Method and apparatus for determining predicted beams to report
The method addresses the challenge of accurately reporting predicted beams by configuring the number of beams and mapping their order, enhancing communication performance in complex networks.
Patent Information
- Application Number
- PCT/CN2024/084611
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-03-28
- Publication Date
- 2025-10-02
AI Technical Summary
Existing communication networks face challenges in accurately determining which predicted beams to report, particularly in cases where machine learning models output multiple predicted top beams, leading to ambiguity in how to determine and report these beams effectively.
A method is proposed for determining predicted beams to report, involving configuring the number of beams to report (K), mapping the order of predicted beams, and addressing duplication, using machine learning models to provide identities and probabilities of predicted elements.
This approach enhances the accuracy and efficiency of beam reporting by clarifying how to select and present predicted beams, improving communication performance in complex networks.
Smart Images

Figure CN2024084611_02102025_PF_FP_ABST
Abstract
Description
METHOD AND APPARATUS FOR DETERMINING PREDICTED BEAMS TO REPORT
[0001] FIELDS
[0002] Example embodiments of the present disclosure generally relate to the field of communication techniques and in particular, to method and apparatus for determining predicted beams to report.BACKGROUND
[0003] 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, machine learning (ML) / artificial intelligence (AI) technology is proposed to be used in the wireless communication network. For example, the terminal device and the network device may use different ML models to assist communication-related functionalities, such as, beam management (BM) , mobility management and so on.SUMMARY
[0004] In general, embodiments of the present disclosure provide a solution for providing inaccurate predicted information.
[0005] In a first aspect, there is provided a first device. The first device comprises: a processor configured to cause the first device to: receive, from a second device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event; obtain predicted information of a machine learning (ML) model, wherein, the predicted information comprising N groups of predicted results, N is an integer larger than 1, each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, each group comprises at least one predicted result of at least one predicted element, and each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element, determine, at least one predicted element to be reported based on at least one of the following: probabilities of predicted elements in the predicted results, or values of n associated with predicted elements in the predicted results; and transmit, to the second device, a report comprising identities of the at least one predicted element.
[0006] In a second aspect, there is provided a first device. The first device comprises: a processor configured to cause the first device to: generate, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer larger than 0, and the predicted element is a predicted beam, a predicted cell or a predicted event; and transmit the measurement report to a second device.
[0007] In a third aspect, there is provided a second device. The second device comprises: a processor configured to cause the second device to: transmit, to a first device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event; and receive, from the first device, a report comprising identities of the at least one predicted element, wherein the at least one predicted element is determined by the first device based on the first number and predicted information of a machine learning (ML) model, and wherein, the predicted information comprising N groups of predicted results, N is an integer larger than 1, each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, each group comprises at least one predicted result of at least one predicted element, and each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element.
[0008] In a fourth aspect, there is provided a second device. The second device comprises: a processor configured to cause the second device to: receive, from a first device, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer and the predicted element is a predicted beam, a predicted cell or a predicted event.
[0009] In a fifth aspect, there is provided a communication method performed by a first device. The method comprises: receiving, from a second device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event; obtaining predicted information of a machine learning (ML) model, wherein, the predicted information comprising N groups of predicted results, N is an integer larger than 1, each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, each group comprises at least one predicted result of at least one predicted element, and each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element, determining, at least one predicted element to be reported based on at least one of the following: probabilities of predicted elements in the predicted results, or values of n associated with predicted elements in the predicted results; and transmitting, to the second device, a report comprising identities of the at least one predicted element.
[0010] In a sixth aspect, there is provided a communication method performed by a first device. The method comprises: generating, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer larger than 0, and the predicted element is a predicted beam, a predicted cell or a predicted event; and transmitting the measurement report to a second device.
[0011] In a seventh aspect, there is provided a communication method performed by a second device. The method comprises: transmitting, to a first device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event; and receiving, from the first device, a report comprising identities of the at least one predicted element, wherein the at least one predicted element is determined by the first device based on the first number and predicted information of a machine learning (ML) model, and wherein, the predicted information comprising N groups of predicted results, N is an integer larger than 1, each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, each group comprises at least one predicted result of at least one predicted element, and each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element.
[0012] In an eighth aspect, there is provided a communication method performed by a second device. The method comprises: receiving, from a first device, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer and the predicted element is a predicted beam, a predicted cell or a predicted event.
[0013] In a ninth aspect, there is provided a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to carry out the method according to the fifth, sixth, seventh, or eighth aspect.
[0014] Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS
[0015] 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:
[0016] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;
[0017] FIG. 2A to 2D illustrate example AI / ML models for beam prediction in accordance with some embodiments of the present disclosure;
[0018] FIG. 3A to 3B illustrate signaling flows of communication in accordance with some embodiments of the present disclosure;
[0019] FIG. 4A to 4G illustrate example applications of AI / ML models in accordance with some embodiments of the present disclosure;
[0020] FIG. 5 illustrates a flowchart of a communication method implemented at a first device according to some example embodiments of the present disclosure;
[0021] FIG. 6 illustrates a flowchart of a communication method implemented at a first device according to some example embodiments of the present disclosure;
[0022] FIG. 7 illustrates a flowchart of a communication method implemented at a second device according to some example embodiments of the present disclosure;
[0023] FIG. 8 illustrates a flowchart of a communication method implemented at a second device according to some example embodiments of the present disclosure; and
[0024] FIG. 9 illustrates a simplified block diagram of an apparatus that is suitable for implementing example embodiments of the present disclosure.
[0025] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION
[0026] 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.
[0027] 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.
[0028] 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.
[0029] 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.
[0030] The terminal device or the network device may have Artificial intelligence (AI) or Machine learning capability. It generally includes a model which has been trained from numerous collected data for a specific function, and can be used to predict some information.
[0031] The terminal or the network device may work on several frequency ranges, e.g., FR1 (e.g., 450 MHz to 6000 MHz) , FR2 (e.g., 24.25GHz to 52.6GHz) , frequency band larger than 100 GHz as well as Tera Hertz (THz) . It can further work on licensed / unlicensed / shared spectrum. The terminal device may have more than one connection with the network devices under Multi-Radio Dual Connectivity (MR-DC) application scenario. The terminal device or the network device can work on full duplex, flexible duplex and cross division duplex modes.
[0032] 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.
[0033] 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.
[0034] 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.
[0035] 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.
[0036] As used herein, the terms “UE expects” , “UE does not expect, “terminal device expects” , “terminal device does not expect” may imply restrictions on a configuration of a network device (also referred to as NW configuration) . The terms “UE is not expected to” and “terminal device is not expected to” may imply a terminal implementation, also referred to as UE implementation. In some embodiments, the terms “UE does not expect” and “UE is not expected to” may be used equally.
[0037] As discussed above, the terminal device and the network device may use different ML models to assist communication-related functionalities, such as, beam management (BM) , mobility management and so on.
[0038] So far, two BM cases (i.e., BM-case1 and BM-case2) have been proposed and discussed separately, specifically,
[0039] ● BM-Case1: Spatial-domain downlink beam prediction for Set A of beams based on measurement results of Set B of beams;
[0040] Consider: 1) : artificial intelligence (AI) / machine learning (ML) model training and inference at NW side. 2) : AI / ML model training and inference at UE side.
[0041] Consider: 1) : Set A and Set B are different (Set B is not a subset of Set A) . 2) : Set B is a subset of Set A. Note: Set A is for DL beam prediction.
[0042] AI / ML model input consider: 1) : only L1-RSRP measurement based on Set B; 2) : L1-RSRP measurement based on Set B and assistance information; 3) : channel impulse response (CIR) based on Set B; 4) : layer 1 (L1) -reference signal receiving power (RSRP) measurement based on Set B and the corresponding DL Tx and / or Rx beam ID.
[0043] ● BM-Case2: Temporal Downlink beam prediction for Set A of beams based on the historic measurement results of Set B of beams;
[0044] Consider: 1) : AI / ML model training and inference at NW side. 2) : AI / ML model training and inference at UE side.
[0045] Consider: 1) : Set A and Set B are different (Set B is NOT a subset of Set A) . 2) : Set B is a subset of Set A (Set A and Set B are not the same) . 3) : Set A and Set B are the same.
[0046] AI / ML model input consider: measurement results of K (K≥1) latest measurement instances with the following alternatives: 1) : Only L1-RSRP measurement based on Set B; 2) : L1-RSRP measurement based on Set B and assistance information; 3) : L1-RSRP measurement based on Set B and the corresponding DL Tx and / or Rx beam ID.
[0047] F predictions for F future time instances can be obtained based on the output of AI / ML model, where each prediction is for each time instance. At least F=1.
[0048] Set B is a set of beams whose measurements may be taken as inputs of the AI / ML model.
[0049] It has been agreed to provide specification support for the following aspects:
[0050] ● Beam management -DL Tx beam prediction for both UE-sided model and NW-sided model, encompassing:
[0051] - Spatial-domain DL Tx beam prediction for Set A of beams based on measurement results of Set B of beams ( “BM-Case1” ) ;
[0052] - Temporal DL Tx beam prediction for Set A of beams based on the historic measurement results of Set B of beams ( “BM-Case2” ) ;
[0053] - Specify necessary signalling / mechanism (s) to facilitate LCM operations specific to the Beam Management use cases, if any;
[0054] - Enabling method (s) to ensure consistency between training and inference regarding NW-side additional conditions (if identified) for inference at UE.
[0055] ● Strive for common framework design to support both BM-Case1 and BM-Case2.
[0056] It has been agreed that for UE-sided model at least for BM-Case1, for content in the report of inference results, to support that the first option is beam information on predicted Top K beam (s) among a set of beams. The second option is beam information on predicted Top K beam (s) among a set of beams and RSRP of predicted Top K beam (s) among a set of beams. Furthermore, the agreement includes: at least K=1 and more. The third option is beam information on predicted Top K beam (s) among a set of beams and probability information of predicted Top K beam (s) among a set of beams. Furthermore, the agreement includes probability information is the probability of the beam to be the Top 1 or Top K beam. The fourth option is beam information on predicted Top K beam (s) among a set of beams, RSRP of predicted Top K beam (s) among a set of beams, and confidence information of the RSRP. So far, other options are not precluded. In the agreement, the set of beams is Set A, namely the beams for UE prediction.
[0057] Further, it also needs to study and evaluate potential benefits and gains of AI / ML aided mobility for network triggered layer 3 (L3) -based handover, considering the following aspects:
[0058] ● AI / ML based RRM measurement and event prediction,
[0059] - Cell-level measurement prediction including intra and inter-frequency (UE-sided and NW-sided model) . Inter-cell Beam-level measurement prediction for L3 Mobility (UE sided and NW sided model) ;
[0060] - Handover (HO) failure / radio link failure (RLF) prediction (UE sided model) ;
[0061] - Measurement events prediction (UE sided model) ;
[0062] ● Study the need / benefits of any other UE assistance information for the network side model;
[0063] ● Potential AI mobility specific enhancement should be based on the AI / ML-air interface work item description (WID) general framework (e.g. life cycle management (LCM) , performance monitoring and so on) .
[0064] For better descriptions, some terms used herein are listed as below:
[0065] Beam can be replaced or represented by beam ID, where the beam ID is interchangeably with (Tx / Rx) beam ID, RS (e.g., Channel state information reference signal, CSI-RS, synchronization signal or physical broadcast channel (PBCH) Block, SSB, sounding reference signal, SRS) ID, RS resource ID (e.g., CSI-RS resource indicator (CRI) , SRS resource indicator (SSBRI) ) , transmission configuration indicator (TCI) state ID, quasi co-location (QCL) RS (e.g., QCL-typeD RS) ID, measurement RS ID, measurement RS resource ID, path-loss RS ID. Beam may be interchangeably with (Tx / Rx) beam, beam direction / orientation, RS (e.g., CSI-RS, SSB, SRS) , RS resource, TCI state, QCL RS (e.g., QCL-typeD RS) , measurement RS, measurement RS resource, path-loss RS.
[0066] Measurement result (s) / beam quality may include but be not limited to, L1-reference signal received power (RSRP) , L1-SINR, L1-received signal strengthen indicator (RSSI) , L1-reference signal received quality (RSRQ) , receive signal channel power (RSCP) , RSRP, SINR, RSSI, or RSRQ.
[0067] Predicted L1-RSRP means a predicted quality / metric related to beam, cell or measurement event, and / or outputted by the AI / ML model related to beam prediction, cell prediction or measurement event prediction.
[0068] RRC message is a L3 signaling. MAC CE is a L2 signaling. Uplink control information (UCI) is a L1 signaling. Each of them may be transmitted in PUSCH or / and physical uplink control channel (PUCCH) .
[0069] Measurement report initiated by UE means that a measurement report triggered or initiated by UE based on certain pre-defined or NW configured event (s) .
[0070] Indicator of set may refer to RS resource set ID, where each RS resource in the RS resource corresponds to a beam.
[0071] Model inference means a process of using a trained AI / ML model to produce a set of outputs based on a set of inputs.
[0072] Model training means a process to train an AI / ML Model [by learning the input / output relationship] in a data driven manner and obtain the trained AI / ML Model for inference.
[0073] Model switching means deactivating a currently active AI / ML model and activating a different AI / ML model for a specific AI / ML-enabled feature.
[0074] Model selection means a process of selecting an AI / ML model for activation among multiple models for the same AI / ML enabled feature.
[0075] Model update means a process of updating the model parameters and / or model structure of a model.
[0076] Model activation means to enable an AI / ML model for a specific AI / ML-enabled feature.
[0077] Model monitoring means a procedure that monitors the inference performance of the AI / ML model.
[0078] Reference data distribution means a data distribution corresponding to a dataset used for training / validating / testing / updating an AI / ML model.
[0079] Period of time means a time duration where performance monitoring is performed. And it is interchangeably with time window, time duration, timer, monitoring window.
[0080] Beam report may refer to measurement report, which may be periodic, semi-persistent or aperiodic report configured by NW (e.g., CSI report) , or event / UE triggered / initiated report. The beam report may be carried by an UCI, UL MAC CE or UL RRC.
[0081] Top 1 / 2 / 3 / M beam in a set of beams refers to a beam at least satisfying the following condition: at least one quantity (e.g., beam quality, probability, parameter related to beam performance) associated with the beam is the 1st / 2nd / 3rd / M-th largest (or lowest) in the set of beams. In this patent, ‘1’ , ‘2’ or ‘3’ , …, etc. is called as ‘top number’ or ‘top level’ for the convenience of description.
[0082] ‘Top M (M>1) beams in a set of beams’ includes the top 1 beam in the set, the top 2 beam in the set, the top 3 beam in the set, …, and the top M beam in the set.
[0083] The predicted top 1 beam in a set of beams may refer to a predicted beam associated with the largest probability, where the probability is the probability of the (predicted) beam is to be the top 1 beam in the set of beams, the predicted top 2 beam in a set of beams may refer to a predicted beam associated with the largest probability, where the probability is the probability of the (predicted) beam is to be the top 2 beam in the set of beams, et cetera. Optionally, the predicted top beam may not be limited to just referring to a predicted beam associated with the largest probability. It may also be depend on design of (the output of) the AI / ML model, e.g., the AI / ML model will associate each predicted beam with an ID, which is used to indicate which top beam (e.g., top 1 beam, top 2 beam) the associated predicted beam is.
[0084] Top-1 beam means the beam having the largest beam (measured or predicted) quality (e.g., L1-RSRP, L1-SINR) in a set of beams.
[0085] Top-1 cell means the cell having the largest (measured or predicted) quality (e.g., RSRP, SINR, RSRQ) in a set of cells, it can be interchangeably with target cell.
[0086] In the context of the present disclosure,
[0087] terms “beam” may be replaced by “beam pair” ;
[0088] terms “ID” , “identifier” , “identity” , “index” or “indicator” , “indication” may be used interchangeably;
[0089] Occur may be replaced with declare, happen, take place.
[0090] Condition may be replaced with (pre-defined) condition, event, rule, criterion.
[0091] Accurate may be replaced with precise, good, success, correct, right, exact, true.
[0092] Inaccurate may be replaced with incorrect, inexact, improper, wrong, not good, bad, failure, false.
[0093] Parameter may be replaced with information element (IE) , higher layer (e.g., RRC layer) configuration / parameter.
[0094] Group may be replaced with interchangeably with set, list.
[0095] Configure may be replaced with indicate, provide, activate, trigger.
[0096] Equal is interchangeably with same, consistent, close, similar.
[0097] Maintain is interchangeably with keep, store, hold, reserve.
[0098] Reporting (time) instance is interchangeably with report setting, report, measurement report.
[0099] ‘Top W (W≥1) beam’ is interchangeably with ‘Top W beams’ , ‘Top 1 / W beam’ , ‘Top W / 1 beam’ .
[0100] Probability may be replaced with proportion, ratio, confidence (level / interval) .
[0101] Report may be replaced with transmit, send, provide, indicate.
[0102] Terminal device / UE (or network device / NW) may be replaced with OTT (server) , OAM (server) , CN (server) , edge cloud (server) , transmission reception point (TRP) ;
[0103] Predicted time instance may be replaced with (future or predicted) time instance, time point, time stamp, time interval, time.
[0104] Cell may be replaced with serving / non-serving / source / target / candidate cell, (active or inactive) DL / UL BWP, frequency range, frequency carrier, carrier component (CC) , cell group, PCell, SCell, PScell, (cell) configuration for mobility / measurement / report (e.g., LTM / CLTM cell configuration) . Cell may be replaced or represented by indicator of cell, where the indicator of cell may refer to PCI (physical cell identifier) , serving cell index, SSB index, cell ID, LTM candidate ID, measurement ID, report ID.
[0105] Zone may be replaced with region, site, area, sector, location. And it may comprise one or multiple cells (or / and partial regions of cell) .
[0106] Predict may be replaced with inference, output, estimate.
[0107] Output is interchangeably with infer, predict, estimate, calculate, determine.
[0108] Future time instance is interchangeably with predicted / future time instance / interval / stamp / duration / point, beam application time / dwelling time.
[0109] Probability is interchangeably with proportion, ratio, confidence (level / interval) . For example, the probability can be a probability of the beam to be the top K (K≥1) beam.
[0110] Available is interchangeably with applicable.
[0111] Predicted beam may be interchangeably with beam.
[0112] As used herein, term “specific” means predefined, predetermined, particular, or unique. For example, a specific beam may refer to a predefined beam, a predetermined beam, a particular beam, or a unique beam.
[0113] As used herein, the threshold mentioned in this patent may be configured by NW and optionally based on a UE capability information.
[0114] As used herein, model may refer to AI / ML, AI / ML model, functionality, AI / ML functionality, AI-enabled feature / feature group (FG) , which means 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. AI / ML-enabled feature refers to a feature where AI / ML may be used.
[0115] Model ID may be one of the following: functionality ID, dataset ID, scenario ID, zone ID, configuration ID, quantization ID, local (model) ID, global (model) ID, logical (model) ID, physical (model) ID, etc.
[0116] UE-side (AI / ML) model means an AI / ML Model whose inference is performed entirely at the UE.
[0117] The result outputted by the AI / ML model may comprise at least one of predicted beam, predicted RSRP, probability (associated with predicted beam) . For example, the (predicted) beam outputted by the AI / ML model means that the (predicted) beam is determined based on the AI / ML model, or the output of the AI / ML model.
[0118] In some embodiments, an input of the ML model (i.e., AI input) may refer to the input of a model and indicate data inputted into the model, which may be equivalent to data.
[0119] In some embodiments, an output of ML model (i.e., AI output) may refers to the output of a model and indicate result (s) outputted by the model, which is equivalent to label / data.
[0120] In some embodiments, the model may comprise a set of weights values that may be learned during training, for example for a specific architecture or configuration, where a set of weights values may also be called a parameter set.
[0121] Wording ‘Acorresponds to B’ may be replaced by ‘A is associated with B’ , ‘A is mapped to B’ , or ‘B is mapped to A’ . Term ‘confidence’ may be replaced by uncertainty, reliability, probability, confidence level.
[0122] It should be noted that, examples where the inaccurate predicted information are provided. As the accurate predicted information and inaccurate predicted information are corresponding with each other, and thus all the examples related to inaccurate predicted information also may be applicable to the cases of providing accurate predicted information. Merely for brevity, the same or the similar contents are omitted herein.
[0123] The current proposal has agreed that UE may report predicted top K beam (s) for beam prediction using UE-side AI / ML model. Further, at least the following issues need to be addressed, especially in the case of the output of the AI / ML model are multiple predicted top beams (or multiple distinct probabilities) . The first issue is that specifying or defining the predicted top K beam (s) to report. In other words, there is a lack of how UE determines the predicted top K beam (s) to report from the results outputted by the AI / ML model. The second issue is that how to determine the value of K. In other words, there is a lack of how to determine the number of predicted beams to report.
[0124] To address these issues, the present disclosure proposes a novel method of determining predicted beams to report. The present disclosure includes determining predicted beams to report, UE capability affecting configuration of K, the methods may be configurable, mapping order of the predicted beams to report, duplication of predicted beams to report, and a new method of reporting predicted beams.
[0125] Principles and implementations of the present disclosure will be described in detail below with reference to the figures.
[0126] Example environment
[0127] 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 first device 110 and a second device 120, can communicate with each other.
[0128] Further, multiple input multiple output (MIMO) is supported in the communication environment 100, such that the second device 120 and the first device 110 may communicate with each other via different beams to enable a directional communication.
[0129] In FIG. 1, the first device 110 / second device 120 may be included a terminal device, a network device, an over the top (OTT) (server) , an operation administration and maintenance (OAM) (server) , an edge cloud (server) , a neutral site, core network, transmission reception point (TRP) and so on.
[0130] As one example scenario, the first device 110 may include a terminal device and the second device 120 may include a network device serving the terminal device. In this specific example embodiment, a link from the first device 110 to the second device 120 is referred to as uplink, while a link from the second device 120 to the first device 110 is referred to as a downlink.
[0131] In downlink, the second device 120 is a transmitting (TX) device (or a transmitter) and the first device 110 is a receiving (RX) device (or a receiver) , and the second device 120 may transmit downlink transmission to the first device 110 via one or more beams. As illustrated in FIG. 1, the second device 120 transmits downlink transmission to the first device 110 via the beams 140-1 to 140-3. For purpose of discussion, the beams 140-1 to 140-3 are collectively or individually referred to as beam 140.
[0132] Correspondingly, in uplink, the second device 120 is an RX device (or a receiver) and the first device 110 is a TX device (or a transmitter) , and the first device 110 may transmit uplink transmission to the second device 120 via one or more beams. As illustrated in FIG. 1, the first device 110 transmits uplink transmission to the second device 120 via the beams 130-1 to 130-3. For purpose of discussion, the beams 130-1 to 130-3 are collectively or individually referred to as beam 130.
[0133] In some embodiments, one or more models may be deployed at the second device 120 and / or the first device 110. As illustrated in FIG. 1, the model 115 is deployed at the first device 110.
[0134] 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.
[0135] In some embodiments, the first device 110 and the second device 120 may communicate with each other via a channel such as a wireless communication channel on an air interface (e.g., Uu interface) . The wireless communication channel may comprise a physical uplink control channel (PUCCH) , a physical uplink shared channel (PUSCH) , a physical random-access channel (PRACH) , a physical downlink control channel (PDCCH) , a physical downlink shared channel (PDSCH) and a physical broadcast channel (PBCH) . Of course, any other suitable channels are also feasible.
[0136] 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.
[0137] Example processes
[0138] Taking spatial beam prediction (i.e., BM-Case1) using UE-side model as an example.
[0139] In some embodiments, NW may configure for UE a set of beams (e.g., Set A) and a further set of beams (e.g., Set B) , which may be associated with at least one AI / ML model (called as ‘the AI / ML model’ for short) . Specifically, the set of beams may be used as predicted beams in model inference, i.e., the output (s) of the at least one AI / ML model may derive from the set of beams, so the beam in the set of beams can be called as ‘predicted beam’ . The further set of beams may be used as measured beams in model inference, i.e., the input (s) of the at least one AI / ML model may derive from the measurements of the further set of beams, so the beam in the further set of beams can be called as ‘measured beam’ .
[0140] In some embodiments, UE may calculate qualities (e.g., L1-RSRPs) of at least one beam (generally, all measured beams) in the further set (i.e., determine measured L1-RSRPs of at least one beam in the further set) .
[0141] Based on the AI / ML model and the measured L1-RSRPs, UE may determine at least one of the following shown in FIG. 2A to 2D, which illustrate example AI / ML models for beam prediction in accordance with some embodiments of the present disclosure.
[0142] For the sake of facilitating the description, K and N are introduced in this patent, and their interpretations or definitions are provided as follows. K is / represents the number of predicted beams to report (in one reporting instance) , i.e., the number of beams in the set of (predicted) beams to report mentioned in above procedure. It may be provided by NW by using RRC / MAC CE / downlink control information (DCI) (e.g., using higher layer parameter ‘nrofReportedRS’ ) . N is / represents the maximum / largest top number corresponding to the predicted (top) beam (s) (outputted by the AI / ML model) .
[0143] If the output is 1 predicted top beam (e.g., top 1 beam) in a set of beams, the corresponding AI / ML model may be designed as follows shown in FIG. 2A and FIG. 2C. For this case, there is only one probability, i.e., probability of the beam to be the top 1 beam.
[0144] Reference is now made to FIG. 2A and 2C, where the N may be equal to 1. In the example of FIG. 2A, which illustrates an AI / ML model for beam prediction in accordance with some embodiments of the present disclosure. Considering that, the AI / ML model may only be an executable file for UE, meaning the output at UE side may be limited. Therefore, the AI / ML model may only output the top 1 beam (in Set A) , or output the top 1 beam (in Set A) and associated probability.
[0145] Reference is made to FIG. 2C, which illustrates another AI / ML model for beam prediction in accordance with some embodiments of the present disclosure. Generally, especially in the case of the AI / ML model is trained by UE itself, the AI / ML model at UE side may output probabilities associated with all beams in Set A. Furthermore, the predicted top 1 beam may be the beam associated with the largest probability.
[0146] If the output are multiple predicted top beams (e.g., top 1 beam, top 2 beam, top 3 beam, top 4 beam and so on) in a set of beams, the corresponding AI / ML model may be designed as follows shown in FIG. 2B and FIG. 2D. For this case, there are four different distinct probabilities, i.e., probability of the beam to be the top 1 beam, top 2 beam, top 3 beam, or top 4 beam.
[0147] Reference is made to FIG. 2B, which illustrates an AI / ML model for beam prediction in accordance with some embodiments of the present disclosure. Considering that, the AI / ML model may only be an executable file for UE, meaning the output at UE side may be limited. Therefore, the AI / ML model may only output the top 4 beams (in Set A) , or output the top 4 beams (in Set A) and associated probabilities. As shown in FIG. 2B, there is at least one predicted top beam (in the set) , and probability (ies) associated with the at least one predicted top beam (if exist or available) . If there are multiple predicted top beams, their associated probabilities are distinct, e.g., predicted top 1 beam is associated with the probability of the beam (in the set) to be the top 1 beam (in the set) , predicted top 2 beam is associated with the probability of the beam (in the set) to be the top 2 beam (in the set) .
[0148] Reference is made to FIG. 2D, which illustrates another AI / ML model for beam prediction in accordance with some embodiments of the present disclosure. Generally, especially in the case of the AI / ML model is trained by UE itself, the AI / ML model at UE side may output probabilities associated with all beams in Set A. Furthermore, the predicted top 1 beam may be the beam associated with the largest probability (of the beam to be the top 1 beam) , the predicted top 2 beam may be the beam associated with the largest probability (of the beam to be the top 2 beam) , the predicted top 3 beam may be the beam associated with the largest probability (of the beam to be the top 3 beam) , the predicted top 4 beam may be the beam associated with the largest probability (of the beam to be the top 4 beam) .
[0149] As shown in FIG. 2D, probability (ies) may be associated with at least one predicted beam in the set (e.g., generally, probabilities associated with all predicted beams in the set) . Additionally, in some embodiments, the probability (ies) may comprise one or more distinct probabilities, e.g., probability of the beam (in the set) to be the top 1 beam (in the set) , probability of the beam (in the set) to be the top 2 beam (in the set) . It can be considered that each probability corresponds to a top number, e.g., probability of the beam to be the top 1 beam corresponds to the top number ‘1’ .
[0150] Reference is made to FIG. 3A to 3B, which illustrate signaling flows 300A and 300B for communication in accordance with some embodiments of the present disclosure. For the purposes of discussion, the signaling flow 300A will be discussed with reference to FIG. 1, for example, by using the first device 110 and the second device 120.
[0151] It is to be understood that the operations at the first device 110 and the second device 120 should be coordinated. In other words, the second device 120 and the first device 110 should have common understanding about configurations, parameters and so on. Such common understanding may be implemented by any suitable interactions between the second device 120 and the first device 110 or both the second device 120 and the first device 110 applying the same rule / policy. In the following, although some operations are described from a perspective of the first device 110, it is to be understood that the corresponding operations should be performed by the second device 120. Similarly, although some operations are described from a perspective of the second device 120, it is to be understood that the corresponding operations should be performed by the first device 110. Merely for brevity, some of the same or similar contents are omitted here.
[0152] For the purpose of discussion, the first device 110 may be a terminal device and the second device 120 may be a network device. It should be understood that, in the other embodiments, the first device 110 / second device 120 may be any of: a terminal device, a network device, an over the top (OTT) (server) , an operation administration and maintenance (OAM) (server) , an edge cloud (server) , a neutral site, transmission reception point (TRP) core network and so on. In present disclosure is not limited in this regard.
[0153] In the present disclosure, an element may be a beam, a cell, an event or any other element which may be predicted by an ML mode. Further, the predicted information may be related to at least of the following: at least one predicted beam, at least one predicted cell, or at least one predicted event. In view of this, terms of beam, cell and event may be used interchangeably.
[0154] As shown in FIG. 3A, the first device 110 receives (310) , from a second device 120, configuration information indicating a first number of predicted elements to be reported (represented as K) , wherein the predicted element is a predicted beam, a predicted cell or a predicted event. Then the first device 110 obtains (320) predicted information of a machine learning (ML) model, wherein the predicted information comprising N groups of predicted results, N is an integer larger than 1, each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, each group comprises at least one predicted result of at least one predicted element, and each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element.
[0155] The first device 110 determines (330) , at least one predicted element to be reported, based on at least one of probabilities of predicted elements in the predicted results, or values of n associated with predicted elements in the predicted results. Then the first device 110 transmits (340) , to the second device 120, a report comprising identities of the at least one predicted element.
[0156] In some embodiments, in a case that a value of N is the same as the first number (such as, K=N=1, or K=N=4) and the number of predicted results in each group is 1, the first device 110 determines (330) the at least one predicted element to be reported which are all of the predicted elements of the ML model. In the example of FIG. 2A and 2B, all the predicted beams are determined to be reported.
[0157] In some embodiments, in a case that the first number is 1 (K=1) and a value of N is 1 (N=1) and the number of predicted results in the group corresponding to a prediction of being a top 1 element is larger than 1, the first device 110 determines (330) the at least one predicted element to be reported, which is one predicted element with a largest probability in the group of predicted results corresponding to a prediction of being a top 1 element. In the example of FIG. 2C, predicted top1 beam to top K beam are determined to be reported.
[0158] In some embodiments, the first number is larger than 1 (K>1) and a value of N is 1 (N=1) . In a case that a number of predicted results in the group corresponding to a prediction of being a top 1 element is larger than the first number, the first device 110 determines (330) at least one predicted element to be reported, which are top M predicted elements in the group of predicted results corresponding to a prediction of being a top 1 element according to a descending order of probability, and M equals to the first number. In the example of FIG. 2C, top M beams are determined to be reported according to a descending order of probability.
[0159] In some embodiments, the first number is larger than 1 (K>1) and a value of N is larger than or equal to the first number, in a case that a number of predicted results in each group is 1, the first device 110 determines (330) at least one predicted element to be reported:
[0160] ● M predicted elements comprised in M groups of predicted results, each group corresponding to a prediction of being a top n element, wherein M equals to the first number and n is smaller than or equal to the first number;
[0161] ● top M predicted elements comprised in M groups of predicted results according to a descending order of probability; or
[0162] ● the first M predicted elements in M groups of predicted results, a probability of the predicted element being larger than or equal to a threshold.
[0163] In some embodiments, if the number of predicted results in each group is larger than 1, each of the predicted element is a predicted element with a largest probability in a respective group of predicted results.
[0164] In some embodiments, if more than one predicted element is associated with a same probability, the first device 110 determines (330) at least one of the following is prioritized:
[0165] ● a predicted element associated with a lowest identity is prioritized,
[0166] ● a predicted element associated with a highest identity is prioritized, or
[0167] ● a predicted element associated with a measured element is prioritized.
[0168] In some embodiments, if a number of predicted elements with a probability larger than or equal to the threshold is smaller than the first number, the first device 110 determines (330) at least one predicted element comprised in at least one group associated with a lower value of n as the at least one predicted element to be reported.
[0169] In some embodiments, the first number is larger than 1 and the number of predicted results in each group is larger than 1, and the at least one predicted element to be reported is determined to be the following: top M predicted elements comprised in predicted results of the ML model according to a descending order of probability, wherein M equals to the first number.
[0170] In some embodiments, in a case that the first number is larger than 1, a value of N is larger than 1, and the number of predicted results in each group is larger than the first number determine the at least one predicted element to be reported as below: for each group of predicted results, determine top M predicted elements according to a descending order of probability; determines a sum of the M probabilities of the top M predicted elements for each group of predicted results; and determine the top M predicted elements with a largest sum as the at least one predicted element to be reported.
[0171] In some embodiments, the first number is larger than 1, a value of N is larger than 1, and the number of predicted results in each group is larger than the first number, the first device 110 determines a first group where a sum of top M probabilities of the M predicted elements in the group of predicted results is larger than or equal to a threshold, and the first device 110 determines (330) the M predicted elements in the first group as the at least one predicted element to be reported.
[0172] In some embodiments, the first device 110 transmits, to the second device 120, information about at least one of the following: a maximum value of N, whether the ML model supports outputting more than one predicted top beam, whether the ML model supports outputting probability, whether the ML model supports outputting the largest probability, or whether the ML model supports outputting probability associated with each predicted beam.
[0173] In some embodiments, the at least one predicted element is different from each other.
[0174] Reference is now made to FIG. 3B. In the example of FIG. 3B, the first device 110 generates (350) a measurement report indicating a plurality predicted results of a plurality predicted elements. The plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer larger than 0, and the predicted element is a predicted beam, a predicted cell or a predicted event; and the first device 110 transmits (360) the measurement report to a second device 120.
[0175] In some embodiments, the first device 110 receives (345) , from the second device 120, configuration information indicating a first number indicating a number of groups of predicted elements to be reported and at least one of the following: a second number indicating a number of predicted elements to be reported in each group, or at least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more groups, or wherein any of the first, second or the third number is determined by the first device 110.
[0176] In some embodiments, the measurement report further comprises at least one of the following: a first number indicating a number of groups of predicted elements to be reported, or a second number indicating a number of predicted elements to be reported in each group, or at least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more group.
[0177] In some embodiments, the measurement report comprises: a first part comprising at least one of the following: the first number, the second number or the at least one third number; and a second part comprising at least one of the following: identities of the at least one group of predicted results, identities of the plurality predicted elements, probabilities of the plurality predicted elements.
[0178] Embodiments
[0179] In order to better understanding the above processes, some example embodiments will be further discussed, where a UE is used as an example of the first device and an NW is used as an example of the second device.
[0180] In some embodiments, UE may determine K predicted beam (s) to report may be based on at least one of the following: for model type 1 (such as, illustrated in FIG. 2A and FIG. 2B) , the at least one predicted top beam, and the probability (ies) associated with the at least one predicted top beam, or for model type 2 (such as, illustrated in FIG. 2C and FIG. 2D) , the probability (ies) associated with the at least one predicted beam (in the set) . UE may report the (determined) K predicted beam (s) to NW in a measurement report. In this case, UE may know which predicted top beams or predicted beams (outputted by the AI / ML model) need to be reported.
[0181] In some embodiments, the K predicted beam (s) to report may be called as ‘reported K predicted beam (s) ’ for short.
[0182] In some embodiments, for model type 2, general speaking, the at least one predicted beam may be likely to include more than one predicted beam, so it is called as ‘predicted beams’ .
[0183] When N = 1 and K = N, i.e., N=1 and K=1. In some embodiments, for model type 1, the AI / ML model may output only one predicted top beam (e.g., predicted top 1 beam) . In this case, UE may determine the reported K predicted beam based on the (one) predicted top beam, i.e., the reported 1 predicted beam includes the predicted top 1 beam. In some other embodiments, for model type shown in FIG. 2D, UE may determine the reported K predicted beam based on the probabilities associated with the predicted beams. In this case, all probabilities may be the probability of the beam to be the top 1 beam. Specifically, the reported K predicted beam (i.e., reported 1 predicted beam) includes the predicted beam associated with the largest probability, where the probability is the probability of the beam to be the top 1 beam.
[0184] Additionally, in some embodiments, if the probabilities associated with different predicted beams are equal, the predicted beam satisfying at least one of the following is prioritized to be included in the reported K predicted beam. The predicted beam may comprise the following. In some embodiments, the predicted beam is associated with the lowest beam ID. In some embodiments, the predicted beam is associated with the largest beam ID. In some other embodiments, the predicted beam is (or associated with) a measured beam. In other words, UE maintained a measured RSRP corresponding to the predicted beam. For example, the predicted beam is (or associated with) a measured beam in the further set (associated with the set) .
[0185] When N = 1 and K > N, i.e., N=1 and K=4. In some embodiments, for model type 1, this case may not exist. In some other embodiments, for model type 2, similar to when N = 1 and K = N, UE may determine the reported K predicted beams based on the probabilities associated with the predicted beams. In this case, all probabilities may be the probability of the beam to be the top 1 beam. Specifically, the reported K predicted beams (i.e., reported 4 predicted beams) include the (top) 4 predicted beams associated with the largest probability 410, as shown in FIG. 4A, where the probability is the probability of the beam to be the top 1 beam.
[0186] Additionally, in some embodiments, if the probabilities associated with different predicted beams are equal, the predicted beam satisfying at least one of the following is prioritized to be included in the reported K predicted beams. The predicted beam may comprise the following. In some embodiments, the predicted beam is associated with the lowest beam ID. In some embodiments, the predicted beam is associated with the largest beam ID. In some other embodiments, the predicted beam is (or associated with) a measured beam.
[0187] When N > 1 and K < N, e.g., N=4 and K=2. For model type 1, in some embodiments, UE may determine the reported K predicted beams based on top numbers (e.g., 1, 2, 3, 4) corresponding to the at least one predicted top beam. For example, the reported 2 predicted beams include the (top) 2 predicted top beams 420 with the lowest top number, i.e., predicted top 1 beam and predicted top 2 beam, as shown in FIG. 4B.
[0188] In some embodiments, UE may determine the reported K predicted beams based on probabilities associated with the at least one predicted top beam. Specifically, for example, assuming the AI / ML model outputs four predicted top beams and associated probabilities: predicted top 1 beam in the set and associated probability (e.g., 85%) , predicted top 2 beam in the set and associated probability (e.g., 95%) , predicted top 3 beam in the set and associated probability (e.g., 99%) , predicted top 4 beam in the set and associated probability (e.g., 75%) , the reported 2 beams may include the (top) 2 predicted top beams 430 with the largest probability, i.e., predicted top 2 beam and predicted top 3 beam, as shown in FIG. 4C.
[0189] Additionally, in some embodiments, if the probabilities associated with different predicted top beams are equal, the predicted top beam satisfying at least one of the following is prioritized to be included in the reported K predicted beams. In some embodiments, the predicted top beam corresponds to the lowest top number. In some embodiments, the predicted top beam is (or associated with) a measured beam. In some other embodiments, the predicted top beam is associated with the lowest or largest beam ID.
[0190] In some other embodiments, UE may determine the reported K predicted beams based on top numbers (e.g., 1, 2, 3, 4) corresponding to the at least one predicted top beam, probabilities associated with the at least one predicted top beam, and at least one criterion / threshold. Specifically, UE may determine predicted top beam (s) satisfying the following criterion / threshold in the at least one predicted top beam, for example, the probability associated with the predicted top beam is larger than or equal to a threshold related to probability (e.g., 80%) . The reported K predicted beams may include the predicted top beam (s) with the lowest top number in the predicted top beam (s) determined based on the above criterion / threshold. For example, assuming the threshold related to probability is 80%, in the above case (mentioned in the prior embodiment) , it can be observed that the predicted top 1 beam, the predicted top 2 beam and the predicted top 3 beam can satisfy the above criterion / threshold. Therefore, the reported 2 beams 440 include the predicted top 1 beam and the predicted top 2 beam, as shown in FIG. 4D. Furthermore, if there is no predicted top beam satisfying the above criterion / threshold, or the number of satisfied predicted top beams is less than the K, the reported K predicted beams may include the predicted top beam with the lowest top number in the unsatisfied predicted top beams, or an indication information of this event (i.e., there is no predicted top beam satisfying the above criterion / threshold) .
[0191] When N > 1 and K < N, e.g., N=4 and K=2. For model type 2, in some embodiments, UE may determine the reported K predicted beams based on top numbers (e.g., 1, 2, 3, 4) corresponding to the predicted beams, and probabilities associated with the predicted beams. Specifically, for the predicted beams corresponding to each top number (i.e., 1, 2, 3, 4) , UE may determine the predicted beam associated with the largest probability. If the probabilities associated with different predicted beams are equal, the method mentioned when N = 1 and K = N may be adopted. Then, in the 4 determined predicted beams (associated with the largest probability) , the reported K predicted beams include the (top) K predicted beams with the lowest top number. This embodiment is similar to the first embodiment for model type 1 when N > 1 and K < N, e.g., N=4 and K=2, with an additional step to determine the predicted top beam based on the probabilities associated with the predicted beams.
[0192] In some embodiments, UE may determine the reported K predicted beams based on top numbers (e.g., 1, 2, 3, 4) corresponding to the predicted beams, probabilities associated with the predicted beams, and at least one criterion / threshold. Specifically, for the predicted beams corresponding to each top number (i.e., 1, 2, 3, 4) , UE may determine the predicted beam associated with the largest probability. If the probabilities associated with different predicted beams are equal, the method mentioned when N = 1 and K = N may be adopted. In the 4 determined predicted beams (associated with the largest probability) , similar to the second embodiment for model type 1 in this case, UE may further determine the (top) 2 predicted beams associated with the largest. If the probabilities associated with different predicted beams are equal, the method mentioned when N = 1 and K = N may be adopted. This embodiment is similar to the second embodiment for model type 1 when N > 1 and K < N, e.g., N=4 and K=2, with an additional step to determine the predicted top beam based on the probabilities associated with the predicted beams.
[0193] In some embodiment, UE may determine the reported K predicted beams based on top numbers (e.g., 1, 2, 3, 4) corresponding to the predicted beams, probabilities associated with the predicted beams, and at least one criterion / threshold. Specifically, for the predicted beams corresponding to each top number (i.e., 1, 2, 3, 4) , UE may determine the predicted beam associated with the largest probability. If the probabilities associated with different predicted beams are equal, the method mentioned when N = 1 and K = N may be adopted. In the 4 determined predicted beams (associated with the largest probability) , similar to the third embodiment for model type 1 in this case, UE may determine predicted beam (s) satisfying the following criterion / threshold. The probability associated with the predicted beam is larger than or equal to a threshold related to probability (e.g., 80%) . The reported K predicted beams may include the predicted beam (s) with the lowest top number in the predicted beam (s) determined based on the above criterion / threshold. Furthermore, if there is no predicted beam satisfying the above criterion / threshold, or the number of satisfied predicted beams is less than the K, the reported K predicted beams may include the predicted beam with the lowest top number in the unsatisfied predicted beams, or an indication information of this event (i.e., there is no predicted beam satisfying the above criterion / threshold) . This embodiment is similar to the third embodiment for model type 1 when N > 1 and K < N, e.g., N=4 and K=2, with an additional step to determine the predicted top beam based on the probabilities associated with the predicted beams.
[0194] In some embodiments, UE may determine the reported K predicted beams based on probabilities associated with the predicted beams. For example, similar to the case when N = 1 and K = N, the reported K predicted beams include the (top) K predicted beams associated with largest probability.
[0195] In some embodiments, UE may determine the reported K predicted beams based on top numbers (e.g., 1, 2, 3, 4) corresponding to the predicted beams, probabilities associated with the predicted beams, and at least one criterion / threshold. Specifically, as shown in FIG. 4E, for the predicted beams corresponding to each top number (i.e., 1, 2, 3, 4) , UE determines (450) the (top) K predicted beams associated with the largest probability. If the probabilities associated with different predicted beams are equal, the method mentioned when N > 1 and K < N, e.g., N=4 and K=2 may be adopted. For each top number, UE may determine (452) the sum of the probabilities associated with the K predicted beams determined above. The reported K predicted beams include the K predicted beams corresponding to the top number corresponding to the largest sum of probabilities. If the sum of probabilities corresponding to different top numbers are equal, the K predicted beams corresponding to the top number satisfying at least one of the following: the lowest top number, at least one predicted beams corresponding to the top number is measured beam (s) , and the number of (corresponding) predicted beams that is measured beam is the largest for the top number.
[0196] In some other embodiments, UE may determine the reported K predicted beams based on top numbers (e.g., 1, 2, 3, 4) corresponding to the predicted beams, probabilities associated with the predicted beams, and at least one criterion / threshold. Specifically, as shown in FIG. 4F, for the predicted beams corresponding to each top number (i.e., 1, 2, 3, 4) , UE determines (460) the (top) K predicted beams associated with the largest probability. If the probabilities associated with different predicted beams are equal, the method mentioned when N = 1 and K = N may be adopted. UE may determine (462) top number (s) satisfying the following criterion. For the K predicted beams (determined above) corresponding to the top number, the sum of the probabilities associated with the K predicted beams is larger than or equal to a threshold related to probability (e.g., 90%) . The reported K predicted beams include the K predicted beams corresponding to the lowest top number in the satisfied top number (s) . If there is no satisfied top number, the above embodiments can be adopted.
[0197] When N > 1 and K = N, e.g., N=4 and K=4. For model type 1, in some embodiments, similar to when N = 1 and K = N, UE may determine the reported K predicted beams based on the (four) predicted top beams, i.e., the reported 4 predicted beams include the predicted top 1 beam, the predicted top 2 beam, the predicted top 3 beam and the predicted top 4 beam. For model type 2, in some embodiments, similar to when N > 1 and K < N, e.g., N=4 and K=2, the embodiments for model type 2 can be adopted.
[0198] When N > 1 and K > N, e.g., N=4 and K=8. For model type 1, in some embodiments, this case may not exist. For model type 2, similar to when N > 1 and K < N, e.g., N=4 and K=2, the embodiments for model type 2 can be adopted.
[0199] In case of temporal beam prediction (i.e., BM-Case2) using UE-side model, UE may determine at least one of the following. For model type 1, multiple sets of predicted top beams, where each set of predicted top beams includes at least one predicted top beam, and it is associated with a future time instance. Furthermore, for the same future time instance, each predicted top beam may be associated with a probability (if available) . For model type 2, multiple sets of predicted beams, where each set of predicted beams includes at least one predicted beam, and it is associated with a future time instance. Furthermore, for the same future time instance, each predicted beam may be associated with a probability (if available) . For each set of predicted top beams or predicted beams (in other words, for each future time instance) , UE may independently determine K predicted beam (s) to report based on at least one of the methods when N = 1 and K = N.
[0200] In some embodiments, UE may provide NW with at least one of the following information by using an UL RRC, UL MAC CE or UCI. Information related to the N. E.g., the maximum top number corresponding to the predicted beams outputted by the AI / ML model at UE side. For example, in the following figures, the N may be equal to 4, as shown in FIG. 2B and FIG. 2D. Information related to the K. E.g., the number (or the maximum number, or the minimum number) of predicted beams to report (in at least one beam report / reporting instance / report setting) supported / preferred / expected by UE. Where the UL RRC may be a UE capability information or UE Assistance Information (UAI) . Meanwhile, the UL RRC may be used to report information related to the AI / ML model associated with the information related to the N. NW may configure the K associated with a measurement report that is used for reporting predicted beams based on the information related to the N reported by UE. The key effect of this embodiment is that NW can configure the value of K reasonably.
[0201] In some embodiments, UE may report to NW a UL RRC message (e.g., UE capability information) , which indicates at least one of the following: the AI / ML model at UE side supports outputting more than one predicted top beam; the AI / ML model at UE side supports outputting probability; the AI / ML model at UE side supports outputting the largest probability; or the AI / ML model at UE side supports outputting probability associated with each predicted beam (in the set) , or probabilities associated with all predicted beams (in the set) . Based on the above information reported by UE, NW may provide at least one parameter, which is used to indicate / activate / deactivate / enable / disable a (specific) method of determining predicted beams to report. This means the method of determining predicted beams to report may be configurable. UE may determine (or select) the method of determining predicted beams to report based on at least one of: the at least one parameter provided by NW, the value of K, or the value of N. The key effect of this embodiment is that based on the above information (e.g., UE capability information) reported by UE, NW can know if UE can support the above ability, and if UE can support the methods / options when N = 1 and K = N. When more than one method / option as N = 1 and K = N are supported, UE can determine which method to use based on at least one of the NW’s configuration, the value of K, or the value of N.
[0202] In some embodiments, the mapping order of the reported predicted K (especially for K>1) beams may be determined based on at least one of top numbers corresponding to the reported predicted K beams, or probabilities associated with the reported predicted K beams. For example, if the reported predicted K beams is included in a CSI report, the mapping order of the CSI fields for the reported predicted K beams may be determined based on top numbers corresponding to the reported predicted K beams, or probabilities associated with the reported predicted K beams. The key effect of this embodiment is that based on the predefined mapping order, UE can know how to map the reported predicted beams in an orderly manner to the UL resource (e.g., UCI) . NW can know which reported predicted beam (s) are best (e.g., which reported predicted beam is the predicted top 1 beam, which reported predicted beam is the predicted top 2 beam) or are associated with the largest probability.
[0203] For beam prediction using UE-side AI / ML model, it has been agreed that UE reports predicted top K beam (s) among a set of beams (i.e., Set A) . If the output of the AI / ML model are more than one predicted top beams (e.g., predicted top 1 beam, predicted top 2 beam, predicted top 3 beam, predicted top 4 beam) , UE may report these more than one predicted top beams. However, due to the following reasons, multiple reported predicted (top) beams may correspond to the same beam in the set of beams.
[0204] The AI / ML model will each predicted top beam individually, unaffected by other predicted top beam, in other words, recognition of the predicted top 1 beam and recognition of the predicted top 2 beam are two independent processes / thread. This means, for example, that one beam in the set of beams may be both the predicted top 1 beam and the predicted top 2 beam simultaneously.
[0205] This respective reporting will lead to wastage of reporting resources and potentially hinder NW from further finding / identifying the actual best beam (e.g., NW may rely on the predicted beams reported by UE for subsequent beam measurement and reporting) .
[0206] In some embodiments, UE is not expected to report the same predicted beam (e.g., multiple predicted beams correspond to the same beam ID) in at least one beam report (or at least one reporting instance, or report setting) . The key effect is saving reporting overhead and beneficial for NW to find the actual best beam.
[0207] Actually, for a predicted top beam, i.e., the predicted beam associated with the largest probability, its associated probability may not be close to 100%. In this case, if only this predicted beam is reported, it may cause NW to be unable to find the actual best beam.
[0208] UE may report one or multiple groups of predicted beams, where each group of predicted beams corresponds to a top number, and each group of predicted beams includes a set of predicted beams satisfying at least one criterion / threshold related to probability. The key effect is beneficial for NW to find the actual best beam, e.g., actual top 1 beam, actual top 2 beam.
[0209] In some embodiment, NW may configure a new parameter K1 and a new parameter K2 for a measurement report that is configured for reporting predicted beams. Where the K1 may be used to indicate the number of predicted beam groups to report, each predicted beam group corresponds to a (specific) top number (e.g., 1, 2) , or a (specific) probability (e.g., probability of the beam to be the top 1 beam, probability of the beam to be the top 2 beam) . K1 is an integer that is larger than or equal to 1. And the configuration of the K1 may be based on the information related to the N reported by UE (mentioned in Case 2) , e.g., K1 ≤ N. Where the K2 may be used to indicate the number of predicted beams in a predicted beam group. K2 is an integer that is larger than or equal to 0. And the configuration of the K2 may be based on a UE capability that indicates the maximum number of (predicted) beams in one beam report or one predicted beam group. Furthermore, UE may be configured with only one K2, in this case, the K2 may be applied for all predicted beam groups configured by the K1. Optionally, UE may be configured with multiple K2s, and each K2 is associated with a predicted beam groups configured by the K1. For a given predicted beam group (e.g., corresponding to the top number ‘1’ ) , the K2 predicted beams included in the beam report may include the (top) K2 predicted beams associated with the largest probability 470, where the probability is the probability of the beam to be the top 1 beam. For example, K1 = 4, K2 = 2, as shown in FIG. 4G.
[0210] Optionally, the number of predicted beam groups to report and the number of predicted beams in a beam group can be determined based by UE and reported to NW.
[0211] For example, the measurement report comprises at least two parts, e.g., part 1 and part 2. The part 1 comprises at least one of: the number of predicted beam groups to report, the number of predicted beams in a beam group. The part 2 comprises at least one of: information related to the reported beam group (e.g., indicator of top number corresponding to the reported beam group or probability associated with the reported beam group) , information related to the reported predicted beam (e.g., indicator of the reported predicted beam, probability associated with the reported predicted beam) .
[0212] For a given top number (or beam group) , UE may determine predicted beams to report (in part 2) based on at least one of the following criterion / thresholds. The reported predicted beams include (top) P (P≥1) predicted beam (s) associated with the largest probability. The sum of the probability (ies) associated with the P predicted beam (s) is larger than or equal to a threshold related to probability (e.g., 90%) . Furthermore, for different top numbers (or beam groups) , independent threshold related to probability may be provided.
[0213] Example methods
[0214] FIG. 5 illustrates a flowchart of a communication method 500 implemented at a first 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 first device 110 in FIG. 1.
[0215] At block 510, the first device receives, from a second device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event.
[0216] At block 520, the first device obtains predicted information of a machine learning (ML) model, wherein, the predicted information comprising N groups of predicted results, N is an integer larger than 1, each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, each group comprises at least one predicted result of at least one predicted element, and each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element.
[0217] At block 530, the first device determines, at least one predicted element to be reported based on at least one of the following: probabilities of predicted elements in the predicted results, or values of n associated with predicted elements in the predicted results.
[0218] At block 540, the first device transmits, to the second device, a report comprising identities of the at least one predicted element.
[0219] In some example embodiments, if a value of N is the same as the first number, and a number of predicted results in each group is 1, the at least one predicted element to be reported is determined to be all of the predicted elements of the ML model.
[0220] In some example embodiments, the first number is 1 and a value of N is 1, a number of predicted results in the group corresponding to a prediction of being a top 1 element is larger than 1, and the at least one predicted element to be reported is determined to be one predicted element with a largest probability in the group of predicted results corresponding to a prediction of being a top 1 element.
[0221] In some example embodiments, the first number is larger than 1 and a value of N is 1, and wherein, in a case that a number of predicted results in the group corresponding to a prediction of being a top 1 element is larger than the first number, the at least one predicted element to be reported is determined to be top M predicted elements in the group of predicted results corresponding to a prediction of being a top 1 element according to a descending order of probability, and M equals to the first number.
[0222] In some example embodiments, M equals to the first number and n is smaller than or equal to the first number top M predicted elements comprised in M groups of predicted results according to a descending order of probability, or the first M predicted elements in M groups of predicted results, a probability of the predicted element being larger than or equal to a threshold.
[0223] In some example embodiments, if the number of predicted results in each group is larger than 1, each of the predicted element is a predicted element with a largest probability in a respective group of predicted results.
[0224] In some example embodiments, if more than one predicted element is associated with a same probability, at least one of the following is prioritized to be determined to be the at least one predicted element to be reported: a predicted element associated with a lowest identity, a predicted element associated with a highest identity, or a predicted element associated with a measured element.
[0225] In some example embodiments, if a number of predicted elements with a probability larger than or equal to the threshold is smaller than the first number, determine at least one predicted element comprised in at least one group associated with a lower value of n as the at least one predicted element to be reported.
[0226] In some example embodiments, M equals to the first number.
[0227] In some example embodiments, the first device may for each group of predicted results, determine top M predicted elements according to a descending order of probability; for each group of predicted results, determine a sum of the M probabilities of the top M predicted elements; and determine the top M predicted elements with a largest sum as the at least one predicted element to be reported.
[0228] In some example embodiments, the first device may determine a first group where a sum of top M probabilities of the M predicted elements in the group of predicted results is larger than or equal to a threshold; and determine the M predicted elements in the first group as the at least one predicted element to be reported.
[0229] In some example embodiments, the first device may transmit, to the second device, information about at least one of the following: a maximum value of N, whether the ML model supports outputting more than one predicted top beam, whether the ML model supports outputting probability, whether the ML model supports outputting the largest probability, or whether the ML model supports outputting probability associated with each predicted beam.
[0230] In some example embodiments, the at least one predicted element is different from each other.
[0231] In some example embodiments, the first device is a terminal device and the second device is a network device.
[0232] FIG. 6 illustrates a flowchart of a communication method 600 implemented at a first 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 first device 110 in FIG. 1.
[0233] At block 610, the first device generates, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer larger than 0, and the predicted element is a predicted beam, a predicted cell or a predicted event.
[0234] At block 620, the first device transmits the measurement report to a second device.
[0235] In some example embodiments, the first device may receive, form the second device, configuration information indicating a first number indicating a number of groups of predicted elements to be reported and at least one of the following: a second number indicating a number of predicted elements to be reported in each group, or at least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more groups, or wherein any of the first, second or the third number is determined by the first device.
[0236] In some example embodiments, the measurement report further comprises at least one of the following: a first number indicating a number of groups of predicted elements to be reported, or a second number indicating a number of predicted elements to be reported in each group, or at least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more group.
[0237] In some example embodiments, the measurement report comprises: a first part comprising at least one of the following: the first number, the second number or the at least one third number; and a second part comprising at least one of the following: identities of the at least one group of predicted results, identities of the plurality predicted elements, probabilities of the plurality predicted elements.
[0238] In some example embodiments, the first device is a terminal device and the second device is a network device.
[0239] FIG. 7 illustrates a flowchart of a communication method 700 implemented at a second device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 700 will be described from the perspective of the second device 120 in FIG. 1.
[0240] At block 710, the second device transmits, to a first device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event.
[0241] At block 720, the second device receives, from the first device, a report comprising identities of the at least one predicted element, wherein the at least one predicted element is determined by the first device based on the first number and predicted information of a machine learning (ML) model, and wherein, the predicted information comprising N groups of predicted results, N is an integer larger than 1, each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, each group comprises at least one predicted result of at least one predicted element, each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element.
[0242] In some example embodiments, the second device may receive, from the first device, information about at least one of the following: a maximum value of N, whether the ML model supports outputting more than one predicted top beam, whether the ML model supports outputting probability, whether the ML model supports outputting the largest probability, or whether the ML model supports outputting probability associated with each predicted beam.
[0243] In some example embodiments, the at least one predicted element is different from each other.
[0244] In some example embodiments, the first device is a terminal device, and the second device is a network device.
[0245] FIG. 8 illustrates a flowchart of a communication method 800 implemented at a second device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 800 will be described from the perspective of the second device 120 in FIG. 1.
[0246] At block 810, receive, from a first device, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer and the predicted element is a predicted beam, a predicted cell or a predicted event.
[0247] In some example embodiments, the second device may transmit, to the first device, configuration information indicating a first number indicating a number of groups of predicted elements to be reported and at least one of the following: a second number indicating a number of predicted elements to be reported in each group, or at least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more groups.
[0248] In some example embodiments, the measurement report further comprises at least one of the following: a first number indicating a number of groups of predicted elements to be reported, or a second number indicating a number of predicted elements to be reported in each group, or at least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more groups.
[0249] In some example embodiments, the measurement report comprises: a first part comprising at least one of the following: the first number, the second number or the at least one third number; and a second part comprising at least one of the following: identities of the at least one group of predicted results, identities of the plurality predicted elements, probabilities of the plurality predicted elements.
[0250] In some example embodiments, the first device is a terminal device and the second device is a network device.
[0251] Example Apparatus and Devices
[0252] FIG. 9 is a simplified block diagram of a device 900 that is suitable for implementing embodiments of the present disclosure. The device 900 can be considered as a further example implementation of any of the devices as shown in FIG. 1. Accordingly, the device 900 can be implemented at or as at least a part of the terminal device 110 or the network device 120.
[0253] As shown, the device 900 includes a processor 910, a memory 920 coupled to the processor 910, a suitable transceiver 940 coupled to the processor 910, and a communication interface coupled to the transceiver 940. The memory 920 stores at least a part of a program 930. The transceiver 940 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 940 may include at least one of a transmitter 942 and a receiver 944. The transmitter 942 and the receiver 944 may be functional modules or physical entities. The transceiver 940 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.
[0254] The program 930 is assumed to include program instructions that, when executed by the associated processor 910, enable the device 900 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGS. 1 to 8. The embodiments herein may be implemented by computer software executable by the processor 910 of the device 900, or by hardware, or by a combination of software and hardware. The processor 910 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 910 and memory 920 may form processing means 950 adapted to implement various embodiments of the present disclosure.
[0255] The memory 920 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 920 is shown in the device 900, there may be several physically distinct memory modules in the device 900. The processor 910 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 900 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.
[0256] According to embodiments of the present disclosure, a first device comprising a circuitry is provided. The circuitry is configured to: receive, from a second device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event; obtain predicted information of a machine learning (ML) model, wherein, the predicted information comprising N groups of predicted results, N is an integer larger than 1, each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, each group comprises at least one predicted result of at least one predicted element, and each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element, determine, at least one predicted element to be reported based on at least one of the following: probabilities of predicted elements in the predicted results, or values of n associated with predicted elements in the predicted results; and transmit, to the second device, a report comprising identities of the at least one predicted element. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the first device as discussed above.
[0257] According to embodiments of the present disclosure, a first device comprising a circuitry is provided. The circuitry is configured to: generate, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer larger than 0, and the predicted element is a predicted beam, a predicted cell or a predicted event; and transmit the measurement report to a second device. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the first device as discussed above.
[0258] According to embodiments of the present disclosure, a second device comprising a circuitry is provided. The circuitry is configured to: transmit, to a first device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event; and receive, from the first device, a report comprising identities of the at least one predicted element, wherein the at least one predicted element is determined by the first device based on the first number and predicted information of a machine learning (ML) model, and wherein, the predicted information comprising N groups of predicted results, N is an integer larger than 1, each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, each group comprises at least one predicted result of at least one predicted element, and each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the second device as discussed above.
[0259] According to embodiments of the present disclosure, a second device comprising a circuitry is provided. The circuitry is configured to: receive, from a first device, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer and the predicted element is a predicted beam, a predicted cell or a predicted event. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the second device as discussed above.
[0260] 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.
[0261] . According to embodiments of the present disclosure, a first apparatus is provided. The first apparatus comprises means for receiving, from a second device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event; means for obtaining predicted information of a machine learning (ML) model, wherein, means for the predicted information comprising N groups of predicted results, N is an integer larger than 1, means for each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, means for each group comprises at least one predicted result of at least one predicted element, and means for each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element, means for determining, at least one predicted element to be reported based on at least one of the following: probabilities of predicted elements in the predicted results, or values of n associated with predicted elements in the predicted results; and means for transmitting, to the second device, a report comprising identities of the at least one predicted element. In some embodiments, the first apparatus may comprise means for performing the respective operations of the method 500. In some example embodiments, the first 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.
[0262] According to embodiments of the present disclosure, a first apparatus is provided. The first apparatus comprises means for generating, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer larger than 0, and the predicted element is a predicted beam, a predicted cell or a predicted event; and means for transmitting the measurement report to a second device. In some embodiments, the second apparatus may comprise means for performing the respective operations of the method 600. In some example embodiments, the second 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.
[0263] According to embodiments of the present disclosure, a second apparatus is provided. The second apparatus comprises means for transmitting, to a first device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event; and means for receiving, from the first device, a report comprising identities of the at least one predicted element, wherein the at least one predicted element is determined by the first device based on the first number and predicted information of a machine learning (ML) model, and wherein, means for the predicted information comprising N groups of predicted results, N is an integer larger than 1, means for each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, means for each group comprises at least one predicted result of at least one predicted element, and means for each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element. In some embodiments, the third apparatus may comprise means for performing the respective operations of the method 700. In some example embodiments, the third apparatus may further comprise means for performing other operations in some example embodiments of the method 700. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.
[0264] According to embodiments of the present disclosure, a second apparatus is provided. The second apparatus comprises means for receiving, from a first device, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer and the predicted element is a predicted beam, a predicted cell or a predicted event. In some embodiments, the fourth apparatus may comprise means for performing the respective operations of the method 800. In some example embodiments, the fourth apparatus may further comprise means for performing other operations in some example embodiments of the method 800. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.
[0265] In summary, embodiments of the present disclosure provide the following aspects.
[0266] In an aspect, it is proposed a first device comprising: a processor configured to cause the first device to: receive, from a second device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event; obtain predicted information of a machine learning (ML) model, wherein, the predicted information comprising N groups of predicted results, N is an integer larger than 1, each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, each group comprises at least one predicted result of at least one predicted element, and each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element, determine, at least one predicted element to be reported based on at least one of the following: probabilities of predicted elements in the predicted results, or values of n associated with predicted elements in the predicted results; and transmit, to the second device, a report comprising identities of the at least one predicted element.
[0267] In some embodiments, if a value of N is the same as the first number, and a number of predicted results in each group is 1, the at least one predicted element to be reported is determined to be all of the predicted elements of the ML model.
[0268] In some embodiments, the first number is 1 and a value of N is 1, a number of predicted results in the group corresponding to a prediction of being a top 1 element is larger than 1, and the at least one predicted element to be reported is determined to be one predicted element with a largest probability in the group of predicted results corresponding to a prediction of being a top 1 element.
[0269] In some embodiments, the first number is larger than 1 and a value of N is 1, and wherein, in a case that a number of predicted results in the group corresponding to a prediction of being a top 1 element is larger than the first number, the at least one predicted element to be reported is determined to be top M predicted elements in the group of predicted results corresponding to a prediction of being a top 1 element according to a descending order of probability, and M equals to the first number.
[0270] In some embodiments, M equals to the first number and n is smaller than or equal to the first number top M predicted elements comprised in M groups of predicted results according to a descending order of probability, or the first M predicted elements in M groups of predicted results, a probability of the predicted element being larger than or equal to a threshold.
[0271] In some embodiments, if the number of predicted results in each group is larger than 1, each of the predicted element is a predicted element with a largest probability in a respective group of predicted results.
[0272] In some embodiments, if more than one predicted element is associated with a same probability, at least one of the following is prioritized to be determined to be the at least one predicted element to be reported: a predicted element associated with a lowest identity, a predicted element associated with a highest identity, or a predicted element associated with a measured element.
[0273] In some embodiments, if a number of predicted elements with a probability larger than or equal to the threshold is smaller than the first number, determine at least one predicted element comprised in at least one group associated with a lower value of n as the at least one predicted element to be reported.
[0274] In some embodiments, M equals to the first number.
[0275] In some embodiments, the first device may for each group of predicted results, determine top M predicted elements according to a descending order of probability; for each group of predicted results, determine a sum of the M probabilities of the top M predicted elements; and determine the top M predicted elements with a largest sum as the at least one predicted element to be reported.
[0276] In some embodiments, the first device may determine a first group where a sum of top M probabilities of the M predicted elements in the group of predicted results is larger than or equal to a threshold; and determine the M predicted elements in the first group as the at least one predicted element to be reported.
[0277] In some embodiments, the first device may transmit, to the second device, information about at least one of the following: a maximum value of N, whether the ML model supports outputting more than one predicted top beam, whether the ML model supports outputting probability, whether the ML model supports outputting the largest probability, or whether the ML model supports outputting probability associated with each predicted beam.
[0278] In some embodiments, the at least one predicted element is different from each other.
[0279] In some embodiments, the first device is a terminal device and the second device is a network device.
[0280] In an aspect, it is proposed a first device comprising: a processor configured to cause the first device to: generate, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer larger than 0, and the predicted element is a predicted beam, a predicted cell or a predicted event; and transmit the measurement report to a second device.
[0281] In some embodiments, the first device may receive, form the second device, configuration information indicating a first number indicating a number of groups of predicted elements to be reported and at least one of the following: a second number indicating a number of predicted elements to be reported in each group, or at least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more groups, or wherein any of the first, second or the third number is determined by the first device.
[0282] In some embodiments, the measurement report further comprises at least one of the following: a first number indicating a number of groups of predicted elements to be reported, or a second number indicating a number of predicted elements to be reported in each group, or at least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more group.
[0283] In some embodiments, the measurement report comprises: a first part comprising at least one of the following: the first number, the second number or the at least one third number; and a second part comprising at least one of the following: identities of the at least one group of predicted results, identities of the plurality predicted elements, probabilities of the plurality predicted elements.
[0284] In some embodiments, the first device is a terminal device and the second device is a network device.
[0285] In an aspect, it is proposed a second device comprising: the second device may transmit, to a first device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event; and receive, from the first device, a report comprising identities of the at least one predicted element, wherein the at least one predicted element is determined by the first device based on the first number and predicted information of a machine learning (ML) model, and wherein, the predicted information comprising N groups of predicted results, N is an integer larger than 1, each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N, each group comprises at least one predicted result of at least one predicted element, and each predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element.
[0286] In some embodiments, the second device may receive, from the first device, information about at least one of the following: a maximum value of N, whether the ML model supports outputting more than one predicted top beam, whether the ML model supports outputting probability, whether the ML model supports outputting the largest probability, or whether the ML model supports outputting probability associated with each predicted beam.
[0287] In some embodiments, the at least one predicted element is different from each other.
[0288] In some embodiments, the first device is a terminal device and the second device is a network device.
[0289] In an aspect, it is proposed a second device comprising: the second device may receive, from a first device, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer and the predicted element is a predicted beam, a predicted cell or a predicted event.
[0290] In some embodiments, the second device may transmit, to the first device, configuration information indicating a first number indicating a number of groups of predicted elements to be reported and at least one of the following: a second number indicating a number of predicted elements to be reported in each group, or at least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more groups.
[0291] In some embodiments, the measurement report further comprises at least one of the following: a first number indicating a number of groups of predicted elements to be reported, or a second number indicating a number of predicted elements to be reported in each group, or at least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more groups.
[0292] In some embodiments, the measurement report comprises: a first part comprising at least one of the following: the first number, the second number or the at least one third number; and a second part comprising at least one of the following: identities of the at least one group of predicted results, identities of the plurality predicted elements, probabilities of the plurality predicted elements.
[0293] In some embodiments, the first device is a terminal device and the second device is a network device.
[0294] In an aspect, a first 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 first device discussed above.
[0295] In an aspect, a first 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 first device discussed above.
[0296] In an aspect, a second 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 second device discussed above.
[0297] In an aspect, a second 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 second device discussed above.
[0298] 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 first device discussed above.
[0299] 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 first device discussed above.
[0300] 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 second device discussed above.
[0301] 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 second device discussed above.
[0302] 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 first device discussed above.
[0303] 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 first device discussed above.
[0304] 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 second device discussed above.
[0305] 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 second device discussed above.
[0306] 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.
[0307] 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 9. 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.
[0308] 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.
[0309] 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.
[0310] 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.
[0311] 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 first device comprising:a processor configured to cause the first device to:receive, from a second device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event;obtain predicted information of a machine learning (ML) model, wherein,the predicted information comprising N groups of predicted results, N is an integer larger than 1,each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N,each group comprises at least one predicted result of at least one predicted element, andeach predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element,determine, at least one predicted element to be reported based on at least one of the following: probabilities of predicted elements in the predicted results, or values of n associated with predicted elements in the predicted results; andtransmit, to the second device, a report comprising identities of the at least one predicted element.2.The first device of claim 1, wherein if a value of N is the same as the first number, and a number of predicted results in each group is 1, the at least one predicted element to be reported is determined to be all of the predicted elements of the ML model.3.The first device of claim 1, wherein the first number is 1 and a value of N is 1, a number of predicted results in the group corresponding to a prediction of being a top 1 element is larger than 1, and the at least one predicted element to be reported is determined to be one predicted element with a largest probability in the group of predicted results corresponding to a prediction of being a top 1 element.4.The first device of claim 1, wherein the first number is larger than 1 and a value of N is 1, and wherein,in a case that a number of predicted results in the group corresponding to a prediction of being a top 1 element is larger than the first number,the at least one predicted element to be reported is determined to be top M predicted elements in the group of predicted results corresponding to a prediction of being a top 1 element according to a descending order of probability, and M equals to the first number.5.The first device of claim 1, wherein, the first number is larger than 1 and a value of N is larger than or equal to the first number,in a case that a number of predicted results in each group is 1, the at least one predicted element to be reported is determined to be one of the following:M predicted elements comprised in M groups of predicted results, each group corresponding to a prediction of being a top n element, wherein M equals to the first number and n is smaller than or equal to the first number,top M predicted elements comprised in M groups of predicted results according to a descending order of probability, orthe first M predicted elements in M groups of predicted results, a probability of the predicted element being larger than or equal to a threshold.6.The first device of claim 5, wherein if the number of predicted results in each group is larger than 1, each of the predicted element is a predicted element with a largest probability in a respective group of predicted results.7.The first device of claim 3 or 5, wherein if more than one predicted element is associated with a same probability, at least one of the following is prioritized to be determined to be the at least one predicted element to be reported:a predicted element associated with a lowest identity,a predicted element associated with a highest identity, ora predicted element associated with a measured element.8.The first device of claim 5, wherein if a number of predicted elements with a probability larger than or equal to the threshold is smaller than the first number, determine at least one predicted element comprised in at least one group associated with a lower value of n as the at least one predicted element to be reported.9.The first device of claim 1, wherein, the first number is larger than 1 and the number of predicted results in each group is larger than 1, and the at least one predicted element to be reported is determined to be the following:top M predicted elements comprised in predicted results of the ML model according to a descending order of probability, wherein M equals to the first number.10.The first device of claim 1, wherein, the first number is larger than 1, a value of N is larger than 1, and the number of predicted results in each group is larger than the first number,and wherein processor is configured to cause the first device to:for each group of predicted results, determine top M predicted elements according to a descending order of probability;for each group of predicted results, determine a sum of the M probabilities of the top M predicted elements; anddetermine the top M predicted elements with a largest sum as the at least one predicted element to be reported.11.The first device of claim 1, wherein, the first number is larger than 1, a value of N is larger than 1, and the number of predicted results in each group is larger than the first number,and wherein processor is configured to cause the first device to:determine a first group where a sum of top M probabilities of the M predicted elements in the group of predicted results is larger than or equal to a threshold; anddetermine the M predicted elements in the first group as the at least one predicted element to be reported.12.The first device of claim 1, wherein the processor is further configured to cause the first device to:transmit, to the second device, information about at least one of the following:a maximum value of N,whether the ML model supports outputting more than one predicted top beam,whether the ML model supports outputting probability,whether the ML model supports outputting the largest probability, orwhether the ML model supports outputting probability associated with each predicted beam.13.The first device of claim 1, wherein the at least one predicted element is different from each other.14.A first device comprising:a processor configured to cause the first device to:generate, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer larger than 0, and the predicted element is a predicted beam, a predicted cell or a predicted event; andtransmit the measurement report to a second device.15.The first device of claim 14, wherein the processor is further configured to cause the first device to:receive, form the second device, configuration information indicating a first number indicating a number of groups of predicted elements to be reported and at least one of the following:a second number indicating a number of predicted elements to be reported in each group, orat least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more groups,or wherein any of the first, second or the third number is determined by the first device.16.The first device of claim 14, wherein the measurement report further comprises at least one of the following:a first number indicating a number of groups of predicted elements to be reported, ora second number indicating a number of predicted elements to be reported in each group, orat least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more group.17.The first device of claim 16 wherein the measurement report comprises:a first part comprising at least one of the following: the first number, the second number or the at least one third number; anda second part comprising at least one of the following: identities of the at least one group of predicted results, identities of the plurality predicted elements, probabilities of the plurality predicted elements.18.A second device comprising:a processor configured to cause the second device to:transmit, to a first device, configuration information indicating a first number of predicted elements to be reported, wherein the predicted element is a predicted beam, a predicted cell or a predicted event; andreceive, from the first device, a report comprising identities of the at least one predicted element,wherein the at least one predicted element is determined by the first device based on the first number and predicted information of a machine learning (ML) model, and wherein,the predicted information comprising N groups of predicted results, N is an integer larger than 1,each group of predicted results corresponds to a prediction of being a top n element, n is an integer larger than or equal to 1 while smaller than or equal to N,each group comprises at least one predicted result of at least one predicted element, andeach predicted result comprises at least one of the following: an identity of a predicted element or a probability of being the top n element.19.The second device of claim 18, wherein the processor is further configured to cause the second device to:receive, from the first device, information about at least one of the following:a maximum value of N,whether the ML model supports outputting more than one predicted top beam,whether the ML model supports outputting probability,whether the ML model supports outputting the largest probability, orwhether the ML model supports outputting probability associated with each predicted beam.20.The second device of claim 19, wherein the at least one predicted element is different from each other.21.The second device of claim 19, wherein the first device is a terminal device and the second device is a network device.22.A second device comprising:a processor configured to cause the second device to:receive, from a first device, a measurement report indicating a plurality predicted results of a plurality predicted elements, wherein the plurality predicted results are belong to at least one group of predicted results, each group of predicted results corresponds to a prediction of being a top n element, wherein n is an integer and the predicted element is a predicted beam, a predicted cell or a predicted event.23.The second device of claim 22, wherein the processor is further configured to cause the second device to:transmit, to the first device, configuration information indicating a first number indicating a number of groups of predicted elements to be reported and at least one of the following:a second number indicating a number of predicted elements to be reported in each group, orat least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more groups.24.The second device of claim 22, wherein the measurement report further comprises at least one of the following:a first number indicating a number of groups of predicted elements to be reported, ora second number indicating a number of predicted elements to be reported in each group, orat least one third number, each third number corresponding to one or more groups and indicating a number of predicted elements to be reported in the one or more groups.25.The second device of claim 24, wherein the measurement report comprises:a first part comprising at least one of the following: the first number, the second number or the at least one third number; anda second part comprising at least one of the following: identities of the at least one group of predicted results, identities of the plurality predicted elements, probabilities of the plurality predicted elements.26.The second device of claim 22, wherein the first device is a terminal device and the second device is a network device.
Citation Information
Patent Citations
Hanging transmission of measurement reports when measured values correspond to predicted values
CN116724650A
Beam prediction for wireless networks
US20220190883A1
Reporting of measured and prediction based beam management
WO2023155126A1
Methods for communication, terminal device, network device and computer readable medium
WO2024011469A1