Method and apparatus for wireless communication

Abstract

Provided are a method and apparatus for wireless communication. The method comprises: a first device receiving, within an observation window, a plurality of beams sent by a second device, wherein the plurality of beams are used for determining a first beam set; the first device performing beam prediction on a second beam set within the prediction window on the basis of measurement values of the first beam set; and the first device sending a first report to the second device, wherein the first report is used for determining one or K optimal beams in the second beam set, K is a positive integer, the first beam set is determined on the basis of first information, and the first information comprises at least two of measurement values of the plurality of beams, the capability of the first device, and a network configuration.

Description

Methods and apparatus for wireless communication Technical Field

[0001] This application relates to the field of communication technology, and more specifically, to a method and apparatus for wireless communication. Background Technology

[0002] In certain beam management scenarios, terminal devices can predict downlink transmission beams using models and report this information to network devices. For example, a terminal device can measure beams received in set B to predict the optimal beam in set A. However, there are no clear regulations on how the terminal device determines set B based on beams transmitted by the network device.

[0003] Summary of the Invention

[0004] This application provides a method and apparatus for wireless communication. The various aspects related to the embodiments of this application are described below.

[0005] In a first aspect, a method for wireless communication is provided, comprising: a first device receiving, within an observation window, a plurality of beams transmitted by a second device, the plurality of beams being used to determine a first beam set; the first device performing beam prediction on a second beam set within a prediction window based on measurements of the first beam set; the first device sending a first report to the second device; wherein the first report is used to determine one or K optimal beams in the second beam set, K being a positive integer, the first beam set being determined according to first information, the first information including at least two of the measurements of the plurality of beams, the capabilities of the first device, and network configuration.

[0006] In a second aspect, a method for wireless communication is provided, comprising: a second device transmitting a plurality of beams within an observation window, the plurality of beams being used to determine a first beam set; the second device receiving a first report transmitted by a first device; wherein the first report is used to determine one or K optimal beams in a second beam set within a prediction window, K being a positive integer, beam prediction of the second beam set being based on measurements of the first beam set, the first beam set being determined according to first information, the first information including at least two of the measurements of the plurality of beams, the capabilities of the first device, and network configuration.

[0007] Thirdly, an apparatus for wireless communication is provided, the apparatus being a first device, comprising: a transceiver unit configured to receive, within an observation window, a plurality of beams transmitted by a second device, the plurality of beams being used to determine a first beam set; a processing unit configured to perform beam prediction on a second beam set within a prediction window based on measurements of the first beam set; the transceiver unit further configured to send a first report to the second device; wherein the first report is used to determine one or K optimal beams in the second beam set, K being a positive integer, the first beam set being determined based on first information, the first information including at least two of the measurements of the plurality of beams, the capabilities of the first device, and network configuration.

[0008] Fourthly, an apparatus for wireless communication is provided, the apparatus being a first device, comprising: a transceiver unit configured to transmit a plurality of beams within an observation window, the plurality of beams being used to determine a first beam set; the transceiver unit further configured to receive a first report transmitted by the first device; wherein the first report is used to determine one or K optimal beams in a second beam set within a prediction window, K being a positive integer, the beam prediction of the second beam set being based on measurements of the first beam set, the first beam set being determined according to first information, the first information including at least two of the measurements of the plurality of beams, the capabilities of the first device, and network configuration.

[0009] Fifthly, a communication device is provided, comprising a memory and a processor, the memory for storing a program, and the processor for calling the program in the memory to perform the method as described in the first or second aspect.

[0010] A sixth aspect provides an apparatus including a processor for calling a program from memory to perform the method as described in the first or second aspect.

[0011] A seventh aspect provides a chip including a processor for calling a program from memory, causing a device on which the chip is mounted to perform the method as described in the first or second aspect.

[0012] Eighthly, a computer-readable storage medium is provided having a program stored thereon that causes a computer to perform the method as described in the first or second aspect.

[0013] Ninth aspect, a computer program product is provided, including a program that causes a computer to perform the method as described in the first or second aspect.

[0014] In a tenth aspect, a computer program is provided that causes a computer to perform the method as described in the first or second aspect.

[0015] In this embodiment, after receiving multiple beams in the observation window, the first device can determine a first beam set based on at least two of the measured values ​​of the multiple beams, the capabilities of the first device, and the network configuration. The first beam set can be used by the first device to perform beam prediction on a second beam set. Therefore, when the second device sends multiple beams, the first device does not need to confirm the purpose of these beams, but directly determines and measures the first beam set, thereby improving model inference efficiency. Attached Figure Description

[0016] Figure 1 shows the wireless communication system used in an embodiment of this application.

[0017] Figure 2 is a schematic diagram of the model processing procedure applied in the embodiments of this application.

[0018] Figure 3 is a schematic diagram of the model inference process on the terminal device side applied in the embodiments of this application.

[0019] Figure 4 is a flowchart illustrating a method for wireless communication provided in an embodiment of this application.

[0020] Figure 5 is a flowchart illustrating one possible implementation of the method shown in Figure 4.

[0021] Figure 6 is a flowchart illustrating another possible implementation of the method shown in Figure 4.

[0022] Figure 7 is a schematic diagram of one possible implementation of the method shown in Figure 4.

[0023] Figure 8 is a schematic diagram of a device for wireless communication provided in an embodiment of this application.

[0024] Figure 9 is a schematic diagram of another device for wireless communication provided in an embodiment of this application.

[0025] Figure 10 is a schematic diagram of the structure of a wireless communication device provided in an embodiment of this application. Detailed Implementation

[0026] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0027] Figure 1 is a schematic diagram of the architecture of the wireless communication system 100 used in an embodiment of this application. As shown in Figure 1, the wireless communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 may provide communication coverage for a specific geographical area and may communicate with terminal devices located within that coverage area.

[0028] Figure 1 exemplarily illustrates a network device and two terminal devices. Optionally, the wireless communication system 100 may include multiple network devices, and each network device may include an additional number of terminal devices within its coverage area; this is not limited. In other words, the wireless communication system may include one or more network devices, and each network device may support wireless communication for one or more terminal devices.

[0029] In the embodiments of this application, the communication system shown in FIG1 may also include other network entities such as a mobility management entity (MME), an access and mobility management function (AMF), and a network controller. The embodiments of this application do not limit this.

[0030] It should be understood that the embodiments of this application can be applied to various communication systems. For example, the embodiments of this application can be applied to Global System for Mobile Communication (GSM), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), General Packet Radio Service (GPRS), Long Term Evolution (LTE), Advanced Long Term Evolution (LTE-A), New Radio (NR), evolution systems of NR, LTE-based access to unlicensed spectrum (LTE-U), NR-based access to unlicensed spectrum (NR-U), Universal Mobile Telecommunications System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), and 5th-generation (5G) systems. The embodiments of this application can also be applied to other communication systems, such as 6th-generation (6G) mobile communication systems, or future communication systems such as satellite communication systems.

[0031] Traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, communication systems can support not only traditional cellular communication but also one or more other types of communication. For example, a communication system can support one or more of the following communication methods: device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), enhanced machine-type communication (eMTC), vehicle-to-vehicle (V2V) communication, and vehicle-to-everything (V2X) communication. The embodiments of this application can also be applied to communication systems that support the above-mentioned communication methods.

[0032] The communication system in this application embodiment can be applied to carrier aggregation (CA) scenarios, dual connectivity (DC) scenarios, and standalone (SA) network deployment scenarios.

[0033] The communication system in this application embodiment can be applied to unlicensed spectrum. This unlicensed spectrum can also be considered a shared spectrum. Alternatively, the communication system in this application embodiment can also be applied to licensed spectrum. This licensed spectrum can also be considered a dedicated spectrum.

[0034] The embodiments of this application can be applied to non-terrestrial network (NTN) systems. As an example, the NTN system can be a 4G-based NTN system, an NR-based NTN system, an Internet of Things (IoT)-based NTN system, or a narrowband Internet of Things (NB-IoT)-based NTN system.

[0035] The wireless communication system in this application embodiment can utilize the following resources to support wireless communication with one or more communication devices: time resources (e.g., symbols, sub-slots, time slots, subframes, frames, etc.) or frequency resources (e.g., subcarriers, carriers). Additionally, the wireless communication system can support wireless communication across various radio access technologies (RATs), including third-generation (3G), fourth-generation (4G), fifth-generation (5G), and other suitable RATs beyond 5G.

[0036] The terminal equipment in this application embodiment may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, user communication equipment, wireless communication equipment, user agent, or user device, etc.

[0037] In some embodiments, the terminal device in this application can be a device that provides voice and / or data connectivity to a user, and can be used to connect people, objects, and machines, such as a handheld device with wireless connectivity, an in-vehicle device, etc. The terminal device in the embodiments of this application can be a mobile phone, tablet computer, laptop computer, PDA, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc. Optionally, the UE can be used to act as a base station. For example, the UE can act as a scheduling entity, providing sidelink signals between UEs in V2X or D2D, etc. For example, cellular phones and cars communicate with each other using sidelink signals. Cellular phones and smart home devices can communicate without relaying communication signals through base stations.

[0038] In some embodiments, the terminal device may be a station (ST) in a WLAN. In some embodiments, the terminal device may be a cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA) device, handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, in-vehicle device, wearable device, terminal device in a next-generation communication system (e.g., NR system), or terminal device in a future public land mobile network (PLMN) network, etc.

[0039] The network device in this application embodiment can be a device for communicating with a terminal device, and can also be referred to as an access network device or a radio access network device. For example, the network device can be a base station. In this application embodiment, the network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station (MeNB), secondary station (SeNB), multi-mode radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), location node, network communication equipment, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, a device that performs base station functions in D2D, V2X, and M2M communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. A base station can support networks using the same or different access technologies. The embodiments of this application do not limit the specific technologies or device forms used in the network equipment.

[0040] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0041] In some deployments, the network device in this application embodiment may refer to a CU or a DU, or the network device may include both a CU and a DU. The gNB may also include an AAU.

[0042] Network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located.

[0043] It should be understood that all or part of the functions of the communication device in this application can also be implemented by software functions running on hardware, or by virtualization functions instantiated on a platform (e.g., a cloud platform).

[0044] In this embodiment, the network device can provide services to a cell. The terminal device communicates with the network device through the transmission resources (e.g., frequency domain resources, or spectrum resources) used by the cell. The cell can be the cell corresponding to the network device (e.g., a base station). The cell can belong to a macro base station or to a base station corresponding to a small cell. The small cell can include: metro cell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage area and low transmission power, and are suitable for providing high-speed data transmission services.

[0045] It should be understood that devices with communication functions in the network / system of this application embodiment can be referred to as communication devices. Taking the wireless communication system 100 shown in FIG1 as an example, the communication device may include network device 110 and terminal device 120 with communication functions, and may also include other devices in the wireless communication system 100, such as network controllers, mobility management entities and other network entities. This application embodiment does not limit this.

[0046] To facilitate understanding, some related technical knowledge involved in the embodiments of this application is first introduced. The following related technologies are optional solutions and can be arbitrarily combined with the technical solutions of the embodiments of this application, all of which fall within the protection scope of the embodiments of this application. The embodiments of this application include at least some of the following contents.

[0047] In wireless communication systems, terminal devices can acquire beams (also known as spatial beams) to establish a wireless connection to a wireless network. For example, the terminal device can perform beam scanning against available beams transmitted by the wireless network and measure beam properties such as signal strength and signal quality. For example, after performing beam scanning, the terminal device can also perform beam thinning to achieve a potentially narrower set of beams for wireless connection to the wireless network. Beaming not only enables wireless connectivity between the terminal device and the wireless network but also achieves high directional accuracy and high signal quality for wireless signal transmission between the terminal device and the wireless network.

[0048] With the development of communication technology, research on artificial intelligence (AI) / machine learning (ML) technologies based on the air interface of communication systems (e.g., NR systems) has become a research direction. The goals of this research include exploring how to enhance the advantages of the air interface. For example, enhancing support for AI / ML algorithms can improve the performance of the air interface. Similarly, enhancing support for AI / ML algorithms can reduce the complexity and / or overhead of the air interface.

[0049] Research into AI / ML technologies can also enhance beam management (BM) capabilities. As an example, AI / ML enhancements related to beam management can help reduce overhead and lower beam measurement and reporting latency. As another example, applying AI / ML models can predict beams to improve transmission efficiency at the air interface.

[0050] The entire process of augmenting AI / ML models includes model training, model inference, and model monitoring. During this process, after training, the AI / ML model can generate a set of outputs based on a set of inputs. The input can be a set of beam measurements, while the output can be a set of beams that are different from or larger than the inputs.

[0051] During the model inference process, AI / ML models can predict the optimal beam in a set of different / larger beam groups using a set of beam measurements.

[0052] In some embodiments, the AI / ML model may be located on the terminal device side or the terminal device may perform model training and / or model inference. This model may be referred to as a UE-side model. For example, the AI ​​model may be located on the terminal device or the terminal device may perform AI model training and / or use AI model inference to generate the optimal beam.

[0053] As an example, a terminal device can use beams from set B (also called beam group B) as input to an ML model. This ML model can predict the optimal beam in set A (also called beam group A), which is not fully measured by the terminal device.

[0054] In the example above, set B can be the beam group that the terminal device first measures. Set B can be multiple beams transmitted by the base station (e.g., gNB). Each beam can correspond to a different direction or angle to cover multiple spatial directions. Each beam can also correspond to a measurement signal used to obtain a measurement value, such as reference signal received power (RSRP). The role of set B is to provide the model with preliminary environmental information and channel conditions. In the example above, set A can be the beam group that needs to be predicted. The number of beams in set A is usually larger than that in set B, or the beam directions may be more concentrated. The AI / ML model can predict the optimal beam in set A by measuring set B, thereby improving the efficiency of data transmission.

[0055] Optionally, the beams of set A and set B can be in the same frequency range. The selection of set B can be given by the base station or determined by the terminal equipment itself. The relationship between set A and set B can be: set A and set B are different (set B is not a subset of set A), or set B is a subset of set A (set A and set B are different), or set A and set B are the same. For the first two cases, set B can be transmitted simultaneously in the measurement window and the prediction window, or it can be transmitted only in the measurement window. The last case can save the reference signal (RS) transmission overhead, as set B, as a measurement resource, can be transmitted only in the measurement window.

[0056] Alternatively, 64 or more beams can be used as the size of the beam set A. For future-oriented networks, network devices will be able to transmit 64 more highly directional narrow beams. More narrow beams can also scan a larger set A; for example, the number of beams in set A could be as high as 256.

[0057] Optionally, the network device may transmit a channel state information-reference signal (CSI-RS) or a synchronization signal block (SSB) as a reference signal. It should be understood that SSB can also represent a synchronization signal / physical broadcast channel block (SS / PBCH block). The SSB includes a primary synchronization signal (PSS) and a secondary synchronization signal (PSS).

[0058] Optionally, the terminal device estimates the channel quality of each beam by measuring the RSRP received from the CSI-RS / SSS.

[0059] Optionally, during model training, the AI / ML model can adjust its weights by minimizing the loss function so that the model can accurately predict the optimal beam in set A from the RSRP measurements of set B.

[0060] In some embodiments, AI / ML can be located at the network device (such as a base station) or the network device can perform model training and / or model inference. This model can be referred to as a network-side model (NW-side model). For example, the AI ​​model can be located at the base station or the base station can perform AI model training and / or use AI model inference to generate optimal beams.

[0061] In some embodiments, the network can have complete control over the data collection process for model training on the terminal device side, including the initiation, termination, and management of data collection and data transmission.

[0062] In the model monitoring process, AI / ML model monitoring is used for at least the following purposes: model activation, deactivation, selection, switching, rollback, and updating (including retraining). Model monitoring can also be referred to as the process of monitoring the inference performance of AI / ML models. There is always a time interval between the model's training and inference processes. When radio parameters / conditions change in the network, the probability of errors occurring during the model's inference phase is higher; therefore, it is necessary to continuously correct and train the model based on the results of model monitoring.

[0063] Compared to other beam management technologies, beam management that supports AI / ML technologies enables terminal devices to experience reduced latency, reduced overhead, lower power consumption, and improved signal quality based on beam prediction.

[0064] To facilitate understanding, the entire process of model processing on the terminal device side is described below with reference to Figure 2. Figure 2 illustrates the interaction between the terminal device (e.g., UE) and the network (NW) side. Four beams are used as an example on the network side. As shown in Figure 2, the entire process can include model training, model inference, and reporting. The model training process includes steps S210 and S220, and the model inference process includes steps S230 and S240.

[0065] Referring to Figure 2, in step S210, the terminal device reports training-related information (UEreport training-related information).

[0066] In step S220, the network side performs beam scanning based on four beams.

[0067] In step S230, the terminal device reports inference-related information.

[0068] In step S240, the network side selects two beams from the four beams for beam scanning based on the report from the terminal device.

[0069] In step S250, the terminal device reports the optimal K beams (top-K beam report).

[0070] In step S260, the network side performs beam scanning based on the beams in the beam report. As shown in Figure 2, the two beams used for beam scanning by the network side in step S260 may be different from the two beams used for beam scanning in step S240.

[0071] In step S270, the terminal device sends a beam report so that the network side can determine the optimal beam.

[0072] In step S280, the network side sends a beam indication to the terminal device.

[0073] The preceding text, with reference to Figure 2, described the process of processing the model when it is located on the terminal device side. To complete this process, the terminal device needs to collect and analyze data. As mentioned earlier, the data collection process can include data collection, data transmission initiation, transmission, and management. The following section uses the terminal device-side model as an example to introduce data collection and analysis.

[0074] For end-device-side models, the behavior or reported content of the end-device may vary depending on whether it is a measurement resource for training, inference, or monitoring. In other words, the content may differ for different end-device behaviors or reports. Therefore, when configuring AI / ML operation-related measurements for end-device-side models, it is necessary to indicate to the end-device the purpose of the measurement configuration or the implied end-device behavior (e.g., training, inference, monitoring, or non-AI / ML operations).

[0075] As an example, for the training process, the terminal device may only need to measure the beam of the configuration resources. For instance, the model inputs and labels generated from set A / set B can be used for internal training on the terminal device side and do not need to be reported to the network device.

[0076] As an example, for the inference process, the terminal device may need to measure the transmit (Tx) beam from set B and use it as model input, while the terminal device should also report the model output regarding the predicted beam / RSRP value.

[0077] Regarding data collection, this application embodiment can support data collection initiated / triggered by network configuration, or it can support data collection requested by the terminal device. Data collection for different purposes can correspond to different behaviors of the terminal device.

[0078] As an example, data collection can be used to train AI models or to give end devices an initial understanding of network performance. When performing data collection based on training datasets, end devices need to be equipped with mechanisms to determine when and what data to collect for effective training. Since the network side may not know the specific data requirements of the end device or the optimal time for data collection, the end device can autonomously trigger the collection process and report relevant configurations. For example, an end-device-side AI / ML model may have inputs that include layer 1 (L1) RSRPs with 8 SSBs and outputs that include predicted L1-RSRPs with 32 CSI-RSs. The 8 SSBs can be applied to set B for training purposes, and the 32 CSI RSs can be applied to set A for training purposes.

[0079] Taking the AI / ML model in the example above, in order to collect data for training the AI / ML model, the network can configure a first SSB resource set and a first CSI-RS resource set for the terminal device. In the first SSB resource set, the SSB resource indicator (RI) or resource index (RI) can be from 1 to 8. The SSB RI can be defined based on the identity (ID) associated with each SSB in the SSB resource set. In the first CSI-RS resource set, the CSI-RS resource indicator (CSI-RS RI, CRI) can be from 1 to 32. The CRI can be defined based on the ID associated with each CSI-RS in the CSI-RS resource set.

[0080] Optionally, the CSI-RS in the first CSI-RS resource set will share the same periodicity as the SSBs in the first SSB resource set.

[0081] Optionally, the terminal device can collect L1-RSRP about SSB and CSI-RS at various times and upload the data to an over-the-top (OTT) server for offline model training.

[0082] Optionally, during model training, the L1-RSRP corresponding to SSB RI = m (1 ≤ m ≤ 8) in the first SSB resource set can be used to determine the input value of the m-th input feature of the AI / ML model, and the L1-RSRP corresponding to CRI = n (1 ≤ n ≤ 32) in the first CSI-RS resource set can be used to determine the value label associated with the n-th output feature of the AI / ML model. Then, this offline-trained AI / ML model can be downloaded back to the terminal device for future model inference.

[0083] The following section will continue to use the terminal device-side model as an example to introduce the model inference and reporting process, which also includes the beam management inference process.

[0084] For the inference process of the terminal device-side model, the terminal device measures the RS of beams in set B and predicts the Top-K beams in set A, then reports the prediction results to the network. In traditional L1-RSRP reporting, the terminal device should report the L1-RSRP values ​​of the channel measurement resource (CMR) associated with the CSI report. However, for AI-based beam management, the beam group used for measurement (set B) and the beam group used for reporting (set A) may be different. Therefore, to inform the terminal device to report the prediction results, the association between set A and set B should be indicated to the terminal device.

[0085] It's important to note that the model training process also requires confirming the association between set A and set B. For model training, the measurement results from set B will be used as model input, and the measurement results from set A will be used as ground truth labels. Therefore, the association between set B and set A can be achieved by pre-configuring the resources of both sets A and B to the terminal device. However, for model inference, the terminal device only needs to measure the beams in set B; the resources or indices of the beams in set A will only be used for reporting. Therefore, the key issue in the model inference process is how to represent the resources or indices of set A.

[0086] During inference, the terminal device does not measure beams in set A, therefore, it does not need to configure the RS (Resource Sets) for beams in set A. However, in some scenarios, the RS of beams in set A can be configured for the terminal device for other purposes, such as performance monitoring. In this case, both the resource sets of set B and set A will be configured for the terminal device. This demonstrates that the network can configure the resource sets of set B and set A based on different purposes. Taking CSI (Computer-Side Interface) resources as an example, the terminal device needs to know the intent of the configured CSI resources (whether for training, inference, monitoring, or non-AI / ML operations), because the corresponding CSI report types may differ.

[0087] As an example, for a monitoring process, based on the discussion of monitoring types, the end device may need to measure the monitoring resources configured for the network device and report the model output / labels, or report calculated metrics (e.g., beam prediction accuracy). For traditional non-AI / ML operations, the end device may need to measure the Tx beam and report the measured beam / RSRP.

[0088] During the inference process of the AI / ML model, measurements based on beams in set B can be used as model input. Additionally, beam ID information can also be provided as model input. Based on the model output, the Top-1 / Top-K beams in set A can be obtained, or the predicted L1-RSRP can be used to determine the Top-1 / Top-K beams in set A (depending on the label).

[0089] Alternatively, the model output may be, for example, the probability of each beam in Set A becoming the Top-1 beam, or the predicted L1-RSRPs.

[0090] In certain scenarios, terminal devices can support beam prediction in the spatial and / or temporal domains, i.e., BM-Case 1 and / or BM-Case 2. Based on AI / ML enhancements, spatial domain beam prediction (BM-Case 1) and temporal domain beam prediction (BM-Case 2) can reduce terminal device overhead and decrease beam measurement and reporting latency. BM-Case 1 performs spatial domain downlink (DL) beam prediction on set A based on measurements from set B. For BM-Case 1, measurements based on set B of beams are used as model input to predict the Top-1 / Top-K beams in set A. BM-Case 2 performs temporal DL beam prediction on set A based on historical measurements from set B. For BM-Case 2, measurements based on set B of beams at historic time instance(s) can be used as model input to predict the temporal DL beams of set A. Predictions for DL ​​Tx beams and DL Tx / Rx beams can also be used to evaluate prediction performance.

[0091] For BM-Case1 and BM-Case2, the terminal device can report the prediction results to the NW based on the output of the terminal device-side model, or the NW can predict the Top-1 / Top-K beams based on the measurement reports of the NW-side model set B.

[0092] Taking the terminal device-side model as an example, for BM-Case 1 with a terminal device-side AI / ML model, beam indication can be performed using the traditional transmission configuration indicator (TCI) state mechanism. Optionally, the terminal device can report the measurement results of more than four beams in a single reporting instance. For BM-Case 2 with a terminal device-side AI / ML model, the terminal device can report the following information from the AI / ML model inference to the NW in a single reporting instance: the beams used at N future times based on the AI / ML model inference output; the timestamp information corresponding to the reported beams; and information about the measurement values ​​for multiple past time instances.

[0093] Beam indication is also crucial information in beam management reasoning. After the terminal device reports the Top-K predicted beam, the NW will further indicate the beam used for the second-step measurement, or the terminal device can directly trigger the second measurement. Unlike BM-Case 1, BM-Case 2 can obtain Top-K beams corresponding to multiple time instances. Beam indication on the network device side needs to consider time information.

[0094] As an example, network devices can use multiple indicators to specify the beam for terminal devices. The advantage of doing so is that the network device can select a more suitable beam based on real-time channel changes.

[0095] The following section, with reference to Figure 3, uses the UE-side model as an example to introduce the beam prediction-based model inference process based on the interaction between the UE and gNB.

[0096] Referring to Figure 3, in step S310, gNB performs sweeping based on the beams in the sparse set B.

[0097] In step S320, the UE-side model performs Top-K beam prediction. The UE inputs the measurement values ​​of the set of B beams into the AI ​​model and outputs the indices and L1-RSRPs of the top K best beams among all measured beams, as well as the beam ID or beam index. The UE-side model can also output the L1-RSRP of the best beam and the difference between the RSRPs of the other K-1 beams and the L1-RSRP of the best beam, and report them to the base station. The value of K can be configured by the base station, or the UE can determine the value of K based on the mobile speed, location information, and service mode.

[0098] In step S330, report the CRI and / or predicted quality of the Top-K beam.

[0099] In step S340, the gNB can continue to initiate Top-K beam sweeping. The Top-K beam sweeping procedure can be configured by the gNB. Step S340 is an optional step.

[0100] In step S350, the UE reports the beam quality. The UE can report the actual top-performing beam, or it can report part or all of the indices and L1-RSRPs of the top K best beams. The UE can reuse the traditional beam reporting mechanism.

[0101] In step S360, the gNB indicates the beam used for DL ​​data transmission. The gNB can reuse the traditional TCI beam indication mechanism.

[0102] The above section, with reference to Figures 2 and 3, outlines the process for beam management or beam prediction based on AI / ML models. However, AI / ML-based beam management enhancement still faces some challenges that require further research and resolution.

[0103] As an example, when a terminal device uses AI algorithms to process beams detected and measured from a wireless network to infer other beams that may have higher strength and / or higher quality, the terminal device needs to ensure the consistency of the model between the training and inference phases. As mentioned earlier, there is a certain time interval between the training and inference phases, and changes in radio parameters / conditions may lead to errors in the inference phase.

[0104] As an example, as mentioned earlier, set A typically has more beams than set B. Set B usually represents the measurement set or a portion of the downlink reference signal, used to assist the network side in beam prediction and selection. However, the terminal device may not need to know whether the beam scan performed by the network device is for beams in set A or set B, or even for non-AI / ML-based beamforming. Therefore, how the terminal device determines the beams in set B from the beams transmitted by the network device is a problem that needs to be considered.

[0105] It should be understood that the above description of the problems is based on the terminal device side model, and the embodiments of this application can also be used for the network side model.

[0106] Based on this, embodiments of this application propose a method for wireless communication. In this method, after receiving multiple beams transmitted by a second device, a first device can determine a first beam set (set B) based on at least two of three factors: beam measurement values, the capabilities of the first device, and network configuration, in order to perform beam prediction on a second beam set (set A). Through this method, the first device can determine the first beam set independently according to actual conditions, improving the flexibility of beam prediction.

[0107] The method for wireless communication proposed in this application will be described in detail below with reference to Figure 4. Figure 4 is presented from the perspective of the interaction between the first device and the second device.

[0108] The first device can be any of the terminal devices described above, or it can include any type of terminal device. For example, the first device is a UE (User Equipment). Alternatively, the first device can include a terminal device and any processing device for beam prediction.

[0109] In some embodiments, the first device supports functional enhancements based on AI / ML operations. For example, the first device has the capability to enhance beam management based on AI / ML operations.

[0110] In some embodiments, a first model is deployed on the first device to perform beam prediction. When the second device is a network device, the first device performs DL beam prediction. When the second device is a terminal device, the first device performs side-travel beam prediction.

[0111] As an example, the first model is a model that supports AI algorithms or ML, that is, the first model is an AI / ML model.

[0112] As an example, the beam prediction implemented by the first model can be BM-Case1 as mentioned above, or BM-Case2, or other beam prediction types in the future, which are not limited here.

[0113] In some embodiments, a first model is deployed on the first device side. That is, the first model is not on the terminal device, but on a server that communicates with the terminal device. For example, the first model is on an OTT server that communicates directly with the terminal device.

[0114] The second device can be any network device communicating with the first device, or it can be a terminal device communicating with the first device. When the first device is within the coverage area of ​​a network device, the second device can be a network device. In a side-by-side communication system, the first device communicates with a terminal device, and the second device can be a terminal device.

[0115] In some embodiments, the second device can monitor the process by which the first device processes the first model. For example, the second device can determine whether the first model is currently in the training or inference phase based on a report sent by the first device.

[0116] In some embodiments, the second device supports AI / ML operations. The first model may be deployed on the second device.

[0117] In some embodiments, the second device may send multiple beams to the first device multiple times to enable the first device to perform measurements and to train and infer the first model based on the measurement results.

[0118] Referring to Figure 4, in step S410, the first device receives multiple beams transmitted by the second device. The window through which the first device receives multiple beams or the window through which the second device transmits multiple beams is called the observation window. That is, the first device receives multiple beams transmitted by the second device within the observation window.

[0119] The observation window is used by the first device to receive multiple beams. The observation window includes RS resources for multiple beams, which need to be configured.

[0120] In some embodiments, the observation window of the first device can be configured periodically. For example, when the second device periodically transmits multiple beams, the first device can set one or more observation windows based on the transmission period of the multiple beams. When the second device periodically transmits multiple beams, the periodically transmitted multiple beams can be shared by multiple terminal devices, including the first device. That is, the periodically transmitted multiple beams may correspond to multiple observation windows, and the observation windows of multiple terminal devices can each correspond to these multiple observation windows, as will be explained later with reference to Figure 5.

[0121] As an example, each terminal device has a corresponding observation window. Therefore, the observation window for the first device to receive multiple beams is different from the observation windows for other terminal devices to receive beams. Optionally, the observation window for the first device to receive multiple beams may partially overlap with the observation windows for other terminal devices to receive beams.

[0122] As an example, when a second device transmits multiple beams based on a period, these multiple beams will be transmitted even during the prediction window of the first device's model inference. For instance, when performing model inference based on a periodic beam group B, the NW will still transmit the periodic beam group B even during the prediction window. In this scenario, the observation window can overlap with the prediction window. Within the overlapping temporal resources, the first device can choose to receive the beams transmitted by the second device or not.

[0123] In some embodiments, periodic beam transmission can be triggered based on the triggering of periodic prediction reports. The network can configure RS resources for a first beam set for inference of a first model for a first device. Based on the resource periodicity and offset of the configured RS resources for the first beam set, the first device can identify the time slot of the RS corresponding to each scheduled first beam set in order to measure the beam at one or more corresponding time points. This RS resource can also be referred to as the RS resource for multiple beams transmitted by a second device.

[0124] As an example, the first beam set (RS) resource can be located in the observation window of the first device. Beam resources corresponding to multiple time instances can be configured in the observation window. Considering that the first beam set may differ in each time instance, the resource of the first beam set for each time instance within the observation window can be configured as an RS set.

[0125] In periodic reporting or periodic beam transmission, the observation window is one of multiple observation windows. The observation window of the first device can be one or more windows among multiple observation windows. The positions of the multiple observation windows can be determined based on the position of the initial observation window and the first period. The first beam set is used for repeated transmission in the multiple observation windows.

[0126] As an example, the first period may or may not be equal to the reporting period.

[0127] As an example, the first device can be one of multiple devices sharing periodic RS resources. These multiple devices can perform beam prediction based on a first set of beams within any of multiple observation windows.

[0128] In some embodiments, the network can configure the length of the observation window for the first device. For example, how many time slots are needed as RS resources. The observation window can be a set of RSs configured by the network for the first device to perform measurements for CSI reporting or other reporting. These resources are configured as periodic resources, and different time instances can correspond to different RS configurations.

[0129] In some embodiments, the length of the observation window can be configured or adjusted in one or more of the following ways: configured by a third parameter, which is used to define the length of the observation window; determined by a report offset and a resource offset; increased by increasing the reporting period or decreasing the reference signal resource offset; decreased by decreasing the reporting period or increasing the reference signal resource offset; or predicted based on the number of time instances corresponding to the first beam set.

[0130] As an example, the window length (duration) of the observation window can be indicated or configured via the CSI framework.

[0131] As an example, the observation window length can be configured based on a third parameter, which can directly define the observation window length. For instance, the observation window length can be a new information element (IE) defined in csi-ReportConfig. The new IE can directly define a window length, such as 20 time slots or 50 time slots. This configuration method allows network operators to control the duration of the observation window more directly, without relying on the difference between the report offset and the resource offset.

[0132] As an example, the length of the observation window can be determined based on the report offset and resource offset of the periodic reports. For instance, the value of the network configuration parameter ReportPeriodityAndOffset can determine the report offset; the value of the parameter ResourcePeriodityAndOffset can determine the resource offset. ResourcePeriodityAndOffset indicates the period and offset of the RS resources in the first beam set, defining from which time slot the terminal device begins measuring the RS resources and how many time slots the resources repeat.

[0133] For example, the first device can determine the length of the observation window using the values ​​of ReportPeriodityAndOffset and ResourcePeriodityAndOffset. The length of the observation window can be defined as: L w =T re ―T RS ; among which, L w It is the length of the observation window, T re It was the first reported time slot, T RS It is the first time slot of the first beam set RS resources and also the starting time slot of the observation window.

[0134] Optionally, T RS It can be described as: T RS= slot 0 + offset1; where slot 0 is the position of time slot 0; offset1 is the offset of the first beam set RS resource (ResourceOffset), indicating which time slot the first beam set RS resource starts from.

[0135] Optionally, the first reporting time slot T re It can be described as: T re =slot 0+offset2; where offset2 is the report offset (ReportOffset), indicating which time slot the report starts from.

[0136] Therefore, the length of the observation window can be described as: L w =T re ―T RS =offset2―offset1.

[0137] As discussed above, the length of the observation window typically depends on the difference between the report offset and the RS resource offset. This difference determines the amount of measurement information the first device can accumulate before each report. As an example, to configure or adjust the observation window length, the CSI framework can add the following elements: report periodicity, report offset, RS resource periodicity, and RS resource offset.

[0138] Optionally, the reporting period can be used to configure how often (in time slots) the terminal device submits a CSI report.

[0139] Optionally, the report offset can be used to configure the offset of the report slot relative to the time axis to determine the starting slot of the report.

[0140] Optionally, the RS resource period can be used to configure the repetition period of the RS resources of the first beam set to determine how many time slots the first device can measure the same resource.

[0141] Optionally, the RS resource offset can be used to configure the starting time slot of the RS resource to determine the starting point of the measurement window or observation window.

[0142] As an example, the network side can extend the duration of the observation window by increasing the reporting period or decreasing the RS resource offset. This allows the first device to collect more RS resources over a longer period. Reducing the RS resource offset allows RS resources to be measured at an earlier time slot. This method is suitable for scenarios requiring more accurate channel state information, such as in high-interference or high-signal-to-noise ratio environments.

[0143] Optionally, the configuration of extending the observation window length may also include increasing the reporting offset so that the first reporting slot is later, thereby providing a longer time period for measuring RS resources.

[0144] As an example, the network can shorten the observation window length by reducing the reporting period or increasing the RS resource offset. In some low-load or relatively stable environments, the network may shorten the observation window length to reduce the computational burden or resource overhead of the primary device.

[0145] As an example, the length of the observation window can be predicted based on the number of time instances corresponding to the first beam set. This number of time instances can be configured by the network or dynamically adjusted. For instance, in BM-Case2, the observation window could include three time instances of beam transmission.

[0146] In some embodiments, the observation window of the first device can be configured aperiodically. For example, when the second device can transmit multiple beams aperiodically, the observation window of the first device can be set based on the triggering of aperiodic reports, as will be explained later with reference to Figure 6.

[0147] As an example, a trigger command can be sent whenever the network needs to predict future beams. Once beam prediction is triggered, the first device can launch an AI / ML model to perform inference and predict future beams based on measurements from the current observation window.

[0148] As an example, the timing of network-triggered beam prediction can be dynamically adjusted based on network conditions, user location, channel changes, and other factors.

[0149] In some embodiments, when the observation window is configured aperiodically, the observation window of the first device can be determined according to a trigger command. As an example, the length of the observation window in aperiodic configuration can be defined as the duration between the "time of triggering aperiodic reporting" and the "time of the reporting slot". The length of the observation window can be variable, allowing for dynamic adjustment based on actual conditions. For example, the network can set different observation window lengths based on changes in channel conditions. As an example, in aperiodic configuration, instead of configuring the length of the observation window, only the length of the prediction window can be configured to align with the time instances of the prediction.

[0150] Multiple beams received by the first device are used to determine a first beam set. The first beam set, or measurements of the first beam set, can be used as input to a first model. The first beam set can be set B as described above. The first beam set is used to predict a second beam set. The second beam set can be set A as described above.

[0151] In some embodiments, the first beam set is a subset of the multiple beams. That is, after receiving multiple beams in the observation window, the first device selects a subset of beams as the first beam set. In this scenario, the first device does not need to determine whether the multiple beams transmitted by the second device are for set B, set A, or non-AI / ML operations; i.e., it does not need to determine the purpose of the transmitted beams, but directly determines the first beam set based on the multiple beams. Furthermore, since the first device aims to predict the optimal beam in the second beam set, pre-selecting the received multiple beams helps reduce prediction errors in predicting the optimal beam.

[0152] In some embodiments, the first beam set is all the beams among the plurality of beams. That is, all the beams received by the first device within the observation window are considered as the first beam set. For example, depending on the network configuration, the first device may consider the received beams as being used for set B. Alternatively, when the capabilities of the first device meet certain conditions, all received beams may be considered as the first beam set for inference.

[0153] As an example, when multiple beams are transmitted periodically, the first set of beams determined by these multiple beams is also transmitted periodically. Taking set B as an example, each terminal device has its own prediction window and observation window, and the periodic set B can be easily shared among multiple terminal devices. Therefore, the periodic set B is feasible when multiple terminal devices, including the first device, use AI / ML beam management features.

[0154] As an example, when multiple beams are transmitted aperiodically, the first set of beams determined by the multiple beams is also transmitted aperiodically.

[0155] The first beam set can be determined based on the first information. In other words, the first device can determine all beams in the first beam set from multiple beams based on the first information. For example, the first information can be used by the first device to filter multiple received beams to determine the first beam set. For example, the first information can be used by the first device to determine that multiple received beams belong to the first beam set.

[0156] The first information includes at least two of the following: measurements of multiple beams, the capabilities of the first device, and network configuration. As an example, the first device can select the beam with better channel quality from the multiple beams based on its capabilities and RSRP measurements, and use this as the first beam set. As an example, the first device can select the beam with better channel quality from the multiple beams based on network configuration and RSRP measurements, and use this as the first beam set. As an example, the first device can determine the beams in the first beam set from the multiple beams based on its capabilities and network configuration. As an example, the first device can determine the first beam set by comprehensively considering RSRP measurements, its capabilities, and network configuration.

[0157] When the first information includes measurements of multiple beams, the first beam set may include N beams with relatively good beam channel quality, where N is a positive integer. Alternatively, the first beam set may include N beams with beam channel quality within a certain range.

[0158] In some embodiments, the measurements of multiple beams can be represented by RSRP, signal to interference plus noise ratio (SINR), or other similar parameters.

[0159] In some embodiments, the measurement values ​​of the multiple beams are obtained by measuring after receiving the multiple beams, that is, real-time measurement values. When the first device receives multiple beams in the observation window, it can directly measure the multiple beams.

[0160] As an example, measurements from multiple beams can be grouped into a measurement vector for easier processing. For instance, the RSRP values ​​of each beam in the first beam set can be formed into a vector, such as RSRP... B1 RSRP B2 RSRP Bn , where n is the number of beams in the first beam set. The RSRP measurements of all beams can be formed into a vector set, which can be used as input to an AI / ML model for training or inference. For example, the model can use these measurements to predict the best K beams (Top-K) or the best 1 beam (Top-1) in the second beam set.

[0161] In some embodiments, the measurements of multiple beams may include historical measurements of multiple beams. Historical measurements may be represented by measurement vectors or in other ways.

[0162] As one embodiment, the first device can select a first beam set by analyzing historical measurements. For example, the first device can combine RSRP measurement results from several past time steps and determine the RSRP measurement values ​​of multiple beams by weighting the RSRP of historical beam measurements, thereby determining the first beam set. Furthermore, if the geographical location information and movement speed of the first device are known, the network can use this information to further optimize beam selection.

[0163] When the first information includes the capabilities of the first device, the capabilities of the first device may include the type or algorithm of the first model, the number of samples required by the first model, the computing power of the first device, and the business models that the first device can support. In some scenarios, the capability information of the first device may also include capability information related to beam reception, such as the moving speed and location information of the first device.

[0164] As an example, the first device can determine the first beam set based on its capabilities or business model. For instance, the first device can report basic information such as the required number of samples, the number of Tx beams required for sets A and B, the type / algorithm of the first model, and the preferred set B mode corresponding to the first model to the network, so that the network can configure the first beam set or the first device can determine the first beam set from multiple beams. As another example, when requesting data collection for training, the first device can report the preferred set B mode specific to the model.

[0165] As an example, the first beam set can be one of multiple beam sets. These multiple beam sets can correspond to various beam set patterns related to device capabilities. These multiple beam set patterns are determined based on network configuration. For example, to reduce RS overhead on the network side, the network can pre-configure multiple beam set patterns, then select and transmit the appropriate beam set pattern to the first device to generate input data for the AI ​​model. Alternatively, the network can send multiple beam set patterns, and the first device can use a set of multiple beam sets as input.

[0166] Optionally, when sending basic information, the first device may not disclose detailed receive (Rx) beam information to the network.

[0167] When configuring the network, the network can directly configure the beams in the first beam set, the number of beams in the first beam set, and can also configure different first beam sets for different regions or types of terminal devices. For example, the network can indicate which beam IDs can be used as beam IDs in the CSI frame information. Furthermore, when the network performs beam scanning based on terminal devices in several different regions, the settings of the first beam set can be different or the same. Additionally, the network can determine the type of the first device based on its movement speed, location information, computing power, service mode, etc., and configure different first beam sets for different types of terminal devices to facilitate selection by the first device. Detailed configuration information can be reported by the network device and / or requested by the first device.

[0168] As one embodiment, all beams in the first beam set are the N beams with the highest measured values ​​among multiple beams, where N is determined according to the network configuration. For example, the first device can select the N beams with the best channel quality (based on RSRP or other quality parameters) as the first beam set, and then report it to the network device. The value of N can be defined according to the specific network configuration.

[0169] As one embodiment, all beams in the first beam set are those whose measured values ​​are greater than a first threshold among a plurality of beams. The first threshold may be a threshold related to signal quality. For example, the first device may base its signal quality on a set signal quality threshold RSRP. target Select beams that satisfy a threshold value greater than the threshold value as the first beam set.

[0170] In the above embodiments, the first threshold can be determined according to the network configuration or by the first device itself.

[0171] As one embodiment, the first beam set includes multiple beam subsets, each beam subset corresponding to multiple thresholds related to the measured value. For example, the first device may base its measurement on multiple predefined quality thresholds RSRP. target A first device selects beams that satisfy different threshold values ​​as a subset of beams in a first beam set. Multiple beam subsets can correspond to a second beam set. The first device can predict the second beam set using some or all of the beam subsets in the first beam set.

[0172] In the above embodiments, multiple thresholds can be determined according to network configuration or by the first device itself.

[0173] In the above embodiments, multiple beam subsets may have the same or similar quasi co-location (QCL).

[0174] In the above embodiments, the number of beam subsets in the first beam set is determined based on the moving speed and / or coverage of the first device. That is, the first device can determine how many beam subsets to use to form the first beam set to predict the second beam set based on its speed and coverage. For example, the higher the speed of the first device, the more beam subsets can be used to form the first beam set to predict the second beam set. Similarly, the worse the coverage or the device is at the cell edge, the more beam subsets can be used to form the first beam set to predict the second beam set.

[0175] In the above embodiments, location-based beam selection can be more accurate when the first device is relatively stationary because the channel state changes less. In high-speed moving scenarios, the speed of the first device can help predict the trend of rapid channel changes, thereby optimizing beam selection. In multipath propagation environments, the first device can receive signals from multiple paths, and different beams may cover different propagation paths. The first device can select the path with better signal quality and use the corresponding beam as the beam in the first beam set.

[0176] It should be understood that when the determination of the first beam set takes into account the position, motion, or environmental information of the first device, in order to improve the generalization ability of the first model, the training data may also include information such as the position, motion speed, and environment of the first device.

[0177] In step S420, the first device performs beam prediction on the second beam set within the prediction window based on the measurement values ​​of the first beam set.

[0178] A prediction window can include multiple time instances of beam prediction from a first device. As an example, a prediction window is used by the network to perform beam indication or configuration based on the beam prediction results.

[0179] In some embodiments, the prediction window of the first device can be configured periodically. For example, when the first beam set is transmitted periodically, the first device can set one or more prediction windows based on the transmission period of the first beam set, as will be explained later with reference to Figure 5. The periodically transmitted first beam set may correspond to multiple prediction windows, and the prediction windows of multiple terminal devices can each correspond to these multiple prediction windows.

[0180] As an example, each terminal device has a corresponding prediction window. The prediction window used by the first device for model inference can be different from, the same as, or partially overlapped with the prediction windows used by other terminal devices for model inference; this is not limited here.

[0181] As an example, the configuration of the prediction window length can refer to the configuration or adjustment method of the observation window length, which will not be elaborated here.

[0182] In a periodic configuration, the prediction window and observation window of the first device share the same periodicity. This periodicity can be the same as the periodicity of the RS resources of multiple beams or the first beam set. Therefore, the prediction window can be implicitly determined.

[0183] As one embodiment, the length of the prediction window and the length of the observation window are used to determine the reporting period for which the first device sends a report. For example, the first period can be the sum of the lengths of the prediction window and the observation window. For example, if there is no gap between the observation window and the prediction window, a reporting period can be completely divided into the observation window and the prediction window. The reporting period can be the first period. Therefore, the duration of the prediction window can be determined by the reporting period, i.e., the reporting period minus the duration of the observation window.

[0184] As an example, when the prediction window is configured periodically, the prediction window of the first device can be one or more windows from a plurality of prediction windows. The positions of the plurality of prediction windows can be determined based on the position of the initial prediction window and the first period.

[0185] In a periodic configuration, the prediction window and the observation window may not have the same periodicity. For example, the first beam set is configured with a longer periodicity, while the first device needs to perform prediction and reporting in the time slot between RS resources of two beam sets with shorter periodicities. In this case, the NW can further configure the prediction periodicity and prediction offset in csi-ReportConfig. The prediction offset, for example, is the sign that shifts the prediction window to the last set of RS resources within the observation window.

[0186] As an example, when the observation window and prediction window have different periods, the prediction window can be determined based on the position of the initial prediction window and the second period. The length of the second period differs from the length of the first period. Optionally, the length of the second period is shorter than the length of the first period. Optionally, the length of the second period is longer than the length of the first period.

[0187] As an example, the prediction period is the configured prediction window time interval, defining how often the first device should generate a prediction report.

[0188] As an example, the prediction offset, which is the configured start time slot of the prediction window, can be determined based on the time slot of the last RS resource within the observation window. For instance, the start time slot of the prediction window is the time slot of the last RS resource within the observation window plus the prediction window offset.

[0189] In some embodiments, the prediction window can be configured based on the configuration of the observation window. For example, the prediction window can correspond one-to-one with the observation window.

[0190] In some embodiments, the prediction window of the first device can be configured aperiodically. For example, when the first beam set is transmitted aperiodically, the prediction window of the first device can be set based on the triggering of aperiodic reports, as will be explained later with reference to Figure 6.

[0191] In a non-periodic configuration, the network can configure the length of the prediction window for the first device, which is the future time period the first device wants to predict. The length of the prediction window can be a fixed length or can be adjusted according to specific conditions (such as measurement error or the performance of the AI / ML model). As an example, the length of the prediction window can be dynamically adjusted based on the prediction error of the AI / ML model.

[0192] For example, the length of the prediction window may include two future time instances that need to be predicted.

[0193] For example, assuming the difference reaches β (i.e., the error between the previous prediction and the actual measurement is large), the AI / ML model needs to be fine-tuned, and the prediction window length should be increased accordingly to offset random errors. In other words, if the prediction error is large, the network can increase the prediction window length, thereby providing the AI / ML model with more data to correct the error and improve the accuracy of future beam predictions.

[0194] The second beam set contains more or more beams than the first beam set, allowing for prediction of a larger number of beams with fewer beams. As mentioned earlier, the second beam set can be set A, and the first beam set can be set B.

[0195] In some embodiments, the first device can perform beam prediction on the second beam set using a first model. For example, the first device can use measurements of the first beam set as input to the first model, and then output the optimal beam in the second beam set through the first model.

[0196] In some embodiments, the first model can perform beam prediction on the second beam set after model training is completed. When the first model is located on the terminal device side, the terminal device or the server connected to the terminal device can collect training data and train the first model. When the first model is located on the network device side, the network device can collect training data and train the first model.

[0197] As an example, the training data used to train the first model can be determined based on the intended use of the first model. When the first model is used to predict a second set of beams transmitted by a second device, the training data of the first model can be related to the transmitted beams of the second device. For example, the training data can be related to multiple beams transmitted by the second device. Alternatively, the training data can be related to a first set of beams transmitted by the second device. Or, the training data can be related to a second set of beams transmitted by the second device.

[0198] In some embodiments, the first device can generate training data. For example, when the first device is a terminal device, the terminal device can generate measurement values ​​of multiple beams as training data.

[0199] In some embodiments, the first device may collect training data for model training. For example, when the first device includes a terminal device and a first server for training the first model, either the terminal device or the first server may receive training data sent by other devices. The server used by the terminal device to collect training data may be referred to as a data acquisition server.

[0200] As an example, the first device can generate or collect training data related to the transmitted beam of the second device. For instance, the terminal device can generate or collect training data and then send this training data to the first server.

[0201] In some embodiments, when the first device is a terminal device, the terminal device can directly use the training data to train the first model. That is, when the first device is a terminal device on which the first model is deployed, the endpoint of the training data may include the terminal device.

[0202] In some embodiments, when the first device trains the first model through the first server, the data acquisition server of the terminal device can transmit the training data to the first server so that the first server can train the model.

[0203] In the above embodiments, the first server is, for example, an OTT server. When the OTT server is used to train the first model, the endpoint of the training data may include the OTT server.

[0204] For ease of understanding, the following example uses an OTT server as the first server for illustration.

[0205] As an example, for a device-side model, training data can be generated by the device itself. The endpoint of the training data can include the device or a device-side OTT server. Operation administration and maintenance (OAM) or the core network can be used to collect data for device-side model training.

[0206] In the example above, the OTT server on the terminal device side collects data and trains the model. Therefore, the OTT server on the terminal device side knows what data it needs. Leaving the data collection on the terminal device side to the OTT server means that the OTT server can collect the data it needs more directly. The required data type does not need to be specified, and when / what is transmitted is determined by the terminal device. This provides ample flexibility for terminal device / chipset vendors to train and implement their specific AI / ML models. The terminal device can use the same method to send training data to the terminal device-side OTT server for model training; this process is transparent to the network side and does not require control / visibility from the network / mobile network operator (MNO).

[0207] As an example, the terminal device itself should be responsible for protecting data privacy and obtaining user consent. More specifically, training data is reported via the user plane (UP), i.e., from the application-level data collection client on the terminal device to the application server (i.e., the OTT server on the terminal device side). Terminal device vendors can install their own data collection clients on the terminal device to collect lower-level data and report it to their own application server for AI / ML model training. For the data collection application client on the terminal device, data transmission from the terminal device to the terminal device vendor's application server can be supported according to relevant regulations, without network-side involvement. The data type / format of the collected data does not need to be specified, which provides ample flexibility for the terminal device to train and implement its specific AI / ML models.

[0208] As an example, after a terminal device collects training data, it can first transmit it to a data collection server (within the MNO) used for terminal device-side model training. Then, the training data can be transmitted from this data collection server to an OTT server (outside the MNO). In other words, the terminal device can collect data and transmit it to a server for terminal device-side model training. The data collection server for terminal device-side model training can be designated as the first entity.

[0209] In the example above, the first entity can choose whether to send the collected data to the OTT server. This OTT server has a different ownership than the OTT server in the previous example. The terminal device can transmit the collected data to the first entity within the MNO via UP, and then the first entity can choose to forward the collected data to the OTT server, a process that depends on the implementation of the terminal device.

[0210] Referring again to Figure 4, in step S430, the first device sends a first report to the second device. The first report is used to determine one or K optimal beams (i.e., Top-1 or Top-K beams) in the second beam set, where K is a positive integer.

[0211] In some embodiments, the first report can be determined based on the output of the first model. When the first model performs the model inference phase, the output of the first model can be an inference result report. The first report can be determined based on the inference result report. For example, the first report can be an inference result report, or it can be a new report submitted after processing the inference result report.

[0212] As an example, the output of the first model could be the optimal beam ID in the second beam set, or a probability distribution of a beam ID. As another example, the output of the first model could also be the channel quality prediction value of the beam, or the L1-RSRP, and the difference between the RSRP of multiple beams and the optimal beam's RSRP.

[0213] In some embodiments, the first report is used to report one of the following: beam information of the K optimal beams, the beam information including RS indicators or predefined beam indices of the K optimal beams; beam information and RSRP of the K optimal beams; beam information of the K optimal beams and probability information of the K optimal beams predicted by the second beam set; RSRP difference between the measured RSRP of the first beam set and the best RSRP of some / all beams in the second beam set; indicating the strongest beam ID in a bitmap format; predicting RSRP of the measured beams and non-measured beams; predicting RSRP of the non-measured beams and measured RSRP of the measured beams; and reporting the error and error threshold between the predicted RSRP and the actual measured RSRP of each measured beam.

[0214] In the above embodiments, RSRP can be L1-RSRP or may include L1-RSRP.

[0215] In the above embodiments, RSRP can be replaced with SINR or other parameters indicating signal or channel quality.

[0216] As an example, the error threshold between the predicted RSRP and the actual RSRP can be one of several thresholds configured at a higher layer, or it can be a threshold determined by the terminal device and then communicated to the network side.

[0217] As one embodiment, the first report is used to report beam information of the predicted Top-K beams in a set of beams (the second beam set). The beam information of the Top-K beams can be an RS indicator (e.g., a conventional CRI / SSB RI) or a predefined beam index.

[0218] As an example, the first report is used to report the beam information of the predicted Top-K beams in the second beam set and the RSRP value of the predicted Top-K beams in the second beam set.

[0219] As an example, the first report is used to report the L1-RSRP difference between the measured L1-RSRP of the first beam set and the optimal L1-RSRP of the complete / subset of the second beam set.

[0220] As an example, the first report is used to report the beam information of the predicted Top-K beams in the second beam set and the predicted Top-K beam probability information of the second beam set, which will be illustrated in conjunction with Figure 7 below.

[0221] As an example, the first report is used to indicate the strongest beam ID in bitmap form.

[0222] As an example, for the predicted RSRP of the Top-K beams in the inference results report, the first report is used to report the predicted L1-RSRP of the measured beams and non-measured beams, or to report the predicted RSRP of the non-measured beams and the measured RSRP of the measured beams. If the beams are not configured to be measured, the predicted RSRP is reported; if the beams are configured to be measured, the measured L1-RSRP is reported.

[0223] As an example, the first report is used to report the L1-RSRP difference between the measured L1-RSRP of the predicted beam and the optimal L1-RSRP of the complete / subset of the second beam set.

[0224] As one example, the first report is used to report the error between the predicted RSRP and the actual measured RSRP for each measured beam. In this case, the first report may also include a set error threshold.

[0225] In some embodiments, the first report is configured to report at least two of the following: beam information of the predicted K optimal beams; beam information and RSRP values ​​of the predicted K optimal beams; beam information and probability information of the predicted K optimal beams; the difference between the predicted beam RSRP values ​​and the highest RSRP values ​​among some or all of the beams in the second beam set; and bitmap indication of one or K optimal beams.

[0226] As an example, the content of the first report may depend on the options for configuring the report content in the base station configuration.

[0227] In some embodiments, when the first report is configured to report multiple beams, the number of beams in the first report can be determined based on the base station configuration, or based on one or more of the following information: nrofReportedRS; nrofTopK; whether the first report is one of the multiple reports in the current reporting period; the weight of the first report in the multiple reports in the current reporting period; and the prediction error of the beam prediction.

[0228] As an example, when the network device is configured with nrofReportedRS>1, or nrofReportedRS is M (M is a positive integer), the beam in the first report can be M or less than M.

[0229] As one embodiment, when the network configuration received by the first device includes a new beam count parameter (e.g., nrofTopK), the beam count in the first report is determined by the first device. For example, through protocol extensions or parameter adjustments (e.g., introducing the new parameter nrofTopK), the first device with AI / ML capabilities is allowed to dynamically adjust the number and strategy of its beam reports. In this way, the network can receive the optimal Top-K beam reports from the first device, without necessarily requiring all first devices to report the same number of beams.

[0230] As a sub-implementation of the above embodiments, a network device (e.g., a gNB) can transmit parameter information nrofTopK to a first device via radio resource control (RRC) connection configuration messages, allowing the first device to dynamically adjust the number of beams reported. When the network shares this new parameter with the first device, it indicates that under certain conditions (such as the first device's location remaining unchanged, network additional conditions remaining unchanged, etc.), the first device can report fewer beams than nrofReportedRS.

[0231] As an example, the number of reports in the first report can be determined based on the prediction error of the beam prediction. For instance, the first device can evaluate the credibility of the AI / ML model inference results by calculating the error between the predicted L1-RSRP value and the actual measured L1-RSRP value for each beam. If the prediction error is very low, the model's prediction results have high credibility. In this scenario, the first device can report Top-K beams based on the predicted L1-RSRP values, where K can be less than the configured nrofReportedRS value.

[0232] As a sub-implementation of the above embodiments, the first device can set an error threshold. If the prediction error of some beams is lower than the threshold, these beams can be considered "high-confidence beams," and a smaller number of Top-K beams are selected for reporting. If the error is higher than the threshold, the first device needs to further adjust the beam reporting strategy to ensure coverage of all potentially important M beams.

[0233] As an example, when the number of beams in the first report is less than the value of nrofReportedRS, the first device can adopt a multi-round reporting strategy to send the first report. That is, if the number of beams determined by the first device in a beam report is less than the network-configured nrofReportedRS value, a multi-round reporting strategy can be adopted. For example, the first report may be one of multiple reports, the number of which is determined based on the value of nrofReportedRS and the number of beams in each report. Alternatively, the first report may include multiple reports submitted in multiple rounds.

[0234] As a sub-example of the above embodiments, the first device may first report the beams with smaller prediction errors (Top-K beams) in the first report. If the network has further requirements for the number of beams, the first device may gradually supplement other beams in subsequent reports.

[0235] As a sub-implementation of the above embodiments, multiple reports submitted in multiple rounds can correspond to multiple transmission priorities. When the first report is one of the multiple reports, the transmission priority of the first report can be determined based on the beam prediction error in the first report.

[0236] As a sub-implementation of the above embodiments, the first device can assign a weight to each of the multiple reports to determine the transmission priority. This weight can be determined based on the magnitude of the L1-RSRP prediction error of the beam. For example, beams with smaller prediction errors have higher weights and higher reporting priority; beams with larger errors have lower weights and may have their reports delayed or not reported at all.

[0237] For example, when the first report is one of multiple reports, the weight of the first report can be a first weight. The first weight can be used to determine the transmission priority of the first report, and the first weight is determined based on the beam prediction error in the first report.

[0238] The method for determining the first beam set and the content of the first report by the first device have been explained above with reference to Figure 4. In the method shown in Figure 4, the transmission of the first beam set can be periodic or aperiodic. Correspondingly, the first report can be transmitted periodically or aperiodically. The following describes two types of periodic and aperiodic reports with reference to Figures 5 and 6. Figures 5 and 6 are both introduced from the perspective of the interaction between the UE (first device) and the NW (second device), and the first model is located on the UE side.

[0239] During periodic reporting, the NW can configure periodic reporting and offsets to define how many slots the first device reports every and from which slot it begins reporting. From the configured periodic reporting and offsets, the first device can also identify the reporting slot for each reporting instance. For example, the parameter ReportPeriodityAndOffset can configure the network to trigger periodic predictive reporting in slot 0. Similarly, the parameter ResourcePeriodityAndOffset can configure the period and offset of RS resources.

[0240] Alternatively, by combining the values ​​of ReportPeriodityAndOffset and ResourcePeriodityAndOffset, the first device can determine the time point for each measurement and report, and thereby calculate the length of the observation window.

[0241] Optionally, when configuring the RS resources of the first beam set as periodic RS resources, a prediction time instance (prediction window) related to sending periodic reports can also be configured.

[0242] Figure 5 illustrates the entire process of periodic reporting, which enables periodic model inference for beam management. During this process, the UE can continuously measure the L1-RSRP of the first beam set RS resources in the periodic set.

[0243] Referring to Figure 5, in step S510, the NW sends a periodic report to the UE in time slot 0 to trigger the process.

[0244] In step S520, the NW can send multiple beams in the first observation window (SetB (first beam set) RS resource), the UE measures the first beam set, and inputs it into the AI / ML model.

[0245] In step S530, the UE can send the first periodic report based on the output of the AI / ML model. The first periodic report can be used to design beam indicators P2 at times T1 and T2 in the NW design. The two beam indicators P2 can correspond to the beam predictions made by the UE at times T1 and T2 in step S535.

[0246] In step S540, the NW can send multiple beams in the second observation window (SetB (first beam set) RS resource), the UE measures the first beam set, and inputs it into the AI / ML model.

[0247] In step S550, the UE can send a second periodic report based on the output of the AI / ML model. This second periodic report can be used for NW design of beam indicators P2 at times T3 and T4. The two beam indicators P2 can correspond to the beam predictions made by the UE at times T3 and T4 in step S555.

[0248] In Figure 5, the starting time slot for the RS resource can be time slot n, which is determined based on the resource offset. The first beam set can be transmitted within the observation window. The UE can use the measurements from the first beam set as model input to predict the optimal beam for one or more future time slots and report the predicted information of the optimal beam in the second beam set at times T1, T2, T3, and T4 to the NW. T1 and T2 are time instances of the first prediction window, and T3 and T4 are time instances of the second prediction window. Based on each future time slot, the NW can design and execute beam indication and / or configure the P2 / P3 process according to the model output. The interval between the two periodic reports can be determined based on the reporting period.

[0249] Figure 6 illustrates the entire process of aperiodic reporting, which enables aperiodic model inference for beam management.

[0250] Referring to Figure 6, in step S610, the NW sends an aperiodic report trigger to the UE.

[0251] Step S620 is the same as step S520 in Figure 5, and will not be described again.

[0252] In step S630, the UE sends an aperiodic report to the NW. This aperiodic report can be used by the NW to design beam indicators P2 for times T1 and T2. The two beam indicators P2 can correspond to the beam predictions made by the UE for times T1 and T2 in step S635.

[0253] In step S640, NW sends an aperiodic report trigger to UE again.

[0254] Step S650 is the same as step S540 in Figure 5, and will not be described again.

[0255] In step S660, the UE sends an aperiodic report to the NW. This aperiodic report can be used by the NW to design beam indications P2 for times T3 and T4. The two beam indications P2 can correspond to the beam predictions made by the UE for times T3 and T4 in step S665.

[0256] In Figure 6, the NW can configure RS resources for transmitting the first beam set only within the observation window. This RS resource is configured as a combination of multiple aperiodic resources and connected via aperiodic reports. Therefore, the NW does not need to configure the length of the observation window in csi-ReportConfig. However, for the length of the prediction window, the NW and UE need to align to determine the duration of the prediction window and where the predicted future time slots are located. Therefore, the period and length of the prediction window need to be explicitly configured within the CSI framework.

[0257] The preceding text introduced that the first report can include probability information for predicted Top-K beams. The following section, with reference to Figure 7, explains the probability information in the first report. Probability information refers to the probability that a beam will become a Top-1 or Top-K beam. Based on this probability information, some understanding of model performance can be gained. For example, probability information can be used to rank candidate beams, and the similarity of the ranking sequence can be compared with the beam's RSRP ranking sequence. Although different models may output different levels of probability information, if the beam's probability information is accurate enough, the final ranking of the beams should be the same or similar.

[0258] Figure 7 shows a comparison example of the beam ranking from model inference and the beam ranking from monitoring measurements of a second subset of beams. As shown in Figure 7, for comparison, the subset of beams configured for measurement in the model output can be filtered to compare probability scores. The measurement result can be the L1-RSRP value.

[0259] Referring to Figure 7, two examples of the best 8 beams are derived from model inference and monitoring measurements by comparing probability scores and measured L1-RSRP, respectively. The beams in Figure 7 are those with even-numbered beam IDs. As shown in Figure 7, there is a certain difference between the 8 best beams obtained from model inference and the 8 best beams obtained from measurement. For example, the best beam ID from model inference is 16, and the second best (2...)... nd The best beam ID is 12, and the third best (3) rd The best beam ID is 14, and the fourth beam ID is 8; the measured optimal beam ID is 16, and the second best (2) beam ID is 8. nd The best beam ID is 12, and the third best (3)rd The best beam ID is 8, and the fourth beam ID is 14.

[0260] Figure 7 compares whether the model's inference ranking matches the measured ranking and / or calculates the correlation between the two to determine the model's performance. This correlation can be, for example, Spearman correlation or Kendall correlation, effectively evaluating the accuracy of beam prediction ranking between model inference and actual measurements. A higher correlation coefficient indicates a closer consistency between the model's predictions and actual measurements, and thus better predictive performance.

[0261] The method embodiments of this application have been described in detail above with reference to Figures 1 to 7. The apparatus embodiments of this application will now be described in detail below with reference to Figures 8 to 10. It should be understood that the descriptions of the apparatus embodiments correspond to the descriptions of the method embodiments; therefore, any parts not described in detail can be referred to the preceding method embodiments.

[0262] Figure 8 is a schematic block diagram of a wireless communication apparatus according to an embodiment of this application. The apparatus 800 can be any of the first devices described above. The first device can be a terminal device. The apparatus 800 shown in Figure 8 includes a transceiver unit 810 and a processing unit 820.

[0263] The transceiver unit 810 is used to receive multiple beams transmitted by the second device within an observation window, the multiple beams being used to determine a first beam set; the processing unit 820 is used to perform beam prediction on a second beam set within a prediction window based on the measurement values ​​of the first beam set; the transceiver unit 810 is also used to send a first report to the second device; wherein, the first report is used to determine one or K optimal beams in the second beam set, K being a positive integer, the first beam set being determined based on first information, the first information including at least two of the measurement values ​​of the multiple beams, the capabilities of the first device, and the network configuration.

[0264] Optionally, the first report is used to report one of the following information: beam information of the K optimal beams, including reference signal indicators or predefined beam indices of the K optimal beams; beam information and RSRP of the K optimal beams; beam information and probability information of the K optimal beams predicted by the second beam set; RSRP difference between the measured RSRP of the first beam set and the best RSRP of some / all beams in the second beam set; indicating the strongest beam ID in a bitmap format; predicting RSRP of the measured and non-measured beams; predicting RSRP of the non-measured beams and measured RSRP of the measured beams; and reporting the error and error threshold between the predicted RSRP and the actual measured RSRP of each measured beam.

[0265] Optionally, all beams in the first beam set are one of the following: the N beams with the highest measurement values ​​among multiple beams, where N is a positive integer and is determined according to the network configuration; or the beams among multiple beams whose measurement values ​​are greater than a first threshold, where the first threshold is determined according to the network configuration.

[0266] Optionally, the first beam set includes multiple beam subsets, each beam subset corresponding to multiple thresholds related to the measurement value, and the number of beam subsets in the first beam set is determined based on the moving speed and / or coverage of the first device.

[0267] Optionally, the first beam set is one of multiple beam sets, and the multiple beam sets correspond to various beam set patterns related to capabilities. The various beam set patterns are determined according to the network configuration.

[0268] Optionally, the measurements of multiple beams include historical measurements of multiple beams, which are represented by measurement vectors.

[0269] Optionally, the observation window is one of multiple observation windows, the positions of which are determined based on the position of the initial observation window and the first period, and the first beam set is used to repeatedly transmit in the multiple observation windows.

[0270] Optionally, the first device is one of a plurality of devices, and the plurality of devices perform beam prediction based on a first beam set in any one of a plurality of observation windows.

[0271] Optionally, the length of the observation window can be configured or adjusted in one or more of the following ways: configured via a third parameter, which is used to define the length of the observation window; determined via report offset and resource offset; increased by increasing the reporting period or decreasing the reference signal resource offset; decreased by decreasing the reporting period or increasing the reference signal resource offset; or predicted based on the number of time instances corresponding to the first beam set.

[0272] Optionally, the prediction window is one of multiple prediction windows, the position of which is determined based on the position of the initial prediction window and the first period, and the length of the prediction window and the length of the observation window are used to determine the reporting period.

[0273] Optionally, the prediction window is one of a plurality of prediction windows, which is determined based on the position of the initial prediction window and the second period, the length of the second period being less than the length of the first period.

[0274] Optionally, the position of the observation window is determined according to the trigger command.

[0275] Optionally, the number of beams in the first report is determined based on one or more of the following information: nrofReportedRS; nrofTopK; whether the first report is one of multiple reports in the current reporting period; the weight of the first report in the multiple reports in the current reporting period; and the prediction error of the beam prediction.

[0276] Optionally, when the number of beams in the first report is less than the value of nrofReportedRS, the first report is one of multiple reports, and the number of multiple reports is determined based on the value of nrofReportedRS and the number of beams in each report.

[0277] Optionally, multiple reports correspond to multiple transmission priorities, and the first weight of the first report is used to determine the transmission priority of the first report. The first weight is determined based on the beam prediction error in the first report.

[0278] Optionally, when the network configuration received by the first device includes nrofTopK, the number of beams in the first report is determined by the first device.

[0279] Optionally, beam prediction is achieved by a first model, which is an artificial intelligence or machine learning model.

[0280] Optionally, the first model is located on the terminal device side. The first device includes the terminal device and a first server for training the first model. The processing unit 820 is also used to generate or collect training data related to the transmission beam of the second device. The terminal device is used to send training data to the first server.

[0281] Figure 9 is a schematic block diagram of another device for wireless communication according to an embodiment of this application. The device 900 can be any of the second devices described above. The second device can be a terminal device or a network device. The second device 900 shown in Figure 9 includes a transceiver unit 910.

[0282] The transceiver unit 910 is used to transmit multiple beams within an observation window, the multiple beams being used to determine a first beam set; the transceiver unit 910 is also used to receive a first report transmitted by a first device; wherein the first report is used to determine one or K optimal beams in a second beam set within a prediction window, K being a positive integer, the beam prediction of the second beam set is based on the measurement values ​​of the first beam set, the first beam set being determined according to first information, the first information including at least two of the measurement values ​​of multiple beams, the capabilities of the first device, and the network configuration.

[0283] Optionally, the first report is used to report one of the following information: beam information of the K optimal beams, including reference signal indicators or predefined beam indices of the K optimal beams; beam information and RSRP of the K optimal beams; beam information and probability information of the K optimal beams predicted by the second beam set; RSRP difference between the measured RSRP of the first beam set and the best RSRP of some / all beams in the second beam set; indicating the strongest beam ID in a bitmap format; predicting RSRP of measured and non-measured beams; predicting RSRP of non-measured beams and measured RSRP of measured beams; and reporting the error and error threshold between the predicted RSRP and the actual measured RSRP of each measured beam.

[0284] Optionally, all beams in the first beam set are one of the following: the N beams with the highest measurement values ​​among multiple beams, where N is a positive integer and is determined according to the network configuration; or the beams among multiple beams whose measurement values ​​are greater than a first threshold, where the first threshold is determined according to the network configuration.

[0285] Optionally, the first beam set includes multiple beam subsets, each beam subset corresponding to multiple thresholds related to the measurement value, and the number of beam subsets in the first beam set is determined based on the moving speed and / or coverage of the first device.

[0286] Optionally, the first beam set is one of multiple beam sets, and the multiple beam sets correspond to various beam set patterns related to capabilities. The various beam set patterns are determined according to the network configuration.

[0287] Optionally, the measurements of multiple beams include historical measurements of multiple beams, which are represented by measurement vectors.

[0288] Optionally, the observation window is one of multiple observation windows, the positions of which are determined based on the position of the initial observation window and the first period, and the first beam set is used to repeatedly transmit in the multiple observation windows.

[0289] Optionally, the first device is one of a plurality of devices, and the plurality of devices perform beam prediction based on a first beam set in any one of a plurality of observation windows.

[0290] Optionally, the length of the observation window can be configured or adjusted in one or more of the following ways: configured via a third parameter, which is used to define the length of the observation window; determined via report offset and resource offset; increased by increasing the reporting period or decreasing the reference signal resource offset; decreased by decreasing the reporting period or increasing the reference signal resource offset; or predicted based on the number of time instances corresponding to the first beam set.

[0291] Optionally, the prediction window is one of multiple prediction windows, the position of which is determined based on the position of the initial prediction window and the first period, and the length of the prediction window and the length of the observation window are used to determine the reporting period.

[0292] Optionally, the prediction window is one of a plurality of prediction windows, which is determined based on the position of the initial prediction window and the second period, the length of the second period being less than the length of the first period.

[0293] Optionally, the position of the observation window is determined according to the trigger command.

[0294] Optionally, the number of beams in the first report is determined based on one or more of the following information: nrofReportedRS; nrofTopK; whether the first report is one of multiple reports in the current reporting period; the weight of the first report in the multiple reports in the current reporting period; and the prediction error of the beam prediction.

[0295] Optionally, when the number of beams in the first report is less than the value of nrofReportedRS, the first report is one of multiple reports, and the number of multiple reports is determined based on the value of nrofReportedRS and the number of beams in each report.

[0296] Optionally, multiple reports correspond to multiple transmission priorities, and the first weight of the first report is used to determine the transmission priority of the first report. The first weight is determined based on the beam prediction error in the first report.

[0297] Optionally, when the network configuration received by the first device includes nrofTopK, the number of beams in the first report is determined by the first device.

[0298] Optionally, beam prediction is achieved by a first model, which is an artificial intelligence or machine learning model.

[0299] Optionally, the first model is located on the terminal device side. The first device includes the terminal device and a first server for training the first model. Training data related to the transmission beam of the second device is sent by the terminal device to the first server.

[0300] Figure 10 is a schematic diagram of the structure of a communication device according to an embodiment of this application. The dashed lines in Figure 10 indicate that the unit or module is optional. This device 1000 can be used to implement the methods described in the above method embodiments. The device 1000 can be a chip, a terminal device, or a network device.

[0301] Apparatus 1000 may include one or more processors 1010. The processor 1010 may support apparatus 1000 in implementing the methods described in the preceding method embodiments. The processor 1010 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0302] The apparatus 1000 may further include one or more memories 1020. The memories 1020 store a program that can be executed by the processor 1010, causing the processor 1010 to perform the methods described in the preceding method embodiments. The memories 1020 may be independent of the processor 1010 or integrated within the processor 1010.

[0303] The device 1000 may also include a transceiver 1030. The processor 1010 can communicate with other devices or chips via the transceiver 1030. For example, the processor 1010 can send and receive data with other devices or chips via the transceiver 1030.

[0304] This application also provides a computer-readable storage medium for storing a program. This computer-readable storage medium can be applied to a terminal device or network device provided in this application, and the program causes a computer to execute the methods performed by the terminal device or network device in various embodiments of this application.

[0305] The computer-readable storage medium can be any available medium that a computer can read, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs, DVDs), or semiconductor media (e.g., solid-state disks, SSDs), etc.

[0306] This application also provides a computer program product. The computer program product includes a program. This computer program product can be applied to a terminal device or network device provided in this application embodiment, and the program causes a computer to execute the methods performed by the terminal device or network device in the various embodiments of this application.

[0307] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0308] This application also provides a computer program. This computer program can be applied to a terminal device or network device provided in this application, and the computer program causes the computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0309] In this application, the terms "system" and "network" are used interchangeably. Furthermore, the terminology used in this application is only for explaining specific embodiments of the application and is not intended to limit the application. The terms "first," "second," "third," and "fourth," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. In addition, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0310] In the embodiments of this application, the term "instruction" can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0311] In the embodiments of this application, the term "correspondence" may indicate a direct or indirect correspondence between two things, or an association between two things, or a relationship such as instruction and being instructed, configuration and being configured.

[0312] In the embodiments of this application, "predefined" or "preconfigured" can be implemented by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device (e.g., including terminal devices and network devices). This application does not limit the specific implementation method. For example, predefined can refer to what is defined in the protocol.

[0313] In the embodiments of this application, the term "protocol" may refer to standard protocols in the field of communications, such as LTE protocols, NR protocols, and related protocols applied in future communication systems. This application does not limit the scope of these protocols.

[0314] In the embodiments of this application, determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information.

[0315] In the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0316] In the embodiments of this application, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0317] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0318] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0319] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0320] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for wireless communication, comprising: include: The first device receives multiple beams transmitted by the second device within the observation window, and the multiple beams are used to determine the first beam set; The first device performs beam prediction on the second beam set within the prediction window based on the measurement values ​​of the first beam set; The first device sends a first report to the second device; The first report is used to determine one or K optimal beams in the second beam set, where K is a positive integer. The first beam set is determined based on first information, which includes at least two of the measurements of the plurality of beams, the capabilities of the first device, and the network configuration.

2. The method of claim 1, wherein, The first report is used to report one of the following information: The report contains beam information for the K optimal beams, including reference signal indicators or predefined beam indices for the K optimal beams. The report describes the beam information and reference signal received power (RSRP) of the K optimal beams. The report includes the beam information of the K optimal beams and the probability information of the K optimal beams predicted by the second beam set; Report the RSRP difference between the measured RSRP of the first beam set and the optimal RSRP of some / all beams in the second beam set; The strongest beam ID is indicated in bitmap form; Report the predicted RSRP for both measurement beam and non-measurement beam; The report includes the predicted RSRP of the unmeasured beam and the measured RSRP of the measured beam. Report the error and error threshold between the predicted RSRP and the actual measured RSRP for each measurement beam.

3. The method according to claim 1 or 2, characterized in that, All beams in the first beam set are one of the following: The N beams with the highest measurement values ​​among the multiple beams, where N is a positive integer and is determined according to the network configuration; The beam whose measured value is greater than a first threshold among the plurality of beams, wherein the first threshold is determined according to the network configuration.

4. The method according to claim 1 or 2, characterized in that, The first beam set includes multiple beam subsets, each beam subset corresponding to multiple thresholds related to the measurement value. The number of beam subsets in the first beam set is determined based on the moving speed and / or coverage of the first device.

5. The method according to any one of claims 1-4, characterized in that, The first beam set is one of a plurality of beam sets, which correspond to multiple beam set patterns related to capabilities, and the multiple beam set patterns are determined according to the network configuration.

6. The method according to any one of claims 1-5, characterized in that, The measurements of the multiple beams include historical measurements of the multiple beams, which are represented by measurement vectors.

7. The method according to any one of claims 1 to 6, characterized in that, The observation window is one of a plurality of observation windows, the positions of which are determined based on the position of the initial observation window and the first period, and the first beam set is used to repeatedly transmit within the plurality of observation windows.

8. The method of claim 7, wherein, The first device is one of a plurality of devices, which perform beam prediction based on a first beam set in any of the plurality of observation windows.

9. The method according to claim 7 or 8, characterized in that, The length of the observation window is configured or adjusted according to one or more of the following methods: The observation window is configured via a third parameter, which is used to define its length. Determined by report offset and resource offset; The length of the observation window can be increased by increasing the reporting period or decreasing the reference signal resource offset; The length of the observation window can be reduced by decreasing the reporting period or increasing the reference signal resource offset; The length of the observation window is predicted based on the number of time instances corresponding to the first beam set.

10. The method according to any one of claims 7-9, characterized in that, The prediction window is one of a plurality of prediction windows, the positions of which are determined based on the position of the initial prediction window and the first period, and the length of the prediction window and the length of the observation window are used to determine the reporting period.

11. The method according to any one of claims 7-9, characterized in that, The prediction window is one of a plurality of prediction windows, and the prediction window is determined based on the position of the initial prediction window and the second period, wherein the length of the second period is less than the length of the first period.

12. The method of any one of claims 1-6, wherein, The position of the observation window is determined according to the trigger command.

13. The method according to any one of claims 1-12, characterized in that, The number of beams in the first report is determined based on one or more of the following information: nrofReportedRS; nrofTopK; Is the first report one of multiple reports in the current reporting cycle? The weight of the first report among the multiple reports in the current reporting cycle; The prediction error of the beam prediction.

14. The method of claim 13, wherein, When the number of beams in the first report is less than the value of nrofReportedRS, the first report is one of the plurality of reports, the number of which is determined based on the value of nrofReportedRS and the number of beams in each report.

15. The method of claim 14, wherein, The multiple reports correspond to multiple transmission priorities. The first weight of the first report is used to determine the transmission priority of the first report. The first weight is determined based on the beam prediction error in the first report.

16. The method of claim 13, wherein, When the network configuration received by the first device includes nrofTopK, the number of beams in the first report is determined by the first device.

17. The method of any one of claims 1-16, wherein, The beam prediction is achieved by a first model, which is an artificial intelligence or machine learning model.

18. The method according to claim 16, wherein the first model is located on the terminal device side, the first device includes a terminal device and a first server for training the first model, and the method further includes: The first device generates or collects training data related to the transmitted beam of the second device; The terminal device sends the training data to the first server.

19. A method for wireless communication, comprising: include: The second device transmits multiple beams within the observation window, and these multiple beams are used to determine the first beam set; The second device receives the first report sent by the first device; The first report is used to determine one or K optimal beams in a second beam set within a prediction window, where K is a positive integer. The beam prediction of the second beam set is based on the measurements of the first beam set, which is determined according to first information, including at least two of the measurements of the plurality of beams, the capabilities of the first device, and the network configuration.

20. The method of claim 19, wherein, The first report is used to report one of the following information: The report contains beam information for the K optimal beams, including reference signal indicators or predefined beam indices for the K optimal beams. The report describes the beam information and reference signal received power (RSRP) of the K optimal beams. The report includes the beam information of the K optimal beams and the probability information of the K optimal beams predicted by the second beam set; Report the RSRP difference between the measured RSRP of the first beam set and the optimal RSRP of some / all beams in the second beam set; The strongest beam ID is indicated in bitmap form; Report the predicted RSRP for both measurement beam and non-measurement beam; The report includes the predicted RSRP of the unmeasured beam and the measured RSRP of the measured beam. Report the error and error threshold between the predicted RSRP and the actual measured RSRP for each measurement beam.

21. The method of claim 19 or 20, wherein, All beams in the first beam set are one of the following: The N beams with the highest measurement values ​​among the multiple beams, where N is a positive integer and is determined according to the network configuration; The beam whose measured value is greater than a first threshold among the plurality of beams, wherein the first threshold is determined according to the network configuration.

22. The method of claim 19 or 20, wherein, The first beam set includes multiple beam subsets, each beam subset corresponding to multiple thresholds related to the measurement value. The number of beam subsets in the first beam set is determined based on the moving speed and / or coverage of the first device.

23. The method of any one of claims 19-22, wherein, The first beam set is one of a plurality of beam sets, which correspond to multiple beam set patterns related to capabilities, and the multiple beam set patterns are determined according to the network configuration.

24. The method of any one of claims 19-23, wherein, The measurements of the multiple beams include historical measurements of the multiple beams, which are represented by measurement vectors.

25. The method of any one of claims 19-24, wherein, The observation window is one of a plurality of observation windows, the positions of which are determined based on the position of the initial observation window and the first period, and the first beam set is used to repeatedly transmit within the plurality of observation windows.

26. The method of claim 25, wherein, The first device is one of a plurality of devices, which perform beam prediction based on a first beam set in any of the plurality of observation windows.

27. The method of claim 25 or 26, wherein, The length of the observation window is configured or adjusted according to one or more of the following methods: The observation window is configured via a third parameter, which is used to define its length. Determined by report offset and resource offset; The length of the observation window can be increased by increasing the reporting period or decreasing the reference signal resource offset; The length of the observation window can be reduced by decreasing the reporting period or increasing the reference signal resource offset; The length of the observation window is predicted based on the number of time instances corresponding to the first beam set.

28. The method of any one of claims 25-27, wherein, The prediction window is one of a plurality of prediction windows, the positions of which are determined based on the position of the initial prediction window and the first period, and the length of the prediction window and the length of the observation window are used to determine the reporting period.

29. The method of any one of claims 25-27, wherein, The prediction window is one of a plurality of prediction windows, and the prediction window is determined based on the position of the initial prediction window and the second period, wherein the length of the second period is less than the length of the first period.

30. The method of any one of claims 19-24, wherein, The position of the observation window is determined according to the trigger command.

31. The method of any one of claims 19-30, wherein, The number of beams in the first report is determined based on one or more of the following information: nrofReportedRS; nrofTopK; Is the first report one of multiple reports in the current reporting cycle? The weight of the first report among the multiple reports in the current reporting cycle; The prediction error of the beam prediction.

32. The method of claim 31, wherein, When the number of beams in the first report is less than the value of nrofReportedRS, the first report is one of the plurality of reports, the number of which is determined based on the value of nrofReportedRS and the number of beams in each report.

33. The method of claim 32, wherein, The multiple reports correspond to multiple transmission priorities. The first weight of the first report is used to determine the transmission priority of the first report. The first weight is determined based on the beam prediction error in the first report.

34. The method of claim 31, wherein, When the network configuration received by the first device includes nrofTopK, the number of beams in the first report is determined by the first device.

35. The method of any one of claims 19-34, wherein, The beam prediction is achieved by a first model, which is an artificial intelligence or machine learning model.

36. The method according to claim 35, wherein the first model is located on the terminal device side, the first device includes the terminal device and a first server for training the first model, and training data related to the transmission beam of the second device is sent by the terminal device to the first server.

37. A device for wireless communication, characterized in that, The device is a first device, the device comprising: A transceiver unit is used to receive multiple beams transmitted by a second device within an observation window, the multiple beams being used to determine a first beam set; The processing unit is configured to perform beam prediction on the second beam set within the prediction window based on the measurement values ​​of the first beam set; The transceiver unit is also used to send a first report to the second device; The first report is used to determine one or K optimal beams in the second beam set, where K is a positive integer. The first beam set is determined based on first information, which includes at least two of the measurements of the plurality of beams, the capabilities of the first device, and the network configuration.

38. The device of claim 37, wherein, The first report is used to report one of the following information: The report contains beam information for the K optimal beams, including reference signal indicators or predefined beam indices for the K optimal beams. The report describes the beam information and reference signal received power (RSRP) of the K optimal beams. The report includes the beam information of the K optimal beams and the probability information of the K optimal beams predicted by the second beam set; Report the RSRP difference between the measured RSRP of the first beam set and the optimal RSRP of some / all beams in the second beam set; The strongest beam ID is indicated in bitmap form; Report the predicted RSRP for both measurement beam and non-measurement beam; The report includes the predicted RSRP of the unmeasured beam and the measured RSRP of the measured beam. Report the error and error threshold between the predicted RSRP and the actual measured RSRP for each measurement beam.

39. The device of claim 37 or 38, wherein, All beams in the first beam set are one of the following: The N beams with the highest measurement values ​​among the multiple beams, where N is a positive integer and is determined according to the network configuration; The beam whose measured value is greater than a first threshold among the plurality of beams, wherein the first threshold is determined according to the network configuration.

40. The device of claim 37 or 38, wherein, The first beam set includes multiple beam subsets, each beam subset corresponding to multiple thresholds related to the measurement value. The number of beam subsets in the first beam set is determined based on the moving speed and / or coverage of the first device.

41. The device of any one of claims 37-40, wherein, The first beam set is one of a plurality of beam sets, which correspond to multiple beam set patterns related to capabilities, and the multiple beam set patterns are determined according to the network configuration.

42. The device of any one of claims 37-41, wherein, The measurements of the multiple beams include historical measurements of the multiple beams, which are represented by measurement vectors.

43. The device of any one of claims 37-42, wherein, The observation window is one of a plurality of observation windows, the positions of which are determined based on the position of the initial observation window and the first period, and the first beam set is used to repeatedly transmit within the plurality of observation windows.

44. The device of claim 43, wherein, The first device is one of a plurality of devices, which perform beam prediction based on a first beam set in any of the plurality of observation windows.

45. The device of claim 43 or 44, wherein, The length of the observation window is configured or adjusted according to one or more of the following methods: The observation window is configured via a third parameter, which is used to define its length. Determined by report offset and resource offset; The length of the observation window can be increased by increasing the reporting period or decreasing the reference signal resource offset; The length of the observation window can be reduced by decreasing the reporting period or increasing the reference signal resource offset; The length of the observation window is predicted based on the number of time instances corresponding to the first beam set.

46. The device of any one of claims 43-45, wherein, The prediction window is one of a plurality of prediction windows, the positions of which are determined based on the position of the initial prediction window and the first period, and the length of the prediction window and the length of the observation window are used to determine the reporting period.

47. The device of any one of claims 43-45, wherein, The prediction window is one of a plurality of prediction windows, and the prediction window is determined based on the position of the initial prediction window and the second period, wherein the length of the second period is less than the length of the first period.

48. The device of any one of claims 37-42, wherein, The position of the observation window is determined according to the trigger command.

49. The device of any of claims 37-48, wherein, The number of beams in the first report is determined based on one or more of the following information: nrofReportedRS; nrofTopK; Is the first report one of multiple reports in the current reporting cycle? The weight of the first report among the multiple reports in the current reporting cycle; The prediction error of the beam prediction.

50. The device of claim 49, wherein, When the number of beams in the first report is less than the value of nrofReportedRS, the first report is one of the plurality of reports, the number of which is determined based on the value of nrofReportedRS and the number of beams in each report.

51. The device of claim 50, wherein, The multiple reports correspond to multiple transmission priorities. The first weight of the first report is used to determine the transmission priority of the first report. The first weight is determined based on the beam prediction error in the first report.

52. The device of claim 49, wherein, When the network configuration received by the first device includes nrofTopK, the number of beams in the first report is determined by the first device.

53. The device of any one of claims 37-52, wherein, The beam prediction is achieved by a first model, which is an artificial intelligence or machine learning model.

54. The apparatus of claim 53, wherein the first model is located on the terminal device side, the first device includes the terminal device and a first server for training the first model, and the processing unit is further configured to generate or collect training data related to the transmission beam of the second device; the terminal device is configured to send the training data to the first server.

55. An apparatus for wireless communication, characterized in that, The device is a second device, and the device includes: A transceiver unit is used to transmit multiple beams within an observation window, the multiple beams being used to determine a first beam set; The transceiver unit is also used to receive a first report sent by the first device; The first report is used to determine one or K optimal beams in a second beam set within a prediction window, where K is a positive integer. The beam prediction of the second beam set is based on the measurements of the first beam set, which is determined according to first information, including at least two of the measurements of the plurality of beams, the capabilities of the first device, and the network configuration.

56. The device of claim 55, wherein, The first report is used to report one of the following information: The report contains beam information for the K optimal beams, including reference signal indicators or predefined beam indices for the K optimal beams. The report describes the beam information and reference signal received power (RSRP) of the K optimal beams. The report includes the beam information of the K optimal beams and the probability information of the K optimal beams predicted by the second beam set; Report the RSRP difference between the measured RSRP of the first beam set and the optimal RSRP of some / all beams in the second beam set; The strongest beam ID is indicated in bitmap form; Report the predicted RSRP for both measurement beam and non-measurement beam; The report includes the predicted RSRP of the unmeasured beam and the measured RSRP of the measured beam. Report the error and error threshold between the predicted RSRP and the actual measured RSRP for each measurement beam.

57. The device of claim 55 or 56, wherein, All beams in the first beam set are one of the following: The N beams with the highest measurement values ​​among the multiple beams, where N is a positive integer and is determined according to the network configuration; The beam whose measured value is greater than a first threshold among the plurality of beams, wherein the first threshold is determined according to the network configuration.

58. The device of claim 55 or 56, wherein, The first beam set includes multiple beam subsets, each beam subset corresponding to multiple thresholds related to the measurement value. The number of beam subsets in the first beam set is determined based on the moving speed and / or coverage of the first device.

59. The device of any one of claims 55-58, wherein, The first beam set is one of a plurality of beam sets, which correspond to multiple beam set patterns related to capabilities, and the multiple beam set patterns are determined according to the network configuration.

60. The device of any one of claims 55-59, wherein, The measurements of the multiple beams include historical measurements of the multiple beams, which are represented by measurement vectors.

61. The apparatus according to any one of claims 55-60, characterized in that, The observation window is one of a plurality of observation windows, the positions of which are determined based on the position of the initial observation window and the first period, and the first beam set is used to repeatedly transmit within the plurality of observation windows.

62. The apparatus according to claim 61, characterized in that, The first device is one of a plurality of devices, which perform beam prediction based on a first beam set in any of the plurality of observation windows.

63. The apparatus according to claim 61 or 62, characterized in that, The length of the observation window is configured or adjusted according to one or more of the following methods: The observation window is configured via a third parameter, which is used to define its length. Determined by report offset and resource offset; The length of the observation window can be increased by increasing the reporting period or decreasing the reference signal resource offset; The length of the observation window can be reduced by decreasing the reporting period or increasing the reference signal resource offset; The length of the observation window is predicted based on the number of time instances corresponding to the first beam set.

64. The apparatus according to any one of claims 61-63, characterized in that, The prediction window is one of a plurality of prediction windows, the positions of which are determined based on the position of the initial prediction window and the first period, and the length of the prediction window and the length of the observation window are used to determine the reporting period.

65. The apparatus according to any one of claims 61-63, characterized in that, The prediction window is one of a plurality of prediction windows, and the prediction window is determined based on the position of the initial prediction window and the second period, wherein the length of the second period is less than the length of the first period.

66. The apparatus according to any one of claims 55-60, characterized in that, The position of the observation window is determined according to the trigger command.

67. The apparatus according to any one of claims 55-66, characterized in that, The number of beams in the first report is determined based on one or more of the following information: nrofReportedRS; nrofTopK; Is the first report one of multiple reports in the current reporting cycle? The weight of the first report among the multiple reports in the current reporting cycle; The prediction error of the beam prediction.

68. The apparatus according to claim 67, characterized in that, When the number of beams in the first report is less than the value of nrofReportedRS, the first report is one of the plurality of reports, the number of which is determined based on the value of nrofReportedRS and the number of beams in each report.

69. The apparatus according to claim 68, characterized in that, The multiple reports correspond to multiple transmission priorities. The first weight of the first report is used to determine the transmission priority of the first report. The first weight is determined based on the beam prediction error in the first report.

70. The apparatus according to claim 67, characterized in that, When the network configuration received by the first device includes nrofTopK, the number of beams in the first report is determined by the first device.

71. The apparatus according to any one of claims 55-70, characterized in that, The beam prediction is achieved by a first model, which is an artificial intelligence or machine learning model.

72. The apparatus according to claim 71, wherein the first model is located on the terminal device side, the first device includes the terminal device and a first server for training the first model, and training data related to the transmission beam of the second device is sent by the terminal device to the first server.

73. A communication device, characterized in that, It includes a memory and a processor, the memory being used to store a program, and the processor being used to invoke the program in the memory to perform the method as described in any one of claims 1-36.

74. An apparatus, characterized in that, Includes a processor for calling a program from memory to perform the method as described in any one of claims 1-36.

75. A chip, characterized in that, Includes a processor for calling a program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1-36.

76. A computer-readable storage medium, characterized in that, It contains a program that causes a computer to perform the method as described in any one of claims 1-36.

77. A computer program product, characterized in that, Includes a program that causes a computer to perform the method as described in any one of claims 1-36.

78. A computer program, characterized in that, The computer program causes the computer to perform the method as described in any one of claims 1-36.

Images