the procedure of adaptive activation or deactivation of sub-configuration, more details are discussed as below.

In some embodiments, in order to provide correct resources and report configuration for the AI/ML model implicit/adaptive activation/deactivation of some CSI reports or sub-configurations is performed based on AI/ML model condition/additional conditions/UE internal conditions without explicit signaling.

In some embodiments, AI/ML model condition/additional conditions/UE internal conditions may be defined as follows:

“Conditions” : configurations supported as indicated via UE capability reporting, UE assistance information reporting or NW indication, related to model training, model inference, performance monitoring, validation procedure, fallback, of an AI/ML model/functionality or a group of models/functionalities;

“additional conditions” : e.g., application conditions, scenarios, datasets, cell ID, timestamp and SNR, and so on;

“UE internal conditions” : e.g., memory, battery, computation resource, overheating and other hardware limitations.

In a nutshell, the above AI/ML model condition/additional conditions/UE internal conditions (and/or other AI-related conditions) may be the criteria of the selection of sub-configurations. That is, the change of the AI/ML model condition/additional conditions/UE internal conditions may imply the change of the application of sub-configurations.

Further, in order to enable implicit/adaptive activation/deactivation of some CSI reports or sub-configurations, the network device 120 and the terminal device 110 may need to understand whether the adaption may be supported without any explicit signaling.

In some embodiment, the network device 120 may provide an enabler of adaptive activation/deactivation of sub-configurations, e.g., via explicit RRC/MAC CE/DCI signaling.

Alternatively, in some embodiments, the terminal device 110 may report whether to support the adaptive activation/deactivation of sub-configurations via UE capability reporting or UE assistance information reporting.

Alternatively, in some embodiments, the association between sub-configurations and AI/ML model condition/additional conditions/UE internal conditions may need to be defined, signaled, reported or determined by the implementation of the network device 120/terminal device110.

As one embodiment, one “Conditions” for example means that a first sub-configuration corresponds to a first condition or a first combination of conditions.

As another embodiment, one “additional conditions” for example means that a first sub-configuration corresponds to a first additional condition or a first combination of additional conditions.

As a further embodiment, one “UE internal conditions” for example means that a first sub-configuration for a first UE internal condition or a first combination of UE internal conditions.

In addition to implicit/adaptive activation/deactivation of some CSI reports or sub-configurations, the CSI reports or sub-configurations may be activated/deactivated explicitly, which will be discussed as below.

In some embodiments, the terminal device 110 may receive, from the network device 120, a message used for activating or deactivating the one or more sub-configurations being one of the following:

a first messaged explicitly indicating the terminal device 110 to activate or deactivate the one or more sub-configurations, or

a life cycle management (LCM) signalling.

That is, according to the mapping between the LCM stages and sub-configurations, the LCM signalling may be reused as a signalling use for activating or deactivating the one or more sub-configurations, and further the terminal device 110 may reuse the first message as an LCM signalling.

In this way, signaling overhead/latency to activate/deactivate sub-configurations may be reduced, activation/deactivation of sub-configurations/CSI may be controlled by the network device 120, and no additional pre-configuration is needed.

In order to better understand the procedure of activation or deactivation of sub-configuration via explicit signalling, more details are discussed as below.

In some embodiments, signaling related to AI/ML model management, e.g., LCM signaling, may be used as signaling of sub-configurations. Specifically, a first sub-configurations associated with a first AI/ML model management stage are applied when the first LCM signaling are activated, and a second sub-configurations may be deactivated accordingly. As one example, LCM signaling is to activate model monitoring, the same signaling is to activate the sub-configurations for model monitoring.

In some embodiments, current AI/ML model management stage may be used to determine activation/deactivation of the sub-configurations. Specifically, sub-configurations associated with a first AI/ML model management stage may be applied when the first stage is activated, and/or sub-configurations associated with a first AI/ML model management stage may be not applied when the first stage is not activated or deactivated. Further, current AI/ML model management stage may be determined by NW signaling, like LCM signaling, and/or current AI/ML model management stage may be determined by UE request, like UE assistance information.

Additionally, signaling on activation/deactivation/selection of sub-configurations can be used as LCM signaling. Specifically, the first LCM stage may be activated when sub-configurations associated are activated, and/or the first LCM stage is deactivated when sub-configurations associated are deactivated.

Additionally, the association may be provided by the “usage” for each sub-configuration. That is, when the “usage” filed in a sub-configuration is configured as a first LCM stage, the first LCM stage may be activated upon the activation of this sub-configuration.

In some embodiments, the AI/ML model management stage may include the following: Data collection, Model training, Model registration, Model deployment, Model configuration, Model inference, Model selection, activation, deactivation, switching, and fallback operation, Model monitoring, Model update, Model transfer and so on.

In some embodiments, the LCM signaling may include the signaling to control (e.g., start/stop) the following procedures: Data collection, Model training, Model registration, Model deployment, Model configuration, Model inference, Model selection, activation, deactivation, switching, and fallback operation, Model monitoring, Model update, Model transfer and so on.

In some embodiments, in order to reduce UE processing complexity, the terminal device 110 may skip 235 a subset of the plurality of sub-configurations, which will be discussed as below.

In some embodiments, the terminal device 110 may skip a subset of the plurality of sub-configurations based on at least one of the following:

a first maximum number of sub-configurations allowed to be skipped,

a first minimum number of non-skipped sub-configurations supported by the terminal device 110 or the network device 120,

a second maximum number of jointly-applied sub-configurations allowed to be skipped, or

a second minimum number of non-skipped jointly-applied sub-configurations supported by the terminal device 110 or the network device 120.

In some embodiments, any of the first maximum number, the second maximum number, the first the minimum number or the second the minimum number is defined as default configuration, configured by the network device 120 or reported by the terminal device 110.

In some embodiments, skipping sub-configuration may be implemented as UE capability or controlled by the network. Specifically, in some embodiments, the terminal device 110 may receive, from the network device 120, a third indication used for enabling or disabling the skipping a sub-configuration or a jointly-applied sub-configuration. Alternatively, or in addition, in some embodiments, the terminal device 110 may transmit, to the network device 120, a fourth indication used for indicating whether the skipping the sub-configuration or the jointly-applied sub-configuration is supported by the terminal device 110.

In some embodiments, the terminal device 110 may skip the subset of the plurality of sub-configurations associated with at least one of the following: an AI management stage, an AI functionality, or an AI model.

In some embodiments, the terminal device 110 may transmit 240, a message to the network device 120, the message indicating at least one of the following:

at least one skipped sub-configuration,

at least one AI management stage associated with at least one skipped sub-configuration,

at least one AI functionality associated with at least one skipped sub-configuration, or

at least one AI model associated with at least one skipped sub-configuration.

In order to better understand the procedure of skipping the sub-configuration, more details are discussed as below.

In some embodiments, the terminal device 110 may be allowed to select/skip application of some CSI report and/or sub-configurations, the number of skipped CSI reports and/or sub-configurations may be limited as discussed below.

For example, assuming L sub-configurations with one CSI report configuration, and forCSI, where 1<=N<=L, amongCSI, there could be N’ CSI skipped, where N’ <=N. For another example, among L sub-configurations, there could be L’ sub-configurations skipped, where L’ <= L.

In some embodiments, information on whether the selection/skip of some CSI reports/sub-configurations is supported and information on N’ and/or L’ (the numbers, which N’ or L’) may be based on configuration (s) from the network device 120, UE report via UE capability reporting or UE assistance information reporting.

In addition, or alternatively, assuming L_s joint sub-configurations with one CSI report configuration, or for N_s simultaneous CSI, among N_s simultaneous CSI, there could be N” CSI skipped, where N” <=N_s, and further among L_s joint sub-configurations, there could be L” sub-configurations skipped, where L” <= L_s.

In some embodiments, information on whether the selection/skip of some CSI reports/sub-configurations is supported and information on N” and/or L” (the numbers, which N’ or L’) can be based on NW configuration, UE report via UE capability reporting or UE assistance information reporting.

Alternatively, or in addition, in some embodiments, the number of selected CSI reports and/or sub-configurations can be defined similarly.

Additionally, in some embodiments, the terminal device 110 may be allowed to select/skip application of some sub-configurations, which implies that the terminal device 110 may be allowed to autonomously start/stop/select/switch the AI/ML management stages, at least for one AI/ML model.

Additionally, in some embodiments, the terminal device 110 may be allowed to select/skip application of some sub-configurations, which implies that UE is allowed to autonomously start/stop/select/switch the applied AI/ML models, at least for the same functionality, when different sub-configurations for different AI/ML models are associated with one CSI report configurations.

Additionally, in some embodiments, the terminal device 110 may report the selected/skipped CSI reports and/or sub-configurations. As one example, the UE report is represented by the information related to sub-configuration, e.g., sub-configuration ID. Alternatively, the UE report is represented by the information related to AI/ML model management, e.g., model ID.

It should be clarified that the UE report may be before or after the performed selection/skip.

In addition, the computation of the number of CSI processing units (CPUs) and CSI report priority also may be determined 250 due to the introducing of the sub-configurations, which will be discussed as below.

In some embodiments, the at least one of the following is associated with an identity of a sub-configuration:

a CSI processing time,

the number of CSI processing units (CPUs) , or

a CSI report priority.

In some embodiments, a duration occupied by at least one CPU corresponding to a sub-configuration may start from the first symbol of the earliest one of each RS resource corresponding to sub-configuration until the last symbol of the configured uplink resources carrying the CSI report.

In some embodiments, if the CSI comprised in the CSI report is a simultaneous multi-CSI, or the one or more sub-configurations are jointly activated, the number of CPUs for the CSI report is determined to be one of the following:

a sum of the numbers of CPUs corresponding to the one or more sub-configurations,

the maximum number of the numbers of CPUs, or

a defined number less than the sum of the numbers of CPUs.

In some embodiments, if the CSI comprised in the CSI report is a simultaneous multi-CSI, or the one or more sub-configurations are jointly activated, a CSI processing time for the CSI report is determined to be one of the following:

a sum of CSI processing time corresponding to the one or more sub-configurations,

the maximum of the CSI processing times, or

a defined processing time less than the sum of the sum of CSI processing time.

In some embodiments, a duration occupied by CPUs corresponding to the CSI report may start from the first symbol of first symbol of the earliest RS resource corresponding to the CSI report until the last symbol of the configured uplink carrying the CSI report.

In some embodiments, in the CSI report priority is further associated with the maximum number of sub-configurations associated with the CSI report configuration.

In some embodiments, a priority of a CSI report with multi-CSI may be higher than a CSI report with single CSI.

In some embodiments, each sub-configuration associated with one CSI report configuration may be associated with different number of CPUs (i.e., NCPU) , and/or computation timing (which may be represented as Z and/or Zref, and also may include Z’/Z’ref) . For the simultaneous multiple CSI and/or jointly applied sub-configurations, NCPU and Z/Zref can take a larger value.

In the following, since Zref is function of Z, the discussion below only provides example based on Z.

In some embodiments, NCPU and Z/Zref of a CSI report out of multiple CSI may be associated with a sub-configuration ID of the corresponding CSI report configuration, e.g., NCPU_subConfig_i and Z_subConfig_i (Zref__subConfig_i) .

Further, the exact value of a sub-configuration ID may be based on pre-definition, UE class, or based on UE capability reporting. Alternatively, the exact value of a sub-configuration ID may be based on requirements of different AI/ML model management stages, which may be included in AI/ML model description.

For this corresponding CSI report configuration, a maximum supported NCPU or Z may be also defined (less than the sum) , for example, max_NCPU <= SUM (NCPU_subConfig_i) , max_Z <= SUM (Z_subConfig_i) , where i = 1, …, N sub-configurations.

In addition, in some embodiments, the NCPU_subConfig_i are occupied for a number of OFDM symbols as follows: from the first symbol of the earliest one of each RS resource corresponding to NCPU_subConfig_i, until the last symbol of the configured PUSCH/PUCCH carrying the report.

In some embodiments, the applied value of NCPU and Z/Zref of a CSI report may be different based on the joint application or the separate application of sub-configurations.

Specifically, in case of simultaneous multiple CSI and/or joint sub-configurations, NCPU = SUM (NCPU_subConfig_i) , where i = 1, …, N_s for all the jointly applied sub-configurations, or NCPU = MAX (NCPU_subConfig_i) , where i = 1, …, N_s for all the jointly applied sub-configurations, or NCPU_joint is defined as NCPU_joint > NCPU_subConfig_i.

In addition, the NCPU are occupied for a number of OFDM symbols as follows: from the first symbol of the earliest one of each RS resource for N_s sub-configurations, until the last symbol of the configured PUSCH/PUCCH carrying the report.

In some embodiments, the processing time Z = SUM (Z_subConfig_i) , where i = 1, …, N_s for all the jointly applied sub-configurations, or Z = MAX (Z_subConfig_i) , where i = 1, …, N_s for all the jointly applied sub-configurations, or Z_joint is defined as Z_joint >Z_subConfig_i.

In some embodiments, for a resource associated with multiple (e.g., K) sub-configurations, if it is counted K times, then for each sub-configuration, the measurement/computation method corresponding to this resource may be different. Alternatively, it is counted once if the measurement/computation method corresponding to this resource is the same for different sub-configuration.

In some embodiments, the CSI reports are associated with a priority value based on information about sub-configuration, e.g., sub-configuration ID, Max number of sub-configurations, and so on. In this way, the collided CSI reports/CSIs may be avoided.

In some embodiments, the CSI reports (CSIs) may be associated with a priority value based on information about sub-configuration, e.g., sub-configuration ID.

Usually, sub-configuration ID may be signaled by the network device 120. Further, for AI/ML model application, the priority may be also based on AI/ML related information, in this case, the order of sub-configuration IDs may need to be aligned with the priority of different AI/ML related aspects, for example, AI based CSI report has a higher (or a lower) sub-configuration ID, compared to the sub-configuration ID of non-AI based CSI report.

In some embodiments, the CSI report for AI model monitoring has a higher (or a lower) sub-configuration ID, compared to the sub-configuration ID of CSI report for AI model training.

In some embodiments, the maximum number of sub-configurations associated with a reportConfigID, which may be based on UE capability reporting or requirement of AI/ML model management, included in AI/ML model description.

In some embodiments, simultaneous multiple CSI or joint sub-configurations may has a higher priority, that is, if a CSI report carries more than one CSI, the priority is higher. In other words, the priority is based on the number of multiple CSI carried in one CSI report.

In some embodiments, the CSI reports are associated with a priority value Pri_iCSI (y, k, c, s, n) =2·N_cells·M_s·y+N_cells·M_s·k+M_s·c+N_sub·s+n, where y=0 for aperiodic CSI reports to be carried on PUSCH y=1 for semi-persistent CSI reports to be carried on PUSCH, y=2 for semi-persistent CSI reports to be carried on PUCCH and y=3 for periodic CSI reports to be carried on PUCCH; k=0 for CSI reports carrying L1-RSRP or L1-SINR and k=1 for CSI reports not carrying L1-RSRP or L1-SINR; c is the serving cell index and N_cells is the value of the higher layer parameter maxNrofServingCells; s is the reportConfigID and M_s is the value of the higher layer parameter maxNrofCSI-ReportConfigurations. Further, n is the sub-configuration ID and N_sub is the value of the max number of sub-configurations associated with a reportConfigID.

In the above example, a first CSI report is said to have priority over a second CSI report if the associated Pri_iCSI (y, k, c, s, n) value is lower for the first report than for the second report. That is, a higher priority is associated with a lower priority value.

Example methods

FIG. 4 illustrates a flowchart of a communication method 400 implemented at a terminal device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 400 will be described from the perspective of the terminal device 110 in FIG. 1.

At block 410, the terminal device receives, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations. The plurality of sub-configurations comprise: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage. Alternatively, the plurality of sub-configurations comprise: the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with CSI for the second usage.

At block 420, the terminal device transmits to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.

In some example embodiments, a subset of the plurality of sub-configurations support to be activated jointly, or the plurality of sub-configurations corresponding to a plurality of CSIs, a subset of the plurality of CSIs support to be comprised in one CSI report or comprised in more than one CSI report within a time window.

In some example embodiments, the report configuration further indicates at least one of the following: first information about the subset of the plurality of sub-configurations, or second information about subset of the plurality of CSIs.

In some example embodiments, the CSI report configuration further comprises a main configuration, and wherein if a configuration parameter is absent in a sub-configuration, determine a first value of the configuration parameter to be a second value of a corresponding configuration parameter comprised in main configuration.

In some example embodiments, one of the plurality of sub-configurations is configured as a default sub-configuration or a fallback sub-configuration.

In some example embodiments, any of the fallback sub-configuration or the default sub-configuration is configured to be one of the following: the first sub-configuration, or a sub-configuration with the lowest or highest identity.

In some example embodiments, the CSI report configuration is associated with at least one of the following: an AI model or an AI functionality, and wherein the second sub-configuration and the third sub-configuration are associated with at least one of the following: two different management stages, two different types of CSI, two different AI models.

In some example embodiments, the sub-configuration comprises at least one of the following: a first parameter indicating a usage of the sub-configuration, a second parameter indicating a model identity associated with the sub-configuration.

In some example embodiments, the CSI determined based on one or more of the plurality of sub-configurations is multi-CSI, and the multi-CSI comprises at least two of the following: first CSI comprising raw channel, second CSI comprising compressed CSI, or third CSI comprising codebook-based CSI.

In some example embodiments, in case of model training data collection, the multi-CSI comprises: the first CSI or third CSI which is used as model input, and the second CSI which is used as model output, in case of model monitoring, the multi-CSI comprises: the second CSI which is used for inference, the first CSI or third CSI which is used for collecting ground truth data, in case of model switching or model selection, the multi-CSI comprises: different second CSIs corresponding to different AI models.

In some example embodiments, the CSI determined based on one or more of the plurality of sub-configurations is multi-CSI, and the multi-CSI comprises at least two of the following: first CSI comprising historical CSI, second CSI comprising predicted CSI, or third CSI comprising codebook-based CSI.

In some example embodiments, in case of model training data collection, the multi-CSI comprises: the first CSI or third CSI which is used as model input, and the second CSI which is used as model output, in case of model monitoring, the multi-CSI comprises: the second CSI which is used for inference, the third CSI which is used for collecting ground truth data, in case of model switching or model selection, the multi-CSI comprises: different second CSIs corresponding to different AI models.

In some example embodiments, the CSI determined based on one or more of the plurality of sub-configurations is a multi-beam report, and the multi-beam report comprises at least two of the following: a first beam report comprising measurement results corresponding to a first beam set, a second beam report comprising predicted beam, or a third beam report comprising measurement results corresponding to a second beam set.

In some example embodiments, in case of model training data collection, the multi-beam report comprises: the first beam report which is used as model input, and the second beam report or third beam report which is used as model output, in case of model monitoring, the multi-beam report comprises: the second beam report which is used for inference, the third beam report which is used for collecting ground truth data, in case of model switching or model selection, the multi-beam report comprises: different second beam reports corresponding to different AI models.

In some example embodiments, the CSI determined based on one or more of the plurality of sub-configurations is a multi-beam report, and the multi-beam report comprises at least two of the following: a first beam report comprising historical measurement results corresponding to a first beam set, a second beam report comprising predicted beam, or a third beam report comprising historical measurement results corresponding to a second beam set, a fourth beam report comprising measurement results corresponding to the first beam set or the second beam set.

In some example embodiments, in case of model training data collection, the multi-beam report comprises: the first beam report which is used as model input, and the second beam report or third beam report which is used as model output, in case of model monitoring, the multi-beam report comprises: the second beam report which is used for inference, the fourth beam report which is used for collecting ground truth data, in case of model switching or model selection, the multi-beam report comprises: different second beam reports corresponding to different AI models.

In some example embodiments, the plurality of sub-configurations is associated with the same or different CSI RS resources.

In some example embodiments, the terminal device 110 may activate or deactivate one or more of the plurality of sub-configurations.

In some example embodiments, the terminal device may keep valid of the CSI report configuration regardless of a deactivation of a sub-configuration of the plurality of sub-configurations.

In some example embodiments, during a period from receiving the CSI report configuration and the first activation of at least one sub-configuration, the terminal device may validate 220 one of the following: none of the plurality of sub-configurations, all the plurality of sub-configurations, or a default sub-configuration of the plurality of sub-configurations.

In some example embodiments, the terminal device may receive, from the network device, a first indication used for enabling or disabling an adaptive activation or deactivation of sub-configuration, or transmit, to the network device, a second indication used for indicating whether an adaptive activation or deactivation of sub-configuration is supported by the terminal device.

In some example embodiments, the terminal device 110 may activate or deactivate one or more of the plurality of sub-configurations based on at least one activation/deactivation condition associated with an artificial intelligence (AI) model.

In some example embodiments, the terminal device may determine at least one association between at least one sub-configuration and at least one activation/deactivation condition.

In some example embodiments, the association is defined as default configuration, configured by the network device or reported by the terminal device.

In some example embodiments, the terminal device may receive 225, from the network device, a message used for activating or deactivating the one or more sub-configurations being one of the following: a first messaged explicitly indicating the terminal device to activate or deactivate the one or more sub-configurations, or a life cycle management (LCM) signalling.

In some example embodiments, the terminal device may reuse the first message as an LCM signalling.

In some example embodiments, the terminal device may skip a subset of the plurality of sub-configurations based on at least one of the following: a first maximum number of sub-configurations allowed to be skipped, a first minimum number of non-skipped sub-configurations supported by the terminal device or the network device, a second maximum number of jointly-applied sub-configurations allowed to be skipped, or a second minimum number of non-skipped jointly-applied sub-configurations supported by the terminal device or the network device.

In some example embodiments, at least one of the first maximum number, the second maximum number, the first the minimum number or the second the minimum number is defined as default configuration, configured by the network device or reported by the terminal device.

In some example embodiments, the terminal device may receive, from the network device, a third indication used for enabling or disabling the skipping a sub-configuration or a jointly-applied sub-configuration, or transmit, to the network device, a fourth indication used for indicating whether the skipping the sub-configuration or the jointly-applied sub-configuration is supported by the terminal device.

In some example embodiments, the terminal device may skip the subset of the plurality of sub-configurations associated with at least one of the following: an AI management stage, an AI functionality, or an AI model.

In some example embodiments, the terminal device may transmit, a message to the network device, the message indicating at least one of the following: at least one skipped sub-configuration, at least one AI management stage associated with at least one skipped sub-configuration, at least one AI functionality associated with at least one skipped sub-configuration, or at least one AI model associated with at least one skipped sub-configuration.

In some example embodiments, the first usage is a non-artificial intelligence (non-AI) usage and the second usage is an AI-based usage.

FIG. 5 illustrates a flowchart of a communication method 500 implemented at a terminal device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 500 will be described from the perspective of the terminal device 110 in FIG. 1.

At block 510, the terminal device receives, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations.

At block 520, the terminal device transmits to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, wherein at least one of the following is associated with an identity of a sub-configuration: a CSI processing time, the number of CSI processing units (CPUs) , or a CSI report priority.

In some example embodiments, a duration occupied by at least one CPU corresponding to a sub-configuration starts from the first symbol of the earliest one of each RS resource corresponding to sub-configuration until the last symbol of the configured uplink resources carrying the CSI report.

In some example embodiments, if the CSI comprised in the CSI report is a simultaneous multi-CSI, or the one or more sub-configurations are jointly activated, the number of CPUs for the CSI report is determined to be one of the following: a sum of the numbers of CPUs corresponding to the one or more sub-configurations, the maximum number of the numbers of CPUs, or a defined number less than the sum of the numbers of CPUs, and a CSI processing time for the CSI report is determined to be one of the following: a sum of CSI processing time corresponding to the one or more sub-configurations, the maximum of the CSI processing times, or a defined processing time less than the sum of the sum of CSI processing time.

In some example embodiments, a duration occupied by CPUs corresponding to the CSI report starts from the first symbol of first symbol of the earliest RS resource corresponding to the CSI report until the last symbol of the configured uplink carrying the CSI report.

In some example embodiments, the CSI report priority is further associated with the maximum number of sub-configurations associated with the CSI report configuration.

In some example embodiments, a priority of a CSI report with multi-CSI is higher than a CSI report with single CSI.

FIG. 6 illustrates a flowchart of a communication method 600 implemented at a network device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 600 will be described from the perspective of the network device 120 in FIG. 1.

At block 610, the network device transmits, to the terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations, wherein the plurality of sub-configurations comprise at least one of the following: a first sub- configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with the second usage.

At block 620, the network device receives from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.

In some example embodiments, one of the plurality of sub-configurations is configured as a sub-default configuration or a fallback sub-configuration.

In some example embodiments, any of the fallback configuration or the sub-default configuration is configured to be one of the following: the first sub-configuration, or a sub-configuration with the lowest or highest identity.

In some example embodiments, the CSI determined based on one or more of the plurality of sub-configurations is a multi-beam report, and the multi-beam report comprises at least two of the following: a first beam report comprising historical measurement results corresponding to a first beam set, a second beam report comprising predicted beam, a third beam report comprising historical measurement results corresponding to a second beam set, or a fourth beam report comprising measurement results corresponding to the first beam set or the second beam set.

In some example embodiments, the first usage is a non-artificial intelligence (non-AI) usage and the second usage is an AI-based usage .

In some example embodiments, the network device may transmit, to a terminal device, a message used for activating or deactivating the one or more sub-configurations.

In some example embodiments, the message used for activating or deactivating the one or more sub-configurations is one of the following: a first messaged explicitly indicating the terminal device to activate or deactivate the one or more sub-configurations, or a life cycle management (LCM) signalling.

In some example embodiments, the network device may receive, from the network device, a first indication used for enabling or disabling an adaptive activation or deactivation of sub-configuration, or transmit, to the network device, a second indication used for indicating whether an adaptive activation or deactivation of sub-configuration is supported by the terminal device.

In some example embodiments, the network device may receive, a message from the terminal device, the message indicating at least one of the following: at least one skipped sub-configuration, at least one AI management stage associated with at least one skipped sub-configuration, at least one AI functionality associated with at least one skipped sub-configuration, or at least one AI model associated with at least one skipped sub-configuration.

In some example embodiments, the network device may receive, from the network device, a third indication used for enabling or disabling skipping a sub-configuration or a jointly-applied sub-configuration, or transmit, to the network device, a fourth indication used for indicating whether the skipping the sub-configuration or the jointly-applied sub-configuration is supported by the terminal device.

FIG. 7 illustrates a flowchart of a communication method 700 implemented at a network device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 700 will be described from the perspective of the network device in FIG. 1.

At block 710, the network device transmits, to a terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations.

At block 720, the network device receives from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, wherein at least one of the following is associated with an identity of a sub-configuration: a CSI processing time, the number of CSI processing units (CPUs) , or a CSI report priority.

Example apparatuses and devices

FIG. 8 is a simplified block diagram of a device 800 that is suitable for implementing embodiments of the present disclosure. The device 800 can be considered as a further example implementation of any of the devices as shown in FIG. 1. Accordingly, the device 800 can be implemented at or as at least a part of the terminal device 110 or the network device 120.

As shown, the device 800 includes a processor 810, a memory 820 coupled to the processor 810, a suitable transceiver 840 coupled to the processor 810, and a communication interface coupled to the transceiver 840. The memory 820 stores at least a part of a program 830. The transceiver 840 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 840 may include at least one of a transmitter 842 and a receiver 844. The transmitter 842 and the receiver 844 may be functional modules or physical entities. The transceiver 840 has at least one antenna to facilitate communication, though in practice an Access Node mentioned in this application may have several ones. The communication interface may represent any interface that is necessary for communication with other network elements, such as X2/Xn interface for bidirectional communications between eNBs/gNBs, S1/NG interface for communication between a Mobility Management Entity (MME) /Access and Mobility Management Function (AMF) /SGW/UPF and the eNB/gNB, Un interface for communication between the eNB/gNB and a relay node (RN) , or Uu interface for communication between the eNB/gNB and a terminal device.

The program 830 is assumed to include program instructions that, when executed by the associated processor 810, enable the device 800 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGS. 1 to 8. The embodiments herein may be implemented by computer software executable by the processor 810 of the device 800, or by hardware, or by a combination of software and hardware. The processor 810 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 810 and memory 820 may form processing means 850 adapted to implement various embodiments of the present disclosure.

The memory 820 may be of any type suitable to the local technical network and may be implemented using any suitable data storage technology, such as a non-transitory computer readable storage medium, semiconductor based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory, as non-limiting examples. While only one memory 820 is shown in the device 800, there may be several physically distinct memory modules in the device 800. The processor 810 may be of any type suitable to the local technical network, and may include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 800 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.

According to embodiments of the present disclosure, a terminal device comprising a circuitry is provided. The circuitry is configured to: receive, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations, wherein the plurality of sub-configurations comprise at least one of the following: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with CSI for the second usage; and transmit to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the terminal device as discussed above.

According to embodiments of the present disclosure, a terminal device comprising a circuitry is provided. The circuitry is configured to: receive, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations; transmit to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, wherein at least one of the following is associated with an identity of a sub-configuration: a CSI processing time, the number of CSI processing units (CPUs) , or a CSI report priority. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the terminal device as discussed above.

According to embodiments of the present disclosure, a network device comprising a circuitry is provided. The circuitry is configured to: transmit, to the terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations, wherein the plurality of sub-configurations comprise at least one of the following: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with the second usage; and receive from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the network device as discussed above.

According to embodiments of the present disclosure, a network device comprising a circuitry is provided. The circuitry is configured to: transmit, to a terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations; receive from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, wherein at least one of the following is associated with an identity of a sub-configuration: a CSI processing time, the number of CSI processing units (CPUs) , or a CSI report priority. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the network device as discussed above.

The term “circuitry” used herein may refer to hardware circuits and/or combinations of hardware circuits and software. For example, the circuitry may be a combination of analog and/or digital hardware circuits with software/firmware. As a further example, the circuitry may be any portions of hardware processors with software including digital signal processor (s) , software, and memory (ies) that work together to cause an apparatus, such as a terminal device or a network device, to perform various functions. In a still further example, the circuitry may be hardware circuits and or processors, such as a microprocessor or a portion of a microprocessor, that requires software/firmware for operation, but the software may not be present when it is not needed for operation. As used herein, the term circuitry also covers an implementation of merely a hardware circuit or processor (s) or a portion of a hardware circuit or processor (s) and its (or their) accompanying software and/or firmware.

According to embodiments of the present disclosure, a terminal apparatus is provided. The terminal apparatus comprises means for receiving, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations, means for wherein the plurality of sub-configurations comprise at least one of the following: means for a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or means for the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with CSI for the second usage; and means for transmitting to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations. In some embodiments, the first apparatus may comprise means for performing the respective operations of the method 400. In some example embodiments, the first apparatus may further comprise means for performing other operations in some example embodiments of the method 400. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

According to embodiments of the present disclosure, a terminal apparatus is provided. The terminal apparatus comprises means for receiving, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations; means for transmitting to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, means for wherein at least one of the following is associated with an identity of a sub-configuration: means for a CSI processing time, means for the number of CSI processing units (CPUs) , or means for a CSI report priority. In some embodiments, the second apparatus may comprise means for performing the respective operations of the method 500. In some example embodiments, the second apparatus may further comprise means for performing other operations in some example embodiments of the method 500. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

According to embodiments of the present disclosure, a network apparatus is provided. The network apparatus comprises means for transmitting, to the terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations, means for wherein the plurality of sub-configurations comprise at least one of the following: means for a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or means for the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with the second usage; and means for receiving from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations. In some embodiments, the third apparatus may comprise means for performing the respective operations of the method 600. In some example embodiments, the third apparatus may further comprise means for performing other operations in some example embodiments of the method 600. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

According to embodiments of the present disclosure, a network apparatus is provided. The network apparatus comprises means for transmitting, to a terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations; means for receiving from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, means for wherein at least one of the following is associated with an identity of a sub-configuration: means for a CSI processing time, means for the number of CSI processing units (CPUs) , or means for a CSI report priority. In some embodiments, the fourth apparatus may comprise means for performing the respective operations of the method 700. In some example embodiments, the fourth apparatus may further comprise means for performing other operations in some example embodiments of the method 700. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

In summary, embodiments of the present disclosure provide the following aspects.

In an aspect, it is proposed a terminal device comprising: a processor configured to cause the terminal device to: receive, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations, wherein the plurality of sub-configurations comprise at least one of the following: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with CSI for the second usage; and transmit to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.

In some embodiments, a subset of the plurality of sub-configurations support to be activated jointly, or the plurality of sub-configurations corresponding to a plurality of CSIs, a subset of the plurality of CSIs support to be comprised in one CSI report or comprised in more than one CSI report within a time window.

In some embodiments, the report configuration further indicates at least one of the following: first information about the subset of the plurality of sub-configurations, or second information about subset of the plurality of CSIs.

In some embodiments, the CSI report configuration further comprises a main configuration, and wherein if a configuration parameter is absent in a sub-configuration, determine a first value of the configuration parameter to be a second value of a corresponding configuration parameter comprised in main configuration.

In some embodiments, one of the plurality of sub-configurations is configured as a default sub-configuration or a fallback sub-configuration.

In some embodiments, the CSI report configuration is associated with at least one of the following: an AI model or an AI functionality, and wherein the second sub-configuration and the third sub-configuration are associated with at least one of the following: two different management stages, two different types of CSI, two different AI models.

In some embodiments, the sub-configuration comprises at least one of the following: a first parameter indicating a usage of the sub-configuration, a second parameter indicating a model identity associated with the sub-configuration.

In some embodiments, the CSI determined based on one or more of the plurality of sub-configurations is multi-CSI, and the multi-CSI comprises at least two of the following: first CSI comprising raw channel, second CSI comprising compressed CSI, or third CSI comprising codebook-based CSI.

In some embodiments, in case of model training data collection, the multi-CSI comprises: the first CSI or third CSI which is used as model input, and the second CSI which is used as model output, in case of model monitoring, the multi-CSI comprises: the second CSI which is used for inference, the first CSI or third CSI which is used for collecting ground truth data, in case of model switching or model selection, the multi-CSI comprises: different second CSIs corresponding to different AI models.

In some embodiments, the CSI determined based on one or more of the plurality of sub-configurations is multi-CSI, and the multi-CSI comprises at least two of the following: first CSI comprising historical CSI, second CSI comprising predicted CSI, or third CSI comprising codebook-based CSI.

In some embodiments, in case of model training data collection, the multi-CSI comprises: the first CSI or third CSI which is used as model input, and the second CSI which is used as model output, in case of model monitoring, the multi-CSI comprises: the second CSI which is used for inference, the third CSI which is used for collecting ground truth data, in case of model switching or model selection, the multi-CSI comprises: different second CSIs corresponding to different AI models.

In some embodiments, the CSI determined based on one or more of the plurality of sub-configurations is a multi-beam report, and the multi-beam report comprises at least two of the following: a first beam report comprising measurement results corresponding to a first beam set, a second beam report comprising predicted beam, or a third beam report comprising measurement results corresponding to a second beam set.

In some embodiments, in case of model training data collection, the multi-beam report comprises: the first beam report which is used as model input, and the second beam report or third beam report which is used as model output, in case of model monitoring, the multi-beam report comprises: the second beam report which is used for inference, the third beam report which is used for collecting ground truth data, in case of model switching or model selection, the multi-beam report comprises: different second beam reports corresponding to different AI models.

In some embodiments, the CSI determined based on one or more of the plurality of sub-configurations is a multi-beam report, and the multi-beam report comprises at least two of the following: a first beam report comprising historical measurement results corresponding to a first beam set, a second beam report comprising predicted beam, a third beam report comprising historical measurement results corresponding to a second beam set, or a fourth beam report comprising measurement results corresponding to the first beam set or the second beam set.

In some embodiments, in case of model training data collection, the multi-beam report comprises: the first beam report which is used as model input, and the second beam report or third beam report which is used as model output, in case of model monitoring, the multi-beam report comprises: the second beam report which is used for inference, the fourth beam report which is used for collecting ground truth data, in case of model switching or model selection, the multi-beam report comprises: different second beam reports corresponding to different AI models.

In some embodiments, the plurality of sub-configurations is associated with the same or different CSI RS resources.

In some embodiments, the processor is further configured to cause the terminal device to: activate or deactivate one or more of the plurality of sub-configurations.

In some embodiments, the processor is further configured to cause the terminal device to: keep valid of the CSI report configuration regardless of a deactivation of a sub-configuration of the plurality of sub-configurations.

In some embodiments, the processor is further configured to cause the terminal device to: during a period from receiving the CSI report configuration and the first activation of at least one sub-configuration, validate one of the following: none of the plurality of sub-configurations, all the plurality of sub-configurations, or a default sub-configuration of the plurality of sub-configurations.

In some embodiments, the processor is further configured to cause the terminal device to: receive, from the network device, a first indication used for enabling or disabling an adaptive activation or deactivation of sub-configuration, or transmit, to the network device, a second indication used for indicating whether an adaptive activation or deactivation of sub-configuration is supported by the terminal device.

In some embodiments, the processor is further configured to cause the terminal device to: activate or deactivate one or more of the plurality of sub-configurations based on at least one activation/deactivation condition associated with an artificial intelligence (AI) model.

In some embodiments, the processor is further configured to cause the terminal device to: determine at least one association between at least one sub-configuration and at least one activation/deactivation condition.

In some embodiments, the association is defined as default configuration, configured by the network device or reported by the terminal device.

In some embodiments, the processor is further configured to cause the terminal device to: receive, from the network device, a message used for activating or deactivating the one or more sub-configurations being one of the following: a first messaged explicitly indicating the terminal device to activate or deactivate the one or more sub-configurations, or a life cycle management (LCM) signalling.

In some embodiments, the processor is further configured to cause the terminal device to: reuse the first message as an LCM signalling.

In some embodiments, the processor is further configured to cause the terminal device to: skip a subset of the plurality of sub-configurations based on at least one of the following: a first maximum number of sub-configurations allowed to be skipped, a first minimum number of non-skipped sub-configurations supported by the terminal device or the network device, a second maximum number of jointly-applied sub-configurations allowed to be skipped, or a second minimum number of non-skipped jointly-applied sub-configurations supported by the terminal device or the network device.

In some embodiments, at least one of the first maximum number, the second maximum number, the first the minimum number or the second the minimum number is defined as default configuration, configured by the network device or reported by the terminal device.

In some embodiments, the processor is further configured to cause the terminal device to: receive, from the network device, a third indication used for enabling or disabling the skipping a sub-configuration or a jointly-applied sub-configuration, or transmit, to the network device, a fourth indication used for indicating whether the skipping the sub-configuration or the jointly-applied sub-configuration is supported by the terminal device.

In some embodiments, the processor is further configured to cause the terminal device to: skip the subset of the plurality of sub-configurations associated with at least one of the following: an AI management stage, an AI functionality, or an AI model.

In some embodiments, the processor is further configured to cause the terminal device to: transmit, a message to the network device, the message indicating at least one of the following: at least one skipped sub-configuration, at least one AI management stage associated with at least one skipped sub-configuration, at least one AI functionality associated with at least one skipped sub-configuration, or at least one AI model associated with at least one skipped sub-configuration.

In some embodiments, the first usage is a non-artificial intelligence (non-AI) usage and the second usage is an AI-based usage.

In an aspect, it is proposed a terminal device comprising: a processor configured to cause the terminal device to: receive, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations; transmit to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, wherein at least one of the following is associated with an identity of a sub-configuration: a CSI processing time, the number of CSI processing units (CPUs) , or a CSI report priority.

In some embodiments, a duration occupied by at least one CPU corresponding to a sub-configuration starts from the first symbol of the earliest one of each RS resource corresponding to sub-configuration until the last symbol of the configured uplink resources carrying the CSI report.

In some embodiments, if the CSI comprised in the CSI report is a simultaneous multi-CSI, or the one or more sub-configurations are jointly activated, the number of CPUs for the CSI report is determined to be one of the following: a sum of the numbers of CPUs corresponding to the one or more sub-configurations, the maximum number of the numbers of CPUs, or a defined number less than the sum of the numbers of CPUs, and a CSI processing time for the CSI report is determined to be one of the following: a sum of CSI processing time corresponding to the one or more sub-configurations, the maximum of the CSI processing times, or a defined processing time less than the sum of the sum of CSI processing time.

In some embodiments, a duration occupied by CPUs corresponding to the CSI report starts from the first symbol of first symbol of the earliest RS resource corresponding to the CSI report until the last symbol of the configured uplink carrying the CSI report.

In some embodiments, the CSI report priority is further associated with the maximum number of sub-configurations associated with the CSI report configuration.

In some embodiments, a priority of a CSI report with multi-CSI is higher than a CSI report with single CSI.

In an aspect, it is proposed a network device comprising: a processor configured to cause the network device to: transmit, to the terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations, wherein the plurality of sub-configurations comprise at least one of the following: a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with the second usage; and receive from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.

In some embodiments, one of the plurality of sub-configurations is configured as a sub-default configuration or a fallback sub-configuration.

In some embodiments, any of the fallback configuration or the sub-default configuration is configured to be one of the following: the first sub-configuration, or a sub-configuration with the lowest or highest identity.

In some embodiments, in case of model training data collection, the multi-beam report comprises: the first beam report which is used as model input, and the second beam report or third beam report which is used as model output, in case of model monitoring, the multi- beam report comprises: the second beam report which is used for inference, the fourth beam report which is used for collecting ground truth data, in case of model switching or model selection, the multi-beam report comprises: different second beam reports corresponding to different AI models.

In some embodiments, the first usage is a non-artificial intelligence (non-AI) usage and the second usage is an AI-based usage .

In some embodiments, the processor is further configured to cause the network device to: transmit, to a terminal device, a message used for activating or deactivating the one or more sub-configurations.

In some embodiments, the message used for activating or deactivating the one or more sub-configurations is one of the following: a first messaged explicitly indicating the terminal device to activate or deactivate the one or more sub-configurations, or a life cycle management (LCM) signalling.

In some embodiments, the processor is further configured to cause the network device to: receive, from the network device, a first indication used for enabling or disabling an adaptive activation or deactivation of sub-configuration, or transmit, to the network device, a second indication used for indicating whether an adaptive activation or deactivation of sub-configuration is supported by the terminal device.

In some embodiments, the processor is further configured to cause the network device to: receive, a message from the terminal device, the message indicating at least one of the following: at least one skipped sub-configuration, at least one AI management stage associated with at least one skipped sub-configuration, at least one AI functionality associated with at least one skipped sub-configuration, or at least one AI model associated with at least one skipped sub-configuration.

In some embodiments, the processor is further configured to cause the network device to: receive, from the network device, a third indication used for enabling or disabling skipping a sub-configuration or a jointly-applied sub-configuration, or transmit, to the network device, a fourth indication used for indicating whether the skipping the sub-configuration or the jointly-applied sub-configuration is supported by the terminal device.

In an aspect, it is proposed a network device comprising: a processor configured to cause the network device to: transmit, to a terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations; receive from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations, wherein at least one of the following is associated with an identity of a sub-configuration: a CSI processing time, the number of CSI processing units (CPUs) , or a CSI report priority.

In an aspect, a terminal device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the device to perform the method implemented by the terminal device discussed above.

In an aspect, a network device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the device to perform the method implemented by the network device discussed above.

In an aspect, a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the terminal device discussed above.

In an aspect, a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the network device discussed above.

In an aspect, a computer program comprising instructions, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the terminal device discussed above.

In an aspect, a computer program comprising instructions, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the network device discussed above.

Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representation, it will be appreciated that the blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, being executed in a device on a target real or virtual processor, to carry out the process or method as described above with reference to FIGS. 1 to 8. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowcharts and/or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

The above program code may be embodied on a machine readable medium, which may be any tangible medium that may contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine readable medium may be a machine readable signal medium or a machine readable storage medium. A machine readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM) , a read-only memory (ROM) , an erasable programmable read-only memory (EPROM or Flash memory) , an optical fiber, a portable compact disc read-only memory (CD-ROM) , an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable sub-combination.

Although the present disclosure has been described in language specific to structural features and/or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

A terminal device comprising:

a processor configured to cause the terminal device to:

receive, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations,

wherein the plurality of sub-configurations comprise at least one of the following:

a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or

the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with CSI for the second usage; and

transmit to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.
The terminal device of claim 1, wherein,

a subset of the plurality of sub-configurations support to be activated jointly, or

a plurality of sub-configurations corresponding to a plurality of CSIs, a subset of the plurality of CSIs support to be comprised in one CSI report or comprised in more than one CSI report within a time window.
The terminal device of claim 1, wherein the CSI report configuration further comprises a main configuration,

and wherein if a configuration parameter is absent in a sub-configuration, determine a first value of the configuration parameter to be a second value of a corresponding configuration parameter comprised in main configuration.
The terminal device of claim 1, wherein one of the plurality of sub-configurations is configured as a default sub-configuration or a fallback sub-configuration.
The terminal device of claim 1, wherein any of the fallback sub-configuration or the default sub-configuration is configured to be one of the following:

the first sub-configuration, or

a sub-configuration with the lowest or highest identity.
The terminal device of claim 1, wherein the CSI report configuration is associated with at least one of the following: an AI model or an AI functionality,

and wherein the second sub-configuration and the third sub-configuration are associated with at least one of the following:

two different management stages,

two different types of CSI, or

two different AI models.
The terminal device of claim 1, wherein the sub-configuration comprises at least one of the following:

a first parameter indicating a usage of the sub-configuration, or

a second parameter indicating a model identity associated with the sub-configuration.
The terminal device of claim 1, wherein the processor is further configured to cause the terminal device to:

activate or deactivate one or more of the plurality of sub-configurations.
The terminal device of claim 8, wherein the processor is further configured to cause the terminal device to:

during a period from receiving the CSI report configuration and the first activation of at least one sub-configuration, validate one of the following:

none of the plurality of sub-configurations,

all the plurality of sub-configurations, or

a default sub-configuration of the plurality of sub-configurations.
The terminal device of claim 8, wherein the processor is further configured to cause the terminal device to:

activate or deactivate one or more of the plurality of sub-configurations based on at least one activation/deactivation condition associated with an artificial intelligence (AI) model.
The terminal device of claim 8, wherein the processor is further configured to cause the terminal device to:

receive, from the network device, a message used for activating or deactivating the one or more sub-configurations being one of the following:

a first messaged explicitly indicating the terminal device to activate or deactivate the one or more sub-configurations, or

a life cycle management (LCM) signalling.
The terminal device of claim 11, wherein the processor is further configured to cause the terminal device to:

reuse the first message as an LCM signalling.
The terminal device of claim 8, wherein the processor is further configured to cause the terminal device to:

skip a subset of the plurality of sub-configurations based on at least one of the following:

a first maximum number of sub-configurations allowed to be skipped,

a first minimum number of non-skipped sub-configurations supported by the terminal device or the network device,

a second maximum number of jointly-applied sub-configurations allowed to be skipped, or

a second minimum number of non-skipped jointly-applied sub-configurations supported by the terminal device or the network device.
The terminal device of claim 8, wherein the processor is further configured to cause the terminal device to:

transmit, a message to the network device, the message indicating at least one of the following:

at least one skipped sub-configuration,

at least one AI management stage associated with at least one skipped sub-configuration,

at least one AI functionality associated with at least one skipped sub-configuration, or

at least one AI model associated with at least one skipped sub-configuration.
The terminal device of claim 1, wherein the first usage is a non-artificial intelligence (non-AI) usage and the second usage is an AI-based usage.
A terminal device comprising:

a processor configured to cause the terminal device to:

receive, from a network device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations;

transmit to the network device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations,

wherein at least one of the following is associated with an identity of a sub-configuration:

a CSI processing time,

the number of CSI processing units (CPUs) , or

a CSI report priority.
The terminal device of claim 16, wherein if the CSI comprised in the CSI report is a simultaneous multi-CSI, or the one or more sub-configurations are jointly activated,

the number of CPUs for the CSI report is determined to be one of the following:

a sum of the numbers of CPUs corresponding to the one or more sub-configurations,

the maximum number of the numbers of CPUs, or

a defined number less than the sum of the numbers of CPUs,

and a CSI processing time for the CSI report is determined to be one of the following:

a sum of CSI processing time corresponding to the one or more sub-configurations,

the maximum of the CSI processing times, or

a defined processing time less than the sum of the sum of CSI processing time.
The terminal device of claim 16, wherein a duration occupied by CPUs corresponding to the CSI report starts from the first symbol of first symbol of the earliest RS resource corresponding to the CSI report until the last symbol of the configured uplink carrying the CSI report.
The terminal device of claim 16, wherein the CSI report priority is further associated with the maximum number of sub-configurations associated with the CSI report configuration.
A network device comprising:

a processor configured to cause the network device to:

transmit, to the terminal device, a channel state information (CSI) report configuration associated with a plurality of sub-configurations,

wherein the plurality of sub-configurations comprise at least one of the following:

a first sub-configuration and a second sub-configuration, the first sub-configuration being associated with CSI for a first usage and the second sub-configuration being associated with CSI for a second usage, or

the second sub-configuration and a third sub-configuration, both of the second and the third sub-configuration being associated with the second usage; and

receive from the terminal device at least one CSI report comprising CSI determined based on one or more of the plurality of sub-configurations.