Terminal device and method

Abstract

An embodiment of the present disclosure provides a solution for reporting model performance. The terminal device determines a first set of parameters based on a first measurement on a first set of reference signals and determines a second set of parameters based on a data processing model and a second measurement on a second set of reference signals. The terminal device determines first information based on a comparison between the first set of parameters and the second set of parameters. The terminal device determines second information based on the first information and predetermined condition information and transmits the second information to a network device. The second information indicates at least one of status information related to the performance metrics, a numerical value related to the performance metrics, or a percentage related to the performance metrics. In this way, the terminal device knows how to report the performance metrics of the AI / ML model.

Description

[Technical Field]

[0001] FIELD Exemplary embodiments of the present disclosure relate to the field of communications technology, and more particularly to a method, apparatus, and medium for reporting model performance. [Background technology]

[0002] Several techniques have been proposed to improve communication performance. For example, communication devices can employ artificial intelligence / machine learning (AI / ML) models to improve communication quality. AI / ML models can be applied to different scenarios to achieve better performance. Therefore, a solution for fully reporting AI / ML performance is needed. Summary of the Invention [Problem to be solved by the invention]

[0003] Embodiments of the present disclosure provide a method, apparatus, and computer storage medium for reporting model performance.

[0004] In a first aspect, a terminal device is provided, including a processor configured to cause the terminal device to: determine a first set of parameters based on first measurements on a first set of reference signals, determine a second set of parameters based on a data processing model and second measurements on a second set of reference signals, determine first information based on a comparison of the first set of parameters with the second set of parameters, determine second information based on predetermined condition information and the first information, the second information indicating at least one of status information related to a performance metric, a numerical value related to a performance metric, a percentage related to a performance metric, or the first information; and transmit the second information to the network device.

[0005] In a second aspect, a network device is provided, including a processor configured to cause the terminal device to receive, from the terminal device, second information indicative of at least one of status information related to a performance metric, a numerical value related to the performance metric, a percentage related to the performance metric, or first information, where the second information is determined based on predetermined condition information and the first information, where the first information is determined based on a comparison of a first set of parameters and a second set of parameters, where the first set of parameters is determined based on first measurements on the first set of reference signals, and where the second set of parameters is determined based on second measurements on the second set of reference signals.

[0006] In a third aspect, a method for communication is provided, the method including: determining a first set of parameters based on first measurements on a first set of reference signals, determining a second set of parameters based on a data processing model and second measurements on a second set of reference signals, determining first information based on a comparison of the first set of parameters and the second set of parameters, determining second information based on predetermined condition information and the first information, the second information indicating at least one of status information related to a performance metric, a numerical value related to a performance metric, a percentage related to a performance metric, or the first information, and transmitting the second information to the network device.

[0007] In a fourth aspect, a communication method is provided, the method including receiving, from a terminal device, second information indicative of at least one of status information related to a performance metric, a numerical value related to the performance metric, a percentage related to the performance metric, or first information, wherein the second information is determined based on predetermined condition information and the first information, the first information is determined based on a comparison of a first set of parameters and a second set of parameters, the first set of parameters is determined based on first measurements on the first set of reference signals, and the second set of parameters is determined based on second measurements on the second set of reference signals.

[0008] In a fifth aspect, there is provided a computer-readable medium having instructions stored thereon which, when executed on at least one processor, cause the at least one processor to perform a method according to the third or fourth aspect.

[0009] Other features of the present disclosure will become readily apparent from the following description. [Brief explanation of the drawings]

[0010] These and other objects, features and advantages of the present disclosure will become more apparent from a more particular description of several exemplary embodiments of the present disclosure in the accompanying drawings.

[0011] [Figure 1] 1 illustrates an exemplary communication environment in which exemplary embodiments of the present disclosure may be practiced.

[0012] [Figure 2] 1 illustrates a signaling flow for reporting angle information according to some embodiments of the present disclosure.

[0013] [Figure 3] 1 illustrates a flowchart of a method performed in a terminal device according to some exemplary embodiments of the present disclosure.

[0014] [Figure 4] 1 illustrates a flowchart of a method performed in a network device according to some exemplary embodiments of the present disclosure.

[0015] [Figure 5] FIG. 1 shows a simplified block diagram of an apparatus suitable for practicing exemplary embodiments of the present disclosure.

[0016] Throughout the drawings, the same or similar numbers represent the same or similar elements. DETAILED DESCRIPTION OF THE INVENTION

[0017] The principles of the present disclosure will be explained with reference to some exemplary embodiments. It will be understood that these embodiments are provided for illustrative purposes to help those skilled in the art understand and practice the present disclosure, and are not intended to imply any limitations on the scope of the present disclosure. The embodiments described herein can be implemented in various ways other than those described below.

[0018] 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 belongs.

[0019] As used herein, the term "terminal device" refers to any device with wireless or wired communication capabilities. Examples of terminal devices include, but are not limited to, user equipment (UE), personal computers, desktops, mobile phones, mobile phones, smartphones, personal digital assistants (PDAs), portable computers, tablets, wearable devices, IoT devices, Ultra-Reliable and Low Latency Communications (URLLC) devices, IoE devices, machine-type communications (MTC) devices, vehicle-mounted equipment for V2X communications (where X stands for pedestrian, vehicle, and infrastructure / network), equipment for integrated access and backhaul (IAB), space- or air-operated vehicles in non-terrestrial networks (NTN) including satellites and advanced platforms (HAPs) including unmanned aerial systems (UAS), augmented reality (XR) devices including different types of reality such as augmented reality (AR), mixed reality (MR), and virtual reality (VR), unmanned aerial vehicles (UAVs), commonly known as aircraft without a human pilot, devices on high-speed trains (HST), or image capture devices such as digital cameras, sensors, gaming devices, music storage and playback appliances, or internet appliances enabling wireless or wired internet access and browsing. The terminal device may further have a "multicast / broadcast" feature and may support public safety and mission-critical, V2X applications, transparent IPv4 / IPv6 multicast distribution, IPTV, smart TV, wireless services, over-the-air software distribution, group communication, and IoT applications. It may also incorporate one or more subscriber identity modules (SIMs), referred to as multi-SIM. The term "terminal device" may be used interchangeably with UE, mobile station, subscriber station, mobile terminal, user terminal, or wireless device.

[0020] The term "network device" refers to a device capable of providing or hosting a cell or coverage area over which terminal devices can communicate. Examples of network devices include, but are not limited to, a Node B (NodeB or NB), an evolved Node B (eNodeB or eNB), a next generation Node B (gNB), a transmission reception point (TRP), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), a low-power node such as an IAB node, a femto node, a pico node, and a reconfigurable intelligent surface (RIS).

[0021] A terminal device or network device may have artificial intelligence (AI) or machine learning capabilities, which typically include models trained from a large amount of collected data for a specific function and can be used to predict some information.

[0022] A terminal device or network device may operate in multiple frequency ranges, such as FR1 (e.g., 550 MHz to 6000 MHz), FR2 (e.g., 24.25 GHz to 52.6 GHz), frequency bands greater than 100 GHz, and terahertz (THz). It can also operate in licensed, unlicensed, and shared spectrum. A terminal device may have multiple connections with network devices in Multi-Radio Dual Connectivity (MR-DC) application scenarios. The terminal device or network device can operate in full duplex, flexible duplex, and cross division duplex modes.

[0023] Embodiments of the present disclosure may be implemented in test equipment, such as a signal generator, a signal analyzer, a spectrum analyzer, a network analyzer, a test terminal device, a test network device, or a channel emulator. In some embodiments, a terminal device may be connected to a first network device and a second network device. One of the first network device and the second network device may be a master node and the other may be a secondary node. The first network device and the second network device may use different radio access technologies (RATs). In some embodiments, the first network device may be a first RAT device and the second network device may be a second RAT device. In some embodiments, the first RAT device is an eNB and the second RAT device is a gNB. Information regarding the different RATs may be transmitted to the terminal device from at least one of the first network device and the second network device. In some embodiments, 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 to the terminal device directly or via the first network device. In some embodiments, information regarding the terminal device configuration configured by the second network device may be transmitted from the second network device via the first network device. The information regarding the reconfiguration of the terminal device configured by the second network device may be transmitted to the terminal device directly from the second network device or via the first network device.

[0024] In this disclosure, unless the context clearly indicates otherwise, the singular forms "a," "the," and "the" are intended to include the plural. The term "comprises" and variations thereof are interpreted as open-ended terms meaning "including, but not limited to." The term "based on" is interpreted as "based at least in part on." The terms "one embodiment" and "embodiment" are interpreted as "at least one embodiment." The term "another embodiment" is interpreted as "at least one other embodiment." Terms such as "first," "second," etc. may refer to different objects or the same object. The following content may include other definitions, both explicit and implicit.

[0025] In some instances, values, procedures, or devices are referred to as "optimal," "lowest," "highest," "minimum," "maximum," etc. It is understood that such descriptions are intended to indicate choices among multiple functional alternatives used, and that such choices are not necessarily better, smaller, higher, or more preferred than other choices.

[0026] As used herein, the terms "resource," "transmission resource," "uplink resource," or "downlink resource" may refer to any resource for performing communication, such as a time domain resource, a frequency domain resource, a space domain resource, a code domain resource, or any other resource that enables communication. Hereinafter, unless otherwise specified, both frequency domain and time domain resources are used as examples of transmission resources to describe some exemplary embodiments of the present disclosure. It should be noted that the exemplary embodiments of the present disclosure are equally applicable to other resources in other domains. As used herein, the term "channel state information (CSI)" refers to the channel characteristics of a communication link. CSI describes how a signal propagates from a transmitter to a receiver, representing, for example, the combined effects of scattering, fading, and power attenuation over distance. The term "CSI report" may refer to a report indicating whether the channel is good or bad.

[0027] As mentioned above, AI / ML models are applied in different scenarios. Regarding UE-side performance monitoring, i.e., model monitoring on the UE side, the UE must monitor (i.e., calculate or measure) performance metrics (or monitoring results) corresponding to the AI / ML model and report them to the network (NW). Specifically, in the case of beam management (BM) (i.e., spatial / temporal beam prediction using a one-sided model), the UE must monitor and report to the network the performance metrics of beam prediction accuracy or L1-reference signal received power (RSRP) difference. In the case of CSI compression using a two-sided model or temporal CSI prediction using a one-sided model, the UE must monitor and report to the network the performance metrics of squared generalized cosine similarity (SGCS) or normalized mean squared error (NMSE). However, there has been no discussion to date about how to report the above performance metrics (especially intermediate key performance metrics (KPIs)) corresponding to AI / ML models. In other words, there is no effective and reasonable method for reporting performance metrics corresponding to AI / ML models.

[0028] To solve at least some of the above problems, an embodiment of the present disclosure provides a solution for reporting model performance. The terminal device determines a first set of parameters based on a first measurement of a first set of reference signals and determines a second set of parameters based on a second measurement of a second set of reference signals and a data processing model. The terminal device determines first information based on a comparison between the first set of parameters and the second set of parameters. The terminal device further determines second information based on the first information and predetermined condition information and transmits the second information to a network device. The second information indicates at least one of status information related to a performance metric, a numerical value related to the performance metric, or a percentage related to the performance metric. In this way, the terminal device or the network device knows how to report the performance metric of the AI / ML model. Based on the reported performance-related information, the NW can make rational and systematic decisions related to the AI / ML model for the UE and provide rational configuration or instruction information related to the AI / ML model for the UE.

[0029] In the context of this application, the term "data processing model" as used herein refers to an algorithm used to process data. The term "AI / ML model" as used herein is a data-driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs. The term "AI / ML model" may be interchangeable with the terms "data processing model" or "model." The term "data collection" refers to the process of data collection by a network node, management entity, or UE for the purposes of AI / ML model training, data analysis, and inference. The term "AI / ML model training" as used herein refers to the process of training an AI / ML model in a data-driven manner [by learning input / output relationships] and obtaining a trained AI / ML model for inference. The term "AI / ML model inference" as used herein refers to the process of using a trained AI / ML model to generate a set of outputs based on a set of inputs. The term "performance metric" as used herein refers to measurement data used to track and measure the performance of a model. Performance metrics can directly or indirectly indicate the performance of an AI / ML model.

[0030] As used herein, the term "AI / ML model validation" refers to a subprocess of training that helps select model parameters that generalize beyond the dataset used for model training in order to evaluate the quality of an AI / ML model using a dataset different from the dataset used for model training. As used herein, the term "model monitoring" refers to the procedure of monitoring the inference performance of an AI / ML model.

[0031] As used herein, the term "UE-side (AI / ML) model" refers to an AI / ML model in which inference is performed by all UEs. As used herein, the term "network-side (AI / ML) model" refers to an AI / ML model in which inference is performed by all networks. As used herein, the term "single-sided (AI / ML) model" refers to a UE-side (AI / ML) model or a network-side (AI / ML) model. As used herein, the term "two-sided (AI / ML) model" refers to paired AI / ML models in which joint inference is performed, where joint inference includes AI / ML inference in which inference is performed jointly across the UE and the network. That is, the first part of the inference is first performed by the UE, and then the remaining part is performed by the gNB (or vice versa).

[0032] As used herein, the term "model activation" refers to enabling an AI / ML model for a particular function. As used herein, the term "model deactivation" refers to disabling an AI / ML model for a particular function. As used herein, the term "model switching" refers to deactivating a currently active AI / ML model and activating a different AI / ML model for a particular function. As used herein, the term "model management" refers to a more general term that includes one or more of the following functions / procedures: model activation, deactivation, selection, switching, fallback, and updating (including retraining).

[0033] As used herein, the term "supervised learning" refers to the process of training a model from inputs and corresponding labels. As used herein, the term "unsupervised learning" refers to the process of training a model without labeled data. As used herein, the term "semi-supervised learning" refers to the process of training a model with a mixture of labeled and unlabeled data. As used herein, the term "reinforcement learning (RL)" refers to the process of training an AI / ML model from inputs (also called states) and feedback signals (also called rewards) that are derived from the model's outputs (also called actions) in the environment with which the model is interacting.

[0034] The term "beam" refers to a reference signal or a reference signal resource. For example, a beam refers to a channel state information reference signal (CSI-RS) or a CSIRS resource. Alternatively, a beam refers to a synchronization signal / physical broadcast channel (PBCH) block (SSB) or an SSB resource. As used herein, the term "beam identity (ID)" refers to a CSI-RS resource index (CRI) or an SSB resource index (SSBRI). As used herein, the term "measured Layer 1 reference signal received power (L1-RSRP)" refers to a measurement of L1-RSRP. This corresponds to the ideal L1-RSRP.

[0035] The principles and embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0036] 1 illustrates a schematic diagram of an exemplary communication environment 100 in which exemplary embodiments of the present disclosure may be implemented. In the communication environment 100, multiple communication devices, including terminal devices 110 and network devices 120, may communicate with each other.

[0037] 1, the terminal device 110 may be a UE, and the network device 120 may be a base station serving the UE. The serving area of ​​the network device 120 may be referred to as a cell 102.

[0038] It should be understood that the number of devices and their connections shown in FIG. 1 are for illustrative purposes only, with no limitation implied. Communication environment 100 includes any suitable number of devices configured to implement exemplary embodiments of the present disclosure. Although not shown, it is understood that one or more additional devices may be located in cell 102 and one or more additional cells may be deployed in communication environment 100. While illustrated as a network device, it should be noted that network device 120 may be a device separate from the network device. Although illustrated as a terminal device, terminal device 110 may be a device other than a terminal device.

[0039] For purposes of explanation, the following describes some exemplary embodiments in which terminal device 110 operates as a UE and network device 120 operates as a base station. However, in some exemplary embodiments, operations described with reference to a terminal device may be performed by a network device or other device, and operations described with reference to a network device may be performed by a terminal device or other device.

[0040] In some exemplary embodiments, if terminal device 110 is a terminal device and network device 120 is a network device, the link from network device 120 to terminal device 110 is referred to as the downlink (DL), while the link from terminal device 110 to network device 120 is referred to as the uplink (UL). In the DL, network device 120 is the transmit (TX) device (or transmitter) and terminal device 110 is the receive (RX) device (or receiver). In the UL, terminal device 110 is the TX device (or transmitter) and network device 120 is the RX device (or receiver).

[0041] Communications in the communication environment 100 may conform to any suitable standard, including, but not limited to, Global System for Mobile Communications (GSM), Long Term Evolution (LTE), LTE-Evolution, Advanced LTE (LTE-A), New Radio (NR), Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access (CDMA), Global System for Mobile Communications (GSMEDGE) Radio Access Network (GERAN), Machine Type Communications (MTC), etc. Embodiments of the present disclosure may be performed in accordance with any currently known or future-developed generation of communication protocols. 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, advanced 5G networks, or sixth generation (6G) networks.

[0042] Referring to Figure 2, a signaling flow 200 for reporting angle information according to some embodiments of the present disclosure is shown. For purposes of discussion, signaling flow 200 will be discussed with reference to Figure 1, using, for example, terminal device 110 and network device 120. Note that Figure 2 is merely an example embodiment.

[0043] The network device 120 may transmit (2005) a configuration to the terminal device 110. The configuration may indicate a first set of reference signals and / or resources of the first set of reference signals. Additionally, the configuration may indicate a second set of reference signals and / or resources of the second set of reference signals. In some embodiments, the second set of reference signals may be a subset of the first set of reference signals. Alternatively, the second set of reference signals may be the same as the first set of reference signals. In some other embodiments, the second set of reference signals may be different from the first set of reference signals. In some embodiments, the first set of reference signals and the second set of reference signals may refer to CSI-RS. Alternatively, the first set of reference signals and the second set of reference signals may refer to SSBs. It should be noted that the first set of reference signals and the second set of reference signals may refer to any suitable type of reference signal.

[0044] Furthermore, the configuration may indicate a data processing model for monitoring. For example, the configuration may include an index of the data processing model. Alternatively, the configuration may include model parameters for the data processing model. The data processing model may be expressed or indicated by (or replaced with) a model ID or function. In the case of CSI compression, the AI / ML model may correspond to a CSI generator or a CSI reconstructor.

[0045] The network device 120 may transmit 2010 a plurality of reference signals to the terminal device 110. For example, the plurality of reference signals may include a first set of reference signals and a second set of reference signals. As mentioned above, in some embodiments, the plurality of reference signals may be a plurality of CSI-RS. Alternatively, or additionally, the plurality of reference signals may be a plurality of SSBs.

[0046] Terminal device 110 may perform measurements 2020 on multiple reference signals. In some embodiments, terminal device 110 may measure RSRP of the multiple reference signals. Terminal device 110 may determine received signal strength indicators (RSSIs) of the multiple reference signals. Alternatively, or additionally, terminal device 110 may determine reference signal received quality (RSRQs) of the multiple reference signals. In some other embodiments, terminal device 110 may measure signal-to-interference-and-noise ratios (SINRs) of the multiple reference signals. It should be noted that any suitable type of measurements may be performed on the multiple reference signals.

[0047] Terminal device 110 determines 2030 a first set of parameters based on first measurements on the first set of reference signals. For example, in some embodiments, terminal device 110 may determine the first set of beams based on RSRPs of the first set of reference signals. In this case, the first set of parameters may include the first set of beams. Alternatively, the first set of parameters may include first channel state information. Examples of the first set of parameters are described in more detail below.

[0048] The terminal device 110 determines a second set of parameters based on second measurements on the second set of reference signals and the data processing model (2040). For example, in some embodiments, the terminal device 110 may determine a second set of beams based on the RSRPs of the second set of reference signals. In this case, the second set of parameters may include the second set of beams. Alternatively, the second set of parameters may include second channel state information. For example, the measured L1-RSRPs of beams in the second set of reference signals are used as inputs (i.e., one input sample) of the data processing model. The beam IDs of the top-K beams of beams in the first set of reference signals may be outputs of the data processing model. Examples of the second set of parameters are described in more detail below.

[0049] The terminal device 110 determines 2050 the first information based on a comparison of the first set of parameters with the second set of parameters, examples of which are described in more detail below.

[0050] The terminal device 110 determines (2060) second information based on the first information and the predetermined condition information. The second information indicates one or more of status information related to a performance metric, a numerical value related to a performance metric, a percentage related to a performance metric, or the first information. As used herein, the term "status" may correspond to any one of information, a state, or an event. The terminal device 110 may determine the status based on predefined criteria or conditions. In some embodiments, if the predefined criteria / conditions are met, the terminal device 110 may determine a status corresponding to the predefined criteria. Examples of predetermined condition information and status information are described below.

[0051] In some embodiments, the performance metric may refer to beam prediction accuracy. For example, the beam prediction index may include beam prediction accuracy (%) for the Top-1 and / or Top-K beams. Top-1 (%) may represent the percentage of Top-1 elite support beams that are the Top-1 predicted beams. Top-K / 1 (%) may represent the percentage of Top-1 elite support beams that are one of the Top-K predicted beams. Top-1 / K (%) may represent the percentage of Top-1 predicted beams that are one of the Top-K elite support beams. In some embodiments, the beam prediction index may include beam prediction accuracy (%) with a 1 dB margin for the Top-1 beam. Beam prediction accuracy (%) with a 1 dB margin may be the percentage of Top-1 predicted beams whose ideal L1-RSRP is within 1 dB of the ideal L1-RSRP of the Top-1 elite support beam.

[0052] Alternatively, or in addition, the performance metric may refer to the L1-RSRP difference between the measured L1-RSRP and the predicted L1-RSRP. For example, the L1-RSRP difference may include the average L1-RSRP difference of the Top-1 predicted beams or the cumulative distribution function (CDF) of the L1-RSRP difference for the Top-1 predicted beams. The term "L1-RSRP difference of the Top-1 predicted beams" may refer to the difference between the ideal L1-RSRP of the Top-1 predicted beams and the ideal L1-RSRP of the Top-1 elite support beams.

[0053] In some other embodiments, the performance metric may include one or more of link quality, overall, L1-RSRP, or L1-SINR. The throughput may refer to one of: overall may refer to any one of CDF across UEs, average, and 5%ile across UEs. L1-RSRP / SINR may refer to the measured L1-RSRP / SINR of the current / indicated link. In some embodiments, the performance metric may relate to input / output data distribution, e.g., data drift between training and observed data sets, out-of-distribution detection.

[0054] In some embodiments, the performance metric may refer to the accuracy of the AI / ML output CSI. For example, the performance metric may refer to CSI compression by a two-sided model and temporal CSI prediction. In some embodiments, the performance metric may refer to the SGCS, i.e., the precoding matrix as the AI / ML input / output. For example, if Rank=1, the performance metric may include one SGCS (e.g., 0≦SGCS≦1). If Rank>1, the performance metric may include one SGCS, e.g., the average SGCS of all ranks, or a weighted average SGCS of all ranks. Alternatively, if Rank>1, the performance metric may include separate SGCSs. In some embodiments, the performance metric may refer to the NMSE, i.e., the raw channel as the AI / ML input / output, with units of dB. In some embodiments, the performance metric may include one or more of the equivalent MSE, the received SNR, or the numerical spectral efficiency difference.

[0055] Terminal device 110 transmits (2070) the second information to network device 120. In some embodiments, the second information may be transmitted in uplink control information. Alternatively, or additionally, the second information may be transmitted in a medium access control element (MAC CE).

[0056] As described above, in some embodiments, the first set of parameters includes a first set of beams, and the second set of parameters includes a second set of beams. For example, the terminal device 110 may determine the top-K1 beams in the first set of reference signals (i.e., the first set of beams). The top-K1 beams in the first set of reference signals may refer to the beam IDs of the K1 beams with the largest measured L1-RSRPs in the first set of reference signals. The top-K1 beams in the first set of reference signals determined based on the measured L1-RSRPs may be referred to as "top-K1 elite support beams." Furthermore, the terminal device 110 may directly or indirectly determine the top-K2 beams in the first set of reference signals (i.e., the second set of beams) based on the measured L1-RSRPs of the beams in the second set of reference signals and a data processing model. The top-K2 beams in the first set of reference signals determined based on the data processing model may be referred to as "top-K2 predicted beams." In some embodiments, the data processing model may be any one of the following: An AI / ML model designed based on clarification, where the output of the AI / ML model is the beam ID of the top-K2 predicted beam, means that the terminal device 110 can directly determine the top-K2 predicted beam; An AI / ML model designed based on regression, where the output of the AI / ML model is a predicted or estimated value of the L1-RSRP of the beam in the first set of reference signals (referred to as the "predicted L1-RSRP"), means that the terminal device 110 can indirectly determine the top-K2 predicted beam based on the predicted L1-RSRP of the beam in the first set of reference signals.

[0057] In some embodiments, the predetermined condition information may include a first predetermined condition. In this case, the terminal device 110 may determine first information indicating whether the first set of beams overlaps with the second set of beams based on a comparison between the first set of beams and the second set of beams. In other words, the terminal device 110 may compare the first set of beams with the second set of beams to determine whether the first set of beams overlaps with the second set of beams. The terminal device 110 may determine whether the first information satisfies the first predetermined condition. If the first information satisfies the first predetermined condition, the terminal device 110 may determine a first status indicating that the first predetermined condition is satisfied. In this case, the second information may include the first status. For example, in some embodiments, the terminal device 110 may transmit a CSI report or a MAC CE carrying the first status. In some embodiments, a 1-bit CSI field may be introduced into the UCI or into the MAC CE including a 1-bit field indicating the first status. That is, the first status may be defined by a 1-bit value. This means that different bit values ​​(i.e., 1 and 0) correspond to different first statuses. In some other embodiments, the second information may include at least one first status, for example, multiple 1-bit fields are used to indicate multiple first statuses.

[0058] In some embodiments, the first predetermined condition may indicate that a first target beam in the first set of beams overlaps with a beam in the second set. As an example, the first target beam may refer to a beam in the first set of beams with the highest L1-RSRP. For example, the first predetermined condition may indicate that the top-1 elite support beam is one of the top-K2 predicted beams. In other words, if the top-1 elite support beam is one of the top-K2 predicted beams, the terminal device 110 may determine a first status in which the top-1 elite support beam is one of the top-K2 predicted beams. Here, the first predetermined condition may indicate that the beam ID of the top-1 elite support beam overlaps (or is the same as) the beam ID of one of the top-K2 predicted beams. For example, K2=1 means that the beam ID of the top-1 elite support beam overlaps with the beam ID of the top-1 predicted beam.

[0059] Alternatively, the first predetermined condition may indicate that the first target beam of the first set of beams does not overlap with the beams of the second set. For example, the first predetermined condition may indicate that the top-1 elite supporting beam is not one of the top-K2 predicted beams. In other words, if the top-1 elite supporting beam is not one of the top-K2 predicted beams, the terminal device 110 may determine a first status that the top-1 elite supporting beam is not one of the top-K2 predicted beams. The first predetermined condition may indicate that the beam ID of the top-1 elite supporting beam does not overlap (or is different from) the beam ID of any one of the top-K2 predicted beams.

[0060] In some other embodiments, the first predetermined condition may indicate that a second target beam in the second set of beams overlaps with a beam in the first set. For example, the first predetermined condition may indicate that the top-1 predicted beam is one of the top-K1 elite support beams. In other words, if the top-1 predicted beam is one of the top-K1 elite support beams, the terminal device 110 may determine a first status that the top-1 predicted beam is one of the top-K1 elite support beams. The first predetermined condition may indicate that the beam ID of the top-1 predicted beam overlaps (or is the same as) the beam ID of one of the top-K1 elite support beams.

[0061] In some embodiments, the first predetermined condition may indicate that the second target beam in the second set of beams does not overlap with the first set of beams. For example, the first predetermined condition may indicate that the top-1 predicted beam is not one of the top-K1 elite supporting beams. In other words, if the top-1 predicted beam is not one of the top-K1 elite supporting beams, the terminal device 110 may determine a first status that the top-1 predicted beam is not one of the top-K1 elite supporting beams. The first predetermined condition may indicate that the beam ID of the top-1 predicted beam overlaps (or is different from) the beam ID of one of the top-K1 elite supporting beams.

[0062] In some other embodiments, the terminal device 110 may determine the third information based on the first set of beams and the second set of beams. The third information indicates which beams in the first set of beams overlap with the first target beam in the second set of beams. In this case, the second information may include the first status, the third information, and beam information of the first set of beams. In some embodiments, the beam information may include the beam ID of the beam (or reference signal) and the beam quality of the beam (or reference signal). As an example, the terminal device 110 may determine which beams in the top-K elite assistance beams overlap with the top-1 predicted beam based on the beam IDs in the top-K elite assistance beams and the beam IDs of the top-K2 predicted beams. Alternatively, the terminal device 110 may determine which beams in the top-K predicted beams overlap with the top-1 elite assistance beam, or which beams in the top-K predicted beams overlap with the top-1 elite assistance beam. The terminal device 110 may report the top-K1 elite supporting beams and which beams among the top-K elite supporting beams overlap with the top-1 predicted beam. For example, the terminal device 110 may report the beam IDs and measured L1-RSRPs of the top-K1 elite supporting beams. In this case, a CSI report may be used to report the beam IDs and measured L1-RSRPs of the top-K1 elite supporting beams. In some embodiments, the mapping order of different CSI fields indicating the beam IDs and measured L1-RSRPs of the top-K1 elite supporting beams may be shown in Table 1. The value of K1 may be determined based on a configuration (e.g., nrofReportedRS) provided by the network device 120. Alternatively, the terminal device 110 may report the top-K1 elite supporting beams by using a new MAC-CE including a bit field indicating the beam ID and measured L1-RSRP. [Table 1]

[0063] In some embodiments, an M-bit CSI field may be included in the UCI to indicate the third information. Alternatively, an MEC CE including an M-bit field may be used to indicate the third information. The value of M (i.e., the bit width for the M-bit field) may be determined based on (e.g., equal to) the number of elite supporting beams to be reported (i.e., the value of K1), for example: TIFF2026507525000003.tif435. For example, a bit value of "00" indicates that the top-1 predicted beam is the first beam of the top-K1 elite aiding beams (i.e., the beam corresponding to CRI or SSBRI#1). Additionally, a 1-bit field may be required. This 1-bit field is used to indicate whether the top-1 predicted beam is one of the top-K1 elite aiding beams. Furthermore, if the 1-bit field indicates that the top-1 predicted beam is not one of the top-K1 elite aiding beams, the M-bit field (i.e., the third information) can be omitted or ignored. For example, the mapping order of the CSI field indicating the top-K1 elite aiding beams, the M-bit CSI field indicating the first information, and the 1-bit CSI field indicating the second information in the UCI may be determined based on Table 2. [Table 2]

[0064] Alternatively, the CSI report would look like Table 3. [Table 3]

[0065] In some embodiments, the first set of parameters includes a first measured beam quality of a first beam in the first set of beams, and the second set of parameters includes a second measured beam quality of a second beam in the second set of beams. Alternatively, the first set of parameters includes a first measured beam quality of a first set of beams in the first set of beams, and the second set of parameters includes a second predicted beam quality of a second set of beams in the second set of beams. In this case, the predetermined condition information may include a second predetermined condition. As an example, the first beam may be a first target beam in the first set of beams (i.e., the beam with the highest L1RSRP), and the second beam may refer to the first target beam in the second set of beams. Alternatively, the first beam may be the same as the second beam. In some embodiments, the terminal device 110 may determine the first information based on a comparison between the first measured beam quality and the second measured beam quality. The first information may indicate a first difference between the first measured beam quality and the second measured beam quality. For example, the terminal device 110 may determine a first difference based on the measured L1-RSRP of the top-1 elite supporting beam and the measured L1-RSRP of the top-1 predicted beam. The terminal device 110 may determine whether the first information satisfies a second predetermined condition. If the first information satisfies the second predetermined condition, the terminal device 110 may determine a second status indicating that the second predetermined condition is satisfied. In this case, the second information may include the second status. As an example, the terminal device 110 may determine the second status based on the second predetermined condition, the measured L1-RSRP of the top-1 elite supporting beam, and the measured L1-RSRP of the top-1 predicted beam. Alternatively, the terminal device 110 may determine the second status based on the second predetermined condition, the measured L1-RSRP of the beam of the first set of reference signals, and the predicted L1-RSRP of the beam of the first set of reference signals. The terminal device 110 may report the second status to the network device 120. In this case, in some embodiments, the second status may be transmitted in the UCI or MAC CE.

[0066] In some embodiments, the second predetermined condition may indicate that the first difference is less than or equal to a first threshold. For example, the second predetermined condition may indicate that the difference between the measured L1-RSRP of the top-1 predicted beam and the measured L1-RSRP of the top-1 elite support beam is less than or equal to a threshold (i.e., first threshold) (e.g., 1 dB). As used herein, difference may refer to the difference measurement or the absolute value of the difference measurement. As another example, the second predetermined condition may indicate that the difference between the predicted L1-RSRP of the beam in the first set of reference signals and the measured L1-RSRP of the beam is less than or equal to a threshold (i.e., first threshold) (e.g., 1 dB).

[0067] Alternatively, the second predetermined condition may indicate that the first difference is greater than or equal to a first threshold. As one example, the second predetermined condition may indicate that the difference between the measured L1-RSRP of the top-1 predicted beam and the measured L1-RSRP of the top-1 elite support beam is greater than or equal to a threshold (i.e., a first threshold). As another example, the second predetermined condition may indicate that the difference between the predicted L1-RSRP of a beam of the first set of reference signals and the measured L1-RSRP of the beam is greater than or equal to a threshold (i.e., a first threshold). The second predetermined condition may be applied to a data processing model based on classification or regression.

[0068] In some embodiments, the terminal device 110 may determine the first information based on a comparison between the first set of measured beam qualities and the second set of predicted beam qualities. In this case, the first information may indicate a first set of differences between the first set of measured beam qualities and the second set of predicted beam qualities, or statistics of the first set of differences. For example, the terminal device 110 may compare the first set of measured beam qualities with the second set of predicted beam qualities to determine the first set of differences. If the first information satisfies a second predetermined condition, the terminal device 110 may determine a second status indicating that the second predetermined condition is satisfied. In this case, the second information may include the second status.

[0069] In some embodiments, the second predetermined condition may indicate that a second number of differences in the first set of differences is less than or equal to a second threshold. For example, the second predetermined condition may indicate that the number (or percentage) of beams (i.e., differences) satisfying the above-mentioned first threshold is less than or equal to a threshold (i.e., second threshold) in the first set of reference signals. Alternatively, the second predetermined condition may indicate that a second number of differences in the first set of differences is greater than or equal to a second threshold. For example, the second predetermined condition may indicate that the number (or percentage) of beams (i.e., differences) satisfying the above-mentioned first threshold is greater than or equal to a threshold (i.e., second threshold) in the first set of reference signals. The second difference may refer to a difference less than or equal to a threshold or greater than or equal to a third threshold.

[0070] In some embodiments, the first set of difference statistics may be less than or equal to a fourth threshold. For example, the statistics of the differences between the predicted L1-RSRPs of all beams in the first set of reference signals and the measured L1-RSRPs of the beams are less than or equal to a threshold (i.e., the fourth threshold). Alternatively, the first set of difference statistics may be greater than or equal to the fourth threshold. For example, the statistics of the differences between the predicted L1-RSRPs of all beams in the first set of reference signals and the measured L1-RSRPs of the beams are greater than or equal to a threshold (i.e., the fourth threshold). The statistics may include one or more of the mean, variance, standard deviation, minimum, median, or maximum of the first set of differences.

[0071] In some embodiments, each beam of the first set of reference signals may correspond to a second status. For example, the terminal device 110 may report the second status corresponding to all beams of the first set of reference signals. In other words, the second information may include the second status corresponding to all beams in the first set of reference signals. In this case, the mapping order of the 1-bit fields indicating the second status in the UCI or MAC-CE may be determined based on the beam IDs of the beams corresponding to the second status, for example, based on the ascending (or descending) order of the beam IDs.

[0072] Furthermore, terminal device 110 may report a first status and a second status. For example, the second information may include the first status and the second status. In this case, the first status and the second status may be reported using the same CSI report or MAC-CE. For example, the mapping order of the 1-bit CSI field indicating the first status and the 1-bit CSI field indicating the second status in the UCI may be determined based on Table 4. In some embodiments, terminal device 110 may report one or more second statuses, for example, multiple 1-bit fields may be used to indicate multiple second statuses. [Table 4]

[0073] In some embodiments, terminal device 110 determines an L1-RSRP difference based on the measured L1-RSRP of the top-1 elite supporting beam and the measured L1-RSRP of the top-1 predicted beam. Alternatively, terminal device 110 may determine the measured L1-RSRP of the beam in set A and the predicted L1-RSRP of the beam in set A. In this case, terminal device 110 may report the L1-RSRP difference to network device 120. The second information may include the L1-RSRP difference.

[0074] In some embodiments, the L1-RSRP may be the difference between the measured L1-RSRP of the top-1 predicted beams and the measured L1-RSRP of the top-1 elite support beams. The L1-RSRP difference may be applied to AI / ML models designed based on classification or regression. In some embodiments, the L1-RSRP difference may be the difference between the predicted L1-RSRP of a beam in set A and the measured L1-RSRP of the beam. Alternatively, or additionally, the L1-RSRP difference may be a statistic (e.g., mean, variance, standard deviation, minimum, median, maximum) of the difference between the predicted L1-RSRP of all beams in set A and the measured L1-RSRP of the beam.

[0075] In some embodiments, an M1-bit CSI field may be introduced into the UCI to report the L1-RSRP difference. Alternatively, the MAC-CE including the M1-bit field may indicate the L1-RSRP difference. The M1-bit (CSI) field may include at least one of M2-bit fields indicating a reported value of the L1-RSRP difference (referred to as a "reported L1-RSRP difference") corresponding to the measurement value (absolute value) of the L1-RSRP difference (referred to as a "measured L1-RSRP difference"). For example, the mapping between the reported L1-RSRP difference and the measured L1-RSRP difference may be as shown in Table 5. The intervals between a1 and a2, and a2 and a3 shown in Table 5 may be the same (e.g., determined based on a step size (e.g., 1 dB)) or may be different. The value of M2 (i.e., the bit width for the M2-bit field) is determined based on the value of A, e.g., TIFF2026507525000007.tif735 or TIFF2026507525000008.tif753, or TIFF2026507525000009.tif744. In some embodiments, the 1-bit field indicates whether the (corresponding) L1-RSRP difference measurement is positive or negative. [Table 5]

[0076] Furthermore, when the L1-RSRP difference is L1-RSRP difference 2, each beam in the first set of reference signals may correspond to an L1-RSRP difference. In this case, the terminal device 110 may need to report the L1-RSRP differences corresponding to all beams in the first set of reference signals. In this case, the mapping order of the M1-bit field indicating the L1-RSRP difference in the UCI or MAC-CE is determined based on the beam ID of the beam corresponding to the L1-RSRP difference, for example, in ascending (or descending) order of the beam IDs. When the L1-RSRP difference is L1-RSRP difference 3, the terminal device 110 may report multiple L1-RSRP differences, for example, the average and variance of the differences between the predicted L1-RSRP of all beams in the first set of reference signals and the measured L1-RSRP of the beam.

[0077] In some embodiments, the terminal device 110 may determine first information based on a comparison between a first set of measured beam qualities and a second set of predicted beam qualities. The first information may indicate a first set of differences between the first set of measured beam qualities and the second set of predicted beam qualities. The terminal device 110 may determine a first number of differences based on the first set of differences and a second predetermined condition. In this case, the second information transmitted by the terminal device 110 may include the first number of differences. Alternatively, or additionally, the terminal device 110 may determine a second set of differences based on the first set of differences and the second predetermined condition. The second set of differences may include a subset of differences from the first set of differences that satisfy the second predetermined condition. In this case, the second information may also include the second set of differences. For example, the terminal device 110 may determine an L1-RSRP difference (e.g., L1-RSRP difference 2) corresponding to all beams in the first set of reference signals based on the measured L1-RSRPs of all beams in the first set of reference signals and the predicted L1-RSRPs of the beams. The terminal device 110 may determine an L1-RSRP number difference that satisfies a second predetermined condition. The L1-RSRP difference that satisfies the predetermined criterion may be determined based on the predetermined criterion and the L1-RSRP difference. The terminal device 110 may report an L1-RSRP number difference that satisfies the second predetermined condition (simply referred to as a "satisfied L1-RSRP number difference"). Optionally, the terminal device 110 may also report an L1-RSRP difference that satisfies the predetermined criterion (simply referred to as a "satisfied L1-RSRP difference").

[0078] In some embodiments, the second predetermined condition may include the difference being less than or equal to a fifth threshold. Alternatively, the second predetermined condition may include the difference being greater than or equal to a fifth threshold. In some embodiments, an M3-bit CSI field may be introduced into the UCI to report the difference in the number of satisfied L1-RSRPs. Alternatively, a MAC-CE including an M3-bit field may be transmitted to indicate the difference in the number of satisfied L1-RSRPs. The value of M3 (i.e., the bit width for the M3-bit field) may be determined by the number of beams (e.g., TIFF2026507525000011.tif774, or Determined based on TIFF2026507525000012.tif765.

[0079] In some embodiments, terminal device 110 may report the difference in the number of filled L1-RSRPs and the difference in the number of filled L1-RSRPs simultaneously, i.e., the difference in the number of filled L1-RSRPs and the difference in the number of filled L1-RSRPs are reported by using the same CSI report or MAC-CE. Furthermore, terminal device 110 may report the difference in the number of filled L1-RSRPs in Part 1 of the CSI report and the difference in the number of filled L1-RSRPs in Part 2 of the CSI report. In this case, terminal device 110 and network device 120 may determine the difference in the number of filled L1-RSRPs reported in Part 2 of the CSI report, which may be determined based on (e.g., equal to) the difference in the number of filled L1-RSRPs indicated in Part 1 of the CSI report. For example, Part 1 of the CSI report includes one M3-bit CSI field, and Part 2 of the CSI report includes N1 M1-bit fields. The value of N1 may be determined based on the difference in the number of filled L1-RSRPs indicated in Part 1 of the CSI report.

[0080] In some other embodiments, in addition to the satisfied L1-RSRP difference, the beam ID corresponding to the satisfied L1-RSRP difference may be reported in Part 2 of the CSI report. For example, the mapping order of the M3-bit CSI field indicating the difference in the number of satisfied L1-RSRPs in the UCI, the M1-bit CSI field indicating the satisfied L1-RSRP difference, and the CSI field indicating the beam ID (i.e., CRI or SSBRI) may be determined based on Table 6, assuming that the difference in the number of satisfied L1-RSRPs is 4. In this case, the mapping order of the beam ID and the satisfied L1-RSRP difference may be determined based on the beam ID (of the beam corresponding to the satisfied L1-RSRP difference), for example, based on the ascending (or descending) order of the beam ID. [Table 6]

[0081] The terminal device 110 may also determine and report the number of beams that satisfy a second predetermined condition. The second predetermined condition may include an L1-RSRP difference corresponding to the beam being less than or equal to a threshold, or an L1-RSRP difference corresponding to the beam being greater than or equal to a threshold. That is, the L1-RSRP difference corresponding to the beam may be one of an L1-RSRP difference corresponding to the beam being less than or equal to a threshold, or an L1-RSRP difference corresponding to the beam being greater than or equal to a threshold. In other words, the above-mentioned "satisfied L1-RSRP number difference" and "satisfied L1-RSRP difference" can be replaced with "the number of beams that satisfy a predefined criterion" and "L1-RSRP difference corresponding to the beam."

[0082] In some embodiments, the first set of parameters includes a first set of reference signals, and the second set of parameters includes a second set of reference signals. The predetermined condition information may include a first predetermined condition. In this case, terminal device 110 may determine first information indicating whether the first set of reference signals overlaps with the second set of reference signals based on a comparison of the first set of reference signals with the second set of reference signals. If the first information satisfies the first predetermined condition, terminal device 110 may determine a first status indicating that the predetermined condition is satisfied. In this case, terminal device 110 may transmit second information including the first status. In some embodiments, the second information may be transmitted in UCI or MAC CE.

[0083] In some embodiments, the first predetermined condition indicates that a first target reference signal in the first set of reference signals overlaps with a reference signal in the second set. Alternatively, the first predetermined condition may indicate that a first target reference signal in the first set of reference signals does not overlap with a reference signal in the second set. In some other embodiments, the first predetermined condition may indicate that a second target reference signal in the second set of reference signals overlaps with a reference signal in the first set. Alternatively, the first predetermined condition may indicate that a second target reference signal in the second set of reference signals does not overlap with a reference signal in the first set.

[0084] In some embodiments, terminal device 110 may determine the third information based on the first set of reference signals and the second set of reference signals. The third information may indicate which reference signals in the first set of reference signals overlap with the first target reference signal in the second set of reference signals. In this case, the second information transmitted to network device 120 may include the first status, the third information, and information on the first set of reference signals. Alternatively, if the first status indicates that the first target reference signal in the first set of reference signals does not overlap with any reference signal in the second set, the third information may be omitted.

[0085] In some embodiments, the first set of parameters includes a first measured signal quality of a first reference signal in the first set of reference signals, and the second set of parameters includes a second measured signal quality of a second reference signal in the second set of reference signals. Alternatively, the first set of parameters may include measured signal qualities of a first set of reference signals in the first set of reference signals, and the second set of parameters may include predicted signal qualities of a second set of reference signals in the second set of reference signals. The predetermined condition information may include a second predetermined condition. In some embodiments, the first reference signal may refer to a first target reference signal in the first set of reference signals, and the second reference signal may refer to a first target reference signal in the second set of reference signals. Alternatively, the first reference signal may be the same as the second reference signal.

[0086] In some embodiments, terminal device 110 may determine first information based on a comparison of the first measured signal quality and the second measured signal quality. The first information may indicate a first difference between the first measured signal quality and the second measured signal quality. If the first information satisfies a second predetermined condition, terminal device 110 may determine a second status indicating that the second predetermined condition is satisfied. Terminal device 110 may transmit the second information including the second status to network device 120. In some embodiments, the second predetermined condition indicates one of the first difference being less than or equal to a first threshold or the first difference being greater than or equal to a first threshold.

[0087] In some embodiments, terminal device 110 may determine first information based on a comparison between the first set of measured signal qualities and the second set of predicted signal qualities. The first information may indicate a first set of differences between the first set of measured signal qualities and the second set of predicted signal qualities, or statistics of the first set of differences. If the first information satisfies a second predetermined condition, terminal device 110 may determine a second status indicating that the second predetermined condition is met. In this case, the second information transmitted to network device 120 may include the second status. In some embodiments, the second predetermined condition may indicate one of: a second number of differences in the first set of differences being less than or equal to a second threshold; or a second number of differences in the first set of differences being greater than or equal to a second threshold. The second difference may refer to a difference less than or equal to a threshold, or greater than or equal to a third threshold. Alternatively, the second predetermined condition may indicate that the statistics of the first set of differences are less than or equal to a fourth threshold, or that the statistics are greater than or equal to the fourth threshold. In some embodiments, the second information includes the first status and the second status.

[0088] In some other embodiments, terminal device 110 may determine the first information based on a comparison of the first set of measured signal qualities and the second set of predicted signal qualities. The first information may indicate a first set of differences between the first set of measured signal qualities and the second set of predicted signal qualities. Terminal device 110 may further determine a first number of differences based on the first set of differences and a second predetermined condition. In this case, terminal device 110 may transmit second information including the first number of differences to network device 120. In some embodiments, the second predetermined condition may include the difference being less than or equal to a fifth threshold. Alternatively, the second predetermined condition may include the difference being greater than or equal to a fifth threshold.

[0089] In some embodiments, the first set of parameters may include first channel state information, and the second set of parameters may include second channel state information. The predetermined condition may include a third predetermined condition. For example, the terminal device 110 may be provided with at least one of a CSI-RS or an AI / ML model (or a CSI generator and a CSI reconstructor) that is configuration or instruction information for model monitoring. Based on the received CSI-RS, the terminal device 110 may determine a precoding matrix or raw channel that can reflect the channel (information / quality / condition). The precoding matrix may indicate a precoding matrix indication (PMI) such as a group of eigenvectors or eType II. The raw channel (i.e., a full Tx*Rx multiple-input multiple-output (MIMO) channel) may refer to the raw channel in the frequency domain, the time delay domain, or the transform delay / frequency domain. The determined precoding matrix or raw channel may be referred to as the “input CSI” or the “target CSI.” Based on the input CSI and the data processing model, the terminal device 110 may determine a recovered precoding matrix or raw channel. Specifically, the input CSI is used as an input of the data processing model, and the output of the data processing model is a reconstructed precoding matrix or raw channel, which may be referred to as "output CSI."

[0090] In some embodiments, terminal device 110 may determine first information based on a comparison between the first channel state information and the second channel state information. The first information may indicate a squared generalized cosine similarity (SGCS) or a normalized mean squared error (NMSE). The SGCS may include one of an SGCS associated with or corresponding to a rank (e.g., rank=1), a layer, or a data processing model, an averaged SGCS corresponding to a rank (e.g., rank=1, 2, 3, 4), a list of layers or data processing models, or a statistic of an SGCS corresponding to a rank, a layer, or a list of data processing models. The NMSE may include one of an NMSE associated with or corresponding to a data processing model, or a statistic of an NMSE corresponding to a list of data processing models. Terminal device 110 may determine whether the first information satisfies a third predetermined condition. If the first information satisfies the third predetermined condition, terminal device 110 may determine a third status indicating that the third predetermined condition is satisfied. In this case, the second information transmitted to network device 120 may include the third status. For example, terminal device 110 may determine an SGCS or NMSE based on the input CSI and the corresponding output CSI. Terminal device 110 may further determine a third status based on a third predefined criterion and the SGCS or NMSE. Terminal device 110 may report the third status to network device 120.

[0091] In some embodiments, the third predetermined condition indicates that the SGCS is greater than or equal to a sixth threshold. Alternatively, the third predetermined condition may indicate that the SGCS is less than or equal to a sixth threshold. For determining the rank, layer, or data processing model, the rank, layer, or data processing model (i.e., the rank, layer, or data processing model) can be provided by configuration or instruction information, for example, an indicator of the rank, layer, or data processing model. Optionally, the rank, layer, or AI / ML model can be a predefined rank, layer, or AI / ML model based on, for example, the minimum (or maximum) rank, layer, or model ID (in the list of configured or instruction ranks, layers, or AI / ML models).

[0092] In some embodiments, the third predetermined condition may indicate that an average or weighted SGCS corresponding to a rank, a layer, or a list of data processing models is equal to or greater than a threshold. The list of ranks, layers, or data processing models may be provided by configuration or instruction information, for example, the list of ranks is provided in a configuration related to "RI-Restriction" (e.g., ri-Restriction, type II-RI-Restriction, type II-RI-Restriction-r16). The list of ranks, layers, or data processing models may correspond to the configured or indicated ranks, layers, or AI / ML models. In some other embodiments, the third predetermined condition may indicate that an average or weighted SGCS corresponding to a rank, a layer, or a list of AI / ML models is equal to or less than a threshold.

[0093] In some embodiments, the third predetermined condition may indicate that a statistic (e.g., mean, variance, standard deviation, minimum, median, maximum) of the SGCS corresponding to the rank, layer, or list of AI / ML models is greater than or equal to a threshold. Alternatively, or additionally, the third predetermined condition may indicate that a statistic of the SGCS corresponding to the rank, layer, or list of AI / ML models is less than or equal to a threshold.

[0094] In some embodiments, the third predetermined condition may indicate that the number of SGCSs that are greater than or equal to the sixth threshold is greater than or equal to the tenth threshold. Alternatively, or additionally, the third predetermined condition may indicate that the number of SGCSs that are greater than or equal to the sixth threshold is less than or equal to the tenth threshold.

[0095] Alternatively, or additionally, the third predetermined condition may indicate that the NMSE is less than or equal to a ninth threshold, or that the NMSE is greater than or equal to the ninth threshold. In some other embodiments, the third predetermined condition may indicate that the number of NMSEs less than or equal to the seventh threshold is greater than or equal to an eleventh threshold. In some embodiments, the third predetermined condition may indicate that the number of NMSEs less than or equal to the seventh threshold is less than or equal to an eleventh threshold.

[0096] In some embodiments, each rank / layer / AI / ML model may correspond to a third status. In this case, terminal device 110 may need to report the third status corresponding to all ranks, layers, or AI / ML models that it configures or indicates. In this case, the mapping order of the 1-bit fields indicating the third status in the UCI or MAC-CE may be determined based on the indicator of the rank, layer, or AI / ML model corresponding to the third status, for example, based on ascending (or descending) order of the indicator. In some embodiments, terminal device 110 may report at least one third status, for example, multiple 1-bit fields may be used to indicate multiple third states.

[0097] In some embodiments, terminal device 110 may determine an SGCS or NMSE based on the input CSI and the corresponding output CSI. In this case, terminal device 110 may report the SGCS or NMSE to network device 120. In some embodiments, to report the SGCS or NMSE, a new M4-bit CSI field may be introduced in the UCI, or a new MAC-CE including an M4-bit field indicating the SGCS or NMSE may be introduced, i.e., the SGCS or NMSE may be defined by an M4-bit value. As an example, the M4-bit field may indicate a reported value of SGCS or NMSE (referred to as a "reported SGCS or NMSE") corresponding to a measurement value of SGCS or NMSE (referred to as a "measured SGCS or NMSE"). For example, the mapping between the reported SGCS or NMSE and the measured SGCS or NMSE may be as shown in Tables 7 and 8 below. In some embodiments, the intervals between b0 and b1, b1 and b2, ..., or c1 and c2, c2 and c3, etc., can be the same (e.g., determined based on a step size) or different. The value of M4 (i.e., the bit width for the M4-bit field) can be determined based on the value of B or C, for example: TIFF2026507525000014.tif544, or TIFF2026507525000015.tif557, or TIFF2026507525000016.tif535. [Table 7] [Table 8]

[0098] Furthermore, in some embodiments, when each rank, layer, or AI / ML model corresponds to an SGCS or NMSE, terminal device 110 may be required to report the SGCS or NMSE corresponding to all ranks, layers, or AI / ML models that it sets or indicates. In this case, the mapping order of the M4-bit field indicating the SGCS or NMSE in the UCI or MAC-CE may be determined based on the indicator of the rank, layer, or AI / ML model corresponding to the SGCS or NMSE, for example, based on the ascending (or descending) order of the indicator of the rank, layer, or AI / ML model.

[0099] In some embodiments, terminal device 110 may determine an SGCS or NMSE based on a comparison between the first channel state information and the second channel state information. Terminal device 110 may determine a first set of SGCSs or NMSEs based on the SGCSs or NMSEs and a predetermined condition. In this case, in some embodiments, the second information transmitted by terminal device 110 may include one or more of an indicator of the rank, layer, or data processing model of the first set of SGCSs or NMSEs, or an indicator of the rank, layer, or data processing model of the first set of SGCSs or NMSEs. Alternatively, the second information transmitted by terminal device 110 may include one or more of an indicator of the rank, layer, or data processing model of the SGCSs or NMSEs, or an SGCS or NMSE. In some embodiments, the third predetermined condition may comprise the first set of SGCSs including N1 SGCSs having the largest values ​​in the SGCSs. Alternatively, the third predetermined condition may comprise the first set of NMSEs including N1 NMSEs having the smallest values ​​in the NMSEs. N1 may be an integer.

[0100] In some embodiments, terminal device 110 may determine, based on the input CSI and the corresponding output CSI, an SGCS or NMSE corresponding to a set or indicated rank, layer, or AI / ML model. Terminal device 110 may determine a first set of SGCS or NMSE based on the determined SGCS or NMSE. In this case, terminal device 110 may report to network device 120 an indicator of the rank, layer, or AI / ML model corresponding to the first set of SGCS or NMSE (simply referred to as a “first set of indicators”) and the first set of SGCS or NMSE (optional).

[0101] In some embodiments, the first set of SGCSs or NMSEs may include SGCSs or NMSEs corresponding to the set or indicated rank, layer, or AI / ML model. This means that the first set of indicators includes indicators of the set or indicated rank, layer, or AI / ML model. Alternatively, the first set of SGCSs or NMSEs may include the top-N2 SGCSs or NMSEs among the SGCSs or NMSEs corresponding to the set or indicated rank, layer, or AI / ML model. In some embodiments, the top-N2 SGCSs among the SGCSs may refer to the N2 SGCSs with the largest SGCSs in the SGCS. Alternatively, the top-N2 NMSEs among the NMSEs may refer to the NMSEs with the smallest NMSEs in the NMSE. The value of N2 is provided by the new setting or indication information. For example, the value of N2 may be a positive integer not greater than the number of set or indicated ranks, layers, or AI / ML models.

[0102] In some embodiments, a new or legacy M5-bit CSI field can be introduced in the UCI to report one indicator of the first set of indicators, or a new MAC-CE including an M5-bit field can be introduced to indicate the indicator, e.g., reusing the legacy "RI" field to indicate the rank indicator and using a new "Layer ID" or "Model ID" field to indicate the layer, AI / ML model indicator. The value of M5 can set or indicate the number of ranks, layers, AI / ML models, e.g., It may be determined based on TIFF2026507525000019.tif5111.

[0103] In some embodiments, to report the first set of indicators, an N2 M5-bit field may be used to indicate the first set of indicators. Specifically, the mapping order of the N2 M5-bit field may be determined based on the values ​​of the first set of SGCS or NMSE, for example, descending order (i.e., from largest to smallest) for SGCS and ascending order for NMSE, as shown in Table 9. [Table 9]

[0104] Optionally, in addition to the first set of indicators, terminal device 110 can also report the first set of SGCS or NMSE by using the same CSI report or MAC-CE. For example, the mapping order of the N2 M5-bit CSI field indicating the first set of indicators and the N2 M4-bit CSI field indicating the first set of SGCS or NMSE in the UCI can be determined based on Table 10. [Table 10]

[0105] In some embodiments, the terminal device 110 may determine the number or percentage of occurrences of the first status based on multiple monitoring results of the data processing model. In this case, the second information transmitted from the terminal device 110 to the network device 120 may indicate the number or percentage of occurrences of the first status. As an example, after completing N (N>1) model monitorings, the terminal device 110 may determine N monitoring results. Specifically, for each model monitoring, the terminal device 110 needs to determine whether the first status has occurred based on the beam IDs of the top-K1 elite support beams and the beam IDs of the top-K2 predicted beams determined during this model monitoring. The terminal device 110 may determine the number or percentage of occurrences of the first status based on the N monitoring results. In this case, the terminal device 110 may report the number or percentage of occurrences to the network device 120.

[0106] In some embodiments, an M6-bit CSI field can be introduced in the UCI to report the number, or a MAC-CE including an M6-bit field can be introduced to indicate the number. The value of M6 (i.e., the bit width for the M6-bit field) can be determined based on the value of N (i.e., the number of model monitoring), for example: TIFF2026507525000022.tif553, or The file is TIFF2026507525000023.tif444.

[0107] Alternatively, or additionally, for percentage reporting similar to L1-RSRP difference, an M7-bit CSI field can be introduced in the UCI, and a MAC-CE including an M7-bit field can be introduced to indicate a percentage report value (referred to as "reported percentage") corresponding to a percentage measurement or determination value (referred to as "measured percentage"). For example, a mapping between reported L1-RSRP difference and measured L1-RSRP difference can be as shown in Table 11. In some embodiments, the intervals between a1 and a2, a2 ​​and a3, etc. can be the same (e.g., determined based on a step size (e.g., 20%)) or different. The value of M7 (i.e., the bit width for the M7-bit field) can be determined based on the value of A, for example, TIFF2026507525000024.tif436, or TIFF2026507525000025.tif553, or The file is TIFF2026507525000026.tif444. [Table 11]

[0108] In some embodiments, terminal device 110 may determine the number or percentage of occurrences of the first status based on multiple monitoring results of the data processing model. Terminal device 110 may determine whether the number or percentage of occurrences of the first status satisfies a fourth predetermined condition. If the number or percentage of occurrences of the first status satisfies the fourth predetermined condition, terminal device 110 may determine a fourth status indicating that the fourth predetermined condition is satisfied. In this case, the second information transmitted by terminal device 110 to network device 120 may include the fourth status. In some embodiments, the second information may be transmitted in UCI. Alternatively, the second information may be transmitted in MAC CE. In some embodiments, the fourth predetermined condition may indicate that the number or percentage of occurrences of the first status is equal to or greater than a twelfth threshold. Alternatively, the fourth predetermined condition may indicate that the number or percentage of occurrences of the first status is equal to or less than a twelfth threshold.

[0109] Alternatively, the terminal device 110 may determine the number or percentage of occurrences of the second status based on multiple monitoring results of the data processing model. As an example, after completing N (N>1) model monitoring sessions, the terminal device 110 may determine N monitoring results. Specifically, for each model monitoring session, the terminal device 110 needs to determine whether the second status occurs. The terminal device 110 may determine the number or percentage of occurrences of the second status based on the N monitoring results. In some embodiments, the terminal device 110 may transmit second information indicating the number or percentage of occurrences of the second status to the network device 120. Alternatively, the terminal device 110 may determine whether the number or percentage of occurrences of the second status satisfy a fifth predetermined condition. If the number or percentage of occurrences of the second status satisfy the fifth predetermined condition, the terminal device 110 may determine a fifth status indicating that the fifth predetermined condition is satisfied. In this case, the second information transmitted from the terminal device 110 to the network device 120 may include the fifth status. In some embodiments, the number or rate of occurrence of the second status may be greater than or equal to the thirteenth threshold. Alternatively, the number or rate of occurrence of the second status is less than or equal to the thirteenth threshold.

[0110] Alternatively, the terminal device 110 may determine the statistical RSRP difference based on multiple monitoring results of the data processing model. In this case, the terminal device 110 may transmit second information including the statistical RSRP difference to the network device 120. The statistical RSRP difference may be one of the mean, variance, standard deviation, minimum, median, maximum, and CDF-related quantities of the L1-RSRP difference. As an example, after completing N (N>1) model monitoring rounds, the terminal device 110 may determine N monitoring results. Specifically, for each model monitoring round, the terminal device 110 needs to determine an L1-RSRP difference. The terminal device 110 may determine the statistical L1-RSRP difference based on the N monitoring results (i.e., N L1-RSRP differences). For example, the statistical L1-RSRP difference may be a statistic (e.g., mean, variance, standard deviation, minimum, median, maximum, CDF related quantity (e.g., L1-RSRP difference corresponding to 90%)) of N L1-RSRP differences (e.g., L1-RSRP difference 1). In this case, the terminal device 110 may report the statistical L1-RSRP difference to the network device 120.

[0111] In some embodiments, the terminal device 110 may determine the number or percentage of occurrences of the third status based on multiple monitoring results of the data processing model. For example, after completing N (N>1) model monitoring rounds, the terminal device 110 may determine N monitoring results. Specifically, for each model monitoring round, the terminal device 110 needs to determine whether the third status occurs. In some embodiments, the second information transmitted from the terminal device 110 to the network device 120 may include the number or percentage of occurrences of the third status. Alternatively, the terminal device 110 may determine whether the number or percentage of occurrences of the third status satisfies a sixth predetermined condition. If the number or percentage of occurrences of the third status satisfies the sixth predetermined condition, the terminal device 110 may determine a sixth status indicating that the sixth predetermined condition is satisfied. In this case, the terminal device 110 may transmit the second information including the sixth status.

[0112] In some embodiments, the sixth predetermined condition may indicate that the number or percentage of occurrences of the third status is greater than or equal to a fourteenth threshold. Alternatively, the sixth predetermined condition may indicate that the number or percentage of occurrences of the third status is less than or equal to a fourteenth threshold.

[0113] In some embodiments, for each model monitoring, the terminal device 110 needs to determine whether a third status corresponding to a rank, layer, or AI / ML model occurs. Thus, the terminal device 110 can determine at least one of the number or percentage of occurrences of the third status based on the N monitoring results, where each number or percentage of occurrences corresponds to a rank, layer, or AI / ML model. The terminal device 110 can then report the number or percentage of at least one occurrence. Optionally, the terminal device 110 can also determine and report at least one sixth status based on the number or percentage of at least one occurrence, where each sixth status corresponds to a rank, layer, or AI / ML model.

[0114] Alternatively or additionally, terminal device 110 may report the sixth status corresponding to all ranks, layers, or AI / ML models that it configures or indicates. The mapping order of the 1-bit fields indicating the sixth status in the UCI or MAC-CE may be determined based on the indicators of the ranks, layers, or AI / ML models corresponding to the sixth status.

[0115] In some embodiments, the terminal device 110 may determine at least one of a statistical SGCS or a statistical NMSE based on multiple monitoring results of a data processing model. In this case, the second information transmitted from the terminal device 110 to the network device 120 may include at least one of a statistical SGCS or a statistical NMSE. As an example, after completing N (N>1) model monitorings, the terminal device 110 may determine N monitoring results. Specifically, for each model monitoring, the terminal device 110 may determine at least one SGCS or NMSE. Furthermore, each SGCS may correspond to a rank, a layer, or an AI / ML model. In some embodiments, the terminal device 110 determines at least one statistical SGCS or NMSE based on the N monitoring results (i.e., the determined SGCS or NMSE). Furthermore, each statistical SGCS may correspond to a rank, a layer, or an AI / ML model. In this case, the terminal device 110 may report the at least one statistical SGCS or NMSE to the NW. The statistical NMSE may be a statistic (eg, mean, variance, standard deviation, minimum, median, maximum) of the NMSEs of N.

[0116] In some embodiments, when a determined SGCS corresponds to a rank, a layer, or an AI / ML model, the statistical SGCS (corresponding to / associated with the rank, layer, or AI / ML model) may be a statistic of the SGCS corresponding to the rank, layer, or AI / ML model. Optionally, the statistical SGCS may be a statistic of the SGCS corresponding to all (set or indicated) ranks, layers, or AI / ML models. Alternatively, when the terminal device 110 determines one SGCS (e.g., an average SGCS or a weighted SGCS) during model monitoring, the statistical SGCS may be a statistic of N SGCSs.

[0117] According to the embodiment described with reference to Figure 2, the terminal device or the network device knows how to report the performance (metric) of the AI / ML model. Furthermore, based on the reported performance-related information, the network device can make rational and systematic decisions related to the AI / ML model for the UE and provide rational configuration or instruction information related to the AI / ML model for the terminal device.

[0118] 3 illustrates a flowchart of a communication method 300 implemented in a terminal device according to some embodiments of the present disclosure. In some embodiments, the method 300 may be implemented by the terminal device 110 of FIG.

[0119] In some embodiments, terminal device 110 may receive a first set of reference signals from a network device. Terminal device 110 may perform first measurements on the first set of reference signals.

[0120] In block 310, the terminal device 110 determines a first set of parameters based on first measurements on the first set of reference signals. For example, in some embodiments, the terminal device 110 may determine the first set of beams based on RSRPs of the first set of reference signals. In this case, the first set of parameters may include the first set of beams. Alternatively, the first set of parameters may include first channel state information.

[0121] In block 320, the terminal device 110 determines a second set of parameters based on the data processing model and second measurements on the second set of reference signals. For example, in some embodiments, the terminal device 110 may determine a second set of beams based on the RSRPs of the second set of reference signals. In this case, the second set of parameters may include the second set of beams. Alternatively, the second set of parameters may include second channel state information. For example, the measured L1-RSRPs of beams in the second set of reference signals are used as inputs (i.e., one input sample) of the data processing model. The beam IDs of the top-K beams of beams in the first set of reference signals may be outputs of the data processing model.

[0122] In block 330, terminal device 110 determines first information based on a comparison of the first set of parameters and the second set of parameters.

[0123] In block 340, the terminal device 110 determines second information based on the predetermined condition information and the first information, wherein the second information indicates at least one of status information related to the performance metric, a numerical value related to the performance metric, a percentage related to the performance metric, or the first information.

[0124] In block 350, terminal device 110 transmits the second information to the network device. In some embodiments, the second information may be transmitted in uplink control information. Alternatively, or additionally, the second information may be in a MAC CE.

[0125] In some embodiments, the first set of parameters comprises a first set of beams and the second set of parameters comprises a second set of beams. In some embodiments, the predetermined condition information comprises a first predetermined condition.

[0126] In some embodiments, terminal device 110 may determine first information indicating whether the first set of beams overlaps with the second set of beams based on a comparison of the first set of beams and the second set of beams. In some embodiments, terminal device 110 may determine whether the first information satisfies a first predetermined condition. In some embodiments, if the first information satisfies the first predetermined condition, terminal device 110 may determine a first status indicating that the first predetermined condition is satisfied. In some embodiments, terminal device 110 may transmit second information including the first status to a network device.

[0127] In some embodiments, the first predetermined condition indicates at least one of: a first target beam in the first set of beams overlapping with a beam in the second set; a first target beam in the first set of beams not overlapping with a beam in the second set; a second target beam in the second set of beams overlapping with a beam in the first set; or a second target beam in the second set of beams not overlapping with a beam in the first set.

[0128] In some embodiments, the terminal device 110 can determine the third information based on the first set of beams and the second set of beams. The third information may indicate which beams in the first set of beams overlap with the first target beam in the second set of beams. In some embodiments, the terminal device 110 may transmit the second information, including the first status, the third information, and beam information of the first set of beams, to the network device. In some embodiments, if the first status indicates that the first target beam in the first set of beams does not overlap with any beams in the second set, the third information is omitted.

[0129] In some embodiments, the first set of parameters includes a first measured beam quality of a first beam in the first set of beams and the second set of parameters includes a second measured beam quality of a second beam in the second set of beams. In some embodiments, the first set of parameters includes measured beam qualities of a first set of beams in the first set of beams and the second set of parameters includes predicted beam qualities of a second set of beams in the second set of beams. In some embodiments, the predetermined condition information includes a second predetermined condition.

[0130] In some embodiments, the first beam refers to the beam in the first set of beams that has the highest beam quality, and the second beam refers to the beam in the second set of beams that has the highest beam quality, In some embodiments, the first beam is the same as the second beam.

[0131] In some embodiments, the terminal device 110 may determine first information indicating a first difference between the first measured beam quality and the second measured beam quality based on a comparison of the first measured beam quality and the second measured beam quality. In some embodiments, the terminal device 110 may determine whether the first information satisfies a second predetermined condition. In some embodiments, if the first information satisfies the second predetermined condition, the terminal device 110 may determine a second status indicating that the second predetermined condition is satisfied. In some embodiments, the terminal device 110 may transmit the second information including the second status to the network device.

[0132] In some embodiments, the second predetermined condition indicates one of the first difference being less than or equal to a first threshold, or the first difference being greater than or equal to a first threshold.

[0133] In some embodiments, the terminal device 110 may determine, based on a comparison between the first set of measured beam qualities and the second set of predicted beam qualities, first information indicating a first set of differences between the first set of measured beam qualities and the second set of predicted beam qualities, or statistics of the first set of differences. In some embodiments, the terminal device 110 may determine whether the first information satisfies a second predetermined condition. In some embodiments, if the first information satisfies the second predetermined condition, the terminal device 110 may determine a second status indicating that the second predetermined condition is satisfied. In some embodiments, the terminal device 110 may transmit the second information including the second status to the network device.

[0134] In some embodiments, the second predetermined condition indicates one of: a second number of differences in the first set of differences being less than or equal to a second threshold; or a second number of differences in the first set of differences being greater than or equal to a second threshold. The second difference may refer to a difference that is less than or equal to a threshold, or a difference that is greater than or equal to a third threshold, or a statistic of the first set of differences being less than or equal to a fourth threshold, or a statistic that is greater than or equal to the fourth threshold. In some embodiments, the second information includes a first status and a second status.

[0135] In some embodiments, the terminal device 110 may determine first information indicating a first set of differences between the first set of measured beam qualities and the second set of predicted beam qualities based on a comparison of the first set of measured beam qualities and the second set of predicted beam qualities. In some embodiments, the terminal device 110 may determine a first number of differences based on the first set of differences and a second predetermined condition. In some embodiments, the terminal device 110 may transmit second information including the first number of differences to the network device. In some embodiments, the second predetermined condition includes any one of the following: the difference being less than or equal to a fifth threshold; or the difference being greater than or equal to a fifth threshold.

[0136] In some embodiments, the first set of parameters includes first channel condition information and the second set of parameters includes second channel condition information. In some embodiments, the predetermined condition information includes a third predetermined condition.

[0137] In some embodiments, terminal device 110 may determine first information indicative of a squared generalized cosine similarity (SGCS) or a normalized mean squared error (NMSE) based on a comparison of the first channel state information and the second channel state information. In some embodiments, terminal device 110 may determine whether the first information satisfies a third predetermined condition. In some embodiments, if the first information satisfies the third predetermined condition, terminal device 110 may determine a third status indicating that the third predetermined condition is satisfied. In some embodiments, terminal device 110 may transmit second information including the third status to a network device.

[0138] In some embodiments, the SGCS comprises any one of an SGCS associated / corresponding to a rank, layer, or data processing model, an averaged SGCS corresponding to a list of ranks, layers, or data processing models, or statistics of SGCS corresponding to a list of ranks, layers, or data processing models. In some embodiments, the NMSE comprises any one of an NMSE associated with or corresponding to a data processing model, or statistics of NMSE corresponding to a list of data processing models.

[0139] In some embodiments, the third predetermined condition indicates at least one of: SGCS being greater than or equal to a sixth threshold; SGCS being less than or equal to a sixth threshold; NMSE being less than or equal to a ninth threshold; NMSE being greater than or equal to a ninth threshold; the number of SGCSs greater than or equal to the sixth threshold being greater than or equal to a tenth threshold; the number of SGCSs greater than or equal to the sixth threshold being less than or equal to the tenth threshold; the number of NMSEs less than or equal to a seventh threshold being greater than or equal to an eleventh threshold; or the number of NMSEs less than or equal to the seventh threshold being less than or equal to the eleventh threshold.

[0140] In some embodiments, terminal device 110 may determine an SGCS or NMSE based on a comparison between the first channel state information and the second channel state information. In some embodiments, terminal device 110 may determine a first set of SGCSs or NMSEs based on the SGCSs or NMSEs and a predetermined condition. In some embodiments, terminal device 110 may transmit second information to a network device, the second information including at least one of a rank of the first set of SGCSs or NMSEs, an indicator of a layer or data processing model, or the first set of SGCSs or NMSEs. In some embodiments, terminal device 110 may transmit second information to a network device, the second information including at least one of a rank of the SGCSs or NMSEs, an indicator of a layer or data processing model, or the SGCSs or NMSEs.

[0141] In some embodiments, the third predetermined condition includes at least one of: the first set of SGCSs includes N1 SGCSs having the largest values ​​in the SGCSs, or the first set of NMSEs includes N1 NMSEs having the smallest values ​​in the NMSEs, where N1 is an integer.

[0142] In some embodiments, terminal device 110 may determine the number or percentage of occurrences of the first status based on the multiple monitoring results of the data processing model. In some embodiments, terminal device 110 may transmit second information indicating the number or percentage of occurrences of the first status to the network device.

[0143] In some embodiments, terminal device 110 may determine the number or percentage of occurrences of the first status based on multiple monitoring results of the data processing model. In some embodiments, terminal device 110 may determine whether the number or percentage of occurrences of the first status satisfies a fourth predetermined condition. In some embodiments, terminal device 110 may determine a fourth status indicating that the fourth predetermined condition is satisfied in accordance with determining that the number or percentage of occurrences of the first status satisfies the fourth predetermined condition. In some embodiments, terminal device 110 may transmit second information including the fourth status to the network device.

[0144] In some embodiments, the fourth predetermined condition indicates one of the following: the number or percentage of occurrences of the first status is greater than or equal to a twelfth threshold; or the number or percentage of occurrences of the first status is less than or equal to a twelfth threshold.

[0145] In some embodiments, terminal device 110 may determine the number or percentage of occurrences of the second status based on the multiple monitoring results of the data processing model. In some embodiments, terminal device 110 may transmit second information indicating the number or percentage of occurrences of the second status to the network device.

[0146] In some embodiments, terminal device 110 may determine the number or percentage of occurrences of the second status based on multiple monitoring results of the data processing model. In some embodiments, terminal device 110 may determine whether the number or percentage of occurrences of the second status satisfies a fifth predetermined condition. In some embodiments, if the number or percentage of occurrences of the second status satisfies the fifth predetermined condition, terminal device 110 may determine a fifth status indicating that the fifth predetermined condition is satisfied. In some embodiments, terminal device 110 may transmit second information including the fifth status to a network device.

[0147] In some embodiments, the fifth predetermined condition indicates one of the following: the number or percentage of occurrences of the second status is greater than or equal to a thirteenth threshold; or the number or percentage of occurrences of the second status is less than or equal to a thirteenth threshold.

[0148] In some embodiments, terminal device 110 may determine the statistical RSRP difference based on the results of multiple monitoring of the data processing model. In some embodiments, terminal device 110 may transmit second information indicative of the statistical RSRP difference to the network device.

[0149] In some embodiments, terminal device 110 may determine the number or percentage of occurrences of the third status based on the multiple monitoring results of the data processing model. In some embodiments, terminal device 110 may transmit second information indicating the number or percentage of occurrences of the third status to the network device.

[0150] In some embodiments, terminal device 110 may determine the number or percentage of occurrences of the third status based on multiple monitoring results of the data processing model. In some embodiments, terminal device 110 may determine whether the number or percentage of occurrences of the third status satisfies a sixth predetermined condition. In some embodiments, if the number or percentage of occurrences of the third status satisfies the sixth predetermined condition, terminal device 110 may determine a sixth status indicating that the sixth predetermined condition is satisfied. In some embodiments, terminal device 110 may transmit second information including the sixth status to a network device.

[0151] In some embodiments, the sixth predetermined condition indicates that the number or percentage of occurrences of the third status is greater than or equal to a fourteenth threshold. In some embodiments, the sixth predetermined condition indicates that the number or percentage of occurrences of the third status is less than or equal to a fourteenth threshold.

[0152] In some embodiments, terminal device 110 may determine at least one of the statistical SGCS or the statistical NMSE based on the plurality of monitoring results of the data processing model. In some embodiments, terminal device 110 may transmit second information indicative of the at least one of the statistical SGCS or the statistical NMSE to a network device.

[0153] In some embodiments, the second information is transmitted in a CSI report. In some embodiments, the second information is transmitted in a medium access control control element (MAC CE). In some embodiments, if the second information includes third information, terminal device 110 may determine a bit width for the third information based on the number of beams being reported.

[0154] In some embodiments, terminal device 110 may determine a bit width for the first number difference based on the number of first set of beams or first set of reference signals. In some embodiments, terminal device 110 may transmit the first number difference to the network device in a first part of the CSI report and transmit the difference value to the network device in a second part of the CSI report. In some embodiments, terminal device 110 may determine a bit width for the number or percentage of occurrences of the first status, the second status, or the third status based on the number of model monitoring.

[0155] 4 illustrates a flowchart of a communication method 400 implemented in a network device according to some embodiments of the present disclosure. In some embodiments, the method 400 may be implemented by the network device 120 of FIG.

[0156] The network device 120 may transmit the configuration to the terminal device 110. The configuration may indicate a first set of reference signals and / or resources of the first set of reference signals. Additionally, the configuration may indicate a second set of reference signals and / or resources of the second set of reference signals. In some embodiments, the second set of reference signals may be a subset of the first set of reference signals. Alternatively, the second set of reference signals may be the same as the first set of reference signals. In some other embodiments, the second set of reference signals may be different from the first set of reference signals. In some embodiments, the first set of reference signals and the second set of reference signals may refer to CSI-RS. Alternatively, the first set of reference signals and the second set of reference signals may refer to SSBs. It should be noted that the first set of reference signals and the second set of reference signals may refer to any suitable type of reference signals.

[0157] Furthermore, the configuration may indicate a data processing model for monitoring. For example, the configuration may include an index of the data processing model. Alternatively, the configuration may include model parameters for the data processing model. The data processing model may be expressed or indicated by (or replaced with) a model ID or function. In the case of CSI compression, the AI / ML model may correspond to a CSI generator or a CSI reconstructor.

[0158] In block 410, the network device 120 may transmit multiple reference signals to the terminal device 110. For example, the multiple reference signals include a first set of reference signals and a second set of reference signals. In some embodiments, the multiple reference signals may be multiple CSI-RSs. Alternatively, or additionally, the multiple reference signals may be multiple SSBs.

[0159] At block 420, second information is received from the network device 120, the terminal device 110, the second information indicating at least one of status information related to the performance metric, a numerical value related to the performance metric, or a ratio related to the performance metric. The second information is determined based on the predetermined status information and the first information. The first information is determined based on a comparison between the first set of parameters and the second set of parameters. The first set of parameters is determined based on first measurements on the first set of reference signals, and the second set of parameters is determined based on second measurements on the second set of reference signals.

[0160] In some embodiments, the first set of parameters comprises a first set of beams and the second set of parameters comprises a second set of beams. In some embodiments, the predetermined condition information comprises a first predetermined condition.

[0161] In some embodiments, the second information may include a first status indicating that a first predetermined condition is met. In some embodiments, the first predetermined condition indicates at least one of: a first target beam in the first set of beams overlaps with a beam in the second set; a first target beam in the first set of beams does not overlap with a beam in the second set; a second target beam in the second set of beams overlaps with a beam in the first set; or a second target beam in the second set of beams does not overlap with a beam in the first set.

[0162] In some embodiments, the second information may include the first status, the third information, and beam information for the first set of beams. The third information may indicate which beams in the first set of beams overlap with the first target beam in the second set of beams.

[0163] In some embodiments, if the first status indicates that the first target beam in the first set of beams does not overlap with the second set of beams, the third information is omitted.

[0164] In some embodiments, the first set of parameters includes a first measured beam quality of a first beam in the first set of beams and the second set of parameters includes a second measured beam quality of a second beam in the second set of beams. In some embodiments, the first set of parameters includes measured beam qualities of a first set of beams in the first set of beams and the second set of parameters includes predicted beam qualities of a second set of beams in the second set of beams. In some embodiments, the predetermined condition information includes a second predetermined condition.

[0165] In some embodiments, the first beam refers to the beam in the first set of beams that has the highest beam quality, and the second beam refers to the beam in the second set of beams that has the highest beam quality, or in some embodiments, the first beam is the same as the second beam.

[0166] In some embodiments, the second information includes a second status indicating that a second predetermined condition is met.

[0167] In some embodiments, the second predetermined condition indicates one of the first difference being less than or equal to a first threshold, or the first difference being greater than or equal to a first threshold.

[0168] In some embodiments, the second information includes a second status indicating that a second predetermined condition is met.

[0169] In some embodiments, the second predetermined condition indicates one of: a second number of differences in the first set of differences being less than or equal to a second threshold; or a second number of differences in the first set of differences being greater than or equal to a second threshold. The second difference may refer to a difference that is less than or equal to a threshold, or a difference that is greater than or equal to a third threshold, or a statistic of the first set of differences being less than or equal to a fourth threshold, or a statistic that is greater than or equal to the fourth threshold. In some embodiments, the second information includes a first status and a second status.

[0170] In some embodiments, the second information includes a first set of differences between the first set of measured beam qualities and the second set of predicted beam qualities, and in some embodiments, the second predetermined condition includes any one of the differences being less than or equal to a fifth threshold or the differences being greater than or equal to a fifth threshold.

[0171] In some embodiments, the first set of parameters includes first channel condition information and the second set of parameters includes second channel condition information. In some embodiments, the predetermined condition information includes a third predetermined condition.

[0172] In some embodiments, the second information includes a third status indicating that a third predetermined condition is satisfied. In some embodiments, the SGCS includes any one of an SGCS associated with or corresponding to a rank, layer, or data processing model, an averaged SGCS corresponding to a rank, layer, or list of data processing models, or statistics of SGCS corresponding to a rank, layer, or list of data processing models. In some embodiments, the NMSE includes any one of an NMSE associated with or corresponding to a data processing model, or statistics of NMSE corresponding to a list of data processing models.

[0173] In some embodiments, the third predetermined condition indicates at least one of: SGCS being greater than or equal to a sixth threshold; SGCS being less than or equal to a sixth threshold; NMSE being less than or equal to a ninth threshold; NMSE being greater than or equal to a ninth threshold; the number of SGCSs greater than or equal to the sixth threshold being greater than or equal to a tenth threshold; the number of SGCSs greater than or equal to the sixth threshold being less than or equal to the tenth threshold; the number of NMSEs less than or equal to a seventh threshold being greater than or equal to an eleventh threshold; or the number of NMSEs less than or equal to the seventh threshold being less than or equal to the eleventh threshold.

[0174] In some embodiments, the second information includes at least one of an indicator of a rank, layer, or data processing model of the first set of SGCSs or NMSEs, or the first set of SGCSs or NMSEs. In some embodiments, the second information includes at least one of an indicator of a rank, layer, or data processing model of the SGCSs or NMSEs, or the SGCSs or NMSEs.

[0175] In some embodiments, the third predetermined condition includes at least one of: the first set of SGCSs includes N1 SGCSs having maximum values ​​in the SGCSs, or the first set of NMSEs includes N1 NMSEs having minimum values ​​in the NMSEs, where N1 is an integer.

[0176] In some embodiments, the second information indicates a number or rate of occurrence of the first status.

[0177] In some embodiments, the second information includes a fourth status indicating that a fourth predetermined condition is met.

[0178] In some embodiments, the fourth predetermined condition indicates one of the following: the number or percentage of occurrences of the first status is greater than or equal to a twelfth threshold; or the number or percentage of occurrences of the first status is less than or equal to a twelfth threshold.

[0179] In some embodiments, the second information indicates a number or rate of occurrence of the second status.

[0180] In some embodiments, the second information includes a fifth status indicating that a fifth predetermined condition is met.

[0181] In some embodiments, the fifth predetermined condition indicates one of the following: the number or percentage of occurrences of the second status is greater than or equal to a thirteenth threshold; or the number or percentage of occurrences of the second status is less than or equal to a thirteenth threshold.

[0182] In some embodiments, the second information indicates a statistical RSRP difference.

[0183] In some embodiments, the second information indicates a number or rate of occurrence of the third status.

[0184] In some embodiments, the second information includes a sixth status indicating that a sixth predetermined condition is met.

[0185] In some embodiments, the sixth predetermined condition indicates that the number or percentage of occurrences of the third status is greater than or equal to a fourteenth threshold. In some embodiments, the sixth predetermined condition indicates that the number or percentage of occurrences of the third status is less than or equal to a fourteenth threshold.

[0186] In some embodiments, the second information is indicative of at least one of a statistical SGCS or a statistical NMSE.

[0187] 5 is a simplified block diagram of an apparatus 500 suitable for implementing embodiments of the present disclosure. Apparatus 500 may be considered a further illustrative example of any of the apparatuses shown in FIG. 1. Thus, apparatus 500 may be implemented in or as at least a portion of terminal device 110 or network device 120.

[0188] As shown, the apparatus 500 includes a processor 510, a memory 520 coupled to the processor 510, a suitable transmitter (TX) / receiver (RX) 540 coupled to the processor 510, and a communication interface coupled to the TX / RX 540. The memory 510 stores at least a portion of a program 530. The TX / RX 540 is for bidirectional communication. The TX / RX 540 has at least one antenna to facilitate communication, although in practice, an access node referred to herein may have multiple antennas. The communication interface may represent any interface required for communication with other network elements, such as an X2 / Xn interface for bidirectional communication between eNBs / gNBs, an S1 / NG interface for communication between a Mobility Management Entity (MME) / Access and Mobility Management Function (AMF) / SGW / UPF and an eNB / gNB, a Un interface for communication between an eNB / gNB and a Relay Node (RN), or a Uu interface for communication between an eNB / gNB and a terminal device.

[0189] The program 530 is assumed to include program instructions that, when executed by an associated processor 510, enable the device 500 to operate according to embodiments of the present disclosure, as described herein with reference to Figures 1-4. The embodiments herein may be implemented by computer software executable by the processor 510 of the device 500, or by hardware, or by a combination of software and hardware. The processor 510 may be configured to implement various embodiments of the present disclosure. Furthermore, the combination of the processor 510 and the memory 520 may form a processing means 550 adapted to implement various embodiments of the present disclosure.

[0190] Memory 520 may be of any type suitable for a local technology network and may be implemented using any suitable data storage technology, such as, by way of non-limiting example, non-transitory computer-readable storage media, semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory, and removable memory. While only one memory 520 is shown in device 500, device 500 may have multiple physically distinct memory modules. Processor 510 may be of any type suitable for a local technology network and may include, by way of non-limiting example, one or more of a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture. Device 500 may have multiple processors, such as application-specific integrated circuit chips that are time-slaved to a clock that synchronizes the main processor.

[0191] In some embodiments, the terminal device includes circuitry configured to cause the terminal device to: determine a first set of parameters based on first measurements on a first set of reference signals; determine a second set of parameters based on a data processing model and second measurements on a second set of reference signals; determine first information based on a comparison of the first set of parameters with the second set of parameters; determine second information based on predetermined condition information and the first information, wherein the second information indicates at least one of status information related to a performance metric, a numerical value related to a performance metric, a percentage related to a performance metric, or the first information; and transmit the second information to a network device.

[0192] In some embodiments, the network device includes circuitry configured to cause the terminal device to receive, from the terminal device, second information indicative of at least one of status information related to a performance metric, a numerical value related to the performance metric, a percentage related to the performance metric, or the first information, wherein the second information is determined based on predetermined condition information and the first information, the first information is determined based on a comparison of a first set of parameters and a second set of parameters, the first set of parameters being determined based on first measurements on the first set of reference signals, and the second set of parameters being determined based on second measurements on the second set of reference signals.

[0193] According to embodiments of the present disclosure, the circuitry may be configured to perform any of the methods implemented by the apparatus described above.

[0194] As used herein, the term "circuit" refers to a hardware circuit and / or a combination of a hardware circuit and software. For example, a circuit may be a combination of analog and / or digital hardware circuitry and software / firmware. As a further example, a circuit may be any portion of a hardware processor with software, including a digital signal processor, software, and memory, that cooperate to cause a device, such as a terminal device or network device, to perform various functions. In yet another example, a circuit may be a hardware circuit and / or processor, such as a microprocessor or portion of a microprocessor, that requires software / firmware for operation, but the software may not be present when not required for operation. As used herein, the term circuit also covers simply a hardware circuit or processor or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware implementation.

[0195] In summary, embodiments of the present disclosure provide the following aspects:

[0196] In one aspect, a terminal device for communications includes a processor configured to cause the terminal device to: determine a first set of parameters based on first measurements on a first set of reference signals; determine a second set of parameters based on a data processing model and second measurements on a second set of reference signals; determine first information based on a comparison of the first set of parameters with the second set of parameters; determine second information based on predetermined condition information and the first information, wherein the second information indicates at least one of status information related to a performance metric, a numerical value related to a performance metric, a percentage related to a performance metric, or the first information; and transmit the second information to a network device.

[0197] In some embodiments, the first set of parameters comprises a first set of beams, the second set of parameters comprises a second set of beams, and the predetermined condition information comprises a first predetermined condition.

[0198] In some aspects, the processor is configured to cause the terminal device to further perform the following: determine first information indicating whether the first set of beams overlaps with the second set of beams based on a comparison of the first set of beams with the second set of beams; determine whether the first information satisfies a first predetermined condition; determine a first status indicating that the first predetermined condition is satisfied according to a determination that the first information satisfies the first predetermined condition; and transmit second information including the first status to the network device.

[0199] In some embodiments, the first predetermined condition indicates at least one of: a first target beam in the first set of beams overlapping with a beam in the second set; a first target beam in the first set of beams not overlapping with a beam in the second set; a second target beam in the second set of beams overlapping with a beam in the first set; or a second target beam in the second set of beams not overlapping with a beam in the first set.

[0200] In some aspects, the processor is further configured to cause the terminal device to perform the following: determine third information based on the first set of beams and the second set of beams, the third information indicating which beams in the first set of beams overlap with the first target beam in the second set of beams; and transmit second information to the network device, the second information including the first status, the third information, and beam information of the first set of beams.

[0201] In some aspects, the third information is omitted pursuant to determining that the first status indicates that the first target beam in the first set of beams does not overlap with the second set of beams.

[0202] In some aspects, the first set of parameters includes a first measured beam quality of a first beam in the first set of beams, and the second set of parameters includes a second measured beam quality of a second beam in the second set of beams, or the first set of parameters includes a first measured beam quality of a beam in the first set of beams and the second set of parameters includes a second predicted beam quality of a beam in the second set of beams, and the predetermined condition information includes a second predetermined condition.

[0203] In some embodiments, the first beam refers to the beam with the highest quality in the first set of beams, the second beam refers to the beam with the highest quality in the second set of beams, or the first beam is the same as the second beam.

[0204] In some aspects, the processor is configured to further cause the terminal device to perform the following: determine first information indicating a first difference between the first measured beam quality and the second measured beam quality based on a comparison between the first measured beam quality and the second measured beam quality; determine whether the first information satisfies a second predetermined condition; determine a second status indicating that the second predetermined condition is satisfied according to a determination that the first information satisfies the second predetermined condition; and transmit the second information including the second status to the network device.

[0205] In some embodiments, the second predetermined condition indicates one of the first difference being less than or equal to a first threshold, or the first difference being greater than or equal to a first threshold.

[0206] In some aspects, the processor is further configured to cause the terminal device to perform the following: determine first information indicating a first set of differences or statistics of the first set of differences between the first set of measured beam qualities and the second set of predicted beam qualities based on a comparison between the first set of measured beam qualities and the second set of predicted beam qualities; determine whether the first information satisfies a second predetermined condition; determine a second status indicating that the second predetermined condition is satisfied according to a determination that the first information satisfies the second predetermined condition; and transmit the second information including the second status to the network device.

[0207] In some embodiments, the second predetermined condition indicates one of: a second number of differences in the first set of differences being less than or equal to a second threshold; or a second number of differences in the first set of differences being greater than or equal to a second threshold, wherein the second difference indicates a difference that is less than or equal to a threshold, or a difference that is greater than or equal to a third threshold, a statistic of the first set of differences being less than or equal to a fourth threshold, or a statistic that is greater than or equal to the fourth threshold.

[0208] In some embodiments, the second information includes a first status and a second status.

[0209] In some aspects, the processor is further configured to cause the terminal device to perform the following: determine first information indicating a first set of differences between the first set of measured beam qualities and the second set of predicted beam qualities based on a comparison of the first set of measured beam qualities and the second set of predicted beam qualities; determine a first number of differences based on the first set of differences and a second predetermined condition; and transmit second information including the first number of differences to the network device.

[0210] In some embodiments, the second predetermined condition comprises any one of the difference being less than or equal to a fifth threshold, or the difference being greater than or equal to a fifth threshold.

[0211] In some aspects, the first set of parameters includes first channel condition information, the second set of parameters includes second channel condition information, and the predetermined condition information includes a third predetermined condition.

[0212] In some aspects, the processor is further configured to cause the terminal device to perform the following: determine first information indicating a squared generalized cosine similarity (SGCS) or a normalized mean squared error (NMSE) based on a comparison between the first channel state information and the second channel state information; determine whether the first information satisfies a third predetermined condition; determine a third status indicating that the third predetermined condition is satisfied according to a determination that the first information satisfies the third predetermined condition; and transmit the second information including the third status to the network device.

[0213] In some embodiments, the SGCS includes any one of an SGCS associated with or corresponding to a rank, layer, or data processing model, an averaged SGCS corresponding to a rank, layer, or list of data processing models, or statistics of SGCS corresponding to a rank, layer, or list of data processing models, and the NMSE includes any one of an NMSE associated with or corresponding to a data processing model, or statistics of NMSE corresponding to a list of data processing models.

[0214] In some embodiments, the third predetermined condition indicates at least one of: SGCS being greater than or equal to a sixth threshold; SGCS being less than or equal to a sixth threshold; NMSE being less than or equal to a ninth threshold; NMSE being greater than or equal to a ninth threshold; the number of SGCSs greater than or equal to the sixth threshold being greater than or equal to a tenth threshold; the number of SGCSs greater than or equal to the sixth threshold being less than or equal to a tenth threshold; the number of NMSEs less than or equal to a seventh threshold being greater than or equal to an eleventh threshold; or the number of NMSEs less than or equal to the seventh threshold being less than or equal to an eleventh threshold.

[0215] The processor is configured to further cause the terminal device to perform the following: determine an SGCS or NMSE based on a comparison between the first channel status information and the second channel status information; determine a first set of SGCSs or NMSEs based on the SGCSs or NMSEs and a predetermined condition; transmit second information to the network device, the second information including at least one of a rank, a layer, or an indicator of a data processing model of the first set of SGCSs or NMSEs, or the first set of SGCSs or NMSEs; or transmit second information to the network device, the second information including at least one of a rank, a layer, or an indicator of a data processing model of the SGCSs or NMSEs, or the SGCSs or NMSEs.

[0216] In some embodiments, the third predetermined condition comprises at least one of: the first set of SGCSs includes N1 SGCSs having the maximum values ​​in the SGCSs, or the first set of NMSEs includes N1 NMSEs having the minimum values ​​in the NMSEs, where N1 is an integer.

[0217] In some embodiments, the processor is configured to further cause the terminal device to determine a number or percentage of occurrences of the first status based on the plurality of monitoring results of the data processing model, and to transmit second information indicating the number or percentage of occurrences of the first status to the network device.

[0218] In some aspects, the processor is configured to cause the terminal device to further perform the following: determine a number or percentage of occurrences of the first status based on multiple monitoring results of the data processing model; determine whether the number or percentage of occurrences of the first status satisfies a fourth predetermined condition; determine a fourth status indicating that the fourth predetermined condition is satisfied according to a determination that the number or percentage of occurrences of the first status satisfies the fourth predetermined condition; and transmit second information including the fourth status to the network device.

[0219] In some embodiments, the fourth predetermined condition indicates one of the following: the number or percentage of occurrences of the first status being greater than or equal to a twelfth threshold; or the number or percentage of occurrences of the first status being less than or equal to a twelfth threshold.

[0220] In some embodiments, the processor is configured to cause the terminal device to further perform the following: determining a number or percentage of occurrences of a second status based on the plurality of monitoring results of the data processing model; and transmitting second information indicating the number or percentage of occurrences of the second status to the network device.

[0221] In some aspects, the processor is configured to cause the terminal device to further perform the following: determine a number or percentage of occurrences of the second status based on multiple monitoring results of the data processing model; determine whether the number or percentage of occurrences of the second status satisfies a fifth predetermined condition; determine a fifth status indicating that the fifth predetermined condition is satisfied according to the determination that the number or percentage of occurrences of the second status satisfies the fifth predetermined condition; and transmit second information including the fifth status to the network device.

[0222] In some embodiments, the fifth predetermined condition indicates one of the following: the number or percentage of occurrences of the second status being greater than or equal to a thirteenth threshold; or the number or percentage of occurrences of the second status being less than or equal to a thirteenth threshold.

[0223] In some aspects, the processor is configured to further cause the terminal device to determine a statistical RSRP difference based on the plurality of monitoring results of the data processing model and transmit second information indicative of the statistical RSRP difference to the network device.

[0224] In some embodiments, the processor is configured to further cause the terminal device to determine a number or percentage of occurrences of a third status based on the plurality of monitoring results of the data processing model, and to transmit second information indicating the number or percentage of occurrences of the third status to the network device.

[0225] In some aspects, the processor is configured to cause the terminal device to further perform the following: determine a number or percentage of occurrences of a third status based on multiple monitoring results of the data processing model; determine whether the number or percentage of occurrences of the third status satisfies a sixth predetermined condition; determine a sixth status indicating that the sixth predetermined condition is satisfied according to a determination that the number or percentage of occurrences of the third status satisfies the sixth predetermined condition; and transmit second information including the sixth status to the network device.

[0226] In some embodiments, the sixth predetermined condition indicates one of the following: the number or percentage of occurrences of the third status being greater than or equal to a fourteenth threshold; or the number or percentage of occurrences of the third status being less than or equal to a fourteenth threshold.

[0227] In some aspects, the processor is configured to cause the terminal device to further perform the following: determining at least one of a statistical SGCS or a statistical NMSE based on a plurality of monitoring results of the data processing model; and transmitting second information indicative of the at least one of the statistical SGCS or the statistical NMSE to the network device.

[0228] In some aspects, the second information is transmitted in a CSI report, or the second information is transmitted in a medium access control control element (MAC CE).

[0229] In some aspects, the processor is configured to further cause the terminal device to, in accordance with a determination that the second information includes the third information, determine a bit width for the third information based on the number of beams reported.

[0230] In some aspects, the processor is configured to cause the terminal device to further perform the following: determining a bit width for the difference of the first number based on the number of the first set of beams or the first set of reference signals.

[0231] In some aspects, the processor is further configured to cause the terminal device to transmit the first number difference to the network device in a first portion of the CSI report and transmit the difference value to the network device in a second portion of the CSI report.

[0232] In some aspects, the processor is configured to further cause the terminal device to determine a bit width for the number or percentage of occurrences of the first status, the second status, or the third status based on the number of model monitoring.

[0233] In one aspect, a network device for communications includes a processor configured to cause a terminal device to receive, from the terminal device, second information indicative of at least one of status information related to a performance metric, a numerical value related to the performance metric, a percentage related to the performance metric, or first information, wherein the second information is determined based on predetermined condition information and the first information, the first information is determined based on a comparison of a first set of parameters and a second set of parameters, the first set of parameters is determined based on first measurements on the first set of reference signals, and the second set of parameters is determined based on second measurements on the second set of reference signals.

[0234] In some aspects, the first set of parameters comprises a first set of beams and the second set of parameters comprises a second set of beams. In some embodiments, the predetermined condition information comprises a first predetermined condition.

[0235] In some aspects, the second information can include a first status indicating that a first predetermined condition is met. In some embodiments, the first predetermined condition indicates at least one of: a first target beam in the first set of beams overlaps with a beam in the second set; a first target beam in the first set of beams does not overlap with a beam in the second set; a second target beam in the second set of beams overlaps with a beam in the first set; or a second target beam in the second set of beams does not overlap with a beam in the first set.

[0236] In some aspects, the second information may include the first status, the third information, and beam information of the first set of beams. The third information may indicate which beams in the first set of beams overlap with the first target beam in the second set of beams.

[0237] In some embodiments, if the first status indicates that the first target beam in the first set of beams does not overlap with the second set of beams, the third information is omitted.

[0238] In some aspects, the first set of parameters includes a first measured beam quality of a first beam in the first set of beams, and the second set of parameters includes a second measured beam quality of a second beam in the second set of beams. In some embodiments, the first set of parameters includes a first measured beam quality of a first set of beams in the first set of beams, and the second set of parameters includes a predicted beam quality of a second set of beams in the second set of beams. In some embodiments, the predetermined condition information includes a second predetermined condition.

[0239] In some aspects, the first beam refers to a first target beam in the first set of beams, and the second beam refers to a first target beam in the second set of beams, hi some embodiments, the first beam is the same as the second beam.

[0240] In some embodiments, the second information may include a second status indicating that a second predetermined condition is met.

[0241] In some embodiments, the second predetermined condition indicates one of the first difference being less than or equal to a first threshold, or the first difference being greater than or equal to a first threshold.

[0242] In some embodiments, the second information may include a second status indicating that a second predetermined condition is met.

[0243] In some aspects, the second predetermined condition indicates one of a second number of differences in the first set of differences being less than or equal to a second threshold, or a second number of differences in the first set of differences being greater than or equal to a second threshold. The second difference may refer to a difference that is less than or equal to a threshold, or a difference that is greater than or equal to a third threshold, a statistic of the first set of differences being less than or equal to a fourth threshold, or a statistic that is greater than or equal to a fourth threshold. In some embodiments, the second information includes a first status and a second status.

[0244] In some aspects, the second information includes a first set of differences between the first set of measured beam qualities and the second set of predicted beam qualities, and in some embodiments, the second predetermined condition includes one of the differences being less than or equal to a fifth threshold or the differences being greater than or equal to a fifth threshold.

[0245] In some aspects, the first set of parameters includes first channel condition information and the second set of parameters includes second channel condition information. In some embodiments, the predetermined condition information includes a third predetermined condition.

[0246] In some aspects, the second information may include a third status indicating that a third predetermined condition is satisfied. In some embodiments, the SGCS includes any one of an SGCS associated with or corresponding to a rank, layer, or data processing model, an averaged SGCS corresponding to a rank, layer, or list of data processing models, or statistics of SGCS corresponding to a rank, layer, or list of data processing models. In some embodiments, the NMSE includes any one of an NMSE associated with or corresponding to a data processing model, or statistics of NMSE corresponding to a list of data processing models.

[0247] In some embodiments, the third predetermined condition indicates at least one of: SGCS being greater than or equal to a sixth threshold; SGCS being less than or equal to a sixth threshold; NMSE being less than or equal to a ninth threshold; NMSE being greater than or equal to a ninth threshold; the number of SGCSs greater than or equal to the sixth threshold being greater than or equal to a tenth threshold; the number of SGCSs greater than or equal to the sixth threshold being less than or equal to a tenth threshold; the number of NMSEs less than or equal to a seventh threshold being greater than or equal to an eleventh threshold; or the number of NMSEs less than or equal to the seventh threshold being less than or equal to an eleventh threshold.

[0248] In some aspects, the second information includes at least one of a rank of the first set of SGCSs or NMSEs, an indicator of a layer or data processing model, or the first set of SGCSs or NMSEs. In some embodiments, the second information includes at least one of a rank of the SGCSs or NMSEs, an indicator of a layer or data processing model, or the SGCSs or NMSEs.

[0249] In some embodiments, the third predetermined condition comprises at least one of: the first set of SGCSs includes N1 SGCSs having the maximum values ​​in the SGCSs, or the first set of NMSEs includes N1 NMSEs having the minimum values ​​in the NMSEs, where N1 is an integer.

[0250] In some embodiments, the second information indicates a number or rate of occurrence of the first status.

[0251] In some embodiments, the second information may include a fourth status indicating that a fourth predetermined condition is met.

[0252] In some embodiments, the fourth predetermined condition indicates one of the following: the number or percentage of occurrences of the first status being greater than or equal to a twelfth threshold; or the number or percentage of occurrences of the first status being less than or equal to a twelfth threshold.

[0253] In some embodiments, the second information indicates a number or rate of occurrence of the second status.

[0254] In some embodiments, the second information includes a fifth status indicating that a fifth predetermined condition is met.

[0255] In some embodiments, the fifth predetermined condition indicates one of the following: the number or percentage of occurrences of the second status being greater than or equal to a thirteenth threshold; or the number or percentage of occurrences of the second status being less than or equal to a thirteenth threshold.

[0256] In some aspects, the second information indicates a statistical RSRP difference.

[0257] In some embodiments, the second information indicates a number or rate of occurrence of the third status.

[0258] In some embodiments, the second information may include a sixth status indicating that a sixth predetermined condition is met.

[0259] In some aspects, the sixth predetermined condition indicates that the number or percentage of occurrences of the third status is greater than or equal to a fourteenth threshold. In some embodiments, the sixth predetermined condition indicates that the number or percentage of occurrences of the third status is less than or equal to a fourteenth threshold.

[0260] In some embodiments, the second information indicates at least one of a statistical SGCS or a statistical NMSE.

[0261] In one aspect, a computer-readable medium having stored thereon instructions that, when executed on at least one processor, cause the at least one processor to perform the above-described method implemented by the above-described apparatus.

[0262] In one aspect, a computer program comprising instructions that, when executed on at least one processor, cause the at least one processor to perform the above method implemented by the above apparatus.

[0263] In general, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. While various aspects of embodiments of the present disclosure are illustrated and described using block diagrams, flowcharts, or some other pictorial representations, it should be understood that the blocks, devices, systems, techniques, or methods described in this disclosure may be implemented in, by way of non-limiting example, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller, or other computing device, or some combination thereof.

[0264] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions (e.g., computer-executable instructions included in program modules) that execute on a device by a target real or virtual processor to perform the processes or methods described above with reference to FIGS. 1 through 4. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split among program modules as desired in various embodiments. The machine-executable instructions for the program modules may be executed in local or distributed devices. In a distributed device, the program modules may be located in both local and remote storage media.

[0265] Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that when executed by the processor or controller, the program code performs the functions / acts specified in the flowcharts and / or block diagrams. The program code may be executed entirely on a machine, partially on a machine, as a stand-alone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0266] The program code may be embodied in a machine-readable medium, which may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium includes, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination thereof. More specific examples of machine-readable storage media include an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0267] Furthermore, although operations are described in a particular order, this should not be understood as requiring such operations to be performed in the particular order shown, or sequentially, or that all of the operations shown be performed, to achieve desirable results. In certain situations, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above description, these should not be construed as limiting the scope of the disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

[0268] Although the present disclosure has been described in language specific to structural features and / or methodological operations, it is to be understood that the present disclosure, which is limited to the appended claims, is not necessarily limited to the specific features or operations described above. Rather, the specific features and operations described above are disclosed as example forms of implementing the claims.

Claims

1. To the terminal device determining a first set of parameters based on first measurements on a first set of reference signals; determining a second set of parameters based on the data processing model and second measurements on a second set of reference signals; determining first information based on a comparison of the first set of parameters and the second set of parameters; determining second information based on predetermined condition information and the first information, the second information indicating at least one of status information related to a performance metric, a numerical value related to the performance metric, a percentage related to the performance metric, and the first information; and transmitting the second information to a network device.

2. the first set of parameters includes a first set of beams, and the second set of parameters includes a second set of beams; The terminal device according to claim 1 , wherein the predetermined condition information includes a first predetermined condition.

3. The processor: determining the first information indicative of whether the first set of beams overlaps with the second set of beams based on the comparison of the first set of beams and the second set of beams; determining whether the first information satisfies the first predetermined condition, the first predetermined condition indicating at least one of: a first target beam in the first set of beams overlaps with a beam in the second set; a first target beam in the first set of beams does not overlap with a beam in the second set; a second target beam in the second set of beams overlaps with a beam in the first set; and a second target beam in the second set of beams does not overlap with a beam in the first set; determining a first status indicating that the first predetermined condition is satisfied in accordance with determining that the first information satisfies the first predetermined condition; The terminal device of claim 2 , further configured to cause the terminal device to: transmit the second information including the first status to the network device.

4. The processor: determining third information based on the first set of beams and the second set of beams, the third information indicating which beams in the first set of beams overlap with the first target beam in the second set of beams; The terminal device of claim 3, further configured to cause the terminal device to transmit the second information, including at least one of the first status, the third information, and beam information of the first set of beams, to the network device.

5. The terminal device of claim 4, wherein the third information is omitted in accordance with a determination that the first status indicates that the first target beam in the first set of beams does not overlap with a beam in the second set.

6. the first set of parameters comprises a first measured beam quality of a first beam in the first set of beams and the second set of parameters comprises a second measured beam quality of a second beam in the second set of beams; or the first set of parameters includes measured beam qualities of a first set of beams within the first set of beams, and the second set of parameters includes predicted beam qualities of a second set of beams within the second set of beams; The terminal device according to claim 1 , wherein the predefined condition information includes a second predetermined condition.

7. The first beam refers to the beam in the first set of beams that has the best beam quality, and the second beam refers to the beam in the second set of beams that has the best beam quality; or the first beam is the same as the second beam, or The terminal device of claim 6 , wherein the first set of beams is the same as the second set of beams.

8. The processor: determining the first information indicative of a first difference between the first measured beam quality and the second measured beam quality based on the comparison of the first measured beam quality and the second measured beam quality; determining whether the first information satisfies the second predetermined condition, the second predetermined condition indicating one of the first difference being less than or equal to a first threshold and the first difference being greater than or equal to the first threshold; determining a second status indicating that the second predetermined condition is satisfied in accordance with determining that the first information satisfies the second predetermined condition; and The terminal device according to claim 6 or 7, further configured to cause the terminal device to: transmit the second information including the second status to the network device.

9. The processor: determining, based on the comparison between the first set of measured beam qualities and the second set of predicted beam qualities, the first information indicative of a first set of differences between the first set of measured beam qualities and the second set of predicted beam qualities, or statistics of the first set of differences; determining whether the first information satisfies the second predetermined condition, the second predetermined condition indicating one of a number of second differences in the first set of differences being less than or equal to a second threshold and a number of second differences in the first set of differences being greater than or equal to a second threshold, the second difference referring to a difference less than or equal to a threshold or a difference greater than or equal to a third threshold, the statistic being less than or equal to a fourth threshold, or the statistic being greater than or equal to the fourth threshold; determining a second status indicating that the second predetermined condition is satisfied in accordance with determining that the first information satisfies the second predetermined condition; and The terminal device according to claim 6 or 7, further configured to cause the terminal device to: transmit the second information including the second status to the network device.

10. The processor: determining, based on the comparison between the first set of measured beam qualities and the second set of predicted beam qualities, the first information indicative of a first set of differences between the first set of measured beam qualities and the second set of predicted beam qualities; determining at least one of a first number of differences and a second set of differences based on the first set of differences and the second predetermined condition, the second predetermined condition including one of the differences being less than or equal to a fifth threshold and the differences being greater than or equal to the fifth threshold; 8. The terminal device of claim 6 or 7, further configured to cause the terminal device to perform the following: transmitting the second information to the network device, the second information including at least one of a first number of differences or a second set of differences, the second set of differences including a subset of differences from the first set of differences that satisfy the second predetermined condition.

11. the first set of parameters includes first channel state information, and the second set of parameters includes second channel state information; The terminal device according to claim 1 , wherein the predetermined condition information includes a third predetermined condition.

12. The processor: determining the first information indicative of a squared generalized cosine similarity (SGCS), a normalized mean squared error (NMSE), a list of SGCS, or a list of NMSE based on the comparison of the first channel state information and the second channel state information; determining whether the first information satisfies the third predetermined condition, wherein the third predetermined condition indicates at least one of: SGCS being equal to or greater than a sixth threshold; SGCS being equal to or less than the sixth threshold; NMSE being equal to or less than a ninth threshold; NMSE being equal to or greater than the ninth threshold; the number of SGCSs equal to or greater than the sixth threshold being equal to or greater than a tenth threshold; the number of SGCSs equal to or greater than the sixth threshold being equal to or less than the tenth threshold; the number of NMSEs equal to or less than a seventh threshold being equal to or greater than an eleventh threshold; and the number of NMSEs equal to or less than the seventh threshold being equal to or less than the eleventh threshold; determining a third status indicating that the third predetermined condition is satisfied in accordance with determining that the first information satisfies the third predetermined condition; and The terminal device of claim 11 , further configured to: transmit the second information including the third status to the network device.

13. The SGCS or the NMSE SGCS or NMSE corresponding to the rank or layer, the averaged or weighted SGCS or NMSE corresponding to the list of ranks or layers, and SGCS or NMSE statistics corresponding to said list of ranks or layers; The terminal device of claim 12 , wherein the list of SGCSs or NMSEs includes a list of SGCSs or NMSEs corresponding to the list of ranks or layers.

14. The processor: determining an SGCS or NMSE based on the comparison of the first channel state information and the second channel state information; determining a first set of SGCSs or a first set of NMSEs based on the SGCSs or the NMSEs and the third predetermined condition, wherein the third predetermined condition includes at least one of: the first set of SGCSs includes N1 SGCSs having maximum values ​​in the SGCSs; and the first set of NMSEs includes N1 NMSEs having minimum values ​​in the NMSEs, where N1 is an integer; 12. The terminal device of claim 11, further configured to cause the terminal device to: transmit to the network device the second information, the second information including an indicator of a rank or layer corresponding to the first set of SGCSs or the first set of NMSEs, and at least one of the first set of SGCSs or the first set of NMSEs.

15. The processor: determining a number or rate of occurrence of a target status based on the plurality of monitoring results of the data processing model, the target status including one of a first status, a second status, and a third status; 15. The terminal device of claim 1, further configured to: transmit the second information indicating the number or rate of occurrence of the target status to the network device.

16. The processor: determining a number or rate of occurrence of a target status based on the plurality of monitoring results of the data processing model, the target status including one of a first status, a second status, and a third status; determining whether a number or rate of occurrence of the target status satisfies a fourth predetermined condition, the fourth predetermined condition indicating one of the number or rate of occurrence of the target status being greater than or equal to a twelfth threshold and the number or rate of occurrence of the target status being less than or equal to a twelfth threshold; determining a fourth status indicating that the fourth predetermined condition is satisfied in accordance with determining that the number or rate of occurrence of the target status satisfies a fourth predetermined condition; 15. The terminal device of claim 1, further configured to: transmit the second information, including the fourth status, to the network device.

17. The processor: determining at least one of a statistical RSRP difference, a statistical SGCS, and a statistical NMSE based on a plurality of monitoring results of the data processing model; 15. The terminal device according to claim 1, further configured to: transmit the second information indicating at least one of the statistical RSRP difference, the statistical SGCS, and the statistical NMSE to the network device.

18. the second information is transmitted in a CSI report; or The terminal device according to claim 1 , wherein the second information is transmitted in a Medium Access Control Control Element (MAC CE).

19. The processor: determining a bit width for the third information based on a number of reported beams in response to determining that the second information includes third information; or 19. The terminal device of claim 18, further configured to cause the terminal device to, in accordance with a determination that the second information includes a first number difference, determine a bit width for the first number difference based on the number of a first set of beams or a first set of reference signals.

20. The processor:

20. The terminal device of claim 1, further configured to: transmit a first number of differences to the network device in a first part of a CSI report; and transmit the second set of differences to the network device in a second part of the CSI report.

Images