Beam prediction accuracy

Abstract

The present disclosure relates to beam prediction accuracy. Embodiments of the present disclosure relate to beam management related to beam prediction accuracy. In one aspect of the solution, a terminal device receives, from a network device, at least one of a resource configuration or a reference signal for performance monitoring associated with beam prediction accuracy. Based on the at least one of the resource configuration or the reference signal, the terminal device determines a performance metric associated with the beam prediction accuracy.

Description

Cross-references to related applications

[0001] This application claims priority and benefit to European Patent Application No. 25156578.4, filed on 7 February 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0002] Various example embodiments relate to the field of communications, and particularly to apparatus, methods, devices, and computer-readable storage media for beam management related to beam prediction accuracy. Background Technology

[0003] A communication network can be viewed as a facility that enables communication between two or more communication devices or provides communication devices with access to a data network. Mobile or wireless communication networks are an example of communication networks.

[0004] Such communication networks operate according to standards, such as those issued by the 3rd Generation Partnership Project (3GPP) or the European Telecommunications Standards Institute (ETSI). Examples of such standards include the so-called fifth-generation (5G) standard, the sixth-generation (6G) standard, or other standards issued by 3GPP. Summary of the Invention

[0005] Overall, the exemplary embodiments of this disclosure provide a beam management solution related to beam prediction accuracy.

[0006] In a first aspect, a terminal device is provided. The terminal device includes at least one processor and at least one memory storing instructions, which, when executed by the at least one processor, cause the terminal device to at least: determine a beam report, the beam report including a beam performance metric associated with beam prediction accuracy, wherein the beam performance metric is represented by at least one of a numerical value or a ratio; and send the beam report to a network device.

[0007] In a second aspect, a network device is provided. The network device includes at least one processor and at least one memory storing instructions, which, when executed by the at least one processor, cause the network device to at least: receive a beam report from a terminal device, the beam report including a beam performance metric associated with beam prediction accuracy, wherein the beam performance metric is represented by at least one of a numerical value or a ratio.

[0008] In a third aspect, a terminal device is provided. The terminal device includes at least one processor and at least one memory storing instructions, which, when executed by the at least one processor, cause the terminal device to at least: receive from a network device at least one of a resource configuration or a reference signal for performance monitoring associated with beam prediction accuracy; and determine a performance metric associated with beam prediction accuracy based on at least one of the resource configuration or reference signals.

[0009] In a fourth aspect, a network device is provided. The network device includes at least one processor and at least one memory storing instructions, which, when executed by the at least one processor, cause the network device to at least: determine at least one of a resource configuration or a reference signal for performance monitoring associated with beam prediction accuracy; and transmit at least one of the resource configuration or reference signals to a terminal device.

[0010] In a fifth aspect, a terminal device is provided. The terminal device includes at least one processor and at least one memory storing instructions, which, when executed by the at least one processor, cause the terminal device to at least: send a first Reference Signal Received Power (RSRP) report to a network device; receive a request from the network device for a differential RSRP report having finer quantization than the first RSRP report; and send a differential RSRP report with finer quantization to the network device.

[0011] In a sixth aspect, a network device is provided. The network device includes at least one processor and at least one memory storing instructions, which, when executed by the at least one processor, cause the network device to at least: receive a first Reference Signal Received Power (RSRP) report from an end device; send a request to the end device for a differential RSRP report having finer quantization than the first RSRP report; and receive a differential RSRP report with finer quantization from the end device.

[0012] In a seventh aspect, a method is provided. The method includes: determining a beam report at a terminal device, the beam report including a beam performance metric associated with beam prediction accuracy, wherein the beam performance metric is represented by at least one of a numerical value or a ratio; and sending the beam report to a network device.

[0013] In an eighth aspect, a method is provided. The method includes: receiving a beam report from an end device at a network device, the beam report including a beam performance metric associated with beam prediction accuracy, wherein the beam performance metric is represented by at least one of a numerical value or a ratio.

[0014] In a ninth aspect, a method is provided. The method includes: receiving at a terminal device at a network device at at least one of a resource configuration or a reference signal for performance monitoring associated with beam prediction accuracy; and determining a performance metric associated with beam prediction accuracy based on at least one of the resource configuration or reference signal.

[0015] In a tenth aspect, a method is provided. The method includes: determining at a network device at at least one of a resource configuration or a reference signal for performance monitoring associated with beam prediction accuracy; and transmitting at least one of the resource configuration or reference signals to a terminal device.

[0016] In an eleventh aspect, a method is provided. The method includes: sending a first reference signal received power (RSRP) report to a network device at a terminal device; receiving a request from the network device for a differential RSRP report having finer quantization than the first RSRP report; and sending the differential RSRP report with finer quantization to the network device.

[0017] In a twelfth aspect, a method is provided. The method includes: receiving a first Reference Signal Received Power (RSRP) report from an end device at a network device; sending a request to the end device for a differential RSRP report having finer quantization than the first RSRP report; and receiving a differential RSRP report with finer quantization from the end device.

[0018] In a thirteenth aspect, an apparatus is provided. The apparatus includes: components for determining a beam report at a terminal device, the beam report including a beam performance index associated with beam prediction accuracy, wherein the beam performance index is represented by at least one of a numerical value or a ratio; and components for transmitting the beam report to a network device.

[0019] In a fourteenth aspect, an apparatus is provided. The apparatus includes: a component for receiving a beam report from a terminal device at a network device, the beam report including a beam performance index associated with beam prediction accuracy, wherein the beam performance index is represented by at least one of a numerical value or a ratio.

[0020] In a fifteenth aspect, an apparatus is provided. The apparatus includes: components for receiving, at a terminal device, at a network device, at least one of a resource configuration or a reference signal for performance monitoring associated with beam prediction accuracy; and components for determining a performance metric associated with beam prediction accuracy based on at least one of the resource configuration or the reference signal.

[0021] In a sixteenth aspect, an apparatus is provided. The apparatus includes: components for determining at least one of a resource configuration or a reference signal at a network device for performance monitoring associated with beam prediction accuracy; and components for transmitting at least one of the resource configuration or reference signals to a terminal device.

[0022] In a seventeenth aspect, an apparatus is provided. The apparatus includes: components for transmitting a first Reference Signal Received Power (RSRP) report to a network device at a terminal device; components for receiving a request from the network device for a differential RSRP report having finer quantization than the first RSRP report; and components for transmitting a differential RSRP report with finer quantization to the network device.

[0023] In an eighteenth aspect, an apparatus is provided. The apparatus includes components for receiving a first Reference Signal Received Power (RSRP) report from a terminal device at a network device; components for sending a request to the terminal device for a differential RSRP report having finer quantization than the first RSRP report; and components for receiving a differential RSRP report with finer quantization from the terminal device.

[0024] In a nineteenth aspect, a non-transitory computer-readable medium is provided, comprising program instructions for causing an apparatus to perform at least the method according to any one of the seventh to twelfth aspects described above.

[0025] In a twentieth aspect, a computer program including instructions is provided that, when executed by a device, causes the device to perform at least the method according to any one of the seventh to twelfth aspects described above.

[0026] In a twenty-first aspect, a terminal device is provided. The terminal device includes: a determining circuitry configured to determine a beam report, the beam report including a beam performance metric associated with beam prediction accuracy, wherein the beam performance metric is represented by at least one of a numerical value or a ratio; and a transmitting circuitry configured to transmit the beam report to a network device.

[0027] In a twenty-second aspect, a network device is provided. The network device includes: a receiving circuitry system configured to receive a beam report from a terminal device, the beam report including a beam performance metric associated with beam prediction accuracy, wherein the beam performance metric is represented by at least one of a numerical value or a ratio.

[0028] In a twenty-third aspect, a terminal device is provided. The terminal device includes: a receiving circuit system configured to receive from a network device at least one of a resource configuration or a reference signal for performance monitoring associated with beam prediction accuracy; and a determining circuit system configured to determine a performance metric associated with beam prediction accuracy based on at least one of the resource configuration or the reference signal.

[0029] In a twenty-fourth aspect, a network device is provided. The network device includes: a determining circuit system configured to determine at least one of a resource configuration or a reference signal for performance monitoring associated with beam prediction accuracy; and a transmitting circuit system configured to transmit at least one of the resource configuration or reference signals to a terminal device.

[0030] In a twenty-fifth aspect, a terminal device is provided. The terminal device includes: a first transmitting circuit system configured to transmit a first Reference Signal Received Power (RSRP) report to a network device; a receiving circuit system configured to receive a request from the network device for a differential RSRP report having finer quantization than the first RSRP report; and a second transmitting circuit system configured to transmit a differential RSRP report with finer quantization to the network device.

[0031] In a twenty-sixth aspect, a network device is provided. The network device includes a first receiving circuit system configured to receive a first Reference Signal Received Power (RSRP) report from a terminal device; a transmitting circuit system configured to send a request to the terminal device for a differential RSRP report having finer quantization than the first RSRP report; and a second receiving circuit system configured to receive a differential RSRP report with finer quantization from the terminal device.

[0032] It should be understood that the summary portion is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0033] Some exemplary embodiments will now be described with reference to the accompanying drawings, in which:

[0034] Figure 1 The illustration shows an example network environment in which example embodiments of the present disclosure can be implemented;

[0035] Figure 2 The illustration shows example signaling diagrams illustrating example processes according to some embodiments of the present disclosure;

[0036] Figure 3The illustration shows another example signaling diagram illustrating example processes according to some embodiments of the present disclosure;

[0037] Figure 4 The illustration shows yet another example signaling diagram illustrating example processes according to some embodiments of the present disclosure;

[0038] Figure 5 The illustrations depict example processes according to some embodiments of the present disclosure;

[0039] Figure 6 The illustration shows a flowchart of a method implemented at a terminal device according to some example embodiments of the present disclosure;

[0040] Figure 7 The illustration shows a flowchart of a method implemented at a network device according to some example embodiments of the present disclosure;

[0041] Figure 8 The illustration shows a flowchart of a method implemented at a terminal device according to some example embodiments of the present disclosure;

[0042] Figure 9 The illustration shows a flowchart of a method implemented at a network device according to some example embodiments of the present disclosure;

[0043] Figure 10 The illustration shows a flowchart of a method implemented at a terminal device according to some example embodiments of the present disclosure;

[0044] Figure 11 The illustration shows a flowchart of a method implemented at a network device according to some example embodiments of the present disclosure;

[0045] Figure 12 A simplified block diagram of an apparatus suitable for implementing embodiments of the present disclosure is illustrated; and

[0046] Figure 13 A block diagram of an example computer-readable medium according to some embodiments of the present disclosure is illustrated.

[0047] Throughout the accompanying drawings, the same or similar reference numerals denote the same or similar elements. Detailed Implementation

[0048] The principles of this disclosure will now be described with reference to some exemplary embodiments. It should be understood that these embodiments are described for illustrative purposes only and to assist those skilled in the art in understanding and implementing exemplary embodiments of this disclosure, and are not intended to limit the scope of this disclosure in any way. The exemplary embodiments of this disclosure described herein can be implemented in various ways other than those described below.

[0049] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0050] In this disclosure, references to "an embodiment," "embodiment," "example embodiment," etc., indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment must include that particular feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Moreover, when a particular feature, structure, or characteristic is described in connection with an embodiment, it should be understood that, whether explicitly described or not, in combination with other embodiments to affect such a feature, structure, or characteristic is within the knowledge of those skilled in the art.

[0051] It should be understood that although the terms “first” and “second” may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. For example, without departing from the scope of the exemplary embodiments, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0052] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments. The singular forms “a,” “an,” and “the” used herein also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprises,” “comprising,” “has,” “having,” “includes,” and / or “including,” when used herein, specify the presence of the stated features, elements, and / or components, but do not exclude the presence or addition of one or more other features, elements, components, and / or combinations thereof. As used herein, “at least one of the following: ” and “<at least one of a list of two or more elements>” and similar wording (where a list of two or more elements is connected by “and” or “or”) means at least any one of the elements, or at least any two or more elements of the element, or at least all elements of the element.

[0053] As used in this application, the term "circuit system" may refer to one or more or all of the following: (a) Pure hardware circuit implementation (such as implementations only in analog and / or digital circuit systems), and (b) A combination of hardware circuitry and software, such as (if applicable): (i) A combination of (multiple) analog and / or digital hardware circuits and software / firmware, and (ii) Any part of the (multiple) hardware processors (including (multiple) digital signal processors) having software, software, and (multiple) memories, which work together to enable a device (such as a mobile phone or server) to perform various functions, and (c) (Multiple) hardware circuits and / or (multiple) processors, such as (multiple) microprocessors or a portion thereof, which require software (e.g., firmware) to operate, but may be absent when operation is not required.

[0054] The definition of "circuit system" applies to all uses of the term in this application, including in any claim. As another example, as used in this application, the term "circuit system" also covers implementations of only hardware circuitry or processors (or processors in general) or portions thereof and their accompanying software and / or firmware. For instance, if applicable to a particular claim element, the term "circuit system" also covers baseband integrated circuits or processor integrated circuits for mobile devices, or similar integrated circuits in servers, cellular network devices, or other computing or network devices.

[0055] As used herein, the term "communication network" refers to a network that conforms to any suitable communication standard, such as Long Term Evolution (LTE), LTE-A, Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), Narrowband Internet of Things (NB-IoT), etc. Furthermore, communication between terminal devices and network devices in a communication network can be performed according to any suitable generation of communication protocol, including but not limited to first-generation (1G), second-generation (2G), 2.5G, 2.75G, third-generation (3G), fourth-generation (4G), 4.5G, future fifth-generation (5G) communication protocols, and / or any other protocols currently known or to be developed in the future. Embodiments of this disclosure can be applied to various communication systems. Given the rapid development of communications, there will naturally be future types of communication technologies and systems that can be used to embody the exemplary embodiments of this disclosure. This should not be construed as limiting the scope of this disclosure to the systems described above.

[0056] As used herein, the term "network device" refers to a node in a communication network through which terminal devices can access the network and receive services. Network devices can refer to base stations (BS) or access points (APs), such as Node B (NodeB or NB), evolved Node B (eNodeB or eNB), New Radio (NR) NB (also known as gNB), Remote Radio Unit (RRU), Radio Head (RH), Remote Radio Head (RRH), relay, low-power nodes (such as femtoseconds, picoseconds), etc., depending on the terminology and technology used.

[0057] The term "terminal device" refers to any terminal device capable of wireless communication. By way of example and not limitation, a terminal device may also be referred to as a communication device, user equipment (UE), subscriber station (SS), portable subscriber station, mobile station (MS), or access terminal (AT). Terminal devices may include, but are not limited to, mobile phones, cellular phones, smartphones, VoIP phones, wireless local loop phones, tablets, wearable terminal devices, personal digital assistants (PDAs), portable computers, desktop computers, image capture terminal devices (such as digital cameras), gaming terminal devices, music storage and playback devices, in-vehicle wireless terminal devices, wireless endpoints, mobile stations, laptop embedded devices (LEEs), laptop mounted devices (LMEs), USB dongles, smart devices, wireless customer premises equipment (CPEs), Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in industrial and / or automated processing chain environments), consumer electronic devices, devices operating on commercial and / or industrial wireless networks, etc. In the following description, the terms "terminal equipment", "communication equipment", "terminal", "user equipment" and "UE" are used interchangeably.

[0058] Figure 1 An example network environment 100 in which exemplary embodiments of the present disclosure may be implemented is illustrated. The environment or communication system 100, which may be part of a communication network, includes terminal devices and network devices.

[0059] like Figure 1As shown, the communication system 100 may include a terminal device 110 (hereinafter also referred to as user equipment 110 or UE 110) and a network device 120 (hereinafter also referred to as base station 120 or gNB 120). The network device 120 can manage cell 101. The terminal device 110 can communicate with the network device 120 within the coverage of cell 101. The link from the terminal device 110 to the network device 120 is called the uplink (UL), and the link from the network device 120 to the terminal device 110 is called the downlink (DL).

[0060] It should be understood that the number of devices is for illustrative purposes only and does not imply any limitation. System 100 may include any suitable number of terminal devices or network devices suitable for implementing embodiments of this disclosure. Although not shown, it should be understood that one or more terminal devices or network devices may be located in system 100.

[0061] Communication in communication system 100 can be implemented according to any suitable communication protocol(s), including but not limited to cellular communication protocols such as first-generation (1G), second-generation (2G), third-generation (3G), fourth-generation (4G), and fifth-generation (5G), wireless local area network communication protocols such as IEEE 802.11, and / or any other protocols currently known or to be developed in the future. Furthermore, communication can utilize any suitable wireless communication technology, including but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiplexing (OFDM), Discrete Fourier Transform Spread Spectrum OFDM (DFT-s-OFDM), and / or any other technologies currently known or to be developed in the future.

[0062] With the development of technology, the application of AI / ML technology in the NR air interface has been studied. Specification support is provided for beam management (DL Tx beam prediction) for both the UE-side model and the NW-side model. DL Tx beam prediction covers spatial DL Tx beam prediction for beam set A based on measurements from beam set B (“BM-Case 1”), and temporal DL Tx beam prediction for beam set A based on historical measurements from beam set B (“BM-Case 2”). DL Tx beam prediction also covers: specifying (multiple) necessary signaling / mechanisms to facilitate lifecycle management (LCM) operations specific to beam management use cases (if any); and enabling (multiple) methods to ensure consistency between training and inference regarding NW-side additional conditions (if identified) for inference at the UE. Furthermore, the common framework design strives to support both BM-Case 1 and BM-Case 2.

[0063] Significant challenges exist in calculating and reporting performance metrics related to beam prediction accuracy used in UE-side models. These include defining how metrics are calculated, ambiguities in the Beam Accuracy Indicator (BAI), and the need for clear guidance when reporting measurement and inference results. Inadequate metric calculation and reporting can lead to inaccurate beam performance assessments, thus impacting network efficiency.

[0064] Specifically, for more detailed problems, the lack of standardized definitions for key metrics, such as BAI, leads to ambiguity regarding whether it should be expressed as a numerical value or a ratio. This inconsistency can result in discrepancies in performance evaluations across different implementations, ultimately impacting network efficiency. Furthermore, the computation of performance metrics becomes complex due to the need to utilize downsampling factors and resource mappings, especially when the monitoring set is a subset of set A.

[0065] Furthermore, there is an urgent need for clear guidance on whether UEs should report measurement results or inference results, as this distinction is crucial to ensuring the accuracy of the reported data. The lack of effective performance monitoring mechanisms for AI / ML models used for beam management exacerbates these problems, as it complicates the determination of appropriate reference signals and the configuration of monitoring resource sets.

[0066] Furthermore, the quantization of L1-RSRP values ​​used for reporting (especially in the context of Differential Reference Signal Received Power (RSRP) reporting) lacks sufficient granularity, which may hinder the network's ability to make informed decisions based on reported data. The need for an efficient feedback mechanism is also crucial, particularly in scenarios like BM Case-2, where the UE can indicate the bitmap of the selected optimal beam across multiple time instances without incurring excessive signaling overhead.

[0067] To address these challenges, a comprehensive framework is needed that defines clear, standardized metrics for beam prediction accuracy (including BAI) and provides explicit guidance for reporting methods. This framework can also incorporate effective performance monitoring strategies for AI / ML models, ensuring the reliability of the metrics used and facilitating accurate evaluation of beam performance.

[0068] According to some embodiments of this disclosure, a beam management solution related to beam prediction accuracy is provided. In one aspect of this solution, a terminal device determines a beam report including indicators of beam performance associated with beam prediction accuracy. The beam performance indicators are represented by at least one of numerical values ​​or ratios. The terminal device then sends the beam report to a network device. In another aspect of this solution, the terminal device receives from the network device at least one of resource configuration or reference signals for performance monitoring associated with beam prediction accuracy. Based on at least one of the resource configuration or reference signals, the terminal device determines a performance metric associated with beam prediction accuracy. In yet another aspect of this solution, the terminal device sends a first RSRP report to the network device and receives from the network device a request for a differential RSRP report with finer quantization than the first RSRP report. The terminal device then sends the differential RSRP report with finer quantization to the network device. In this way, the 3GPP ecosystem can enhance the efficiency of beam management and improve overall network performance. Reference will be made below. Figures 2-13 The principles and implementation of the embodiments of this disclosure are described in detail.

[0069] Figure 2 The illustration shows a signaling diagram illustrating an example process 200 according to some embodiments of the present disclosure. Reference will be made to this diagram for discussion purposes. Figure 1 Describe process 200. Process 200 may involve terminal device 110 and network device 120. It should be understood that, although combined... Figure 1 The process 200 is described in the communication system 100, but this process can also be applied to other communication scenarios with similar problems.

[0070] In process 200, terminal device 110 determines 210 a beam report including beam performance metrics associated with beam prediction accuracy. Beam performance metrics are expressed by at least one of numerical values ​​or ratios. Beam performance metrics may also be referred to as Beam Performance Index (BPI).

[0071] In some embodiments, the terminal device 110 may also determine a numerical representation of beam performance based on a first number of at least one correctly predicted beam and a second number of predicted total beams.

[0072] For example, the following formula (1) can be used for numerical representation: BPI = (Correct Forecasts / Total Forecasts) 100% (1) "Correct prediction" corresponds to a first number of correct predictions for at least one beam, i.e., the number of correct predictions performed by the terminal device 110 (or the prediction model on the terminal device 110 side). "Total prediction" corresponds to a second number of predictions for the total beam, i.e., the total number of predictions performed by the terminal device 110 (or the prediction model on the terminal device 110 side).

[0073] Alternatively or additionally, terminal equipment 110 may also determine a beam performance index expressed as a ratio based on at least one third number of correctly predicted beams among at least one of the predicted optimal beams and a fourth number of predicted optimal beams.

[0074] For example, the following formula (2) can be used to express ratios: BPI = (Top-K correct predictions / K) (2) "Top-K (Optimal K) Correct Predictions" refers to the third number of correct predictions for at least one beam among the predicted optimal beams. K corresponds to the fourth number of predicted optimal beams, i.e., the number of optimal beams considered.

[0075] Furthermore, the terminal device 110 can also determine beam performance metrics based on the downsampling factor, resource mapping, or a combination of both. In other words, the calculation of beam performance metrics can combine the downsampling factor and resource mapping to ensure accuracy.

[0076] In some embodiments, to determine a beam report, terminal device 110 may determine whether to report beam measurement results or beam inference results. If terminal device 110 determines to report beam measurement results, it generates a beam report including the beam measurement results. If terminal device 110 determines to report beam inference results, it generates a beam report including the beam inference results. Furthermore, the beam report may also include a fourth indication of the predicted optimal beam.

[0077] Continue to refer to Figure 2 Terminal device 110 sends beam report 215 220 to network device 120. Correspondingly, network device 120 receives beam report 225 220 from terminal device 110.

[0078] In some embodiments, terminal device 110 may periodically send beam reports. Alternatively or additionally, terminal device 110 may send beam reports based on a metric determining beam performance that is greater than a first threshold or less than a second threshold. In other words, the threshold can be defined for report updates.

[0079] Alternatively or additionally, terminal device 110 may also avoid periodically sending beam reports based on whether a change in a beam performance indicator is greater than a third threshold or less than a fourth threshold. In other words, thresholds can be defined for report exemption.

[0080] Furthermore, terminal device 110 can determine whether the change in beam performance metrics exceeds a fifth threshold. If the change in beam performance metrics is less than the fifth threshold, terminal device 110 can avoid periodically sending beam reports. In other words, a hysteresis value can be defined to avoid switching between two or more values.

[0081] In the example, detailed specifications can be developed to guide when terminal device 110 reports measurement and inference results. Decision trees can be used to help terminal device 110 determine the appropriate reporting method based on the context of the data. Terminal device 110 can report at two levels: periodic reporting with a longer duration (10 ms), and self-organizing reporting based on changes during the scheduled reporting period. Furthermore, terminal device 110 can exempt periodic reporting if the report remains unchanged within a given threshold. Explicit thresholds for reporting ensure that significant deviations are communicated to the network.

[0082] Furthermore, beam reports can be transmitted along with at least one reference signal received power (RSRP) measurement for at least one beam. For example, a finely quantized, fine L1-RSRP measurement for better accuracy, along with a combined report, can be transmitted to network device 120, including BPI and / or top-K beams.

[0083] In some embodiments, terminal device 110 may determine beam reporting based on an artificial intelligence / machine learning (AI / ML) model. The AI / ML model may be implemented at terminal device 110. In some other embodiments, the AI / ML model may be implemented independently of terminal device 110. Alternatively or additionally, the input to the AI / ML model may include at least one beam measurement result. Furthermore, the output of the AI / ML model may include beam performance metrics, an indication of the predicted optimal beam, or a combination of both.

[0084] Figure 3 The illustration shows a signaling diagram illustrating an example process 300 according to some embodiments of the present disclosure. Reference will be made for discussion purposes. Figure 1 Describe process 300. Process 300 may involve terminal device 110 and network device 120. It should be understood that, although combined... Figure 1 The process 300 is described in the communication system 100, but this process can also be applied to other communication scenarios with similar problems.

[0085] In process 300, network device 120 determines 310 at least one of a resource configuration or reference signal for performance monitoring associated with beam prediction accuracy. The reference signal set can be designed for predictive model evaluation, such as AI / ML model evaluation. Monitoring the resource set configuration allows for dynamic adjustment based on real-time performance metrics.

[0086] Then, network device 120 sends at least one of 315 resource configuration or reference signal 320 to terminal device 110. A performance monitor (PM) entity can be implemented at terminal device 110. The PM entity is also notified of resource configuration.

[0087] After receiving at least one of the resource configuration or reference signal 320, the terminal device 110 determines 330 a performance metric associated with beam prediction accuracy based on at least one of the resource configuration or reference signal.

[0088] To determine a performance metric, terminal device 110 may perform at least one beam measurement based on at least one of resource configuration or reference signal. Based on at least one beam measurement, terminal device 110 can determine the performance metric.

[0089] In some embodiments, performance metrics may include beam performance indicators, such as BPI. Beam performance indicators may be represented by at least one of numerical values ​​or ratios.

[0090] Alternatively or additionally, terminal device 110 may determine a numerical representation of beam performance based on a first number of correctly predicted at least one beam and a second number of predicted total beams.

[0091] Furthermore, the terminal device 110 can determine a beam performance index expressed as a ratio based on at least one correct third number of at least one beam in the predicted optimal beams and a fourth number of the predicted optimal beams.

[0092] In some embodiments, terminal device 110 may determine beam reports based on an artificial intelligence / machine learning (AI / ML) model. Alternatively or additionally, the input to the AI / ML model may include at least one beam measurement result. Furthermore, the output of the AI / ML model may include at least one of a beam performance metric or an indication of a predicted optimal beam. For example, terminal device 110 may perform at least one beam measurement based on resource configuration, and at least one beam measurement may be sent to the AI / ML model to obtain a beam performance metric. The AI / ML model then provides the beam performance metric to the PM entity for continuous evaluation.

[0093] In some embodiments, terminal device 110 may also determine whether a performance metric is greater than a threshold. If the performance metric is less than the threshold, terminal device 110 may send an alert related to beam prediction accuracy to network device 120. In the example, the PM entity may check whether AI / ML beam prediction remains within an acceptable threshold. If performance degrades, terminal device 110 sends an alert to network device 120.

[0094] On the other side of the communication, network device 120 can receive alarms related to beam prediction accuracy from terminal device 110. In some embodiments, based on the received alarm, network device 120 can send a request to terminal device 110 for a differential RSRP report with more fine-grained quantization than the previously received RSRP report. Based on feedback from the PM entity or internal policies, network device 120 can request a more granular differential RSRP report to refine its understanding of link conditions.

[0095] Accordingly, terminal device 110 can receive a request from network device 120 for a differential RSRP report with finer quantization than the previously sent RSRP report, and the request can be in response to an alarm.

[0096] Figure 4 The illustration shows a signaling diagram illustrating an example process 400 according to some embodiments of the present disclosure. Reference will be made to this diagram for discussion purposes. Figure 1 Describe process 400. Process 400 may involve terminal device 110 and network device 120. It should be understood that, although combined... Figure 1 The process described in the communication system 100 is 400, but this process can also be applied to other communication scenarios with similar problems.

[0097] In process 400, terminal device 110 sends a first RSRP report 415 to network device 120. After receiving the first RSRP report 415 from terminal device 110, network device 120 sends a request to terminal device 110 for a differential RSRP report with finer quantization than the first RSRP report.

[0098] In some embodiments, network device 120 may send the request based on an alarm received from an end device that is associated with beam prediction accuracy. For example, the alarm may indicate that beam prediction accuracy has deteriorated, and network device 120 may request a more granular differential RSRP report to refine its understanding of link conditions.

[0099] In some alternative embodiments, network device 120 may send the request based on determining that the false alarm rate of the bit array needs to be reduced. Since multiple beams can map to the same position in the array, false alarms may occur; that is, a beam may appear "selected" even if it is not actually "selected." If network device 120 needs further clarification on the actual state of the beam, it may request a differential RSRP report.

[0100] Continue to refer to Figure 4 Upon receiving a request for a differential RSRP report with more refined quantization, terminal device 110 sends a differential RSRP report with more refined quantization to network device 120.

[0101] In some embodiments, terminal device 110 can also determine differential RSRP reports based on non-uniform quantization. The quantization process for differential RSRP reports can use a multi-level quantization scheme, which allows for finer granularity in the report and has specific thresholds for differential RSRP reports. Non-uniform quantization techniques allow scaling of report accuracy (absolute and relative accuracy) based on current requirements. In this way, reporting overhead can be minimized.

[0102] Network device 120 can also perform a feedback loop. The feedback loop enables network device 120 to adjust the quantization level based on observed performance. For an efficient feedback mechanism, terminal device 110 can implement a bitmap reporting system and address the requirements of minimizing signaling overhead and utilizing a compact representation of the selected beam.

[0103] The differential RSRP report may be sent together with: a beam bitmap indicating at least one beam selected by the terminal device, or a bit array indicating at least one beam selected by the terminal device.

[0104] Alternatively or additionally, terminal device 110 may select at least one beam based on at least one RSRP of at least one beam, the predicted beam performance of at least one beam, channel quality, signal strength, mobility of the terminal device, or any combination of two or more of the above. For the beam selection algorithm, terminal device 110 may implement a beam selection algorithm that identifies the optimal beam across multiple time instances. This algorithm may take into account factors such as channel quality, signal strength, and user mobility.

[0105] In some embodiments, the terminal device 110 may further divide the time domain into one or more groups of consecutive time instances, and the beam bitmap or bit array may further indicate at least one beam selected by the terminal device for at least one time instance in the group. This allows feedback to be reported for multiple time instances using a single bitmap.

[0106] In some embodiments, the beammap may include at least one index of at least one beam, and the at least one index corresponds to at least one bit in the beammap. Furthermore, a first value (e.g., 1) of a bit in the beammap may indicate that the beam corresponding to that bit is selected by the terminal device. Additionally, a second value (e.g., 0) of a bit in the beammap may indicate that the beam corresponding to that bit is not selected by the terminal device.

[0107] For beam selection and representation, a unique index is assigned to each beam in the system. This unique index can be used to represent a beam in a bitmap. In the bitmap structure, the bitmap is a binary representation where each bit corresponds to a specific beam index. A "1" bit indicates that the corresponding beam is selected, while a "0" bit indicates that it is not selected.

[0108] For feedback reports, terminal device 110 can send a beammap to network device 120, indicating the selected beam for the corresponding time instance group. The beammap can be used to report feedback for multiple time instances within a group. This reduces the number of feedback transmissions required. The size of the beammap can be dynamically adjusted based on the number of beams in the system. This ensures efficient bandwidth utilization.

[0109] For example, consider a system with 100 beams and a group of time instances comprising 10 time instances. The bitmap might require 100 bits to represent the selected beams for the entire group. This is much more compact than sending the beam indexes individually, which would require 1000 bits, i.e., 10 beams multiplied by 100 time instances.

[0110] Furthermore, terminal device 110 and network device 120 can synchronize on time instance packets and beam index mapping to ensure correct interpretation of the bitmap. Mechanisms for handling errors in bitmap transmission and interpretation can be implemented to ensure reliable feedback.

[0111] The beammap representation is very compact; each beam requires only a single bit. This significantly reduces the amount of data transmitted compared to other feedback mechanisms. By grouping data into time instances and using a single bitmap to report feedback for multiple time instances, the frequency of feedback transmissions is reduced, further minimizing signaling overhead. The bitmap size is adjusted based on the number of beams to ensure that only necessary information is sent, thereby minimizing overhead.

[0112] The bitmap reporting system significantly reduces the amount of data sent for feedback, improving network efficiency. Reduced signaling overhead results in faster response times and improved data rates for users, thus enhancing the user experience. Furthermore, the system can be easily scaled to accommodate a greater number of beams and time instances.

[0113] Overall, the proposed bitmap reporting system provides an efficient and compact mechanism for feedback reporting, minimizing signaling overhead and ensuring accurate beam selection. This implementation can significantly improve network performance and user experience in future wireless communication systems.

[0114] In some embodiments, terminal device 110 may determine the bit array based on a Bloom filter. For an efficient feedback mechanism, terminal device 110 may also utilize a Bloom filter to implement a Bloom-based bitmap reporting system. The goal of an efficient feedback mechanism is to reduce signaling overhead by compressing the list of selected beams (or “optimal beams”) across multiple time instances into a compact data structure.

[0115] Alternatively or additionally, in order to determine the bit array based on a Bloom filter, terminal device 110 may initialize the bit array, and the bits in the bit array may be set to a first value (e.g., 0). Using a first number of hash functions, terminal device 110 may map at least one index of at least one beam to a first number of bits in the bit array, and the first number of bits may be set to a second value (e.g., 1).

[0116] For example, each beam can be assigned a unique index (e.g., 0, 1, 2, ...). These indices are used to map the beams to a Bloom filter. A Bloom filter is a probabilistic data structure that uses multiple hash functions to indicate membership in a set. Instead of assigning dedicated bits to each beam (as in a bitmap), the UE initializes an array of bits of length mm (all set to 0) and uses k different hash functions to map each selected beam index to k positions in the bit array, setting the corresponding bits to 1.

[0117] Furthermore, terminal device 110 can group consecutive time instances of a set together. For each group, terminal device 110 can identify a subset of beams that meet specific selection criteria (e.g., the optimal beam based on RSRP or predicted quality). The same Bloom filter represents the selection of beams for multiple time instances within a single message. This compresses multiple feedback events into a single structure, thereby reducing the frequency and magnitude of the feedback signal.

[0118] Furthermore, based on the target false alarm rate, the expected number of selected beams in the bit array, or a combination of the above two, the terminal device 110 can determine the length of the bit array, the first number of hash functions, or a combination of the above two.

[0119] False alarms can occur because multiple beams can map to the same position in the bit array. However, assuming no transmission errors, there will be no missed alarms (the selected beam is completely missed). Depending on the number of beams in the system and the desired false alarm rate, m (bit array length) and k (number of hash functions) can be dynamically adjusted. This ensures efficient bandwidth utilization and an acceptable probability of misclassification.

[0120] In some embodiments, terminal device 110 may also send information associated with the bit array to network device 120. Accordingly, network device 120 may receive information associated with the bit array from terminal device 110.

[0121] Alternatively or additionally, the information associated with the bit array may include the ID of the group indicated in the bit array, the length of the bit array, the first number of hash functions, the seed of the hash functions, or any combination of two or more of the above items.

[0122] For example, terminal device 110 may send the obtained Bloom filter bit array along with metadata (such as time instance group ID, Bloom filter size mmm, and number of hash functions k) to network device 120. Optionally, if needed, terminal device 110 may send the bit array along with a seed for the hash functions.

[0123] For the beam selection algorithm, similar to the bitmap scheme, the terminal device 110 can implement an algorithm (e.g., based on channel quality, RSRP, or AI-driven prediction) to select the optimal beams at the time instances of packets. These beams become members of a set encoded in a Bloom filter.

[0124] For synchronization and configuration, terminal device 110 and network device 120 agree on the size mm of the Bloom filter bit array, the number k of hash functions, and the definition (or seed) of the hash functions. This ensures that network device 120 can correctly interpret the Bloom filter.

[0125] For false alarm management, Bloom filters are unlikely to indicate that a beam has been selected (i.e., a false alarm) when the beam is not actually part of the set. To mitigate false alarms, if network device 120 requires further clarification of the actual state of the beam, it can request fine-grained or differential feedback (e.g., partial explicit indexing, or subsequent measurements). Furthermore, over-dimensioning the Bloom filter array (choosing a larger mmm and an appropriate k) can reduce the false alarm rate to an acceptable level for beam management decisions.

[0126] For error handling, standard error correction protocols (e.g., CRC, HARQ) still apply to transmission errors. If the Bloom filter fails, network device 120 can discard the feedback and request a retransmission to resolve the decoding error.

[0127] To minimize signaling overhead, Bloom filters typically require fewer bits than a full bitmap when the selected beam set is relatively small compared to the total beam space. This compact representation significantly reduces the size of the feedback data. Similar to bitmap-based schemes, grouping multiple time instances into a single feedback message further minimizes signaling. Instead of sending separate feedback for each time instance, the UE sends only one Bloom filter array per group. By tuning the Bloom filter parameters (e.g., bit array length mm, number of hash functions k) according to network conditions and the expected number of selected beams, terminal device 110 and network device 120 can utilize adaptive parameters to optimize between memory / overhead and accuracy.

[0128] In an example of a system with 100 beams and 10 time groups, a traditional bitmap has 100 bits per time instance, and the total number of bits can be determined based on the following formula: 100 × 10 = 1000; 100 multiplied by 10 = 1000 100 × 10 = 1000 (3)

[0129] Using a Bloom filter, if we choose m=200 as the bit array length and k=4 as the number of hash functions, the total number of bits can be determined based on the following formula: m=200 m=200 m=200 bits, k=4 k=4 k=4 hash functions (4)

[0130] Even with multiple beams, the total overhead for each group is only 200 bits, plus negligible metadata. A small false alarm rate is acceptable if network device 120 is willing to occasionally check for "suspicious" beams.

[0131] Bloom filters significantly compress data for the selected beam, reducing feedback size and thus signaling overhead compared to direct lists or full bitmaps. Fewer transmissions are required through efficient multi-time instance reporting, saving bandwidth and reducing system load. Bloom filter parameters can be scaled based on the total number of beams and the desired false positive rate. The same basic mechanism can support small or large beam sets. Lower overhead translates to more efficient use of radio resources and better user throughput, thereby improving network performance.

[0132] Replacing bitmaps with Bloom filters allows terminal devices 110 to provide a compact probabilistic feedback mechanism for selected beams across multiple time instances. While Bloom filters introduce a manageable risk of false alarms, they significantly reduce signaling overhead compared to classic bitmap or index-based reporting schemes. This trade-off can significantly enhance the network efficiency and scalability of beam-based feedback reporting.

[0133] Overall, beam reporting systems with beam bitmaps or bit arrays allow for the selection of the optimal beam across multiple time instances, with a focus on minimizing signaling overhead. Utilizing a compact representation of the selected beam, bitmap reporting systems ensure the delivery of essential information without excessive data transmission.

[0134] Figure 5 An example process 500 according to various aspects of this disclosure is illustrated. Process 500 may involve UE 501, gNB 502, AI / ML model 503, and performance monitor entity 504. Figure 5 UE 501 in the context can be Figure 2 , Figure 3 or Figure 4 Example of terminal device 110 in the example. Figure 5 gNB 502 in the text can be Figure 2 , Figure 3 or Figure 4 Example of network device 120. Figure 5 AI / ML model 503 in the middle can be Figure 2 , Figure 3 or Figure 4 The terminal devices are implemented in 110 locations. Figure 5 The performance monitor entity 504 in the middle can be Figure 2 , Figure 3 or Figure 4 The process is implemented at terminal device 110. It should be understood that process 500 can be considered as... Figure 2 The process in 200 Figure 3 Process 300 or Figure 4 A more specific example of process 400.

[0135] At 510, UE 501 continuously measures the received signal power across beams (e.g., L1-RSRP) and applies any downsampling or resource mapping rules to manage measurement overhead.

[0136] At 515, UE 501 sends measurement data for beam prediction by forwarding relevant measurement data / features to AI / ML model 503, which can run locally on UE 501 or be partially offloaded depending on the architecture.

[0137] At position 520, AI / ML model 503 sends the predicted beam and BPI to UE 501. Prior to this, AI / ML model 503 predicts (multiple) optimal beams and calculates or updates the BPI based on a normalized algorithm that incorporates both numerical and ratio aspects.

[0138] At 525, UE 501 determines the reporting method. UE 501 applies decision logic to determine whether to report raw measurement results, inference results, or both (according to the new reporting guidelines).

[0139] At 530, UE 501 sends a combined report to gNB 502, along with fine L1-RSRP measurements with improved quantization for better accuracy. The combined report may include BPI and top-K beam.

[0140] At 535, gNB 502 sends a configuration monitoring resource set / reference signal to UE 501. gNB 502 updates the resource configuration or reference signal specifically for performance monitoring of AI / ML driven beam management. At 540, gNB 502 notifies performance monitor entity 504 of the new configuration.

[0141] At 545, UE 501 sends the updated measurements under the new configuration to AI / ML model 503. UE 501 follows the updated resource configuration when measuring and sending additional data to AI / ML model 503. At 550, AI / ML model 503 forwards the performance metrics to performance monitor entity 504 for continuous evaluation.

[0142] At position 555, performance monitor entity 504 sends a performance status or threshold alarm to gNB 502. For example, performance monitor entity 504 checks whether AI / ML beam prediction remains within an acceptable threshold. If performance degrades, performance monitor entity 504 sends an alarm to gNB 502.

[0143] At 560, based on feedback from performance monitor entity 504 or internal policies, gNB 502 requests a more granular differential RSRP report to refine its understanding of link conditions.

[0144] At 565, UE 501 reports to gNB 502 a requested differential RSRP with finer quantization, and the requested differential RSRP may include a beam bitmap (for optimal beams across multiple time instances) to reduce signaling overhead. At 570, gNB 502 acknowledges the report and may adjust beam resources or scheduling to optimize network performance.

[0145] It should be understood that embodiments of process 200, process 300, process 400 or process 500 can be used in combination or individually.

[0146] Overall, the exemplary embodiments of this disclosure provide a comprehensive framework for standardizing the definition and reporting methods for key performance metrics, particularly BAI, to address challenges in beam management for UEs within the 3GPP ecosystem. This framework introduces a new metric called BPI, which serves as a unified representation of beam prediction accuracy, combining both numerical and ratio metrics to eliminate ambiguity. BPI can be calculated using a standardized algorithm that takes into account downsampling factors and resource mapping to ensure consistency across different implementations.

[0147] Furthermore, this framework provides explicit guidance for distinguishing between measurement and inference results, thereby enhancing the accuracy of the reported data. It can also incorporate performance monitoring mechanisms specifically designed for AI / ML models used in beam management, allowing for efficient evaluation of reference signals and monitoring resource sets. The quantization of L1-RSRP values ​​will be refined to provide greater granularity, thus facilitating more informed decision-making by the network.

[0148] The proposed solution standardizes key metrics, reduces discrepancies in performance evaluation, and improves network efficiency through enhanced accuracy in the reported data (effective monitoring of AI / ML models leads to better beam management strategies). The greater granularity of the L1-RSRP value allows for more accurate network decisions and reduces signaling overhead while maintaining basic information flow.

[0149] Figure 6 A flowchart of an example method 600 implemented at a terminal device according to some embodiments of the present disclosure is shown. Reference will be made to this flowchart for discussion purposes. Figure 1 Method 600 is described from the perspective of terminal device 110.

[0150] At box 610, terminal device 110 determines a beam report, which includes a beam performance metric associated with beam prediction accuracy, wherein the beam performance metric is represented by at least one of a numerical value or a ratio. At box 620, terminal device 110 sends the beam report to network device.

[0151] In some embodiments, the first terminal device 110 may determine a beam report by: determining whether to report beam measurement results or beam inference results; generating a beam report including beam measurement results based on the determination that beam measurement results should be reported; and generating a beam report including beam inference results based on the determination that beam inference results should be reported.

[0152] In some embodiments, the first terminal device 110 may also determine a beam performance index, expressed in numerical terms, based on a first number of at least one correctly predicted beam and a second number of predicted total beams.

[0153] In some embodiments, the first terminal device 110 may also determine a beam performance index expressed as a ratio based on at least one third number of correctly predicted beams among at least one of the predicted optimal beams and a fourth number of predicted optimal beams.

[0154] In some embodiments, the first terminal device 110 may determine beam performance metrics based on at least one of a downsampling factor and a resource map. In some embodiments, the beam report may further include a fourth number of indications of the predicted optimal beam.

[0155] In some embodiments, the terminal device 110 may send beam reports by: periodically sending beam reports; or sending beam reports based on an indicator that determines beam performance as being greater than a first threshold or less than a second threshold.

[0156] In some embodiments, the terminal device 110 may also avoid periodically sending beam reports based on whether the change in a beam performance indicator is greater than a third threshold or less than a fourth threshold.

[0157] In some embodiments, the terminal device 110 may also determine whether the change in the beam performance index is greater than a fifth threshold; and based on the determination that the change in the beam performance index is less than the fifth threshold, avoid periodically sending beam reports.

[0158] In some embodiments, the beam report may be transmitted along with at least one reference signal received power (RSRP) measurement for at least one beam. In some embodiments, the terminal device 110 may determine the beam report based on an artificial intelligence / machine learning (AI / ML) model.

[0159] In some embodiments, at least one of the following may be included: the input to the AI / ML model may include at least one beam measurement result; or the output of the AI / ML model may include at least one of a beam performance metric or an indication of the predicted optimal beam.

[0160] Figure 7 A flowchart of an example method 700 implemented at a network device according to some embodiments of the present disclosure is shown. Reference will be made to this flowchart for discussion purposes. Figure 1 Method 700 is described from the perspective of network device 120.

[0161] At box 710, network device 120 receives a beam report from terminal device, the beam report including a beam performance metric associated with beam prediction accuracy, wherein the beam performance metric is represented by at least one of a numerical value or a ratio.

[0162] In some embodiments, the beam report may further include a fourth indication of the predicted optimal beam. In some embodiments, the beam report may be received together with at least one reference signal received power (RSRP) measurement of at least one beam.

[0163] Figure 8 A flowchart of an example method 800 implemented at a terminal device according to some embodiments of the present disclosure is shown. Reference will be made to this flowchart for discussion purposes. Figure 1 Method 800 is described from the perspective of terminal device 110.

[0164] At block 810, terminal device 110 receives from network device at least one of resource configuration or reference signals for performance monitoring associated with beam prediction accuracy. At block 820, terminal device 110 determines a performance metric associated with beam prediction accuracy based on at least one of the resource configuration or reference signals.

[0165] In some embodiments, the terminal device 110 may determine the performance metric by performing at least one beam measurement based on at least one of resource configuration or reference signal; and by determining the performance metric based on at least one beam measurement.

[0166] In some embodiments, the performance metric may include an indicator of beam performance, and the indicator of beam performance may be represented by at least one of a numerical value or a ratio.

[0167] In some embodiments, the terminal device 110 may determine a performance metric by: determining an index of beam performance expressed in numerical form based on a first number of at least one correctly predicted beam and a second number of predicted total beams.

[0168] In some embodiments, the terminal device 110 may also determine a beam performance index expressed as a ratio based on at least one third number of correctly predicted beams among at least one of the predicted optimal beams and a fourth number of predicted optimal beams.

[0169] In some embodiments, the terminal device 110 may determine performance metrics based on an artificial intelligence / machine learning (AI / ML) model. In some embodiments, at least one of the following may be true: the input to the AI / ML model may include at least one beam measurement; or the output of the AI / ML model may include a performance metric.

[0170] In some embodiments, the terminal device 110 may further: determine whether a performance metric is greater than a threshold; and based on the determination that the performance metric is less than the threshold, send an alarm related to beam prediction accuracy to the network device.

[0171] In some embodiments, terminal device 110 may also receive a request from network device for a differential reference signal received power (RSRP) report, which has finer quantization than the previously sent RSRP report, wherein the request is in response to an alarm.

[0172] Figure 9 A flowchart of an example method 900 implemented at a network device according to some embodiments of the present disclosure is shown. Reference will be made to this flowchart for discussion purposes. Figure 1 Method 900 is described from the perspective of network device 120.

[0173] At 910, network device 120 determines at least one of a resource configuration or a reference signal for performance monitoring associated with beam prediction accuracy. At 920, network device 120 sends at least one of the resource configuration or reference signals to the terminal device.

[0174] In some embodiments, network device 120 may also receive an alarm related to beam prediction accuracy from terminal device. In some embodiments, network device 120 may also send a request to terminal device for a differential reference signal received power (RSRP) report based on the received alarm, the differential RSRP report having finer quantization than the previously received RSRP report.

[0175] Figure 10 A flowchart of an example method 1000 implemented at a terminal device according to some embodiments of the present disclosure is shown. For ease of discussion, reference will be made to... Figure 1 Method 1000 is described from the perspective of terminal device 110.

[0176] At block 1010, terminal device 110 sends a first Reference Signal Received Power (RSRP) report to network device. At block 1020, terminal device 110 receives a request from network device for a differential RSRP report, which has finer quantization than the first RSRP report. At block 1030, terminal device 110 sends a differential RSRP report with finer quantization to network device.

[0177] In some embodiments, the terminal device 110 may also determine a differential RSRP report based on non-uniform quantization. In some embodiments, the differential RSRP report may be sent together with one of the following: a beam bitmap indicating at least one beam selected by the terminal device, or a bit array indicating at least one beam selected by the terminal device.

[0178] In some embodiments, terminal device 110 may select at least one beam based on at least one of the following: at least one RSRP of at least one beam, predicted beam performance of at least one beam, channel quality, signal strength, or mobility of the terminal device.

[0179] In some embodiments, the terminal device 110 may further divide the time domain into one or more groups of consecutive time instances, wherein the beam bitmap or bit array further indicates at least one beam selected by the terminal device for at least one time instance in the group.

[0180] In some embodiments, the beam bitmap may include at least one index of at least one beam, and the at least one index corresponds to at least one bit in the beam bitmap.

[0181] In some embodiments, at least one of the following may be true: a first value of a bit in the beam bitmap may indicate that the beam corresponding to the bit is selected by the terminal device; or a second value of a bit in the beam bitmap may indicate that the beam corresponding to the bit is not selected by the terminal device.

[0182] In some embodiments, terminal device 110 may also determine the bit array based on a Bloom filter. In some embodiments, terminal device 110 may determine the bit array based on a Bloom filter by: initializing the bit array, wherein the bits in the bit array are set to a first value; and mapping at least one index of at least one beam to a first number of bits in the bit array using a first number of hash functions, wherein the first number of bits are set to a second value.

[0183] In some embodiments, the terminal device 110 may also determine at least one of the length of the bit array or the first number of hash functions based on at least one of the target false alarm rate or the expected number of selected beams of the bit array.

[0184] In some embodiments, terminal device 110 may also send information associated with a bit array to network device.

[0185] In some embodiments, the information associated with the bit array may include at least one of the following: the identifier (ID) of the group indicated in the bit array; the length of the bit array; the first number of hash functions; or the seed of the hash functions.

[0186] Figure 11 A flowchart of an example method 1100 implemented at a network device according to some embodiments of the present disclosure is shown. Reference will be made to this flowchart for discussion purposes. Figure 1 Method 1100 is described from the perspective of network device 120.

[0187] At 1110, network device 120 receives a first Reference Signal Received Power (RSRP) report from the terminal device. At 1120, network device 120 sends a request to the terminal device for a differential RSRP report, which has finer quantization than the first RSRP report. At 1130, network device 120 receives a differential RSRP report with finer quantization from the terminal device.

[0188] In some embodiments, a differential RSRP report may be received together with one of the following: a beam bitmap indicating at least one beam selected by the terminal device; or a bit array indicating at least one beam selected by the terminal device, wherein the bit array is determined based on a Bloom filter.

[0189] In some embodiments, the beam bitmap may include at least one index of at least one beam, and the at least one index corresponds to at least one bit in the beam bitmap.

[0190] In some embodiments, at least one of the following may be true: a first value of a bit in the beam bitmap may indicate that the beam corresponding to the bit is selected by the terminal device; or a second value of a bit in the beam bitmap may indicate that the beam corresponding to the bit is not selected by the terminal device.

[0191] In some embodiments, network device 120 may also receive information associated with a bit array from a terminal device.

[0192] In some embodiments, the information associated with the bit array may include at least one of the following: an identifier (ID) of a group indicating at least one time instance in the bit array, the length of the bit array, a first number of hash functions used to determine the bit array, or a seed for determining the hash functions of the bit array.

[0193] In some embodiments, network device 120 may send the request based on at least one of the following: receiving an alarm related to beam prediction accuracy from a terminal device; or determining to reduce the false alarm rate of the bit array.

[0194] In some embodiments, an apparatus (e.g., terminal device 110) is provided capable of performing any of the methods 600. The apparatus may include components for performing the corresponding steps of method 600. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module.

[0195] In some embodiments, the apparatus includes: components for determining a beam report, the beam including a beam performance metric associated with beam prediction accuracy, wherein the beam performance metric is represented by at least one of a numerical value or a ratio; and components for sending the beam report to a network device.

[0196] In some embodiments, the components for determining a beam report may include: components for determining whether to report beam measurement results or beam inference results; components for generating a beam report including beam measurement results based on the determination that beam measurement results should be reported; and components for generating a beam report including beam inference results based on the determination that beam inference results should be reported.

[0197] In some embodiments, the apparatus may further include: a component for determining an index of beam performance expressed in numerical terms based on a first number of at least one correct prediction of at least one beam and a second number of predictions of the total beam.

[0198] In some embodiments, the apparatus may further include: a component for determining an index of beam performance expressed as a ratio based on at least one third number of correctly predicted at least one beam among the predicted optimal beams and a fourth number of predicted optimal beams.

[0199] In some embodiments, the apparatus may include a component for determining a metric for beam performance based on at least one of a downsampling factor and a resource map.

[0200] In some embodiments, the beam report may also include a fourth number of indications of the predicted optimal beam.

[0201] In some embodiments, the component for sending beam reports may include: a component for periodically sending beam reports; or a component for sending beam reports based on a metric determining beam performance that is greater than a first threshold or less than a second threshold.

[0202] In some embodiments, the apparatus may further include a component for avoiding periodically sending beam reports based on a change in a beam performance metric that is greater than a third threshold or less than a fourth threshold.

[0203] In some embodiments, the apparatus may further include: a component for determining whether a change in a beam performance index is greater than a fifth threshold; and a component for avoiding periodically sending beam reports based on determining that the change in a beam performance index is less than the fifth threshold.

[0204] In some embodiments, the beam report may be transmitted along with at least one reference signal received power (RSRP) measurement for at least one beam. In some embodiments, the apparatus may include components for determining the beam report based on an artificial intelligence / machine learning (AI / ML) model.

[0205] In some embodiments, at least one of the following may be included: the input to the AI / ML model may include at least one beam measurement result; or the output of the AI / ML model may include at least one of a beam performance metric or an indication of the predicted optimal beam.

[0206] In some embodiments, the apparatus may further include components for performing additional steps of some embodiments of method 600. In some embodiments, the components include at least one processor and at least one memory including computer program code, the at least one memory and the computer program code being configured to, together with the at least one processor, cause the execution of the apparatus described above.

[0207] In some embodiments, an apparatus (e.g., network device 120) capable of performing any of the methods 700 is provided. The apparatus may include components for performing the corresponding steps of method 700. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module.

[0208] In some embodiments, the apparatus includes components for receiving a beam report from a terminal device, the beam report including a beam performance metric associated with beam prediction accuracy, wherein the beam performance metric is represented by at least one of a numerical value or a ratio.

[0209] In some embodiments, the beam report may further include a fourth indication of the predicted optimal beam. In some embodiments, the beam report may be received together with at least one reference signal received power (RSRP) measurement of at least one beam.

[0210] In some embodiments, the apparatus may further include components for performing other steps of some embodiments of method 700. In some embodiments, the components include at least one processor and at least one memory including computer program code, the at least one memory and the computer program code being configured to, together with the at least one processor, cause the execution of the apparatus described above.

[0211] In some embodiments, an apparatus (e.g., terminal device 110) is provided capable of performing any of the methods 800. The apparatus may include components for performing the corresponding steps of method 800. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module.

[0212] In some embodiments, the apparatus includes: components for receiving at least one of a resource configuration or a reference signal from a network device for performance monitoring associated with beam prediction accuracy; and components for determining a performance metric associated with beam prediction accuracy based on at least one of the resource configuration or the reference signal.

[0213] In some embodiments, the components for determining a performance metric may include: components for performing at least one beam measurement based on at least one of a resource configuration or a reference signal; and components for determining a performance metric based on at least one beam measurement.

[0214] In some embodiments, the performance metric may include an indicator of beam performance, and the indicator of beam performance may be represented by at least one of a numerical value or a ratio.

[0215] In some embodiments, the components for determining performance metrics may include: components for determining an index of beam performance expressed in numerical terms based on a first number of at least one correct prediction of at least one beam and a second number of predictions of the total beam.

[0216] In some embodiments, the apparatus may further include: a component for determining an index of beam performance expressed as a ratio based on at least one third number of correctly predicted at least one beam among the predicted optimal beams and a fourth number of predicted optimal beams.

[0217] In some embodiments, the apparatus may include a component for determining performance metrics based on an artificial intelligence / machine learning (AI / ML) model.

[0218] In some embodiments, at least one of the following may be true: the input to the AI / ML model may include at least one beam measurement; or the output of the AI / ML model may include a performance metric.

[0219] In some embodiments, the apparatus may further include: a component for determining whether a performance metric is greater than a threshold; and a component for sending an alarm related to beam prediction accuracy to a network device based on determining that the performance metric is less than the threshold.

[0220] In some embodiments, the apparatus may further include: a component for receiving from a network device a request for a differential reference signal received power (RSRP) report, the differential RSRP report having finer quantization than the previously transmitted RSRP report, wherein the request is in response to an alarm.

[0221] In some embodiments, the apparatus may further include components for performing additional steps of some embodiments of method 800. In some embodiments, the components include at least one processor and at least one memory including computer program code, the at least one memory and the computer program code being configured to, together with the at least one processor, cause the execution of the apparatus described above.

[0222] In some embodiments, an apparatus (e.g., network device 120) capable of performing any one of the methods 900 is provided. The apparatus may include components for performing the corresponding steps of method 900. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module.

[0223] In some embodiments, the apparatus includes: components for determining at least one of a resource configuration or a reference signal for performance monitoring associated with beam prediction accuracy; and components for transmitting at least one of the resource configuration or reference signals to a terminal device.

[0224] In some embodiments, the apparatus may further include a component for receiving an alarm associated with beam prediction accuracy from a terminal device.

[0225] In some embodiments, the apparatus may further include: a component for sending a request for a differential reference signal received power (RSRP) report to a terminal device based on the receipt of an alarm, the differential RSRP report having finer quantization than the previously received RSRP report.

[0226] In some embodiments, the apparatus may further include components for performing additional steps of some embodiments of method 900. In some embodiments, the components include at least one processor and at least one memory including computer program code, the at least one memory and the computer program code being configured to, together with the at least one processor, cause the execution of the apparatus described above.

[0227] In some embodiments, an apparatus (e.g., terminal device 110) is provided capable of performing any of the methods 1000. The apparatus may include components for performing the corresponding steps of method 1000. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module.

[0228] In some embodiments, the apparatus includes: components for sending a first Reference Signal Received Power (RSRP) report to a network device; components for receiving a request from the network device for a differential RSRP report having finer quantization than the first RSRP report; and components for sending a differential RSRP report with finer quantization to the network device.

[0229] In some embodiments, the apparatus may further include components for determining a differential RSRP report based on non-uniform quantization. In some embodiments, the differential RSRP report may be transmitted together with one of the following: a beam bitmap indicating at least one beam selected by the terminal device; or a bit array indicating at least one beam selected by the terminal device.

[0230] In some embodiments, the apparatus may include components for selecting at least one beam based on at least one of the following: at least one RSRP of at least one beam, predicted beam performance of at least one beam, channel quality, signal strength, or mobility of the terminal device.

[0231] In some embodiments, the apparatus may further include: a component for dividing the time domain into one or more groups of consecutive time instances, wherein the beam bitmap or bit array further indicates: at least one beam selected by the terminal device for at least one time instance in the group.

[0232] In some embodiments, the beam bitmap may include at least one index of at least one beam, and the at least one index corresponds to at least one bit in the beam bitmap.

[0233] In some embodiments, at least one of the following may be true: a first value of a bit in the beam bitmap may indicate that the beam corresponding to the bit is selected by the terminal device; or a second value of a bit in the beam bitmap may indicate that the beam corresponding to the bit is not selected by the terminal device.

[0234] In some embodiments, the apparatus may further include: a component for determining a bit array based on a Bloom filter. In some embodiments, the component for determining a bit array based on a Bloom filter may include: a component for initializing the bit array, wherein bits in the bit array are set to a first value; and a component for mapping at least one index of at least one beam to a first number of bits in the bit array using a first number of hash functions, wherein the first number of bits are set to a second value.

[0235] In some embodiments, the apparatus may further include a component for determining at least one of the length of the bit array or a first number of hash functions based on at least one of the target false alarm rate or the expected number of selected beams of the bit array.

[0236] In some embodiments, the apparatus may further include components for sending information associated with the bit array to a network device. In some embodiments, the information associated with the bit array may include at least one of the following: an identifier (ID) of a group indicated in the bit array, the length of the bit array, a first number of hash functions, or a seed for the hash functions.

[0237] In some embodiments, the apparatus may further include components for performing additional steps of some embodiments of method 1000. In some embodiments, the components include at least one processor and at least one memory including computer program code, the at least one memory and the computer program code being configured to, together with the at least one processor, cause the execution of the apparatus described above.

[0238] In some embodiments, an apparatus (e.g., network device 120) capable of performing any of the methods 1100 is provided. The apparatus may include components for performing the corresponding steps of method 1100. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module.

[0239] In some embodiments, the apparatus includes: components for receiving a first reference signal received power (RSRP) report from a terminal device; components for sending a request to the terminal device for a differential RSRP report having finer quantization than the first RSRP report; and components for receiving a differential RSRP report with finer quantization from the terminal device.

[0240] In some embodiments, a differential RSRP report may be received together with one of the following: a beam bitmap indicating at least one beam selected by the terminal device; or a bit array indicating at least one beam selected by the terminal device, wherein the bit array is determined based on a Bloom filter.

[0241] In some embodiments, the beam bitmap may include at least one index of at least one beam, and the at least one index corresponds to at least one bit in the beam bitmap.

[0242] In some embodiments, at least one of the following may be true: a first value of a bit in the beam bitmap may indicate that the beam corresponding to the bit is selected by the terminal device; or a second value of a bit in the beam bitmap may indicate that the beam corresponding to the bit is not selected by the terminal device.

[0243] In some embodiments, the apparatus may further include a component for receiving information associated with a bit array from a terminal device. In some embodiments, the information associated with the bit array may include at least one of the following: an identifier (ID) of a group indicating at least one time instance in the bit array, the length of the bit array, a first number of hash functions for determining the bit array, or a seed for determining the hash functions of the bit array.

[0244] In some embodiments, the apparatus may include components for sending the request based on at least one of: receiving an alarm associated with beam prediction accuracy from a terminal device; or determining to reduce the false alarm rate of the bit array.

[0245] In some embodiments, the apparatus may further include components for performing additional steps of some embodiments of method 1100. In some embodiments, the components include at least one processor and at least one memory including computer program code, the at least one memory and the computer program code being configured to, together with the at least one processor, cause the execution of the apparatus described above.

[0246] Figure 12 This is a simplified block diagram of a device 1200 suitable for implementing embodiments of the present disclosure. Device 1200 can be provided to implement a communication device, for example, Figure 1 The terminal device 110 or network device 120 shown. As shown, device 1200 includes one or more processors 1210, one or more memories 1220 coupled to processor 1210, and one or more communication modules 1240 coupled to processor 1210.

[0247] The communication module 1240 is used for bidirectional communication. The communication module 1240 has at least one antenna to facilitate communication. The communication interface can represent any interface required for communication with other network elements.

[0248] Processor 1210 can be of any type suitable for a local technology network, and by way of non-limiting example, can include one or more of the following: general-purpose computer, special-purpose computer, microprocessor, digital signal processor (DSP), and processor based on a multi-core processor architecture. Device 1200 can have multiple processors, such as application-specific integrated circuit chips that are time-dependent on a clock synchronized with the main processor.

[0249] Memory 1220 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 1224, electrically programmable read-only memory (EPROM), flash memory, hard disk, compact disc (CD), digital video disc (DVD), and other magnetic storage devices and / or optical storage devices. Examples of volatile memories include, but are not limited to, random access memory (RAM) 1222 and other volatile memories that do not persist during power outages.

[0250] Computer program 1230 includes computer-executable instructions that are executed by the associated processor 1210. Program 1230 may be stored in ROM 1224. Processor 1210 may perform any suitable actions and processes by loading program 1230 into RAM 1222.

[0251] Embodiments of this disclosure can be implemented using program 1230, enabling device 1200 to execute reference... Figures 2 to 5 Any process described in the exemplary embodiments of this disclosure. Embodiments of this disclosure may also be implemented by hardware or by a combination of software and hardware.

[0252] In some embodiments, program 1230 may be tangibly contained in a computer-readable medium, which may be included in device 1200 (such as memory 1220) or in other storage devices accessible by device 1200. Device 1200 may load program 1230 from the computer-readable medium into RAM 1222 for execution. The computer-readable medium may include any type of tangible non-volatile storage, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. Figure 13 An example of a computer-readable medium 1300 in the form of a CD or DVD is shown. The computer-readable medium has a program 1230 stored thereon.

[0253] In general, the various embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented using firmware or software that can be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of this disclosure are illustrated and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that, as non-limiting examples, the blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0254] Example embodiments of this disclosure also provide at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, which execute in a device on a target real or virtual processor to perform the above-referenced... Figures 6-11Methods 600, 700, 800, 900, 1000, and 1100 are described. Generally, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc., that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of a program module can be combined or split among program modules as needed. The machine-executable instructions for a program module can be executed on a local or distributed device. In a distributed device, a program module can reside on both local and remote storage media.

[0255] Program code for performing the methods of the exemplary embodiments of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that, when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0256] In the context of this disclosure, computer program code or related data may be carried by any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, etc.

[0257] Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable media can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any suitable combination of the foregoing. More specific examples of computer-readable storage media will include electrical connections having one or more wires, portable computer floppy disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable optical disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. The term "non-transient" as used herein is a limitation on the medium itself (i.e., tangible, not signaling), not a limitation on the persistence of data storage (e.g., RAM and ROM).

[0258] Furthermore, although operations are described in a specific order, this should not be construed as requiring the operations to be performed in the specific order shown or in sequential order, or to perform all of the shown operations to obtain the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the foregoing discussion, these should not be construed as limiting the scope of this disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features described in the context of a single embodiment may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0259] Although exemplary embodiments of this disclosure have been described in language specific to structural features and / or methodological actions, it should be understood that the exemplary embodiments of this disclosure as defined in the appended claims are not necessarily limited to the specific features or actions described above. Rather, the specific features or actions described above are disclosed as exemplary forms of implementing the claims.

[0260] The embodiments disclosed herein relate to the following examples.

[0261] Example 1. A terminal device for communication, comprising: At least one processor; and At least one memory stores instructions that, when executed by the at least one processor, cause the terminal device to at least: Receive at least one of the following from the network device: resource configuration or reference signal for performance monitoring associated with beam prediction accuracy; and Based on at least one of the resource configuration or the reference signal, a performance metric associated with the beam prediction accuracy is determined.

[0262] Example 2. The terminal device according to Example 1, wherein the terminal device is configured to determine the performance metric by: Perform at least one beam measurement based on the resource configuration or the reference signal; and The performance metric is determined based on the at least one beam measurement.

[0263] Example 3. The terminal device according to Example 1 or 2, wherein the performance metric includes an indicator of beam performance, and the indicator of beam performance is represented by at least one of a numerical value or a ratio.

[0264] Example 4. A terminal device according to any one of Examples 1 to 3, wherein the terminal device is configured to determine the performance metric by: The index of beam performance, represented by the numerical value, is determined based on a first number of at least one correctly predicted beam and a second number of predicted total beams.

[0265] Example 5. The terminal device according to any one of Examples 1 to 3, wherein the terminal device is further configured to: The index of beam performance, represented by the ratio, is determined based on at least one correct prediction of at least one beam in the predicted optimal beams and a fourth prediction of the predicted optimal beams.

[0266] Example 6. A terminal device according to any one of Examples 1 to 5, wherein the terminal device is configured to: determine the performance metric based on an artificial intelligence / machine learning (AI / ML) model.

[0267] Example 7. The terminal device according to Example 6, wherein at least one of the following: The input to the AI / ML model includes at least one beam measurement; or The output of the AI / ML model includes the performance metric.

[0268] Example 8. The terminal device according to any one of Examples 1 to 7, wherein the terminal device is further configured to: Determine whether the performance metric is greater than a threshold; and Based on the determination that the performance metric is less than the threshold, an alarm associated with the beam prediction accuracy is sent to the network device.

[0269] Example 9. The terminal device according to Example 8, wherein the terminal device is further configured to: The network device receives a request for a Differential Reference Signal Received Power (RSRP) report, the differential RSRP report having finer quantization than the previously sent differential RSRP report, wherein the request is in response to the alarm.

[0270] Example 10. A network device for communication, comprising: At least one processor; and At least one memory storing instructions that, when executed by the at least one processor, cause the network device to at least: Determine at least one of the resource configurations or reference signals used for performance monitoring associated with beam prediction accuracy; and Send at least one of the resource configuration or the reference signal to the terminal device.

[0271] Example 11. The network device according to Example 10, wherein the network device is further configured such that: Receive an alarm associated with the beam prediction accuracy from the terminal device.

[0272] Example 12. The network device according to Example 10 or 11, wherein the network device is further configured to: Based on the received alarm, a request for a Differential Reference Signal Received Power (RSRP) report is sent to the terminal device, the differential RSRP report having finer quantization than the previously received differential reference signal received power (RSRP) report.

[0273] Example 13. A method for communication, comprising: At the terminal device and from the network device, at least one of the following is received: resource configuration or reference signal for performance monitoring associated with beam prediction accuracy; and Based on at least one of the resource configuration or the reference signal, a performance metric associated with the beam prediction accuracy is determined.

[0274] Example 14. A method for communication, comprising: At the network device, determine at least one of the resource configuration or reference signal used for performance monitoring associated with beam prediction accuracy; and Send at least one of the resource configuration or the reference signal to the terminal device.

Claims

1. A terminal device for communication, comprising: At least one processor; as well as At least one memory stores instructions that, when executed by the at least one processor, cause the terminal device to at least: Receive at least one of the following from the network device: a resource configuration or a reference signal for performance monitoring associated with beam prediction accuracy; as well as Based on at least one of the resource configuration or the reference signal, a performance metric associated with the beam prediction accuracy is determined.

2. The terminal device of claim 1, wherein the terminal device is configured to determine the performance metric by: Perform at least one beam measurement based on the resource configuration or the reference signal; and The performance metric is determined based on the at least one beam measurement.

3. The terminal device according to claim 1 or 2, wherein the performance metric includes an indicator of beam performance, and the indicator of beam performance is represented by at least one of a numerical value or a ratio.

4. The terminal device of claim 1, wherein the terminal device is configured to determine the performance metric by: The index of beam performance, represented by the numerical value, is determined based on a first number of at least one correctly predicted beam and a second number of predicted total beams.

5. The terminal device according to claim 1, wherein the terminal device is further configured to: The index of beam performance, represented by the ratio, is determined based on at least one correct prediction of at least one beam in the predicted optimal beams and a fourth prediction of the predicted optimal beams.

6. The terminal device of claim 1, wherein the terminal device is configured to: determine the performance metric based on an artificial intelligence / machine learning (AI / ML) model.

7. The terminal device according to claim 6, wherein at least one of the following: The input to the AI / ML model includes at least one beam measurement; or The output of the AI / ML model includes the performance metric.

8. The terminal device according to claim 1, wherein the terminal device is further configured to: Determine whether the performance metric is greater than a threshold; and Based on the determination that the performance metric is less than the threshold, an alarm associated with the beam prediction accuracy is sent to the network device.

9. The terminal device according to claim 8, wherein the terminal device is further configured to: The network device receives a request for a Differential Reference Signal Received Power (RSRP) report, the differential RSRP report having finer quantization than the previously sent RSRP report, wherein the request is in response to the alarm.

10. A network device for communication, comprising: At least one processor; as well as At least one memory storing instructions that, when executed by the at least one processor, cause the network device to at least: Determine at least one of the resource configurations or reference signals used for performance monitoring associated with beam prediction accuracy; as well as Send at least one of the resource configuration or the reference signal to the terminal device.

Images