Method of communication

Abstract

Exemplary embodiments of the present disclosure relate to a method of communication, a terminal device, a network device, and a computer-readable medium. In an exemplary method, the terminal device may determine beam information of a first number of beams predicted by an artificial intelligence (AI) model, and the terminal device may generate a beam report including a first indication regarding the first number and beam information of a second number of predicted beams among the first number of predicted beams, and the terminal device may transmit the beam report to a network device. In this way, it helps the network device and the terminal device to determine an optimal beam and also helps to determine the generalization performance of the AI model.

Description

Technical Field

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

Background Art

[0002] In communication technologies, there has been an ongoing evolution to provide efficient and reliable solutions for utilizing wireless communication networks. Each new generation has its own technical challenges in dealing with different situations and processes required to connect to and serve devices connected to the wireless network. In order to meet the growing demand for wireless data traffic since the introduction of the fourth generation (4G) communication system, efforts have been made to develop an improved fifth generation (5G) or pre-5G communication system. The new communication system can support various types of service applications for terminal devices.

[0003] Regarding AI / ML (Artificial Intelligence / Machine Learning)-based beam management, for characterization and baseline performance evaluation, it supports BM (Beam Management) case 1 (spatial region DL beam prediction for set A of beams based on measurement results of set B of beams) and BM case 2 (temporal DL beam prediction for set A of beams based on past measurement results of set B of beams). BM case 1 and BM case 2 are based on classification and regression, respectively. However, various aspects of the methods related to AI / ML-based beams need further research and improvement.

Summary of the Invention

Problems to be Solved by the Invention

[0004] Overall, embodiments of the present disclosure provide a communication method, a terminal device, a network device, and a computer-readable medium.

Means for Solving the Problem

[0005] In a first aspect, a communication method is provided. The method includes, at a terminal device, determining beam information of a first number of beams predicted by an artificial intelligence (AI) model, generating a beam report including a first indication regarding the first number and beam information of a second number of predicted beams among the first number of predicted beams, and transmitting the beam report to a network device.

[0006] In a second aspect, a communication method is provided. The method includes, at a terminal device, determining beam information of a first number of beams predicted by an artificial intelligence (AI) model, generating a beam report including beam information of a second number of predicted beams among the first number of predicted beams and a second indication indicating whether the first number is greater than, less than, or equal to a value of the number of beams reported by the terminal device set by the network device, and transmitting the beam report to a network device.

[0007] In a third aspect, a communication method is provided. The method includes, at a network device, receiving, from a terminal device, a beam report including a first indication regarding a first number and beam information of a second number of predicted beams among the first number of predicted beams, where the predicted beams are predicted by an artificial intelligence (AI) model, and processing the beam report.

[0008] In a fourth aspect, a communication method is provided. The method includes, in a network device, receiving, from a terminal device, beam information of a second number of predicted beams among a first number of predicted beams predicted by an artificial intelligence (AI) model, and a second indication indicating whether the first number is greater than, less than, or equal to a value of the number of beams reported by the terminal device and set by the network device, and processing the beam report.

[0009] In a fifth aspect, a terminal device is provided. The terminal device includes a processor and a memory storing computer program code, and the memory and the computer program code are configured to, together with the processor, cause the terminal device to execute the method described in the first aspect above.

[0010] In a sixth aspect, a network device is provided. The network device includes a processor and a memory storing computer program code, and the memory and the computer program code are configured to, together with the processor, cause the network device to execute the method described in the second aspect above.

[0011] In a seventh aspect, a computer-readable medium storing instructions for causing at least one processor to execute the method described in the first aspect or the second aspect above when executed on the at least one processor is provided.

[0012] It should be understood that the summary part of the invention is not intended to identify important or fundamental features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure should be easily understood from the following description.

Brief Description of the Drawings

[0013] By further elaborating several exemplary embodiments of the present disclosure in the accompanying drawings, the above and other objects, features, and advantages of the present disclosure will become more apparent.

[0014]

Figure 1

[0015]

Figure 2

[0016]

Figure 3

[0017]

Figure 4

[0018]

Figure 5

[0019]

Figure 6

[0020]

Figure 7

[0021]

Figure 8

[0022]

Figure 9

[0023]

Figure 10

[0024]

Figure 11

[0025]

Figure 12

[0026]

Figure 13

[0027]

Figure 14

[0028]

Figure 15

[0029]

Figure 16

[0030] In the figure, the same or similar reference numerals represent the same or similar elements.

Embodiments for Carrying Out the Invention

[0031] Here, the principles of the present disclosure will be explained with reference to some exemplary embodiments. These embodiments are described for illustrative purposes only and are intended to assist those skilled in the art in understanding and implementing the present disclosure, and should not be construed as suggesting any limitation on the scope of the present disclosure. The embodiments described herein can be implemented in various ways different from the methods described below.

[0032] 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.

[0033] References to "one embodiment", "an embodiment", "an exemplary embodiment", etc. in this disclosure indicate that the described embodiment can include a particular feature, structure, or characteristic, but each embodiment does not necessarily include that particular feature, structure, or characteristic. Further, such phrases do not necessarily refer to the same embodiment. Moreover, when a particular feature, structure, or characteristic is described in relation to an embodiment, it is considered within the knowledge of one of ordinary skill in the art to affect such feature, structure, or characteristic in relation to other embodiments, whether or not explicitly described.

[0034] It should be understood that terms such as "first" and "second" can be used herein to describe various elements, but these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of the exemplary embodiments, a first element could be named a second element, and similarly, a second element could be named a first element. As used herein, the term "and / or" includes any and all combinations of one or more of the recited terms.

[0035] The terms used in this specification are for the purpose of describing particular embodiments only and are not intended to limit the exemplary embodiments. As used in this specification, the singular forms "a", "an", and "the" also include the plural forms unless the context clearly dictates otherwise. As used herein, the terms "comprising", "including", "having", "containing", "composed of", and / or "possessing" specify the presence of the stated features, elements, and / or components, etc., but do not preclude the presence or addition of one or more other features, elements, components, and / or combinations thereof.

[0036] In some instances, values, procedures, or devices are referred to as "best", "lowest", "highest", "minimum", "maximum", etc. Such descriptions are intended to indicate that a selection can be made from among a number of functional alternatives that are used, and it should be understood that such a selection need not be better, smaller, higher, or otherwise more preferred than other selections.

[0037] As used herein, the term "communication network" means a network that complies with any suitable communication standard, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA®), High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB-IoT), and the like. Further, the communication between the terminal device and the network device in the communication network may be realized according to any suitable generation of communication protocol, including but not limited to the first generation (1G), second generation (2G), 2.5G, 2.75G, third generation (3G), fourth generation (4G), 4.5G, fifth generation (5G), 5.5G, 5G-Advanced network or sixth generation (6G) communication protocol, and / or any other protocol known currently or developed in the future. Embodiments of the present disclosure are applicable to various communication systems. In view of the rapid development of communication, there will naturally be future types of communication technologies and systems in which the present disclosure can be implemented. This should not be regarded as limiting the scope of the present disclosure to only the aforementioned systems.

[0038] As used herein, the term "terminal device" refers to any device having wireless or wired communication capabilities. Examples of terminal devices include user equipment (UE), personal computers, desktops, mobile phones, cellular phones, smartphones, personal digital assistants (PDAs), portable computers, tablets, wearable devices, Internet of Things (IoT) devices, Ultra-reliable and Low Latency Communication (URLLC) devices, Internet of Everything (IoE) devices, machine type communication (MTC) devices, in-vehicle devices for vehicle-to-everything (V2X) communication where X means pedestrian, vehicle, or infrastructure / network, devices for Integrated Access and Backhaul (IAB), satellite-mounted vehicles or aircraft-mounted vehicles in non-terrestrial networks (NTN) including high altitude platforms (HAP) that include satellites and unmanned aircraft systems (UAS), extended reality (XR) devices including different types of reality such as extended reality (AR), mixed reality (MR), virtual reality (VR), unmanned aerial vehicles (UAVs) commonly referred to as drones which are aircraft without human pilots, devices on high speed trains (HSTs), or image acquisition devices such as digital cameras, sensors, game devices, music storage and playback devices, or Internet devices enabling wireless or wired Internet access and browsing, etc., but are not limited thereto.The "terminal device" can further have a multicast / broadcast function and support public safety, mission-critical, V2X applications, transparent IPv4 / IPv6 multicast delivery, IPTV, smart TV, wireless services, wireless software delivery, group communication, and IoT applications. Also, one or more subscriber identity modules (SIMs), known as multi-SIM, may be incorporated. The term "terminal device" may be used interchangeably with UE, mobile station, subscriber station, mobile terminal, user terminal, or wireless device.

[0039] As used herein, the term "network device" means a device that can provide or host a cell or coverage with which a terminal device can communicate. Examples of network devices include, but are not limited to, satellites, unmanned aerial system (UAS) platforms, Node B (NodeB or NB), evolved Node B (eNodeB or eNB), next generation Node B (gNB), transmission reception point (TRP), remote radio unit (RRU), radio head (RH), remote radio head (RRH), IAB node, femto node, low-power nodes such as pico nodes, reconfigurable intelligent surface (RIS), etc.

[0040] The communications described in this specification may conform to any suitable standard, including but not limited to New Radio Access (NR), Long Term Evolution (LTE), LTE-Evolution, LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access (CDMA), cdma2000, and Global System for Mobile Communication (GSM) for mobile communications. Further, the communications may be performed according to any generation of communication protocol known currently or developed in the future. Examples of communication protocols include, but are not limited to, the first generation (1G), the second generation (2G), 2.5G, 2.85G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G), and the sixth generation (6G) communication protocols. The techniques described in this specification can be used in the wireless networks and wireless technologies described above, as well as other wireless networks and wireless technologies. Embodiments of the present disclosure may be performed according to any generation of communication protocol known currently or developed in the future.Examples of communication protocols include, but are not limited to, the first generation (1G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G) communication protocol, 5.5G, 5G-Advanced network, or the sixth generation (6G) network.

[0041] The terminal device or network device may have the ability of artificial intelligence (AI) or machine learning. Generally, it includes a trained model from a large number of data collected for a specific function and can be used to predict some information.

[0042] The terminal device or network device may operate on several frequency ranges such as FR1 (410 MHz to 7125 MHz), FR2 (24.25 GHz to 71 GHz), frequency bands greater than 100 GHz, and terahertz (THz). Furthermore, it can operate on licensed / unlicensed / shared spectrum. The terminal device may have two or more connections with the network device under a multi-radio dual connectivity (MR-DC) application scenario. The terminal device or network device can operate in full-duplex, flexible-duplex, cross-split duplex modes.

[0043] Embodiments of the present disclosure may be implemented in test equipment such as, for example, a signal generator, a signal analyzer, a spectrum analyzer, a network analyzer, a test terminal device, a test network device, or a channel emulator.

[0044] Embodiments of the present disclosure may be implemented according to any generation of communication protocols that are currently known or will be developed in the future. Examples of communication protocols include, but are not limited to, the first generation (1G), second generation (2G), 2.5G, 2.75G, third generation (3G), fourth generation (4G), 4.5G, fifth generation (5G) communication protocol, 5.5G, 5G-Advanced network, or sixth generation (6G) network.

[0045] As used herein, the term "circuit" may mean a hardware circuit and / or a combination of a hardware circuit and software. For example, a circuit may be a combination of analog and / or digital hardware circuits and software / firmware. As yet another example, a circuit may be any part of a hardware processor with software, including a digital signal processor, software, and one or more memories, that cooperate to cause a device, such as a terminal device or a network device, to perform various functions. In yet another example, a circuit may be a hardware circuit and / or a processor, such as a microprocessor or a part thereof, that requires software / firmware for operation, but the software may not be present if it is not required for operation. As used herein, the term "circuit" also includes only a hardware circuit or one or more processors, or an implementation of a part of a hardware circuit or one or more processors and its (or their) accompanying software and / or firmware.

[0046] As used herein, the singular forms "a", "an", and "the" include the plural forms as well, unless the context clearly dictates otherwise. The terms "comprising" and variations thereof should be construed as open-ended terms meaning "including, but not limited to". The term "based on" should be construed as "at least partially based on". The terms "one embodiment" and "an embodiment" should be construed as "at least one embodiment". The term "another embodiment" should be construed as "at least one other embodiment". Terms such as "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0047] In some instances, values, procedures, or devices are referred to as "best", "lowest", "highest", "minimum", "maximum", etc. Such descriptions are intended to indicate that a selection can be made from among a number of available functional alternatives, and it should be understood that such a selection need not be better, smaller, higher, or otherwise more preferred than other selections.

[0048] Hereinafter, with reference to the accompanying drawings, the principles and embodiments of the present disclosure will be described in detail. According to [R1-2205454, Overview of discussions on other aspects of AI / ML (Artificial intelligence / Machine learning) for BM #4], the following potential specification impacts are studied. (1) New or extended mechanisms to facilitate data collection for UE / NW (Network) models, such as training, fine-tuning, and verification. For example, some of the following examples were mentioned in the contributions. Extended BM procedures (including signaling / configuration, reporting) to facilitate the collection of training data, introduction of some new information, such as UE positioning, information from sensors (e.g., speed, orientation, rotation), and other auxiliary information for training. (2) New or extended mechanisms to facilitate AI / ML inference. For example, some of the following examples were mentioned in the contributions. Extended BM measurements / reports for AI inference, signaling / configuration for the extended BM measurements / reports, and auxiliary information for AI inference. (3) New or extended mechanisms to facilitate the lifecycle management of AI models. For example, some of the following examples were mentioned in the contributions. Mechanisms / auxiliary information for activation and deactivation of AI / ML models, mechanisms / auxiliary information for the selection of AI models, and mechanisms / auxiliary information for performance monitoring. It may include the exchange of some auxiliary information. (4) AI-related UE capabilities and reports. (5) Interfaces of AI models, such as inputs and outputs. (6) Other extensions.

[0049] According to RAN1#109-e [Chairman's Memo RAN1#109-ev15], for AI / ML-based beam management, to support characterization and baseline performance evaluation, BM Case 1 and BM Case 2 are considered. BM Case 1: Spatial domain DL beam prediction for set A of beams based on measurement results for set B of beams. BM Case 2: Temporal DL beam prediction for set A of beams based on past measurement results for set B of beams. For BM Case 1 and BM Case 2, the beams within set A and set B may be in the same frequency range.

[0050] According to RAN1#109-e [Chairman's Memo RAN1#109-ev15] and [R1-2205454, Summary of Discussions on Other Aspects of AI / ML for Beam Management #4], for sub-case BM Case 1, two alternatives are considered for further study. The first alternative is that set B is a subset of set A. The number of beams within set A and set B and how to determine set B from the beams within set A (e.g., fixed pattern, random pattern, etc.) can be studied. The second alternative is that set A and set B are different (e.g., set A consists of narrow beams and set B consists of wide beams). The number of beams within set A and set B and the QCL (Quasi-co location) relationship between the beams within set A and the beams within set B can be studied. Set A is for DL beam prediction and set B is for DL beam measurement. The terms "narrow beam" and "wide beam" are for SI discussions only and have no impact on the specifications. The codebook construction for set A and set B may be clarified by the company.

[0051] For Sub-Use Case BM Case 1, consider both Alternative 1 and Alternative 2 for further research. Alternative 1: AI / ML inference on the NW side. Alternative 2: AI / ML inference on the UE side. According to RAN1#109-e [Chair's Memo RAN1#109-e v15], for the input of the AI model, for Sub-Use Case BM Case 1, further research the following alternatives for AI / ML input. Alternative 1: Only L1-RSRP measurements based on Set B. Alternative 2: L1-RSRP measurements based on Set B and auxiliary information. In this discussion, the following was mentioned by the attendees. Tx and / or Rx beam shape information (e.g., Tx and / or Rx beam pattern, Tx and / or Rx beam aiming direction (azimuth and elevation angle), 3dB beamwidth, etc.), predicted Tx and / or Rx beams for prediction (e.g., predicted Tx and / or Rx angles, Tx and / or Rx beam IDs (CRI or SSBRI) for prediction), UE location information, UE direction information, Tx beam utilization information, UE orientation information, etc. The provision of auxiliary information may be impossible to achieve because there are concerns about disclosing confidential information to the other party. Alternative 3: CIR based on Set B. Alternative 4: L1-RSRP measurements based on Set B and the corresponding DL Tx and / or Rx beam IDs. It depends on the company whether to provide other alternatives including combinations of some alternatives. All inputs are "nominal" and only for discussion purposes.

[0052] According to [RAN1#109-e [R1-2205454, Summary of Discussion on Other Aspects of AI / ML for Beam Management #4]], regarding the output of the AI model, for sub-case BM case 1, further study the following alternatives for AI / ML output. Alternative 1: For the predicted top N1 DL Tx and / or Rx beams, the Tx and / or Rx beam IDs and / or the predicted L1-RSRP. The method for selecting the top N1 DL Tx and / or Rx beams (e.g., L1-RSRP higher than a threshold, total probability of being the best beam higher than a threshold). Alternative 2: For the predicted top N1 DL Tx and / or Rx beams, the Tx and / or Rx beam IDs, and other information (e.g., the probability that the beam is the best beam, updated set B). Alternative 3: The predicted RSRP corresponding to the Tx and / or Rx beam directions input to the model. Alternative 4: For the predicted top N1 DL Tx and / or Rx beams, the Tx and / or Rx beam angles and the predicted RSRP (optional). Whether to provide other alternatives depends on the company. The beam ID is only used for discussion purposes. All outputs are "nominal" and only for discussion purposes. The value of N1 depends on each company.

[0053] As described above, various aspects of the AI / ML-based beam-related methods need to be further studied and improved. In order to solve at least these and potential other technical problems in the art, exemplary embodiments of the present disclosure provide several solutions for reporting the beams predicted by the AI model. The embodiments of the present disclosure can help the network device and the terminal device determine the optimal beam and can also help determine the generalization performance of the AI model. Hereinafter, with reference to the accompanying drawings, the principles of the present disclosure and some exemplary embodiments will be described in detail.

[0054] FIG. 1 shows an exemplary communication system 100 in which some embodiments of the present disclosure can be implemented. The communication system 100, which is part of a communication network, includes a network device 120 and a terminal device 110.

[0055] The network device 120 can provide services to the terminal device 110, and the network device 120 and the terminal device 110 may communicate data and control information with each other. In some embodiments, the network device 120 and the terminal device 110 may communicate using a direct link / channel.

[0056] In the system 100, the link from the network device 120 to the terminal device 110 is referred to as a downlink (DL), and the link from the terminal device 110 to the network device 120 is referred to as an uplink (UL). In the downlink, the network device 120 is a transmitting (TX) device (or transmitter), and the terminal device 110 is a receiving (RX) device (or receiver). In the uplink, the terminal device 110 is a transmitting TX device (or transmitter), and the network device 120 is an RX device (or receiver). It should be understood that the network device 120 may provide one or more serving cells. In some embodiments, the network device 120 may provide multiple cells.

[0057] Communication in the communication system 100 may comply with any suitable standard, including but not limited to Long Term Evolution (LTE), LTE-Evolution, LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access (CDMA), and Global System for Mobile Communication (GSM) for mobile communication. Further, the communication may be performed according to any generation of communication protocol known currently or developed in the future. Examples of communication protocols include, but are not limited to, the first generation (1G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G), 5.5G, 5G-Advanced network, or the sixth generation (6G) communication protocol.

[0058] It should be understood that the number of devices shown in FIG. 1 and their connection relationships and types are provided for illustrative purposes only and do not imply any limitation. The communication system 100 may include any suitable number of devices suitable for implementing the embodiments of the present disclosure. In some embodiments, the network device 120 may provide a plurality of cells.

[0059] FIG. 2 is a schematic diagram showing a process 200 of communication between the terminal device 110 and the network device 120. As shown in FIG. 2, in the terminal device 110, the terminal device 110 may determine beam information of a first number of beams predicted by an artificial intelligence (AI) model (210), the terminal device 110 may generate a beam report (205) including a first indication regarding the first number and beam information of a second number of predicted beams among the first number of predicted beams (220), and then the terminal device 110 may transmit the beam report (205) to the network device 120 (230).

[0060] In the network device 120, the network device 120 may receive, from the terminal device 110, a beam report (205) including a first indication regarding a first number and beam information of a second number of predicted beams among the first number of predicted beams (240), where the predicted beams are predicted by an artificial intelligence (AI) model, and the network device 120 may process the beam report (205) (250). In this way, it helps the network device 120 and the terminal device 110 to determine the optimal beam and also helps to determine the generalization performance of the AI model.

[0061] In some embodiments, the beam report refers to a CSI report carrying L1-RSRP, L1-SINR, CRI or SSBRI, or a CSI report having a reporting amount of "cri-RSRP", "ssb-Index-RSRP", "cri-SINR" or "ssb-Index-SINR", etc. The beam of the target signal refers to the QCL type D (source) reference signal of the target signal. The beam information refers to a beam ID and the corresponding beam quality. The beam ID refers to CRI or SSBRI. The beam quality refers to L1-RSRP or L1-SINR. The QCL type D refers to a spatial Rx parameter. In some embodiments, the AI model is used to predict, output, infer or determine one or more optimal beams.

[0062] To more clearly explain the method of the embodiments of the present disclosure, first, the AI model is introduced as follows. FIG. 3 shows an example of an AI model for predicting the best beam. As shown in FIG. 3, the AI model predicts the best beam based on classification. That is, the input of the AI model is the L1-RSRP (Layer 1 Reference Signal Received Power) corresponding to four beams (i.e., set B), and it is assumed that set A consists of 16 beams. Set B is a set of beams or beam IDs as the input of the AI model. One or more beams (including beam ID and beam quality) output by the AI model are from set A. Additionally, set B may be a subset of set A. Overall, the AI model may be used to estimate one or more beams (e.g., one or more optimal beams) within set A using a part of the beams within set A (i.e., set B). The AI model can first obtain the probability (or weight ratio) that each beam (within set A) is the best beam. Ideally or generally, as shown in FIG. 3, only one beam has the highest probability. Then, the AI model can output the beam with the highest probability as the predicted best beam (i.e., the top 1 beam within set A). As shown in FIG. 3, the highest probability is 0.999, and the ID of the beam output by the AI model is 3.

[0063] FIG. 4 shows another example of an AI model for predicting the best beam. As shown in FIG. 4, the AI model predicts the best beam based on classification. In some cases, for example, the actual qualities corresponding to multiple beams are close. In some other cases, for example, the inference performance of the AI model in the current environment is poor, i.e., the generalization performance is poor. Since the probabilities that multiple beams are the best beam are close and these probabilities are clearly higher than other probabilities, the AI model can output these beams as the predicted best beams, i.e., the top 4 beams within set A. As shown in FIG. 4, the IDs of the beams output by the AI model are 2, 3, 4, and 5.

[0064] Figure 5 shows another example of an AI model for predicting the best beam. As shown in Figure 5, the AI model predicts the best beam based on regression. The AI model can first estimate the L1-RSRP corresponding to each beam (within set A). Ideally or generally, as shown in Figure 5, only one beam has the highest L1-RSRP (which is relatively obvious). Then, the AI model can output the beam with the highest L1-RSRP as the predicted best beam (i.e., the top 1 beam within set A). As shown in Figure 5, the ID of the beam output by the AI model is 3.

[0065] Figure 6 shows yet another example of an AI model for predicting the best beam. As shown in Figure 6, the AI model predicts the best beam based on regression. In some cases, for example, the actual quality corresponding to multiple beams is close. In some other cases, for example, the inference performance of the AI model in the current environment is poor, i.e., the generalization performance is poor. Since the estimated L1-RSRPs corresponding to multiple beams are close and thus coincide, and these L1-RSRPs are clearly higher than other L1-RSRPs, the AI model can output these beams as the predicted best beams, i.e., the top 4 beams within set A. As shown in Figure 6, the IDs of the beams output by the AI model are 2, 3, 4, and 5.

[0066] Referring to the AI model in FIGS. 3 to 6, the number of predicted beams output by the AI model is indefinite. That is, the value of N1 is indefinite and depends on the AI model. The value of K depends on the gNB settings. When the AI model is deployed on the gNB side, the value of N1 is determined by the gNB. When N1>1, the gNB can trigger a beam report for the predicted beams to determine the actual best beam. When the AI model is deployed on the UE side, the value of N1 is determined by the UE. As a result, the following situations may occur. In the first situation, N1 = K and there is no problem. In the second situation, N1>K, which means that the UE reports only K beams out of the N1 predicted beams output by the AI model. However, in reality, the actual best beam may be any one of the N1 predicted beams, for example, any one of the N1 - K beams. Therefore, in this method, there is a possibility that the gNB cannot obtain the actual best beam. Additionally, even if this problem is tolerated, the UE cannot determine the cause of N1>1, for example, whether it is the previously mentioned case 1 or case 2. In case 1, there is no problem. However, in case 2, it should not be tolerable.

[0067] To solve this problem, the UE needs to report N1 predicted beams to the gNB. Then, the gNB triggers beam reporting (i.e., beam measurement and reporting) for the N1 predicted beams. In a third scenario, N1 < K, for example, N1 = 1 and K = 4, which means that the UE only needs to report one beam, but the gNB reserves resources for four beams. This may lead to waste of resources for beam reporting. In conclusion, when the AI model is deployed on the UE side, the UE needs to report the N1 predicted beams output by the AI model to the gNB. This means that the number of beams to be reported is not fixed but variable (i.e., depends on the set K). Embodiments of the present disclosure can solve the above problems. Details will be described below.

[0068] In some embodiments of the present disclosure, the UE is taken as an example of the terminal device 110, and the gNB is taken as an example of the network device 120. It should be noted that the terminal device 110 in the embodiments of the present disclosure is not limited to the UE, and the network device 120 is not limited to the gNB.

[0069] In some embodiments, the terminal device 110 may determine the payload size of the first indication based on the number of channel state information reference signals (CSI-RS) or synchronization signal and PBCH block (SSB) resources corresponding to the beam reporting. In some embodiments, the terminal device 120 may determine the payload size of the first indication based on the value of the number of beams reported by the terminal device 110 set by the network device 120. In some embodiments, the value of the number of beams reported by the terminal device 110 set by the network device 120 is determined by the network device 120 based on the capability information of the terminal device 110.

[0070] In the network device 120, in some embodiments, the network device 120 may receive the capability information of the terminal device 110 and may determine the value based on the capability information of the terminal device 110. Therefore, in the network device 120, in some embodiments, the network device 120 may determine the payload size of the first indication based on the number of channel state information reference signals (CSI-RS) or synchronization signals and PBCH blocks (SSB) resources corresponding to the beam report.

[0071] In some embodiments, the network device 120 may determine the payload size of the first indication based on the value of the number of beams reported by the terminal device 110 set by the network device 120. In some embodiments, the network device 120 may determine the payload size of the first indication based on the capability information of the terminal device 110 indicating the maximum number of beams predicted by the AI model.

[0072] In some embodiments, the terminal device 110 may determine the payload size of the first indication based on the capability information of the terminal device 110 indicating the maximum number of beams predicted by the AI model. In some embodiments, the beam report includes a first part including the first indication and a second part including the beam information of the second number of predicted beams.

[0073] As shown in FIG. 7 showing an example of a schematic diagram of the beam report configuration, the beam report consists of two parts, namely, part 1 and part 2. Part 1 includes at least an indication of the number of beams to be reported (or the number of beams output by the AI model), and part 2 includes at least beam information. In these embodiments, the terminal device 110 may determine the second number based on the first number indicated by the first indication.

[0074] Referring to FIG. 7, in some embodiments, the beam report on PUCCH / PUSCH consists of two parts as described above. In some embodiments, Part 1 has a fixed payload size (or bit width) and is used to specify the number of information bits in Part 2. Part 1 will be transmitted in its entirety before Part 2. Part 1 includes an indication of the number of beams to be reported (abbreviated as the "first indicator"). Specifically, the first indicator refers to the number of beams to be reported within the beam report or within Part 2. Further, the first indicator may refer to the number of predicted beams output by the AI model.

[0075] Additionally, the number of beams to be reported may also be used as a metric / quantity reflecting the performance of the AI model. Part 2 has a variable payload size and is determined based on the number of beams to be reported indicated by the indication in Part 1. The first indicator is an example of the first indication. By reporting a beam report including two parts, the network device 120 first receives Part 1, and after obtaining the number of beams to be reported from Part 1, the network device 120 determines the payload size of Part 2. This is beneficial for further blind detection by the network device 120.

[0076] In some embodiments, an additional indication of the number of beams (or the number of beams to be reported) output by the AI model is introduced. This indication is applied to the current beam report. Part 1 includes fixed information, such as an indication, and Part 2 includes variable information, such as beam information. In some embodiments, Part 1 includes only an indication of the number of beams to be reported. For example, the indication in Part 1 indicates that there are N beams to be reported. In some embodiments, the beam information includes the CRI (CSI-RS resource indicator) of the beam to be reported. In some embodiments, the beam information includes the CRI and L1-RSRP of the beam to be reported.

[0077] According to the above example, the payload size of the beam information in part 2 needs to be determined based on the total bit width for the information of N beams, for example, N CRIs and N L1-RSRPs. That is, it may be determined based on existing beam reports, such as group-based beam reports: N CRIs, 1 absolute L1-RSRP (for example, there are 7 bits), and N - 1 differential L1-RSRPs (for example, there are 4 bits each).

[0078] In some embodiments, it is a CSI report that carries L1-RSRP, L1-SINR (layer 1 Signal to interference plus noise ratio), CRI, or SSBRI (SSB resource indicator), or a CSI report having a reporting amount of "cri-RSRP", "ssb-Index-RSRP", "cri-SINR", or "ssb-Index-SINR". In some embodiments, the beam information may include a beam ID and a corresponding beam quality (L1-RSRP or L1-SINR).

[0079] Referring to FIG. 7, in some embodiments, the payload size (or bit width) of the first indicator may be determined based on one of the following information. In some embodiments, it is the number of CSI-RS (Channel state information reference signal) / SSB (Synchronization Signal and PBCH block) resources corresponding to (or set in) the beam report. Specifically, the payload size may be determined based on the following formula.

[0080]

Equation

[0081] Here, KS CSI-RS is the number of corresponding CSI-RS / SSB resources. For example, K S CSI-RS Assuming that K is equal to 64, the payload size of the first indicator has 6 bits. Also, "000000" means there is 1 beam to report, "000001" means there are 2 beams to report, and so on.

[0082] In some embodiments, the set value of K corresponds to beam reporting (if K is not set, it is equal to 1). Specifically, the following formula may be adopted to determine the payload size.

[0083]

Number

[0084] This means that the number of beams to report needs to be less than or equal to the value of K. For example, assuming that K is equal to 8, the payload size of the first indicator has 3 bits. Also, "000" means there is 1 beam to report, "001" means there are 2 beams to report, and so on. The value of K depends on the new UE (User Equipment) capability (referred to as the "first UE capability"). The first UE capability may refer to the maximum number of predicted beams output by the AI model.

[0085] In this way, the network device 120 can determine the value of K based on the first UE capability. For example, if the value of the first UE capability is Nmax, so the network device 120 can determine that the value of K is less than or equal to Nmax. Also, since the resources are set according to the UE capability, waste of resources is avoided.

[0086] In some embodiments, assuming that the first UE capability is represented by "Nmax", the following formula may be adopted to determine the payload size.

[0087]

Number

[0088] In this case, the payload size (or bit width) of the first indicator may be determined by the terminal device 110 based on the capability information.

[0089] In some embodiments, the beam report includes a first portion including beam information of one beam of the first indication and the predicted beam, and a second portion including beam information of a second number of predicted beams.

[0090] In some embodiments, the terminal device 110 may determine the second number based on the first number indicated by the first indication. In these embodiments, the terminal device 110 may determine the payload size of the beam information in the first portion based on a CSI-RS resource indicator (CRI) and an absolute reference signal received power (RSRP).

[0091] In these embodiments, the terminal device 110 may determine the payload size of the beam information in the second portion based on the second number of CRIs and the second number of differential RSRPs. Therefore, in the network device 120, in some embodiments, the network device 120 may determine the second number based on the first number indicated by the first indication.

[0092] In the network device 120, in some embodiments, the network device 120 may determine the payload size of the beam information in the first portion based on a CSI-RS resource indicator (CRI) and a reference signal received power (RSRP). In some embodiments, the network device 120 may determine the payload size of the beam information in the second portion based on a second number of CRIs and a second number of differential RSRPs.

[0093] In some embodiments, the first portion includes a first indication and beam information of one of the predicted beams. In other words, in addition to the first indicator, part 1 may further include beam information of the best (predicted) beam, that is, the top 1 beam among the predicted N beams. At the same time, part 2 includes beam information of other beams to be reported.

[0094] FIG. 8 shows another example of a schematic diagram of a beam reporting configuration. As shown in FIG. 8, in addition to the first indicator, part 1 further includes beam information of the best (predicted) beam, that is, the top 1 beam among the predicted N beams. At the same time, part 2 includes beam information of other beams to be reported. As shown in FIG. 8, the beam report includes part 1 including the first indicator and the top 1 beam information, and part 2 including other beam information. Briefly, "beam information in part 1" and "beam information in part 2" may be referred to as "first beam information" and "second beam information", respectively.

[0095] In some embodiments, the beam information of top 1 (i.e., the predicted best beam) includes one CRI and one absolute L1-RSRP. The other beam information includes N - 1 CRIs and N - 1 differential L1-RSRPs. Therefore, the payload size of the first beam information may be determined based on one CRI and one absolute L1-RSRP, and the payload size of the second beam information may be determined based on N - 1 CRIs and N - 1 differential L1-RSRPs.

[0096] In some embodiments, especially for P / SP (periodic or semi-permanent) beam reporting based on PUCCH, the UE may report only part 1. That is, it may report only the indication of the number of beams to be reported and the top 1 beam among the predicted beams. Based on this method, the overhead of beam reporting can be saved. At the same time, there is one beam available for the network device 120. Meanwhile, it is possible to ensure that the gNB receives at least one predicted best beam. Additionally, if the AI model outputs only one beam, the UE may report only part 1.

[0097] In some embodiments, the beam report includes a first part including a first indication and a third number of predicted beams among the first number of predicted beams, and a second part including beam information of the second number of beams.

[0098] In these embodiments, the terminal device 110 may determine the third number based on the value of the number of beams reported by the terminal device 110 set by the network device 120, and may determine the second number based on the first number indicated by the first indication and the third number.

[0099] In these embodiments, the terminal device 110 may determine the payload size of the beam information in the first portion based on a third number of CSI-RS resource indicators (CRIs), the reference signal received power (RSRP), and a number of differential RSRPs equal to (the value obtained by subtracting 1 from the third number).

[0100] In these embodiments, the terminal device 110 may determine the payload size of the beam information in the second portion based on a second number of CRIs and a second number of differential RSRPs. In these embodiments, the terminal device 110 may determine the payload size of the CRI in the second portion based on the first number and the third number. Accordingly, in the network device 120, in some embodiments, the network device 120 may determine the third number based on the value of the number of beams reported by the terminal device 110 set by the network device 120.

[0101] In some embodiments, the network device 120 may determine the second number based on the first number and the third number indicated by the first indication. In these embodiments, the network device 120 may determine the payload size of the beam information in the first portion based on a third number of CSI-RS resource indicators (CRIs), the reference signal received power (RSRP), and a number of differential RSRPs equal to (the value obtained by subtracting 1 from the third number). In these embodiments, the network device 120 may determine the payload size of the beam information in the second portion based on a second number of CRIs and a second number of differential RSRPs.

[0102] In some embodiments, the network device 120 may determine the payload size of the CRI in the second part based on the first number and the third number. According to the above embodiments, part 1 may include information on the top M (e.g., 1 < M < N) beams to be reported. Part 2 includes beam information of other beams to be reported (e.g., N - M beams). In this case, the information of the top M beams includes M CRIs, one absolute L1 - RSRP, and M - 1 L1 - RSRPs. The information of other beams includes N - M CRIs and N - M differential L1 - RSRPs.

[0103] In some embodiments, in addition to the first indicator, part 1 further includes beam information of the top M (M ≥ 1) beams among the predicted N beams. At the same time, part 2 includes beam information of other beams to be reported (i.e., N - M beams). Also, the value of M may be determined based on the value of K. Thus, the number of beams to be reported may be determined by the network device 120. For example, M may be equal to the set K, e.g., the upper layer setting "nrofReportedRS". If K is not set, M is equal to 1. "nrofReportedRS" represents the number (N) of measured RS resources reported for each reporting setting in non - group - based reporting. N ≤ N_max, where N_max is either 2 or 4 depending on the UE capability (TS 38.214

[19] , clause 5.2.1.4). If this field does not exist, the UE applies the value 1.

[0104] In some embodiments, the payload size of the first beam information can be determined based on K CRIs, one absolute L1 - RSRP, and K - 1 differential L1 - RSRPs. The payload size of the first beam information can be determined based on K CRIs, one absolute L1 - RSRP, and K - 1 differential L1 - RSRPs. In particular, for the CRI (i.e., the CRI in part 1), the corresponding payload size may be determined based on the following formula.

[0105]

Number

[0106] The payload size of the second beam information can be determined based on N - K CRI and N - K differential L1 - RSRP. In particular, for the CRI (i.e., the CRI within part 2), the corresponding payload size may be determined based on the following formula.

[0107]

Number

[0108] In this case, the first indicator may be used to indicate the number of beams to be reported within part 2. The corresponding payload size may be determined based on one of the following formulas.

[0109]

Number

[0110]

Number

[0111]

Number

[0112] In some embodiments, the beam report is the first beam report among a plurality of periodic or semi - persistent (P / SP) beam reports, and the second number is determined based on the value of the number of beams reported by the terminal device 110 set by the network device 120.

[0113] In some embodiments, the beam report is a beam report among a plurality of periodic or semi-persistent beam reports, and the terminal device 110 may determine a second number based on the first number indicated by a first indication in the most recently reported beam report. Accordingly, in the network device 120, the network device 120 may also determine a second number based on the first number indicated by the first indication in the most recently reported beam report.

[0114] In some embodiments, the beam report is a beam report among a plurality of periodic or semi-persistent beam reports that meets the offset and period set by the network device 120, and the beam report includes a first indication and beam information of a second number of predicted beams. In some embodiments, the beam report is a beam report among a plurality of periodic or semi-persistent beam reports that does not meet the offset and period set by the network device 120, and the beam report includes only the beam information of the second number of predicted beams.

[0115] Specifically, the UE may report an indication of a predicted beam output by an AI model to the gNB, and the indication is applied to one or more of the following beam reports. In this case, the conventional beam report can be reused. In some embodiments, in order to assist the gNB when setting the value of K, the indication can be used as a recommended value for K. In other words, K depends on the information indicated by the indication.

[0116] FIG. 9 shows an example of a signaling diagram for beam reporting between the terminal device 110 and the network device 120. An indication (referred to as the "fourth indicator") is reported in the current beam report (referred to as the "first beam report"), but the information indicated by the fourth indicator is not applied to the first beam report, but to another beam report (referred to as the "second beam report"), for example, the next or subsequent beam report.

[0117] In some embodiments, similar to the first indicator, the fourth indicator may be reported together with the CRI and the L1-RSRP, and its payload size may be determined based on the method described in the previous embodiments. The introduction of the fourth indicator may be regarded as an extension of the conventional beam reporting. For example, as shown in FIG. 9, assume that the fourth indicator occupies 4 bits.

[0118] Regarding the conventional beam reporting, after the UE is triggered with P (Periodic) / SP (semi-persistent) / AP (Aperiodic) beam reporting, the UE should report the beam ID and the beam quality corresponding to the top K beams to the gNB. K is set by the gNB via RRC signaling. If K is not set for the UE, K is equal to 1. In some situations, especially for P / SP beam reporting, it is not possible to dynamically reset or indicate the number of beams to be reported for each beam reporting. FIG. 10 shows another example of a signaling diagram for beam reporting between the terminal device 110 and the network device 120.

[0119] As shown in FIG. 10, if K = 4 is set by the gNB but the number of beams to be reported needs to be changed to 8, how to determine the number of beams to be reported should be solved. Resetting K will take a long time due to reasons such as signaling delay. For example, the delay may reach 10 ms.

[0120] In some embodiments, as one solution to the above problem, the UE / gNB can apply the number of beams to be reported, indicated by the fourth indicator in the first beam report, to the second beam report. This also means that the number of beams to be reported may not depend on the value of K. For example, in some embodiments, the number of beams to be reported indicated by the fourth indicator is applied to the next single beam report. For example, in some other embodiments, the number of beams to be reported indicated by the fourth indicator is applied to the next multiple beam reports.

[0121] In some embodiments, another solution to the above problem is to introduce a new DL (down link) indication of the number of beams to be reported, that is, to support a dynamic indication of K. For example, in some other embodiments, a (new or conventional) DCI (Downlink control information) or DL MAC-CE (Media access control - control element) is introduced to indicate the number of beams to be reported. Below, according to specific examples, the above two solutions and their specific implementation manners will be introduced.

[0122] FIG. 11 shows another example of a signaling diagram for beam reporting between the terminal device 110 and the network device 120. As shown in FIG. 11, the number of beams to be reported indicated by the fourth indicator is applied to the next single beam report.

[0123] In some embodiments, for each P / SP beam report, the UE needs to report the fourth indicator and beam information. For at least the first P / SP beam report, the UE needs to determine the number of beams to be reported based on the set K. For other P / SP beam reports, the UE can determine the number of beams to be reported based on the information indicated by the fourth indicator reported in the most recent beam report.

[0124] In some embodiments, when the number of predicted beams output by the AI model is less than 8, zero filling may be considered. For example, if the AI model outputs two beams, the base station reserves resources for eight beams, and the number of beams to be reported is not six, the reserved resources corresponding to the six beams are complemented with 0. In some embodiments, when the number of predicted beams output by the AI model is greater than 8 and the base station reserves resources for eight beams, it may be considered to report the top eight beams among the predicted beams.

[0125] FIG. 12 shows another example of a signaling diagram for beam reporting between the terminal device 110 and the network device 120. As shown in FIG. 12, the number of beams to be reported indicated by the fourth indicator is applied to the following multiple beam reports.

[0126] In some embodiments, for example, a dedicated new (start) offset and a new period (e.g., time unit: symbol, slot, ms or s) may be set for the UE to report the fourth indicator (set by RRC (Radio Resource Control)). Optionally, the offset of the P / SP beam report can be reused as the new offset.

[0127] In some embodiments, at least for P / SP beam reporting in the time domain corresponding to the new offset and the new period, the UE needs to report the fourth indicator and the beam information. For other P / SP beam reports, the UE does not need to report the fourth indicator and only needs to report the beam information.

[0128] In some embodiments, for at least the first P / SP beam report, the UE needs to determine the number of beams to report based on the set K. For other P / SP beam reports, the UE can determine the number of beams to report based on the information indicated by the fourth indicator reported in the most recent beam report.

[0129] As shown at X1, as the initial number of beams to report, for example, it is only applicable to the first beam report. As shown at X2, when the number of predicted beams output by the AI model is less than 8, it may be considered to perform zero filling. When the number of predicted beams output by the AI model is greater than 8, it may be considered to report the top 8 beams among the predicted beams.

[0130] In these embodiments, the indication reported in the beam report is applied to one other beam report or several other beam reports, and the indication may be used as auxiliary information for K. In particular, in some embodiments, for the P / SP beam report, the dynamic setting / indication of K may be realized explicitly or implicitly.

[0131] In some embodiments, the network device 120 may send control signaling indicating the number of beams reported by the terminal device 110 to the terminal device 110. In these embodiments, the beam report may be a beam report among a plurality of periodic or semi-persistent beam reports. In some embodiments, the terminal device 110 may determine a second number based on the number of beams reported by the terminal device 110 indicated by the control signaling sent by the network device 120.

[0132] Therefore, in network device 120, network device 120 may determine a second number based on the number of beams reported by terminal device 110 indicated by control signaling. In these embodiments, the beam report may be the beam report among a plurality of periodic or semi-persistent beam reports.

[0133] In some embodiments, the control signaling may be downlink control information (DCI) or a downlink (DL) media access control (MAC) control element (CE). In some embodiments, the CSI request field in the DCI indicates an aperiodic trigger state associated with the beam report. In some embodiments, the DCI is scrambled by a radio network temporary identifier (RNTI), and the RNTI indicates that the DCI contains a value of the number of beams reported by terminal device 110 set by network device 120. In some embodiments, the MAC-CE contains an identifier regarding the second number.

[0134] Refer to FIG. 13, which shows another example of a signaling diagram for beam reporting between terminal device 110 and network device 120. As shown in FIG. 13, in some embodiments, a new indication, such as DCI or DL MAC-CE, is introduced to indicate the number of beams to be reported. After the UE receives the new indication, the number of beams to be reported corresponding to the next beam report indicated by the new indication is determined based on the information (e.g., the value of K) indicated by the new indication.

[0135] In some embodiments, the gNB can use the "CSI request" field in the DCI to indicate the AP trigger state associated with the JIM beam report (ID). Also, the DCI may be scrambled by a new RNTI (Radio network temporary identity). In other embodiments, the gNB can use a new MAC-CE that includes at least the ID or index of the beam report and the number of beams to be reported.

[0136] In some embodiments, after the UE receives the new instruction, the number of beams to be reported corresponding to the next multiple beam reports indicated by the new instruction is determined based on the information indicated by the new instruction. The UE does not use the newly indicated number of beams to be reported until another new instruction is received. Thus, when it is necessary to reset the number of beams to be reported, for example, K, it is possible to reduce the time delay of the reset of K.

[0137] FIG. 14 is a schematic diagram showing a process 1400 for communication between the terminal device 110 and the network device 120. As shown in FIG. 14, the terminal device 110 may determine beam information of a first number of beams predicted by an artificial intelligence (AI) model (1410), and the terminal device 110 may determine beam information of a second number of predicted beams among the first number of predicted beams, and a second instruction indicating whether the first number is greater than, less than, or equal to the value of the number of beams reported by the terminal device 110 set by the network device 120, and generate a beam report (1405) including the above (1420), and the terminal device 110 may transmit the beam report (1405) to the network device 120 (1430).

[0138] Therefore, in network device 120, network device 120 may receive (1440) a beam report (1405) including, in network device 120, beam information of a second number of predicted beams out of the first number of predicted beams predicted by the artificial intelligence (AI) model from terminal device 110, and a second indication indicating whether the first number is greater than, less than, or equal to a value of the number of beams reported by terminal device 110 set by network device 120, and network device 120 may process (1450) the beam report (1405).

[0139] FIG. 15 shows an example of a signaling diagram for beam reporting between terminal device 110 and network device 120. As shown in FIG. 15, the UE reports an indication (referred to as the "fifth indicator") indicating whether the number of beams output or predicted by the AI model is greater than a predefined threshold (e.g., the value of K) to the gNB.

[0140] In some embodiments, the information indicated by the fifth indicator in the first beam report is applied to the second beam report. In some embodiments, the fifth indicator may be part of the beam report and may be reported together with the CRI and L1-RSRP. In some embodiments, the payload size of the fifth indicator may be 1 bit. For example, for the reported fifth indicator, "1" indicates that the number of beams output by the AI model is greater than the value of K, and "0" indicates that the number of beams output by the AI model is less than or equal to the value of K.

[0141] In some embodiments, the payload size of the fifth indicator may be 2 bits. For example, "10" indicates that the number of beams output by the AI model is greater than the value of K, "01" indicates that the number of beams output by the AI model is less than the value of K, and "00" indicates that the number of beams output by the AI model is equal to the value of K.

[0142] In some embodiments, assume that the value of K is 4. For the triggered first beam report, the AI model outputs the (top) 4 beams. Since the number of output beams is equal to K, the fifth indicator should be "0". In this case, the beam report may be executed based on the existing specification (i.e., the conventional beam report). For the triggered second beam report, the AI model outputs 8 beams. It is possible that K is not set for the UE. In this case, the beam report may be executed based on the fact that the beam report includes Part 1 and Part 2. Since the number of output beams is greater than K, the fifth indicator should be "1". For the triggered third beam report, since the AI model outputs 7 beams, the fifth indicator should be "1". The beam report is also executed based on the fact that the beam report includes Part 1 and Part 2.

[0143] In these embodiments, since it is possible to realize the switching between reporting the beam report in the conventional method and reporting the beam report in two parts (e.g., Part 1 + Part 2), the network device 120 can select the format of the beam report based on the comparison result between the number of beams output by the AI model and the value of the number of beams reported by the terminal device 110 determined by the network device 120. In this way, it is possible to assist the UE / gNB in determining which of the conventional beam reporting method or the beam reporting method in the format including Part 1 and Part 2 is used.

[0144] According to the embodiments of the present disclosure, it is beneficial for determining the actual best beam, beneficial for determining, verifying, or validating the (generalization) performance of the AI model, and beneficial for potentially saving the overhead of the beam report.

[0145] In short, the embodiments of the present disclosure can provide the following solutions.

[0146] The communication method includes, in a terminal device, determining beam information of a first number of beams predicted by an artificial intelligence (AI) model, generating a beam report including a first indication regarding the first number and beam information of a second number of the predicted beams among the first number of predicted beams, and transmitting the beam report to a network device.

[0147] In one embodiment, the method further includes determining the payload size of the first indication based on one of the number of channel state information reference signal (CSI-RS) or synchronization signal and PBCH block (SSB) resources corresponding to the beam report, a value of the number of beams reported by the terminal device set by the network device, and the capability information of the terminal device indicating the maximum number of beams predicted by the AI model.

[0148] In one embodiment, in the method, the value is determined by the network device based on the capability information of the terminal device.

[0149] In one embodiment, in the method, the beam report includes a first portion including the first indication and a second portion including beam information of the second number of predicted beams.

[0150] In one embodiment, in the method, the beam report includes a first portion including the first indication and beam information of one of the predicted beams and a second portion including beam information of the second number of predicted beams.

[0151] In one embodiment, the method further includes determining the second number based on the first number indicated by the first indication.

[0152] In one embodiment, the method further includes at least one of: determining a payload size of beam information in the first portion based on a CSI-RS resource indicator (CRI) and a reference signal received power (RSRP); and determining a payload size of beam information in the second portion based on the second number of CRIs and the second number of differential RSRPs.

[0153] In one embodiment, in the method, the beam report includes a first portion including a third number of predicted beams among the first indication and the first number of predicted beams, and a second portion including beam information of the second number of beams.

[0154] In one embodiment, the method further includes: determining the third number based on a value of the number of beams reported by the terminal device and set by the network device; and determining the second number based on the first number indicated by the first indication and the third number.

[0155] In one embodiment, the method further includes at least one of: determining a payload size of beam information in the first portion based on the third number of CSI-RS resource indicators (CRIs), a reference signal received power (RSRP), and a differential RSRP whose number is equal to a value obtained by subtracting 1 from the third number; and determining a payload size of beam information in the second portion based on the second number of CRIs and the second number of differential RSRPs.

[0156] In one embodiment, the method further includes determining a payload size of the CRI in the second portion based on the first number and the third number.

[0157] In one embodiment, in the method, the beam report is the first beam report among a plurality of periodic or semi-persistent (P / SP) beam reports, and the second number is determined based on a value of the number of beams reported by the terminal device and set by the network device.

[0158] In one embodiment, in the method, the beam report is a beam report among a plurality of periodic or semi-persistent beam reports, and the method further includes determining the second number based on the first number indicated by the first indication in the most recently reported beam report that has already been reported.

[0159] In one embodiment, in the method, the beam report is a beam report among a plurality of periodic or semi-persistent beam reports that satisfies an offset and a period set by the network device, and the beam report includes the first indication and beam information of the predicted beams of the second number.

[0160] In one embodiment, in the method, the beam report is a beam report among a plurality of periodic or semi-persistent beam reports that does not satisfy an offset and a period set by the network device, and the beam report includes only beam information of the predicted beams of the second number.

[0161] In one embodiment, the method further includes determining the second number based on the number of beams reported by the terminal device and indicated by control signaling transmitted by the network device.

[0162] In one embodiment, in the method, the control signaling is downlink control information (DCI) or a downlink (DL) medium access control (MAC) control element (CE).

[0163] In one embodiment, in the method, at least one of the following holds: the CSI request field in the DCI indicates an aperiodic trigger state associated with the beam report; the DCI is scrambled by a radio network temporary identifier (RNTI), and the RNTI includes a value of the number of beams reported by the terminal device and set by the network device; the MAC-CE includes an identifier related to the second number.

[0164] In one embodiment, in the method, the beam report is a beam report among a plurality of periodic or semi-persistent beam reports.

[0165] A communication method includes, at a terminal device, determining beam information of a first number of beams predicted by an artificial intelligence (AI) model; generating a beam report including the beam information of a second number of predicted beams among the first number of predicted beams, and a second indication indicating whether the first number is greater than, less than, or equal to a value of the number of beams reported by the terminal device and set by the network device; and transmitting the beam report to a network device.

[0166] A communication method includes, at a network device, receiving, from a terminal device, a beam report including a first indication regarding a first number and beam information of a second number of predicted beams among the predicted beams of the first number, where the predicted beams are predicted by an artificial intelligence (AI) model, and processing the beam report.

[0167] In one embodiment, the method further includes determining a value of the number of beams reported by the terminal device based on the first number indicated by the first indication.

[0168] In one embodiment, the method further includes determining the payload size of the first indication based on one of the number of channel state information reference signal (CSI-RS) or synchronization signal and PBCH block (SSB) resources corresponding to the beam report, the value of the number of beams reported by the terminal device set by the network device, and the capability information of the terminal device indicating the maximum number of beams predicted by the AI model.

[0169] In one embodiment, the method further includes receiving the capability information of the terminal device and determining the value based on the capability information of the terminal device.

[0170] In one embodiment, in the method, the beam report includes a first part including the first indication and a second part including the beam information of the second number of predicted beams.

[0171] In one embodiment, in the method, the beam report includes a first part including the first indication and the beam information of one of the predicted beams and a second part including the beam information of the second number of predicted beams.

[0172] In one embodiment, the method further includes determining the second number based on the first number indicated by the first indication.

[0173] In one embodiment, the method further includes at least one of: determining a payload size of beam information in the first portion based on a CSI-RS resource indicator (CRI) and a reference signal received power (RSRP); and determining a payload size of beam information in the second portion based on the second number of CRIs and the second number of differential RSRPs.

[0174] In one embodiment, in the method, the beam report includes a first portion including a third number of predicted beams among the first indication and the first number of predicted beams, and a second portion including beam information of the second number of beams.

[0175] In one embodiment, the method further includes determining the third number based on a value of the number of beams reported by the terminal device and set by the network device, and determining the second number based on the first number indicated by the first indication and the third number.

[0176] In one embodiment, the method further includes at least one of: determining a payload size of beam information in the first portion based on a CSI-RS resource indicator (CRI) of the third number, a reference signal received power (RSRP), and a differential RSRP whose number is equal to a value obtained by subtracting 1 from the third number; and determining a payload size of beam information in the second portion based on the second number of CRIs and the second number of differential RSRPs.

[0177] In one embodiment, the method further includes determining the payload size of the CRI in the second portion based on the first number and the third number.

[0178] In one embodiment, in the method, the beam report is the first beam report among a plurality of periodic or semi-persistent beam reports, and the second number is determined based on a value of the number of beams reported by the terminal device and set by the network device.

[0179] In one embodiment, in the method, the beam report is a beam report among a plurality of periodic or semi-persistent beam reports, and the method further includes determining the second number based on the first number indicated by the first indication in the most recently reported beam report.

[0180] In one embodiment, in the method, the beam report is a beam report among a plurality of periodic or semi-persistent beam reports that satisfies an offset and a period set by the network device, and the beam report includes the first indication and beam information of the predicted beams of the second number.

[0181] In one embodiment, in the method, the beam report is a beam report among a plurality of periodic or semi-persistent beam reports that does not satisfy an offset and a period set by the network device, and the beam report includes only the beam information of the predicted beams of the second number.

[0182] In one embodiment, the method further includes transmitting control signaling indicating the number of beams reported by the terminal device to the terminal device.

[0183] In one embodiment, the method further includes determining the second number based on the number of beams reported by the terminal device indicated by the control signaling.

[0184] In one embodiment, in the method, the control signaling is downlink control information (DCI) or a downlink (DL) medium access control (MAC) control element (CE).

[0185] In one embodiment, in the method, at least one of the following holds: the CSI request field in the DCI indicates an aperiodic trigger state associated with the beam report; the DCI is scrambled by a radio network temporary identifier (RNTI), and the RNTI includes a value of the number of beams reported by the terminal device, which is set by the network device; the MAC-CE includes an identifier related to the second number.

[0186] In one embodiment, in the method, the beam report is a beam report among a plurality of periodic or semi-persistent beam reports.

[0187] A communication method includes, in a network device, receiving a beam report from a terminal device, the beam report including beam information of a second number of predicted beams among a first number of predicted beams predicted by an artificial intelligence (AI) model, and a second indication indicating whether the first number is greater than, less than, or equal to a value of the number of beams reported by the terminal device, which is set by the network device, and processing the beam report.

[0188] A terminal device includes a processor and a memory storing computer program code, and the memory and the computer program code are configured to, together with the processor, cause the terminal device to execute the above communication method.

[0189] The network device includes a processor and a memory storing computer program code, and the memory and the computer program code are configured, together with the processor, to cause the network device to execute the above communication method.

[0190] The computer-readable medium stores instructions that, when executed by a processor of a device, cause the device to execute the above communication method.

[0191] FIG. 16 is a schematic block diagram of an apparatus 1600 suitable for implementing an embodiment of the present disclosure. The apparatus 1600 may be regarded as another exemplary embodiment of the terminal device 110 and / or the network device 120 as shown in FIG. 1. Accordingly, the apparatus 1600 may be implemented in the terminal device 110 or the network device 120, or as at least a part thereof.

[0192] As shown, apparatus 1600 includes a processor 1610, a memory 1620 coupled to the processor 1610, a suitable transmitter (TX) and receiver (RX) 1640 coupled to the processor 1610, and a communication interface coupled to the TX / RX 1640. The memory 1610 stores at least a part of a program 1630. The TX / RX 1640 is used for bidirectional communication. The TX / RX 1640 has at least one antenna to facilitate communication, although the access nodes referred to in this disclosure may actually have multiple antennas. The communication interface may represent any interface necessary for communication with other network elements, such as an X2 interface for bidirectional communication between eNBs, an S1 interface for communication between a Mobility Management Entity (MME) / Serving Gateway (S-GW) and an eNB, a Un interface for communication between an eNB and a relay node (RN), or a Uu interface for communication between an eNB and a terminal device.

[0193] It is assumed that when the program 1630 is executed by the associated processor 1610, as described herein with reference to FIGS. 3 - 15, it includes program instructions that enable the apparatus 1600 to operate in accordance with embodiments of this disclosure. Embodiments herein may be implemented by computer software executable by the processor 1610 of the apparatus 1600, or by hardware, or by a combination of software and hardware. The processor 1610 may be configured to implement various embodiments of this disclosure. Further, the combination of the processor 1610 and the memory 1620 may form processing means 1650 suitable for implementing various embodiments of this disclosure.

[0194] Memory 1620 may be of any type suitable for a local technology network, and by way of non-limiting example, may be implemented using any suitable data storage technology such as a non-transitory computer-readable storage medium, a semiconductor-based memory device, a magnetic memory device and system, an optical memory device and system, a fixed memory, and a removable memory. Only one memory 1620 is shown within device 1600, but there may be several physically different memory modules within device 1600. Processor 1610 may be of any type suitable for a local technology network, and by way of non-limiting example, may include one or more of a general-purpose computer, a dedicated computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture. Device 1600 may have a specific-purpose integrated circuit chip that is temporally dependent on a clock that synchronizes a plurality of processors, such as a main processor.

[0195] Overall, various embodiments of the present disclosure may be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software executable by a controller, a microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are illustrated and described using block diagrams, flowcharts, or other pictorial representations, it should be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented, by way of non-limiting example, in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or any combination thereof.

[0196] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, that are executed within a device on a target physical processor or virtual processor to perform the processes or methods described above with reference to FIGS. 2-15. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of the program modules may be combined or divided among the program modules as needed. The machine-executable instructions of the program modules may be executed within a local or distributed device. In a distributed device, the program modules may be located in both local and remote storage media.

[0197] The program code for executing the method of the present disclosure may be described in any combination of one or more programming languages. These program codes are provided to a processor or controller of a general-purpose computer, a dedicated computer, or other programmable data processing equipment, and when executed by the processor or controller, the program codes implement the functions / operations specified in the flowchart and / or block diagram. The program code may be executed entirely on the machine, partially on the machine, as an independent software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0198] The above program code may be implemented on a machine-readable medium, which may be any tangible medium that can be utilized by or associated with an instruction execution system, apparatus, or device and that can contain or store a program for the same. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing media. More specific examples of the machine-readable storage medium may include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0199] Note that although the operations have been described in a particular order, it should be understood that such operations may be performed in the particular order shown or in sequential order, or that all of the described operations may be required to obtain the desired results. In some cases, multitasking and parallel processing may be advantageous. Similarly, while some specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to a particular embodiment. Some features described in the context of individual embodiments may be combined and implemented in a single embodiment. Conversely, various features described in the context of a single embodiment may be implemented separately in multiple embodiments or in any suitable sub-combination.

[0200] Although the present disclosure has been described in language specific to structural features and / or methodological acts, it is to be understood that the disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as illustrative forms of implementing the claims.

Claims

1. A method of communication, comprising: in a terminal device, determining beam information of a first number of beams predicted by an artificial intelligence (AI) model; generating a beam report including a first indication regarding the first number and beam information of a second number of predicted beams among the first number of predicted beams; transmitting the beam report to a network device. The method as described above.

2. Determining the payload size of the first indication based on one of: the number of channel state information reference signal (CSI-RS) or synchronization signal and PBCH block (SSB) resources corresponding to the beam report; a value of the number of beams reported by the terminal device, set by the network device; the capability information of the terminal device indicating the maximum number of beams predicted by the AI model. The method according to Claim 1, further comprising the above. The method according to Claim 1.

3. The value is determined by the network device based on the capability information of the terminal device. The method according to Claim 2.

4. The beam report includes a first part including the first indication and a second part including beam information of the second number of predicted beams. The method according to Claim 1.

5. The beam report includes a first part including the first indication and beam information of one of the predicted beams, and a second part including beam information of the second number of predicted beams. The method according to Claim 1.

6. The method according to Claim 4 or 5, further comprising determining the second number based on the first number indicated by the first indication. The method according to Claim 4 or 5.

7. Determining the payload size of the beam information in the first part based on a CSI-RS resource indicator (CRI) and a reference signal received power (RSRP); Determining the payload size of the beam information in the second part based on the CRI of the second number and the differential RSRP of the second number. The method further includes at least one of the above. The method according to claim 5.

8. The beam report includes a first portion including a third number of predicted beams among the first indication and the first number of predicted beams, and a second portion including beam information of the second number of beams. The method according to claim 1.

9. Determining the third number based on a value of the number of beams reported by the terminal device and set by the network device; Determining the second number based on the first number indicated by the first indication and the third number; further comprising The method according to claim 8.

10. Determining a payload size of beam information in the first portion based on a CSI-RS resource indicator (CRI: CSI-RS resource indicator) of the third number, a reference signal received power (RSRP: reference signal received power), and a differential RSRP whose number is equal to a value obtained by subtracting 1 from the third number; Determining a payload size of beam information in the second portion based on a CRI of the second number and a differential RSRP of the second number; further comprising at least one of The method according to claim 8 or 9.

11. further comprising determining a payload size of the CRI in the second portion based on the first number and the third number. The method according to claim 10.

12. The beam report is a first beam report among a plurality of periodic or semi-persistent beam reports, and the second number is determined based on a value of the number of beams reported by the terminal device and set by the network device. The method according to claim 1.

13. The beam report is a beam report among a plurality of periodic or semi-persistent beam reports, and the method further comprises: determining the second number based on the first number indicated by the first indication in the most recently reported beam report that has already been reported. The method according to claim 1.

14. The beam report is a beam report among a plurality of periodic or semi-persistent beam reports that satisfies an offset and a period set by the network device, and the beam report includes the first indication and beam information of the second number of predicted beams. The method according to claim 1.

15. The beam report is a beam report among a plurality of periodic or semi-persistent beam reports that does not satisfy the offset and period set by the network device, and the beam report includes only beam information of the second number of predicted beams The method according to claim 1.

16. further comprising determining the second number based on the number of beams reported by the terminal device, indicated by control signaling transmitted by the network device The method according to claim 1.

17. The control signaling is downlink control information (DCI), or a downlink (DL) media access control (MAC) control element (CE) The method according to claim 16.

18. the CSI request field in the DCI indicates an aperiodic trigger state associated with the beam report the DCI is scrambled by a radio network temporary identifier (RNTI), and the RNTI indicates that the DCI includes a value of the number of beams reported by the terminal device set by the network device the MAC-CE includes an identifier related to the second number at least one of the above is established The method according to claim 17.

19. The beam report is a beam report among a plurality of periodic or semi-persistent beam reports The method according to claim 16.

20. A communication method, comprising: at a terminal device, determining beam information of a first number of beams predicted by an artificial intelligence (AI) model generating a beam report including beam information of a second number of predicted beams among the first number of predicted beams, and a second indication indicating whether the first number is greater than, less than, or equal to a value of the number of beams reported by the terminal device set by the network device transmitting the beam report to a network device A method comprising.

21. A communication method, comprising: In a network device, receiving, from a terminal device, a beam report including a first instruction regarding a first number and beam information of a second number of predicted beams among the first number of predicted beams, where the predicted beams are predicted by an artificial intelligence (AI) model, processing the beam report, A method including the above.

22. Further including determining a value of the number of beams reported by the terminal device based on the first number indicated by the first instruction The method according to claim 21.

Images