Method and device in node for wireless communication

Abstract

The present application provides a method and device in a node for wireless communication. The method comprises: receiving first information, the first information being used for indicating a plurality of adaptive thresholds, the plurality of adaptive thresholds being used for selecting beam information, and the beam information being used for beam prediction on the basis of a first model. Compared with the traditional beam reporting mechanism on the basis of a first model, a first node can autonomously select, on the basis of first information, thresholds suitable for different channel conditions and user requirements, and report a beam on the basis of the selected thresholds, so that the flexibility and adaptability of the beam reporting mechanism are improved.

Description

Methods and apparatus for nodes used in wireless communication Technical Field

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

[0002] In communication systems, beam management can be performed using first-order models (e.g., artificial intelligence / machine learning (AI / ML) models). However, in traditional first-order model-based beam management processes, the reporting mechanisms of terminal devices lack flexibility and may not be able to adapt to different channel conditions and user needs.

[0003] Summary of the Invention

[0004] This application provides a method and apparatus for use in a node for wireless communication. The various aspects covered by this application are described below.

[0005] In a first aspect, a method is provided for a first node in wireless communication, comprising: receiving first information, the first information indicating a plurality of adaptive thresholds, the plurality of adaptive thresholds being used to select beam information, the beam information being used for beam prediction based on a first model.

[0006] In a second aspect, a method for a second node in wireless communication is provided, comprising: transmitting first information, the first information being used to indicate a plurality of adaptive thresholds, the plurality of adaptive thresholds being used to select beam information, the beam information being used for beam prediction based on a first model.

[0007] Thirdly, a first node for wireless communication is provided, comprising: a first transceiver for receiving first information, the first information being used to indicate a plurality of adaptive thresholds, the plurality of adaptive thresholds being used to select beam information, the beam information being used for beam prediction based on a first model.

[0008] Fourthly, a second node for wireless communication is provided, comprising: a second transceiver for transmitting first information, the first information being used to indicate a plurality of adaptive thresholds, the plurality of adaptive thresholds being used to select beam information, the beam information being used for beam prediction based on a first model.

[0009] Fifthly, a first node for wireless communication is provided, comprising a transceiver, a memory, and a processor, wherein the memory stores a program, the processor invokes the program in the memory, and controls the transceiver to receive or transmit signals to cause the first node to perform the method as described in the first aspect.

[0010] In a sixth aspect, a second node for wireless communication is provided, comprising a transceiver, a memory, and a processor, wherein the memory stores a program, the processor invokes the program in the memory, and controls the transceiver to receive or transmit signals to cause the second node to perform the method as described in the second aspect.

[0011] In a seventh aspect, embodiments of this application provide a communication system including the aforementioned first node and / or second node. In another possible design, the system may further include other devices that interact with the first node or second node as described in the embodiments of this application.

[0012] Eighthly, embodiments of this application provide a computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps in the methods described above.

[0013] Ninthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of the methods described in the foregoing aspects. In some implementations, the computer program product may be a software installation package.

[0014] In a tenth aspect, embodiments of this application provide a chip including a memory and a processor, the processor being able to call and run a computer program from the memory to implement some or all of the steps described in the methods of the foregoing aspects.

[0015] In this embodiment, the first node can receive first information, which can be used to indicate multiple adaptive thresholds for the first node to select beam information. The beam information is used for beam prediction based on a first model. Compared to traditional beam reporting mechanisms based on a first model, the first node can autonomously select thresholds suitable for different channel conditions and user needs based on the first information, and report beam information based on the selected thresholds, which helps improve the flexibility and adaptability of the beam reporting mechanism. Attached Figure Description

[0016] Figure 1 shows the wireless communication system 100 used in an embodiment of this application.

[0017] Figure 2 is a schematic flowchart of the network (NW) side model scenario applicable to the embodiments of this application.

[0018] Figure 3 is an example diagram of the specific workflow of the NW side model scenario.

[0019] Figure 4 is a schematic flowchart of a terminal-side model scenario applicable to the embodiments of this application.

[0020] Figure 5 is a schematic flowchart of a method for a first node in wireless communication provided in an embodiment of this application.

[0021] Figure 6 is an example diagram of a combination of Embodiment 1 and Embodiment 2 of this application.

[0022] Figure 7 is a schematic diagram of the adaptive threshold generation model.

[0023] Figure 8 is an example diagram of a combination of the solutions of Embodiment 1, Embodiment 2 and Embodiment 3 of this application.

[0024] Figure 9 is an example diagram of a combination of the solutions of another embodiment 1, embodiment 2 and embodiment 3 of this application.

[0025] Figure 10 is a schematic diagram of the structure of the first node for wireless communication provided in an embodiment of this application.

[0026] Figure 11 is a schematic diagram of the structure of the second node for wireless communication provided in an embodiment of this application.

[0027] Figure 12 is a schematic structural diagram of the device provided in an embodiment of this application. Detailed Implementation

[0028] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0029] Figure 1 illustrates a wireless communication system 100 according to an embodiment of this application. 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 the terminal device 120 located within that coverage area.

[0030] Figure 1 illustrates an exemplary network device and two terminals. Optionally, the wireless communication system 100 may include multiple network devices, and each network device may include other terminal devices within its coverage area. This application embodiment does not limit this.

[0031] Optionally, the wireless communication system 100 may also include other network entities such as a network controller and a mobility management entity, which is not limited in this embodiment.

[0032] It should be understood that the technical solutions of the embodiments of this application can be applied to various communication systems, such as: 5th generation (5G) systems or new radio (NR), long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, etc. The technical solutions provided in this application can also be applied to future communication systems, such as 6th generation mobile communication systems, satellite communication systems, and so on.

[0033] The terminal device in this application embodiment can 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, wireless communication device, user agent, or user device. The terminal device in this application embodiment 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, vehicle-mounted device, etc. The terminal devices in the embodiments of this application can be mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, self-driving, remote medical surgery, smart grids, transportation safety, smart cities, and smart homes, etc. Optionally, the UE can 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 communicate without relaying communication signals through a base station.

[0034] The network device in this application embodiment can be a device used to communicate with a terminal device. This network device can also be called an access network device or a wireless access network device, such as 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 MeNB, secondary 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), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or a combination thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. Base stations can also be mobile switching centers, devices that perform base station functions in device-to-device (D2D), vehicle-to-everything (V2X), and machine-to-machine (M2M) communications, network-side devices in 6G networks, and devices that perform base station functions in future communication systems. Base stations 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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).

[0039] Beam management

[0040] In modern wireless communication systems, beam management is one of the key technologies for ensuring signal quality and user experience. For example, in 5G NR networks, beam management improves signal coverage and communication performance by optimizing the direction of radio beams. With technological advancements, related protocols (e.g., TR 38.843 in Release 18) and related mobile communication technologies (e.g., evolution and enhancement versions of 5G (5G-Advanced, 5G-A)) have introduced AI / ML model-based beam prediction techniques to further enhance network performance.

[0041] In mobile communication technology, AI / ML model-based beam management, enhanced channel state information (CSI) feedback, and improved positioning accuracy are gradually becoming standards and mainstream. Specifically, a general framework based on AI / ML models controls data collection, model training, function / model specification, model transfer / transfer, model inference operations, function / model selection / activation / deactivation / switching and rollback operations, function / model monitoring, model updates, and terminal device capabilities through lifecycle management (LCM). Regarding beam management, compared to traditional solutions, AI / ML models allow 5G network devices (e.g., gNBs) to more accurately predict and adjust beam direction, optimizing resource utilization and user experience. The 3rd Generation Partnership Project (3GPP) has proposed two AI / ML-based beam management (BM) use cases in relevant protocols (e.g., TR 38.843): BM Use Case 1 (BM-Case 1) and BM Use Case 2 (BM-Case 2).

[0042] BM-Case 1 is a downlink set A beam spatial domain prediction based on beam measurement results in set B. It infers the optimal beam prediction result based on the current measurement results and performs beam management in real time based on the prediction result. BM-Case 2 is a downlink set A beam temporal domain prediction based on historical beam measurement results in set B. It infers the optimal beam prediction result for multiple subsequent time slots based on historical measurement results and performs beam management based on the prediction result corresponding to the current time slot.

[0043] Here, set B corresponds to the input of the AI / ML model, and set A corresponds to the output of the AI / ML model. Furthermore, depending on the deployment location of the AI / ML model, each sub-use case is divided into network (NW) side model scenarios and terminal side model scenarios.

[0044] As an example, for BM-Case 1, set B can be a subset of set A, or it can be different from set A. If set B intersects with set A, then set A can be the entire set or a subset of CSI-reference signal (CSI-RS) resources. If it is the entire set, it corresponds to the initial access phase of beam management; if it is a subset, it corresponds to the beam optimization phase. The physical meaning of beam prediction based on the AI / ML model is to predict the overall space through feature extraction of partial spatial information. If set A and set B do not intersect, then set B is usually the wide beam corresponding to the synchronization signal block / physical broadcast channel block (SS / PBCH block, SSB), while set A is the narrow beam within the wide beam angular domain coverage. The physical meaning of beam prediction based on the AI / ML model is to achieve high-precision prediction through feature extraction of a smaller amount of low-precision spatial information.

[0045] As an example, for BM-Case2, the model input is the measurement results of the latest K (K≥1) measurement instances, and the model output is F (F≥1) prediction results for future time slots. Each measurement instance, except for potentially additional timestamp information, follows the same reporting rules as the BM-Case1 sub-use case. Therefore, in this embodiment, the two sub-use cases BM-Case1 and BM-Case2 are not distinguished; both are applicable to this embodiment.

[0046] NW side model scene

[0047] The embodiments of this application are applicable to the LCM stages of data collection, model inference and performance monitoring in NW side model scenarios. A schematic flowchart of data collection is shown in Figure 2, which includes steps S210 to S240.

[0048] In step S210, the terminal device sends a capability report to the network device.

[0049] Under LCM scheduling, the terminal device submits a capability report. The data collection request phase begins, and the network device will perform LCM operations such as model or function selection based on the capability report.

[0050] In step S220, the network device sends a measurement resource set (RS) and report configuration to the terminal device.

[0051] Under LCM scheduling, the network device collects data for model training. The network device configures CSI-ResourceConfig and CSI-ReportConfig to configure the measurement resource set and terminal device reports. This configuration includes the configuration of the CSI-RS / SSB measurement beam resource set for the current set A, used for beam scanning. It also includes configuration information for reports reported by the terminal devices, such as report trigger type, report settings, measurement object, and report content.

[0052] In step S230, the network device transmits set A and / or set B to the terminal device.

[0053] In the data collection phase of training, set A is used as the measurement set to provide ground truth for AI / ML model training. However, if there is no intersection between set A and set B, set B also needs to be included in the measurement set for measurement to provide input for the model.

[0054] In step S240, the terminal device reports data to the network device.

[0055] The network device performs beam scanning of the current resource set according to its configuration, while the terminal device measures the CSI-RS / SSB signals. The terminal device reports beam-related information according to its reporting configuration, including the physical layer reference signal received power (L1-RSRP) and / or the corresponding resource index. As an example, the specific workflow of the NW-side model scenario is shown in Figure 3. The network device collects sufficient data for model training. When the model converges and the prediction performance meets the requirements, it enters the model inference phase. At this time, the network device can use set B as the measurement set for CSI resource and reporting configuration. The network device scans the beams in set B according to the resource configuration. The terminal device measures the current resource set and reports the measurement results to the network device. The NW-side model uses the measurement results fed back by the terminal device as input to the AI / ML model, and the trained model performs inference based on the input. The model outputs the predicted values ​​for the beams in set A, such as the L1-RSRP prediction values ​​of each beam or the prediction probability of each beam as a Top-K beam. The network device performs beam management based on the prediction results. Simultaneously, during the inference phase, LCM periodically initiates model performance monitoring, configures the predicted Top-K beams as the measurement set, and performs beam scanning. Terminal devices measure and report the results; the network device receives the measurement results, calculates performance metrics, and adjusts the LCM operations accordingly.

[0056] Terminal-side model scenario

[0057] The embodiments of this application are applicable to the LCM stage of data collection, model inference and performance monitoring in terminal-side model scenarios. The data collection process is shown in Figure 4, which includes steps S410 to S440.

[0058] In step S410, the terminal device sends a capability report to the network device.

[0059] In step S420, the data collection process is triggered or initialized due to the capability report sent by the terminal device.

[0060] In step S430, the network device performs the corresponding resource set and report configuration (e.g., data collection identity identifier (ID)) and sends it to the terminal device.

[0061] In step S440, the network device performs beam scanning according to the configuration of the resource set, the terminal device performs beam measurement, and uses the measurement results as training data for training the AI / ML model on the terminal device side.

[0062] As an example, when set B is a subset of set A, the network device needs to scan all beams in set A. The terminal device inputs the L1-RSRP measurement values ​​corresponding to set B from the measurement results into the model and uses all measurement results as ground truth to train the model parameters. When set B is not a subset of set A, the network device needs to scan beams in set B in addition to set A to provide ground truth for the model.

[0063] After model training is complete, the model inference phase begins. Network devices scan beam set B, and terminal devices perform measurements. The measurement results are input into the AI / ML model. Through model inference, the L1-RSRP prediction value / Top-K beam prediction probability and / or confidence level corresponding to beam set A can be obtained. The terminal device will, according to its report configuration, provide Top-K beam-related information, which may include the beam index corresponding to the Top-K beam, the L1-RSRP prediction value / measured value, the beam prediction probability, and the confidence level of the beam prediction result.

[0064] During model inference, performance monitoring is integrated to monitor the model's prediction accuracy in real time. Relevant protocols (e.g., TR 38.843) offer two types of performance monitoring: Type 1 and Type 2. In Type 1, network devices directly configure performance monitoring resources and reports. Terminal devices can report beam-related information used for calculating performance metrics on the network device side; they can also independently calculate metrics and report metrics or events to assist in performance monitoring. Type 2, on the other hand, involves performance monitoring actively triggered by the terminal device. Based on the performance monitoring results, LCM performs corresponding operations for model maintenance.

[0065] Employing AI / ML models for beam management requires a large amount of high-quality data as training samples, which potentially impacts the current CSI framework. In relevant 3GPP meetings (e.g., Radio Access Network (RAN) Working Group #116, #116 Part 2 (bis), and #117 meetings), there have been numerous discussions about embedding AI / ML beam prediction models from the traditional CSI framework, including maintaining and modifying CSI resources, report configurations, and report formats. Current large-scale network equipment arrays can provide abundant CSI resources, meaning a vast number of usable beams. This directly leads to a massive data sample volume required for AI / ML models during data collection and model training, necessitating extensive signaling interaction between network equipment and terminal equipment. In the current CSI framework, the maximum number of beam-related information items per report is four; the corresponding beam report format is shown in Table 1. Table 1 contains tables from relevant protocols (e.g., Table 6.3.1.1.2-8 in protocol TR 38.212), which contain the mapping order of CSI fields in reports reported by CSI-RS resource indicator (CSI-RS resource indicator, CRI / ) reference signal received power (RSRP) or SSB resource indicator (SSBRI) / RSRP or CRI / capability index or SSBRI / RSRP / capability index, or the mapping order of CSI fields in reports reported by SSBRI / RSRP in inter-cell communication. It should be noted that the contents of the relevant tables in Table 1 (e.g., Table 6.3.1.1.2-8 in protocol TR 38.212) represent the CRI / SSBRI / RSRP code stream length. The extensive signaling interactions between network devices and terminal devices will undoubtedly challenge the load on the uplink control link. Taking a configuration of 256 beams in set A as an example, during the training phase of the NW-side model, if feedback of all measurement results is required, at least 64 reports need to be submitted, given the current CSI framework's maximum reportable beam count. Simultaneously, during the performance monitoring phase of the terminal-side model, the terminal device also needs to report a large amount of beam-related information. Therefore, subsequent versions of the communication protocol will undoubtedly need to adjust the content, quantity, signaling, and reporting mechanism of the reported beam information.

[0066] Table 1

[0067] In addition, not all data samples have a positive effect on model training. When the terminal device is static, the channel coherence time is large, and a large amount of duplicate data will inevitably occur during multiple beam scans. The reporting of this data not only occupies a large amount of uplink load, but also does not significantly improve model performance. Conversely, when the link quality undergoes drastic changes, the measurement results are of poor quality and have a negative impact on the model. Related meetings also discussed the screening and deletion of measurement results on the terminal device side, aiming to ensure the efficiency of beam management and the robustness of AI / ML prediction models. Currently, there is no consensus on the reporting mechanism of the data collection phase of the BM-Case1NW model, i.e., no agreement has been formed in the meeting minutes (Chairnotes). However, in the proposals in the FL summary of the subsequent meeting, all companies agreed on the proposal that "the terminal device reports the relevant information of the top-M beams of the current test set signal strength," where how M is specified still needs further research; all companies also agreed on the proposal that "the terminal device reports the relevant information of the beam whose L1-RSRP differs from the best beam by X dB," but further research is needed. At the same time, not only for the BM-Case1NW side model, but also for the BM-Case2 and terminal side models, the CSI reporting framework needs to be improved to meet the large amount of data reporting requirements at different stages of LCM.

[0068] As mentioned above, beam management in communication systems can utilize first-order models (e.g., AI / ML models). However, in traditional first-order model-based beam management processes, the reporting mechanism of terminal devices lacks flexibility and may not be able to adapt to different channel conditions and user needs.

[0069] Taking BM-Case1 and BM-Case2 as examples above, the first model is an AI / ML model. Related conferences (e.g., Rel-19RAN1#117) discussed the report content reported by the terminal device during the inference phase. For a single time slot in BM-Case1 and BM-Case2, the beam report content for a single layer 1 (L1) signaling should support the L1-RSRP and corresponding beam information of the Top-M beam in a single resource set, and support two options:

[0070] Option 1: Top-M beams are the M beams with the largest L1-RSRP measurements, where M is specified by the access network equipment (e.g., gNB).

[0071] Option 2: Up to M beams within X dB of the strongest L1-RSRP measurement, where X and M are specified by the access network equipment.

[0072] Option 1 can be understood as the best beam in a fixed feedback M (M≤4) measurement set, while Option 2 is a measurement beam reporting mechanism based on the L1-RSRP differential threshold (X dB in the above text).

[0073] The aforementioned reporting mechanisms based on a single beam count or a single L1-RSRP differential threshold have several problems. Both schemes report the same number of beams or beams meeting the same differential threshold conditions regardless of channel conditions. While simple, they lack flexibility and cannot adapt to different channel conditions and user needs. For example, in poor channel conditions, where L1-RSRPs of different beams are low and the differences are small, reporting a single beam count will result in the loss of significant channel spatial information, leading to a decline in prediction performance. Conversely, a single differential threshold may cause a surge in the number of reported beams, wasting substantial uplink control information (IoT) resources or uplink signaling overhead. Besides resource waste, AI / ML model beam prediction in 5G-A has high latency requirements, necessitating timely training, inference, and monitoring. Using a single differential threshold may result in excessive CSI signaling backhaul, slow model response, and impact on overall system performance. Furthermore, in many Internet of Things (IoT) scenarios, energy consumption control of terminal devices needs to be considered, and the low flexibility of single beam count and single differential threshold schemes may lead to low energy efficiency in terminal devices.

[0074] To address the aforementioned issues, embodiments of this application provide a method for a node in wireless communication. In this method, a first node can receive first information, which can be used to indicate multiple adaptive thresholds for the first node to select beam information. The beam information is used for beam prediction based on a first model. Compared to traditional beam reporting mechanisms based on a first model, the first node can autonomously select thresholds suitable for different channel conditions and user needs based on the first information, and report beam information based on the selected thresholds, thus improving the flexibility and adaptability of the beam reporting mechanism.

[0075] On the other hand, the adaptive threshold used for beam information reporting can be autonomously selected by the first node (for example, the first node actively selects the adaptive threshold based on the statistical set of historical beam measurement results), thereby ensuring that the adaptive threshold used for current reporting meets the requirements of the scenario and channel environment, which helps to reduce unnecessary beam information reporting, thereby reducing system overhead and improving system performance.

[0076] The method for wireless communication in a first node according to an embodiment of this application is described below with reference to Figure 5. Figure 5 is a schematic flowchart of the method for wireless communication in a first node according to an embodiment of this application. As shown in Figure 5, the method is executed by the first node.

[0077] As an example, the first node can be a network-controlled repeater (NCR).

[0078] As an example, the first node can be a terminal device. For example, the terminal device 120 shown in Figure 1.

[0079] As an example, the first node can be a relay, such as a relay terminal.

[0080] The method shown in Figure 5 includes step S510, which will be described below.

[0081] In step S510, the first node receives the first information. For example, the first node may receive the first information sent by the second node.

[0082] As one example, the second node can be a network device. For instance, the second node can be an access network device. Another example is a gNB.

[0083] In some embodiments, the first information is used to indicate multiple adaptive thresholds, which are used to select beam information, and the beam information is used for beam prediction based on the first model. Accordingly, upon receiving the first information, the first node can select beam information based on the multiple adaptive thresholds. For example, the first node can proactively select an adaptive threshold from the multiple adaptive thresholds based on its current environment and scenario, combined with its capabilities and beam measurement results, and report beam information based on that threshold.

[0084] As one embodiment, the first information is used to indicate multiple adaptive thresholds, which can be understood as indicating at least two adaptive thresholds. For example, the first node is a terminal device, the second node is an access network device, and the access network device generates at least two adaptive thresholds [Th1, Th2, ...] according to the access network device manufacturer or network operator's policy, and sends them to the terminal device through the first information.

[0085] In the embodiments of this application, the adaptive threshold is not limited. For example, the adaptive threshold can be used to indicate the threshold corresponding to the L1-RSRP measurement or prediction value, the confidence level of the measurement or prediction result, the measurement or prediction probability, etc.

[0086] As one example, the adaptive threshold is an absolute threshold. For example, the adaptive threshold is an absolute threshold for the L1-RSRP measurement value, the confidence level of the measurement result, or the measurement probability. Another example is that the adaptive threshold is an absolute threshold for the L1-RSRP measurement value. If the adaptive threshold is used as a threshold for beam reporting, it indicates that beam information corresponding to L1-RSRP measurement values ​​higher than this threshold will be reported.

[0087] As one example, the adaptive threshold is a differential threshold. For example, the adaptive threshold is a differential threshold for the predicted value of L1-RSRP, the confidence level of the prediction result, or the prediction probability. Another example is that the adaptive threshold is a differential threshold for the predicted value of L1-RSRP. If the adaptive threshold is used as the threshold for beam reporting, the absolute threshold is obtained by subtracting the predicted value of the strongest L1-RSRP in the current measurement set from the adaptive threshold. Then, the beam information corresponding to the measured values ​​of L1-RSRPs higher than this absolute threshold will be reported.

[0088] In the embodiments of this application, the first model is not limited. For example, the first model can be an AI / ML model.

[0089] As an example, AI models can include deep learning models. Examples include deep neural networks (DNN), convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory networks (LSTM), generative adversarial networks (GAN), variational autoencoders (VAE), transformers, etc.

[0090] As an example, the ML model may include a model generated through machine learning or by the device itself. For example, deep reinforcement learning (DRL).

[0091] In this application, the deployment method of the first model is not limited. In some embodiments, the first model is deployed on the first node side. For example, taking the first model as an AI / ML model and the first node as a terminal device, see the terminal-side model scenario above, where the first model is deployed on the terminal device side. In other embodiments, the first model is deployed on the second node side. For example, taking the first model as an AI / ML model and the second node as a network device, see the NW-side model scenario above, where the first model is deployed on the network device side.

[0092] As one embodiment, the first information can also be used to indicate an upper limit on the number of beams, that is, the maximum number of beams reported by the first node. For example, the first information indicates an upper limit N for the number of beams, where N is a positive integer greater than or equal to 1.

[0093] As one example, multiple adaptive thresholds are used to select beam information. This can be understood as the beam information being determined based on multiple adaptive thresholds. For example, the adaptive thresholds are absolute thresholds of L1-RSRP. The first node determines the relevant beam information of the beam corresponding to the L1-RSRP measurement values ​​of one or more beams based on multiple absolute thresholds of L1-RSRP.

[0094] As a sub-implementation of the above embodiments, beam information may be beam measurement values ​​and / or corresponding beam indices. For example, beam information may be the L1-RSRP measurement value of a beam and its corresponding beam index. Another example is the beam index corresponding to the L1-RSRP measurement value of a beam.

[0095] As a sub-implementation of the above embodiments, beam information may be beam prediction values ​​and / or corresponding beam indices. For example, beam information may be the L1-RSRP prediction value of a beam and its corresponding beam index. Another example is the beam index corresponding to the L1-RSRP prediction value of a beam.

[0096] As an example, beam information is used for beam prediction based on the first model. This can be understood as the beam information being the output of the beam prediction process based on the first model. For instance, taking an AI / ML model as the first model, a terminal device as the first node, and a network device as the second node, refer to the terminal-side model above. The first model is deployed on the terminal device side, and the output of the first model is the L1-RSRP prediction value of the beam. Based on multiple adaptive thresholds, a portion of the L1-RSRP prediction values ​​of the beams are selected from the L1-RSRP prediction values, and their corresponding beam information is used as the final output of the beam prediction process based on the first model. This helps to reduce the number of reported beams.

[0097] As an example, beam information is used for beam prediction based on the first model. This can be understood as beam information serving as input to the beam prediction process based on the first model. For instance, taking an AI / ML model as the first model, a terminal device as the first node, and a network device as the second node, referencing the NW-side model above, the first model is deployed on the network device side. In this case, the beam information can be the L1-RSRP measurement value of the beam determined by the terminal device based on multiple adaptive thresholds. The terminal device reports the determined L1-RSRP measurement value of the beam to the network device, which uses the L1-RSRP measurement value of the beam as input to the first model and performs beam prediction, i.e., determines the predicted L1-RSRP value of the beam.

[0098] As an example, the first information can be carried in a radio resource control (RRC) message. For instance, the first information can be carried in RRC messages such as RRC connection establish, RRC reconfiguration, RRC connection re-establishment, RRC connection release, and RRC connection resume. Specifically, it can be carried in information elements (IEs) such as measConfig, BeamFailureRecoveryConfig, CSI-MeasConfig, and CSI-ReportConfig of the relevant RRC messages.

[0099] As a sub-implementation of the above embodiments, a first field can be added to the IE carrying the first information. This first field indicates whether the distribution of a single threshold (i.e., the traditional approach) or multiple adaptive thresholds (i.e., the first information) is supported. For example, the first field could be a `thresholds` field. In the high-level parameter `reportQuantity` of the CSI-ReportConfig IE in RRC Reconfiguration, a `thresholds` field can be added to add an array corresponding to multiple adaptive thresholds. Furthermore, a `maxQuantity` parameter can be added to change the upper limit of the number of beams.

[0100] In some embodiments, multiple adaptive thresholds are used to select beam information. This can be understood as determining a first threshold based on multiple adaptive thresholds, and the first threshold is used to determine the beam information. For example, the first node is a terminal device. During or after the current resource set measurement, the terminal device selects a first threshold from multiple adaptive thresholds indicated by the first information. After selecting the first threshold, the terminal device can determine the aforementioned beam information in the report submitted to the network device based on the first threshold. The following describes a scheme for determining the first threshold based on multiple adaptive thresholds through Embodiment 1.

[0101] Example 1: Determine the first threshold based on multiple adaptive thresholds.

[0102] Implementation method 1-1: Based on multiple adaptive thresholds, the first threshold is determined using a second model.

[0103] In some embodiments, determining the first threshold based on multiple adaptive thresholds can be understood as using a second model to determine the first threshold, where the multiple adaptive thresholds are the inputs of the second model and the first threshold is the output of the second model.

[0104] It should be noted that the second model can be the same model as the first model mentioned above, or it can be a different model. The description of the first model mentioned above also applies to the second model, and will not be repeated here.

[0105] As an example, the second model is deployed on the first node side.

[0106] As a sub-implementation of the above embodiments, the second model is the same as the first model. That is, the first model can be used for both beam prediction and determining the first threshold. For example, the first node is a terminal device, and the first model may include a first threshold generation model and a beam prediction model. In other words, the first model can be used for both beam prediction and determining the first threshold. The terminal device takes multiple adaptive thresholds indicated by the received first information, the terminal device's capabilities (such as the current LCM stage and the currently specified function), the measurement results of the current measurement resource set, the current beam prediction results, the terminal device's mobility, uplink (UL) resource allocation, and beam prediction performance indicators as inputs through the first model, and the first threshold as the output. The training phase of the first threshold generation model will be carried out simultaneously with the training phase of the beam prediction model. During this process, the first threshold generation model will extract the features of the comprehensive optimal first threshold until convergence. Its inference phase will perform model inference at the end of each measurement resource set measurement and generate a first threshold that fits the current scenario, which will be applied to determine the beam information in the beam report.

[0107] As an example, the performance index of the second model is determined based on the type of the second model. The performance index of the second model is used to comprehensively evaluate the suitability of the first threshold for beam management, and the second model can be adjusted based on the performance index.

[0108] As a sub-example of the above embodiments, the type of the second model may include a regression model or a classification model.

[0109] As a sub-example of the above embodiment, the second model is a regression model, and the performance index of the second model can be one or more of the following: mean square error, root mean square error, mean absolute error, and coefficient of determination.

[0110] As a sub-example of the above embodiments, the second model is a classification model, and the performance metrics of the second model can be one or more of the following: accuracy, recall, F1 score, and area under the curve-receiver operating characteristic (AUC-ROC).

[0111] It should be noted that the specific definition of the performance metrics for the second model depends on the specific application.

[0112] As an example, the second model is the same as the first model, and its performance metric can be the weighted accuracy-resource efficiency ratio (WARER). For instance, if the first and second models are the same model, the first model includes a first threshold generation model and a beam prediction model. Since Top-K beam prediction accuracy (Acc) and other performance metrics are generated during the beam prediction model performance monitoring phase, we will use Acc as an example here and define the weighted accuracy-resource efficiency ratio. The weighted accuracy-resource efficiency ratio can be expressed by the formula... Confirmed. Here, α is the accuracy weight, reflecting the priority of prediction accuracy; it is recommended to set it to a high value to ensure that the model's prediction accuracy dominates the metrics. β is the resource overhead weight, reflecting the importance of uplink resource utilization; if resources are very limited, it is recommended to increase this weight. γ is the latency weight, reflecting the impact of latency on terminal device performance and user experience; for latency-sensitive applications, this weight should be high. ULRO is UL resource overhead, i.e., the uplink resources (such as UCI) used during reporting. ULRA is UL resource allocation, referring to the total amount of uplink resources allocated for reporting. D is the delay time from measurement completion to threshold generation and reporting. TRTL is the time length for the model to calculate and generate the threshold (threshold predicting time length).

[0113] Implementation method 2-1: Determine the first threshold based on multiple adaptive thresholds and / or historical data.

[0114] As an example, determining the first threshold based on multiple adaptive thresholds and historical data can be referred to as "hard decision with memory".

[0115] In some embodiments, historical data is used to indicate one or more of the following: a set of statistics of historical beam measurement results; a set of first thresholds corresponding to historical beam measurements; the update frequency of first information; and the trend of change of the first threshold.

[0116] As an example, the beam measurement result can be the measurement result of a first reference signal. For example, the beam measurement result can be L1-RSRP, reference signal received quality (RSRQ), received signal strength indication (RSSI), signal interference noise ratio (SINR), etc.

[0117] As a sub-implementation of the above embodiments, the first reference signal may be CSI-RS.

[0118] As a sub-implementation of the above embodiments, the first reference signal may be SSB.

[0119] As a sub-implementation of the above embodiments, the first reference signal is configured by the CSI-ResourceConfig IE on the network device side.

[0120] As a sub-example of the above embodiments, the statistics of the beam measurement results can be the first-order mean, second-order variance, etc. of the beam measurement results. For example, the beam measurement results are L1-RSRP, and the statistics of the beam measurement results are the second-order variance of the L1-RSRP of M beams in the measurement set.

[0121] In some embodiments, determining a first threshold based on multiple adaptive thresholds and / or historical data can be understood as determining the first threshold corresponding to the i-th round of beam measurement based on multiple adaptive thresholds and / or historical data.

[0122] As an example, the first threshold corresponding to the i-th round of beam measurement can be understood as a first threshold determined based on multiple adaptive thresholds and / or historical data during the i-th round of beam measurement. In other words, the first threshold corresponding to the i-th round of beam measurement can be used to select the beam information mentioned above from the results of the i-th round of beam measurement.

[0123] As an example, the set of statistics for historical beam measurement results can be understood as the set of statistics for historical beam measurement results cached by the first node. For example, the first node is a terminal device, the available cache depth of the terminal device is C, and the terminal device can store the set of statistics for beam measurement results at C time points. In other words, the terminal device can store a set of statistics of C-beam measurement results. The cached data on the terminal device is first-in, first-out (FIFO).

[0124] As a sub-implementation of the above embodiment, if the round i of beam measurement is less than or equal to the buffer depth of the first node, the statistical set of historical beam measurement results includes the statistical set of beam measurement results from the previous i-1 rounds. For example, the first node is a terminal device, the available buffer depth of the terminal device is C, and the terminal device can store the statistical set of beam measurement results from C rounds. When i ≤ C, the set of statistics for historical beam measurement results is: S i-1 This is a statistical measure of the beam measurement results in the (i-1)th round.

[0125] As a sub-implementation of the above embodiment, if the round i of beam measurement is greater than the buffer depth of the first node, the statistical set of historical beam measurement results includes the statistical set of beam measurement results from round i-C to round i-1. For example, the first node is a terminal device, the available buffer depth of the terminal device is C, and the terminal device can store the statistical set of beam measurement results from round C. When i>C, the set of statistics for historical beam measurement results is: Si ―1 This is a statistical measure of the beam measurement results in the (i-1)th round.

[0126] As an example, the first threshold set corresponding to historical beam measurements can be understood as the first threshold set corresponding to historical beam measurements cached by the first node. For example, the first node is a terminal device, the available cache depth of the terminal device is C, and the terminal device can store the first threshold set corresponding to beam measurements at C time points. In other words, the terminal device can store the first threshold set corresponding to the C-round beam measurement. Cached data is first-in, first-out (FIFO).

[0127] As a sub-implementation of the above embodiment, if the round i of beam measurement is less than or equal to the buffer depth of the first node, the first threshold set corresponding to the historical beam measurements includes the first threshold set corresponding to the beam measurements of the previous i-1 rounds. For example, the first node is a terminal device, the available buffer depth of the terminal device is C, and the terminal device can store the first threshold set corresponding to C beam measurements. When i ≤ C, the first threshold set corresponding to historical beam measurements is: Th i―1 The first threshold corresponding to the (i-1)th round of beam measurement.

[0128] As a sub-implementation of the above embodiment, if the number of beam measurement rounds i is greater than the statistical set of beam measurement results, the first threshold set corresponding to historical beam measurements includes the first threshold sets corresponding to beam measurements from round i-C to round i-1. For example, the first node is a terminal device, the available cache depth of the terminal device is C, and the terminal device can store the first threshold sets corresponding to rounds C of beam measurements. When i>C, the first threshold set corresponding to historical beam measurements Th i―1 The first threshold corresponding to the (i-1)th round of beam measurement.

[0129] As an example, the update frequency of the first information can be understood as the update frequency of the historical first information. For example, the time interval between the reception times of the two most recent first information messages is compared with a time threshold. If the time interval is greater than the time threshold, the update frequency of the first information is high; if it is less than the time threshold, the update frequency of the first information is low.

[0130] As an example, the changing trend of the first threshold can be understood as the changing trend of the first threshold corresponding to historical beam measurements. For example, the set of first thresholds corresponding to historical beam measurements is... When determining the first threshold corresponding to the i-th round of beam measurement, the trend of the change of the first threshold corresponding to the two adjacent rounds of beam measurement is judged, that is, the first threshold Th corresponding to the (i-1)-th round of beam measurement. i―1 The value of is compared to the first threshold Thi corresponding to the i-2th round of beam measurement. ―2 The value of is either increased or decreased.

[0131] In some embodiments, the first threshold corresponding to the first round of beam measurement is an adaptive threshold among multiple adaptive thresholds that can filter out more beams. For example, the multiple adaptive thresholds include -102dBm and -106dBm. The first threshold corresponding to the first round of beam measurement can be the lower -106dBm to filter out more beams. In this case, Th1 = -106dBm. The first node can cache the statistics S1 and Th1 of the measurement results corresponding to the first round of beam measurement. Then the cached data of the first node is... and

[0132] As an example, the first round of beam measurement can be understood as the initial round of beam measurement. For instance, the first model is deployed on the second node side, the LCM of the first model is initialized, the first node and the second node enter the data collection phase, the second node collects a large amount of data for the model training of the first model, and the first round of beam measurement provides the first set of data for the model training phase.

[0133] In some embodiments, if the absolute value of the difference between the statistic of the i-th round beam measurement result and the weighted sum of the set of statistics of the historical beam measurement results is less than or equal to the second threshold, then the first threshold corresponding to the i-th round beam measurement is the adaptive threshold of the set of weighted sums of the first thresholds corresponding to the historical beam measurements among a plurality of adaptive thresholds.

[0134] As an example, the second threshold may be preset by the terminal equipment manufacturer or network operator.

[0135] As an example, the weighted sum of the statistical set of historical beam measurement results can be the product of the vector corresponding to the preset memory factor and the transpose of the vector corresponding to the statistical set of historical beam measurement results; the weighted sum of the first threshold set corresponding to historical beam measurements can be the product of the vector corresponding to the preset memory factor and the transpose of the vector corresponding to the first threshold set of historical beam measurements. For example, the statistical measure of the i-th round of beam measurement results is S. i The statistical set of historical beam measurement results is The first threshold set corresponding to historical beam measurements is The second threshold is δ, and the preset memory factor is... and The weighted sum of the statistical set of historical beam measurement results can be expressed as: and The product of these terms, and the weighted sum of the first threshold set corresponding to historical beam measurements, is: and The product of . Therefore, when At that time, the first threshold corresponding to the i-th round of beam measurement is the closest among multiple adaptive thresholds. Adaptive threshold.

[0136] As a sub-example of the above embodiments, the preset memory factor can be set by the terminal device manufacturer or network operator. The influence of historical data at different times on the first threshold judgment can be controlled by adjusting the preset memory factor.

[0137] In some embodiments, if the absolute value of the difference between the statistic of the i-th round beam measurement result and the weighted sum of the statistic sets of historical beam measurement results is greater than a second threshold, then the first threshold corresponding to the i-th round beam measurement is determined based on the update frequency of the first information and / or the changing trend of the first threshold. For example, the statistic of the i-th round beam measurement result is S. i The statistical set of historical beam measurement results is The first threshold set corresponding to historical beam measurements is The second threshold is δ, and the preset factor is... and The weighted sum of the statistical set of historical beam measurement results can be expressed as: and The product of these terms, and the weighted sum of the first threshold set corresponding to historical beam measurements, is: and The product of . Therefore, when At that time, the first threshold corresponding to the i-th round of beam measurement is determined based on the update frequency of the first information and / or the changing trend of the first threshold.

[0138] In some embodiments, determining the first threshold corresponding to the i-th round of beam measurement based on the update frequency of the first information can be understood as follows: if the time interval between the reception time of the first information and the reception time of the previous first information is less than a first threshold, then the first threshold corresponding to the i-th round of beam measurement is an adaptive threshold among multiple adaptive thresholds that can filter out fewer beams. For example, the first threshold is T. up The first node records the reception time of the first message, and the time interval between the reception time of the most recent first message and the reception time of the previous first message is ΔT. up ,like And ΔT up <T up This indicates that the channel changes significantly at this time, and the quality of the current i-th round beam measurement result is poor. The first threshold corresponding to the i-th round beam measurement is the adaptive threshold that can filter out fewer beams from multiple adaptive thresholds.

[0139] As an example, the first threshold may be pre-set by the terminal equipment manufacturer or network operator to determine the degree of channel change.

[0140] In some embodiments, the first threshold corresponding to the i-th round of beam measurement is determined based on the changing trend of the first threshold and the update frequency of the first information. This can be understood as follows: if the time interval between the reception time of the first information and the reception time of the previous first information is greater than or equal to a first threshold, the first threshold corresponding to the i-th round of beam measurement is determined based on the changing trend of the first threshold. For example, the first threshold is T. up The first node records the reception time of the first message, and the time interval between the reception time of the most recent first message and the reception time of the previous first message is ΔT. up ,like And ΔT up ≥T up The first threshold corresponding to the i-th round of beam measurement is determined based on the changing trend of the first threshold.

[0141] In some embodiments, determining the first threshold corresponding to the i-th round of beam measurement based on the changing trend of the first threshold can be understood as follows: if the first threshold corresponding to the (i-1)-th round of beam measurement is greater than or equal to the first threshold corresponding to the (i-2)-th round of beam measurement, then the first threshold corresponding to the i-th round of beam measurement is an adaptive threshold among multiple adaptive thresholds that is greater than the first threshold corresponding to the (i-1)-th round of beam measurement. For example, the first threshold corresponding to the (i-1)-th round of beam measurement is Th. i―1 The first threshold corresponding to the i-2th round of beam measurement is Th i―2 If Th i―1 ≥Th i―2 That is, Th i―1 ―Th i―2 For a positive value, the first threshold corresponding to the i-th round of beam measurement is greater than Th among multiple adaptive thresholds. i―1 Adaptive threshold.

[0142] In some embodiments, determining the first threshold corresponding to the i-th round of beam measurement based on the changing trend of the first threshold can be understood as follows: if the first threshold corresponding to the (i-1)-th round of beam measurement is less than the first threshold corresponding to the (i-2)-th round of beam measurement, then the first threshold corresponding to the i-th round of beam measurement is an adaptive threshold among multiple adaptive thresholds that is less than the first threshold corresponding to the (i-1)-th round of beam measurement. For example, the first threshold corresponding to the (i-1)-th round of beam measurement is Th. i―1 The first threshold corresponding to the i-2th round of beam measurement is Th i―2 If Th i―1 <Th i―2 That is, Th i―1 ―Th i―2 If the value is negative, the first threshold corresponding to the i-th round of beam measurement is less than Th among multiple adaptive thresholds. i―1 Adaptive threshold.

[0143] In some embodiments, when determining the first threshold corresponding to the i-th round of beam measurement based on the changing trend of the first threshold, when i=2, since only the threshold corresponding to the first round of beam measurement is cached, the adaptive threshold that can filter out fewer beams among multiple adaptive thresholds is selected as the first threshold corresponding to the second round of beam measurement.

[0144] Implementation methods 1-3: Determine the first threshold based on multiple adaptive thresholds and the first event.

[0145] In some embodiments, the first event includes existing event types.

[0146] As an example, the first event is an event related to the signal quality of the neighboring cell.

[0147] As an example, the first event includes one or more of the following: event A1; event A2; event I2; condition-based event T1 (CondEvent T1).

[0148] As an example, the first event includes event A1, that is, the first event includes the serving cell signal quality of the first node being higher than a specified threshold.

[0149] As an example, the first event includes event A2, that is, the first event includes the first node's serving cell signal quality being lower than a specified threshold.

[0150] As an example, the first event includes event I2, that is, the first event includes interference in the serving cell of the first node exceeding a specified threshold.

[0151] As an example, the first event includes a condition-based event T1, that is, the first event includes the measurement time of the serving cell of the first node within a specified threshold duration.

[0152] In other embodiments, the first event includes a newly defined event type.

[0153] As an example, the newly defined event type can be channel degradation event R1. The triggering strategy of channel degradation event R1 is that the difference between two adjacent channel quality measurements of the first node is lower than a specified threshold. That is to say, the first event includes the difference between two adjacent channel quality measurements of the first node being lower than a specified threshold.

[0154] In some embodiments, the first threshold is determined based on a plurality of adaptive thresholds and a first event. This can be understood as determining the first threshold based on one or more of the following: a plurality of adaptive thresholds; a hysteresis parameter of the first event; an event threshold of the first event; a measurement result of the serving cell of the first node; or a measurement result of the channel quality of the first node.

[0155] Since the stopping or triggering of the first event can be determined based on one or more of the first event hysteresis parameters, the event threshold of the first event, the measurement results of the serving cell of the first node, and the measurement results of the channel quality of the first node, the above embodiments can also be understood as selecting the first threshold from multiple adaptive thresholds based on the triggering and / or stopping of the first event.

[0156] As an example, the delay parameter and the event threshold of the first event can be sent to the first node via a reportConfigNR IE or an IE containing the reportConfigNR field.

[0157] As an example, the measurement result of the serving cell of the first node can be the L1-RSRP / RSRQ / SINR of the serving cell of the first node.

[0158] As an example, the measurement result of the channel quality of the first node can be the L1-RSRP / RSRQ / SINR of the channel where the first node is located.

[0159] As an example, the first event includes event A1. If event A1 is triggered, that is, the difference between the measurement result of the serving cell of the first node and the hysteresis parameter of event A1 is greater than the event threshold of event A1, the first threshold is the adaptive threshold among multiple adaptive thresholds that can filter out more beams. For example, the measurement result of the serving cell of the first node is Ms, the hysteresis parameter of event A1 is Hys1, and the event threshold of event A1 is Thresh1. If Ms - Hys1 > Thresh1, that is, event A1 is triggered, it means that the current link channel quality is good, and the first node can select the adaptive threshold that can filter out more beams from multiple adaptive thresholds as the first threshold.

[0160] As an example, the first event includes event A1. If event A1 is stopped, that is, the sum of the measurement result of the serving cell of the first node and the hysteresis parameter of event A1 is less than the event threshold of event A1, the first threshold is the adaptive threshold among multiple adaptive thresholds that can filter out a moderate (relatively more) number of beams. For example, the measurement result of the serving cell of the first node is Ms, the hysteresis parameter of event A1 is Hys1, and the event threshold of event A1 is Thresh1. If Ms + Hys1 < Thresh1, that is, event A1 is stopped, then the first node can select the adaptive threshold that can filter out a moderate (relatively more) number of beams from multiple adaptive thresholds as the first threshold.

[0161] As an example, the first event includes event A2. If event A2 is stopped, that is, the difference between the measurement result of the serving cell of the first node and the hysteresis parameter of event A2 is greater than the event threshold of event A2, the first threshold is the adaptive threshold among multiple adaptive thresholds that can filter out a moderate (relatively less) number of beams. For example, the measurement result of the serving cell of the first node is Ms, the hysteresis parameter of event A2 is Hys2, and the event threshold of event A2 is Thresh2. If Ms - Hys2 > Thresh2, that is, event A2 is stopped, then the first node can select the adaptive threshold that can filter out a moderate (relatively less) number of beams from multiple adaptive thresholds as the first threshold.

[0162] As an example, the first event includes event A2. If event A2 is triggered, that is, the sum of the measurement result of the serving cell of the first node and the hysteresis parameter of event A2 is less than the event threshold of event A2, the first threshold is the adaptive threshold among multiple adaptive thresholds that can filter out fewer beams. For example, the measurement result of the serving cell of the first node is Ms, the hysteresis parameter of event A2 is Hys2, and the event threshold of event A2 is Thresh2. If Ms + Hys 2 < Thresh2, that is, event A2 is triggered, then the first node can select the adaptive threshold that can filter out fewer beams from multiple adaptive thresholds as the first threshold. Another example is that the multiple adaptive thresholds include absolute thresholds -102 dBm and -106 dBm, and the preset first threshold is -96 dB. The first node detects that the channel quality deteriorates but not severely, that is, the sum of the measurement result of the serving cell of the first node and the hysteresis parameter of event A2 is less than event A2, and event A2 is triggered. Then the first node selects the lower absolute threshold -102 dBm to ensure that less beam information is reported to help the second node side better optimize resource allocation.

[0163] As an example, the first event includes the channel degradation event R1. If the channel degradation event R1 is triggered, that is, the sum of the difference between the maximum values of the measurement results of the channel quality of the first node in two adjacent times and the hysteresis parameter of the channel degradation event R1 is less than the event threshold of the channel degradation event R1, then the first threshold is the adaptive threshold among multiple adaptive thresholds that can filter out fewer beams. For example, the difference between the maximum values of the measurement results of the channel quality of the first node in two adjacent times is Diff, the hysteresis parameter of the channel degradation event R1 is Hys 3 , and the event threshold of the channel degradation event R1 is Thresh3. If Diff + Hys3 < Thresh3, that is, the channel degradation event R1 is triggered, then the first node can select the adaptive threshold that can filter out fewer beams from multiple adaptive thresholds as the first threshold. Another example is that the multiple adaptive thresholds include absolute thresholds -102 dBm and -106 dBm, and the preset first threshold is -96 dB. The first node detects that the channel change is weak and event R1 is triggered. The terminal device selects the moderate absolute threshold -102 dBm to maintain a moderate beam information report; when the first node discovers according to its own rules that the link quality is higher than expected but the uplink pressure is large, it selects the higher absolute threshold -96 dBm to reduce the reported beam information and maintain a good link quality.

[0164] As a sub - example of the above embodiment, the hysteresis parameter and the event threshold of the channel degradation event R1 can be defined in reportConfigNR.

[0165] As a sub-example of the above embodiment, the event threshold of the channel degradation event R1 can be the differential threshold of L1-RSRP / SINR / RSRQ (usually a negative number).

[0166] The preceding sections introduced schemes for determining the first threshold based on multiple adaptive thresholds through implementation methods 1-1, 1-2, and 1-3. After determining the first threshold, the first node can select beam information based on the first threshold and report it through the second information. The following section introduces the scheme for the first node to send the second information through Example 2.

[0167] Example 2: The first node sends the second information.

[0168] For example, the second node can receive the second information sent by the first node.

[0169] In some embodiments, the second information includes one or more of the following: beam information corresponding to a beam measurement result that satisfies a first condition; beam information corresponding to a beam prediction result that satisfies a first condition; and a first threshold.

[0170] In some embodiments, the first condition is associated with a first threshold.

[0171] As an example, the beam information corresponding to the beam measurement result that satisfies the first condition can be understood as the beam information corresponding to the beam measurement result that has been filtered by the first threshold.

[0172] As an example, the beam information corresponding to the beam prediction result that satisfies the first condition can be understood as the beam information corresponding to the beam prediction result that has been filtered by the first threshold.

[0173] As an example, the first condition can also be associated with an upper limit on the number of beams. For example, if the upper limit on the number of beams is N, the first condition is that it is greater than a first threshold and the number of beams does not exceed N. If the number of beams corresponding to the beam prediction results that are greater than the first threshold is greater than N, then the beam information corresponding to the N beams with the highest beam measurement results is selected and transmitted.

[0174] As an example, if the first model is deployed on the first node side, the second information includes beam information corresponding to the beam prediction result that satisfies the first condition and a first threshold.

[0175] As an example, if the first model is deployed on the second node side, the second information includes beam information corresponding to the beam measurement results that satisfy the first condition and a first threshold.

[0176] As an example, the second information is carried in an L1 message.

[0177] As one example, the second information is carried in an RRC message. For instance, the second information is carried in the MeasResults IE of a MeasurmentReport message, which is an RRC message.

[0178] As one example, the second information bearer media access control element (MAC CE).

[0179] As an example, the second information is carried in the beam report.

[0180] As one embodiment, the second node receives the second information and can perform beam prediction based on the second information. For example, the beam information included in the second information is the L1-RSRP measurement value of the beam. After receiving the second information, the second node completes the data according to the Default Value of the lowest L1-RSRP data and inputs it into the first model to train the first model, and performs beam prediction during the inference phase of the first model.

[0181] As one embodiment, the second node receives the second information and can perform beam management based on the second information. For example, the beam information included in the second information is the L1-RSRP prediction value of the beam. After receiving the second information, the second node can perform beam management based on the L1-RSRP prediction values ​​of different beams.

[0182] As one embodiment, upon receiving the second information, the second node can adjust multiple adaptive thresholds based on the second information. For example, the second information includes a first threshold. After receiving the second information, the second node can adjust multiple adaptive thresholds corresponding to the first node according to the first threshold in order to resend the first information.

[0183] The above examples 1 and 2 illustrate the relevant schemes for determining the first threshold and sending the second information by the first node based on multiple adaptive thresholds. In some scenarios, the two schemes can be used independently. In other scenarios, the two schemes can be used in combination.

[0184] The following example, using Figure 6, illustrates a scheme combining the two approaches. Figure 6 includes steps S610 to S640. Assume the first node is a terminal device and the second node is a network device.

[0185] In step S610, the network device sends the first information to the terminal device.

[0186] The first message sent by the network device to the terminal device indicates multiple adaptive thresholds.

[0187] In step S620, the terminal device determines the first threshold.

[0188] The terminal device receives the first information sent by the network device and determines the first threshold based on multiple adaptive thresholds indicated by the first information.

[0189] In step S630, the terminal device determines the second information.

[0190] The terminal device selects beam information based on the first threshold determined in step S620, and determines the beam information corresponding to the beam measurement result that satisfies the first condition. The first condition is associated with the first threshold, and the second information includes the beam information and the first threshold.

[0191] In step S640, the terminal device sends the second information to the network device.

[0192] The terminal device sends the second information determined in step S630 to the network device.

[0193] The first information received by the first node above indicates multiple adaptive thresholds. This first information can be sent by the second node. Before sending this information, the second node needs to determine the multiple adaptive thresholds. The following example, exemplified by Example 3, describes a scheme for the second node to determine these multiple adaptive thresholds.

[0194] Example 3: The second node determines multiple adaptive thresholds.

[0195] In some embodiments, the second node determines multiple adaptive thresholds based on one or more of the following: first node status information; first model information; network status information; and link quality information. In determining these adaptive thresholds, the first node does not need to provide redundant auxiliary information, protecting user privacy and security. Furthermore, the first node can autonomously select thresholds in a timely manner based on available information such as its own privacy information and measurement results, thereby ensuring high-quality data transmission and the completeness of spatial information contained within the transmitted data. In addition, the second node leverages its computational and informational advantages to generate adaptive reporting thresholds, comprehensively considering first model information, network status information, and first node status information. Under the premise of controllable system performance, this helps to significantly reduce UCI overhead.

[0196] As an example, the state information of the first node may include one or more of the following: the mobility of the first node; the location information of the first node; the needs of the first node; and the behavior pattern of the first node.

[0197] As a sub-implementation of the above embodiments, the state information of the first node can be carried in the capability report of the first node. For example, before the second node decides to start training the first model, the first node can send its capability report to the second node for the second node's LCM reference for the first model. The capability report of the first node carries the state information of the first node and can be used to determine multiple adaptive thresholds.

[0198] As an example, the first model information includes one or more of the following: the LCM indication of the first model; the beam prediction result output by the first model; and the prediction accuracy monitoring index of the first model.

[0199] As an example, network status information includes one or more of the following: network load information; interference information; network policies.

[0200] As an example, link quality information includes one or more of the following: historical CSI; current CSI; environmental information.

[0201] As one example, the second node determines multiple adaptive thresholds based on the first node's state information, the first model information, network state information, and link quality information. For instance, due to the high density of first nodes, high channel interference, large network load, and weak mobility of the first nodes, the second node, considering the LCM indication of the first model, the location information of the first nodes, historical CSI data, etc., decides to generate multiple lower adaptive thresholds, such as -102dBm and -106dBm.

[0202] As an example, one or more of the aforementioned determination of multiple adaptive thresholds can be determined by strategies employed by network operators and equipment manufacturers.

[0203] As an example, multiple adaptive thresholds can be generated by traditional conditional judgment, optimization problem modeling, and optimization methods.

[0204] As an example, multiple adaptive thresholds can be generated by a third model, which can also be called an "adaptive threshold generation model." One or more of the aforementioned determined adaptive thresholds can be used as inputs to the adaptive threshold generation model. For example, referring to the adaptive threshold generation model in Figure 7, the first node state information, the first model information, the network state information, and the link quality information are all inputs to the adaptive threshold generation model.

[0205] As a sub-implementation of the above embodiments, the third model can be an AI / ML model.

[0206] As a sub-implementation of the above embodiments, the third model can be a general model deployed on the second node side. For example, the third model can be the same model as the first model.

[0207] As a sub-implementation of the above embodiments, the third model can be a dedicated model deployed on the second node side. For example, the third model employs AI / ML methods such as random forest.

[0208] As an example, the second node can also generate multiple adaptive thresholds based on a typical threshold and one or more of the multiple adaptive thresholds determined above.

[0209] As a sub-example of the above embodiments, the typical threshold may be specified by the network operator and the equipment manufacturer.

[0210] In some embodiments, the first node sends a first indication message to the second node. The first indication message is used to indicate the type of adaptive threshold. For example, if the output of the first model is a confidence score or probability, the first node sends the first indication message to the second node. The first indication message is carried in a newly added output type field in the first node's capability report, so that the second node knows that the required adaptive threshold type is not an L1-RSRP absolute value or difference value. The second node generates an adaptive threshold of the corresponding type based on the first indication message for the first node to select.

[0211] In some embodiments, the second node may send an updated first message indicating a plurality of adjusted adaptive thresholds.

[0212] As an example, the adjustment of multiple adaptive thresholds is triggered by performance monitoring results. For instance, taking the first node as a terminal device and the second node as a network device, when the first model is deployed on the terminal device side and performance monitoring uses Type 1, or when the first model is deployed on the network device side, the adjustment of multiple adaptive thresholds is triggered by the network device based on the performance monitoring results. When the performance monitoring results are generated on the terminal device side, the terminal device can provide feedback on the monitoring results, and the adjustment of multiple adaptive thresholds is still triggered by the network device side; otherwise, it is triggered by the terminal device side.

[0213] The preceding sections, through Examples 1, 2, and 3, respectively introduced the relevant schemes for determining a first threshold based on multiple adaptive thresholds, sending second information by a first node, and determining multiple adaptive thresholds by a second node. In some scenarios, the three schemes can be used independently. In other scenarios, the three schemes can be used in combination.

[0214] The following section uses Figures 8 and 9 to illustrate a scheme that combines the three schemes.

[0215] Figure 8 includes steps S810 to S860, taking the example of a terminal device using a second model to determine a first threshold. Assume the first node is a terminal device, the second node is a network device, the second model and the first model are the same model, and the first model is deployed on the terminal device side.

[0216] In step S810, the network device determines multiple adaptive thresholds.

[0217] Network devices determine multiple adaptive thresholds based on the status information of terminal devices and historical link quality information.

[0218] In step S820, the network device sends the first information to the terminal device.

[0219] The network device sends multiple adaptive thresholds to the terminal device via initial information. Furthermore, the network device evaluates the capabilities of the terminal device received from the network device and configures LCM indication, resource allocation, and beam reporting.

[0220] In step S830, the terminal device uses the first model to perform beam prediction and determine the first threshold.

[0221] The network device scans the beams according to the resource configuration. The terminal device performs beam measurement on the corresponding beam based on the received first reference signal, and uses the first model to predict the beams and determine the first threshold. Multiple adaptive thresholds and beam measurement results are used as inputs to the first model, and the first threshold and beam prediction results are used as outputs of the first model.

[0222] In step S840, the terminal device determines the second information.

[0223] The second information includes a first threshold and beam information corresponding to the beam prediction result that satisfies the first condition. The first condition is associated with the first threshold. The terminal device determines the second information based on the beam prediction result output by the first model in step S830 and the first threshold.

[0224] In step S850, the terminal device sends the second information to the network device.

[0225] The terminal device sends the second information determined in step S840 to the network device.

[0226] In step S860, the network device adjusts multiple adaptive thresholds.

[0227] The network device receives the second information sent by the network device, and adjusts multiple adaptive thresholds corresponding to the terminal device based on the first threshold included in the second information, so as to resend the first information.

[0228] Figure 9 includes steps S910 to S960, taking the example of a terminal device determining a first threshold based on multiple adaptive thresholds and / or historical data. Assume the first node is the terminal device, the second node is the network device, and the first model is deployed on the network device side.

[0229] In step S910, the network device determines multiple adaptive thresholds.

[0230] Network devices determine multiple adaptive thresholds based on the status information of terminal devices and historical link quality information.

[0231] In step S920, the network device sends the first information to the terminal device.

[0232] The network device sends multiple adaptive thresholds to the terminal device via initial information. Furthermore, the network device evaluates the capabilities of the terminal device received from the network device and configures LCM indication, resource allocation, and beam reporting.

[0233] In step S930, the terminal device determines a first threshold based on multiple adaptive thresholds and / or historical data.

[0234] The network device scans the beams according to the resource configuration, and the terminal device performs beam measurement on the corresponding beams based on the received first reference signal, and determines the first threshold based on multiple adaptive thresholds and / or historical data. The historical data indicates the statistical set of historical beam measurement results, the first threshold set corresponding to historical beam measurement, the update frequency of the first information, and the changing trend of the first threshold.

[0235] In step S940, the terminal device determines the second information.

[0236] The second information includes a first threshold and beam information corresponding to beam measurement results that meet the first condition. The first condition is associated with the first threshold. The terminal device determines the second information based on the beam measurement results determined in step S930 and the first threshold.

[0237] In step S950, the terminal device sends the second information to the network device.

[0238] The terminal device sends the second information determined in step S940 to the network device.

[0239] In step S960, the network device performs beam prediction.

[0240] The network device receives the second information, uses the beam information corresponding to the beam measurement results that meet the first condition, which are included in the second information, as the input of the first model, and performs beam prediction using the first model.

[0241] In step S970, the network device adjusts multiple adaptive thresholds.

[0242] The network device receives the second information sent by the network device, and adjusts multiple adaptive thresholds corresponding to the terminal device based on the first threshold included in the second information, so as to resend the first information.

[0243] The method embodiments of this application have been described in detail above with reference to Figures 1 to 9. The apparatus embodiments of this application will be described in detail below with reference to Figures 10 to 12. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments; therefore, any parts not described in detail can be referred to the preceding method embodiments.

[0244] Figure 10 illustrates a first node for wireless communication provided in an embodiment of this application. As shown in Figure 10, the first node 1000 includes a first transceiver 1010.

[0245] A first transceiver 1010 is configured to receive first information, the first information being configured to indicate multiple adaptive thresholds, the multiple adaptive thresholds being configured to select beam information, the beam information being configured for beam prediction based on a first model.

[0246] As one embodiment, the plurality of adaptive thresholds for selecting beam information includes: determining a first threshold based on the plurality of adaptive thresholds, wherein the first threshold is used to determine the beam information.

[0247] As one embodiment, determining the first threshold based on multiple adaptive thresholds includes: determining the first threshold using a second model, wherein the multiple adaptive thresholds are the inputs of the second model, and the first threshold is the output of the second model.

[0248] As one embodiment, determining the first threshold based on multiple adaptive thresholds includes: determining the first threshold based on the multiple adaptive thresholds and / or historical data, wherein the historical data is used to indicate one or more of the following: a set of statistics of historical beam measurement results; a set of first thresholds corresponding to historical beam measurements; the update frequency of the first information; and the changing trend of the first threshold.

[0249] As one embodiment, determining the first threshold based on the plurality of adaptive thresholds includes: the first threshold corresponding to the first round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that can filter out more beams.

[0250] As an example, determining the first threshold based on the plurality of adaptive thresholds and historical data includes: if the absolute value of the difference between the statistics of the i-th round beam measurement result and the weighted sum of the set of statistics of the historical beam measurement results is less than or equal to a second threshold, then the first threshold corresponding to the i-th round beam measurement is the adaptive threshold of the set of weighted sums of the plurality of adaptive thresholds that is closest to the first threshold set corresponding to the historical beam measurement.

[0251] As an example, determining the first threshold based on the plurality of adaptive thresholds and historical data includes: if the absolute value of the difference between the statistics of the i-th round beam measurement result and the weighted sum of the sets of statistics of historical beam measurement results is greater than a second threshold, then determining the first threshold corresponding to the i-th round beam measurement based on the update frequency of the first information and / or the changing trend of the first threshold.

[0252] As an example, determining the first threshold based on the plurality of adaptive thresholds and historical data includes: if the time interval between the reception time of the first information and the reception time of the previous first information is less than a first threshold, then the first threshold corresponding to the i-th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that can filter out fewer beams.

[0253] As one embodiment, determining the first threshold corresponding to the i-th round of beam measurement based on the changing trend of the first threshold includes: if the first threshold corresponding to the (i-1)-th round of beam measurement is greater than or equal to the first threshold corresponding to the (i-2)-th round of beam measurement, then the first threshold corresponding to the i-th round of beam measurement is an adaptive threshold among the plurality of adaptive thresholds that is greater than the first threshold corresponding to the (i-1)-th round of beam measurement; if the first threshold corresponding to the (i-1)-th round of beam measurement is less than the first threshold corresponding to the (i-2)-th round of beam measurement, then the first threshold corresponding to the i-th round of beam measurement is an adaptive threshold among the plurality of adaptive thresholds that is less than the first threshold corresponding to the (i-1)-th round of beam measurement; the first threshold corresponding to the second round of beam measurement is an adaptive threshold among the plurality of adaptive thresholds that can filter out fewer beams.

[0254] As one embodiment, determining the first threshold based on the plurality of adaptive thresholds includes: determining the first threshold based on the plurality of adaptive thresholds and a first event, wherein the first event includes one or more of the following: the serving cell signal quality of the first node is higher than a specified threshold; the serving cell signal quality of the first node is lower than a specified threshold; the difference between two adjacent channel quality measurements of the first node is lower than a specified threshold.

[0255] As one embodiment, determining the first threshold based on the plurality of adaptive thresholds and the first event includes: determining the first threshold based on one or more of the following: the plurality of adaptive thresholds; the hysteresis parameter of the first event; the event threshold of the first event; the measurement result of the serving cell of the first node; and the measurement result of the channel quality of the first node.

[0256] As an example, the first node further includes: the first transceiver 1010 is also configured to transmit second information, the second information including one or more of the following: beam information corresponding to a beam measurement result that satisfies a first condition, the first condition being associated with a first threshold; beam information corresponding to a beam prediction result that satisfies the first condition; and the first threshold.

[0257] Figure 11 illustrates a second node for wireless communication provided in an embodiment of this application. As shown in Figure 11, the second node 1100 includes a second transceiver 1110.

[0258] The second transceiver 1110 is used to transmit first information, which indicates multiple adaptive thresholds for selecting beam information for beam prediction based on a first model.

[0259] As one embodiment, the plurality of adaptive thresholds for selecting beam information includes: determining a first threshold based on the plurality of adaptive thresholds, wherein the first threshold is used to determine the beam information.

[0260] As one embodiment, determining the first threshold based on multiple adaptive thresholds includes: determining the first threshold using a second model, wherein the multiple adaptive thresholds are the inputs of the second model, and the first threshold is the output of the second model.

[0261] As one embodiment, determining the first threshold based on multiple adaptive thresholds includes: determining the first threshold based on the multiple adaptive thresholds and / or historical data, wherein the historical data is used to indicate one or more of the following: a set of statistics of historical beam measurement results; a set of first thresholds corresponding to historical beam measurements; the update frequency of the first information; and the changing trend of the first threshold.

[0262] As one embodiment, determining the first threshold based on the plurality of adaptive thresholds includes: the first threshold corresponding to the first round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that can filter out more beams.

[0263] As an example, determining the first threshold based on the plurality of adaptive thresholds and historical data includes: if the absolute value of the difference between the statistics of the i-th round beam measurement result and the weighted sum of the set of statistics of the historical beam measurement results is less than or equal to a second threshold, then the first threshold corresponding to the i-th round beam measurement is the adaptive threshold of the set of weighted sums of the plurality of adaptive thresholds that is closest to the first threshold set corresponding to the historical beam measurement.

[0264] As an example, determining the first threshold based on the plurality of adaptive thresholds and historical data includes: if the absolute value of the difference between the statistics of the i-th round beam measurement result and the weighted sum of the sets of statistics of historical beam measurement results is greater than a second threshold, then determining the first threshold corresponding to the i-th round beam measurement based on the update frequency of the first information and / or the changing trend of the first threshold.

[0265] As an example, determining the first threshold based on the plurality of adaptive thresholds and historical data includes: if the time interval between the reception time of the first information and the reception time of the previous first information is less than a first threshold, then the first threshold corresponding to the i-th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that can filter out fewer beams.

[0266] As one embodiment, determining the first threshold corresponding to the i-th round of beam measurement based on the changing trend of the first threshold includes: if the first threshold corresponding to the (i-1)-th round of beam measurement is greater than or equal to the first threshold corresponding to the (i-2)-th round of beam measurement, then the first threshold corresponding to the i-th round of beam measurement is an adaptive threshold among the plurality of adaptive thresholds that is greater than the first threshold corresponding to the (i-1)-th round of beam measurement; if the first threshold corresponding to the (i-1)-th round of beam measurement is less than the first threshold corresponding to the (i-2)-th round of beam measurement, then the first threshold corresponding to the i-th round of beam measurement is an adaptive threshold among the plurality of adaptive thresholds that is less than the first threshold corresponding to the (i-1)-th round of beam measurement; the first threshold corresponding to the second round of beam measurement is an adaptive threshold among the plurality of adaptive thresholds that can filter out fewer beams.

[0267] As one embodiment, determining the first threshold based on the plurality of adaptive thresholds includes: determining the first threshold based on the plurality of adaptive thresholds and a first event, wherein the first event includes one or more of the following: the serving cell signal quality of the first node is higher than a specified threshold; the serving cell signal quality of the first node is lower than a specified threshold; the difference between two adjacent channel quality measurements of the first node is lower than a specified threshold.

[0268] As one embodiment, determining the first threshold based on the plurality of adaptive thresholds and the first event includes: determining the first threshold based on one or more of the following: the plurality of adaptive thresholds; the hysteresis parameter of the first event; the event threshold of the first event; the measurement result of the serving cell of the first node; and the measurement result of the channel quality of the first node.

[0269] As an embodiment, the second node further includes: the second transceiver 1110 is also configured to receive second information, the second information including one or more of the following: beam information corresponding to a beam measurement result that satisfies a first condition, the first condition being associated with the first threshold; beam information corresponding to a beam prediction result that satisfies the first condition; and the first threshold.

[0270] As one embodiment, the second node further includes: a first processor, configured to determine the plurality of adaptive thresholds based on one or more of the following: first node status information; first model information; network status information; link quality information.

[0271] In an optional embodiment, the first transceiver 1010 may be a transceiver 1230. The first node 1000 may also include a processor 1210 and a memory 1220, as shown in FIG12.

[0272] In an optional embodiment, the second transceiver 1110 may be a transceiver 1230. The second node 1100 may also include a processor 1210 and a memory 1220, as shown in FIG12.

[0273] Figure 12 is a schematic structural diagram of a communication device according to an embodiment of this application. The dashed lines in Figure 12 indicate that the unit or module is optional. This device 1200 can be used to implement the methods described in the above method embodiments. Device 1200 can be a chip, a terminal device, or a network device.

[0274] Apparatus 1200 may include one or more processors 1210. The processor 1210 may support apparatus 1200 in implementing the methods described in the preceding method embodiments. The processor 1210 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.

[0275] The apparatus 1200 may further include one or more memories 1220. The memories 1220 store a program that can be executed by the processor 1210, causing the processor 1210 to perform the methods described in the preceding method embodiments. The memories 1220 may be independent of the processor 1210 or integrated within the processor 1210.

[0276] The device 1200 may also include a transceiver 1230. The processor 1210 can communicate with other devices or chips via the transceiver 1230. For example, the processor 1210 can send and receive data with other devices or chips via the transceiver 1230.

[0277] This application also provides a computer-readable storage medium for storing a program. This computer-readable storage medium can be applied to a terminal or network device provided in this application, and the program causes a computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0278] This application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to a terminal or network device provided in this application embodiment, and the program causes a computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0279] This application also provides a computer program. This computer program can be applied to the terminal 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.

[0280] It should be understood that the terms "system" and "network" in this application can be 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.

[0281] 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.

[0282] In the embodiments of this application, the term "correspondence" can 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.

[0283] In this application embodiment, the "protocol" may refer to a standard protocol in the field of communication, such as the LTE protocol, the NR protocol, and related protocols applied to future communication systems. This application does not limit this.

[0284] 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.

[0285] In the various embodiments of this application, the order of the above-mentioned processes 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.

[0286] 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.

[0287] 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.

[0288] 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.

[0289] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of 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 website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. 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 media may 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.

[0290] 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 a first node in wireless communication, characterized in that, include: Receive first information, the first information being used to indicate multiple adaptive thresholds, the multiple adaptive thresholds being used to select beam information, the beam information being used for beam prediction based on a first model.

2. The method as described in claim 1, characterized in that, The multiple adaptive thresholds are used to select beam information, including: A first threshold is determined based on the plurality of adaptive thresholds, and the first threshold is used to determine the beam information.

3. The method as described in claim 2, characterized in that, Determining the first threshold based on multiple adaptive thresholds includes: The first threshold is determined using a second model, wherein the plurality of adaptive thresholds are inputs to the second model, and the first threshold is output of the second model.

4. The method as described in claim 2, characterized in that, Determining the first threshold based on multiple adaptive thresholds includes: Based on the plurality of adaptive thresholds and / or historical data, the first threshold is used to indicate one or more of the following: A set of statistics on historical beam measurement results; The first threshold set corresponding to historical beam measurements; The update frequency of the first information; The changing trend of the first threshold.

5. The method as described in claim 4, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds includes: The first threshold corresponding to the first round of beam measurement is the adaptive threshold that can filter out more beams among the multiple adaptive thresholds.

6. The method as described in claim 4 or 5, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the absolute value of the difference between the statistic of the i-th round beam measurement result and the weighted sum of the statistic set of historical beam measurement results is less than or equal to the second threshold, then the first threshold corresponding to the i-th round beam measurement is the adaptive threshold of the weighted sum of the set of first thresholds corresponding to historical beam measurements among the plurality of adaptive thresholds.

7. The method as described in claim 4 or 5, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the absolute value of the difference between the statistic of the i-th round beam measurement result and the weighted sum of the statistic set of historical beam measurement results is greater than the second threshold, then the first threshold corresponding to the i-th round beam measurement is determined based on the update frequency of the first information and / or the changing trend of the first threshold.

8. The method as described in claim 7, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the time interval between the reception time of the first information and the reception time of the previous first information is less than a first threshold, then the first threshold corresponding to the i-th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that can filter out fewer beams.

9. The method as described in claim 7, characterized in that, Determining the first threshold corresponding to the i-th round of beam measurement based on the changing trend of the first threshold includes: If the first threshold corresponding to the (i-1)th round of beam measurement is greater than or equal to the first threshold corresponding to the (i-2)th round of beam measurement, then the first threshold corresponding to the (i-1)th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that is greater than the first threshold corresponding to the (i-1)th round of beam measurement. If the first threshold corresponding to the (i-1)th round of beam measurement is less than the first threshold corresponding to the (i-2)th round of beam measurement, then the first threshold corresponding to the (i-1)th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that is less than the first threshold corresponding to the (i-1)th round of beam measurement. The first threshold corresponding to the second round of beam measurement is the adaptive threshold that can filter out fewer beams among the plurality of adaptive thresholds.

10. The method as described in claim 2, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds includes: The first threshold is determined based on the plurality of adaptive thresholds and a first event, wherein the first event includes one or more of the following: The signal quality of the serving cell of the first node is higher than a specified threshold; The signal quality of the serving cell of the first node is lower than a specified threshold; The difference between two consecutive channel quality measurements of the first node is below a specified threshold.

11. The method as described in claim 10, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and the first event includes: The first threshold is determined based on one or more of the following: The plurality of adaptive thresholds; The hysteresis parameter of the first event; The event threshold for the first event: Measurement results of the serving cell of the first node; The measurement results of the channel quality of the first node.

12. The method according to any one of claims 1-11, characterized in that, The method further includes: Send a second message, which includes one or more of the following: The beam information corresponding to the beam measurement result that satisfies the first condition, wherein the first condition is associated with the first threshold. Beam information corresponding to the beam prediction result that satisfies the first condition; The first threshold.

13. A method for a second node in wireless communication, characterized in that, include: Send first information, which indicates multiple adaptive thresholds for selecting beam information for beam prediction based on a first model.

14. The method as described in claim 13, characterized in that, The multiple adaptive thresholds are used to select beam information, including: A first threshold is determined based on the plurality of adaptive thresholds, and the first threshold is used to determine the beam information.

15. The method as described in claim 14, characterized in that, Determining the first threshold based on multiple adaptive thresholds includes: The first threshold is determined using a second model, wherein the plurality of adaptive thresholds are inputs to the second model, and the first threshold is output of the second model.

16. The method as described in claim 14, characterized in that, Determining the first threshold based on multiple adaptive thresholds includes: Based on the plurality of adaptive thresholds and / or historical data, the first threshold is used to indicate one or more of the following: A set of statistics on historical beam measurement results; The first threshold set corresponding to historical beam measurements; The update frequency of the first information; The changing trend of the first threshold.

17. The method as described in claim 16, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds includes: The first threshold corresponding to the first round of beam measurement is the adaptive threshold that can filter out more beams among the multiple adaptive thresholds.

18. The method as described in claim 16 or 17, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the absolute value of the difference between the statistic of the i-th round beam measurement result and the weighted sum of the statistic set of historical beam measurement results is less than or equal to the second threshold, then the first threshold corresponding to the i-th round beam measurement is the adaptive threshold of the weighted sum of the set of first thresholds corresponding to historical beam measurements among the plurality of adaptive thresholds.

19. The method as described in claim 16 or 17, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the absolute value of the difference between the statistic of the i-th round beam measurement result and the weighted sum of the statistic set of historical beam measurement results is greater than the second threshold, then the first threshold corresponding to the i-th round beam measurement is determined based on the update frequency of the first information and / or the changing trend of the first threshold.

20. The method as described in claim 19, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the time interval between the reception time of the first information and the reception time of the previous first information is less than a first threshold, then the first threshold corresponding to the i-th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that can filter out fewer beams.

21. The method as described in claim 19, characterized in that, Determining the first threshold corresponding to the i-th round of beam measurement based on the changing trend of the first threshold includes: If the first threshold corresponding to the (i-1)th round of beam measurement is greater than or equal to the first threshold corresponding to the (i-2)th round of beam measurement, then the first threshold corresponding to the (i-1)th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that is greater than the first threshold corresponding to the (i-1)th round of beam measurement. If the first threshold corresponding to the (i-1)th round of beam measurement is less than the first threshold corresponding to the (i-2)th round of beam measurement, then the first threshold corresponding to the (i-1)th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that is less than the first threshold corresponding to the (i-1)th round of beam measurement. The first threshold corresponding to the second round of beam measurement is the adaptive threshold that can filter out fewer beams among the plurality of adaptive thresholds.

22. The method as described in claim 14, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds includes: The first threshold is determined based on the plurality of adaptive thresholds and a first event, wherein the first event includes one or more of the following: The signal quality of the serving cell of the first node is higher than a specified threshold; The signal quality of the serving cell of the first node is lower than a specified threshold; The difference between two consecutive channel quality measurements of the first node is below a specified threshold.

23. The method as described in claim 22, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and the first event includes: The first threshold is determined based on one or more of the following: The plurality of adaptive thresholds; The hysteresis parameter of the first event; The event threshold for the first event: Measurement results of the serving cell of the first node; The measurement results of the channel quality of the first node.

24. The method according to any one of claims 13-23, characterized in that, The method further includes: Receive second information, the second information including one or more of the following: The beam information corresponding to the beam measurement result that satisfies the first condition, wherein the first condition is associated with the first threshold. Beam information corresponding to the beam prediction result that satisfies the first condition; The first threshold.

25. The method according to any one of claims 13-24, characterized in that, The method further includes: The plurality of adaptive thresholds are determined based on one or more of the following: The status information of the first node; The first model information; Network status information; Link quality information.

26. A first node for wireless communication, characterized in that, include: A first transceiver is configured to receive first information, which indicates multiple adaptive thresholds for selecting beam information for beam prediction based on a first model.

27. The first node as described in claim 26, characterized in that, The multiple adaptive thresholds are used to select beam information, including: A first threshold is determined based on the plurality of adaptive thresholds, and the first threshold is used to determine the beam information.

28. The first node as described in claim 27, characterized in that, Determining the first threshold based on multiple adaptive thresholds includes: The first threshold is determined using a second model, wherein the plurality of adaptive thresholds are inputs to the second model, and the first threshold is output of the second model.

29. The first node as described in claim 27, characterized in that, Determining the first threshold based on multiple adaptive thresholds includes: Based on the plurality of adaptive thresholds and / or historical data, the first threshold is used to indicate one or more of the following: A set of statistics on historical beam measurement results; The first threshold set corresponding to historical beam measurements; The update frequency of the first information; The changing trend of the first threshold.

30. The first node as described in claim 29, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds includes: The first threshold corresponding to the first round of beam measurement is the adaptive threshold that can filter out more beams among the multiple adaptive thresholds.

31. The first node as described in claim 29 or 30, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the absolute value of the difference between the statistic of the i-th round beam measurement result and the weighted sum of the statistic set of historical beam measurement results is less than or equal to the second threshold, then the first threshold corresponding to the i-th round beam measurement is the adaptive threshold of the weighted sum of the set of first thresholds corresponding to historical beam measurements among the plurality of adaptive thresholds.

32. The first node as described in claim 29 or 30, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the absolute value of the difference between the statistic of the i-th round beam measurement result and the weighted sum of the statistic set of historical beam measurement results is greater than the second threshold, then the first threshold corresponding to the i-th round beam measurement is determined based on the update frequency of the first information and / or the changing trend of the first threshold.

33. The first node as described in claim 32, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the time interval between the reception time of the first information and the reception time of the previous first information is less than a first threshold, then the first threshold corresponding to the i-th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that can filter out fewer beams.

34. The first node as described in claim 32, characterized in that, Determining the first threshold corresponding to the i-th round of beam measurement based on the changing trend of the first threshold includes: If the first threshold corresponding to the (i-1)th round of beam measurement is greater than or equal to the first threshold corresponding to the (i-2)th round of beam measurement, then the first threshold corresponding to the (i-1)th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that is greater than the first threshold corresponding to the (i-1)th round of beam measurement. If the first threshold corresponding to the (i-1)th round of beam measurement is less than the first threshold corresponding to the (i-2)th round of beam measurement, then the first threshold corresponding to the (i-1)th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that is less than the first threshold corresponding to the (i-1)th round of beam measurement. The first threshold corresponding to the second round of beam measurement is the adaptive threshold that can filter out fewer beams among the plurality of adaptive thresholds.

35. The first node as described in claim 27, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds includes: The first threshold is determined based on the plurality of adaptive thresholds and a first event, wherein the first event includes one or more of the following: The signal quality of the serving cell of the first node is higher than a specified threshold; The signal quality of the serving cell of the first node is lower than a specified threshold; The difference between two consecutive channel quality measurements of the first node is below a specified threshold.

36. The first node as described in claim 35, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and the first event includes: The first threshold is determined based on one or more of the following: The plurality of adaptive thresholds; The hysteresis parameter of the first event; The event threshold for the first event: Measurement results of the serving cell of the first node; The measurement results of the channel quality of the first node.

37. The first node as described in any one of claims 26-36, characterized in that, The first node also includes: The first transceiver is also used to transmit second information, the second information including one or more of the following: The beam information corresponding to the beam measurement result that satisfies the first condition, wherein the first condition is associated with the first threshold. Beam information corresponding to the beam prediction result that satisfies the first condition; The first threshold.

38. A second node for wireless communication, characterized in that, include: A second transceiver is used to transmit first information, which indicates multiple adaptive thresholds for selecting beam information for beam prediction based on a first model.

39. The second node as described in claim 38, characterized in that, The multiple adaptive thresholds are used to select beam information, including: A first threshold is determined based on the plurality of adaptive thresholds, and the first threshold is used to determine the beam information.

40. The second node as described in claim 39, characterized in that, Determining the first threshold based on multiple adaptive thresholds includes: The first threshold is determined using a second model, wherein the plurality of adaptive thresholds are inputs to the second model, and the first threshold is output of the second model.

41. The second node as described in claim 39, characterized in that, Determining the first threshold based on multiple adaptive thresholds includes: Based on the plurality of adaptive thresholds and / or historical data, the first threshold is used to indicate one or more of the following: A set of statistics on historical beam measurement results; The first threshold set corresponding to historical beam measurements; The update frequency of the first information; The changing trend of the first threshold.

42. The second node as described in claim 41, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds includes: The first threshold corresponding to the first round of beam measurement is the adaptive threshold that can filter out more beams among the multiple adaptive thresholds.

43. The second node as described in claim 41 or 42, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the absolute value of the difference between the statistic of the i-th round beam measurement result and the weighted sum of the statistic set of historical beam measurement results is less than or equal to the second threshold, then the first threshold corresponding to the i-th round beam measurement is the adaptive threshold of the weighted sum of the set of first thresholds corresponding to historical beam measurements among the plurality of adaptive thresholds.

44. The second node as described in claim 41 or 42, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the absolute value of the difference between the statistic of the i-th round beam measurement result and the weighted sum of the statistic set of historical beam measurement results is greater than the second threshold, then the first threshold corresponding to the i-th round beam measurement is determined based on the update frequency of the first information and / or the changing trend of the first threshold.

45. The second node as described in claim 44, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and historical data includes: If the time interval between the reception time of the first information and the reception time of the previous first information is less than a first threshold, then the first threshold corresponding to the i-th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that can filter out fewer beams.

46. ​​The second node as described in claim 44, characterized in that, Determining the first threshold corresponding to the i-th round of beam measurement based on the changing trend of the first threshold includes: If the first threshold corresponding to the (i-1)th round of beam measurement is greater than or equal to the first threshold corresponding to the (i-2)th round of beam measurement, then the first threshold corresponding to the (i-1)th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that is greater than the first threshold corresponding to the (i-1)th round of beam measurement. If the first threshold corresponding to the (i-1)th round of beam measurement is less than the first threshold corresponding to the (i-2)th round of beam measurement, then the first threshold corresponding to the (i-1)th round of beam measurement is the adaptive threshold among the plurality of adaptive thresholds that is less than the first threshold corresponding to the (i-1)th round of beam measurement. The first threshold corresponding to the second round of beam measurement is the adaptive threshold that can filter out fewer beams among the plurality of adaptive thresholds.

47. The second node as described in claim 39, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds includes: The first threshold is determined based on the plurality of adaptive thresholds and a first event, wherein the first event includes one or more of the following: The signal quality of the serving cell of the first node is higher than a specified threshold; The signal quality of the serving cell of the first node is lower than a specified threshold; The difference between two consecutive channel quality measurements of the first node is below a specified threshold.

48. The second node as described in claim 47, characterized in that, Determining the first threshold based on the plurality of adaptive thresholds and the first event includes: The first threshold is determined based on one or more of the following: The plurality of adaptive thresholds; The hysteresis parameter of the first event; The event threshold for the first event: Measurement results of the serving cell of the first node; The measurement results of the channel quality of the first node.

49. The second node as described in any one of claims 38-48, characterized in that, The second node also includes: The second transceiver is also configured to receive second information, the second information including one or more of the following: The beam information corresponding to the beam measurement result that satisfies the first condition, wherein the first condition is associated with the first threshold. Beam information corresponding to the beam prediction result that satisfies the first condition; The first threshold.

50. The second node as described in any one of claims 38-49, characterized in that, The second node also includes: A first processor is configured to determine the plurality of adaptive thresholds based on one or more of the following: The status information of the first node; The first model information; Network status information; Link quality information.

51. A terminal device, characterized in that, The device includes a transceiver, a memory, and a processor. The memory is used to store a program, and the processor is used to invoke the program in the memory and control the transceiver to receive or send signals so that the terminal performs the method as described in any one of claims 1-12.

52. A network device, characterized in that, The device includes a transceiver, a memory, and a processor. The memory stores a program, and the processor invokes the program in the memory and controls the transceiver to receive or transmit signals so that the network device performs the method as described in any one of claims 13-25.

53. An apparatus, characterized in that, Includes a processor for calling a program from memory to cause the device to perform the method as described in any one of claims 1-25.

54. 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 1-25.

55. 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 1-25.

56. 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 1-25.

57. A computer program, characterized in that, The computer program causes the computer to perform the method as described in any one of claims 1-25.

Images