Method, terminal device, and network device

Abstract

The embodiments of the present disclosure relate to a method, an apparatus, and a computer-readable medium for communication. According to the embodiments of the present disclosure, a terminal device receives a measurement configuration or a transmission configuration from a network device. The terminal device performs a measurement based on the measurement configuration, and reports a result of the measurement to the network device. Alternatively, if the terminal device performs a transmission based on the transmission configuration, the network device performs a measurement based on the transmission. The network device trains an artificial intelligence (AI) or machine learning (ML) based on the result of the measurement. Thus, the actual measurement result is used to build a dataset suitable for the AI ​​or ML model in the network device.

Description

Technical Field

[0001] Embodiments of the present disclosure generally relate to the field of telecommunications, and more particularly to communication methods, devices, and computer-readable media.

Background Art

[0002] Several technologies have been proposed to improve communication performance. For example, a communication device may adopt an artificial intelligence / machine learning (AI / ML) model to improve communication quality. The AI / ML model can be applied to various scenarios to achieve better performance. Therefore, it is valuable to study how to properly train the AI / ML model to ensure satisfactory communication performance.

Summary of the Invention

Problems to be Solved by the Invention

[0003] Generally, exemplary embodiments of the present disclosure provide solutions for communication.

Means for Solving the Problems

[0004] In a first embodiment, a communication method is provided, the communication method comprising: a terminal device receiving from a network device a first setting indicating at least one resource subset from a first set of resources, wherein the at least one resource subset is for constructing a first dataset for training a first artificial intelligence (AI) / machine learning (ML) model in the network device, wherein the first dataset includes at least one of a training dataset for model training, a validation dataset for model training, a test dataset for model training, or a dataset for model inference; and transmitting to the network device information relating to a quality determination based on the at least one resource subset, wherein the information is for constructing the first dataset.

[0005] In a second embodiment, a communication method is provided, which includes a network device transmitting a first setting to a terminal device, which indicates at least one resource subset from a first set of resources, wherein the at least one resource subset is for constructing a first dataset for training a first artificial intelligence (AI) / machine learning (ML) model in the network device, and the first dataset includes at least one of a training dataset for model training, a validation dataset for model training, a test dataset for model training, or a dataset for model inference, and receiving from the terminal device information relating to a quality determination based on the at least one resource subset, wherein the information is for constructing the first dataset.

[0006] In a third embodiment, a terminal device is provided, comprising a processing unit and a memory coupled to the processing unit for storing instructions, wherein when an instruction is executed by the processing unit, the terminal device performs an operation including receiving a first setting from a network device indicating at least one resource subset from a first set of resources, the at least one resource subset being for constructing a first dataset for training a first artificial intelligence (AI) / machine learning (ML) model in the network device, the first dataset being for at least one of a training dataset for model training, a validation dataset for model training, a test dataset for model training, or a dataset for model inference, and transmitting information to the network device regarding a quality determination based on the at least one resource subset, the information being for constructing the first dataset.

[0007] In a fourth embodiment, a network device is provided, comprising a processing unit and a memory coupled to the processing unit for storing instructions, wherein when an instruction is executed by the processing unit, the network device performs an operation that includes transmitting a first setting to a terminal device, which indicates at least one resource subset from a first set of resources, the at least one resource subset being for constructing a first dataset for training a first artificial intelligence (AI) / machine learning (ML) model in the network device, the first dataset being for at least one of a training dataset for model training, a validation dataset for model training, a test dataset for model training, or a dataset for model inference, and receiving from the terminal device information relating to a quality determination based on the at least one resource subset, the information relating to constructing the first dataset.

[0008] In a fifth embodiment, a computer-readable medium is provided that, when executed on at least one processor, stores instructions causing the at least one processor to perform the method described in the first or second embodiment.

[0009] Other features of this disclosure should be easily understood from the following explanation. [Brief explanation of the drawing]

[0010] The accompanying drawings further illustrate some exemplary embodiments of this disclosure, thereby further highlighting the aforementioned and other objectives, features, and advantages of this disclosure. [Figure 1] This is a schematic diagram of a communication environment in which the embodiments of this disclosure can be implemented. [Figure 2A] This is a schematic diagram of an AI / ML model that can be implemented in a network device. [Figure 2B] This is a schematic diagram of the dataset built for the AI / ML model. [Figure 3] This figure shows a signaling flow for communication according to some embodiments of the present disclosure. [Figure 4A] This figure shows a signaling flow for communication according to some embodiments of the present disclosure. [Figure 4B] This figure shows a signaling flow for communication according to some embodiments of the present disclosure. [Figure 4C] This figure shows a signaling flow for communication according to some embodiments of the present disclosure. [Figure 5A] This figure shows a signaling flow for communication according to some embodiments of the present disclosure. [Figure 5B] This figure shows a signaling flow for communication according to some embodiments of the present disclosure. [Figure 5C] This figure shows a signaling flow for communication according to some embodiments of the present disclosure. [Figure 6A]Schematic diagrams of the inputs and outputs of an AI / ML model according to some embodiments of the present disclosure. [Figure 6B] Schematic diagrams of the inputs and outputs of an AI / ML model according to some embodiments of the present disclosure. [Figure 6C] Schematic diagrams of the inputs and outputs of an AI / ML model according to some embodiments of the present disclosure. [Figure 6D] Schematic diagrams of the inputs and outputs of an AI / ML model according to some embodiments of the present disclosure. [Figure 7A] Schematic diagram of a dataset according to some embodiments of the present disclosure. [Figure 7B] Schematic diagram of a dataset according to some embodiments of the present disclosure. [Figure 8] Flowchart of an exemplary method according to an embodiment of the present disclosure. [Figure 9] Flowchart of an exemplary method according to an embodiment of the present disclosure. [Figure 10] Schematic block diagram of an apparatus suitable for implementing an embodiment of the present disclosure.

[0011] In the figures, the same or similar reference numerals represent the same or similar elements.

MODE FOR CARRYING OUT THE INVENTION

[0012] Here, the principles of the present disclosure will be explained with reference to some exemplary embodiments. It should be understood that these embodiments are described for illustrative purposes only and are intended to assist those skilled in the art in understanding and implementing the present disclosure, and do not imply any limitation on the scope of the present disclosure. The disclosure described herein can be implemented in various ways different from the methods described below.

[0013] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0014] As used herein, the term “terminal device” refers to any device having wireless or wired communication capabilities. Examples of terminal devices include user equipment (UE), personal computers, desktops, mobile phones, cellular phones, smartphones, personal digital assistants (PDAs), portable computers, tablets, wearable devices, Internet of Things (IoT) devices, ultra-reliable low-latency communication (URLLC) devices, Internet of Everything (IoE) devices, machine-type communication (MTC) devices, in-vehicle devices for V2X communication where X represents pedestrians, vehicles, or infrastructure / networks, devices for integrated access and integrated access and backhaul (IAB), satellite-borne or aircraft-borne vehicles within non-terrestrial networks (NTN) including high-altitude platforms (HAP) encompassing satellites and unmanned aircraft systems (UAS), extended reality (XR) devices including different types of reality such as augmented reality (AR), mixed reality (MR), and virtual reality (VR), and unmanned aerial vehicles (UAVs), which are aircraft without human pilots and are commonly referred to as drones. This includes, but is not limited to, devices on a vehicle, a high-speed train (HST), or image acquisition devices such as digital cameras, sensor game devices, music storage and playback devices, or internet-connected home appliances that enable wireless or wired internet access and browsing. A “terminal device” may further have “multicast / broadcast” capabilities to support V2X applications, transparent IPv4 / IPv6 multicast distribution, IPTV, smart TV, wireless services, wireless software distribution, group communications, and IoT applications, where public safety and mission are of paramount importance. It may also incorporate one or more Subscriber Identity Modules (SIMs), known as multi-SIMs.The term "terminal equipment" may be used interchangeably with UE, mobile station, subscriber station, mobile terminal, user terminal, or radio equipment. In the following description, the terms "terminal equipment," "communication equipment," "terminal," "user equipment," and "UE" may be used interchangeably.

[0015] Terminal devices or network devices may possess artificial intelligence (AI) or machine learning capabilities. Generally, this includes a trained model derived from a large amount of data collected for a specific function, which can be used to predict certain information.

[0016] Terminal or network devices may operate on several frequency ranges, such as FR1 (410 MHz to 7125 MHz), FR2 (24.25 GHz to 71 GHz), frequency bands greater than 100 GHz, and terahertz (THz). Furthermore, they can operate on licensed / unlicensed / shared spectrum. Terminal devices may have two or more connections to network devices under Multi-Radio Dual Connectivity (MR-DC) application scenarios. Terminal or network devices can operate in full-duplex, flexible-duplex, or cross-split-duplex modes.

[0017] The term "network device" refers to a device that can provide or host a cell or coverage on which terminal devices can communicate. Examples of network devices include, but are not limited to, Node B (NodeB or NB), Evolutionary Node B (eNodeB or eNB), Next Generation Node B (gNB), Transmit / Receive Point (TRP), Remote Radio Unit (RRU), Radio Head (RH), Remote Radio Head (RRH), IAB Node, Femto Node, Pico Node, Reconfigurable Intelligent Surface (RIS) and other low-power nodes, and network management entities such as Operations, Administration and Maintenance (OAM) entities.

[0018] In one embodiment, a terminal device can be connected to a first network device and a second network device. One of the first and second network devices may be a master node and the other a secondary node. The first and second network devices may use different radio access technologies (RATs). In one embodiment, the first network device may be a first RAT device, and the second network device may be a second RAT device. In one embodiment, the first RAT device is an eNB, and the second RAT device is a gNB. Information regarding different RATs may be transmitted to the terminal device from at least one of the first and second network devices. In one embodiment, the first information may be transmitted from the first network device to the terminal device, and the second information may be transmitted from the second network device directly or via the first network device to the terminal device. In one embodiment, information regarding the settings of the terminal device set by the second network device may be transmitted from the second network device via the first network device. Information regarding the reconfiguration of terminal devices set by the second network device may be transmitted from the second network device directly to the terminal devices or via the first network device.

[0019] The communications described herein may conform to any appropriate standard, including but not limited to New Radio Access (NR), Long-Term Evolution (LTE), LTE-Evolution, LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA®), Code Division Multiple Access (CDMA), cdma2000, and Global System for Mobile Communications (GSM). Furthermore, the communications may be performed in accordance with any generation of communication protocols currently known or to be developed in the future. Examples of communication protocols include, but are not limited to, first-generation (1G), second-generation (2G), 2.5G, 2.85G, third-generation (3G), fourth-generation (4G), 4.5G, fifth-generation (5G), and sixth-generation (6G) communication protocols. The technologies described herein can be used in the aforementioned wireless networks and technologies, as well as other wireless networks and technologies. Embodiments of this disclosure may be performed in accordance with any generation of communication protocols currently known or to be developed in the future. Examples of communication protocols include, but are not limited to, first-generation (1G), second-generation (2G), 2.5G, 2.75G, third-generation (3G), fourth-generation (4G), 4.5G, fifth-generation (5G) communication protocols, 5.5G, 5G-Advanced networks, or sixth-generation (6G) networks.

[0020] As used herein, the term “circuit” may mean a hardware circuit and / or a combination of a hardware circuit and software. For example, a circuit may be a combination of an analog and / or digital hardware circuit and software / firmware. In yet another example, a circuit may be any part of a hardware processor having a digital signal processor, software and one or more memories, which work together to cause a device such as a terminal or network device to perform various functions. In yet another example, a circuit may be a hardware circuit and / or a processor such as a microprocessor or a part thereof that requires software / firmware for operation, but the software may not be present if it is not required for operation. As used herein, the term “circuit” also includes the implementation of a hardware circuit or one or more processors alone, or a part of a hardware circuit or one or more processors and their (or their) accompanying software and / or firmware.

[0021] As used herein, the singular "one" and "the foregoing" also include the plural unless explicitly indicated in the context. The term "including" and its variations should be understood as open-ended terms meaning "including, but not limited to." The term "based on" should be understood as "at least partially based on." The terms "one embodiment" and "embodiment" should be understood as "at least one embodiment." The term "another embodiment" should be understood as "at least one other embodiment." Terms such as "first," "second," etc., may refer to different or identical subjects. The following may include other explicit and implicit definitions.

[0022] In some examples, values, procedures, or devices are referred to as “best,” “worst,” “highest,” “minimum,” “maximum,” etc. Such descriptions are intended to show that a choice can be made from among many usable functional alternatives, and it should be understood that such a choice does not need to be better, smaller, higher, or otherwise more desirable than other choices.

[0023] As mentioned above, the AI / ML model can be applied to various scenarios to achieve better performance. In some embodiments, the AI / ML model may be implemented on the network device side. Alternatively, the AI / ML model may be implemented on the terminal device side. In other embodiments, the AI / ML model may be implemented on both the network device side and the terminal device side.

[0024] For example, terminal equipment can perform beam management on an AI / ML model. In this case, the terminal equipment can measure a portion of candidate beam pairs and use AI or ML to estimate the quality of all candidate beam pairs. Massive MIMO (mMIMO) and beamforming are widely used in the telecommunications industry. The terms "beamforming" and "mMIMO" may be used interchangeably. Generally speaking, beamforming uses multiple antennas to control the direction of the wavefront by appropriately weighting the amplitude and phase of the individual antenna signals in an array of multiple antennas. The most commonly seen definition is that mMIMO is a system where the number of antennas exceeds the number of users. Coverage in 5G is beam-based, not cell-based. There is no cell-level reference channel from which cell coverage can be measured. Instead, each cell has one or more Synchronization Signal Block (SSB) beams. SSB beams are static or semi-static and always point in the same direction. They form a grid of beams that cover the entire cell area. The user equipment (UE) searches for and measures beams and maintains a set of candidate beams. This set of candidate beams may include beams from multiple cells. Efficient beam management is becoming crucial, enabling the UE and gNB to periodically identify the optimal beam to work with at any given time, by allowing directional communication with more antenna elements in 5G millimeter wave (mmWave) and providing additional beamforming gain.

[0025] Additionally, the terminal device may perform CSI feedback based on an AI / ML model. In this case, the original CSI information may be compressed by an AI encoder located in the terminal device and recovered by an AI decoder located in the network device. The AI / ML model can also be used for reference signal (RS) overhead reduction. For example, the terminal device may use a new RS pattern, such as a lower-density DMRS or fewer CSI-RS ports.

[0026] Many studies use 3GPP® channel models (statistical models) to generate all samples. Samples within training / validation / test datasets are naturally independent and identically distributed. AI / ML models may be trained and deployed solely by the network, without actual measurements. However, in the field, actual channel characteristics and real-world implementations differ from statistical models. Statistical models may not be suitable for real-world environments. Therefore, it is worthwhile to propose new solutions for constructing datasets suitable for AI / ML models.

[0027] To address at least some of the above-mentioned problems and other potential problems, a solution for improving the AI / ML model is proposed. According to embodiments of this disclosure, a terminal device receives measurement settings or transmission settings from a network device. The terminal device performs measurements based on the measurement settings and reports the measurement results to the network device. Alternatively, if the terminal device performs a transmission based on the transmission settings, the network device performs measurements based on the transmission. The network device trains the AI / ML model based on the measurement results. Thus, the actual measurement results are used to build a suitable dataset for the AI / ML model in the network device.

[0028] Figure 1 is a schematic diagram of a communication system that can implement an embodiment of the present disclosure. The communication system 100, which is part of a communication network, comprises terminal device 110-1, terminal device 110-2, ..., terminal device 110-N, which may be collectively referred to as "terminal device 110". The number N may be any suitable integer. The terminal devices 110 may communicate with each other.

[0029] The communication system 100 further includes network equipment. In the communication system 100, the network equipment 120 and the terminal equipment 110 can communicate data and control information with each other. The number of terminal equipment shown in Figure 1 is for illustrative purposes only and does not imply any limitation.

[0030] Communication in the communication system 100 can be implemented in accordance with any suitable communication protocol, including but not limited to, cellular communication protocols such as first-generation (1G), second-generation (2G), third-generation (3G), fourth-generation (4G), and fifth-generation (5G), wireless local area network communication protocols such as IEEE 802.11, and / or any other protocols currently known or to be developed in the future. Furthermore, communication may utilize any suitable wireless communication technology, including but not limited to code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), frequency division duplexer (FDD), time division duplexer (TDD), multi-input multiple-output (MIMO), orthogonal frequency division multiple access (OFDMA), and / or any other technologies currently known or to be developed in the future.

[0031] Embodiments of the present disclosure can be applied to any suitable scenario. For example, embodiments of the present disclosure can be implemented on NR equipment with reduced capabilities. Alternatively, embodiments of the present disclosure can be implemented within one of the following: NR multi-input multi-output (MIMO), NR sidelink enhancement, NR systems with frequencies above 52.6 GHz, extended NR operations up to 71 GHz, narrowband Internet of Things (NB-IOT) / extended machine-type communications (eMTC) on non-terrestrial networks (NTN), NTN, UE power saving enhancement, NR coverage enhancement, NB-IOT and LTE-MTC, integrated access and backhaul (IAB), NR multicast and broadcast services, or multi-radio dual connectivity enhancement.

[0032] As used herein, the term "slot" means a dynamic scheduling unit. A slot contains a predetermined number of symbols. The term "downlink (DL) subslot" may refer to a virtual subslot built upon an uplink (UL) subslot. A DL subslot may contain fewer symbols than a single DL slot. As used herein, a slot may refer to a normal slot containing a predetermined number of symbols and a subslot containing fewer symbols than said predetermined number. As used herein, the terms "beam," "beam pair," and "beam pair link" refer to a communication link and may be expressed by "resource," "resource set," or "resource setting" or "resource configuration." As used herein, the term "beam quality" refers to "RSRP," "SINR," "RSSI," or "RSRQ" measured on the corresponding resource or through the corresponding beam. The terms “precoder,” “precoding,” “precoding matrix,” “beam,” “spatial relationship information,” “spatial domain transmit filter,” “spatial domain filter,” “spatial parameter,” “spatial relationship information,” “spatial relationship info,” “TPMI,” “precoding information,” “precoding information and layer number,” “precoding matrix indicator (PMI),” “precoding matrix indicator,” “transmit precoding matrix support,” “precoding matrix indicator,” “TCI status,” “transmit setting indicator,” “quasi co-location (QCL),” “quasi-co-location,” “QCL ​​parameter,” and “spatial relationship” may be used interchangeably. The terms “SRI,” “SRS resource set index,” “UL TCI,” “UL spatial domain filter,” “UL beam,” and “combined TCI” may be used interchangeably. The terms “candidate,” “predicted,” “target,” and “potential” may be used interchangeably.

[0033] Figure 2A shows a schematic diagram of the AI / ML model. The AI / ML model 200 may be implemented on the network device 120 side. As used herein, the term "AI / ML model" can refer to a program or algorithm that utilizes a set of data that enables the recognition of a specific pattern. This enables reaching a conclusion or making a prediction given sufficient information. Generally speaking, an AI / ML model may also be a mathematical algorithm that is "trained" using data and input from human experts to reproduce the decisions that experts would make given the same information.

[0034] According to embodiments of the present disclosure, the AI / ML model 200 may be used to learn how to generate an output based on inputs for beam management. For example, in this case, the input to the AI / ML model may include at least a subset of beams K1 and optionally their RSRPs, and the output may include at least a recovered set of beams K (K>K1) and their RSRPs, or the best beam and its RSRP. In some embodiments, time-domain measurements are possible. In this case, the input to the AI / ML model may be at time nT, and the output to the AI / ML model may be at time n. Alternatively, according to some embodiments of the present disclosure, the AI / ML model 200 can learn how to find narrow beams based on wide beam information. In this case, the input to the AI / ML model may include at least a set of wide beams K' and optionally their RSRPs, and the output to the AI / ML model may include at least a recovered set of narrow beams K and their RSRPs, or the best Alt2 beam in K and optionally its RSRP. The wide beam may be the beam used for initial access, and the narrow beam may be the beam used for UE-specific data transmission. In some embodiments, different AI / ML models may be used for the selection of different subsets K1.

[0035] As shown in Figure 2A, the AI / ML model 200 may comprise a data acquisition function 210, a model training function 220, a model inference function 230, and an actor function 240. The data acquisition function 210 is a function that provides input data to the model training function 220 and the model inference function 230. Data preparation specific to the AI / ML algorithm (e.g., data preprocessing and cleaning, formatting, and transformation) is not performed in the data acquisition function 210. Examples of input data may include measurements from the UE or different network entities, feedback from the actor function 240, and outputs from the AI / ML model. As used herein, the term "training data" may refer to the data required as input for the model training function 220. As used herein, the term "inference data" may refer to the data required as input for the model inference function 230.

[0036] Model training 220 is a function that performs ML model training, validation, and testing, which may generate model performance metrics as part of the model testing procedure. Model training 220 is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the training data delivered by data collection 210, if necessary. As shown in Figure 2B, there may be three datasets for model training 220: a training dataset, a validation dataset, and a test dataset. Model training 220 may use model deployment / update to initially deploy the trained, validated, and tested AI / ML model to model inference 230, or to deliver the updated model to model inference 230. The classification of different datasets follows common conventions in machine learning. The training dataset may be used to directly improve the model parameters. The validation dataset may be used to evaluate the model's performance while optimizing the model's hyperparameters. The test dataset may be used to evaluate the model after hyperparameter optimization is complete.

[0037] Model inference 230 is a function that provides AI / ML model inference output (e.g., prediction or decision). It may also provide model performance feedback to model training 220. Model inference 230 is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting and transformation) based on the inference data delivered by data collection 210, if necessary.

[0038] Actor 210 is a function that receives the output from model inference 230 and triggers or performs a corresponding action. Actor 210 may also trigger actions on other entities or on itself.

[0039] First, refer to Figure 3. Figure 3 shows a signaling diagram illustrating a process 300 between a terminal device and a network device according to some exemplary embodiments of the present disclosure. For illustrative purposes only, refer to Figure 1 to describe the process 300. The process 300 may involve terminal devices 110-1 and network device 120 in Figure 1. The process 300 may be used to collect field data for AI / ML model training. Collecting field data for AI / ML model training is aperiodic or semi-persistent setup / measurement / reporting and may have a lower priority than data traffic transmission and other normal setup / measurement / reporting. Collecting field data for model training may be performed within a time window / time interval or duty cycle proposed or requested by the terminal device based on its capabilities.

[0040] The network device 120 transmits a first configuration to the terminal device 110-1 (3010). The first configuration indicates at least one resource subset from a first set of resources. In some embodiments, the first set of resources may include resources for beam measurement and reporting. The at least one resource subset is for constructing a first dataset for training the AI / ML model 200 in the network device 120. The first dataset includes one or more of the following: a training dataset for model training, a validation dataset for model training, a test dataset for model training, or a dataset for model inference.

[0041] In some embodiments, the first setting may be a first measurement setting. In this case, the terminal device 110-1 may perform measurements on the at least one resource subset based on the first measurement setting. For example, the first setting may indicate a first candidate data sample for constructing the first dataset. The first candidate data sample may include a resource subset as input to an AI / ML model and a target resource as output to an AI / ML model. The input and / or output of the AI / ML model may also include other parameters not limited to the resource subset and the target resource. Alternatively, the first setting may instruct the terminal device 110-1 to perform measurements on a first set of resources. In some embodiments, the terminal device 110-1 may determine quality based on the measurement results. For example, the terminal device 110-1 may determine the reference signal received power (RSRP) based on the measurement. Alternatively, the terminal device 110-1 may determine the signal-to-interference noise ratio (SINR) based on the measurement.

[0042] In other embodiments, the first setting may be a first transmission setting. In this case, the terminal device may perform a transmission based on the first transmission setting. For example, the first setting may indicate a set of reference signal resources for a sounding reference signal (SRS). Alternatively or additionally, the first setting may indicate a subset of reference signal resources from the set of reference signal resources. In other embodiments, the first setting may indicate a target reference signal resource.

[0043] The terminal device 110-1 transmits information to the network device 120 (3020). In some embodiments, if the first setting is a first measurement setting, the terminal device 110-1 may transmit the measurement results to the network device 120. Alternatively, the first setting may be a first transmission setting, and the terminal device 110-1 may transmit a sounding reference signal to the network 120. In this case, the network device 120 may measure the sounding reference signal.

[0044] Network device 120 trains an AI / ML model (3030). Network device 120 may construct a first dataset based on the measurement results. The AI / ML model may be trained based on the first dataset. Thus, the AI / ML model may be optimized based on the actual measurement results.

[0045] The network device 120 may send instructions for the updated resource subset to the terminal device 110-1 (3040). As shown in Figure 6D, the updated resource subset may be the output from the AI / ML model. In some embodiments, the updated resource subset may be the input for AI / ML model training. Alternatively or additionally, the updated resource subset may be used to collect data for AI / ML model training. In other embodiments, the updated resource subset may be used to collect data for AI / ML model inference. In some other embodiments, the updated resource subset may be used for normal beam measurement and reporting. This avoids randomly selected measurement subsets and can provide better predictive performance.

[0046] In some embodiments, explicit signaling may be required to notify the terminal device 110-1 of the updated measurement subset K1'. For example, the input for AI / ML model training may be updated based on the updated resource subset. In other embodiments, the updated resource subset may be transmitted within a first measurement setting, meaning that the settings for collecting data for AI / ML model training can be updated. In this case, the RRC IE "RS-subset-to-measure-for-training" and "RS-to-compare-for-training" may be used to notify of the updated resource subset. Alternatively, the updated resource subset may be transmitted within a second measurement setting, meaning that the settings for collecting data for AI / ML model inference can be updated. In this case, the new signaling "RS-subset-measure-for-inference" may be used to notify of the updated resource subset. As described above, different AI / ML models may be used to select different subsets K1. In other words, multiple AI / ML models (model i) can learn how to generate K from different versions of K1_i. In this case, instead of using K1' as the output, the AI / ML model ID i may be used as the output if one version of the K1 selections corresponds to one AI / ML model.

[0047] In some embodiments, the input from terminal device 110-1 for the first AI / ML mode may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, position information, trajectory, velocity, orientation, direction of movement, transmit power, Tx / Rx beam measurement subset, transmission method, wide beam used in initial access. The input from network device 120 for the AI / ML model may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, position information, transmit power, handover, Tx / Rx beam measurement subset, scheduling information, beam switching decision, multi-user scheduling decision, traffic status, transmission method, wide beam used in initial access. The input from other terminal devices for the AI / ML model may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, position information, trajectory, velocity, orientation, direction of movement, transmit power, Tx / Rx beam measurement subset, transmission method, wide beam used in initial access. Inputs from other network devices 120 for the AI / ML model may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, location information, transmit power, handover, measured subset of Tx / Rx beams, scheduling information, beam switching decision, multi-user scheduling decision, traffic status, transmission method, and wide beam used in initial access. Inputs from other AI / ML models for the AI / ML model may include one or more of the following: prediction of UE location, prediction of UE trajectory, prediction of handover, prediction of initial access, and prediction of channel state information (CSI).

[0048] In some embodiments, the output from the AI / ML model for terminal device 110-1 may include one or more of the following: transmit power, beam switching decision, active subset of Tx / Rx beams, and transmission method. The output from the AI / ML model for network device 120 may include one or more of the following: transmit power, handover, active subset of Tx / Rx beams, scheduling, beam switching decision, multi-user scheduling decision, traffic status, and transmission method. The output from the AI / ML model may be used as input to other AI / ML models for UE position / trajectory prediction, handover / load balancing / energy saving decision prediction, and CSI prediction.

[0049] In some embodiments, when AI / ML model inference is applied, an additional parameter relating to the number of reduced UE Rx beams may be used to determine the number of configured RS resources in the RS resource set, measurement period requirements, and measurement accuracy requirements. In some embodiments, this parameter may be indicated by network device 120. Alternatively, this parameter may be reported by terminal device 110-1. Alternatively, this parameter may be reported by terminal device 110-1 in a capability report. In other embodiments, this parameter may also be an output from the AI / ML model. Thus, it is possible to guide the settings and set performance requirements when AI / ML model inference is applied. Tables 1-3 show an updated description based on the number of received beam reductions. [Table 1] [Table 2] [Table 3]

[0050] In some other embodiments, the number of occupied CSI processing units (CPUs) and the CSI computation time may depend on the number of resources actually measured for beam quality within the first set of resources. For example, the number of occupied CPUs may be NCPU (i.e., UE capability on the maximum number of concurrently supported CSI computations) or K1+1 (i.e., the number of resources actually measured in the resource set, including the target resource). Alternatively or additionally, for a time span from the CSI reference to the last symbol carrying the RS in K1, the number of occupied CPUs may be NCPU or K1 (i.e., the number of resources actually measured in the resource set). The number of occupied CPUs is

number

[0051] An exemplary embodiment of the dataset construction method of this disclosure will be described with reference to Figures 4A to 5C.

[0052] Figure 4A is a signaling chart showing the process between terminal device 110-1 and network device 120 according to some exemplary embodiments of the present disclosure, where the first setting is a measurement setting.

[0053] The network device 120 may transmit a first measurement setting to the terminal device 110-1 (4010). The first measurement setting may indicate resources for measurement. In some embodiments, the first measurement setting may indicate an index of resources for measurement. In this case, for example, the first measurement setting may include a synchronization signal / physical broadcast channel block index. Alternatively, the first measurement setting may include a channel state information (CSI) reference signal (RS) resource index. The first measurement setting may indicate to the terminal device 110-1 to perform measurements on all resources. In other words, the network device 120 can obtain information on a complete set of beam pairs and beam quality.

[0054] In some embodiments, the first measurement configuration may include a ReportConfigForModelTraining configuration. Additionally, the first measurement configuration may include a ResourceConfigForModelTraining configuration.

[0055] Terminal device 110-1 may perform a first measurement based on a first measurement setting (4020). Terminal device 110-1 may perform a first measurement on the resource. Terminal device 110-1 may determine the quality on the resource based on the results of the first measurement. For example, terminal device 110-1 may determine the RSRP on the resource. Alternatively, terminal device 110-1 may determine the SINR on the resource.

[0056] Terminal device 110-1 may transmit a first measurement report to network device 120 (4030). The first measurement report may include resource indices and their quality. For example, the first measurement report may include K beam pairs and their quality, e.g., K SSBRI / CRI + K L1-RSRP. The number of resources in the first measurement report may be based on the number of beams in network device 120 and the number of beams in terminal device 110-1. Figure 6A shows one data sample reported by terminal device 110-1 based on the first measurement results. As shown in Figure 6A, the first measurement report includes a complete set of beam pairs and their RSRPs. The number of rows in Figure 6A corresponds to the number of UE received beams. The number of columns in Figure 6A corresponds to the number of network transmitted beams. Each element in Figure 6A corresponds to one resource. As shown in Figure 7A, the measurement results in the first measurement report (i.e., the reported quality of the resources) may be part of a sample in the test dataset. Similarly, the measurement results may also be part of a sample within the training or validation dataset.

[0057] In some embodiments, terminal device 110-1 may not report resource indices. In this case, the RSRP of the resources may be sorted in ascending / descending order of resource indices in the first measurement report. Alternatively or additionally, terminal device 110-1 may not report resources with inferior quality. For example, if one resource has an RSRP lower than a threshold RSRP, terminal device 110-1 may not report the index of such resource in the first measurement report. In other embodiments, terminal device 110-1 may not report received beam information. For example, terminal device 110-1 may report only information about the transmitted beam, assuming that each transmitted beam is measured through its optimal UE received beam. In some embodiments, the AI / ML model is limited to each wide beam pair identified in the initial access phase. In some other embodiments, network device 120 may transmit the reference quality of the resources to terminal device 110-1. In this case, terminal device 110-1 may transmit a first measurement report including the differential quality of a first set of resources relative to the reference quality. For example, network device 120 may send a map of (RS ID + RSRP) to terminal device 110-1. In this case, terminal device 110-1 may provide feedback of a differential map for the NW version. More specifically, network device 120 may send (RSRP1, RSRP2, ..., RSRP K ) may be transmitted, and terminal device 110-1 measures RS and calculates the difference from ID 1 to K,

number

[0058] The network device 120 may train an AI / ML model based on the measurement results (4040). In some embodiments, the output of the AI / ML model may recover all resources and all RSRPs. Alternatively, the output of the AI / ML model may be the best resource / beam and the RSRP of the best resource. Referring to Figure 6B, the input of the AI / ML model may be a resource subset K1 and its corresponding RSRP, and the output of the AI / ML model may recover all resources / beams and their RSRPs. Alternatively, referring to Figure 6C, the input of the AI / ML model may be a resource subset K1 and its corresponding RSRP, and the output of the AI / ML model may be the best beam in set K that maximizes the RSRP.

number

[0059] In some embodiments, the network device 120 may transmit a second measurement setting to the terminal device 110-1 (4050). The second measurement setting may indicate a resource for the second measurement. In some embodiments, the second measurement setting may indicate an index of the resource for the second measurement. In this case, for example, the second measurement setting may include an SSB index. Alternatively, the second measurement setting may include a CSI-RS resource index.

[0060] Terminal device 110-1 may perform a second measurement based on the second measurement settings (4060). Terminal device 110-1 may perform a second measurement on the resource. Terminal device 110-1 may determine the quality on the resource based on the results of the second measurement. For example, terminal device 110-1 may determine the RSRP on the resource. Alternatively, terminal device 110-1 may determine the SINR on the resource.

[0061] Terminal device 110-1 may transmit a second measurement report to network device 120 (4070). The second measurement report may include resource indices and their quality. The second measurement report may be used as inference data for real-time UE beam management.

[0062] The network device 120 may perform inference using an AI / ML model based on the second measurement report (4080). In other words, the network device 120 may perform model inference according to the AI / ML model. For example, the AI / ML model may output predictions including, for example, a complete set of beam pairs and beam quality, the best beam for subsequent transmission, and an updated subset for the second measurement.

[0063] Figure 4B is a signaling chart showing the process between terminal device 110-1 and network device 120 according to some exemplary embodiments of the present disclosure, in which the first setting is a transmit setting.

[0064] The network device 120 may transmit a first transmission setting to the terminal device 110-1 (4011). The first transmission setting may indicate resources for transmitting a sounding reference signal. In some embodiments, the first transmission setting may indicate an index of resources for transmitting a sounding reference signal. The first transmission setting may indicate to the terminal device 110-1 to perform a transmission on all resources. In some embodiments, the first transmission setting may include an information element "SRS resource set usage" indicating that the resources are used to train an AI / ML model.

[0065] The terminal device 110-1 may perform a first measurement based on the first transmission setting (4021). The terminal device 110-1 may transmit a sounding reference signal on the resource based on the first transmission setting. In this way, no extra burden is placed on the terminal device 110-1.

[0066] The network device 120 may perform a first measurement based on the sounding reference signal (4031). The network device 120 may determine the quality on the received sounding reference signal. For example, the network device 120 may determine the RSRP of the received sounding reference signal. Alternatively, the network device 120 may determine the SINR of the received sounding reference signal. As shown in Figure 7A, the measurement results in the first measurement report (i.e., the measured quality of the resource) may be part of a sample in the test dataset. Similarly, the measurement results may also be part of a sample in the training dataset or validation dataset.

[0067] The network device 120 may train an AI / ML model based on the results of the first measurement (4041). In some embodiments, the output of the AI / ML model may recover all resources and all RSRPs. Alternatively, the output of the AI / ML model may be the best resource / beam and the RSRP of the best resource. Thus, the AI / ML model may be optimized based on the actual measurement results.

[0068] In some embodiments, the network device 120 may transmit a second measurement setting to the terminal device 110-1 (4051). The second measurement setting may indicate a resource for the second measurement. In some embodiments, the second measurement setting may indicate an index of the resource for the second measurement. In this case, for example, the second measurement setting may include an SSB index. Alternatively, the second measurement setting may include a CSI-RS resource index.

[0069] Terminal device 110-1 may perform a second measurement based on the second measurement settings (4061). Terminal device 110-1 may perform a second measurement on the resource. Terminal device 110-1 may determine the quality on the resource based on the results of the second measurement. For example, terminal device 110-1 may determine the RSRP on the resource. Alternatively, terminal device 110-1 may determine the SINR on the resource.

[0070] Terminal device 110-1 may transmit a second measurement report to network device 120 (4071). The second measurement report may include resource indices and their quality. The second measurement report may be used as inference data for real-time UE beam management.

[0071] The network device 120 may perform inference using an AI / ML model based on the second measurement report (4081). In other words, the network device 120 may perform model inference according to the AI / ML model. For example, the AI / ML model may output predictions including, for example, a complete pair of beams and beam quality, the best beam for subsequent transmission, and a subset for the second measurement.

[0072] Figure 4C is a signaling chart showing the process between terminal device 110-1 and network device 120 according to some exemplary embodiments of the present disclosure, in which the first setting is a transmit setting.

[0073] The network device 120 may transmit a first transmission setting to the terminal device 110-1 (4012). The first transmission setting may indicate resources for transmitting a sounding reference signal. In some embodiments, the first transmission setting may indicate an index of resources for transmitting a sounding reference signal. The first transmission setting may indicate to the terminal device 110-1 to perform a transmission on all resources. In some embodiments, the first transmission setting may include an information element "SRS resource set usage" indicating that the resources are used to train an AI / ML model.

[0074] The terminal device 110-1 may perform a first measurement based on the first transmission setting (4022). The terminal device 110-1 may transmit a sounding reference signal on the resource based on the first transmission setting. In this way, no additional burden is placed on the terminal device 110-1.

[0075] The network device 120 may perform a first measurement based on the sounding reference signal (4032). The network device 120 may determine the quality on the received sounding reference signal. For example, the network device 120 may determine the RSRP of the received sounding reference signal. Alternatively, the network device 120 may determine the SINR of the received sounding reference signal. As shown in Figure 7A, the measurement results in the first measurement report (i.e., the measured quality of the resource) may be part of a sample in the test dataset. Similarly, the measurement results may also be part of a sample in the training dataset or validation dataset.

[0076] The network device 120 may train an AI / ML model based on the results of the first measurement (4042). In some embodiments, the output of the AI / ML model may recover all resources and all RSRPs. Alternatively, the output of the AI / ML model may be the best resource / beam and the RSRP of the best resource. Thus, the AI / ML model may be optimized based on the actual measurement results.

[0077] The network device 120 may transmit a second transmission setting to the terminal device 110-1 (4052). The second transmission setting may indicate a resource for transmitting a sounding reference signal. In some embodiments, the second transmission setting may indicate an index of the resource for transmitting a sounding reference signal. In some embodiments, the second transmission setting may include an information element "SRS resource set usage" indicating that the resource is used to infer an AI / ML model.

[0078] The terminal device 110-1 may perform a second measurement based on a second transmission setting (4062). The terminal device 110-1 may transmit a sounding reference signal on the resource based on the second transmission setting.

[0079] The network device 120 may perform a second measurement based on the sounding reference signal (4072). The network device 120 may determine the quality on the received sounding reference signal. For example, the network device 120 may determine the RSRP of the received sounding reference signal. Alternatively, the network device 120 may determine the SINR of the received sounding reference signal.

[0080] The network device 120 may perform inference using an AI / ML model based on the results of the second measurement (4082). In other words, the network device 120 may perform model inference according to the AI / ML model. For example, the AI / ML model may output predictions including, for example, a complete set of beam pairs and beam quality, the best beam for subsequent transmission, and a subset for the second measurement.

[0081] According to some embodiments, the terminal device 110-1 may be used as a classifier to identify training data samples generated by the network device 120. The terminal device 110-1 may transmit the identification results to the network device 120. Embodiments will be described with reference to Figures 5A to 5C in which the terminal device 110-1 functions as a classifier.

[0082] Figure 5A is a signaling chart showing the process between terminal device 110-1 and network device 120 according to some exemplary embodiments of the present disclosure, in which the first setting is a measurement setting.

[0083] The network device 120 may transmit the first measurement settings to the terminal device 110-1 (5010). The first measurement settings may indicate a subset of resources for measurement.

[0084] The network device 120 may notify the terminal device 110-1 of first candidate data samples for constructing the first dataset (5020). In some embodiments, the first candidate data samples may include a subset of resources as input to the AI / ML model and a target resource as output to the AI / ML model. As shown in Figure 7B, potential data samples for training the AI / ML model may be sent to and measured by the terminal device 110-1.

[0085] The first candidate data sample may be indicated to the terminal device 110-1 via appropriate signaling. For example, the first candidate data sample may be indicated via radio resource control (RRC) signaling. Alternatively, the first candidate data sample may be indicated within a medium access control (MAC) control element (CE). In some embodiments, the first candidate data sample may be indicated within downlink control information (DCI). In some embodiments, the first measurement setup may include the first candidate data sample for constructing the first dataset.

[0086] In some embodiments, the RRC IEs “RS-subset-to-measure-for-training” and “RS-to-compare-for-training” may be used to indicate a first candidate data sample. The size of RS-subset-to-measure-for-training may depend on the number of beams on the NW side and the number of beams on the UE side. Additionally, the time offset is between the last symbol carrying the RS in the subset K1 of resource / beams and the target resource / beam.

number

number

[0087] Additionally, the first measurement setting may include a reporting setting for terminal device 110-1. Based on the reporting setting, terminal device 110-1 may decide which reporting quantities to report to network device 120. In some embodiments, the first reporting quantity may indicate whether a first candidate data sample is suitable for constructing a first dataset for an AI / ML model. Alternatively, the first reporting quantity may indicate the result of a comparison between the quality of a resource subset and the quality of a target resource.

[0088] Terminal device 110-1 may perform a first measurement based on a first measurement setting (5030). For example, terminal device 110-1 may perform a first measurement on a resource subset. Terminal device 110-1 may determine the quality of the resource subset based on the first measurement on the resource subset. For example, terminal device 110-1 may determine the RSRP on the resource subset. Alternatively, terminal device 110-1 may determine the SINR on one of the resource subsets.

[0089] Terminal device 110-1 may also perform a first measurement on the target resource. Based on the first measurement on the target resource, terminal device 110-1 may determine the quality of the target resource. For example, terminal device 110-1 may determine the RSRP on the target resource. Alternatively, terminal device 110-1 may determine the SINR on the target resource.

[0090] Terminal device 110-1 may transmit a first measurement report to network device 120 (5040). The first measurement report may include a first report quantity. In some embodiments, the first report quantity may indicate an identification result indicating whether the first candidate data sample is suitable for constructing a first dataset for an AI / ML model. In some embodiments, the first report quantity may indicate whether the first candidate data sample is suitable for constructing a first dataset for an AI / ML model. Alternatively, the first report quantity may indicate the result of a comparison between the quality of a resource subset and the quality of a target resource. For example, terminal device 110-1 may compare the quality of a resource subset with the quality of a target resource. In this case, if the quality of at least one of the resource subsets is better than the quality of the target resource, the first report quantity may indicate that the first candidate data sample is not suitable for constructing a first dataset for an AI / ML model. For example, if at least one RSRP of K1 RSs is

number

number

number

number

[0091] In some embodiments, the first measurement report may include 1 bit for one candidate data sample, or N bits for N candidate data samples. Alternatively, the first measurement report may include 1 bit for N candidate data samples. The bit width for the resource index may be ceil(log2(K1+1)), ceil(log2(K1)), or 0, where K1 represents the number of resources in the resource subset.

[0092] In some embodiments, the first reporting quantity may include a resource index and a resource quality. For example, the first reporting quantity may include a first index of a target resource and a target resource quality. Alternatively or additionally, the first reporting quantity may include a resource subset index and a resource subset quality. In other embodiments, the first reporting quantity may include a first index of a target resource having the target resource quality and an index of a resource subset having the resource subset quality. As an example only, the first reporting quantity may include the SSBRI / CRI of the target resource and the RSRP / SINR of the target resource. Alternatively or additionally, the first reporting quantity may also include the SSBRI / CRI of a resource subset and the RSRP / SINR of a resource subset. In this way, overhead can be reduced.

[0093] Alternatively, the first reported quantity may include a second index of the best resource determined by the terminal device 110-1. For example, the first reported quantity may include the SSBRI / CRI of the best resource. In this case, the terminal device 110-1 may recommend the best resource or the best beam. In some embodiments, the first reported quantity may include an index of a subset of measurement resources determined by the terminal device 110-1. For example, the first reported quantity may include the SSBRI / CRI of a subset of measurement resources. In this case, the terminal device 110-1 may recommend the measured resource or beam. In other embodiments, the first reported quantity may include a second index of the best resource and an index of a subset of measurement resources determined by the terminal device 110-1.

[0094] In some embodiments, the first reported quantity may be the quality of the resources. For example, the first reported quantity may include the quality of the best resource / beam. As an example only, the first reported quantity may include the RSRP or SINR of the best resource / beam. Alternatively, the first reported quantity may be the quality of a subset of the measured resources / beams. In this case, the quality of the subset of measured resources / beams may be sorted in ascending / descending order of the resource index. This makes it possible to reduce the overhead of the first report.

[0095] The network device 120 may train an AI / ML model based on the first measurement report (5050). In some embodiments, if the first measurement report indicates that the first candidate data sample is not suitable for building a dataset, the network device 120 may not use the first candidate data sample to train the AI / ML model. Alternatively, if the first measurement report indicates that the first candidate data sample is suitable for building a dataset, the network device 120 may use the first candidate data sample to train the AI / ML model. As shown in Figure 7B, the network device 120 may build a test dataset based on the identification results in the first measurement report.

[0096] Figure 5B is a signaling chart showing the process between terminal device 110-1 and network device 120 according to some exemplary embodiments of the present disclosure, in which the first setting is a transmit setting.

[0097] The network device 120 may transmit a first measurement setting to the terminal device 110-1 (5011). The first measurement setting may indicate a subset of resources for measurement. The first measurement setting may include two related reporting settings. For example, the first measurement setting may include a first reporting setting for resources in K1,

number

[0098] The network device 120 may notify the terminal device 110-1 of first candidate data samples for constructing the first dataset (5021). In some embodiments, the first candidate data samples may include a subset of resources as input to an AI / ML model. As shown in Figure 7B, potential data samples for training an AI / ML model may be sent to and measured by the terminal device 110-1. The network device 120 may transmit a reference signal over the resource subset.

[0099] The first candidate data sample may be indicated to the terminal device 110-1 via appropriate signaling. For example, the first candidate data sample may be indicated via radio resource control (RRC) signaling. Alternatively, the first candidate data sample may be indicated within a medium access control (MAC) control element (CE). In some embodiments, the first candidate data sample may be indicated within downlink control information (DCI). In some embodiments, the first measurement setup may include the first candidate data sample for constructing the first dataset.

[0100] In some embodiments, the RRC IE "RS-subset-to-measure-for-training" may be used to indicate a first candidate data sample. The size of RS-subset-to-measure-for-training may depend on the number of beams on the NW side and the number of beams on the UE side. An additional IE to indicate the resource subset K1 to be measured may be a bit string (01..01), where 1 means to measure and 0 means not to measure, and the length of the bit string is equal to the number of resources in the resource set. Additionally, a time offset is used between the last symbol carrying the RS in the resource / beam subset K1 and the target resource / beam

number

[0101] Terminal device 110-1 may perform a first measurement based on a first measurement setting (5031). For example, terminal device 110-1 may perform a first measurement on a resource subset. Terminal device 110-1 may determine the quality of the resource subset based on the first measurement on the resource subset. For example, terminal device 110-1 may determine the RSRP on the resource subset. Alternatively, terminal device 110-1 may determine the SINR on the resource subset.

[0102] The terminal device 110-1 may transmit the first measurement report to the network device 120 (5041). In some embodiments, the first report quantity may be the quality of the resources. For example, the first report quantity may be the quality of a subset of measurement resources / beams. In this case, the quality of the subset of measurement resources / beams may be sorted in ascending / descending order of the resource index. This makes it possible to reduce the overhead of the first report.

[0103] In some embodiments, the first reporting quantity may include the resource index and the resource quality. For example, the first reporting quantity may include the resource subset index and the resource subset quality. For example, the first reporting quantity may also include the resource subset's SSBRI / CRI and the resource subset's RSRP / SINR. In this way, the network device determines whether the target resource has the best quality.

[0104] The network device 120 may notify the terminal device 110-1 of the target resource (5051). The network device 120 may transmit a reference signal on the target resource. The target resource may be indicated to the terminal device 110-1 via appropriate signaling. For example, the target resource may be indicated via radio resource control (RRC) signaling. Alternatively, the target resource may be indicated within a medium access control (MAC) control element (CE). In some embodiments, the target resource may be indicated within downlink control information (DCI).

[0105] In some embodiments, the RRC IE "RS-to-compare-for-training" may be used to indicate a first candidate data sample. Alternatively or additionally, the predicted best beam / resource

number

[0106] In some embodiments, the first measurement report may include 1 bit for one candidate data sample, or N bits for N candidate data samples. Alternatively, the first measurement report may include 1 bit for N candidate data samples. The bit width for the resource index may be ceil(log2(K1+1)), ceil(log2(K1)), or 0, where K1 represents the number of resources in the resource subset.

[0107] Terminal device 110-1 may perform a second measurement on the target resource (5061). For example, terminal device 110-1 may determine the RSRP on the target resource. Alternatively, terminal device 110-1 may determine the SINR on the target resource.

[0108] Terminal device 110-1 may transmit a second measurement report to network device 120 (5071). The second measurement report may include the quality of the target resource. For example, the second measurement report may include the RSRP of the target resource.

[0109] Alternatively or in addition, a second measurement report may include the first reported quantity. In some embodiments, the first reported quantity may indicate whether the first candidate data sample is suitable for constructing a first dataset for an AI / ML model. For example, terminal device 110-1 may compare the quality of a resource subset with the quality of a target resource. In this case, if at least one quality of the resource subset is better than the quality of the target resource, the first reported quantity may indicate that the first candidate data sample is not suitable for constructing a first dataset for an AI / ML model. Alternatively, if the quality of the target resource is better than all the qualities of the resource subset, the first reported quantity may indicate that the first candidate data sample is suitable for constructing a first dataset for an AI / ML model. In some embodiments, a comparison offset may be applied. For example, an RSRP offset may be added to the left or right side of the inequality: K1 RS all RSRP <RSRP

number

number

[0110] The network device 120 may train an AI / ML model based on the second measurement report (5081). In some embodiments, if the second measurement report indicates that the first candidate data sample is not suitable for building a dataset, the network device 120 may not use the first candidate data sample to train the AI / ML model. Alternatively, if the second measurement report indicates that the first candidate data sample is suitable for building a dataset, the network device 120 may use the first candidate data sample to train the AI / ML model. As shown in Figure 7B, the network device 120 may build a test dataset based on the identification results in the first measurement report.

[0111] Figure 5C is a signaling chart showing the process between terminal device 110-1 and network device 120 according to some exemplary embodiments of the present disclosure, in which the first setting is a transmit setting.

[0112] The network device 120 may transmit a first transmission setting to the terminal device 110-1 (5012). The first transmission setting may indicate a subset of resources for transmitting a sounding reference signal. In some embodiments, the first transmission setting may indicate an index of the subset of resources for transmitting a sounding reference signal. Alternatively, the first transmission setting may indicate an index of the target resource.

[0113] Resource subsets may be indicated to terminal device 110-1 via appropriate signaling. For example, resource subsets may be indicated via radio resource control (RRC) signaling. For example, RRC IEs “RS-subset-to-transmit-for-training” and “RS-to-compare-for-training” may be added to the RRC signaling. Alternatively, resource subsets may be indicated within a medium access control (MAC) control element (CE). In some embodiments, resource subsets may be indicated within downlink control information (DCI). Additionally, a time offset may be used between the last symbol carrying the RS in the resource / beam subset K1 and the target resource / beam.

number

[0114] The terminal device 110-1 may perform a first measurement based on a first transmission setting (5022). The terminal device 110-1 may transmit a sounding reference signal on the resource subset based on the first transmission setting. In some embodiments, the terminal device 110-1 may also transmit a sounding reference signal on the target resource. In this way, no additional burden is placed on the terminal device 110-1.

[0115] In some other embodiments, the network device 120 may transmit a second transmission setting to the terminal device 110-1. The second transmission setting may indicate an index of the target resource.

[0116] The network device 120 may perform a first measurement based on the sounding reference signal (5032). The network device 120 may determine the quality of the sounding reference signal received on the resource subset. For example, the network device 120 may determine the RSRP of the received sounding reference signal. Alternatively, the network device 120 may determine the SINR of the received sounding reference signal. In some embodiments, the network device 120 may determine the quality of the sounding reference signal received on the target resource.

[0117] The network device 120 may train an AI / ML model based on the measurement results (5042). In some embodiments, if the measurement results indicate that the quality on the target resource is better than the quality on the resource subset, the network device 120 may use a first candidate data sample containing the resource subset as input to the AI / ML model and the target resource as input to the AI / ML model in order to train the AI / ML model. Alternatively, if the measurement results indicate that at least one resource in the resource subset has better quality than the target resource, the network device 120 may not use the first candidate data sample to train the AI / ML model.

[0118] The embodiments described above may be implemented separately. Alternatively, the embodiments described above may be implemented in any suitable combination.

[0119] Figure 8 is a flowchart of an exemplary method 700 according to an embodiment of the present disclosure. Method 700 can be implemented in any suitable apparatus. For illustrative purposes only, Method 700 can be implemented in a terminal device 110-1 as shown in Figure 1.

[0120] In block 710, terminal device 110-1 receives a first configuration from network device 120. The first configuration indicates at least one resource subset from a first set of resources. In some embodiments, the first set of resources may include resources for beam measurement and reporting. The at least one resource subset is for constructing a first dataset for training the AI / ML model 200 at network device 120. The first dataset includes one or more of the following: a training dataset for model training, a validation dataset for model training, a test dataset for model training, or a dataset for model inference.

[0121] In some embodiments, the first setting may be a first measurement setting. In this case, the terminal device 110-1 may perform measurements on the at least one resource subset based on the first measurement setting. For example, the first setting may indicate a first candidate data sample for constructing the first dataset. The first candidate data sample may include a resource subset as input to an AI / ML model and a target resource as output to an AI / ML model. Alternatively, the first setting may instruct the terminal device 110-1 to perform measurements on a first set of resources. In some embodiments, the terminal device 110-1 may determine quality based on the measurement results. For example, the terminal device 110-1 may determine the reference signal received power (RSRP) based on the measurement. Alternatively, the terminal device 110-1 may determine the signal-to-interference noise ratio (SINR) based on the measurement.

[0122] In other embodiments, the first setting may be a first transmission setting. In this case, the terminal device may perform a transmission based on the first transmission setting. For example, the first setting may indicate a set of reference signal resources for a sounding reference signal (SRS). Alternatively or additionally, the first setting may indicate a subset of reference signal resources from the set of reference signal resources. In some embodiments, the first setting may indicate a target reference signal resource.

[0123] In block 720, terminal device 110-1 transmits information to network 120. In some embodiments, if the first setting is the first measurement setting, terminal device 110-1 may transmit the measurement result to network device 120. Alternatively, if the first setting is the first transmission setting, terminal device 110-1 may transmit a sounding reference signal to network device 120. In this case, network device 120 may measure the sounding reference signal.

[0124] In some embodiments, terminal device 110-1 may receive instructions for an updated resource subset from network device 120. In some embodiments, the updated resource subset may be input for AI / ML model training. Alternatively or additionally, the updated resource subset may be used to collect data for AI / ML model training. In other embodiments, the updated resource subset may be used to collect data for AI / ML model inference. In some other embodiments, the updated resource subset may be used for normal beam measurements and reporting. This avoids randomly selected measurement subsets.

[0125] In some embodiments, explicit signaling may be required to notify the terminal device 110-1 of the updated measurement subset K1. For example, the input for AI / ML model training may be updated based on the updated resource subset. In other embodiments, the updated resource subset may be transmitted within a first measurement setting, meaning that the settings for collecting data for AI / ML model training can be updated. In this case, the RRC IE "RS-subset-to-measure-for-training" and "RS-to-compare-for-training" may be used to notify of the updated resource subset. Alternatively, the updated resource subset may be transmitted within a second measurement setting, meaning that the settings for collecting data for AI / ML model inference can be updated. In this case, the new signaling "RS-subset-measure-for-inference" may be used to notify of the updated resource subset. As described above, different AI / ML models may be used to select different subsets K1. In other words, multiple AI / ML models (model i) can learn how to generate K from different versions of K1_i. In this case, instead of using K1' as the output, the AI / ML model ID i may be used as the output if one version of the K1 selections corresponds to one AI / ML model.

[0126] In some embodiments, the input from terminal device 110-1 for the first AI / ML mode may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, position information, trajectory, velocity, orientation, direction of movement, transmit power, Tx / Rx beam measurement subset, transmission method, wide beam used in initial access. The input from network device 120 for the AI / ML model may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, position information, transmit power, handover, Tx / Rx beam measurement subset, scheduling information, beam switching decision, multi-user scheduling decision, traffic status, transmission method, wide beam used in initial access. The input from other terminal devices for the AI / ML model may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, position information, trajectory, velocity, orientation, direction of movement, transmit power, Tx / Rx beam measurement subset, transmission method, wide beam used in initial access. Inputs from other network devices for the AI / ML model may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, location information, transmit power, handover, measured subset of Tx / Rx beams, scheduling information, beam switching decisions, multi-user scheduling decisions, traffic status, transmission method, and wide beam used in initial access. Inputs from other AI / ML models for the AI / ML model may include one or more of the following: prediction of UE location, prediction of UE trajectory, prediction of handover, prediction of initial access, and prediction of channel state information (CSI).

[0127] In some embodiments, the output from the AI / ML model for terminal device 110-1 may include one or more of the following: transmit power, beam switching decision, active subset of Tx / Rx beams, and transmission method. The output from the AI / ML model for network device 120 may include one or more of the following: transmit power, handover, active subset of Tx / Rx beams, scheduling, beam switching decision, multi-user scheduling decision, traffic status, and transmission method. The output from the AI / ML model may be used as input to other AI / ML models for UE position / trajectory prediction, handover / load balancing / energy saving decision prediction, and CSI prediction.

[0128] In some embodiments, when AI / ML model inference is applied, an additional parameter relating to the number of reduced UE Rx beams may be used to determine the number of configured RS resources in the RS resource set, measurement period requirements, and measurement accuracy requirements. In some embodiments, this parameter may be indicated by network device 120. Alternatively, this parameter may be reported by terminal device 110-1. Alternatively, this parameter may be reported by terminal device 110-1 in a capability report. In other embodiments, this parameter may also be an output of the AI / ML model. Thus, it is possible to guide the settings and set performance requirements when AI / ML model inference is applied.

[0129] In some embodiments, the number of occupied CSI processing units (CPUs) and the CSI computation time may depend on the number of resources actually measured for beam quality within the first set of resources. For example, the number of occupied CPUs may be NCPU (i.e., UE capability on the maximum number of concurrently supported CSI computations) or K1+1 (i.e., the number of resources actually measured in the resource set, including the target resource). Alternatively or additionally, for a time span from the CSI reference to the last symbol carrying the RS in K1, the number of occupied CPUs may be NCPU or K1 (i.e., the number of resources actually measured in the resource set). The number of occupied CPUs is

number

[0130] Figure 9 is a flowchart of an exemplary method 800 according to an embodiment of the present disclosure. Method 800 can be implemented in any suitable device. For illustrative purposes only, Method 800 can be implemented in a network device 120 as shown in Figure 1.

[0131] In block 810, the network device 120 transmits a first configuration to the terminal device 110-1. The first configuration indicates at least one resource subset from a first set of resources. In some embodiments, the first set of resources may include resources for beam measurement and reporting. The at least one resource subset is for constructing a first dataset for training the AI / ML model 200 in the network device 120. The first dataset includes one or more of the following: a training dataset for model training, a validation dataset for model training, a test dataset for model training, or a dataset for model inference.

[0132] In some embodiments, the first setting may be a first measurement setting. In this case, the terminal device 110-1 may perform measurements on the at least one resource subset based on the first measurement setting. For example, the first setting may indicate a first candidate data sample for constructing the first dataset. The first candidate data sample may include a resource subset as input to an AI / ML model and a target resource as output to an AI / ML model. Alternatively, the first setting may instruct the terminal device 110-1 to perform measurements on a first set of resources. In some embodiments, the terminal device 110-1 may determine quality based on the measurement results. For example, the terminal device 110-1 may determine the reference signal received power (RSRP) based on the measurement. Alternatively, the terminal device 110-1 may determine the signal-to-interference noise ratio (SINR) based on the measurement.

[0133] In other embodiments, the first setting may be a first transmission setting. In this case, the terminal device may perform a transmission based on the first transmission setting. For example, the first setting may indicate a set of reference signal resources for a sounding reference signal (SRS). Alternatively or additionally, the first setting may indicate a subset of reference signal resources from the set of reference signal resources. In some embodiments, the first setting may indicate a target reference signal resource.

[0134] In block 830, the network device 120 receives information from the terminal device 110-1. In some embodiments, if the first setting is the first measurement setting, the terminal device 110-1 may transmit the measurement results to the network device 120. Alternatively, if the first setting is the first transmission setting, the terminal device 110-1 may transmit a sounding reference signal to the network device 120. In this case, the network device 120 may measure the sounding reference signal.

[0135] In some embodiments, the network device 120 may train an AI / ML model. The network device 120 may construct a first dataset based on the measurement results. The AI / ML model may be trained based on the first dataset. Thus, the AI / ML model may be optimized based on the actual measurement results.

[0136] The network device 120 may transmit instructions for the updated resource subset to the terminal device 110-1. In some embodiments, the updated resource subset may be input for AI / ML model training. Alternatively or additionally, the updated resource subset may be used to collect data for AI / ML model training. In other embodiments, the updated resource subset may be used to collect data for AI / ML model inference. In some other embodiments, the updated resource subset may be used for normal beam measurements and reporting. This avoids randomly selected measurement subsets.

[0137] In some embodiments, explicit signaling may be required to notify the terminal device 110-1 of the updated measurement subset K1. For example, the input for AI / ML model training may be updated based on the updated resource subset. In other embodiments, the updated resource subset may be transmitted within a first measurement setting, meaning that the settings for collecting data for AI / ML model training can be updated. In this case, the RRC IE "RS-subset-to-measure-for-training" and "RS-to-compare-for-training" may be used to notify of the updated resource subset. Alternatively, the updated resource subset may be transmitted within a second measurement setting, meaning that the settings for collecting data for AI / ML model inference can be updated. In this case, the new signaling "RS-subset-measure-for-inference" may be used to notify of the updated resource subset. As described above, different AI / ML models may be used to select different subsets K1. In other words, multiple AI / ML models (model i) can learn how to generate K from different versions of K1_i. In this case, instead of using K1' as the output, the AI / ML model ID i may be used as the output if one version of the K1 selections corresponds to one AI / ML model.

[0138] In some embodiments, the input from terminal device 110-1 for the first AI / ML mode may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, position information, trajectory, velocity, orientation, direction of movement, transmit power, Tx / Rx beam measurement subset, transmission method, wide beam used in initial access. The input from network device 120 for the AI / ML model may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, position information, transmit power, handover, Tx / Rx beam measurement subset, scheduling information, beam switching decision, multi-user scheduling decision, traffic status, transmission method, wide beam used in initial access. The input from other terminal devices for the AI / ML model may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, position information, trajectory, velocity, orientation, direction of movement, transmit power, Tx / Rx beam measurement subset, transmission method, wide beam used in initial access. Inputs from other network devices 120 for the AI / ML model may include one or more of the following: number of Tx / Rx beams / panels, beamforming gain, beamwidth, location information, transmit power, handover, measured subset of Tx / Rx beams, scheduling information, beam switching decision, multi-user scheduling decision, traffic status, transmission method, and wide beam used in initial access. Inputs from other AI / ML models for the AI / ML model may include one or more of the following: prediction of UE location, prediction of UE trajectory, prediction of handover, prediction of initial access, and prediction of channel state information (CSI).

[0139] In some embodiments, the output from the AI / ML model for terminal device 110-1 may include one or more of the following: transmit power, beam switching decision, active subset of Tx / Rx beams, and transmission method. The output from the AI / ML model for network device 120 may include one or more of the following: transmit power, handover, active subset of Tx / Rx beams, scheduling, beam switching decision, multi-user scheduling decision, traffic status, and transmission method. The output from the AI / ML model may be used as input to other AI / ML models for UE position / trajectory prediction, handover / load balancing / energy saving decision prediction, and CSI prediction.

[0140] In some embodiments, when AI / ML model inference is applied, an additional parameter relating to the number of reduced UE Rx beams may be used to determine the number of configured RS resources in the RS resource set, measurement period requirements, and measurement accuracy requirements. In some embodiments, this parameter may be indicated by network device 120. Alternatively, this parameter may be reported by terminal device 110-1. Alternatively, this parameter may be reported by terminal device 110-1 in a capability report. In other embodiments, this parameter may also be an output of the AI / ML model. Thus, it is possible to guide the settings and set performance requirements when AI / ML model inference is applied.

[0141] In some other embodiments, the number of occupied CSI processing units (CPUs) and the CSI computation time may depend on the number of resources actually measured for beam quality within the first set of resources. For example, the number of occupied CPUs may be NCPU (i.e., UE capability on the maximum number of concurrently supported CSI computations) or K1+1 (i.e., the number of resources actually measured in the resource set, including the target resource). Alternatively or additionally, for a time span from the CSI reference to the last symbol carrying the RS in K1, the number of occupied CPUs may be NCPU or K1 (i.e., the number of resources actually measured in the resource set). The number of occupied CPUs is

number

[0142] In some embodiments, the terminal device comprises a circuit configured to receive from a network device a first configuration indicating at least one resource subset from a first set of resources, wherein the at least one resource subset is for constructing a first dataset for training a first artificial intelligence (AI) / machine learning (ML) model in the network device, wherein the first dataset includes at least one of a training dataset for model training, a validation dataset for model training, a test dataset for model training, or a dataset for model inference, and transmit to the network device information relating to a quality decision based on the at least one resource subset, wherein the information is for constructing the first dataset.

[0143] In some embodiments, the first set of resources includes at least resources for beam measurement and reporting. In some embodiments, the terminal device includes a circuit configured to perform reference signal (RS) quality measurements on at least one subset of resources. In some embodiments, the terminal device includes a circuit configured to transmit information by determining the RS quality on at least one subset of resources based on the RS quality measurements and by transmitting information regarding the RS quality on at least one subset of resources to a network device.

[0144] In some embodiments, the first configuration further includes a first candidate data sample for constructing a first dataset and a first reporting configuration. In some embodiments, a terminal device comprises a circuit configured to transmit information by sending a first report to a network device, which includes a first reporting quantity indicating whether the first candidate data sample is suitable for constructing a first dataset for a first AI / ML model.

[0145] In some embodiments, the first candidate data sample includes a subset of resources as input to a first AI / ML model and a target resource as output to the first AI / ML model.

[0146] In some embodiments, the terminal device includes a circuit configured to perform the following: determine the quality of a resource subset based on measurements on the resource subset; determine the quality of a target resource based on measurements on the target resource; and compare the quality of the resource subset with the quality of the target resource. In some embodiments, the terminal device includes a circuit configured to transmit information by transmitting a first report to a network device, the first report containing a first reported quantity indicating the result of the comparison between the quality of the resource subset and the quality of the target resource.

[0147] In some embodiments, the first reported quantity further includes at least one of the following: a first index of the target resource having the quality of the target resource; an index of the resource subset having the quality of the resource subset; a second index of the best resource determined by the terminal device; an index of the measured resource subset determined by the terminal device; the measured quality of the best resource; or the measured quality of the measured resource subset.

[0148] In some embodiments, the first configuration further includes a first candidate data sample for constructing a first dataset, the first candidate data sample including a resource subset as input to a first AI / ML model. In some embodiments, the terminal device comprises a circuit configured to perform measurements on the resource subset, report the quality of the resource subset to a network device based on the measurements on the resource subset, receive a second configuration from the network device indicating a target resource as output to a first AI / ML model, perform measurements on the target resource, and determine the quality of the target resource based on the measurements on the target resource.

[0149] In some embodiments, the terminal device includes a circuit configured to transmit information by transmitting a first report to a network device, which includes the quality of a target resource, or by transmitting a first report to a network device, which includes a first reported quantity indicating a comparison result between the quality of the target resource and the quality of a subset of resources.

[0150] In some embodiments, if the quality of at least one resource subset is better than the quality of the target resource, the first reported quantity indicates that the first candidate data sample is not suitable for building the first dataset for the first AI / ML model; and if the quality of the target resource is better than all the qualities of the resource subset, the first reported quantity indicates that the first candidate data sample is suitable for building the first dataset for the first AI / ML model.

[0151] In some embodiments, the first set of resources includes a set of reference signal resources, at least one resource subset includes a subset of reference signal resources from the set of reference signal resources, and the first setting further indicates a target reference signal resource. In some embodiments, the terminal device includes a circuit configured to transmit information by transmitting a set of sounding reference signals to a network device over a set of reference signal resources and by transmitting a target sounding reference signal to a network device over a target reference signal resource.

[0152] In some embodiments, the terminal device is configured to have a time offset between the last symbol carrying a set of sounding reference signals and the first symbol carrying a target sounding reference signal.

[0153] In some embodiments, the first set of resources includes a set of reference signal resources, and at least one resource subset includes a subset of reference signal resources from the set of reference signal resources. In some embodiments, the terminal device includes a circuit configured to transmit information by transmitting a set of sounding reference signals to a network device over a set of reference signal resources. In some embodiments, the terminal device includes a circuit configured to receive a second setting from a network device indicating a target reference signal resource, and to transmit a target sounding reference signal to the network device over the target reference signal resource.

[0154] In some embodiments, a first setting instructs a terminal device to perform measurements on a first set of resources. In some embodiments, the terminal device includes a circuit configured to perform measurements on the first set of resources and to determine the quality of the first set of resources based on the measurements on the first set of resources. In some embodiments, the terminal device includes a circuit configured to transmit information by sending a second report indicating the quality of the first set of resources to a network device.

[0155] In some embodiments, the second report includes at least one of the following: the index of the first set of resources and the quality of the first set of resources; the index of a subset of resources from the first set of resources and the quality of the subset of resources that exceeds a predetermined threshold; or the difference in the quality of the first set of resources to the reference quality of the first set of resources.

[0156] In some embodiments, the first set of resources includes a set of reference signal resources, and the first setting indicates the terminal device to transmit a sounding reference signal over the set of reference signal resources. In some embodiments, the terminal device includes a circuit configured to transmit information by transmitting a sounding reference signal over the set of reference signal resources to a network device.

[0157] In some embodiments, the terminal device comprises a circuit configured to receive instructions from a network device for an updated resource subset from a first set of resources, and the updated resource subset is output from a first AI / ML model. In some embodiments, the terminal device comprises a circuit configured to receive instructions by receiving a first configuration from a network device, which includes instructions for an updated resource subset, or by receiving a second configuration from a network device, which includes instructions for an updated resource subset, for inference of a data processing model.

[0158] In some embodiments, based on the number of received beams applied during the inference of the AI / ML model, at least one of the number of reference signal resources set in the reference signal resource set, measurement period requirements, or measurement accuracy requirements is determined, and the number of received beams applied during the inference of the first AI / ML model is indicated by a network device or determined by a terminal device, or the number of received beams applied during the inference of the first AI / ML model is output by the AI / ML model.

[0159] In some embodiments, the number of channel state information (CSI) processing units and the CSI calculation time depend on the number of resources for which beam quality has been measured within the first set of resources.

[0160] In some embodiments, the network device comprises a circuit configured to transmit a first setting to a terminal device, in the network device, indicating at least one resource subset from a first set of resources, wherein the at least one resource subset is for constructing a first dataset for training a first artificial intelligence (AI) / machine learning (ML) model in the network device, and the first dataset includes at least one of a training dataset for model training, a validation dataset for model training, a test dataset for model training, or a dataset for model inference, and to receive information from the terminal device regarding quality decisions based on the at least one resource subset, wherein the information is for constructing the first dataset.

[0161] In some embodiments, the first set of resources includes at least resources for beam measurement and reporting. In some embodiments, the network device includes a circuit configured to receive information by receiving information from a terminal device regarding the quality of a reference signal (RS) on at least one subset of resources. In some embodiments, the network device includes a circuit configured to train an AI / ML model based on the RS quality of a pair of beams.

[0162] In some embodiments, the first configuration further includes a first candidate data sample for constructing a first dataset. In some embodiments, the network device comprises a circuit configured to receive information by receiving a first report from a terminal device, which includes a first reporting quantity indicating whether the first candidate data sample is suitable for constructing a first dataset for a first AI / ML model.

[0163] In some embodiments, the first candidate data sample includes a subset of resources as input to a first AI / ML model and a target resource as output to the first AI / ML model.

[0164] In some embodiments, the network device comprises a circuit configured to receive information by receiving a first report from a terminal device, which includes a first reported quantity indicating the result of a comparison between the quality of a subset of resources and the quality of a target resource.

[0165] In some embodiments, the first reporting quantity further includes at least one of the following: a first index of the target resource having the quality of the target resource; an index of the resource subset having the quality of the resource subset; a second index of the best resource determined by the terminal device; an index of the measured resource subset determined by the terminal device; the measured quality of the best resource; or the measured quality of the measured resource subset.

[0166] In some embodiments, the first configuration further includes a first candidate data sample for constructing a first dataset, the first candidate data sample including a subset of resources as input to a first AI / ML model. In some embodiments, a network device comprises a circuit configured to transmit a second configuration to a terminal device, which indicates a target resource as output to a first AI / ML model.

[0167] In some embodiments, the network device comprises a circuit configured to receive information by receiving a first report from a terminal device, which includes the quality of a target resource, or by receiving a first report from a terminal device, which includes a first reported quantity indicating a comparison between the quality of the target resource and the quality of a subset of resources.

[0168] In some embodiments, if the quality of at least one resource subset is better than the quality of the target resource, the first reported quantity indicates that the first candidate data sample is not suitable for building the first dataset for the first AI / ML model; and if the quality of the target resource is better than all the qualities of the resource subset, the first reported quantity indicates that the first candidate data sample is suitable for building the first dataset for the first AI / ML model.

[0169] In some embodiments, the first set of resources includes a set of reference signal resources, at least one resource subset includes a subset of reference signal resources from the set of reference signal resources, and the first setting further indicates a target reference signal resource. In some embodiments, the network device includes a circuit configured to receive information by receiving a set of sounding reference signals from a terminal device on a set of reference signal resources and by receiving a target sounding reference signal from a terminal device on a target reference signal resource.

[0170] In some embodiments, the first set of resources includes a set of reference signal resources, and at least one resource subset includes a subset of reference signal resources from the set of reference signal resources. In some embodiments, the network device includes a circuit configured to receive information by receiving a set of sounding reference signals from a terminal device on a set of reference signal resources. In some embodiments, the network device includes a circuit configured to transmit a second setting indicating a target reference signal resource to a terminal device and to receive a target sounding reference signal from the terminal device on a target reference signal resource.

[0171] In some embodiments, the first setting indicates to the terminal device to perform measurements on a first set of resources. In some embodiments, the network device includes a circuit configured to receive information by receiving a second report from the terminal device indicating the quality of the first set of resources.

[0172] In some embodiments, the second report includes at least one of the following: the index of the first set of resources and the quality of the first set of resources; the index of a subset of resources from the first set of resources and the quality of the subset of resources that exceeds a predetermined threshold; or the difference in the quality of the first set of resources to the reference quality of the first set of resources.

[0173] In some embodiments, the first set of resources includes a set of reference signal resources, and the first configuration instructs the terminal device to transmit a sounding reference signal on the set of reference signal resources. In some embodiments, the network device includes a circuit configured to receive information by receiving a sounding reference signal from the terminal device on the set of reference signal resources.

[0174] In some embodiments, the network device comprises a circuit configured to retrieve an updated resource subset from the output of a first AI / ML model and to transmit instructions for the updated resource subset to a terminal device. In some embodiments, the network device comprises a circuit configured to transmit instructions by transmitting a first setting, which includes instructions for the updated resource subset, to a terminal device, or by transmitting a second setting, which includes instructions for the updated resource subset, to a terminal device for inference of a data processing model.

[0175] In some embodiments, based on the number of received beams applied during the inference of the AI / ML model, at least one of the number of reference signal resources set in the reference signal resource set, measurement period requirements, or measurement accuracy requirements is determined, and the number of received beams applied during the inference of the first AI / ML model is indicated by a network device or determined by a terminal device, or the number of received beams applied during the inference of the first AI / ML model is output by the AI / ML model.

[0176] Figure 10 is a schematic block diagram of a device 900 suitable for implementing an embodiment of the present disclosure. The device 900 may be considered as another exemplary embodiment of the terminal device 110 as shown in Figure 1. Thus, the device 900 can be implemented in or as at least part of the terminal device 110. Alternatively, the device 900 may be considered as another exemplary embodiment of the network device 120 as shown in Figure 1. Thus, the device 900 may be implemented in or as at least part of the network device 120.

[0177] As shown in the figure, the device 900 comprises a processor 910, a memory 920 coupled to the processor 910, appropriate transmitters (TX) and receivers (RX) 940 coupled to the processor 910, and a communication interface coupled to the TX / RX 940. The memory 920 stores at least a portion of the program 930. The TX / RX 940 is used for bidirectional communication. The TX / RX 940 has at least one antenna to facilitate communication, although the access node referred to herein may actually have multiple antennas. The communication interface may represent any interface necessary for communication with other network elements, such as an X2 interface for bidirectional communication between eNBs, an S1 interface for communication between a mobility management entity (MME) / serving gateway (S-GW) and an eNB, an Un interface for communication between an eNB and a relay node (RN), or a Uu interface for communication between an eNB and a terminal device.

[0178] It is assumed that program 930 includes program instructions that, when executed by the associated processor 910, enable the device 900 to operate according to embodiments of the present disclosure, as described herein with reference to Figures 3 to 8. Embodiments of the present disclosure may be implemented by computer software executable by the processor 910 of the device 900, by hardware, or by a combination of software and hardware. The processor 910 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 910 and memory 920 may form processing means 950 suitable for implementing various embodiments of the present disclosure.

[0179] Memory 920 may be of any type suitable for a local technology network and may be implemented using any suitable data storage technology, such as non-temporary computer-readable storage media, semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory, as non-limiting examples. Although only one memory 920 is shown in device 900, several physically different memory modules may be present in device 900. Processor 910 may be of any type suitable for a local technology network and may include, as non-limiting examples, one or more of general-purpose computers, dedicated computers, microprocessors, digital signal processors (DSPs), and processors based on multicore processor architectures. Device 900 may have multiple processors, for example, application-specific integrated circuit chips that are temporally dependent on a clock that synchronizes the main processor.

[0180] Overall, various embodiments of the Disclosure may be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some embodiments may be implemented in hardware, while others may be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. Although various embodiments of the Disclosure are illustrated and described using block diagrams, flowcharts, or any other pictorial representation, it should be understood that any blocks, devices, systems, techniques, or methods described herein may be implemented, in non-limiting examples, in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or any combination thereof.

[0181] This disclosure also provides at least one computer program product tangibly stored on a non-temporary computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions contained in a program module, which are executed within a device on a real or virtual processor of interest to perform the processes or methods described above with reference to Figures 2 to 9. Generally, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc., that perform a specific task or realize a specific abstract data type. In various embodiments, the functions of program modules may be combined or separated among program modules as needed. The machine-executable instructions of a program module may be executed within a local or distributed device. In a distributed device, program modules may reside in both local and remote storage media.

[0182] Program code for performing the methods of this 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, a dedicated computer, or other programmable data processing device, and when executed by the processor or controller, the program code may implement the functions / operations specified in the flowcharts and / or block diagrams. The program code may run entirely on a machine, partially on a machine, as an independent software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0183] The program code described above may be implemented on a machine-readable medium, which may be any tangible medium that can contain or store programs used by or associated with an instruction execution system, device, or apparatus. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or apparatus, or any suitable combination of the aforementioned mediums. More specific examples of machine-readable storage media may include electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0184] While the operations have been described in a specific order, it should not be understood that, in order to obtain the desired results, these operations must be performed in a specific order or sequential order, or that all described operations must be performed. In some cases, multitasking and parallel processing may be advantageous. Similarly, while some specific implementation details are included in the above discussion, these should not be interpreted as limitations on the scope of this disclosure, but rather as descriptions of features that may be specific to a particular embodiment. Some features described in the context of individual embodiments may be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may be implemented separately or in any suitable subcombination in multiple embodiments.

[0185] While this disclosure has been described in language specific to structural features and / or methodological behavior, it should be understood that the disclosure as defined in the attached claims is not necessarily limited to the specific features or behaviors described above. Rather, the specific features and behaviors described above are disclosed as exemplary forms of implementing the claims.

[0186] As used herein, the term “terminal device” refers to any device having wireless or wired communication capabilities. Examples of terminal devices include user equipment (UE), personal computers, desktops, mobile phones, cellular phones, smartphones, personal digital assistants (PDAs), portable computers, tablets, wearable devices, Internet of Things (IoT) devices, ultra-reliable low-latency communication (URLLC) devices, any Internet of Things (IoT) devices, machine-type communication (MTC) devices, in-vehicle devices for V2X communication where X represents pedestrians, vehicles, or infrastructure / networks, devices for integrated access and integrated access and backhaul (IAB), satellite-borne or aircraft-borne vehicles within non-terrestrial networks (NTN) including high-altitude platforms (HAP) encompassing satellites and unmanned aircraft systems (UAS), extended reality (XR) devices including different types of reality such as augmented reality (AR), mixed reality (MR), and virtual reality (VR), unmanned aerial vehicles (UAVs), which are aircraft without human pilots and are commonly referred to as drones, and high-speed trains (HSTs). The “Terminal device” includes, but is not limited to, devices on a train, or image acquisition devices such as digital cameras, sensor game devices, music storage and playback devices, or internet-connected home appliances that enable wireless or wired internet access and browsing. The “Terminal device” may further have “multicast / broadcast” capabilities to support V2X applications, transparent IPv4 / IPv6 multicast distribution, IPTV, smart TV, wireless services, wireless software distribution, group communications, and Iota applications, where public safety and mission are of paramount importance. It may also incorporate one or more Subscriber Identity Modules (SIMs), known as multi-SIMs.The term "terminal device" may be used interchangeably with UE, mobile station, subscriber station, mobile terminal, user terminal, or radio device.

[0187] The term "network device" refers to a device that can provide or host a cell or coverage on which terminal devices can communicate. Examples of network devices include, but are not limited to, low-power nodes such as Node B (Node or NB), Evolutionary Node (Node or eNB), Next Generation Node (gNB), Transmit / Receive Point (TRP), Remote Radio Unit (RRU), Radio Head (RH), Remote Radio Head (RRH), IAB Node, Femtonode, Piconode, and Reconfigurable Intelligent Surface (RIS).

[0188] Terminal devices or network devices may possess artificial intelligence (AI) or machine learning capabilities. Generally, this includes a trained model derived from a large amount of data collected for a specific function, which can be used to predict certain information.

[0189] Terminal or network devices may operate on several frequency ranges, such as FR1 (410 MHz to 7125 MHz), FR2 (24.25 GHz to 71 GHz), frequency bands greater than 100 GHz, and terahertz (THz). Furthermore, they can operate on licensed / unlicensed / shared spectrum. Terminal devices may have two or more connections to network devices under Multi-Radio Dual Connectivity (MR-DC) application scenarios. Terminal or network devices can operate in full-duplex, flexible-duplex, or cross-split-duplex modes.

[0190] Embodiments of this disclosure may be implemented, for example, in test equipment such as signal generators, signal analyzers, spectrum analyzers, network analyzers, test terminal devices, test network devices, and channel emulators.

[0191] Embodiments of the present disclosure may be implemented in accordance with any generation of communication protocols currently known or to be developed in the future. Examples of communication protocols include, but are not limited to, first-generation (1G), second-generation (2G), 2.5G, 2.75G, third-generation (3G), fourth-generation (4G), 4.5G, fifth-generation (5G) communication protocols, 5.5G, 5G-Advanced networks, or sixth-generation (6G) networks.

Claims

1. A method performed by a terminal device, Receiving a first setting from a network device that indicates one or more resources, wherein the one or more resources are from a first set of resources, and the one or more resources are for network-side data collection for training a first artificial intelligence / machine learning (AI / ML) model, Transmitting information based on one or more of the aforementioned resources to the network device, wherein the information is for the purpose of collecting network-side data. Includes, The measurement period for inference of the first AI / ML model is determined based on the number of received beams parameter, which is determined by the terminal device. method.

2. Based on the parameter of the number of received beams, the number of non-zero power (NZP) CSI-RS resource repetitions for each channel state information-reference signal (CSI-RS) resource set is determined. The method according to claim 1.

3. Transmitting the aforementioned information means Transmitting to the network device a first report containing information indicating that the terminal device has measurement results for one or more resources, A second report, including the measurement results of one or more of the aforementioned resources, is transmitted to the network device. including, The method according to claim 1.

4. A method performed by a network device, Transmitting a first setting to a terminal device indicating one or more resources, wherein the one or more resources are from a first set of resources, and the one or more resources are for network-side data collection for training a first artificial intelligence / machine learning (AI / ML) model, Receiving information corresponding to one or more of the aforementioned resources from the terminal device, wherein the information is for the purpose of collecting network-side data, Includes, The measurement period for inference of the first AI / ML model is based on the number of received beams parameter, which is received from the terminal device. method.

5. Based on the parameter of the number of received beams, the number of non-zero power (NZP) CSI-RS resource repetitions for each channel state information-reference signal (CSI-RS) resource set is determined. The method according to claim 4.

6. Receiving the aforementioned information means Receiving a first report from the terminal device that includes information indicating that the terminal device has measurement results for one or more resources, Receiving a second report from the terminal device, which includes the measurement results of one or more of the aforementioned resources, including, The method according to claim 4.

7. A terminal device, Means for receiving a first setting from a network device indicating one or more resources, wherein the one or more resources are from a first set of resources, and the one or more resources are for network-side data collection for training a first artificial intelligence / machine learning (AI / ML) model, Means for transmitting information based on one or more of the aforementioned resources to the network device, wherein the information is for network-side data collection; Equipped with, The measurement period for inference of the first AI / ML model is determined based on the number of received beams parameter, which is determined by the terminal device. Terminal device.

8. Based on the parameter of the number of received beams, the number of non-zero power (NZP) CSI-RS resource repetitions for each channel state information-reference signal (CSI-RS) resource set is determined. The terminal device according to claim 7.

9. The means for transmitting the information is: Means for transmitting a first report to the network device, which includes information indicating that the terminal device has measurement results for one or more resources, Means for transmitting a second report, including the measurement results of one or more of the aforementioned resources, to the network device, including, The terminal device according to claim 7.

10. Means for transmitting a first setting indicating one or more resources to a terminal device, wherein the one or more resources are from a first set of resources, and the one or more resources are for network-side data collection for training a first artificial intelligence / machine learning (AI / ML) model, Means for receiving information corresponding to one or more of the aforementioned resources from the terminal device, wherein the information is for network-side data collection, Equipped with, The measurement period for inference of the first AI / ML model is based on the number of received beams parameter, which is received from the terminal device. Network device.

11. Based on the parameter of the number of received beams, the number of non-zero power (NZP) CSI-RS resource repetitions for each channel state information-reference signal (CSI-RS) resource set is determined. The network device according to claim 10.

12. The means for receiving the information is: Means for receiving from the terminal device a first report containing information indicating that the terminal device has measurement results for one or more resources, A means for receiving a second report from the terminal device, which includes the measurement results of one or more of the aforementioned resources, including, The network device according to claim 10.

Images