Devices and methods for communication
Patent Information
- Application Number
- PCT/CN2025/083525
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-03-19
- Publication Date
- 2026-09-24
Smart Images

Figure CN2025083525_24092026_PF_FP_ABST
Abstract
Description
DEVICES AND METHODS FOR COMMUNICATIONFIELDS
[0001] Example embodiments of the present disclosure generally relate to the field of communication techniques and in particular, to devices and methods for communication.BACKGROUND
[0002] 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. In release 19 and release 20, AI / ML based beam management, channel state information (CSI) prediction and (temporal) CSI compression will be specified.SUMMARY
[0003] In general, embodiments of the present disclosure provide a solution for communication.
[0004] In a first aspect, there is provided a terminal device. The terminal device comprises: a processor configured to cause the terminal device to: receive, from a network device, at least one configuration of at least one monitoring report; for each layer or rank, determine at least one valid monitoring instance; and transmit the at least one monitoring report to the network device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition.
[0005] In a second aspect, there is provided a terminal device. The terminal device comprises: a processor configured to cause the terminal device to: receive, from a network device, at least one configuration of a monitoring report; and determine the monitoring report by using at least one processing unit, wherein in accordance with a determination that the monitoring report is associated with an inference report, the at least one processing unit comprises a first number of processing units, and the first number is determined based on a number of processing units occupied for measurement and / or reporting non-artificial intelligence (AI) / machine learning (ML) related information, and wherein in accordance with a determination that the monitoring report is not associated with an inference report, the at least one processing unit comprises a second number of processing units, and the second number is determined based on at least one of a number of processing units occupied for measurement and / or reporting AI / ML related information, or the first number.
[0006] In a third aspect, there is provided a network device. The network device comprises: a processor configured to cause the network device to: transmit, to a terminal device, at least one configuration of at least one monitoring report; and receive the at least one monitoring report from the terminal device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition.
[0007] In a fourth aspect, there is provided a communication method performed by a terminal device. The method comprises: receiving, from a network device, at least one configuration of at least one monitoring report; for each layer or rank, determining at least one valid monitoring instance; and transmitting the at least one monitoring report to the network device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition.
[0008] In a fifth aspect, there is provided a communication method performed by a terminal device. The method comprises: receiving, from a network device, at least one configuration of a monitoring report; and determining the monitoring report by using at least one processing unit, wherein in accordance with a determination that the monitoring report is associated with an inference report, the at least one processing unit comprises a first number of processing units, and the first number is determined based on a number of processing units occupied for measurement and / or reporting non-artificial intelligence (AI) / machine learning (ML) related information, and wherein in accordance with a determination that the monitoring report is not associated with an inference report, the at least one processing unit comprises a second number of processing units, and the second number is determined based on at least one of a number of processing units occupied for measurement and / or reporting AI / ML related information, or the first number.
[0009] In a sixth aspect, there is provided a communication method performed by a network device. The method comprises: transmitting, to a terminal device, at least one configuration of at least one monitoring report; and receiving the at least one monitoring report from the terminal device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition.
[0010] In a seventh 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 fourth, fifth, or sixth aspect.
[0011] Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS
[0012] 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:
[0013] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;
[0014] FIG. 2 illustrates a signaling flow of communication in accordance with some embodiments of the present disclosure;
[0015] FIG. 3 illustrates an example interaction process between UE and NW in accordance with some embodiments of the present disclosure;
[0016] FIG. 4 illustrates a flowchart of a communication method implemented at a terminal device according to some example embodiments of the present disclosure;
[0017] FIG. 5 illustrates a flowchart of a communication method implemented at a terminal device according to some example embodiments of the present disclosure;
[0018] FIG. 6 illustrates a flowchart of a communication method implemented at a network device according to some example embodiments of the present disclosure;
[0019] FIG. 7 illustrates a simplified block diagram of an apparatus that is suitable for implementing example embodiments of the present disclosure.
[0020] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION
[0021] 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.
[0022] 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.
[0023] 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 have ‘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.
[0024] 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. Further, the network device also may be an operation administration and maintenance (OAM) , a server, location management function (LMF) , access and mobility management function (AMF) , and other core network node.
[0025] The terminal device or the network device may have Artificial intelligence (AI) or Machine learning (ML) 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.
[0026] The terminal device 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.
[0027] 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.
[0028] 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.
[0029] 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.
[0030] 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.
[0031] One objective on AI / ML may provide specification support for CSI feedback enhancement, encompassing: CSI prediction (user equipment (UE) -sided model) : functionality-based life cycle management (LCM) leveraged from other use cases, when necessary and applicable; study, and if necessary, specify consistency of training / inference.
[0032] It has been agreed that for CSI prediction using UE-side model, at least for inference, Rel-18 CSI framework may be reused. For channel state information-reference signal (CSI-RS) resource type for channel measurement resource (CMR) , periodic, semi-persistent, and aperiodic CSI-RS may be supported. For inference report, for N4>=1, may support Rel-18 codebook ( 'typeII-Doppler-r18' ) .
[0033] For CSI prediction using UE-side model, for CSI processing criteria and timeline, at least for inference, may further study on: whether the CSI processing unit (CPU) should be shared or separately counted between legacy CSI reporting and AI / ML-based CSI reporting; whether the processing unit should be shared or separately counted among AI / ML related features / functionalities; whether new timeline is needed / updated for inference, and whether a different timeline is needed when functionality switches / activates; and whether legacy framework for active CSI-RS resource and port counting can be reused.
[0034] It has been agreed that for CSI prediction using UE-side model, for data collection for training, for resource configuration, for CSI-RS resource type for CMR, periodic and semi-persistent may be supported.
[0035] For CSI prediction using UE-side model, if performance monitoring type 1 or 3 is supported, for calculation of monitoring metric, may support, based on intermediate KPI, down select between squared generalized cosine similarity (SGCS) and normalized mean squared error (NMSE) .
[0036] For CSI prediction using UE-side model, for performance monitoring, may support one of following two types with down-selection: Type 1 performance monitoring: UE reports performance monitoring output; Type 3 performance monitoring: UE reports performance monitoring metric. Note: Support of Type 1 or Type 3 performance monitoring may be based on UE capability. If UE does not signal this capability, it may mean that performance monitoring may be achieved via Type2 monitoring with ground-truth reporting via legacy codebooks.
[0037] For CSI prediction using UE-side model, at least for type 3 performance monitoring if supported, may support to reuse CSI framework for configuration for monitoring report, may configure a dedicated CSI report for performance monitoring, and UE may measure the dedicated resource set (s) for monitoring if monitoring resource is aperiodic (AP) CSI-RS resource.
[0038] For better descriptions, some terms used herein are listed as below. Inference report may mean report configured for reporting information about inference results (e.g., CSI-RS resource indicator (CRI) , rank indicator (RI) , precoding matrix indicator (PMI) , channel quality indicator (CQI) ) . Monitoring report may mean report configured for reporting information about performance metric. Monitoring instance may be interchangeably with monitoring report. Inference instance may be interchangeably with inference report. High layer parameter may be interchangeably with information element (IE) , radio resource control (RRC) IE, RRC, medium access control (MAC) control element (CE) , downlink control information (DCI) .
[0039] ‘Information about A’ may mean information determined based on A, information related to A. Layer may mean multiple input multiple output (MIMO) layer, transmission layer. Rank may be interchangeably with RI, number of layers, layers.
[0040] UE capability (information) may mean information about capability reported by UE, or information about applicable / supported functionality (about AI / ML / model) reported by UE. It can be interchangeably with UE assistance information (UAI) .
[0041] Inference results associated with the monitoring instance may mean Inference results of the inference report associated with the monitoring instance, or inference results determined based on the measurement resource (s) associated with the monitoring instance. Field may be interchangeably with parameter, configuration, higher layer parameter / configuration, information element, signaling, indicator, information.
[0042] Monitoring instance may mean a time instance associated with a monitoring report, e.g., transmission occasion of a measurement resource (i.e., measurement instance) , CSI reference resource, or / and reporting instance associated with the monitoring report, or inference instance associated with an inference report associated with the monitoring report.
[0043] Inference instance may mean a time instance associated with a inference report, e.g., transmission occasion of a measurement or prediction resource (i.e., measurement or prediction instance) , CSI reference resource, or / and reporting instance associated with the monitoring report.
[0044] CSI may comprise at least one of: beam ID (or beam information) , CRI, synchronization signal block resource indicator (SSBRI) , reference signal received power (RSRP) , signal to interference plus noise ratio (SINR) , rank indicator (RI) , PMI, channel quality indicator (CQI) , layer indicator (LI) , i1, i2, compressed bits. Monitoring instance is invalid may mean that the inference results or / and measured results (i.e., ground-truth label) corresponding to the monitoring instance is not participate in the calculation or / and reporting of performance metric. In other words, UE may skip (or omit, ignore) the monitoring instance, or does not log or collect (the inference results or / and measured results (i.e., ground-truth label) corresponding to) the monitoring instance.
[0045] Monitoring report or inference report may be interchangeably with report for another LCM procedure. LCM procedure may comprise at least one of model inference, model identification, model training, model testing, model validation, model updating, model selection, model activation, model deactivation, performance (or model) monitoring, model switching, model development, model transfer / delivery, fallback (to non-AI / ML) .
[0046] (Time) instance may be interchangeably with time-domain resource (sub-frame number, system frame number, slot number, symbol number) , time point, time interval, future time instance, measurement time instance, reporting instance, transmission occasion, sample. Layer-1 may mean the first layer, or layer indicator is equal to 1. Rank-1 may mean the rank (or number of layers) is equal to 1.
[0047] Performance metric may comprise at least one of the following: -Top 1 or Top K (e.g., Top 1 / K, Top K / 1) beam prediction accuracy (with or without margin) by comparing the prediction results and the Top 1 or Top K beam based on the measurements from a resource set / resources for monitoring; -the L1-RSRP difference information based on actual measurement of the L1-RSRP of one or more of Top K predicted beam, and L1-RSRP measurements from a resource set / resources for monitoring; -the L1-RSRP difference information between the predicted L1-RSRP and measured L1-RSRP of corresponding beam (s) of a resource set / resources for monitoring; -the probability information of the predicted beam (s) to be the Top 1 or Top K beam; -the confidence information calculated from measured L1-RSRPs and predicted RSRPs for a resource set / resources for monitoring; -squared generalized cosine similarity (SGCS) or normalized mean square error (NMSE) between predicted (or recovered) CSI and measured (or target, input, actual) CSI. The CSI may be interchangeably with channel, precoding matrix, codebook.
[0048] CSI report may be interchangeably with report, monitoring report, inference report, measurement report, beam report, event triggered report, UE initiated repot. Threshold may be interchangeably with criterion, event, condition, comparison.
[0049] In the context of the present disclosure, the threshold may be a predefined value, or / and configured by network (NW) , or / and based on UE capability. ‘A is associated with B’ may be interchangeably with A / B corresponds B / A, A / B is linked B / A, A / B is equivalent to B / A, mapping A / B to B / A, A for B / A, A / B of B / A, A / B is determined based on B, A / B is applicable to B / A, A / B is related to B / A, A / B is about B / A, A / B include B / A, A / B indicate B / A.
[0050] Prediction beam set may mean that UE does not measure the beam (s) in the prediction beam set. ‘≤’ may be interchangeably with ‘<’ , ‘≥’ , ‘>’ , ‘=’ .
[0051] Model may be interchangeably with AI / ML, AI / ML model, AI / ML agent, functionality, AI / ML functionality, AI-enabled feature / FG (feature group) , dataset, NW-side or UE-side additional condition, condition, applicable condition, model structure, model parameter, reference model, proxy model, model description / meta information, UE part (of two-sided model) , NW part (of two-sided model) . It may mean a data driven algorithm that applies AI / ML techniques to generate a set of (AI / ML) outputs based on a set of (AI / ML) inputs.
[0052] AI / ML-enabled feature may refer to a feature where AI / ML may be used. Functionality may refer to an AI / ML-enabled Feature / FG enabled by configuration (s) , where configuration (s) is (are) supported based on conditions indicated by UE capability. Model may be associated with specific configurations / conditions associated with UE capability of an AI / ML-enabled Feature / FG and additional conditions (e.g., scenarios, sites, and datasets) as determined / identified between UE-side and NW-side.
[0053] Model may be represented by model ID, i.e., indication of functionality, model, dataset, cell, bandwidth part (BWP) , cell group / list, scenario, configuration, range, zone, area, sector, public land mobile network (PLMN) , mobile network operation (MNO) , mobile country code (MCC) , (mobile network code) MNC, location area code (LAC) , quantizer / quantization, dequantizer / dequantiztion, encoder, decoder. Model ID may be interchangeably with associated ID, functionality ID, dataset ID, scenario ID, zone ID, cell ID, PLMN ID, configuration ID, quantization ID, local (model) ID, global (model) ID, logical (model) ID, physical (model) ID, pairing ID, and so on.
[0054] Model inference may mean a process of using a trained AI / ML model to produce a set of outputs based on a set of inputs. Performance monitoring may mean a procedure that monitors the inference performance of the AI / ML model. It can be interchangeably with model monitoring, model / performance validation, model / performance testing.
[0055] Calculate may be interchangeably with measure, determine, count, obtain, tally, enumerate, make statistics, compare. Report may be interchangeably with sent, transmit, provide, indicate, inform. SGCS may be an example of performance metric, and it can be replaced with another performance metric (e.g., NMSE) .
[0056] Sample may be interchangeably with (time) instance, monitoring sample, monitoring (time) instance, inference (time) instance, inference sample. Omit may be interchangeably with skip, ignore, drop, not sent, not report. Information about A may comprise at least one of: value (e.g., quantized value) or range of A, or indication of comparison results between A and a threshold.
[0057] Precoding matrix may be interchangeably with PMI, channel, channel matrix, channel response, (channel) eigenvector, codebook (e.g., Type I Codebook, Type II Codebook, Enhanced Type II Codebook, Enhanced Type II codebook for predicted PMI) , compressed CSI (or bits) , CSI feedback bits, CSI.
[0058] Bitwidth may be interchangeably with (UCI) payload, bit length, bit size. Indicator may be interchangeably with ID, indication, identifier, identity, identification, index, bitmap, bit map, configuration, message. Include may be interchangeably with comprise, carry, indicate. Configure may be interchangeably with activate, indicate, trigger, provide, specify, update. Infer may be interchangeably with predict, output. Measure is interchangeably with collect, input.
[0059] UE may be interchangeably with NW, TRP, gNB, AP, OAM (server) , over the top (OTT) (server) , core network (CN) (server) , edge cloud (server) , (serving) cell, BWP.
[0060] Time window may be interchangeably with time offset, time gap, time duration, a period of time, timer, counter, monitoring window. The method (s) mentioned in different cases in the patent may be applicable across cases.
[0061] Principles and implementations of the present disclosure will be described in detail below with reference to the figures.
[0062] 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. It should be understood that, in the other embodiments, the terminal device 110 / network device 120 may be replaced with any of: a terminal device, a network device, an OTT (over the top, a server) , an operation administration and maintenance (OAM) (server) , an edge cloud (server) , a neutral site, transmission reception point (TRP) , or core network (CN, such as, location management function, LMF) and so on. In present disclosure is not limited in this regard.
[0063] In the example of FIG. 1, a direction from the terminal device 110 to the network device 120 is referred to as uplink, while a direction 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. 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.
[0064] Further, in FIG. 1, one or more ML models may be deployed at the terminal device 110 and / or the network device 120.
[0065] 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.
[0066] 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) or a PC5 interface. The wireless communication channel may comprise a sidelink, 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.
[0067] 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.
[0068] Reference is now made to FIG. 2, which illustrates a signaling flow 200 for 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.
[0069] In the following descriptions, 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.
[0070] 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.
[0071] As illustrated in FIG. 2, in operation, the network device 120 transmits (205-1) at least one configuration of at least one monitoring report to the terminal device 110, and the terminal device 110 receives (205-2) the at least one configuration accordingly. It should be noted that whether the at least one configuration is used for configuring the at least one monitoring report may be identified by the report quantity comprised in the at least one configuration.
[0072] In some embodiments, the terminal device 110 needs to determine at least one rank and / or at least one layer to be reported. In the following, how to determine the at least one rank and / or at least one layer will be discussed.
[0073] In some embodiments, the terminal device 110 may determine at least one rank to be reported based on: a first set of ranks determined based on at least one inference result comprised in at least one inference report associated with the at least one monitoring report, a second set of ranks determined based on at least one configuration of the at least one inference report associated with the at least one monitoring report, or a third set of ranks or layers determined based on the at least one configuration of the at least one monitoring report.
[0074] In some embodiments, the at least one rank to be reported may be determined to be all the ranks comprised in the second set of ranks and / or determined based on at least one of the following: a minimum rank of the second set of ranks, or a maximum rank of the second set of ranks.
[0075] In some embodiments, if the at least one monitoring report is associated with at least one inference report, the terminal device 110 may determine at least one rank to be reported based on the first set of ranks. In some embodiments, if the at least one monitoring report is not associated with at least one inference report, the terminal device 110 may determine at least one rank to be reported based on at least one of the following: a set of pre-determined ranks, and / or the third set of ranks or layers.
[0076] In some embodiments, the terminal device 110 may determine at least one layer to be reported based on: the first set of ranks, the second set of ranks, or the third set of ranks.
[0077] In some embodiments, the at least one layer to be reported may be determined to be all the layers associated with the second set of ranks and / or determined based on at least one of the following: a minimum layer associated with the second set of ranks, or a maximum layer associated with the second set of ranks.
[0078] In some embodiments, if the at least one monitoring report is associated with at least one inference report, the terminal device 110 may determine at least one layer to be reported based on the first set of ranks. In some embodiments, if the at least one monitoring report is not associated with at least one inference report, the terminal device 110 may determine at least one layer to be reported based on at least one of the following: a set of pre-determined layers, and / or the third set of ranks or layers.
[0079] Then, for each layer, the terminal device 110 may determine (210) at least one valid monitoring instance. Details of the determination will be discussed.
[0080] In some cases, the at least one monitoring report may be associated with at least one inference result corresponding to at least one monitoring instance. In this case, as one example, the terminal device 110 may determine whether a monitoring instance is valid for a layer based on whether a rank indicator in an inference result associated with the monitoring instance is associated with the layer.
[0081] In another example, the terminal device 110 may determine whether a monitoring instance is valid for a layer based on whether a precoding matrix indicator (PMI) in the inference result associated with the monitoring instance is associated with the layer.
[0082] In a further example, the terminal device 110 may determine whether a monitoring instance is valid for a layer based on whether the precoding matrix indicator (PMI) associated with the layer is not omitted in the at least one inference report.
[0083] In a further example, the terminal device 110 may determine whether a monitoring instance is valid for a layer based on whether the layer is comprised in a set of layers indicated by the network device 120, wherein at least one monitoring instances corresponding to the set of layers is indicated to be valid or invalid.
[0084] Alternatively, or in addition, for each rank, the terminal device 110 also may determine (210) at least one valid monitoring instance. Specifically, the at least one monitoring report may be associated with at least one inference result corresponding to at least one monitoring instance. In this case, as one example, the terminal device 110 may determine whether a monitoring instance is valid for a rank based on whether a rank indicator in an inference result associated with the monitoring instance is associated with the rank. In some embodiments, the rank indicator in the inference result may be determined to be associated with the rank if a rank value of the rank indicator in the inference result is same as the rank, or if a rank value of the rank indicator in the inference result is larger than the rank.
[0085] In another example, the terminal device 110 may determine whether a monitoring instance is valid for a rank based on whether a PMI in the inference result associated with the monitoring instance is associated with the rank.
[0086] In further example, the terminal device 110 may determine whether a monitoring instance is valid for a rank based on whether the PMI associated with the rank is not omitted in the at least one inference report.
[0087] In further example, the terminal device 110 may determine whether a monitoring instance is valid for a rank based on whether the rank is comprised in a set of ranks indicated by the network device 120, wherein at least one monitoring instance corresponding to the set of ranks is indicated to be valid or invalid.
[0088] After determining the at least one valid monitoring instance per layer / rank, the terminal device 110 may transmit (215-1) the at least one monitoring report to the network device 120, and the network device 120 may receive (215-2) the at least one monitoring report accordingly. In some embodiments, the monitoring result may be determined based on channel information or precoding matrix information.
[0089] In some embodiments, whether to determine the monitoring result based on the channel information or the precoding matrix information may be indicated by the network device 120. Alternatively, in some embodiments, whether to determine the monitoring result based on the channel information or the precoding matrix information may be determined based on capability information of the terminal device 110.
[0090] In the following, details about the contents comprised in the at least one monitoring report will be discussed.
[0091] In some embodiments, the at least one monitoring report may comprise a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, or a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank.
[0092] In some cases, each monitoring result may be determined per set of monitoring instances or per monitoring time window. In some embodiments, the at least one monitoring report may comprise statistical monitoring result per layer or per rank.
[0093] In some embodiments, for each layer, the statistical monitoring result may be associated with statistical squared generalized cosine similarity (SGCS) information per layer or statistical normalized mean squared error (NMSE) information or per layer. Similarly, for each rank, the statistical monitoring result may be associated with statistical SGCS information per rank or statistical NMSE information or per rank.
[0094] Further, the statistical monitoring result may be in a format of at least one of the following: a mean value, a variance value, a standard deviation value, a median value, a minimum value, a maximum value, a range indication, or a comparison result between the statistical monitoring result and a threshold.
[0095] In some embodiments, in a cases that each monitoring result may be determined per set of monitoring instances or per monitoring time window, the at least one monitoring report may comprise a total number of monitoring instances comprised in the set of monitoring instances or the monitoring time window, and / or information about a number of valid or invalid monitoring instances per layer or per rank.
[0096] In some embodiments, for each layer, the information about the number of valid or invalid monitoring instances per layer may comprise at least one of the following: a number of monitoring instances per layer, a range of the number of monitoring instances per layer, a comparison result between the number of monitoring instances per layer and a threshold, or a ratio between the number of monitoring instances per layer and the total number.
[0097] Similarly, for each rank, the information about the number of valid or invalid monitoring instances per rank may comprise at least one of the following: a number of monitoring instances per rank, a range of the number of monitoring instances per rank, a comparison result between the number of monitoring instances per rank and a threshold, or a ratio between the number of monitoring instances per rank and the total number.
[0098] In some embodiments, in a cases that each monitoring result may be determined per set of monitoring instances or per monitoring time window, the at least one monitoring report may comprises information about a number of monitoring instances per layer or per rank, information about a number of correct or incorrect monitoring instances per layer or per rank, information about a ratio of correct or incorrect monitoring instances per layer or per rank, information about a number of monitoring instances with a specific level monitoring result per layer or per rank, information about a ratio of monitoring instances with a specific level monitoring result per layer or per rank, information about a number of valid or invalid monitoring instances per layer or per rank, and / or information about a ratio of valid or invalid monitoring instances per layer or per rank.
[0099] In some embodiments, for each layer, the information about the number of valid or invalid monitoring instances per layer may comprise at least one of the following: a number of monitoring instances per layer, a range of the number of monitoring instances per layer, a comparison result between the number of monitoring instances per layer and a threshold, or a ratio between the number of monitoring instances per layer and the total number.
[0100] Similarly, for each rank, the information about the number of valid or invalid monitoring instances per rank may comprise at least one of the following: a number of monitoring instances per rank, a range of the number of monitoring instances per rank, a comparison result between the number of monitoring instances per rank and a threshold, or a ratio between the number of monitoring instances per rank and the total number.
[0101] In some embodiments, at least one layer / rank to be reported corresponds to at least one number of valid / invalid monitoring instances, and a first layer / rank is associated with a first number that is a maximum number of the at least one number of valid / invalid monitoring instances. In this event, the information about the number of valid or invalid monitoring instances per layer or per rank comprises at least one of the following: -an absolute value of the first number corresponding to the first layer / rank, and -at least one difference value corresponding to at least one other layer / rank different from the first layer / rank, wherein the difference value is one of the following: a difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and the first number, or a difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and a number of valid / invalid monitoring instances corresponding to a neighbor layer / rank of the other layer / rank.
[0102] In some embodiments, the monitoring result may be determined per monitoring instance, and for each layer or each rank to be reported. In this case, the at least one monitoring report may comprise a first field indicating a quantized monitoring result per layer or per rank.
[0103] In some embodiments, a specific value of the first field may indicate that the monitoring instance is invalid for the layer or rank corresponding to the first field. Alternatively, in some embodiments, the first field may comprise an indication of whether the monitoring instance is valid for the layer or rank corresponding to the first field.
[0104] Alternatively or in addition to the above, in some embodiments, the at least one monitoring report may comprise information of at least one layer satisfying at least one first condition.
[0105] In some embodiments, the at least monitoring report comprises a first part and a second part, and the first part may be configured to comprise the number of layers, and the second part is configured to comprise the at least one layer indicator of the at least one layer.
[0106] In some embodiments, the information of at least one layer satisfying at least one first condition may comprise at least one of the following: a number of layers comprised in the at least one layer, or at least one layer indicator of the at least one layer.
[0107] In some embodiments, the terminal device 110 may determine that a layer satisfies the at least one first condition in accordance with at least one of the following: -a value of a monitoring result of the layer being higher than or equal to a threshold, -a value of a monitoring result of the layer being lower than or equal to a threshold, -a number of valid or invalid monitoring instances corresponding to the layer being higher than or equal to a threshold, -a number of valid or invalid monitoring instances corresponding to the layer being lower than or equal to a threshold, -a ratio of valid or invalid monitoring instances corresponding to the layer being higher than or equal to a threshold, -a ratio of valid or invalid monitoring instances corresponding to the layer being lower than or equal to a threshold, -a number of correct or incorrect monitoring instances corresponding to the layer being higher than or equal to a threshold, -a number of correct or incorrect monitoring instances corresponding to the layer being lower than or equal to a threshold, -a ratio of correct or incorrect monitoring instances corresponding to the layer being higher than or equal to a threshold, -a ratio of correct or incorrect monitoring instances corresponding to the layer being lower than or equal to a threshold, -a number of monitoring instances with a specific level monitoring result corresponding to the layer being higher than or equal to a threshold, -a number of monitoring instances with a specific level monitoring result corresponding to the layer being lower than or equal to a threshold, -a ratio of monitoring instances with a specific level monitoring result corresponding to the layer being higher than or equal to a threshold, or -a ratio of monitoring instances with a specific level monitoring result corresponding to the layer being lower than or equal to a threshold.
[0108] Alternatively or in addition to the above, in some embodiments, the at least one monitoring report may comprise information of at least one rank satisfying at least one second condition.
[0109] In some embodiments, the information of at least one rank satisfying at least one second condition may comprise at least one of the following: a number of ranks comprised in the at least one rank, or at least one rank indicator of the at least one rank.
[0110] In some embodiments, the at least monitoring report comprises a first part and a second part, and the first part may be configured to comprise the number of ranks, and the second part is configured to comprise the at least one rank indicator of the at least one rank.
[0111] In some embodiments, the terminal device 110 may determine that a rank satisfies the at least one second condition in accordance with at least one of the following: -a value of a monitoring result of the rank being higher than or equal to a threshold, -a value of a monitoring result of the rank being lower than or equal to a threshold, -a number of valid or invalid monitoring instances corresponding to the rank being higher than or equal to a threshold, -a number of valid or invalid monitoring instances corresponding to the rank being lower than or equal to a threshold, -a ratio of valid or invalid monitoring instances corresponding to the rank being higher than or equal to a threshold, -a ratio of valid or invalid monitoring instances corresponding to the rank being lower than or equal to a threshold, -a number of correct or incorrect monitoring instances corresponding to the rank being higher than or equal to a threshold, -a number of correct or incorrect monitoring instances corresponding to the rank being lower than or equal to a threshold, -a ratio of correct or incorrect monitoring instances corresponding to the rank being higher than or equal to a threshold, -a ratio of correct or incorrect monitoring instances corresponding to the rank being lower than or equal to a threshold, -a number of monitoring instances with a specific level monitoring result corresponding to the rank being higher than or equal to a threshold, -a number of monitoring instances with a specific level monitoring result corresponding to the rank being lower than or equal to a threshold, -a ratio of monitoring instances with a specific level monitoring result corresponding to the rank being higher than or equal to a threshold, or -a ratio of monitoring instances with a specific level monitoring result corresponding to the rank being lower than or equal to a threshold.
[0112] In some embodiments, the transmission of the at least one monitoring report may be event-triggered. In this event, the terminal device 110 may transmit the at least one monitoring report if at least one layer or rank satisfies at least one report condition. In particular, a layer or rank may be determined to satisfy the at least one report condition if at least one monitoring result corresponding to the layer or rank meets a reporting event during a number of valid monitoring instances corresponding to the layer or rank.
[0113] In some embodiments, a first layer of the at least one layer may be associated with a first reporting event, and a second layer of the at least one layer may be associated with a second reporting event that is the same as or different from the first reporting event. Similarly, in some embodiments, a first rank of the at least one rank may be associated with a first reporting event, and a second rank of the at least one rank may be associated with a second reporting event that is the same as or different from the first reporting event.
[0114] In some embodiments, if a value of a monitoring result of the first layer satisfies at least one condition, the terminal device 110 may skip determining or / and reporting monitoring result of at least one other layer. In some embodiments, if a value of a monitoring result of the first rank satisfies at least one condition, the terminal device 110 may skip determining and / or reporting monitoring result of at least one other rank. In this way, the unnecessary reporting is avoided.
[0115] Merely for a better understanding about the above example processes, more example embodiments will be discussed in the following. In the following embodiments, UE is used as an example of the terminal device, NW is used an example of the network device. It should be noted that below example embodiments should not be interpreted as any limitations to the embodiments of the present disclosure.
[0116] In some embodiments, UE may be configured by NW with a monitoring report, which is configured for reporting information about SGCS per layer (represented by ‘monitoring results’ ) . Specifically, UE may be indicated by NW to report SGCS (s) corresponding to N layer (s) . The value of N may be configured by NW, and / or based on UE capability (e.g., maximum number of layers (or maximum rank) associated with AI / ML functionality supported by UE) . For example, assuming that the value of N is 4, UE may determine SGCS of layer-1, SGCS of layer-2, SGCS of layer-3 and SGCS of layer-4, and report information about the determined SGCSs.
[0117] In some embodiments, if the monitoring results are reported per set of samples (e.g., samples within a time window (e.g., monitoring time window) , represented ‘a set of monitoring instances’ ) , for each monitoring instance (i.e., sample) , UE may determine validity per layer. Specifically, UE may determine whether the monitoring instance is valid (or invalid) for a layer based on at least one of the following: -whether the reported RI (s) in inference results associated with the monitoring instance is associated with the layer; -whether the reported PMI (s) in inference results associated with the monitoring instance is associated with the layer. Further, optionally, at least part of the reported PMI(s) associated with the layer is not omitted; -whether the layer is comprised in a set of layers indicated by NW, wherein monitoring instance (s) corresponding to the set of layer is indicated to be valid (or invalid) .
[0118] In the example of FIG. 3, for the monitoring instance at T1, the reported RI is equal to 4 and corresponding PMI is also reported, UE may assume that, the monitoring instance is valid for layer-1, layer-2, layer-3 and layer-4; for the monitoring instance at T2, the reported RI is equal to 2 and corresponding PMI is also reported, UE may assume that, the monitoring instance is valid for layer-1 and layer-2, but the monitoring is invalid for layer-3 and layer-4; for the monitoring instance at T3, the reported RI is equal to 1 and corresponding PMI is also reported, UE may assume that, the monitoring instance is valid for layer-1, but the monitoring instance is invalid for layer-2, layer-3 and layer-4.
[0119] In some embodiments, if the monitoring results are reported per set of samples (e.g., samples within a time window (e.g., monitoring time window) , represented ‘a set of monitoring instances’ ) , for each valid monitoring instance, UE may determine SGCS per layer.
[0120] In some embodiments, if the monitoring results are reported per set of samples (e.g., samples within a time window (e.g., monitoring time window) , represented ‘a set of monitoring instances’ ) , UE may determine the number of valid (or invalid) monitoring instances per layer in the set of monitoring instances.
[0121] In some embodiments, if the monitoring results are reported per set of samples (e.g., samples within a time window (e.g., monitoring time window) , represented ‘a set of monitoring instances’ ) , UE may perform option A (monitoring based on statistical SGCS) or option B (e.g., monitoring based on the number of correct samples) as follows. Optionally, whether option A or option B is used may be indicated by NW.
[0122] In some embodiments (e.g., Option A) , for each layer, UE may determine at least one statistical value (e.g., mean, variance, standard deviation, median, minimum, maximum) of SGCS (s) corresponding to valid monitoring instance (s) corresponding the layer. The statistical value is represented by ‘statistical SGCS’ . UE may report at least one of the following in the monitoring report.
[0123] In some embodiments, UE may report information about statistical SGCS per layer. For example, value (e.g., quantized value) or range of statistical SGCS per layer, or indication of comparison results between statistical SGCS per layer and a threshold.
[0124] Alternatively, in some embodiments, UE may report the information about the (total) number of monitoring instances (per layer) . The number of monitoring instances per layer may be the same.
[0125] Alternatively, in some embodiments, UE may report Information about the number of valid (or invalid) monitoring instances per layer. For example, value or range of the number of valid monitoring instances per layer, indication of comparison results between the number of valid monitoring instances per layer and a threshold, ratio of [the number of valid future time instance] / [the number of monitoring instances corresponding to the layer] , value (e.g., quantized value) or range of the ratio, or indication of comparison results between the ratio per layer and a threshold.
[0126] Furthermore, considering that the number of valid monitoring instances corresponding layer-1 (Nv1) , layer-2 (Nv2) , layer-3 (Nv3) and layer-4 (Nv4) generally satisfy the following relationship: Nv1≥Nv2≥Nv3≥Nv4, in some embodiments, reporting the number of valid monitoring instances per layer may be based on differential reporting when the number of valid monitoring instances per layer are reported, which may be used to reduce unnecessary reporting ovehead. Specifically, UE may report the Nv1 based on an absolute value. UE may report the Nv2, Nv3 and Nv4 may be based on a differential value.
[0127] In one emxaple (Option 1) , UE may report the Nv2, Nv3 and Nv4 based on a differential value, which may be determined based on the Nv1. For example, for reporting the Nv2, UE may report a differential value between the Nv2 and the Nv1; for reporting the Nv3, UE may report a differential value between the Nv3 and the Nv1; for reporting the Nv4, UE may report a differential value between the Nv4 and the Nv1.
[0128] Alternatively, in another example (Option 2) , UE may report Nv of a layer (higher than 1) based on a differential value, which may be determined based on Nv of a further layer that is lower than the layer (and nearest to the layer) . For example, for reporting the Nv2, UE may report a differential value between the Nv2 and the Nv1; for reporting the Nv3, UE may report a differential value between the Nv3 and the Nv2; for reporting the Nv4, UE may report a differential value between the Nv4 and the Nv3.
[0129] In the differential reporting, the bitwidth for the field indicating the Nv1 may be determined based on the (total) number of the number of monitoring instances (corresponding to the layer-1) (represented by Ntotal) . The bitwidth for the field indicating the Nv corresponding to a layer except for the layer-1 (e.g., layer-2, layer-3, layer-4) may be determined based on X bits. The value of X may be based on the following mapping table, e.g.,
[0130] The above example is about reporting the number of valid monitoring instances per layer, for reporting the number of invalid monitoring instances, the above Nv1 needs to be replaced with the Nv corresponding to the highest layer (e.g., layer-4) , and reporting the other Nv can be based on the Nv corresponding to the highest layer, or based on a further higher layer.
[0131] Alternatively, in some embodiments, UE may report an indicator of layer (s) satisfying at least one condition, which may comprise at least one of the following. This may means that, e.g., UE may only report the layer (s) having the good (or bad) SGCS to reduce unnecessary reporting overhead. Furthermore, if the information is reported, the monitoring report may comprise multiple parts, e.g., part 1 and part 2, where the part 1 may comprise indication of the number of layers satisfying the at least one condition, the part 2 may comprise the indicator of layers satisfying the at least one condition: Statistical SGCS corresponding to the layer is higher than (or lower than) or equal to a threshold, and / or the number of valid (or invalid) monitoring instances corresponding to the layer is higher than (or lower than) or equal to a threshold.
[0132] In some embodiments (e.g., Option B) : for each valid monitoring instance, for each layer, UE may determine whether the SGCS corresponding to the layer satisfies at least one condition (e.g., SGCS is larger than or equal to a threshold) . If satisfied, the (valid monitoring instance) can be regarded as ‘correct monitoring instance’ . Optionally, for each layer, UE may determine monitoring instance at different / multiple levels, e.g., first level monitoring instance, second level monitoring instance, third level monitoring instance based on the SGCS per layer. For example shown in the following table, the different levels may correspond to different ranges of SGCS.
[0133] In some embodimebts, UE may report at least one of the following in the monitoring report: -Information about the number of monitoring instances per layer. -Information about the number of correct monitoring instances per layer. -Information about the number of first level (or / and, second level, third level) monitoring instances per layer. -Information about the number of valid monitoring instances per layer. -Information (e.g., ratio) about ratio of [the number of correct monitoring instances per layer] / [the number of valid monitoring instances per layer] . -Information (e.g., ratio) about ratio of [the number of first level (or / and, second level, third level) monitoring instances per layer] / [the number of valid monitoring instances per layer] .
[0134] Altertnatively, or in addition, in some embodimebts, UE may report an indicator of layer (s) satisfying at least one condition in the monitoring report. Furthermore, if the information is reported, the monitoring report may comprise multiple parts, e.g., part 1 and part 2, where the part 1 may comprise indication of the number of layers satisfying the at least one condition, the part 2 may comprise the indicator of layers satisfying the at least one condition.
[0135] The at least one condition may comprise: the number of valid (or invalid) monitoring instances corresponding to the layer is higher than (or lower than) or equal to a threshold; the number of correct monitoring instances corresponding to the layer is higher than (or lower than) or equal to a threshold; the radio of correct monitoring instances corresponding to the layer is higher than (or lower than) or equal to a threshold; the number of first level (or / and second level, third level) monitoring instances corresponding to the layer is higher than (or lower than) or equal to a threshold; the ratio of [the number of correct monitoring instances per layer] / [the number of valid monitoring instances per layer] is higher than (or lower than) or equal to a threshold; the ratio of [the number of first level (or / and, second level, third level) monitoring instances per layer] / [the number of valid monitoring instances per layer] is higher than (or lower than) or equal to a threshold.
[0136] In some embodiments, if the monitoring results is reported per sample, for each monitoring instance, UE may determine validity per layer.
[0137] Alternatively, or in addition, if the monitoring results is reported per sample, UE may report information about SGCS per layer in the monitoring report. Assuming a first field is used to indicate SGCS per layer, and bitwidth for the first field may be determined based on the number of quantization levels about SGCS (represented by ‘Q’ ) , for example as shown in the following table (Q=3) , bitwidth for the first field may be determined based on
[0138] Alternatively, or in addition, for each layer, if the monitoring instance corresponding to the layer is a invalid (or valid) monitoring instance, in other words, if there is at least one valid (or available, effective) SGCS corresponding to the layer, UE may perform at least one of the following: -UE may report a specific bit value or bit sequence (e.g., all 0 or 1) in the first field corresponding to the layer. In this case, NW may ignore the reported SGCS corresponding to the layer. -UE may report a specific bit value indicating that the monitoring instance corresponding to the layer is an invalid monitoring instance. In this case, the bitwidth for the first field may be determined based on -UE may report an indication indicating that whether the monitoring instance corresponding to the layer is a valid monitoring instance, e.g., a second field of 1 bit is used to indicate this indication. And first field per layer may correspond to second field per layer.
[0139] In some embodiments, if the monitoring results are reported based on at least one event (i.e., event triggered report) , for each monitoring instance, UE may determine validity per layer.
[0140] In some embodiments, if the monitoring results are reported based on at least one event (i.e., event triggered report) , at least one layer satisfies at least one condition during a time duration (or a number of monitoring instance, or a number of valid monitoring instances) , the monitoring report may be triggered. For example, for a layer, when the SGCS corresponding to the layer is lower than (or higher than) or equal to a threshold during a number of valid monitoring instances, the monitoring report may be triggered. Specifically, when the SGCS corresponding to the layer is lower than or equal to a threshold, a timer may start (or restart) , and increment a counter by 1. If the counter is larger than or equal to a threshold, the monitoring report may be triggered. If the timer expires, the counter may be set to 0.
[0141] In some embodiments, UE may be configured by NW with a monitoring report, which is configured for reporting information about SGCS per rank (represented by ‘monitoring results’ ) . Specifically, UE may be indicated by NW to report SGCS (s) corresponding to N rank (s) . The value of N may be configured by NW, and / or based on UE capability (e.g., maximum rank associated with AI / ML functionality supported by UE) . For example, assuming the value of N is 4, UE may determine SGCS of rank-1, SGCS of rank-2, SGCS of rank-3 and SGCS of rank-4, and report information about the determined SGCSs.
[0142] In some embodiments, if the monitoring results are reported per set of samples, for each monitoring instance, UE may determine validity per rank. Specifically, UE may determine whether the monitoring instance is valid (or invalid) for a rank based on at least one of the following: -Whether the reported RI (s) in inference results associated with the monitoring instance is associated with the rank. E.g., the reported RI is larger than or / and equal to the rank. -Whether the reported PMI (s) in inference results associated with the monitoring instance is associated with the rank. Further, optionally, at least part of the reported PMI(s) associated with the rank is not omitted. -Whether the rank is comprised in a set of ranks indicated by NW, wherein monitoring instance (s) corresponding to the set of ranks is indicated to be valid (or invalid) .
[0143] In the example of FIG. 3, for the monitoring instance at T1, the reported RI is equal to 4 and corresponding PMI is also reported, UE may assume that, the monitoring instance is valid for rank-4, but the monitoring instance is invalid for rank-1, rank-2 and rank-3; for the monitoring instance at T2, the reported RI is equal to 2 and corresponding PMI is also reported, UE may assume that, the monitoring instance is valid for rank-2, but the monitoring is invalid for rank-1, rank-3 and rank-4; for the monitoring instance at T3, the reported RI is equal to 1 and corresponding PMI is also reported, UE may assume that, the monitoring instance is valid for rank-1, but the monitoring instance is invalid for rank-2, rank-3 and rank-4.
[0144] The other operation may be the same as the above embodiments of the per layer operation, and where the ‘layer’ is replaced with ‘rank’ . Merely for brevity, the same or similar content are omitted herein.
[0145] In some embodiments, UE may be configured by NW with a monitoring report, which is associated with an inference report. The inference report (or the monitoring report) may be associated with a set of allowed ranks, which is indicated by NW using a higher layer parameter (e.g., ri-Restriction, typeII-RI-Restriction, typeII-RI-Restriction-r18) . For example, a bitmap parameter ‘typeII-RI-Restriction-r18’ forms a bit sequence r3, r2, r1, r0, where r0 is the LSB (least significant bit) and r3 is the MSB (most significant bit) . When ri is zero, i∈ {0, 1, …, 3} , PMI and RI reporting are not allowed to correspond to any precoder associated with v=i+1 layers. In other words, the υ (i.e., i+1) is a not allowed rank. When ri is zero, i∈ {0, 1, ..., 3} , the υ (i.e., i+1) is an allowed rank.
[0146] In some embodiments, if the monitoring report is configured for reporting information related to SGCS per rank, for the monitoring report, UE may determine or / and report SGCS (s) corresponding to a set of ranks (represented by ‘first set of ranks’ ) . Specifically, UE may determine measured precoding matrix (s) (determined based on the measurement resource (s) associated with the monitoring report) corresponding to the set of ranks, predicted precoding matrix (s) corresponding to the set of ranks (which may be determined based on the inference results of the inference report associated with the monitoring report) . And then UE may determine SGCS (s) corresponding to the set of ranks based on the determined measured precoding matrix (s) (i.e., ground-truth label) and predicted precoding matrix (s) .
[0147] In some embodiments, UE may determine the first set of ranks based on the set of allowed ranks associated with (the inference report associated with) the monitoring report. Specifically, at least one of the following options can be considered.
[0148] In some embodiments (Option 1) , the first set of ranks may be the same as the set of allowed ranks. For example, assuming the set of allowed RIs comprises rank-1, rank-2 and rank-4, the first set of ranks may comprise rank-1, rank-2 and rank-4, this means that UE may determine or / and report SGCSs corresponding to rank-1, rank-2 and rank-4.
[0149] In some embodiments (Option 2) , the first set of ranks may be determined based on the highest rank or / and the lowest rank in the set of allowed ranks. For one example, the first set of ranks may comprise rank (s) lower than or equal to the highest rank in the set of allowed ranks. Assuming the set of allowed ranks comprises rank-1, rank-2 and rank-4, the first set of ranks may comprise rank-1, rank-2, rank-3 and rank-4, this means that UE may determine or / and report SGCSs corresponding to rank-1, rank-2, rank-3 and rank-4. For another example, the first set of ranks may comprise RI (s) lower than or equal to the highest rank in the set of allowed ranks and higher than or equal to the lowest rank in the set of allowed ranks. Assuming the set of allowed ranks comprises rank-2 and rank-4, the first set of ranks may comprise rank-2, rank-3 and rank-4, this means that UE may determine or / and report SGCSs corresponding to rank-2, rank-3 and rank-4.
[0150] In some embodiments (Option 3) , the first set of ranks may be determined based on NW’s indication and the set of allowed ranks. For example, NW may indicate a set of ranks from the set of allowed ranks to UE. And the first set of ranks may comprise the indicated set of ranks.
[0151] In some embodiments, if the monitoring report is configured for reporting information related to SGCS per layer, for the monitoring report, UE may determine or / and report SGCS (s) corresponding to a set of layers (represented by ‘first set of layers’ ) . Specifically, UE may determine measured precoding matrix (s) (determined based on the measurement resource (s) associated with the monitoring report) corresponding to the set of layers, predicted precoding matrix (s) corresponding to the set of layers (which may be determined based on the inference results of the inference report associated with the monitoring report) . And then UE may determine SGCS (s) corresponding to the set of layers based on the determined measured precoding matrix (s) (i.e., ground-truth label) and predicted precoding matrix (s) .
[0152] In some embodiments, UE may determine the first set of layers based on the set of allowed ranks associated with (the inference report associated with) the monitoring report. Further, the first set of layers may be determined based on the largest rank in the set of allowed ranks. For example, assuming the set of allowed ranks comprises rank-1 and rank-2, the first set of layers may be determined based on the rank-2, specifically, the first set of layers may comprise layer-1 and layer-2, this means that UE may determine or / and report SGCSs corresponding to layer-1 and layer-2.
[0153] Additionally, in the above embodiments, for the determination or / and reporting of SGCS per layer or rank, if SGCS corresponding to the first layer (i.e., layer-1) or rank-1 is smaller than or equal to a threshold (or other condition) , UE may skip (or ignore, stop, omit) determining or / and reporting SGCS corresponding to other layer (i.e., a layer except for the first layer, a layer larger than the first layer) or other rank (e.g., rank-2, rank-3, rank-4) .
[0154] Specifically, for example, if SGCS per layer or rank is reported based on per-sample, the SGCS corresponding to the first layer may be included in a first part in the monitoring report, and SGCS (s) corresponding to the other layer (s) may be included in a second part in the monitoring report. If the SGCS corresponding to the first layer in the first part is smaller than or equal to a threshold (or other condition) , the SGCS (s) corresponding to the other layer (s) may not be reported in the second part.
[0155] For example, if SGCS per layer or rank is reported based on set of samples, if the statistical SGCS (or the number of correct monitoring instances, or the number of first / second / third level monitoring instances, or the number of valid (or invalid monitoring instances, etc. ) ) corresponding to the first layer or rank-1 is smaller than or equal to a threshold (or other condition) , statistical SGCS (s) corresponding to the other layer (s) or ranks may not be determined or / and reported. In other words, UE may skip (or ignore, stop, omit) the determination or / and reporting performance metric (e.g., statistical SGCS) corresponding to the other layer (s) or rank (s) .
[0156] For example, if SGCS per layer or rank is reported based on event-based reporting, the first layer may be associated with a first condition, the other layer (i.e., a layer except for the first layer) may be associated with a second condition, where the first condition may be the same as the second condition, or different from the second condition. Furthermore, when the first condition is fulfilled for (performance metric corresponding to) the first layer, UE may report a first indication to a higher layer (e.g., MAC layer) or NW; when the second condition is fulfilled for (performance metric corresponding to) the other layer, UE may report a second indication to a higher layer (e.g., MAC layer) or NW. Where the first indication is different from the second indication.
[0157] In some embodiments, for a monitoring report, UE may determine whether SGCS per layer or SGCS per rank is determined or / and reported based on NW’s indication, e.g., based on report quantity associated with the monitoring report, new specified indicator associated with the monitoring report.
[0158] In some embodiments, for a monitoring report, if the monitoring report is associated with an inference report, UE may determine which layers or ranks correspond the SGCS need to be reported based on the reported inference results (e.g., reported RI, reported PMI) of the inference report, or / and configuration about layer or rank (e.g., configured allowed rank (s) ) associated with the inference report.
[0159] In some embodiments, for a monitoring report, if the monitoring report is associated with no inference report, UE may determine which layers or ranks correspond the SGCS need to be reported based on layer (s) or rank (s) configured by NW, or predefined layer (s) or rank (s) . For example, if rank-4 is indicated by NW for the monitoring CSI report, and SGCS per layer needs to be determined or / and reported, UE may assume that SGCSs corresponding to all layers, i.e., layer-1, layer-2, layer-3 and layer-4 need to be determined or / and reported for the monitoring report.
[0160] In some embodiments, the SGCS may be determined based on channel or precoding matrix (as mentioned in Case 2) . UE may determine whether the SGCS is determined based on channel or / and precoding matrix based on NW’s indication, e.g., new specified indicator associated with the monitoring report. UE may determine whether the SGCS determined based on channel or / and the SGCS determined based on channel is reported based on NW’s indication, e.g., based on report quantity associated with the monitoring report, new specified indicator associated with the monitoring report.
[0161] According to some embodiments of the present disclosure, the number of processing units (such as, CPU or GPU) may be determined / allocated.
[0162] In operation, the network device 120 transmits at least one configuration of at least one monitoring report to the terminal device 110, and the terminal device 110 receives at least one configuration accordingly.
[0163] Then, the terminal device 110 may determine the monitoring report by using at least one processing unit, i.e. process the monitoring report by using the at least one processing unit. As used herein, the processing unit may be a CSI processing unit (CPU) or graphics processing unit (GPU) . In the other words, the present disclosure is not limited with regards to the type of the processing unit.
[0164] In some embodiments, if the monitoring report is associated with an inference report, the at least one processing unit may comprise a first number of processing units, where the first number may be determined based on a number of processing units occupied for measurement and / or reporting non-AI / ML related information. Alternatively, if the monitoring report is not associated with an inference report, the at least one processing unit may comprise a second number of processing units, and the second number may be determined based on at least one of a number of processing units occupied for measurement and / or reporting AI / ML related information, or the first number.
[0165] In one example, if the monitoring report is associated with an inference report, the at least one processing unit may be a first number of processing units with a first type (such as, CPU) , where the first number is determined based on a number of processing units with a first type determined for measurement and / or reporting non-artificial intelligence (AI) / machine learning (ML) information.
[0166] If the monitoring report is not associated with an inference report, the at least one processing unit may be a sum of the first number of processing units with the first type and a second number of processing units with the first type, wherein the second number is determined based on a number of processing units with a first type determined for measurement and / or reporting artificial intelligence (AI) / machine learning (ML) -related information.
[0167] Alternatively, if the monitoring report is not associated with an inference report, the at least one processing unit may be a sum of the first number of processing units with the first type (CPU) and a third number with a second type (GPU) , where the third number is determined based on a number of processing units with a second type determined for measurement and / or reporting AI / ML-related information.
[0168] Merely for a better understanding about the above example processes, more example embodiments will be discussed in the following.
[0169] In some embodiments, CPU shared counted between legacy CSI reporting and AI / ML-based CSI reporting. Processing a monitoring report may occupy a number of CPUs (i.e., OCPU) for a number of symbols as follows: -OCPU = O1 + O2, if the monitoring report is associated with no inference report, or / and if the monitoring report is associated with one measurement resource or measurement resource set (e.g., 1 CSI-ResourceConfig, 1 CSI-ResourceConfigId) . -OCPU = O2, if the monitoring report is associated with at least one inference report. Where the O1 may be determined based on the number of CPUs occupied by a report (e.g., inference report) configured for reporting inference results, or based on the number of CPUs about AI / ML functionality, model, or / and LCM (e.g., performance monitoring) , which may be determined based on a predefined value or / and UE capability. Where the O2 may be determined based on the number of CPUs occupied by an report configured for reporting information unrelated to AI / ML, or based on the number of CPUs about non-AI / ML, or (legacy) measurement (and reporting) , which may be determined based on a predefined value or / and UE capability.
[0170] In some embodiments, CPU separately counted between legacy CSI reporting and AI / ML-based CSI reporting. In one embodiment, processing a monitoring report may occupy a number of CPUs (i.e., OCPU) for a number of symbols as follows: -OCPU = O2, where the O2 may be determined based on the number of CPUs occupied by a report configured for reporting information unrelated to AI / ML, or based on the number of CPUs about non-AI / ML, or (legacy) measurement (and reporting) , which may be determined based on a predefined value or / and UE capability.
[0171] In another embodiment, processing a monitoring report may occupy a number of GPUs (i.e., OGPU) for a number of symbols as follows: -OGPU = O3, if the monitoring report is associated with no inference report, or / and if the monitoring report is associated with at least one measurement resource or measurement resource set (e.g., 1 CSI-ResourceConfig, 1 CSI-ResourceConfigId) . -OGPU = O4 (e.g., 0) , if the monitoring report is associated with at least one inference report. Where the O3 may be determined based on the number of GPUs occupied by a report (e.g., inference report) configured for reporting inference results, or based on the number of GPUs about AI / ML functionality, model, or / and LCM (e.g., performance monitoring) , which may be determined based on a predefined value or / and UE capability.
[0172] In some embodiments, the CPU and GPU are examples of two different types of processing units.
[0173] 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.
[0174] At block 410, the terminal device receives, from a network device, at least one configuration of at least one monitoring report.
[0175] At block 420, for each layer or rank, the terminal device determines at least one valid monitoring instance.
[0176] At block 430, the terminal device transmits the at least one monitoring report to the network device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition.
[0177] In some example embodiments, the at least one monitoring report may be associated with at least one inference result corresponding to at least one monitoring instance, and the terminal device may: determine whether a monitoring instance of the at least one monitoring instance is valid for a layer based on at least one of the following: whether a rank indicator in an inference result associated with the monitoring instance is associated with the layer, whether a precoding matrix indicator (PMI) in the inference result associated with the monitoring instance is associated with the layer, whether the precoding matrix indicator (PMI) associated with the layer is not omitted in the at least one inference report, or whether the layer is comprised in a set of layers indicated by the network device, wherein at least one monitoring instances corresponding to the set of layers is indicated to be valid or invalid; and / or determine whether a monitoring instance is valid for a rank based on at least one of the following: whether a rank indicator in an inference result associated with the monitoring instance is associated with the rank, whether a precoding matrix indicator (PMI) in the inference result associated with the monitoring instance is associated with the rank, whether the precoding matrix indicator (PMI) associated with the rank is not omitted in the at least one inference report, or whether the rank is comprised in a set of ranks indicated by the network device, wherein at least one monitoring instance corresponding to the set of ranks is indicated to be valid or invalid.
[0178] In some example embodiments, the rank indicator in the inference result may be determined to be associated with the rank in accordance with at least one of the following: a rank value of the rank indicator in the inference result is same as the rank, or a rank value of the rank indicator in the inference result is larger than the rank.
[0179] In some example embodiments, each monitoring result may be determined per set of monitoring instances or per monitoring time window, and the at least one monitoring report may comprise at least one of the following: statistical monitoring result per layer or per rank, a total number of monitoring instances comprised in the set of monitoring instances or the monitoring time window, or information about a number of valid or invalid monitoring instances per layer or per rank.
[0180] In some example embodiments, for each layer, the statistical monitoring result may be associated with statistical squared generalized cosine similarity (SGCS) information per layer or statistical normalized mean squared error (NMSE) information or per layer, and / or for each rank, the statistical monitoring result may be associated with statistical squared generalized cosine similarity (SGCS) information per rank or statistical normalized mean squared error (NMSE) information or per rank, and the statistical monitoring result may be in a format of at least one of the following: a mean value, a variance value, a standard deviation value, a median value, a minimum value, a maximum value, a range indication, or a comparison result between the statistical monitoring result and a threshold.
[0181] In some example embodiments, each monitoring result may be determined per set of monitoring instances or per monitoring time window, and the at least one monitoring report may comprise at least one of the following: information about a number of monitoring instances per layer or per rank, information about a number of correct or incorrect monitoring instances per layer or per rank, information about a ratio of correct or incorrect monitoring instances per layer or per rank, information about a number of monitoring instances with a specific level monitoring result per layer or per rank, information about a ratio of monitoring instances with a specific level monitoring result per layer or per rank, information about a number of valid or invalid monitoring instances per layer or per rank, or information about a ratio of valid or invalid monitoring instances per layer or per rank.
[0182] In some example embodiments, for each layer, the information about the number of valid or invalid monitoring instances per layer may comprise at least one of the following: a number of monitoring instances per layer, a range of the number of monitoring instances per layer, a comparison result between the number of monitoring instances per layer and a threshold, or a ratio between the number of monitoring instances per layer and the total number, and / or for each rank, the information about the number of valid or invalid monitoring instances per rank may comprise at least one of the following: a number of monitoring instances per rank, a range of the number of monitoring instances per rank, a comparison result between the number of monitoring instances per rank and a threshold, or a ratio between the number of monitoring instances per rank and the total number.
[0183] In some example embodiments, at least one layer / rank to be reported may correspond to at least one number of valid / invalid monitoring instances, and a first layer / rank may be associated with a first number that is a maximum number of the at least one number of valid / invalid monitoring instances, and the information about the number of valid or invalid monitoring instances per layer or per rank may comprise at least one of the following: an absolute value of the first number corresponding to the first layer / rank, at least one difference value corresponding to at least one other layer / rank different from the first layer / rank, wherein the difference value is one of the following: a difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and the first number, or a difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and a number of valid / invalid monitoring instances corresponding to a neighbor layer / rank of the other layer / rank.
[0184] In some example embodiments, the monitoring result may be determined per monitoring instance, and for each layer or each rank to be reported, the at least one monitoring report may comprise a first field indicating a quantized monitoring result per layer or per rank.
[0185] In some example embodiments, a specific value of the first field indicates that the monitoring instance may be invalid for the layer or rank corresponding to the first field, or the first field comprises an indication of whether the monitoring instance may be valid for the layer or rank corresponding to the first field.
[0186] In some example embodiments, the terminal device may: determine that a layer satisfies the at least one first condition in accordance with at least one of the following: a value of a monitoring result of the layer being higher than or equal to a threshold, a value of a monitoring result of the layer being lower than or equal to a threshold, a number of valid or invalid monitoring instances corresponding to the layer being higher than or equal to a threshold, a number of valid or invalid monitoring instances corresponding to the layer being lower than or equal to a threshold, a ratio of valid or invalid monitoring instances corresponding to the layer being higher than or equal to a threshold, a ratio of valid or invalid monitoring instances corresponding to the layer being lower than or equal to a threshold, a number of correct or incorrect monitoring instances corresponding to the layer being higher than or equal to a threshold, a number of correct or incorrect monitoring instances corresponding to the layer being lower than or equal to a threshold, a ratio of correct or incorrect monitoring instances corresponding to the layer being higher than or equal to a threshold, a ratio of correct or incorrect monitoring instances corresponding to the layer being lower than or equal to a threshold, a number of monitoring instances with a specific level monitoring result corresponding to the layer being higher than or equal to a threshold, a number of monitoring instances with a specific level monitoring result corresponding to the layer being lower than or equal to a threshold, a ratio of monitoring instances with a specific level monitoring result corresponding to the layer being higher than or equal to a threshold, or a ratio of monitoring instances with a specific level monitoring result corresponding to the layer being lower than or equal to a threshold.
[0187] In some example embodiments, the terminal device may: determine that a rank satisfies the at least one second condition in accordance with at least one of the following: a value of a monitoring result of the rank being higher than or equal to a threshold, a value of a monitoring result of the rank being lower than or equal to a threshold, a number of valid or invalid monitoring instances corresponding to the rank being higher than or equal to a threshold, a number of valid or invalid monitoring instances corresponding to the rank being lower than or equal to a threshold, a ratio of valid or invalid monitoring instances corresponding to the rank being higher than or equal to a threshold, a ratio of valid or invalid monitoring instances corresponding to the rank being lower than or equal to a threshold, a number of correct or incorrect monitoring instances corresponding to the rank being higher than or equal to a threshold, a number of correct or incorrect monitoring instances corresponding to the rank being lower than or equal to a threshold, a ratio of correct or incorrect monitoring instances corresponding to the rank being higher than or equal to a threshold, a ratio of correct or incorrect monitoring instances corresponding to the rank being lower than or equal to a threshold, a number of monitoring instances with a specific level monitoring result corresponding to the rank being higher than or equal to a threshold, a number of monitoring instances with a specific level monitoring result corresponding to the rank being lower than or equal to a threshold, a ratio of monitoring instances with a specific level monitoring result corresponding to the rank being higher than or equal to a threshold, or a ratio of monitoring instances with a specific level monitoring result corresponding to the rank being lower than or equal to a threshold.
[0188] In some example embodiments, the information of at least one layer satisfying at least one first condition may comprise at least one of the following: a number of layers comprised in the at least one layer, or at least one layer indicator of the at least one layer, and / or the information of at least one rank satisfying at least one second condition may comprise at least one of the following: a number of ranks comprised in the at least one rank, or at least one rank indicator of the at least one rank.
[0189] In some example embodiments, the first part may be configured to comprise the number of layers, and the second part may be configured to comprise the at least one layer indicator of the at least one layer, and / or the first part may be configured to comprise the number of ranks, and the second part may be configured to comprise the at least one rank indicator of the at least one rank.
[0190] In some example embodiments, the terminal device may: transmit the at least one monitoring report in accordance with a determination that at least one layer or rank satisfies at least one report condition, wherein a layer or rank is determined to satisfy the at least one report condition if at least one monitoring result corresponding to the layer or rank meets a reporting event during a number of valid monitoring instances corresponding to the layer or rank.
[0191] In some example embodiments, a first layer of the at least one layer may be associated with a first reporting event, and a second layer of the at least one layer may be associated with a second reporting event that is the same as or different from the first reporting event, and / or a first rank of the at least one rank may be associated with a first reporting event, and a second rank of the at least one rank may be associated with a second reporting event that is the same as or different from the first reporting event.
[0192] In some example embodiments, the terminal device may: determine at least one rank or layer to be reported based on: a first set of ranks determined based on at least one inference result comprised in at least one inference report associated with the at least one monitoring report, a second set of ranks determined based on at least one configuration of the at least one inference report associated with the at least one monitoring report, or a third set of ranks or layers determined based on the at least one configuration of the at least one monitoring report; and / or determine at least one layer to be reported based on: the first set of ranks, the second set of ranks, or the third set of ranks.
[0193] In some example embodiments, the at least one rank to be reported may be determined to be all the ranks comprised in the second set of ranks and / or determined based on at least one of the following: a minimum rank of the second set of ranks, or a maximum rank of the second set of ranks, the at least one layer to be reported may be determined to be all the layers associated with the second set of ranks and / or determined based on at least one of the following: a minimum layer associated with the second set of ranks, or a maximum layer associated with the second set of ranks.
[0194] In some example embodiments, the terminal device may: in accordance with a determination that the at least one monitoring report is associated with at least one inference report, determine at least one layer to be reported based on the first set of ranks; and / or in accordance with a determination that the at least one monitoring report is not associated with at least one inference report, determine at least one layer to be reported based on at least one of the following: a set of pre-determined layers, and / or the third set of ranks or layers.
[0195] In some example embodiments, the terminal device may: in accordance with a determination that the at least one monitoring report is associated with at least one inference report, determine at least one rank to be reported based on the first set of ranks; and / or in accordance with a determination that the at least one monitoring report is not associated with at least one inference report, determine at least one rank to be reported based on at least one of the following: a set of pre-determined ranks, and / or the third set of ranks or layers.
[0196] In some example embodiments, the terminal device may: in accordance with a determination that a value of a monitoring result of the first layer satisfies at least one condition, skip determining or / and reporting monitoring result of at least one other layer, and / or in accordance with a determination that a value of a monitoring result of the first rank satisfies at least one condition, skip determining and / or reporting monitoring result of at least one other rank.
[0197] In some example embodiments, the monitoring result may be determined based on channel information or precoding matrix information.
[0198] In some example embodiments, whether to determine the monitoring result based on the channel information or the precoding matrix information may be indicated by the network device or determined based on capability information of the terminal device.
[0199] 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.
[0200] At block 510, the terminal device receives, from a network device, at least one configuration of a monitoring report.
[0201] At block 520, the terminal device determines the monitoring report by using at least one processing unit, wherein in accordance with a determination that the monitoring report is associated with an inference report, the at least one processing unit comprises a first number of processing units, and the first number is determined based on a number of processing units occupied for measurement and / or reporting non-artificial intelligence (AI) / machine learning (ML) related information, and wherein in accordance with a determination that the monitoring report is not associated with an inference report, the at least one processing unit comprises a second number of processing units, and the second number is determined based on at least one of a number of processing units occupied for measurement and / or reporting AI / ML related information, or the first number.
[0202] In some example embodiments, the second number may be determined based on a number of processing units with a first type determined for measurement and / or reporting artificial intelligence (AI) / machine learning (ML) -related information, or a sum of the first number of processing units with the first type and a third number with a second type, wherein the third number is determined based on a number of processing units with a second type determined for measurement and / or reporting AI / ML-related information.
[0203] 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.
[0204] At block 610, the network device transmits, to a terminal device, at least one configuration of at least one monitoring report.
[0205] At block 620, the network device receives the at least one monitoring report from the terminal device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition.
[0206] In some example embodiments, the at least one monitoring report may be associated with at least one inference result corresponding to at least one monitoring instance, and the terminal device may: determine whether a monitoring instance of the at least one monitoring instance is valid for a layer based on at least one of the following: whether a rank indicator in an inference result associated with the monitoring instance is associated with the layer, whether a precoding matrix indicator (PMI) in the inference result associated with the monitoring instance is associated with the layer, whether the precoding matrix indicator (PMI) associated with the layer is not omitted in the at least one inference report, or whether the layer is comprised in a set of layers indicated by the network device, wherein at least one monitoring instances corresponding to the set of layers is indicated to be valid or invalid; and / or determine whether a monitoring instance is valid for a rank based on at least one of the following: whether a rank indicator in an inference result associated with the monitoring instance is associated with the rank, whether a precoding matrix indicator (PMI) in the inference result associated with the monitoring instance is associated with the rank, whether the precoding matrix indicator (PMI) associated with the rank is not omitted in the at least one inference report, or whether the rank is comprised in a set of ranks indicated by the network device, wherein at least one monitoring instance corresponding to the set of ranks is indicated to be valid or invalid.
[0207] In some example embodiments, the rank indicator in the inference result may be determined to be associated with the rank in accordance with at least one of the following: a rank value of the rank indicator in the inference result is same as the rank, or a rank value of the rank indicator in the inference result is larger than the rank.
[0208] In some example embodiments, each monitoring result may be determined per set of monitoring instances or per monitoring time window, and the at least one monitoring report may comprise at least one of the following: statistical monitoring result per layer or per rank, a total number of monitoring instances comprised in the set of monitoring instances or the monitoring time window, or information about a number of valid or invalid monitoring instances per layer or per rank.
[0209] In some example embodiments, for each layer, the statistical monitoring result may be associated with statistical squared generalized cosine similarity (SGCS) information per layer or statistical normalized mean squared error (NMSE) information or per layer, and / or for each rank, the statistical monitoring result may be associated with statistical squared generalized cosine similarity (SGCS) information per rank or statistical normalized mean squared error (NMSE) information or per rank, and the statistical monitoring result may be in a format of at least one of the following: a mean value, a variance value, a standard deviation value, a median value, a minimum value, a maximum value, a range indication, or a comparison result between the statistical monitoring result and a threshold.
[0210] In some example embodiments, each monitoring result may be determined per set of monitoring instances or per monitoring time window, and the at least one monitoring report may comprise at least one of the following: information about a number of monitoring instances per layer or per rank, information about a number of correct or incorrect monitoring instances per layer or per rank, information about a ratio of correct or incorrect monitoring instances per layer or per rank, information about a number of monitoring instances with a specific level monitoring result per layer or per rank, information about a ratio of monitoring instances with a specific level monitoring result per layer or per rank, information about a number of valid or invalid monitoring instances per layer or per rank, or information about a ratio of valid or invalid monitoring instances per layer or per rank.
[0211] In some example embodiments, for each layer, the information about the number of valid or invalid monitoring instances per layer may comprise at least one of the following: a number of monitoring instances per layer, a range of the number of monitoring instances per layer, a comparison result between the number of monitoring instances per layer and a threshold, or a ratio between the number of monitoring instances per layer and the total number, and / or for each rank, the information about the number of valid or invalid monitoring instances per rank comprises at least one of the following: a number of monitoring instances per rank, a range of the number of monitoring instances per rank, a comparison result between the number of monitoring instances per rank and a threshold, or a ratio between the number of monitoring instances per rank and the total number.
[0212] In some example embodiments, at least one layer / rank to be reported may correspond to at least one number of valid / invalid monitoring instances, and a first layer / rank may be associated with a first number that is a maximum number of the at least one number of valid / invalid monitoring instances, and the information about the number of valid or invalid monitoring instances per layer or per rank may comprise at least one of the following: an absolute value of the first number corresponding to the first layer / rank, at least one difference value corresponding to at least one other layer / rank different from the first layer / rank, wherein the difference value is one of the following: a difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and the first number, or a difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and a number of valid / invalid monitoring instances corresponding to a neighbor layer / rank of the other layer / rank.
[0213] In some example embodiments, the monitoring result may be determined per monitoring instance, and for each layer or each rank to be reported, the at least one monitoring report may comprise a first field indicating a quantized monitoring result per layer or per rank.
[0214] In some example embodiments, a specific value of the first field indicates that the monitoring instance may be invalid for the layer or rank corresponding to the first field, or the first field comprises an indication of whether the monitoring instance may be valid for the layer or rank corresponding to the first field.
[0215] In some example embodiments, the information of at least one layer satisfying at least one first condition may comprise at least one of the following: a number of layers comprised in the at least one layer, or at least one layer indicator of the at least one layer, and / or the information of at least one rank satisfying at least one second condition may comprise at least one of the following: a number of ranks comprised in the at least one rank, or at least one rank indicator of the at least one rank.
[0216] In some example embodiments, the first part may be configured to comprise the number of layers, and the second part may be configured to comprise the at least one layer indicator of the at least one layer, and / or the first part may be configured to comprise the number of ranks, and the second part may be configured to comprise the at least one rank indicator of the at least one rank.
[0217] In some example embodiments, a first layer of the at least one layer may be associated with a first reporting event, and a second layer of the at least one layer may be associated with a second reporting event that is the same as or different from the first reporting event, and / or a first rank of the at least one rank may be associated with a first reporting event, and a second rank of the at least one rank may be associated with a second reporting event that is the same as or different from the first reporting event.
[0218] In some example embodiments, the monitoring result may be determined based on channel information or precoding matrix information.
[0219] In some example embodiments, whether to determine the monitoring result based on the channel information or the precoding matrix information may be indicated by the network device or determined based on capability information of the terminal device.
[0220] FIG. 7 is a simplified block diagram of a device 700 that is suitable for implementing embodiments of the present disclosure. The device 700 can be considered as a further example implementation of any of the devices as shown in FIG. 1. Accordingly, the device 700 can be implemented at or as at least a part of the terminal device 110 or the network device 120.
[0221] As shown, the device 700 includes a processor 710, a memory 720 coupled to the processor 710, a suitable transceiver 740 coupled to the processor 710, and a communication interface coupled to the transceiver 740. The memory 720 stores at least a part of a program 730. The transceiver 740 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 740 may include at least one of a transmitter 742 and a receiver 744. The transmitter 742 and the receiver 744 may be functional modules or physical entities. The transceiver 740 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.
[0222] The program 730 is assumed to include program instructions that, when executed by the associated processor 710, enable the device 700 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGS. 1 to 7. The embodiments herein may be implemented by computer software executable by the processor 710 of the device 700, or by hardware, or by a combination of software and hardware. The processor 710 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 710 and memory 720 may form processing means 750 adapted to implement various embodiments of the present disclosure.
[0223] The memory 720 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 720 is shown in the device 700, there may be several physically distinct memory modules in the device 700. The processor 710 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 700 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.
[0224] 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, at least one configuration of at least one monitoring report; for each layer or rank, determine at least one valid monitoring instance; and transmit the at least one monitoring report to the network device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the terminal device as discussed above.
[0225] 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, at least one configuration of a monitoring report; and determine the monitoring report by using at least one processing unit, wherein in accordance with a determination that the monitoring report is associated with an inference report, the at least one processing unit comprises a first number of processing units, and the first number is determined based on a number of processing units occupied for measurement and / or reporting non-artificial intelligence (AI) / machine learning (ML) related information, and wherein in accordance with a determination that the monitoring report is not associated with an inference report, the at least one processing unit comprises a second number of processing units, and the second number is determined based on at least one of a number of processing units occupied for measurement and / or reporting AI / ML related information, or the first number. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the terminal device as discussed above.
[0226] 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, at least one configuration of at least one monitoring report; and receive the at least one monitoring report from the terminal device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the network device as discussed above.
[0227] 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.
[0228] According to embodiments of the present disclosure, a terminal apparatus is provided. The terminal apparatus comprises means for receiving, from a network device, at least one configuration of at least one monitoring report; means for, for each layer or rank, determining at least one valid monitoring instance; and means for transmitting the at least one monitoring report to the network device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition. 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.
[0229] According to embodiments of the present disclosure, a terminal apparatus is provided. The terminal apparatus comprises means for receiving, from a network device, at least one configuration of a monitoring report; and means for determining the monitoring report by using at least one processing unit, wherein in accordance with a determination that the monitoring report is associated with an inference report, the at least one processing unit comprises a first number of processing units, and the first number is determined based on a number of processing units occupied for measurement and / or reporting non-artificial intelligence (AI) / machine learning (ML) related information, and wherein in accordance with a determination that the monitoring report is not associated with an inference report, the at least one processing unit comprises a second number of processing units, and the second number is determined based on at least one of a number of processing units occupied for measurement and / or reporting AI / ML related information, or the first number. 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.
[0230] According to embodiments of the present disclosure, a network apparatus is provided. The network apparatus comprises means for transmitting, to a terminal device, at least one configuration of at least one monitoring report; and means for receiving the at least one monitoring report from the terminal device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition. 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.
[0231] In summary, embodiments of the present disclosure provide the following aspects.
[0232] In an aspect, it is proposed a terminal device, comprising: a processor configured to cause the terminal device to: receive, from a network device, at least one configuration of at least one monitoring report; for each layer or rank, determine at least one valid monitoring instance; and transmit the at least one monitoring report to the network device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition.
[0233] In some embodiments, the at least one monitoring report may be associated with at least one inference result corresponding to at least one monitoring instance, and the terminal device is further caused to: determine whether a monitoring instance of the at least one monitoring instance is valid for a layer based on at least one of the following: whether a rank indicator in an inference result associated with the monitoring instance is associated with the layer, whether a precoding matrix indicator (PMI) in the inference result associated with the monitoring instance is associated with the layer, whether the precoding matrix indicator (PMI) associated with the layer is not omitted in the at least one inference report, or whether the layer is comprised in a set of layers indicated by the network device, wherein at least one monitoring instances corresponding to the set of layers is indicated to be valid or invalid; and / or determine whether a monitoring instance is valid for a rank based on at least one of the following: whether a rank indicator in an inference result associated with the monitoring instance is associated with the rank, whether a precoding matrix indicator (PMI) in the inference result associated with the monitoring instance is associated with the rank, whether the precoding matrix indicator (PMI) associated with the rank is not omitted in the at least one inference report, or whether the rank is comprised in a set of ranks indicated by the network device, wherein at least one monitoring instance corresponding to the set of ranks is indicated to be valid or invalid.
[0234] In some embodiments, the rank indicator in the inference result may be determined to be associated with the rank in accordance with at least one of the following: a rank value of the rank indicator in the inference result is same as the rank, or a rank value of the rank indicator in the inference result is larger than the rank.
[0235] In some embodiments, each monitoring result may be determined per set of monitoring instances or per monitoring time window, and the at least one monitoring report may comprise at least one of the following: statistical monitoring result per layer or per rank, a total number of monitoring instances comprised in the set of monitoring instances or the monitoring time window, or information about a number of valid or invalid monitoring instances per layer or per rank.
[0236] In some embodiments, for each layer, the statistical monitoring result may be associated with statistical squared generalized cosine similarity (SGCS) information per layer or statistical normalized mean squared error (NMSE) information or per layer, and / or for each rank, the statistical monitoring result may be associated with statistical squared generalized cosine similarity (SGCS) information per rank or statistical normalized mean squared error (NMSE) information or per rank, and the statistical monitoring result may be in a format of at least one of the following: a mean value, a variance value, a standard deviation value, a median value, a minimum value, a maximum value, a range indication, or a comparison result between the statistical monitoring result and a threshold.
[0237] In some embodiments, each monitoring result may be determined per set of monitoring instances or per monitoring time window, and the at least one monitoring report may comprise at least one of the following: information about a number of monitoring instances per layer or per rank, information about a number of correct or incorrect monitoring instances per layer or per rank, information about a ratio of correct or incorrect monitoring instances per layer or per rank, information about a number of monitoring instances with a specific level monitoring result per layer or per rank, information about a ratio of monitoring instances with a specific level monitoring result per layer or per rank, information about a number of valid or invalid monitoring instances per layer or per rank, or information about a ratio of valid or invalid monitoring instances per layer or per rank.
[0238] In some embodiments, for each layer, the information about the number of valid or invalid monitoring instances per layer may comprise at least one of the following: a number of monitoring instances per layer, a range of the number of monitoring instances per layer, a comparison result between the number of monitoring instances per layer and a threshold, or a ratio between the number of monitoring instances per layer and the total number, and / or for each rank, the information about the number of valid or invalid monitoring instances per rank may comprise at least one of the following: a number of monitoring instances per rank, a range of the number of monitoring instances per rank, a comparison result between the number of monitoring instances per rank and a threshold, or a ratio between the number of monitoring instances per rank and the total number.
[0239] In some embodiments, at least one layer / rank to be reported may correspond to at least one number of valid / invalid monitoring instances, and a first layer / rank may be associated with a first number that is a maximum number of the at least one number of valid / invalid monitoring instances, and the information about the number of valid or invalid monitoring instances per layer or per rank may comprise at least one of the following: an absolute value of the first number corresponding to the first layer / rank, at least one difference value corresponding to at least one other layer / rank different from the first layer / rank, wherein the difference value is one of the following: a difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and the first number, or a difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and a number of valid / invalid monitoring instances corresponding to a neighbor layer / rank of the other layer / rank.
[0240] In some embodiments, the monitoring result may be determined per monitoring instance, and for each layer or each rank to be reported, the at least one monitoring report may comprise a first field indicating a quantized monitoring result per layer or per rank.
[0241] In some embodiments, a specific value of the first field indicates that the monitoring instance may be invalid for the layer or rank corresponding to the first field, or the first field comprises an indication of whether the monitoring instance may be valid for the layer or rank corresponding to the first field.
[0242] In some embodiments, the terminal device may: determine that a layer satisfies the at least one first condition in accordance with at least one of the following: a value of a monitoring result of the layer being higher than or equal to a threshold, a value of a monitoring result of the layer being lower than or equal to a threshold, a number of valid or invalid monitoring instances corresponding to the layer being higher than or equal to a threshold, a number of valid or invalid monitoring instances corresponding to the layer being lower than or equal to a threshold, a ratio of valid or invalid monitoring instances corresponding to the layer being higher than or equal to a threshold, a ratio of valid or invalid monitoring instances corresponding to the layer being lower than or equal to a threshold, a number of correct or incorrect monitoring instances corresponding to the layer being higher than or equal to a threshold, a number of correct or incorrect monitoring instances corresponding to the layer being lower than or equal to a threshold, a ratio of correct or incorrect monitoring instances corresponding to the layer being higher than or equal to a threshold, a ratio of correct or incorrect monitoring instances corresponding to the layer being lower than or equal to a threshold, a number of monitoring instances with a specific level monitoring result corresponding to the layer being higher than or equal to a threshold, a number of monitoring instances with a specific level monitoring result corresponding to the layer being lower than or equal to a threshold, a ratio of monitoring instances with a specific level monitoring result corresponding to the layer being higher than or equal to a threshold, or a ratio of monitoring instances with a specific level monitoring result corresponding to the layer being lower than or equal to a threshold.
[0243] In some embodiments, the terminal device may: determine that a rank satisfies the at least one second condition in accordance with at least one of the following: a value of a monitoring result of the rank being higher than or equal to a threshold, a value of a monitoring result of the rank being lower than or equal to a threshold, a number of valid or invalid monitoring instances corresponding to the rank being higher than or equal to a threshold, a number of valid or invalid monitoring instances corresponding to the rank being lower than or equal to a threshold, a ratio of valid or invalid monitoring instances corresponding to the rank being higher than or equal to a threshold, a ratio of valid or invalid monitoring instances corresponding to the rank being lower than or equal to a threshold, a number of correct or incorrect monitoring instances corresponding to the rank being higher than or equal to a threshold, a number of correct or incorrect monitoring instances corresponding to the rank being lower than or equal to a threshold, a ratio of correct or incorrect monitoring instances corresponding to the rank being higher than or equal to a threshold, a ratio of correct or incorrect monitoring instances corresponding to the rank being lower than or equal to a threshold, a number of monitoring instances with a specific level monitoring result corresponding to the rank being higher than or equal to a threshold, a number of monitoring instances with a specific level monitoring result corresponding to the rank being lower than or equal to a threshold, a ratio of monitoring instances with a specific level monitoring result corresponding to the rank being higher than or equal to a threshold, or a ratio of monitoring instances with a specific level monitoring result corresponding to the rank being lower than or equal to a threshold.
[0244] In some embodiments, the information of at least one layer satisfying at least one first condition may comprise at least one of the following: a number of layers comprised in the at least one layer, or at least one layer indicator of the at least one layer, and / or the information of at least one rank satisfying at least one second condition comprises at least one of the following: a number of ranks comprised in the at least one rank, or at least one rank indicator of the at least one rank.
[0245] In some embodiments, the first part may be configured to comprise the number of layers, and the second part may be configured to comprise the at least one layer indicator of the at least one layer, and / or the first part may be configured to comprise the number of ranks, and the second part may be configured to comprise the at least one rank indicator of the at least one rank.
[0246] In some embodiments, the terminal device may: transmit the at least one monitoring report in accordance with a determination that at least one layer or rank satisfies at least one report condition, wherein a layer or rank is determined to satisfy the at least one report condition if at least one monitoring result corresponding to the layer or rank meets a reporting event during a number of valid monitoring instances corresponding to the layer or rank.
[0247] In some embodiments, a first layer of the at least one layer may be associated with a first reporting event, and a second layer of the at least one layer may be associated with a second reporting event that is the same as or different from the first reporting event, and / or a first rank of the at least one rank may be associated with a first reporting event, and a second rank of the at least one rank may be associated with a second reporting event that is the same as or different from the first reporting event.
[0248] In some embodiments, the terminal device may: determine at least one rank or layer to be reported based on: a first set of ranks determined based on at least one inference result comprised in at least one inference report associated with the at least one monitoring report, a second set of ranks determined based on at least one configuration of the at least one inference report associated with the at least one monitoring report, or a third set of ranks or layers determined based on the at least one configuration of the at least one monitoring report; and / or determine at least one layer to be reported based on: the first set of ranks, the second set of ranks, or the third set of ranks.
[0249] In some embodiments, the at least one rank to be reported may be determined to be all the ranks comprised in the second set of ranks and / or determined based on at least one of the following: a minimum rank of the second set of ranks, or a maximum rank of the second set of ranks, the at least one layer to be reported may be determined to be all the layers associated with the second set of ranks and / or determined based on at least one of the following: a minimum layer associated with the second set of ranks, or a maximum layer associated with the second set of ranks.
[0250] In some embodiments, the terminal device may: in accordance with a determination that the at least one monitoring report is associated with at least one inference report, determine at least one layer to be reported based on the first set of ranks; and / or in accordance with a determination that the at least one monitoring report is not associated with at least one inference report, determine at least one layer to be reported based on at least one of the following: a set of pre-determined layers, and / or the third set of ranks or layers.
[0251] In some embodiments, the terminal device may: in accordance with a determination that the at least one monitoring report is associated with at least one inference report, determine at least one rank to be reported based on the first set of ranks; and / or in accordance with a determination that the at least one monitoring report is not associated with at least one inference report, determine at least one rank to be reported based on at least one of the following: a set of pre-determined ranks, and / or the third set of ranks or layers.
[0252] In some embodiments, the terminal device may: in accordance with a determination that a value of a monitoring result of the first layer satisfies at least one condition, skip determining or / and reporting monitoring result of at least one other layer, and / or in accordance with a determination that a value of a monitoring result of the first rank satisfies at least one condition, skip determining and / or reporting monitoring result of at least one other rank.
[0253] In some embodiments, the monitoring result may be determined based on channel information or precoding matrix information.
[0254] In some embodiments, whether to determine the monitoring result based on the channel information or the precoding matrix information may be indicated by the network device or determined based on capability information of the terminal device.
[0255] In an aspect, it is proposed a terminal device, comprising: a processor configured to cause the terminal device to: receive, from a network device, at least one configuration of a monitoring report; and determine the monitoring report by using at least one processing unit, wherein in accordance with a determination that the monitoring report is associated with an inference report, the at least one processing unit comprises a first number of processing units, and the first number is determined based on a number of processing units occupied for measurement and / or reporting non-artificial intelligence (AI) / machine learning (ML) related information, and wherein in accordance with a determination that the monitoring report is not associated with an inference report, the at least one processing unit comprises a second number of processing units, and the second number is determined based on at least one of a number of processing units occupied for measurement and / or reporting AI / ML related information, or the first number.
[0256] In some embodiments, the second number may be determined based on a number of processing units with a first type determined for measurement and / or reporting artificial intelligence (AI) / machine learning (ML) -related information, or a sum of the first number of processing units with the first type and a third number with a second type, wherein the third number is determined based on a number of processing units with a second type determined for measurement and / or reporting AI / ML-related information.
[0257] In an aspect, it is proposed a network device, comprising: a processor configured to cause the network device to: transmit, to a terminal device, at least one configuration of at least one monitoring report; and receive the at least one monitoring report from the terminal device, wherein the at least one monitoring report comprises at least one of the following: a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer, a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank, information of at least one layer satisfying at least one first condition, or information of at least one rank satisfying at least one second condition.
[0258] In some embodiments, the at least one monitoring report may be associated with at least one inference result corresponding to at least one monitoring instance, and the terminal device may: determine whether a monitoring instance of the at least one monitoring instance is valid for a layer based on at least one of the following: whether a rank indicator in an inference result associated with the monitoring instance is associated with the layer, whether a precoding matrix indicator (PMI) in the inference result associated with the monitoring instance is associated with the layer, whether the precoding matrix indicator (PMI) associated with the layer is not omitted in the at least one inference report, or whether the layer is comprised in a set of layers indicated by the network device, wherein at least one monitoring instances corresponding to the set of layers is indicated to be valid or invalid; and / or determine whether a monitoring instance is valid for a rank based on at least one of the following: whether a rank indicator in an inference result associated with the monitoring instance is associated with the rank, whether a precoding matrix indicator (PMI) in the inference result associated with the monitoring instance is associated with the rank, whether the precoding matrix indicator (PMI) associated with the rank is not omitted in the at least one inference report, or whether the rank is comprised in a set of ranks indicated by the network device, wherein at least one monitoring instance corresponding to the set of ranks is indicated to be valid or invalid.
[0259] In some embodiments, the rank indicator in the inference result may be determined to be associated with the rank in accordance with at least one of the following: a rank value of the rank indicator in the inference result is same as the rank, or a rank value of the rank indicator in the inference result is larger than the rank.
[0260] In some embodiments, each monitoring result may be determined per set of monitoring instances or per monitoring time window, and the at least one monitoring report may comprise at least one of the following: statistical monitoring result per layer or per rank, a total number of monitoring instances comprised in the set of monitoring instances or the monitoring time window, or information about a number of valid or invalid monitoring instances per layer or per rank.
[0261] In some embodiments, for each layer, the statistical monitoring result may be associated with statistical squared generalized cosine similarity (SGCS) information per layer or statistical normalized mean squared error (NMSE) information or per layer, and / or for each rank, the statistical monitoring result may be associated with statistical squared generalized cosine similarity (SGCS) information per rank or statistical normalized mean squared error (NMSE) information or per rank, and the statistical monitoring result may be in a format of at least one of the following: a mean value, a variance value, a standard deviation value, a median value, a minimum value, a maximum value, a range indication, or a comparison result between the statistical monitoring result and a threshold.
[0262] In some embodiments, each monitoring result may be determined per set of monitoring instances or per monitoring time window, and the at least one monitoring report may comprise at least one of the following: information about a number of monitoring instances per layer or per rank, information about a number of correct or incorrect monitoring instances per layer or per rank, information about a ratio of correct or incorrect monitoring instances per layer or per rank, information about a number of monitoring instances with a specific level monitoring result per layer or per rank, information about a ratio of monitoring instances with a specific level monitoring result per layer or per rank, information about a number of valid or invalid monitoring instances per layer or per rank, or information about a ratio of valid or invalid monitoring instances per layer or per rank.
[0263] In some embodiments, for each layer, the information about the number of valid or invalid monitoring instances per layer may comprise at least one of the following: a number of monitoring instances per layer, a range of the number of monitoring instances per layer, a comparison result between the number of monitoring instances per layer and a threshold, or a ratio between the number of monitoring instances per layer and the total number, and / or for each rank, the information about the number of valid or invalid monitoring instances per rank may comprise at least one of the following: a number of monitoring instances per rank, a range of the number of monitoring instances per rank, a comparison result between the number of monitoring instances per rank and a threshold, or a ratio between the number of monitoring instances per rank and the total number.
[0264] In some embodiments, at least one layer / rank to be reported may correspond to at least one number of valid / invalid monitoring instances, and a first layer / rank may be associated with a first number that is a maximum number of the at least one number of valid / invalid monitoring instances, and the information about the number of valid or invalid monitoring instances per layer or per rank may comprise at least one of the following: an absolute value of the first number corresponding to the first layer / rank, at least one difference value corresponding to at least one other layer / rank different from the first layer / rank, wherein the difference value is one of the following: a difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and the first number, or a difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and a number of valid / invalid monitoring instances corresponding to a neighbor layer / rank of the other layer / rank.
[0265] In some embodiments, the monitoring result may be determined per monitoring instance, and for each layer or each rank to be reported, the at least one monitoring report may comprise a first field indicating a quantized monitoring result per layer or per rank.
[0266] In some embodiments, a specific value of the first field indicates that the monitoring instance may be invalid for the layer or rank corresponding to the first field, or the first field comprises an indication of whether the monitoring instance may be valid for the layer or rank corresponding to the first field.
[0267] In some embodiments, the information of at least one layer satisfying at least one first condition may comprise at least one of the following: a number of layers comprised in the at least one layer, or at least one layer indicator of the at least one layer, and / or the information of at least one rank satisfying at least one second condition may comprise at least one of the following: a number of ranks comprised in the at least one rank, or at least one rank indicator of the at least one rank.
[0268] In some embodiments, the first part may be configured to comprise the number of layers, and the second part may be configured to comprise the at least one layer indicator of the at least one layer, and / or the first part may be configured to comprise the number of ranks, and the second part may be configured to comprise the at least one rank indicator of the at least one rank.
[0269] In some embodiments, a first layer of the at least one layer may be associated with a first reporting event, and a second layer of the at least one layer may be associated with a second reporting event that is the same as or different from the first reporting event, and / or a first rank of the at least one rank may be associated with a first reporting event, and a second rank of the at least one rank may be associated with a second reporting event that is the same as or different from the first reporting event.
[0270] In some embodiments, the monitoring result may be determined based on channel information or precoding matrix information.
[0271] In some embodiments, whether to determine the monitoring result based on the channel information or the precoding matrix information may be indicated by the network device or determined based on capability information of the terminal device.
[0272] 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.
[0273] 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.
[0274] 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.
[0275] 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.
[0276] 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 7. 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.
[0277] 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.
[0278] 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.
[0279] 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.
[0280] 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
1.A terminal device, comprising:a processor configured to cause the terminal device to:receive, from a network device, at least one configuration of at least one monitoring report;for each layer or rank, determine at least one valid monitoring instance; andtransmit the at least one monitoring report to the network device, wherein the at least one monitoring report comprises at least one of the following:a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer,a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank,information of at least one layer satisfying at least one first condition, orinformation of at least one rank satisfying at least one second condition.2.The terminal device of claim 1, wherein the at least one monitoring report is associated with at least one inference result corresponding to at least one monitoring instance, and the terminal device is further caused to:determine whether a monitoring instance of the at least one monitoring instance is valid for a layer based on at least one of the following:whether a rank indicator in an inference result associated with the monitoring instance is associated with the layer,whether a precoding matrix indicator (PMI) in the inference result associated with the monitoring instance is associated with the layer,whether the precoding matrix indicator (PMI) associated with the layer is not omitted in the at least one inference report, orwhether the layer is comprised in a set of layers indicated by the network device, wherein at least one monitoring instances corresponding to the set of layers is indicated to be valid or invalid; and / ordetermine whether a monitoring instance is valid for a rank based on at least one of the following:whether a rank indicator in an inference result associated with the monitoring instance is associated with the rank,whether a precoding matrix indicator (PMI) in the inference result associated with the monitoring instance is associated with the rank,whether the precoding matrix indicator (PMI) associated with the rank is not omitted in the at least one inference report, orwhether the rank is comprised in a set of ranks indicated by the network device, wherein at least one monitoring instance corresponding to the set of ranks is indicated to be valid or invalid.3.The terminal device of claim 2, wherein the rank indicator in the inference result is determined to be associated with the rank in accordance with at least one of the following:a rank value of the rank indicator in the inference result is same as the rank, ora rank value of the rank indicator in the inference result is larger than the rank.4.The terminal device of claim 1, wherein each monitoring result is determined per set of monitoring instances or per monitoring time window, and the at least one monitoring report comprises at least one of the following:statistical monitoring result per layer or per rank,a total number of monitoring instances comprised in the set of monitoring instances or the monitoring time window, orinformation about a number of valid or invalid monitoring instances per layer or per rank.5.The terminal device of claim 4, wherein,for each layer, the statistical monitoring result is associated with statistical squared generalized cosine similarity (SGCS) information per layer or statistical normalized mean squared error (NMSE) information or per layer, and / or for each rank, the statistical monitoring result is associated with statistical squared generalized cosine similarity (SGCS) information per rank or statistical normalized mean squared error (NMSE) information or per rank, andthe statistical monitoring result is in a format of at least one of the following: a mean value, a variance value, a standard deviation value, a median value, a minimum value, a maximum value, a range indication, or a comparison result between the statistical monitoring result and a threshold.6.The terminal device of claim 1, wherein each monitoring result is determined per set of monitoring instances or per monitoring time window, and the at least one monitoring report comprises at least one of the following:information about a number of monitoring instances per layer or per rank,information about a number of correct or incorrect monitoring instances per layer or per rank,information about a ratio of correct or incorrect monitoring instances per layer or per rank,information about a number of monitoring instances with a specific level monitoring result per layer or per rank,information about a ratio of monitoring instances with a specific level monitoring result per layer or per rank,information about a number of valid or invalid monitoring instances per layer or per rank, orinformation about a ratio of valid or invalid monitoring instances per layer or per rank.7.The terminal device of any of claims 4 to 6, wherein,for each layer, the information about the number of valid or invalid monitoring instances per layer comprises at least one of the following: a number of monitoring instances per layer, a range of the number of monitoring instances per layer, a comparison result between the number of monitoring instances per layer and a threshold, or a ratio between the number of monitoring instances per layer and the total number, and / orfor each rank, the information about the number of valid or invalid monitoring instances per rank comprises at least one of the following: a number of monitoring instances per rank, a range of the number of monitoring instances per rank, a comparison result between the number of monitoring instances per rank and a threshold, or a ratio between the number of monitoring instances per rank and the total number.8.The terminal device of any of claims 4 to 6, wherein at least one layer / rank to be reported corresponds to at least one number of valid / invalid monitoring instances, and a first layer / rank is associated with a first number that is a maximum number of the at least one number of valid / invalid monitoring instances, andthe information about the number of valid or invalid monitoring instances per layer or per rank comprises at least one of the following:an absolute value of the first number corresponding to the first layer / rank, andat least one difference value corresponding to at least one other layer / rank different from the first layer / rank, wherein the difference value is one of the following:a difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and the first number, ora difference between a number of valid / invalid monitoring instances corresponding to the other layer / rank and a number of valid / invalid monitoring instances corresponding to a neighbor layer / rank of the other layer / rank.9.The terminal device of claim 1, wherein the monitoring result is determined per monitoring instance, and for each layer or each rank to be reported, the at least one monitoring report comprises a first field indicating a quantized monitoring result per layer or per rank.10.The terminal device of claim 9, wherein,a specific value of the first field indicates that the monitoring instance is invalid for the layer or rank corresponding to the first field, orthe first field comprises an indication of whether the monitoring instance is valid for the layer or rank corresponding to the first field.11.The terminal device of claim 1, wherein the terminal device is further caused to:determine that a layer satisfies the at least one first condition in accordance with at least one of the following:a value of a monitoring result of the layer being higher than or equal to a threshold,a value of a monitoring result of the layer being lower than or equal to a threshold,a number of valid or invalid monitoring instances corresponding to the layer being higher than or equal to a threshold,a number of valid or invalid monitoring instances corresponding to the layer being lower than or equal to a threshold,a ratio of valid or invalid monitoring instances corresponding to the layer being higher than or equal to a threshold,a ratio of valid or invalid monitoring instances corresponding to the layer being lower than or equal to a threshold,a number of correct or incorrect monitoring instances corresponding to the layer being higher than or equal to a threshold,a number of correct or incorrect monitoring instances corresponding to the layer being lower than or equal to a threshold,a ratio of correct or incorrect monitoring instances corresponding to the layer being higher than or equal to a threshold,a ratio of correct or incorrect monitoring instances corresponding to the layer being lower than or equal to a threshold,a number of monitoring instances with a specific level monitoring result corresponding to the layer being higher than or equal to a threshold,a number of monitoring instances with a specific level monitoring result corresponding to the layer being lower than or equal to a threshold,a ratio of monitoring instances with a specific level monitoring result corresponding to the layer being higher than or equal to a threshold, ora ratio of monitoring instances with a specific level monitoring result corresponding to the layer being lower than or equal to a threshold.12.The terminal device of claim 1, wherein the terminal device is further caused to:determine that a rank satisfies the at least one second condition in accordance with at least one of the following:a value of a monitoring result of the rank being higher than or equal to a threshold,a value of a monitoring result of the rank being lower than or equal to a threshold,a number of valid or invalid monitoring instances corresponding to the rank being higher than or equal to a threshold,a number of valid or invalid monitoring instances corresponding to the rank being lower than or equal to a threshold,a ratio of valid or invalid monitoring instances corresponding to the rank being higher than or equal to a threshold,a ratio of valid or invalid monitoring instances corresponding to the rank being lower than or equal to a threshold,a number of correct or incorrect monitoring instances corresponding to the rank being higher than or equal to a threshold,a number of correct or incorrect monitoring instances corresponding to the rank being lower than or equal to a threshold,a ratio of correct or incorrect monitoring instances corresponding to the rank being higher than or equal to a threshold,a ratio of correct or incorrect monitoring instances corresponding to the rank being lower than or equal to a threshold,a number of monitoring instances with a specific level monitoring result corresponding to the rank being higher than or equal to a threshold,a number of monitoring instances with a specific level monitoring result corresponding to the rank being lower than or equal to a threshold,a ratio of monitoring instances with a specific level monitoring result corresponding to the rank being higher than or equal to a threshold, ora ratio of monitoring instances with a specific level monitoring result corresponding to the rank being lower than or equal to a threshold.13.The terminal device of claim 1, wherein,the information of at least one layer satisfying at least one first condition comprises at least one of the following: a number of layers comprised in the at least one layer, or at least one layer indicator of the at least one layer, and / orthe information of at least one rank satisfying at least one second condition comprises at least one of the following: a number of ranks comprised in the at least one rank, or at least one rank indicator of the at least one rank.14.The terminal device of claim 13, wherein the at least monitoring report comprises a first part and a second part, and wherein,the first part is configured to comprise the number of layers, and the second part is configured to comprise the at least one layer indicator of the at least one layer, and / orthe first part is configured to comprise the number of ranks, and the second part is configured to comprise the at least one rank indicator of the at least one rank.15.The terminal device of claim 1, wherein the terminal device is further caused to:transmit the at least one monitoring report in accordance with a determination that at least one layer or rank satisfies at least one report condition, wherein a layer or rank is determined to satisfy the at least one report condition if at least one monitoring result corresponding to the layer or rank meets a reporting event during a number of valid monitoring instances corresponding to the layer or rank.16.The terminal device of claim 15, wherein,a first layer of the at least one layer is associated with a first reporting event, and a second layer of the at least one layer is associated with a second reporting event that is the same as or different from the first reporting event, and / ora first rank of the at least one rank is associated with a first reporting event, and a second rank of the at least one rank is associated with a second reporting event that is the same as or different from the first reporting event.17.The terminal device of claim 1, wherein the terminal device is further caused to:determine at least one rank or layer to be reported based on at least one of the following:a first set of ranks determined based on at least one inference result comprised in at least one inference report associated with the at least one monitoring report,a second set of ranks determined based on at least one configuration of the at least one inference report associated with the at least one monitoring report, ora third set of ranks or layers determined based on the at least one configuration of the at least one monitoring report; and / ordetermine at least one layer to be reported based on at least one of the following:the first set of ranks,the second set of ranks, orthe third set of ranks.18.The terminal device of claim 17, wherein,the at least one rank to be reported is determined to be all the ranks comprised in the second set of ranks and / or determined based on at least one of the following: a minimum rank of the second set of ranks, or a maximum rank of the second set of ranks, and / orthe at least one layer to be reported is determined to be all the layers associated with the second set of ranks and / or determined based on at least one of the following: a minimum layer associated with the second set of ranks, or a maximum layer associated with the second set of ranks.19.The terminal device of claim 17, wherein the terminal device is further caused to:in accordance with a determination that the at least one monitoring report is associated with at least one inference report, determine at least one layer to be reported based on the first set of ranks; and / orin accordance with a determination that the at least one monitoring report is not associated with at least one inference report, determine at least one layer to be reported based on at least one of the following: a set of pre-determined layers, and / or the third set of ranks or layers.20.The terminal device of claim 17, wherein the terminal device is further caused to:in accordance with a determination that the at least one monitoring report is associated with at least one inference report, determine at least one rank to be reported based on the first set of ranks; and / orin accordance with a determination that the at least one monitoring report is not associated with at least one inference report, determine at least one rank to be reported based on at least one of the following: a set of pre-determined ranks, and / or the third set of ranks or layers.21.The terminal device of claim 1, wherein the terminal device is further caused to:in accordance with a determination that a value of a monitoring result of the first layer satisfies at least one condition, skip determining or / and reporting monitoring result of at least one other layer, and / orin accordance with a determination that a value of a monitoring result of the first rank satisfies at least one condition, skip determining and / or reporting monitoring result of at least one other rank.22.The terminal device of claim 1, wherein the monitoring result is determined based on channel information or precoding matrix information.23.The terminal device of claim 22, wherein whether to determine the monitoring result based on the channel information or the precoding matrix information is indicated by the network device or determined based on capability information of the terminal device.24.A terminal device, comprising:a processor configured to cause the terminal device to:receive, from a network device, at least one configuration of a monitoring report; anddetermine the monitoring report by using at least one processing unit,wherein in accordance with a determination that the monitoring report is associated with an inference report, the at least one processing unit comprises a first number of processing units, and the first number is determined based on a number of processing units occupied for measurement and / or reporting non-artificial intelligence (AI) / machine learning (ML) related information, andwherein in accordance with a determination that the monitoring report is not associated with an inference report, the at least one processing unit comprises a second number of processing units, and the second number is determined based on at least one of a number of processing units occupied for measurement and / or reporting AI / ML related information, or the first number.25.A network device, comprising:a processor configured to cause the network device to:transmit, to a terminal device, at least one configuration of at least one monitoring report; andreceive the at least one monitoring report from the terminal device, wherein the at least one monitoring report comprises at least one of the following:a monitoring result per layer, determined based on at least one valid monitoring instance corresponding to the layer,a monitoring result per rank, determined based on at least one valid monitoring instance corresponding to the rank,information of at least one layer satisfying at least one first condition, orinformation of at least one rank satisfying at least one second condition.