Devices and methods for communication
Devices report confidence and prediction interval errors to improve beam management and mobility in complex communication networks, addressing the lack of such solutions in existing technologies.
Patent Information
- Application Number
- PCT/CN2024/077169
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-02-12
- Publication Date
- 2025-08-21
AI Technical Summary
Existing communication networks face challenges in managing beam management and mobility due to increasing complexity and user numbers, with a lack of solutions for reporting confidence and prediction interval errors in AI/ML-based beam predictions.
Devices generate and transmit messages containing information about confidence and prediction interval errors, including differences between point predictions and confidence or prediction intervals, to improve beam management and mobility performance.
Enhances communication performance by providing accurate interval error information, enabling better decision-making in beam management and mobility operations.
Smart Images

Figure CN2024077169_21082025_PF_FP_ABST
Abstract
Description
DEVICES AND METHODS FOR COMMUNICATION
[0001] FIELDS
[0002] Example embodiments of the present disclosure generally relate to the field of communication techniques and in particular, to devices and methods for providing information about interval error (s) .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 information about interval error (s) .
[0005] In a first aspect, there is provided a first device comprising: a processor configured to cause the first device to: generate a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; and transmit the message to the second device.
[0006] In a second aspect, there is provided a first device comprising: a processor configured to cause the first device to: determine, at least one requirement for a performance related to one of the following: a beam prediction, an artificial intelligence (AI) / machine learning (ML) -based beam management, a predicted reference signal receiving power (RSRP) , a predicted beam, an AI / ML model, an AI / ML functionality, or a model inference, wherein at least one requirement comprises at least one of the following: a confidence interval requirement, a prediction interval requirement, a confidence interval error requirement, or a prediction interval error requirement; and apply the at least one requirement.
[0007] In a third aspect, there is provided a second device comprising: a processor configured to cause the second device to: receive, from a first device, a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; and determine the interval error based on the message.
[0008] In a fourth aspect, there is provided a communication method performed by a first device. The method comprises: generating a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; and transmitting the message to the second device.
[0009] In a fifth aspect, there is provided a communication method performed by a first device. The method comprises: determining, at least one requirement for a performance related to one of the following: a beam prediction, an artificial intelligence (AI) / machine learning (ML) -based beam management, a predicted reference signal receiving power (RSRP) , a predicted beam, an AI / ML model, an AI / ML functionality, or a model inference, wherein at least one requirement comprises at least one of the following: a confidence interval requirement, a prediction interval requirement, a confidence interval error requirement, or a prediction interval error requirement; and applying the at least one requirement.
[0010] In a sixth aspect, there is provided a communication method performed by a second device. The method comprises: receiving, from a first device, a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; and determining the interval error based on the message.
[0011] In a seventh aspect, there is provided a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to carry out the method according to the fourth, fifth, or sixth aspect.
[0012] Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS
[0013] 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:
[0014] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;
[0015] FIG. 2 illustrates a signaling flow of communication in accordance with some embodiments of the present disclosure;
[0016] FIG. 3 illustrates a signaling flow of communication in accordance with some embodiments of the present disclosure;
[0017] FIG. 4 illustrates example structures of reporting information;
[0018] FIG. 5 illustrates example structures of reporting information;
[0019] FIG. 6 illustrates a signaling flow of communication in accordance with some embodiments of the present disclosure;
[0020] FIG. 7A and FIG. 7B illustrate signaling flows of communication in accordance with some embodiments of the present disclosure;
[0021] FIG. 8 illustrates a flowchart of a method implemented at a first device according to some example embodiments of the present disclosure;
[0022] FIG. 9 illustrates a flowchart of a method implemented at a first device according to some example embodiments of the present disclosure;
[0023] FIG. 10 illustrates a flowchart of a method implemented at a second device according to some example embodiments of the present disclosure;
[0024] FIG. 11 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] The following alternatives according to AI / ML model output may be considered:
[0050] ● Tx and / or Rx Beam ID (s) and / or the predicted L1-RSRP of the N predicted DL Tx and / or Rx beams, e.g., N predicted beams can be the Top-N predicted beams;
[0051] ● Tx and / or Rx Beam ID (s) of the N predicted DL Tx and / or Rx beams and other information (e.g., probability for the beam to be the best beam, the associated confidence, beam application time / dwelling time, Predicted Beam failure) , e.g., N predicted beams can be the Top-N predicted beams;
[0052] ● Tx and / or Rx Beam angle (s) and / or the predicted L1-RSRP of the N predicted DL Tx and / or Rx beams, e.g., N predicted beams can be the Top-N predicted beams.
[0053] Some further discussions are expected to be further discussed, such as,
[0054] ● spatial-domain downlink (DL) transmit (Tx) beam prediction for Set A of beams based on measurement results of Set B of beams ( “BM-Case1” ) ;
[0055] ● temporal DL Tx beam prediction for Set A of beams based on the historic measurement results of Set B of beams ( “BM-Case2” ) ;
[0056] ● necessary signalling / mechanism (s) to facilitate life cycle management (LCM) operations specific to the Beam Management use cases, if any;
[0057] ● enabling method (s) to ensure consistency between training and inference regarding network (NW) -side additional conditions (if identified) for inference at UE.
[0058] For better descriptions, some terms used herein are listed as below:
[0059] Model inference means a process of using a trained AI / ML model to produce a set of outputs based on a set of inputs;
[0060] 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;
[0061] Model switching means deactivating a currently active AI / ML model and activating a different AI / ML model for a specific AI / ML-enabled feature;
[0062] Model selection means a process of selecting an AI / ML model for activation among multiple models for the same AI / ML enabled feature;
[0063] Model update means a process of updating the model parameters and / or model structure of a model;
[0064] Model monitoring means a procedure that monitors the inference performance of the AI / ML model;
[0065] Model activation means to enable an AI / ML model for a specific AI / ML-enabled feature;
[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) , RSRP, SINR, RSSI, or RSRQ;
[0067] Beam refers to a reference signal (RS) (e.g., Channel state information reference signal, (CSI-RS) , synchronization signal or physical broadcast channel (PBCH) Block, SSB, sounding reference signal, SRS) or an RS resource, transmission configuration indicator (TCI) state, RS of a quasi co-location (QCL) type (e.g., typeA, typeB, typeC, typeD) , pathloss reference RS, uplink power control (parameter) ;
[0068] Beam ID refers to CSI-RS resource indicator (CRI) / SRS resource indicator (SSBRI) , TCI state ID, pathloss reference RS ID, or uplink power control ID;
[0069] Predicted / prediction beam refers to a beam that is configured for prediction;
[0070] Measured beam refers to an RS (e.g., CSI-RS, SSB, SRS) or RS resource configured / used for measuring L1-RSRP or L1-SINR and so on, or configured / used as channel measurement resource (CMR) or interference measurement resource (IMR) . In the present disclosure, measured (or reported) beam may be referred to as ‘beam’ for brevity;
[0071] ‘Top M beam (s) out of a set of beams’ means the top M (M≥1) beam (s) with the largest L1-RSRP / L1-SINR out of the set of beams. In this patent, it can be referred to as ‘top M beams’ . Top 1 beam is interchangeably with the best / strongest beam;
[0072] Point prediction (result or value) means an output of AI / ML model, or predicted result or value determined based on AI / ML model. For example, in case of beam prediction, it comprises at least one of a predicted beam quality or predicted beam (ID) , which determined based on AI / ML model (or output by AI / ML model) ;
[0073] Time stamp refers to a time interval, time instance, time duration or a period of time, (CSI or beam) application / dwelling time, e.g., “a time stamp associated with information A” means the information A is applied or used during / within / in / at / over the time stamp.
[0074] In the context of the present disclosure,
[0075] terms “beam” may be replaced by “beam pair” ;
[0076] terms “ID” , “identifier” , “identity” , “index” or “indicator” , “indication” may be used interchangeably;
[0077] wording “provided by a device” may be replaced by “configured by a device” , “indicated by a device” and “activated by a device” .
[0078] As used herein, term “generate” may refer to measure, determine, or calculate. For example, generating a value may refer to obtain a value by measuring, determining a value, or calculating a value and so on.
[0079] 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.
[0080] 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.
[0081] 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.
[0082] 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.
[0083] 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.
[0084] 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.
[0085] Wording ‘A corresponds 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.
[0086] Principles and implementations of the present disclosure will be described in detail below with reference to the figures.
[0087] Example environment
[0088] 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.
[0089] 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.
[0090] In FIG. 1, the first / second device 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 and so on.
[0091] 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.
[0092] 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.
[0093] 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.
[0094] 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.
[0095] 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.
[0096] 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.
[0097] 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.
[0098] With the model 115, a point prediction may be implemented. During the point prediction, in addition to the point prediction result (e.g., predicted beam / beam quality) , the corresponding confidence information may also be obtained or outputted based on the AI / ML model. Below table illustrates an example of point prediction and corresponding confidence interval and prediction interval.
[0099] The confidence information may be used to determine uncertainty of the point prediction result and evaluate the point prediction result.
[0100] Further, for a classification-based AI / ML model, the confidence may be defined as a probability. For example, when the AI / ML output is the best beam of a set of beams, the confidence may refer to the probability for being the best beam. For a regression-based AI / ML model, the confidence may be defined as a confidence interval or prediction interval. For example, for a given confidence level (i.e., percentage related to confidence, e.g., 95%) , a confidence interval or prediction interval can be obtained.
[0101] When the prediction interval is required to output, the point prediction may not be output explicitly by the AI / ML model. Optionally, the point prediction may be equal to the mean of the lower bound and the upper bound of the prediction interval.
[0102] Example processes
[0103] As discussed above, during the point prediction, information about confidence interval and prediction interval also may be obtained. By far, there is no solutions for reporting confidence information (i.e., confidence or prediction interval) related to the predicted beam.
[0104] According to some embodiments of the present disclosure, information about the confidence / prediction interval error may be provided.
[0105] Reference is made to FIG. 2, which illustrates a signaling flow 200 for communication in accordance with some embodiments of the present disclosure. For the purposes of discussion, the signaling flow 200 will be discussed with reference to FIG. 1, for example, by using the first device 110 and the second device 120.
[0106] 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.
[0107] In the example of FIG. 2, a model is deployed at the first device 110 and the second device 120 may receive message comprising information about the interval error from the first device 110.
[0108] In operation, the first device 110 generates 210 a message comprising first information about a first interval error, where the interval error comprises at least one of the following:
[0109] a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or
[0110] a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction.
[0111] As used herein, a lower bound may be interchangeably with a lower limit, i.e., the smallest value of an interval and an upper bound is interchangeably with an upper limit, i.e., the biggest value of an interval.
[0112] Further, confidence / prediction interval error may be an absolute value of the difference, such that the confidence / prediction interval error is a positive value which is larger than 0.
[0113] Then the first device 110 transmits 320 the message to the second device 120.
[0114] In some embodiments, the message may be an RRC message, such as, an RRC message carrying UE capability information, or an RRC message carrying UE assistance information (UAI) , as illustrates in FIG. 3, which illustrates a signaling flow 300 of communication in accordance with some embodiments of the present disclosure. Alternatively, the message may be a measurement report, as illustrates in FIG. 4, which illustrates a signaling flow 400 of communication in accordance with some embodiments of the present disclosure.
[0115] In addition to a specific interval error value, the first information also may be a statistical information for the interval error. Specifically, in some embodiments, the first information may comprise at least one of the following:
[0116] a minimum interval error,
[0117] a maximum interval error,
[0118] an average interval error,
[0119] an interval error range,
[0120] a median of interval error,
[0121] a variance of interval errors, or
[0122] a standard deviation of interval errors.
[0123] According to some embodiments of the present discourse, the first information may be associated with one of the following:
[0124] a beam or a beam identity,
[0125] a beam set or a beam set identity,
[0126] a confidence level or an indication of a confidence level, or
[0127] a machine learning (ML) model or ML model group or an indication of a ML model or ML model group.
[0128] Reference is now made to FIG. 5, which illustrates example structures 500 of reporting information. In the example of FIG. 5, each model may be associated with at least one beam set, each beam set may be associated with at least one beam, and each beam may be associated with an interval error. Additionally, the interval error may be associated with a specific confidence percentage (i.e., confidence level) .
[0129] Reference is now made to FIG. 6, which illustrates example structures 600 of reporting information. In the example of FIG. 6, each model may be associated with at least one beam set. In some embodiments, the statistical information may be associated with a specific beam set. Alternatively, the statistical information may be associated with a specific model. Additionally, the statistical information may be associated with a specific confidence percentage (i.e., confidence level) .
[0130] In addition to the above, the first information also may be associated with at least one of the following:
[0131] a time stamp or an indication of a time stamp,
[0132] a functionality or an indication of a functionality,
[0133] a feature or feature group (FG) or an indication of a feature or feature group.
[0134] In some embodiments, in a case that a confidence level of the first information is absent in the message, the first information may be assumed to be associated with a specific confidence level, such as, 95%.
[0135] For a better understanding, example embodiments are discussed below. As one example scenario, the message comprises first information about a first interval error and second information about a second interval error. In this specific example scenario, the first interval error and the second interval error may be associated with at least one of the following:
[0136] different time stamps, or different indications of time stamps,
[0137] different confidence levels, or different indications of confidence level,
[0138] different interval error types, or different indications of interval error types,
[0139] different machine learning (ML) models or ML model groups, or different indications of machine learning (ML) models or ML model groups,
[0140] different functionalities, or different indications of functionalities,
[0141] different features or feature groups, or different indications of features or feature groups,
[0142] different beam sets, or different beam set identities,
[0143] different beams, or different beams identities.
[0144] According to some embodiments of the present discourse, the transmission of the message may be conditionally, as discussed below.
[0145] In some embodiments, the first device 110 may transmit the message to the second device 120 upon at least one of the following: a completion of a model deployment, a completion of a model identification, a completion of a model delivery or transfer (is completed) , a completion of a model training, a completion of a model validation, a completion of a model testing, a completion of model monitoring, a performance change of a model, a model switching, a model selection, a model activation, or a model update.
[0146] Alternatively, the transmission of the message may be event-based. In some embodiments, the first device 110 may transmit the message in response to at least one of the following:
[0147] an interval error corresponding to a specific predicted quality being lower than or equal to a threshold,
[0148] an interval error corresponding to a specific predicted quality being higher than or equal to a threshold,
[0149] the first minimum interval error being lower than or equal to a threshold,
[0150] the first minimum interval error being higher than or equal to a threshold,
[0151] the first maximum interval error being lower than or equal to a threshold,
[0152] the first maximum interval error being higher than or equal to a threshold,
[0153] the first average interval error being lower than or equal to a threshold,
[0154] the first average interval error being higher than or equal to a threshold,
[0155] the second minimum interval error being lower than or equal to a threshold,
[0156] the second minimum interval error being higher than or equal to a threshold,
[0157] the second maximum interval error being lower than or equal to a threshold,
[0158] the second maximum interval error being higher than or equal to a threshold,
[0159] the second average interval error being lower than or equal to a threshold, or
[0160] the second average interval error being higher than or equal to a threshold.
[0161] In summary, the message may be transmitted as an original reporting information, and also may be an update reporting information. The present discourse is not limited with regard to the condition for trigger the transmission of the message.
[0162] According to some embodiments of the present discourse, how to report the message may be configured by the second device 120. Specifically, the second device 120 may transmit configuration information to the first device 110. These example embodiments will be discussed as below.
[0163] In some embodiments, the first device 110 may receive configuration information from the second device 120, where the configuration information may comprise at least one of the following:
[0164] confidence level information,
[0165] an indication indicating an interval type to be reported, the interval type being a confidence interval or a prediction interval,
[0166] an indication used for enabling or disabling reporting of prediction interval information,
[0167] an indication used for enabling or disabling reporting of confidence interval information,
[0168] an indication used for enabling or disabling reporting of the interval error information,
[0169] an indication indicating an interval error type to be reported, the interval error type being a confidence interval error or prediction interval error,
[0170] an indication used for enabling or disabling reporting of prediction interval error information,
[0171] an indication used for enabling or disabling reporting of confidence interval error information, or
[0172] a report quantity comprising at least one of the following: confidence interval, prediction interval, interval error, confidence interval error, prediction interval error, interval error range, minimum interval error, maximum interval error, average interval error, interval error range, minimum confidence interval error, maximum confidence interval error, average confidence interval error, confidence interval error range, minimum prediction interval error, maximum prediction interval error, average prediction interval error, prediction interval error range.
[0173] In some embodiments, upon the configuration information, the first device 110 may perform a model inference to derive the following:
[0174] a plurality of predicted beams,
[0175] a plurality of predicted qualities corresponding to the plurality of predicted beams, and
[0176] a plurality of interval errors corresponding to the plurality of predicted beams (or the plurality of predicted qualities) .
[0177] Then, the first device 110 may determine at least one predicted beam to be reported from the plurality of predicted beams based on the plurality of predicted qualities (or determine at least one predicted quality to be reported) . Next, the first device 110 may transmit the message comprising at least one of the following:
[0178] at least one interval error corresponding to the at least one predicted beam to be reported (or corresponding to the at least one predicted quality to be reported) ,
[0179] a first minimum interval error of the plurality of interval errors (or of the plurality of predicted beams or the plurality of predicted qualities) ,
[0180] a first maximum interval error of the plurality of interval errors (or of the plurality of predicted beams or the plurality of predicted qualities) ,
[0181] a first average interval error of the plurality of interval errors (or of the plurality of predicted beams or the plurality of predicted qualities) ,
[0182] a second minimum interval error of the at least one interval error (or of the at least one predicted beam to be reported or at least one predicted quality to be reported) ,
[0183] a second maximum interval error of the at least one interval error (or of the at least one predicted beam to be reported or at least one predicted quality to be reported) , or
[0184] a second average interval error of the at least one interval error (or of the at least one predicted beam to be reported or at least one predicted quality to be reported) .
[0185] In some embodiments, the message may be a channel status information (CSI) report. If so, the CSI report may comprise the following:
[0186] at least one first field indicating the at least one predicted beam,
[0187] at least one second field indicating at least one predicted quality,
[0188] at least one third field indicating the at least one interval error.
[0189] In particular, an order of the at least one third field may be the same as an order of the at least one first field.
[0190] In some embodiments, a bit width of the third field may be determined based on at least one of the following:
[0191] a total number of candidate values of interval error,
[0192] a total number of indexes of candidate value ranges of interval error,
[0193] a maximum number of values of interval error supported by the first device 110, or
[0194] a maximum value of interval error supported by the first device 110.
[0195] Optionally, expect for the information about interval error, the message may comprise capability-related information. Specifically, in some embodiments, the message may further indicate at least of the following:
[0196] information indicating whether the first device 110 supports to provide the first information, or
[0197] information indicating whether the first device 110 supports outputting point prediction.
[0198] According to some embodiments of the present discourse, the first device 110 may determine performance requirement, as discussed below.
[0199] In operation, first device 110 determines, at least one requirement for a performance related to one of the following: a beam prediction, an artificial intelligence (AI) / machine learning (ML) -based beam management, a predicted reference signal receiving power (RSRP) , a predicted beam, an AI / ML model, an AI / ML functionality, or a model inference, wherein at least one requirement comprises at least one of the following:
[0200] a confidence interval requirement.
[0201] a prediction interval requirement,
[0202] a confidence interval error requirement, or
[0203] a prediction interval error requirement.
[0204] Then, the first device 110 applies the at least one requirement.
[0205] In some embodiments, the confidence interval error requirement may comprise at least one of the following:
[0206] a specific confidence interval error requirement,
[0207] a minimum confidence interval error requirement,
[0208] a maximum confidence interval error requirement, or
[0209] an average confidence interval error requirement.
[0210] Similarly, in some embodiments, in some embodiments, the prediction interval error requirement may comprise at least one of the following:
[0211] a specific prediction interval error requirement,
[0212] a minimum prediction interval error requirement,
[0213] a maximum prediction interval error requirement, or
[0214] an average prediction interval error requirement.
[0215] In some embodiments, the at least one requirement may be associated with at least one of the following: different confidence levels, different indications of confidence level, different interval error types, different indications of interval error types, different machine learning (ML) models or ML model groups, different indications of machine learning (ML) models or ML model groups, different functionalities, different indications of functionalities, different features or feature groups, different indications of features or feature groups, different beam sets, different beam set identities, different beams, or different beams identities.
[0216] In some embodiments, if the at least one requirement is met, the related performance may be considered as acceptable / good, or the related performance may be considered as meeting / satisfying the requirement, or the related performance may be considered as valid, or the related performance may be considered as practicable / applicable.
[0217] Alternatively, or in addition, if the at least one requirement is met, the predicted results (such as, the predicted L1-RSRPs, the predicted beams) may be considered as acceptable / good, or the predicted results may be considered as meeting / satisfying the requirement, or the predicted results may be considered as valid, or the predicted results may be considered as practicable / applicable / available.
[0218] Embodiments
[0219] In order to better understanding the above processes, some example embodiments will be further discussed with reference to FIG. 3 to FIG. 6.
[0220] According to some embodiments of the present discourse, the information about interval error may be provided to the second device 120. Below table illustrates an example point prediction, confidence interval, confidence interval error, prediction interval and prediction interval error.
[0221] Considering that the interval error may be a model-level (or model-specific) information, e.g., in most cases regarding the confidence interval, UE (such as, the first device 110) may report information related to interval error based on an UL RRC message, e.g., UE capability information.
[0222] In this way, the network device 120 may obtain confidence information associated with an AI / ML model earlier, thereby helping the network device 120 to evaluate the prediction results (e.g., predicted RSRP) obtained from the AI / ML model and reported by UE. It can avoid configuring additional reporting resource in the measurement report used to report the prediction results.
[0223] Reference is now made to FIG. 3, which illustrates a signaling flow 300 of communication in accordance with some embodiments of the present disclosure.
[0224] As illustrated in the example of FIG. 3, an initial AI / ML model is deployed at UE side. In this event, UE may report the information related to interval error associated with the initial AI / ML model in an UL RRC message (e.g., UE capability) .
[0225] In some embodiments, when there is at least one initial artificial intelligence (AI) / machine learning (ML) model at UE side, UE may report at least one of the following information items related to confidence in an UL RRC message (e.g., UE capability information, or UAI) :
[0226] ● information indicating whether UE (i.e., the AI / ML model at UE side) supports outputting confidence interval,
[0227] ● information indicating Whether UE supports outputting prediction interval,
[0228] ● information indicating whether UE supports outputting point prediction, or
[0229] ● information related to interval error.
[0230] Additionally, in some embodiments, the initial AI / ML model may be a trained, identified, activated, available, or / and deployed AI / ML model.
[0231] In some embodiments, the above information may be associated with at least one AI / ML model or identifier of AI / ML model (i.e., model ID) . Additionally, in some embodiments, information related to model ID may be also included in the UL RRC message.
[0232] In some embodiments, the above information may be included in information related to the associated AI / ML model, e.g., model description, meta information, model condition, model additional condition.
[0233] In some embodiments, the information related to interval error may comprise: at least one confidence interval error, where the confidence interval error may indicate a difference between a point prediction and the upper or lower bound of a confidence interval (corresponding to the point prediction) .
[0234] Additionally, in some embodiments, the point prediction may be a predicted reference signal receiving power (RSRP) , interference plus noise ratio (SINR) , reference signal receiving quality (RSRQ) output by an AI / ML model.
[0235] Alternatively, or in addition, in some embodiments, the information related to interval error may comprise: at least one prediction interval error, where the prediction interval error may indicate a difference between a point prediction and the upper or lower bound of a prediction interval (corresponding to the point prediction) .
[0236] Additionally, in some embodiments, the point prediction may be a predicted RSRP / SINR / RSRQ output by an AI / ML model, or may be determined based on the prediction interval, e.g., it may be the mean of the of the lower bound and the upper bound of the prediction interval.
[0237] In some embodiments, the reported information related to interval error may correspond to a specific confidence level, e.g., 95%.
[0238] In some embodiments, in addition to the AI / ML model or identifier of the AI / ML model (i.e., model ID) , the information related to interval error may be associated with at least one of the following:
[0239] ● information related to confidence level, which may comprise the following, such as, at least one percentage related to confidence, e.g., 90%, 95%, 99%. In this patent, it can be called as ‘confidence percentage’ ,
[0240] ● information related to beam ID, which may comprise the following, such as, at least one beam ID. For example, it may correspond to a beam of a set of predictable beams (i.e., Set A) corresponding to an AI / ML model, or
[0241] ● information related to beam set ID, which may comprise the following, such as, at least one beam set ID. For example, it may correspond to a set of predictable beams (i.e., Set A) corresponding to an AI / ML model.
[0242] Reference is now made to FIG. 5. In the example of FIG. 5, each AI / ML model or model ID corresponds to one or more beam set IDs, each beam set ID corresponds to one or more beam IDs, each beam ID corresponds to one or more confidence percentages, each confidence percentage correspond to one confidence or prediction interval error.
[0243] For another example, each AI / ML model or model ID corresponds to one or more beam set IDs, each beam set ID corresponds to one or more confidence percentages, each confidence percentage corresponds to one or more beam IDs, each beam ID correspond to one confidence or prediction interval error.
[0244] In some embodiments, the above correspondence (or association) may mean that, for an AI / ML model, and for a beam set corresponding to the AI / ML model, for a given confidence percentage, there may be multiple (corresponding) confidence or prediction interval errors, and each confidence or prediction interval error corresponds to a beam of the beam set.
[0245] In some embodiments, the information related to interval error may comprise at least one of the following:
[0246] ● at least one minimum confidence interval error. For example, for a given confidence percentage, this indicates the minimum confidence interval error of confidence interval errors corresponding to all beams of a set of predictable beams corresponding to an AI / ML model,
[0247] ● at least one maximum confidence interval error. For example, for a given confidence percentage, this indicates the maximum confidence interval error of confidence interval errors corresponding to all beams of a set of predictable beams corresponding to an AI / ML model,
[0248] ● at least one average confidence interval error. For example, for a given confidence percentage, this indicates the average value of confidence interval errors corresponding to all beams of a set of predictable beams corresponding to an AI / ML model,
[0249] ● at least one confidence interval error range. For example, its lower bound may be the minimum confidence interval, and its upper bound may be the maximum confidence interval error, i.e., [minimum confidence interval error, maximum confidence interval error] ,
[0250] ● at least one minimum prediction interval error,
[0251] ● at least one maximum prediction interval error,
[0252] ● at least one average prediction interval error, or
[0253] ● at least one prediction interval error range.
[0254] In some embodiments, the reported information related to interval error may correspond to a specific confidence level, e.g., 95%.
[0255] In some embodiments, in addition to the AI / ML model or identifier of the AI / ML model (i.e., model ID) , the information related to interval error may be associated with at least one of the following:
[0256] ● information related to confidence level may comprise at least one confidence percentage, e.g., 90%, 95%, 99%, or
[0257] ● information related to beam set ID may comprise at least one beam set ID. For example, it may correspond to a set of predictable beams (i.e., Set A) corresponding to an AI / ML model.
[0258] Reference is now made to FIG. 6. In the example of FIG. 6, each AI / ML model or model ID corresponds to one or more beams set ID, each beam set ID corresponds to one or more confidence percentage, each confidence percentage correspond to one at least one of the following:
[0259] ● one minimum confidence interval error,
[0260] ● one maximum confidence interval error,
[0261] ● one average confidence interval error,
[0262] ● one confidence interval error range,
[0263] ● one minimum prediction interval error,
[0264] ● one maximum prediction interval error,
[0265] ● one average prediction interval error, or
[0266] ● one prediction interval error range.
[0267] Alternatively, or in addition, in some embodiments, the information related to interval error may be associated with information related to time stamp.
[0268] in some embodiments, information related to time stamp may comprise at least one time stamp or time stamp index. Each time stamp or time stamp index may correspond to a future or prediction time instance corresponding to an AI / ML model, e.g., temporal beam prediction. For example, one beam ID may correspond to multiple time stamps, each time stamp corresponds to one interval error.
[0269] Further, as discussed above, the transmission of the information about the interval error may be performed conditionally.
[0270] Reference is now made to FIG. 7A, which illustrates a signaling flow 700A of communication in accordance with some embodiments of the present disclosure.
[0271] In some embodiments, when there is at least one new AI / ML model that is different from the current AI / ML model at UE side, e.g., UE side may comprise at least one following:
[0272] ● for the current AI / ML model, the model performance changes or at least one condition is fulfilled over a period of time during model monitoring,
[0273] ● model switching, e.g., switching to the new AI / ML model,
[0274] ● model selection, e.g., the new AI / ML model is selected,
[0275] ● the new AI / ML model is activated, or
[0276] ● model update (e.g., fine-tuning, retaining) , e.g., (parameter or / and structure of) the current AI / ML model is updated.
[0277] After that, UE may report at least one of the following information items associated with the new AI / ML model in an UL RRC message (UE capability information, UE assistance information) , UL MAC CE or UCI:
[0278] ● information indicating whether UE supports outputting confidence interval,
[0279] ● information indicating Whether UE supports outputting prediction interval,
[0280] ● information indicating whether UE supports outputting point prediction,
[0281] ● information related to interval error,
[0282] ● information related to confidence level,
[0283] ● information related to beam ID,
[0284] ● information related to beam set ID, or
[0285] ● information related to model ID.
[0286] Considering that the interval error may be a sample-level (or sample-specific) , e.g., usually in some cases regarding the prediction interval, UE may report information related to interval error based on a configured measurement report.
[0287] In this way, the network device may obtain corresponding confidence information while receiving the prediction results reported by UE, thereby helping it evaluate the prediction results. Some LCM operations (e.g., model switching) at UE side can be transparent to network device.
[0288] Reference is now made to FIG. 7B, which illustrates a signaling flow 700B of communication in accordance with some embodiments of the present disclosure.
[0289] in the example of FIG. 7B, network (NW) may configure at least one configuration related to confidence and at least one configuration related to measurement report for UE, where the configuration related to confidence comprises at least one of the following:
[0290] ● first enable / disable parameter. This parameter is used to enable / disable UE to report (or generate) confidence information,
[0291] ● first parameter. This parameter indicates a type of (reported) confidence information, e.g., confidence interval, prediction interval,
[0292] ● second enable / disable parameter. This parameter is used to enable / disable UE to report confidence interval,
[0293] ● third enable / disable parameter. This parameter is used to enable / disable UE to report prediction interval, or
[0294] ● confidence percentage, e.g., 90%, 95%, 99%.
[0295] In some embodiments, if the field of confidence percentage is present, UE needs to generate the confidence information (i.e., confidence interval or prediction interval) based on this configured confidence percentage.
[0296] In some embodiments, if the field of confidence percentage is absent, UE may apply a specified value, e.g., 95%. If UE is not provided with at least one of the above parameters enabling / indicating UE to report confidence information / confidence interval / prediction interval, or this field may be ignored.
[0297] Additionally, the field of confidence percentage may indicate multiple confidence percentages.
[0298] In some embodiments, the configuration related to measurement report may provide information related to measurement resource, prediction resource, reporting resource, etc. Especially, the report quantity (i.e., information reported in the measurement report) in the configuration related to measurement report may be associated with (or comprise) at least one of beam ID, beam quality, confidence, confidence interval, prediction interval, confidence interval error, prediction interval error, minimum / maximum / average confidence interval error, confidence interval error range, minimum / maximum / average prediction interval error, or prediction interval error range.
[0299] In some embodiments, the configuration related to confidence (or identifier of the configuration related to confidence) may be associated with at least one configuration related to measurement report or identifier of the configuration related to measurement report.
[0300] In some embodiments, the configuration related to confidence or measurement report (or identifier of the configuration related to confidence or measurement report) or the configuration may be associated with at least one AI / ML model or model ID.
[0301] Additionally, in some embodiments, the measurement report may be transmitted in an UL RRC message, UL MAC CE or UCI. For example, the measurement report may be a channel status information (CSI) report.
[0302] In some embodiments, UE may receive the configuration related to confidence and configuration related to measurement report (e.g., CSI report) , after that, UE may determine a set of predicted L1-RSRPs and at least one set of confidence or prediction intervals (called as ‘interval’ for short) based on at least one AI / ML model and the provided confidence percentage (s) .
[0303] In some embodiments, each set of intervals may correspond to a confidence percentage. Alternatively, in some embodiments, for a set of intervals, each interval corresponds to a predicted Layer 1 reference signal received power (L1-RSRP) of the set of predicted L1-RSRPs. In other words, the interval and the predicted L1-RSRP correspond to the same beam or beam ID.
[0304] In some embodiments, after receiving the configuration related to confidence and configuration related to measurement report, UE may determine at least one set of interval errors based on the at least one set of intervals (and the set of predicted L1-RSRPs, i.e., point predictions) . For a set of intervals, one interval error can be determined based on one interval. Specifically, (as mentioned in Case 1) the interval error may be determined based on at least one of the following:
[0305] ● the interval error may be a difference between a point prediction (i.e., predicted L1-RSRP) and the upper or lower bound of a confidence or prediction interval (corresponding to the point prediction) , or
[0306] ● the interval error may be the mean of the of the lower bound and the upper bound of the confidence or prediction interval.
[0307] In this way, for a predicted L1-RSRP, UE may determine at least one interval error corresponding to the predicted L1-RSRP. And each interval error corresponds to a confidence percentage.
[0308] Additionally, in some embodiments, assuming the above set of predicted L1-RSRPs is called as ‘first set of predicted L1-RSRPs’ , UE may determine a second set of predicted L1-RSRPs based on the first set of predicted L1-RSRPs. In some embodiments, the second set of predicted L1-RSRPs may be a subset of the first set of predicted L1-RSRPs, e.g., top K (K≥1) predicted L1-RSRPs of the first set of predicted L1-RSRPs.
[0309] In some embodiments, UE may report the second set of predicted L1-RSRPs and corresponding interval error (s) (i.e., interval errors corresponding to all predicted L1-RSRPs in the second set of predicted L1-RSPRs) . In other words, UE may transmit the measurement report comprising the second set of predicted L1-RSRPs and corresponding interval error (s) to NW. Optionally, beam ID (s) corresponding to the second set of predicted L1-RSRPs may be included in the measurement report. For example, the mapping order of CSI fields of one CSI report for beam ID, predicted L1-RSRP and interval error reporting is shown in the tables below.
[0310] the mapping order
[0311] CSI report
[0312] In some embodiments, the mapping order of CSI fields for the K interval errors follows the mapping order of CSI fields for the K predicted L1-RSRP (s) or beam ID (s) .
[0313] In some embodiments, the bit width for the CSI field for the interval error may be determined based on predefined information, e.g.,
[0314] One predefined information may be the total number of reported values of interval error. In this case, each bit value in the CSI field corresponds to a reported value of interval error, not an actual (or measured, determined) value of interval error. The mapping between the reported value of interval error and the actual value of interval error can be the table as follows (where A1 ≥ 0, Ai+1>Ai) . For example, if there are 4 reported values of interval error (i.e., 0, 1, 2, 3) , the bit width for the CSI field may be 2-bit.
[0315] Another predefined information may be the (maximum) number of interval errors. For example, UE may report all supported interval errors or the supported maximum number of interval errors to NW in an UL RRC message (e.g., UE capability information) . In this case, each bit value indicates an indicator of interval error, e.g., ‘0’ may indicate the minimum interval error.
[0316] A further predefined information may be the maximum value of interval error. For example, UE may report the supported maximum value of interval error to NW in an UL RRC message (e.g., UE capability information) . In this case, each bit value may indicate an actual value of interval error.
[0317] In some embodiments, UE may report a set of interval errors comprising at least one of the following. For example, the measurement report may comprise the second set of predicted L1-RSRPs, beam ID (s) corresponding to the second set of predicted L1-RSRPs and the set of interval errors.
[0318] ● a minimum interval error,
[0319] ● a maximum interval error,
[0320] ● an average interval error,
[0321] ● a median of interval error,
[0322] ● a variance of interval errors, or
[0323] ● a standard deviation of interval errors.
[0324] In some embodiments, each of the above interval errors may be determined based on interval errors corresponding to all predicted L1-RSPRs in the first set of predicted L1-RSRPs or the second set of predicted L1-RSRPs.
[0325] In some embodiments, determination of the bitwidth for the CSI field for the minimum, maximum or average interval error is similar as the interval error (i.e., interval is replaced with minimum, maximum or average interval error) .
[0326] Additionally, in some embodiments, the measurement report may be an event triggering report. Specifically, UE may transmit the measurement report or report certain information (e.g., predicted RSRP, beam ID, interval error) when at least one the following condition is fulfilled.
[0327] ● an interval error corresponding to a specific predicted RSRP (e.g., the largest predicted RSRP) is lower, larger than or equal to a threshold (over a period of time) ,
[0328] ● minimum interval error is lower, larger than or equal to a threshold (over a period of time) ,
[0329] ● maximum interval error is lower, larger than or equal to a threshold (over a period of time) , or
[0330] ● average interval error is lower, larger than or equal to a threshold (over a period of time) .
[0331] As discussed below, according to some embodiments of the present discourse, the first device 110 may determine performance requirement.
[0332] In some embodiments, for the predicted L1-RSRP outputted by the AI / ML model, or for the AI / ML model itself, there may be some (accuracy) requirements related to the confidence information.
[0333] In some embodiments, in the predicted L1-RSRP related accuracy requirements, or in the AI / ML model related requirements, at least one of the following confidence information items may be considered or included:
[0334] ● confidence interval. For example, the range of the confidence interval needs to be within a specific range,
[0335] ● prediction interval. For example, the range of the prediction interval needs to be within a specific range,
[0336] ● confidence interval error information, or
[0337] ● prediction interval error information.
[0338] In some embodiments, the confidence interval error information may comprise at least one of the following:
[0339] ● confidence interval error,
[0340] ● minimum confidence interval error,
[0341] ● maximum confidence interval error, or
[0342] ● average confidence interval error. For example, at least one of the confidence interval errors, the minimum confidence interval error, the minimum confidence interval error, the minimum confidence interval error, or the minimum confidence interval error needs to be less than, larger than or equal to a specific value (e.g., 2dB, 4dB) , or within a specific range.
[0343] In some embodiments, the prediction interval error information may comprise at least one of the following:
[0344] ● prediction interval error,
[0345] ● minimum prediction interval error,
[0346] ● maximum prediction interval error, or
[0347] ● average prediction interval error. For example, at least one of the prediction interval errors, the minimum prediction interval error, the minimum prediction interval error, the minimum prediction interval error, or the minimum prediction interval error needs to be less than, larger than or equal to a specific value (e.g., 2dB, 4dB) , or within a specific range.
[0348] In some embodiments, the above information may be determined in a specific / given confidence percentage (e.g., 90%, 95%, 99%) , i.e., each one of the above information items may correspond to the specific confidence percentage.
[0349] In some embodiments, the above information may correspond to at least one of a beam or beam ID, a beam set or beam set ID, or an AI / ML model or model ID.
[0350] In this way, the UE or NW can know what are the predicted L1-RSRP accuracy requirements.
[0351] In some embodiments, if the at least one requirement is met, the related performance may be considered as acceptable / good, or the related performance may be considered as meeting / satisfying the requirement, or the related performance may be considered as valid, or the related performance may be considered as practicable / applicable.
[0352] Alternatively, or in addition, if the at least one requirement is met, the predicted results (such as, the predicted L1-RSRPs, the predicted beams) may be considered as acceptable / good, or the predicted results may be considered as meeting / satisfying the requirement, or the predicted results may be considered as valid, or the predicted results may be considered as practicable / applicable / available.
[0353] Example methods
[0354] FIG. 8 illustrates a flowchart of a communication method 800 implemented at a first 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 first device 110 in FIG. 1.
[0355] At block 810, the first device generates a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction.
[0356] At block 820, the first device transmits the message to the second device.
[0357] In some example embodiments, the message is at least one of the following: a radio resource control (RRC) message carrying user equipment (UE) capability information, an RRC message carrying UE assistance information (UAI) , or a measurement report.
[0358] In some example embodiments, the first information is associated with one of the following: a beam, a beam identity, a beam set, a beam set identity, a time stamp, an indication of a time stamp, a confidence level, an indication of a confidence level, a machine learning (ML) model or ML model group, an indication of a ML model or ML model group a functionality, an indication of a functionality, a feature or feature group (FG) , or an indication of a feature or feature group.
[0359] In some example embodiments, the message further comprises second information about a second interval error, and the first interval error and the second interval error are associated with at least one of the following: different time stamps, different indications of time stamps, different confidence levels, different indications of confidence level, different interval error types, different indications of interval error types, different machine learning (ML) models or ML model groups, different indications of machine learning (ML) models or ML model groups different functionalities, different indications of functionalities, different features or feature groups, different indications of features or feature groups, different beam sets, different beam set identities, different beams, or different beams identities.
[0360] In some example embodiments, the first information comprises at least one of the following: a minimum interval error, a maximum interval error, an average interval error, or an interval error range.
[0361] In some example embodiments, in a case that a confidence level of the first information is absent in the message, the first information is assumed to be associated with a specific confidence level.
[0362] In some example embodiments, the first device may transmit the message to the second device upon at least one of the following: a completion of a model deployment, a completion of a model identification, a completion of a model delivery or transfer (is completed) , a completion of a model training, a completion of a model validation, a completion of a model testing, a completion of model monitoring, a performance change of a model, a model switching, a model selection, a model activation, or a model update.
[0363] In some example embodiments, the first device may receive, from the second device, configuration information comprising at least one of the following: confidence level information, an indication indicating an interval type to be reported, the interval type being a confidence interval or a prediction interval, an indication used for enabling or disabling reporting of prediction interval information, an indication used for enabling or disabling reporting of confidence interval information, an indication used for enabling or disabling reporting of the interval error information, an indication indicating an interval error type to be reported, the interval error type being a confidence interval error or prediction interval error, an indication used for enabling or disabling reporting of prediction interval error information, an indication used for enabling or disabling reporting of confidence interval error information, or a report quantity comprising at least one of the following: confidence interval, prediction interval, interval error, confidence interval error, prediction interval error, interval error range, minimum interval error, maximum interval error, average interval error, interval error range, minimum confidence interval error, maximum confidence interval error, average confidence interval error, confidence interval error range, minimum prediction interval error, maximum prediction interval error, average prediction interval error, prediction interval error range.
[0364] In some example embodiments, the first device may perform a model inference to derive the following: a plurality of predicted beams, a plurality of predicted qualities corresponding to the plurality of predicted beams, and a plurality of interval errors corresponding to the plurality of predicted beams; determine, from the plurality of predicted beams based on the plurality of predicted qualities, at least one predicted beam to be reported; and transmit the message comprising at least one of the following: the at least one interval error corresponding to the at least one predicted beam to be reported, a first minimum interval error of the plurality of interval errors or the at least one predicted beam to be reported, a first maximum interval error of the plurality of interval errors or the at least one predicted beam to be reported, a first average interval error of the plurality of interval errors or the at least one predicted beam to be reported, a second minimum interval error of the at least one interval error or the at least one predicted beam to be reported, a second maximum interval error of the at least one interval error or the at least one predicted beam to be reported, or a second average interval error of the at least one interval error or the at least one predicted beam to be reported.
[0365] In some example embodiments, the message is a channel status information (CSI) report comprising the following: at least one first field indicating the at least one predicted beam, at least one second field indicating at least one predicted quality, and at least one third field indicating the at least one interval error, wherein, an order of the at least one third field is the same as an order of the at least one first field.
[0366] In some example embodiments, a bitwidth for the third field is determined based on at least one of the following: a total number of candidate values of interval error, a total number of indexes of candidate value ranges of interval error, a maximum number of values of interval error supported by the first device, or a maximum value of interval error supported by the first device.
[0367] In some example embodiments, the first device may transmit the message in response to at least one of the following: an interval error corresponding to a specific predicted quality being lower than or equal to a threshold, an interval error corresponding to a specific predicted quality being higher than or equal to a threshold, the first minimum interval error being lower than or equal to a threshold, the first minimum interval error being higher than or equal to a threshold, the first maximum interval error being lower than or equal to a threshold, the first maximum interval error being higher than or equal to a threshold, the first average interval error being lower than or equal to a threshold, the first average interval error being higher than or equal to a threshold, the second minimum interval error being lower than or equal to a threshold, the second minimum interval error being higher than or equal to a threshold, the second maximum interval error being lower than or equal to a threshold, the second maximum interval error being higher than or equal to a threshold, the second average interval error being lower than or equal to a threshold, the second average interval error being higher than or equal to a threshold.
[0368] In some example embodiments, the message further indicates at least of the following: information indicating whether the first device supports to provide the first information, or information indicating whether the first device supports outputting point prediction.
[0369] FIG. 9 illustrates a flowchart of a communication method 900 implemented at a first device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 900 will be described from the perspective of the first device 110 in FIG. 1.
[0370] At block 910, determines, at least one requirement for a performance related to one of the following: a beam prediction, an artificial intelligence (AI) / machine learning (ML) -based beam management, a predicted reference signal receiving power (RSRP) , a predicted beam, an AI / ML model, an AI / ML functionality, or a model inference, wherein at least one requirement comprises at least one of the following: a confidence interval requirement, a prediction interval requirement, a confidence interval error requirement, or a prediction interval error requirement.
[0371] At block 920, the first device may apply the at least one requirement.
[0372] In some example embodiments, the confidence interval error requirement comprises at least one of the following: a specific confidence interval error requirement, a minimum confidence interval error requirement, a maximum confidence interval error requirement, or an average confidence interval error requirement, and wherein the prediction interval error requirement comprises at least one of the following: a specific prediction interval error requirement, a minimum prediction interval error requirement, a maximum prediction interval error requirement, or an average prediction interval error requirement.
[0373] In some example embodiments, at least one requirement is associated with at least one of the following: different confidence levels, different indications of confidence level different interval error types, different indications of interval error types, different machine learning (ML) models or ML model groups, different indications of machine learning (ML) models or ML model groups different functionalities, different indications of functionalities, different features or feature groups, different indications of features or feature groups, different beam sets, different beam set identities, different beams, or different beams identities.
[0374] FIG. 10 illustrates a flowchart of a communication method 1000 implemented at a second device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 1000 will be described from the perspective of the second device 120 in FIG. 1.
[0375] At block 1010, the second device receives, from a first device, a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction.
[0376] At block 1020, the second device determines the interval error based on the message.
[0377] In some example embodiments, the message is at least one of the following: a radio resource control (RRC) message carrying user equipment (UE) capability information, an RRC message carrying UE assistance information (UAI) , or a measurement report.
[0378] In some example embodiments, the first information is associated with one of the following: a beam, a beam ID, a beam set, a beam set ID, a time stamp, an indication of a time stamp, a confidence level, an indication of a confidence level, a machine learning (ML) model or ML model group, an indication of a ML model or ML model group a functionality, an indication of a functionality, a feature or feature group (FG) , or an indication of a feature or feature group.
[0379] In some example embodiments, the message further comprises second information about a second interval error, and the first interval error and the second interval error are associated with at least one of the following: different time stamps, different indications of time stamps, different confidence levels, different indications of confidence level, different interval error types, different indications of interval error types, different machine learning (ML) models or ML model groups, different indications of machine learning (ML) models or ML model groups different functionalities, different indications of functionalities, different features or feature groups, different indications of features or feature groups, different beam sets, different beam set identities, different beams, or different beams identities.
[0380] In some example embodiments, the first information comprises at least one of the following: a minimum interval error, a maximum interval error, an average interval error, or an interval error range.
[0381] In some example embodiments, in a case that a confidence level of the first information is absent in the message, the first information is assumed to be associated with a specific confidence level.
[0382] In some example embodiments, the second device may transmit, to the first device, configuration information comprising at least one of the following: confidence level information, an indication indicating an interval type to be reported, the interval type being a confidence interval or a prediction interval, an indication used for enabling or disabling reporting of prediction interval information, an indication used for enabling or disabling reporting of confidence interval information, an indication used for enabling or disabling reporting of the interval error information, an indication indicating an interval error type to be reported, the interval error type being a confidence interval error or prediction interval error, an indication used for enabling or disabling reporting of prediction interval error information, an indication used for enabling or disabling reporting of confidence interval error information, or a report quantity comprising at least one of the following: confidence interval, prediction interval, interval error, confidence interval error, prediction interval error, interval error range, minimum interval error, maximum interval error, average interval error, interval error range, minimum confidence interval error, maximum confidence interval error, average confidence interval error, confidence interval error range, minimum prediction interval error, maximum prediction interval error, average prediction interval error, prediction interval error range.
[0383] In some example embodiments, the message comprises at least one of the following: the at least one interval error corresponding to the at least one predicted beam to be reported, a first minimum interval error of the plurality of interval errors or the at least one predicted beam to be reported, a first maximum interval error of the plurality of interval errors or the at least one predicted beam to be reported, a first average interval error of the plurality of interval errors or the at least one predicted beam to be reported, a second minimum interval error of the at least one interval error or the at least one predicted beam to be reported, a second maximum interval error of the at least one interval error or the at least one predicted beam to be reported, or a second average interval error of the at least one interval error or the at least one predicted beam to be reported.
[0384] In some example embodiments, the message is a channel status information (CSI) report comprising the following: at least one first field indicating the at least one predicted beam, at least one second field indicating at least one predicted quality, and at least one third field indicating the at least one interval error, wherein, an order of the at least one third field is the same as an order of the at least one first field.
[0385] In some example embodiments, a bitwidth for the third field is determined based on at least one of the following: a total number of candidate values of interval error, a total number of indexes of candidate value ranges of interval error, a maximum number of values of interval error supported by the first device, or a maximum value of interval error supported by the first device.
[0386] In some example embodiments, the second device may transmit, to the first device, configuration indicating at least event used for triggering a transmission of the message, the at least one event comprising at least one of the following: an interval error corresponding to a specific predicted quality being lower than or equal to a threshold, an interval error corresponding to a specific predicted quality being higher than or equal to a threshold, the first minimum interval error being lower than or equal to a threshold, the first minimum interval error being higher than or equal to a threshold, the first maximum interval error being lower than or equal to a threshold, the first maximum interval error being higher than or equal to a threshold, the first average interval error being lower than or equal to a threshold, the first average interval error being higher than or equal to a threshold, the second minimum interval error being lower than or equal to a threshold, the second minimum interval error being higher than or equal to a threshold, the second maximum interval error being lower than or equal to a threshold, the second maximum interval error being higher than or equal to a threshold, the second average interval error being lower than or equal to a threshold, the second average interval error being higher than or equal to a threshold.
[0387] In some example embodiments, the message further indicates at least of the following: information indicating the first device supports to provide the first information, or information indicating whether the first device supports outputting point prediction.
[0388] Example Apparatus and Devices
[0389] FIG. 11 is a simplified block diagram of a device 1100 that is suitable for implementing embodiments of the present disclosure. The device 1100 can be considered as a further example implementation of any of the devices as shown in FIG. 1. Accordingly, the device 1100 can be implemented at or as at least a part of the first device 110 or the second device 120.
[0390] As shown, the device 1100 includes a processor 1110, a memory 1120 coupled to the processor 1110, a suitable transceiver 1140 coupled to the processor 1110, and a communication interface coupled to the transceiver 1140. The memory 1120 stores at least a part of a program 1130. The transceiver 1140 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 1140 may include at least one of a transmitter 1142 and a receiver 1144. The transmitter 1142 and the receiver 1144 may be functional modules or physical entities. The transceiver 1140 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.
[0391] The program 1130 is assumed to include program instructions that, when executed by the associated processor 1110, enable the device 1100 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGS. 1 to 11. The embodiments herein may be implemented by computer software executable by the processor 1110 of the device 1100, or by hardware, or by a combination of software and hardware. The processor 1110 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 1110 and memory 1120 may form processing means 1150 adapted to implement various embodiments of the present disclosure.
[0392] The memory 1120 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 1120 is shown in the device 1100, there may be several physically distinct memory modules in the device 1100. The processor 1110 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 1100 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.
[0393] According to embodiments of the present disclosure, a first device comprising a circuitry is provided. The circuitry is configured to: generate a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; and transmit the message to the 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.
[0394] According to embodiments of the present disclosure, a first device comprising a circuitry is provided. The circuitry is configured to: determines, at least one requirement for a performance related to one of the following: a beam prediction, an artificial intelligence (AI) / machine learning (ML) -based beam management, a predicted reference signal receiving power (RSRP) , a predicted beam, an AI / ML model, an AI / ML functionality, or a model inference, wherein at least one requirement comprises at least one of the following: a confidence interval requirement, a prediction interval requirement, a confidence interval error requirement, or a prediction interval error requirement; and apply the at least one requirement. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the first device as discussed above.
[0395] 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 message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; and determine the interval error based on the message. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the second device as discussed above.
[0396] 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.
[0397] According to embodiments of the present disclosure, a first apparatus is provided. The first apparatus comprises means for generating a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: means for a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or means for a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; and means for transmitting the message to the second device. In some embodiments, the first apparatus may comprise means for performing the respective operations of the method 800. In some example embodiments, the first 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.
[0398] According to embodiments of the present disclosure, a first apparatus is provided. The first apparatus comprises means for determines, at least one requirement for a performance related to one of the following: a beam prediction, an artificial intelligence (AI) / machine learning (ML) -based beam management, a predicted reference signal receiving power (RSRP) , a predicted beam, an AI / ML model, an AI / ML functionality, or a model inference, wherein at least one requirement comprises at least one of the following: means for a confidence interval requirement, means for a prediction interval requirement, means for a confidence interval error requirement, or means for a prediction interval error requirement; and means for applying the at least one requirement. In some embodiments, the second apparatus may comprise means for performing the respective operations of the method 900. In some example embodiments, the second apparatus may further comprise means for performing other operations in some example embodiments of the method 900. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.
[0399] According to embodiments of the present disclosure, a second apparatus is provided. The second apparatus comprises means for receiving, from a first device, a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: means for a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or means for a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; and means for determining the interval error based on the message. In some embodiments, the third apparatus may comprise means for performing the respective operations of the method 1000. In some example embodiments, the third apparatus may further comprise means for performing other operations in some example embodiments of the method 1000. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.
[0400] In summary, embodiments of the present disclosure provide the following aspects.
[0401] In an aspect, it is proposed a first device comprising: a processor configured to cause the first device to: generate a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; and transmit the message to the second device.
[0402] In some embodiments, the message is at least one of the following: a radio resource control (RRC) message carrying user equipment (UE) capability information, an RRC message carrying UE assistance information (UAI) , or a measurement report.
[0403] In some embodiments, the first information is associated with one of the following: a beam, a beam identity, a beam set, a beam set identity, a time stamp, an indication of a time stamp, a confidence level, an indication of a confidence level, a machine learning (ML) model or ML model group, an indication of a ML model or ML model group a functionality, an indication of a functionality, a feature or feature group (FG) , or an indication of a feature or feature group.
[0404] In some embodiments, the message further comprises second information about a second interval error, and the first interval error and the second interval error are associated with at least one of the following: different time stamps, different indications of time stamps, different confidence levels, different indications of confidence level, different interval error types, different indications of interval error types, different machine learning (ML) models or ML model groups, different indications of machine learning (ML) models or ML model groups, different functionalities, different indications of functionalities, different features or feature groups, different indications of features or feature groups, different beam sets, different beam set identities, different beams, or different beams identities.
[0405] In some embodiments, the first information comprises at least one of the following: a minimum interval error, a maximum interval error, an average interval error, or an interval error range.
[0406] In some embodiments, in a case that a confidence level of the first information is absent in the message, the first information is assumed to be associated with a specific confidence level.
[0407] In some embodiments, the processor is further configured to cause the first device to: transmit the message to the second device upon at least one of the following: a completion of a model deployment, a completion of a model identification, a completion of a model delivery or transfer (is completed) , a completion of a model training, a completion of a model validation, a completion of a model testing, a completion of model monitoring, a performance change of a model, a model switching, a model selection, a model activation, or a model update.
[0408] In some embodiments, the processor is further configured to cause the first device to: receive, from the second device, configuration information comprising at least one of the following: confidence level information, an indication indicating an interval type to be reported, the interval type being a confidence interval or a prediction interval, an indication used for enabling or disabling reporting of prediction interval information, an indication used for enabling or disabling reporting of confidence interval information, an indication used for enabling or disabling reporting of the interval error information, an indication indicating an interval error type to be reported, the interval error type being a confidence interval error or prediction interval error, an indication used for enabling or disabling reporting of prediction interval error information, an indication used for enabling or disabling reporting of confidence interval error information, or a report quantity comprising at least one of the following: confidence interval, prediction interval, interval error, confidence interval error, prediction interval error, interval error range, minimum interval error, maximum interval error, average interval error, interval error range, minimum confidence interval error, maximum confidence interval error, average confidence interval error, confidence interval error range, minimum prediction interval error, maximum prediction interval error, average prediction interval error, prediction interval error range.
[0409] In some embodiments, the processor is further configured to cause the first device to: perform a model inference to derive the following: a plurality of predicted beams, a plurality of predicted qualities corresponding to the plurality of predicted beams, and a plurality of interval errors corresponding to the plurality of predicted beams; determine, from the plurality of predicted beams based on the plurality of predicted qualities, at least one predicted beam to be reported; and transmit the message comprising at least one of the following: the at least one interval error corresponding to the at least one predicted beam to be reported, a first minimum interval error of the plurality of interval errors or the at least one predicted beam to be reported, a first maximum interval error of the plurality of interval errors or the at least one predicted beam to be reported, a first average interval error of the plurality of interval errors or the at least one predicted beam to be reported, a second minimum interval error of the at least one interval error or the at least one predicted beam to be reported, a second maximum interval error of the at least one interval error or the at least one predicted beam to be reported, or a second average interval error of the at least one interval error or the at least one predicted beam to be reported.
[0410] In some embodiments, the message is a channel status information (CSI) report comprising the following: at least one first field indicating the at least one predicted beam, at least one second field indicating at least one predicted quality, and at least one third field indicating the at least one interval error, wherein, an order of the at least one third field is the same as an order of the at least one first field.
[0411] In some embodiments, a bitwidth for the third field is determined based on at least one of the following: a total number of candidate values of interval error, a total number of indexes of candidate value ranges of interval error, a maximum number of values of interval error supported by the first device, or a maximum value of interval error supported by the first device.
[0412] In some embodiments, the processor is further configured to cause the first device to: transmit the message in response to at least one of the following: an interval error corresponding to a specific predicted quality being lower than or equal to a threshold, an interval error corresponding to a specific predicted quality being higher than or equal to a threshold, the first minimum interval error being lower than or equal to a threshold, the first minimum interval error being higher than or equal to a threshold, the first maximum interval error being lower than or equal to a threshold, the first maximum interval error being higher than or equal to a threshold, the first average interval error being lower than or equal to a threshold, the first average interval error being higher than or equal to a threshold, the second minimum interval error being lower than or equal to a threshold, the second minimum interval error being higher than or equal to a threshold, the second maximum interval error being lower than or equal to a threshold, the second maximum interval error being higher than or equal to a threshold, the second average interval error being lower than or equal to a threshold, the second average interval error being higher than or equal to a threshold.
[0413] In some embodiments, the message further indicates at least of the following: information indicating whether the first device supports to provide the first information, or information indicating whether the first device supports outputting point prediction.
[0414] In an aspect, it is proposed a first device comprising: a processor configured to cause the first device to: determines, at least one requirement for a performance related to one of the following: a beam prediction, an artificial intelligence (AI) / machine learning (ML) -based beam management, a predicted reference signal receiving power (RSRP) , a predicted beam, an AI / ML model, an AI / ML functionality, or a model inference, wherein at least one requirement comprises at least one of the following: a confidence interval requirement, a prediction interval requirement, a confidence interval error requirement, or a prediction interval error requirement; and apply the at least one requirement.
[0415] In some embodiments, the confidence interval error requirement comprises at least one of the following: a specific confidence interval error requirement, a minimum confidence interval error requirement, a maximum confidence interval error requirement, or an average confidence interval error requirement, and wherein the prediction interval error requirement comprises at least one of the following: a specific prediction interval error requirement, a minimum prediction interval error requirement, a maximum prediction interval error requirement, or an average prediction interval error requirement.
[0416] In some embodiments, at least one requirement is associated with at least one of the following: different confidence levels, different indications of confidence level different interval error types, different indications of interval error types, different machine learning (ML) models or ML model groups, different indications of machine learning (ML) models or ML model groups different functionalities, different indications of functionalities, different features or feature groups, different indications of features or feature groups, different beam sets, different beam set identities, different beams, or different beams identities.
[0417] In an aspect, it is proposed a second device comprising: a processor configured to cause the second device to: receive, from a first device, a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following: a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, or a prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; and determine the interval error based on the message.
[0418] In some embodiments, the message is at least one of the following: a radio resource control (RRC) message carrying user equipment (UE) capability information, an RRC message carrying UE assistance information (UAI) , or a measurement report.
[0419] In some embodiments, the first information is associated with one of the following: a beam, a beam ID, a beam set, a beam set ID, a time stamp, an indication of a time stamp, a confidence level, an indication of a confidence level, a machine learning (ML) model or ML model group, an indication of a ML model or ML model group a functionality, an indication of a functionality, a feature or feature group (FG) , or an indication of a feature or feature group.
[0420] In some embodiments, the message further comprises second information about a second interval error, and the first interval error and the second interval error are associated with at least one of the following: different time stamps, different indications of time stamps, different confidence levels, different indications of confidence level, different interval error types, different indications of interval error types, different machine learning (ML) models or ML model groups, different indications of machine learning (ML) models or ML model groups different functionalities, different indications of functionalities, different features or feature groups, different indications of features or feature groups, different beam sets, different beam set identities, different beams, or different beams identities.
[0421] In some embodiments, the first information comprises at least one of the following: a minimum interval error, a maximum interval error, an average interval error, or an interval error range.
[0422] In some embodiments, in a case that a confidence level of the first information is absent in the message, the first information is assumed to be associated with a specific confidence level.
[0423] In some embodiments, the processor is further configured to cause the second device to: transmit, to the first device, configuration information comprising at least one of the following: confidence level information, an indication indicating an interval type to be reported, the interval type being a confidence interval or a prediction interval, an indication used for enabling or disabling reporting of prediction interval information, an indication used for enabling or disabling reporting of confidence interval information, an indication used for enabling or disabling reporting of the interval error information, an indication indicating an interval error type to be reported, the interval error type being a confidence interval error or prediction interval error, an indication used for enabling or disabling reporting of prediction interval error information, an indication used for enabling or disabling reporting of confidence interval error information, or a report quantity comprising at least one of the following: confidence interval, prediction interval, interval error, confidence interval error, prediction interval error, interval error range, minimum interval error, maximum interval error, average interval error, interval error range, minimum confidence interval error, maximum confidence interval error, average confidence interval error, confidence interval error range, minimum prediction interval error, maximum prediction interval error, average prediction interval error, prediction interval error range.
[0424] In some embodiments, the message comprises at least one of the following: the at least one interval error corresponding to the at least one predicted beam to be reported, a first minimum interval error of the plurality of interval errors or the at least one predicted beam to be reported, a first maximum interval error of the plurality of interval errors or the at least one predicted beam to be reported, a first average interval error of the plurality of interval errors or the at least one predicted beam to be reported, a second minimum interval error of the at least one interval error or the at least one predicted beam to be reported, a second maximum interval error of the at least one interval error or the at least one predicted beam to be reported, or a second average interval error of the at least one interval error or the at least one predicted beam to be reported.
[0425] In some embodiments, the message is a channel status information (CSI) report comprising the following: at least one first field indicating the at least one predicted beam, at least one second field indicating at least one predicted quality, and at least one third field indicating the at least one interval error, wherein, an order of the at least one third field is the same as an order of the at least one first field.
[0426] In some embodiments, a bitwidth for the third field is determined based on at least one of the following: a total number of candidate values of interval error, a total number of indexes of candidate value ranges of interval error, a maximum number of values of interval error supported by the first device, or a maximum value of interval error supported by the first device.
[0427] In some embodiments, the processor is further configured to cause the second device to: transmit, to the first device, configuration indicating at least event used for triggering a transmission of the message, the at least one event comprising at least one of the following: an interval error corresponding to a specific predicted quality being lower than or equal to a threshold, an interval error corresponding to a specific predicted quality being higher than or equal to a threshold, the first minimum interval error being lower than or equal to a threshold, the first minimum interval error being higher than or equal to a threshold, the first maximum interval error being lower than or equal to a threshold, the first maximum interval error being higher than or equal to a threshold, the first average interval error being lower than or equal to a threshold, the first average interval error being higher than or equal to a threshold, the second minimum interval error being lower than or equal to a threshold, the second minimum interval error being higher than or equal to a threshold, the second maximum interval error being lower than or equal to a threshold, the second maximum interval error being higher than or equal to a threshold, the second average interval error being lower than or equal to a threshold, the second average interval error being higher than or equal to a threshold.
[0428] In some embodiments, the message further indicates at least of the following: information indicating the first device supports to provide the first information, or information indicating whether the first device supports outputting point prediction.
[0429] 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.
[0430] 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.
[0431] 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.
[0432] 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.
[0433] 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.
[0434] 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.
[0435] 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.
[0436] 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 11. 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.
[0437] 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.
[0438] 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.
[0439] 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.
[0440] 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:generate a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following:a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, ora prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; andtransmit the message to the second device.2.The first device of claim 1, wherein the message is at least one of the following:a radio resource control (RRC) message carrying user equipment (UE) capability information,an RRC message carrying UE assistance information (UAI) , ora measurement report.3.The first device of claim 1, wherein the first information is associated with one of the following:a beam,a beam identity,a beam set,a beam set identity,a time stamp,an indication of a time stamp,a confidence level,an indication of a confidence level,a machine learning (ML) model or ML model group,an indication of a ML model or ML model groupa functionality,an indication of a functionality,a feature or feature group (FG) , oran indication of a feature or feature group.4.The first device of claim 1, wherein the message further comprises second information about a second interval error, and the first interval error and the second interval error are associated with at least one of the following:different time stamps,different indications of time stamps,different confidence levels,different indications of confidence level,different interval error types,different indications of interval error types,different machine learning (ML) models or ML model groups,different indications of machine learning (ML) models or ML model groups,different functionalities,different indications of functionalities,different features or feature groups,different indications of features or feature groups,different beam sets,different beam set identities,different beams, ordifferent beams identities.5.The first device of claim 1, wherein the first information comprises at least one of the following:a minimum interval error,a maximum interval error,an average interval error, oran interval error range.6.The first device of claim 1, wherein,in a case that a confidence level of the first information is absent in the message, the first information is assumed to be associated with a specific confidence level.7.The first device of claim 1, wherein the processor is further configured to cause the first device to:transmit the message to the second device upon at least one of the following:a completion of a model deployment,a completion of a model identification,a completion of a model delivery or transfer (is completed) ,a completion of a model training,a completion of a model validation,a completion of a model testing,a completion of model monitoring,a performance change of a model,a model switching,a model selection,a model activation, ora model update.8.The first device of claim 1, wherein the processor is further configured to cause the first device to:receive, from the second device, configuration information comprising at least one of the following:confidence level information,an indication indicating an interval type to be reported, the interval type being a confidence interval or a prediction interval,an indication used for enabling or disabling reporting of prediction interval information,an indication used for enabling or disabling reporting of confidence interval information,an indication used for enabling or disabling reporting of the interval error information,an indication indicating an interval error type to be reported, the interval error type being a confidence interval error or prediction interval error,an indication used for enabling or disabling reporting of prediction interval error information,an indication used for enabling or disabling reporting of confidence interval error information, ora report quantity comprising at least one of the following: confidence interval, prediction interval, interval error, confidence interval error, prediction interval error, interval error range, minimum interval error, maximum interval error, average interval error, interval error range, minimum confidence interval error, maximum confidence interval error, average confidence interval error, confidence interval error range, minimum prediction interval error, maximum prediction interval error, average prediction interval error, prediction interval error range.9.The first device of claim 1, wherein the processor is further configured to cause the first device to:perform a model inference to derive the following:a plurality of predicted beams,a plurality of predicted qualities corresponding to the plurality of predicted beams, anda plurality of interval errors corresponding to the plurality of predicted beams;determine, from the plurality of predicted beams based on the plurality of predicted qualities, at least one predicted beam to be reported; andtransmit the message comprising at least one of the following:the at least one interval error corresponding to the at least one predicted beam to be reported,a first minimum interval error of the plurality of interval errors,a first maximum interval error of the plurality of interval errors,a first average interval error of the plurality of interval errors,a second minimum interval error of the at least one interval error,a second maximum interval error of the at least one interval error, ora second average interval error of the at least one interval error.10.The first device of claim 9, wherein the message is a channel status information (CSI) report comprising the following:at least one first field indicating the at least one predicted beam,at least one second field indicating at least one predicted quality, andat least one third field indicating the at least one interval error,wherein, an order of the at least one third field is the same as an order of the at least one first field.11.The first device of claim 10, wherein a bitwidth for the third field is determined based on at least one of the following:a total number of candidate values of interval error,a total number of indexes of candidate value ranges of interval error,a maximum number of values of interval error supported by the first device, ora maximum value of interval error supported by the first device.12.The first device of 9, wherein the processor is further configured to cause the first device to:transmit the message in response to at least one of the following:an interval error corresponding to a specific predicted quality being lower than or equal to a threshold,an interval error corresponding to a specific predicted quality being higher than or equal to a threshold,the first minimum interval error being lower than or equal to a threshold,the first minimum interval error being higher than or equal to a threshold,the first maximum interval error being lower than or equal to a threshold,the first maximum interval error being higher than or equal to a threshold,the first average interval error being lower than or equal to a threshold,the first average interval error being higher than or equal to a threshold,the second minimum interval error being lower than or equal to a threshold,the second minimum interval error being higher than or equal to a threshold,the second maximum interval error being lower than or equal to a threshold,the second maximum interval error being higher than or equal to a threshold,the second average interval error being lower than or equal to a threshold, orthe second average interval error being higher than or equal to a threshold.13.The first device of claim 1, wherein the message further indicates at least of the following:information indicating whether the first device supports to provide the first information, orinformation indicating whether the first device supports outputting point prediction.14.A first device comprising:a processor configured to cause the first device to:determine, at least one requirement for a performance related to one of the following: a beam prediction, an artificial intelligence (AI) / machine learning (ML) -based beam management, a predicted reference signal receiving power (RSRP) , a predicted beam, an AI / ML model, an AI / ML functionality, or a model inference, wherein at least one requirement comprises at least one of the following:a confidence interval requirement,a prediction interval requirement,a confidence interval error requirement, ora prediction interval error requirement; andapply the at least one requirement.15.The first device of claim 14, wherein the confidence interval error requirement comprises at least one of the following:a specific confidence interval error requirement,a minimum confidence interval error requirement,a maximum confidence interval error requirement, oran average confidence interval error requirement,and wherein the prediction interval error requirement comprises at least one of the following:a specific prediction interval error requirement,a minimum prediction interval error requirement,a maximum prediction interval error requirement, oran average prediction interval error requirement.16.The first device of claim 14, wherein at least one requirement is associated with at least one of the following:different confidence levels,different indications of confidence leveldifferent interval error types,different indications of interval error types,different machine learning (ML) models or ML model groups,different indications of machine learning (ML) models or ML model groups,different functionalities,different indications of functionalities,different features or feature groups,different indications of features or feature groups,different beam sets,different beam set identities,different beams, ordifferent beams identities.17.A second device comprising:a processor configured to cause the second device to:receive, from a first device, a message comprising first information about a first interval error, wherein the interval error comprises at least one of the following:a confidence interval error indicates a difference between one of the following: a value of a point prediction and a lower bound value of a confidence interval associated with point prediction, or an upper bound value of the confidence interval and the value of the point prediction, ora prediction interval error indicates a difference between one of the following: the value of the point prediction and a lower bound value of a prediction interval associated with point prediction, or an upper bound value of the prediction interval and the value of the point prediction; anddetermine the interval error based on the message.18.The second device of claim 17, wherein the message is at least one of the following:a radio resource control (RRC) message carrying user equipment (UE) capability information,an RRC message carrying UE assistance information (UAI) , ora measurement report.19.The second device of claim 17, wherein the first information is associated with one of the following:a beam,a beam ID,a beam set,a beam set ID,a time stamp,an indication of a time stamp,a confidence level,an indication of a confidence level,a machine learning (ML) model or ML model group,an indication of a ML model or ML model groupa functionality,an indication of a functionality,a feature or feature group (FG) , oran indication of a feature or feature group.20.The second device of claim 17, wherein the message further comprises second information about a second interval error, and the first interval error and the second interval error are associated with at least one of the following:different time stamps,different indications of time stamps,different confidence levels,different indications of confidence level,different interval error types,different indications of interval error types,different machine learning (ML) models or ML model groups,different indications of machine learning (ML) models or ML model groups,different functionalities,different indications of functionalities,different features or feature groups,different indications of features or feature groups,different beam sets,different beam set identities,different beams, ordifferent beams identities.21.The second device of claim 17, wherein the first information comprises at least one of the following:a minimum interval error,a maximum interval error,an average interval error, oran interval error range.22.The second device of claim 17, wherein,in a case that a confidence level of the first information is absent in the message, the first information is assumed to be associated with a specific confidence level.23.The second device of claim 17, wherein the processor is further configured to cause the second device to:transmit, to the first device, configuration information comprising at least one of the following:confidence level information,an indication indicating an interval type to be reported, the interval type being a confidence interval or a prediction interval,an indication used for enabling or disabling reporting of prediction interval information,an indication used for enabling or disabling reporting of confidence interval information,an indication used for enabling or disabling reporting of the interval error information,an indication indicating an interval error type to be reported, the interval error type being a confidence interval error or prediction interval error,an indication used for enabling or disabling reporting of prediction interval error information,an indication used for enabling or disabling reporting of confidence interval error information, ora report quantity comprising at least one of the following: confidence interval, prediction interval, interval error, confidence interval error, prediction interval error, interval error range, minimum interval error, maximum interval error, average interval error, interval error range, minimum confidence interval error, maximum confidence interval error, average confidence interval error, confidence interval error range, minimum prediction interval error, maximum prediction interval error, average prediction interval error, prediction interval error range.24.The second device of claim 17, wherein the message comprises at least one of the following:the at least one interval error corresponding to the at least one predicted beam to be reported,a first minimum interval error of the plurality of interval errors,a first maximum interval error of the plurality of interval errors,a first average interval error of the plurality of interval errors,a second minimum interval error of the at least one interval error,a second maximum interval error of the at least one interval error, ora second average interval error of the at least one interval error.25.The second device of claim 24, wherein the message is a channel status information (CSI) report comprising the following:at least one first field indicating the at least one predicted beam,at least one second field indicating at least one predicted quality, andat least one third field indicating the at least one interval error,wherein, an order of the at least one third field is the same as an order of the at least one first field.26.The second device of claim 25, wherein a bitwidth for the third field is determined based on at least one of the following:a total number of candidate values of interval error,a total number of indexes of candidate value ranges of interval error,a maximum number of values of interval error supported by the first device, ora maximum value of interval error supported by the first device.27.The first device of 24, wherein the processor is further configured to cause the second device to:transmit, to the first device, configuration indicating at least event used for triggering a transmission of the message, the at least one event comprising at least one of the following:an interval error corresponding to a specific predicted quality being lower than or equal to a threshold,an interval error corresponding to a specific predicted quality being higher than or equal to a threshold,the first minimum interval error being lower than or equal to a threshold,the first minimum interval error being higher than or equal to a threshold,the first maximum interval error being lower than or equal to a threshold,the first maximum interval error being higher than or equal to a threshold,the first average interval error being lower than or equal to a threshold,the first average interval error being higher than or equal to a threshold,the second minimum interval error being lower than or equal to a threshold,the second minimum interval error being higher than or equal to a threshold,the second maximum interval error being lower than or equal to a threshold,the second maximum interval error being higher than or equal to a threshold,the second average interval error being lower than or equal to a threshold, orthe second average interval error being higher than or equal to a threshold.28.The second device of claim 17, wherein the message further indicates at least of the following:information indicating the first device supports to provide the first information, orinformation indicating whether the first device supports outputting point prediction.
Citation Information
Patent Citations
Machine learning pipeline for predictions regarding a network
CN113886001A
Method for user equipment for improving transmission efficiency, method for network entity, device, vehicle and computer program
CN115988527A
Network assisted error detection for artificial intelligence on air interface
WO2023187684A1
Predicted measurement reporting
WO2024020026A1