Method and apparatus for wireless communication

Abstract

Provided are a method and apparatus for wireless communication. The method comprises: a first device receives first indication information, the first indication information being used for indicating a first QCL relationship; and the first device performs a first operation on the basis of the first QCL relationship, wherein the first operation is one or more of the following: determining a beam set for model training and / or model reasoning, elements of the first QCL relationship including an identifier of the beam set; and determining multiple optimal beams in a model prediction result.

Description

Methods and apparatus for wireless communication Technical Field

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

[0002] In certain beam management scenarios, terminal devices can predict downlink transmission beams using a model and report this prediction to the network device. This model needs to be trained before inference prediction can be performed. However, there is a time interval between the training and inference phases. If the beam transmission conditions change, the model may err during the inference phase. Therefore, ensuring the consistency of the model between the training and inference phases is a crucial technical problem that needs to be solved.

[0003] Summary of the Invention

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

[0005] In a first aspect, a method for wireless communication is provided, comprising: a first device receiving first indication information, the first indication information indicating a first quasi-co-located (QCL) relationship; the first device performing a first operation based on the first QCL relationship; wherein the first operation is one or more of the following: determining a beam set for model training and / or model inference, the elements of the first QCL relationship including an identifier of the beam set; and determining a plurality of optimal beams in model prediction results.

[0006] In a second aspect, a method for wireless communication is provided, comprising: a second device sending first indication information to a first device, the first indication information indicating a first QCL relationship, the first QCL relationship being used by the first device to perform a first operation; wherein the first operation is one or more of the following: determining a beam set for model training and / or model inference, the elements of the first QCL relationship including an identifier of the beam set; determining a plurality of optimal beams in the model prediction results.

[0007] Thirdly, an apparatus for wireless communication is provided, the apparatus being a first device, comprising: a transceiver unit for receiving first indication information, the first indication information being used to indicate a first QCL relationship; and a processing unit for performing a first operation based on the first QCL relationship; wherein the first operation is one or more of the following: determining a beam set for model training and / or model inference, the elements of the first QCL relationship including an identifier of the beam set; and determining a plurality of optimal beams in the model prediction results.

[0008] Fourthly, an apparatus for wireless communication is provided, the apparatus being a second device, comprising: a transceiver unit for sending first indication information to a first device, the first indication information indicating a first QCL relationship, the first QCL relationship being used by the first device to perform a first operation; wherein the first operation is one or more of the following: determining a beam set for model training and / or model inference, the elements of the first QCL relationship including an identifier of the beam set; determining a plurality of optimal beams in the model prediction results.

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

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

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

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

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

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

[0015] The first device (e.g., a terminal device) in this application embodiment can determine a first QCL relationship based on first indication information. When the elements of the first QCL relationship include the identifier of a beam set, the first QCL relationship can be used to determine the beam set for model training and / or model inference, thereby improving the accuracy of beam prediction by ensuring the consistency of the beam set. The first QCL relationship can also be used to determine multiple optimal beams in the model prediction results, which helps to reduce the number of beams that need to be measured independently. Attached Figure Description

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

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

[0018] Figure 3 is a schematic diagram of the beam relationship during model training and model inference.

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

[0020] Figure 5 is a schematic diagram of another possible implementation of the method shown in Figure 4.

[0021] Figure 6 is a schematic diagram of a device for wireless communication provided in an embodiment of this application.

[0022] Figure 7 is a schematic diagram of another device for wireless communication provided in an embodiment of this application.

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

[0024] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0025] Figure 1 is a schematic diagram of the architecture of the wireless communication system 100 used in an embodiment of this application. As shown in Figure 1, the wireless communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 may provide communication coverage for a specific geographical area and may communicate with terminal devices located within that coverage area.

[0026] Figure 1 exemplarily illustrates a network device and two terminal devices. Optionally, the wireless communication system 100 may include multiple network devices, and each network device may include an additional number of terminal devices within its coverage area; this is not limited. In other words, the wireless communication system may include one or more network devices, and each network device may support wireless communication for one or more terminal devices.

[0027] In the embodiments of this application, the communication system shown in FIG1 may also include other network entities such as a mobility management entity (MME), an access and mobility management function (AMF), and a network controller. The embodiments of this application do not limit this.

[0028] It should be understood that the embodiments of this application can be applied to various communication systems. For example, the embodiments of this application can be applied to Global System for Mobile Communication (GSM), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), General Packet Radio Service (GPRS), Long Term Evolution (LTE), Advanced Long Term Evolution (LTE-A), New Radio (NR), evolution systems of NR, LTE-based access to unlicensed spectrum (LTE-U), NR-based access to unlicensed spectrum (NR-U), Universal Mobile Telecommunications System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), and 5th-generation (5G) systems. The embodiments of this application can also be applied to other communication systems, such as 6th-generation (6G) mobile communication systems, or future communication systems such as satellite communication systems.

[0029] Traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, communication systems can support not only traditional cellular communication but also one or more other types of communication. For example, a communication system can support one or more of the following communication methods: device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), enhanced machine-type communication (eMTC), vehicle-to-vehicle (V2V) communication, and vehicle-to-everything (V2X) communication. The embodiments of this application can also be applied to communication systems that support the above-mentioned communication methods.

[0030] The communication system in this application embodiment can be applied to carrier aggregation (CA) scenarios, dual connectivity (DC) scenarios, and standalone (SA) network deployment scenarios.

[0031] The communication system in this application embodiment can be applied to unlicensed spectrum. This unlicensed spectrum can also be considered a shared spectrum. Alternatively, the communication system in this application embodiment can also be applied to licensed spectrum. This licensed spectrum can also be considered a dedicated spectrum.

[0032] The embodiments of this application can be applied to non-terrestrial network (NTN) systems. As an example, the NTN system can be a 4G-based NTN system, an NR-based NTN system, an Internet of Things (IoT)-based NTN system, or a narrowband Internet of Things (NB-IoT)-based NTN system.

[0033] The wireless communication system in this application embodiment can utilize the following resources to support wireless communication with one or more communication devices: time resources (e.g., symbols, sub-slots, time slots, subframes, frames, etc.) or frequency resources (e.g., subcarriers, carriers). Additionally, the wireless communication system can support wireless communication across various radio access technologies (RATs), including third-generation (3G), fourth-generation (4G), fifth-generation (5G), and other suitable RATs beyond 5G.

[0034] The terminal equipment in this application embodiment may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, user communication equipment, wireless communication equipment, user agent, or user device, etc.

[0035] In some embodiments, the terminal device in this application can be a device that provides voice and / or data connectivity to a user, and can be used to connect people, objects, and machines, such as a handheld device with wireless connectivity, an in-vehicle device, etc. The terminal device in the embodiments of this application can be a mobile phone, tablet computer, laptop computer, PDA, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc. Optionally, the UE can be used to act as a base station. For example, the UE can act as a scheduling entity, providing sidelink signals between UEs in V2X or D2D, etc. For example, cellular phones and cars communicate with each other using sidelink signals. Cellular phones and smart home devices can communicate without relaying communication signals through base stations.

[0036] In some embodiments, the terminal device may be a station (ST) in a WLAN. In some embodiments, the terminal device may be a cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA) device, handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, in-vehicle device, wearable device, terminal device in a next-generation communication system (e.g., NR system), or terminal device in a future public land mobile network (PLMN) network, etc.

[0037] The network device in this application embodiment can be a device for communicating with a terminal device, and can also be referred to as an access network device or a radio access network device. For example, the network device can be a base station. In this application embodiment, the network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station (MeNB), secondary station (SeNB), multi-mode radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), location node, network communication equipment, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, a device that performs base station functions in D2D, V2X, and M2M communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. A base station can support networks using the same or different access technologies. The embodiments of this application do not limit the specific technologies or device forms used in the network equipment.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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).

[0042] In this embodiment, the network device can provide services to a cell. The terminal device communicates with the network device through the transmission resources (e.g., frequency domain resources, or spectrum resources) used by the cell. The cell can be the cell corresponding to the network device (e.g., a base station). The cell can belong to a macro base station or to a base station corresponding to a small cell. The small cell can include: metro cell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage area and low transmission power, and are suitable for providing high-speed data transmission services.

[0043] It should be understood that devices with communication functions in the network / system of this application embodiment can be referred to as communication devices. Taking the wireless communication system 100 shown in FIG1 as an example, the communication device may include network device 110 and terminal device 120 with communication functions, and may also include other devices in the wireless communication system 100, such as network controllers, mobility management entities and other network entities. This application embodiment does not limit this.

[0044] To facilitate understanding, some related technical knowledge involved in the embodiments of this application is first introduced. The following related technologies are optional solutions and can be arbitrarily combined with the technical solutions of the embodiments of this application, all of which fall within the protection scope of the embodiments of this application. The embodiments of this application include at least some of the following contents.

[0045] In wireless communication systems, terminal devices can acquire beams (also known as spatial beams) to establish a wireless connection to a wireless network. For example, the terminal device can perform beam scanning against available beams transmitted by the wireless network and measure beam properties such as signal strength and signal quality. For example, after performing beam scanning, the terminal device can also perform beam thinning to achieve a potentially narrower set of beams for wireless connection to the wireless network. Beaming not only enables wireless connectivity between the terminal device and the wireless network but also achieves high directional accuracy and high signal quality for wireless signal transmission between the terminal device and the wireless network.

[0046] With the development of communication technology, research on artificial intelligence (AI) / machine learning (ML) technologies based on the air interface of communication systems (e.g., NR systems) has become a research direction. The goals of this research include exploring how to enhance the advantages of the air interface. For example, enhancing support for AI / ML algorithms can improve the performance of the air interface. Similarly, enhancing support for AI / ML algorithms can reduce the complexity and / or overhead of the air interface.

[0047] Research into AI / ML technologies can also enhance beam management (BM) capabilities. As an example, AI / ML enhancements related to beam management can help reduce overhead and lower beam measurement and reporting latency. As another example, applying AI / ML models can predict beams to improve transmission efficiency at the air interface.

[0048] The entire process of augmenting AI / ML models includes model training, model inference, and model monitoring. During this process, after training, the AI / ML model can generate a set of outputs based on a set of inputs. The input can be a set of beam measurements, while the output can be a set of beams that are different from or larger than the inputs.

[0049] During the model inference process, AI / ML models can predict the optimal beam in a set of different / larger beam groups using a set of beam measurements.

[0050] In some embodiments, the AI / ML model may be located on the terminal device side or the terminal device may perform model training and / or model inference. This model may be referred to as a UE-side model. For example, the AI ​​model may be located on the terminal device, and the AI ​​model may be trained and / or its inference may be performed on or by the terminal device to generate the optimal beam.

[0051] As an example, a terminal device can use beams from set B (also called beam group B) as input to an ML model. This ML model can predict the optimal beam in set A (also called beam group A), which is not fully measured by the terminal device.

[0052] In the example above, set B can be the beam group that the terminal device first measures. Set B can be multiple beams transmitted by the base station (e.g., gNB). Each beam can correspond to a different direction or angle to cover multiple spatial directions. Each beam can also correspond to a measurement signal used to obtain measurement values, such as reference signal received power (RSRP). The role of set B is to provide the model with preliminary environmental information and channel conditions.

[0053] In the example above, set A can be the beam group that needs to be predicted. Set A typically has a larger number of beams than set B, or the beam orientation may be more concentrated. AI / ML models can predict the optimal beam in set A by measuring set B, thereby improving data transmission efficiency.

[0054] Optionally, the beams of set A and set B can be in the same frequency range. The selection of set B can be given by the base station or determined by the terminal equipment itself. The relationship between set A and set B can be: set A and set B are different (set B is not a subset of set A), or set B is a subset of set A (set A and set B are different), or set A and set B are the same. For the first two cases, set B can be transmitted simultaneously in the measurement window and the prediction window, or it can be transmitted only in the measurement window. The last case can save the reference signal (RS) transmission overhead, as set B, as a measurement resource, can be transmitted only in the measurement window.

[0055] Alternatively, 64 or more beams can be used as the size of the beam set A. For future-oriented networks, network devices will be able to transmit 64 more highly directional narrow beams. More narrow beams can also scan a larger set A; for example, the number of beams in set A could be as high as 256.

[0056] Optionally, the network device may transmit a channel state information-reference signal (CSI-RS) or a synchronization signal block (SSB) as a reference signal. It should be understood that SSB can also represent a synchronization signal / physical broadcast channel block (SS / PBCH block). The SSB includes a primary synchronization signal (PSS) and a secondary synchronization signal (SSS).

[0057] Optionally, the terminal device estimates the channel quality of each beam by measuring the RSRP received from the CSI-RS / SSS.

[0058] Optionally, during model training, the AI / ML model can adjust its weights by minimizing the loss function so that the model can accurately predict the optimal beam in set A from the RSRP measurements of set B.

[0059] In some embodiments, AI / ML can be located at the network device (such as a base station) or the network device can perform model training and / or model inference. This model can be referred to as a network-side model (NW-side model). For example, the AI ​​model is located at the base station, and the training of the AI ​​model and / or the inference of the AI ​​model can be performed at the base station or by the base station to generate the optimal beam.

[0060] In some embodiments, the network can have complete control over the data collection process for model training on the terminal device side, including the initiation, termination, and management of data collection and data transmission.

[0061] In the model monitoring process, AI / ML model monitoring is used for at least the following purposes: model activation, deactivation, selection, switching, rollback, and updating (including retraining). Model monitoring can also be referred to as the process of monitoring the inference performance of AI / ML models. There is always a time interval between the model's training and inference processes. When radio parameters / conditions change in the network, the likelihood of errors occurring during the model's inference phase is higher; therefore, it is necessary to continuously correct and train the model based on the results of model monitoring. Furthermore, in some cases, model monitoring may be required before using the model in a new radio environment / conditions / parameters.

[0062] As an example, due to the different mobile environments, each model has a model identifier (ID) to facilitate model identification.

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

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

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

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

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

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

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

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

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

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

[0073] The above, along with Figure 2, illustrates the process of processing the model when it is located on the terminal device side. To complete this process, the terminal device also needs to collect and analyze data to perform model training. The model inference process is primarily used for beam prediction.

[0074] In relevant scenarios, terminal devices can support beam prediction in the spatial and / or temporal domains, namely BM-Case1 and / or BM-Case2. Based on AI / ML enhancements, beam prediction in the spatial domain (BM-Case1) and beam prediction in the temporal domain (BM-Case2) can reduce the overhead of terminal devices and lower beam measurement and reporting latency.

[0075] BM-Case 1 performs spatial domain downlink (DL) beam prediction on set A based on measurements from set B. For BM-case 1, measurements based on set B of beams are used as model input to predict the Top-1 / Top-K beams in set A.

[0076] BM-Case2 performs time-domain DL beam prediction on set A based on historical measurements from set B. For BM-Case2, measurements based on Set B of beams at historic time instances can be used as model input to predict the time-domain DL beams of set A. Predictions of DL Tx beams and DL Tx / Rx beams can also be used to evaluate prediction performance.

[0077] For BM-Case1 and BM-Case2, the terminal device can report the prediction results to the NW based on the output of the terminal device-side model, or the NW can predict the Top-1 / Top-K beams based on the measurement reports of the NW-side model set B.

[0078] Taking the terminal device-side model as an example, the training and inference process of the terminal device-side AI / ML model can use the traditional transmission configuration indicator (TCI) state mechanism to perform beam indication. Optionally, the terminal device can report the measurement results of more than four beams in a single reporting instance.

[0079] As an example, beam indication is crucial information during beam management inference. After the terminal device reports the Top-K predicted beams, the NW will further indicate the beams used for the second-step measurement, or the terminal device can directly trigger the second measurement. For BM-Case2, the model needs to obtain the Top-K beams corresponding to multiple time instances; therefore, the beam indication on the network device side needs to consider time information. For example, for BM-Case2 with an AI / ML model on the terminal device side, the terminal device can report the following information from the AI / ML model inference to the NW in a reporting example: the beams used for N future times based on the AI / ML model inference output; the timestamp information corresponding to the reported beams; and information about the measurement values ​​for multiple past time instances.

[0080] As an example, the TCI status can be used to indicate the beam information used for transmission on the physical downlink shared channel (PDSCH) or the physical downlink control channel (PDCCH).

[0081] As an example, in a 5G NR system, the TCI state defines the downlink beam selection and transmission configuration. The primary function of the TCI state is to help terminal devices understand the beam or antenna configuration used by the base station (e.g., gNB) when transmitting on certain physical channels (such as PDSCH, PDCCH). Each TCI state corresponds to a specific beam configuration. Generally, each TCI state is associated with one or more specific beams (via QCL relationships). For example, for a unified TCI framework, if there is no PDSCH transmission during the optimal beam change between the base station and the terminal device, the network will indicate the corresponding TCI state to the terminal device via downlink control information (DCI). If a PDSCH is available for transmission, the base station will send a DCI with downlink (DL) allocation to the terminal device, and the TCI field will always be present in the DCI.

[0082] Optionally, network devices can transmit control information via PDCCH, that is, transmit DCI via PDCCH.

[0083] QCL relations can also be called quasi-co-location relations. To ensure the consistency of the demodulation reference signal (DMRS) of PDSCH / PDCCH in NR across different timestamps, the mechanism of QCL relations can be used, especially during model training and inference.

[0084] The following describes the QCL configuration used to indicate QCL relationships in beam indication.

[0085] QCL relationships are typically used to characterize the channel characteristic similarity between certain transmit resources (such as CSI-RS resources). Through QCL configuration, terminal devices can use the same set of measurements to infer the channel state of multiple resources without requiring independent measurements and evaluations for each beam. A QCL relationship defines the similarity of channel characteristics between two (or more) beams or resources in terms of space, frequency, time, etc. In other words, when two or more beams have a QCL relationship, their channel characteristics are similar.

[0086] In some embodiments, QCL is typically defined across several dimensions: delay spread, angle spread, and Doppler spread. Delay spread refers to the fact that the arrival times of two beams are very similar, allowing them to be processed in the same time domain. Angle spread refers to the fact that the arrival angles of the signal sources are almost identical, allowing beams to share spatial processing. Doppler spread refers to the fact that, due to similar signal source velocities, the Doppler frequency shifts are similar, allowing them to share frequency domain processing. In beam management, if two resources have the same QCL level in these characteristics, the terminal device can infer that their channel states are similar, thus eliminating the need to measure the channel state of each beam individually.

[0087] In some embodiments, for a set of antenna ports, the QCL type can be used to indicate which channel properties are common. For example, the various QCL types supported by the protocol can be used to indicate the QCL relationship between the DMRS and the tracking reference signal (TRS) in the PDSCH.

[0088] As an example, for a given QCL association, at most one or two QCL types can be used to indicate the QCL relationship. When using two QCL types, the same RS can be used to indicate the QCL. Table 1 defines four different QCL types.

[0089] Table 1

[0090] As shown in Table 1, QCL types can be defined as QCL Type A, QCL Type B, QCL Type C, and QCL Type D. Referring to Table 1, QCL Type A indicates common Doppler shift, Doppler spread, average delay, and delay spread. QCL Type B indicates common Doppler shift and Doppler spread. QCL Type C indicates common average delay and Doppler shift. QCL Type D indicates common spatial Rx parameter.

[0091] Optionally, the spatial receiver parameters may include beamforming properties of the downlink received signal, such as the main angle of arrival of the signal, the average angle of arrival at the terminal device, or other beamforming properties.

[0092] Optionally, QCL information can help the terminal device perform beam tracking or time / frequency offset tracking, as well as demodulation. For example, beam tracking can be performed using QCL type D. Time / frequency offset tracking can be performed using QCL types A / B / C.

[0093] As mentioned earlier, the training and inference processes of AI / ML models involve two beam sets, set A and set B. The beams in set A and set B can have a certain QCL relationship. For example, during training, the beams in set A have a QCL relationship with the beams in set A during the inference process. Similarly, during training, the beams in set B have a QCL relationship with the beams in set B during the inference process.

[0094] As an example, when performing model training and inference based on QCL, a QCL type can be configured for the resources of each beam in set A and its associated transmit beam. During training and inference, the beams used by network devices for set A have similar channel characteristics in the spatial, temporal, and frequency domains. Because the beam characteristics remain consistent, the channel state of the CSI-RS resources measured by the terminal device during the training phase can be used during the inference phase. For resources in set B, the terminal device can also assume that the transmit beams used during training and inference have the same QCL relationship. The beam measurement results from the training phase can be directly applied to the inference phase.

[0095] As an example, when the transmission (Tx) beams of a network device have the QCL relationships shown in Table 1, consistent channel characteristics can be ensured. For ease of understanding, the QCL relationships of set B and set A beams in Figure 3 are illustrated below.

[0096] Referring to Figure 3, during model training, the beam in set A is A′. j Where 1≤j≤8; the beam in set B is B′. k Where 1 ≤ k ≤ 3. During model inference, the beam in set A is A. j The beam in set B is B k As shown in Figure 3, the beam A′ in model training j Beam A in model inference j The channel characteristics are similar; beam B′ in model training k Beam B in model inference k The channel characteristics are similar. That is, during training, beam A′... j Beam A during inference j Having a QCL relationship, beam B′ during training k During the reasoning period B k It has a QCL relationship.

[0097] The above section, with reference to Figures 2 and 3, illustrates the process of beam management based on AI / ML models and the QCL relationships between beams. Enhanced beam management based on AI / ML still faces some issues that require further research and resolution.

[0098] As an example, when an end device uses AI algorithms or ML to process beams detected and measured from a wireless network to infer other beams that may have higher strength and / or higher quality, the end device needs to ensure the consistency of the model between the training and inference phases. As mentioned earlier, there is a time interval between the training and inference phases, and changes in radio parameters / conditions can lead to errors in the inference phase. For example, in a beam prediction use case, the end device may use a limited set of beam measurements (such as beam group B) as input to the ML model. When the ML model predicts the best or optimal beam from a set of beams that the end device has not fully measured (such as beam group A), the likelihood of errors occurring in the model's inference phase is higher. This is because during the time interval between the model training and model inference processes, the network's radio parameters / conditions may change, resulting in a higher error rate.

[0099] As an example, when introducing QCL relationships, the various QCL types corresponding to traditional QCL relationships may not guarantee beam consistency between model training and model inference. This is because, in some scenarios, the elements of traditional QCL types can change rapidly. When QCL elements change, the change in QCL relationships triggers a new beam set, and the consistency of beam order / index during model training and model inference may not be guaranteed, or even the consistency of beam shape may be compromised, thus requiring model updates. For example, in scenarios where terminal devices move at high speeds, changes in geographical characteristics will lead to rapid changes in Doppler frequency shift. Once the Doppler frequency shift changes, the model trained based on the previous beam set needs to be updated, but frequent model updates are not conducive to model-based beam prediction. Therefore, beam order / index consistency and beam shape consistency cannot be guaranteed by relying on existing QCL types (such as QCL type D).

[0100] As an example, if the terminal device is moving at high speed, the optimal beam between the network device and the terminal device may change frequently, and the network needs to send DCIs frequently to indicate the new TCI status, resulting in high overhead.

[0101] As an example, in the relevant 3rd generation partnership project (3GPP) standard, the maximum number of trigger states for non-periodic CSI reports regarding TCI states is 128. This number includes beam reports and other triggers. However, the optimal beam combinations output by the model far exceed this value. For example, if there are 32 beams in set A, and the model output is the top-4 predicted beams in set A, then all possible combinations of the AI / ML output are... It is impossible for the network to configure all possible combinations of 4 beams in set A, which also introduces complexity to the network triggering the second round of beam scanning of the Top-4 beams.

[0102] Based on this, embodiments of this application propose a method for wireless communication. In this method, a terminal device can determine the beam set for model training and / or model inference based on a first quasi-co-location (QCL) relationship in a first indication information, and can also determine multiple optimal beams in the prediction result based on the first QCL relationship. Wherein, when the first QCL relationship is used to determine the beam set, the element corresponding to the first QCL relationship includes the ID of the beam set, in order to more accurately maintain beam consistency, thereby improving prediction accuracy.

[0103] The method for wireless communication proposed in this application will be described in detail below with reference to Figure 4. Figure 4 is presented from the perspective of the interaction between the first device and the second device.

[0104] The first device can be any of the terminal devices described above, or it can include any type of terminal device. For example, the first device is a UE (User Equipment). Alternatively, the first device can include a terminal device and any processing device for beam prediction.

[0105] In some embodiments, the first device supports functional enhancements based on AI / ML operations. For example, the first device has the capability to enhance beam management based on AI / ML operations.

[0106] In some embodiments, a first model is deployed on the first device to perform beam prediction. When the second device is a network device, the first device performs DL beam prediction. When the second device is a terminal device, the first device performs side-travel beam prediction.

[0107] As an example, the first model is a model that supports AI or ML algorithms; that is, the first model is an AI / ML model.

[0108] As an example, the beam prediction implemented by the first model can be BM-Case1 as mentioned above, or BM-Case2, or other beam prediction types in the future, which are not limited here.

[0109] In some embodiments, a first model is deployed on the first device side. The first model may not be on the terminal device, but on a server that communicates with the terminal device. For example, the first model is on an over-the-top (OTT) server that communicates directly with the terminal device.

[0110] The second device can be any network device communicating with the first device, or it can be a terminal device communicating with the first device. When the first device is within the coverage area of ​​a network device, the second device can be a network device. In a side-by-side communication system, when the first device communicates with other terminal devices, the second device can be one of those other terminal devices.

[0111] In some embodiments, the second device can monitor the process by which the first device processes the first model. For example, the second device can determine whether the first model is currently in the training or inference phase based on a report sent by the first device.

[0112] In some embodiments, the second device supports AI / ML operations. The first model may be deployed on the second device.

[0113] In some embodiments, the second device may send multiple beams to the first device multiple times to enable the first device to perform measurements and to train and infer the first model based on the measurement results.

[0114] In the above embodiments, regardless of whether the first model is deployed on the terminal device side or the network device side, the first model can be one of multiple models deployed on that side. Multiple models can be used to predict the transmission beams of different scenarios or different beam transmitting devices.

[0115] Referring to Figure 4, in step S410, the first device receives first indication information. As an example, the first device may receive first indication information sent by a network device (second device). As an example, the first device may receive first indication information indicating a higher-layer signaling layer.

[0116] The first indication information is used to indicate a first QCL relationship. As an example, the first indication information can indicate that the QCL relationship of a beam or beam resource is a first QCL relationship. For instance, the first indication information is used to indicate that a first beam or first beam resource has a first QCL relationship. As another example, the first indication information is used to indicate that multiple beams or multiple beam resources have a first QCL relationship.

[0117] In some embodiments, the first indication information is used to indicate that all beams in the beam set have a first QCL relationship. This beam set may be a beam set associated with the training and inference process of the first model. For example, the beam set with the first QCL relationship may be set A or set B as described above, where set B may be referred to as the first beam set and set A may be referred to as the second beam set.

[0118] In some embodiments, the first indication information is an indication of beam transmission configuration; that is, the first indication information may include TCI information. For example, the first indication information may be TCI information to indicate the TCI status of one or more beams. For example, the first indication information may be first TCI information. Alternatively, the first indication information may include TCI information to indicate the TCI status and other information. The TCI status of one or more beams in the first indication information will be described in detail below with reference to Figure 5, and will not be elaborated further here.

[0119] In some embodiments, the first indication information may be carried in control signaling. As an example, the first indication information may be carried in one of the following: DCI (Digital Control Information) or Radio Resource Control (RRC) signaling. For example, a network device may transmit indication information for one or more beams in DCI format. Alternatively, a network device may transmit a beam indication via RRC signaling, which may be associated with multiple TCI states.

[0120] The elements of the first QCL relationship can refer to one or more elements used to describe the first QCL relationship. These one or more elements can represent beam characteristics or channel or spatial characteristics of beam resources. That is, the first indication information can indicate, based on one or more elements, which characteristics of the beam are similar or related to the first QCL relationship of the beam.

[0121] In some embodiments, the elements of the first QCL relation include an identifier for the beam set, i.e., a beam set ID. This beam set is used for model training and / or model inference of the first model. As mentioned above, traditional QCL types cannot guarantee the consistency of beam order / index within the beam set. To achieve consistency between training and inference, new elements need to be added to the QCL relation or a new QCL type needs to be configured. When the elements of the first QCL relation include the beam set ID, using this QCL framework in the AI / ML beam management mechanism can ensure consistency between training and inference, and also ensure beam consistency corresponding to different timestamps.

[0122] As an example, the aforementioned beam set could be the first beam set described above, or it could be the second beam set, or it could be both the first and second beam sets. The aforementioned beam set could also be one or more beam sets from different processing stages of the model.

[0123] As an example, the ID of a beam set can also be called beam ID or transmission ID.

[0124] As an example, the identifier for a beam set can be an association ID between beam sets. Based on the same association ID and resources in the same set A (or set B), consistency in beam indexing / sorting can be achieved. That is, the assumption made by the first device about transmit beams with the same association ID and the same resource index can replace the first device's assumptions about beam shape consistency and beam index / sorting consistency. For example, for each resource set A, based on the same association ID in training and inference, it can be assumed that the transmit beams used in training and inference have a certain QCL relationship (first QCL relationship). Similarly, for each resource set B, based on the same association ID, it can also be assumed that the transmit beams used in training and inference have a first QCL relationship.

[0125] As an example, the elements of the first QCL relationship, including the beam set ID, can implement a beam ID tracking mechanism. This beam ID tracking mechanism ensures that the first device knows which beam or transmission it is receiving, even when the signal is slightly adjusted due to channel variations. This beam ID tracking mechanism can also maintain beam identity across time slots to provide continuity in signal processing and demodulation. Therefore, the first device can maintain a consistent understanding of the same beam at different time stamps based on the first QCL relationship; that is, it ensures that the channel properties of the same beam remain consistent across different time stamps, especially in scenarios involving Doppler effects and delay evolution.

[0126] In the above example, the beam ID tracking mechanism may involve explicit beam or CSI-RS resource identifiers carried or embedded in the DMRS signal via higher-layer signaling. This indication method ensures that the first device maintains a consistent understanding of the transmission source even during beam switching or reconfiguration. Furthermore, since the beam's transmission identity is guaranteed over time, the first device can accurately track a specific beam regardless of changes in channel conditions or minor beam adjustments. Even with minor changes in transmission (such as Doppler shift, channel variations, etc.), the beam can maintain a consistent transmission identity, which is crucial for long-duration data transmission and high-mobility scenarios.

[0127] In some embodiments, the elements of the first QCL relation may further include one or more of the following: time instances associated with model training and / or model inference; spatial filter parameters associated with beam sets.

[0128] As an example, temporal instances associated with model training and / or model inference can be used to determine the temporal resources of a beam, thereby determining beam information during model training or model inference.

[0129] As an example, spatial filter parameters can refer to spatial receiver parameters and / or spatial transmitter parameters. Spatial filter parameters associated with beam sets include ID spatial parameters associated with the beam set ID.

[0130] As an example, when the elements of the first QCL relation include spatial filter parameters, the same spatial filter is used for both model training and model inference. That is, a spatial emission filter solution based on beam set IDs can ensure beam consistency. For instance, for each resource set A, the same association ID in model training and model inference can correspond to the network device using the same spatial Tx filter during both processes. Similarly, for each resource set B, the first device can assume that the network device used the same spatial Tx filter during both model training and model inference. From a practical perspective, using the same spatial Tx filter in both inference and training helps ensure beam consistency.

[0131] It should be noted that the elements indicating the first QCL relationship may include not only the beam set ID, time instance, and spatial filter parameters mentioned above, but also elements from various existing QCL types, as well as other elements associated with the beam set ID. In some scenarios, the elements of the first QCL relationship may only include elements from traditional QCL types, which will be explained later in conjunction with the first operation in step S420.

[0132] In some embodiments, the first QCL relationship can be indicated by one or more QCL types. These one or more QCL types can be the traditional QCL types in Table 1, or newly designed QCL types for beam consistency. The four traditional QCL types are QCL type A, QCL type B, QCL type C, and QCL type D in Table 1. Furthermore, to ensure beam consistency across different time stamps, a new QCL type, QCL type E, can be designed to indicate the first QCL relationship. QCL type E can be a type that achieves temporal and spatial consistency to ensure robust beam tracking and state awareness across time slots.

[0133] As an example, the first QCL relationship can be indicated by a QCL type, namely the first QCL type.

[0134] As an example, a first QCL relationship can be indicated by multiple QCL types. For instance, a first QCL relationship can be indicated by two QCL types. The two QCL types can include a first QCL type and a second QCL type.

[0135] As an example, QCL type E can integrate elements of existing QCL types and then add additional mechanisms to support timestamp-level consistency of channel attributes and beam identifiers.

[0136] As an example, the QCL type E can be described using new elements. These new elements can include the beam set ID mentioned above, as well as temporal instances related to model training and / or model inference, and spatial filter parameters related to the beam set.

[0137] In the example above, the newly added QCL type E can guarantee temporal and spatial consistency descriptions through IDs. When QCL type E includes beam set IDs, time instances, and spatial filter parameters, it integrates temporal (time instance-based) and spatial (beam-based) consistency mechanisms to ensure ID consistency for a given transmission across multiple timestamps. In highly mobile environments (such as vehicles and high-speed trains) with frequent Doppler effects and beam switching, maintaining consistent beam identifiers across timestamps is crucial for stable data transmission. For example, for beam tracking in multi-slot PDSCH, when PDSCH data spans multiple time slots, QCL type E can ensure that the first device can consistently demodulate the signal using the same beam identifier, thereby improving reliability. Similarly, when beam consistency across multiple frames is relatively important, QCL type E can ensure that the first device maintains a connection to a consistent beam, even if rapid reconfiguration is required due to signal congestion or beam scanning.

[0138] In the above example, QCL type E may include some or all of the elements indicating the first QCL relationship. For example, Table 2 shows several QCL types after the addition of QCL type E, where QCL type E includes all elements indicating the first QCL relationship.

[0139] Table 2

[0140] In Table 2, the new QCL type E ensures that the first device maintains a consistent transmission identity (ID) across different timestamps when dealing with changes in channel attributes, Doppler effects, and spatial variations. Over time, even as channel conditions change, consistent identification of beams or beam sets during model training and processing can be achieved by tracking the beam set ID.

[0141] As an example, instead of adding a new QCL type, elements such as the beam set ID, time instance, and spatial filter parameters included in the first QCL relationship can be integrated into an existing QCL type. When these elements are partially or fully integrated into QCL type A, QCL type B, QCL type C, or QCL type D, the first QCL relationship can not only capture traditional parameters such as Doppler frequency shift, delay spread, and spatial characteristics, but also introduce a new beam ID tracking mechanism.

[0142] In the above examples, multiple elements indicating the first QCL relationship can be added to QCL types A, B, C, and / or D in various combinations, thus forming multiple new QCL types. Tables 3 and 4 are used as examples below; it should be understood that the addition methods in Tables 3 and 4 are merely two examples and do not constitute a limitation.

[0143] In Table 3, multiple elements indicating the first QCL relationship are added to QCL type D to form a new QCL type D.

[0144] Table 3

[0145] In Table 4, multiple elements indicating the first QCL relationship are added to QCL type B, QCL type C, and QCL type D respectively, forming new QCL types B, QCL type C, and QCL type D.

[0146] Table 4

[0147] In some embodiments, a first QCL relationship can be indicated by a first QCL type. When multiple elements indicating a first QCL relationship are added to a conventional QCL type, the first QCL type can be one of a new QCL type A, QCL type B, QCL type C, or QCL type D that includes one of the multiple elements. When some or all of the elements indicating a first QCL relationship constitute QCL type E, the first QCL type can be QCL type E. Therefore, when a first QCL relationship is indicated by a first QCL type, the first QCL type is one of the following: QCL type A, QCL type B, QCL type C, QCL type D, and QCL type E. Wherein, QCL type A, QCL type B, QCL type C, and QCL type D are new QCL types with added new elements.

[0148] In some embodiments, a first QCL relationship can be indicated by multiple QCL types, such as a first QCL type and a second QCL type. In some scenarios, for a given QCL association, up to two QCL types can be used to indicate the QCL relationship. For both QCL types, the same RS can be used to indicate the QCL relationship.

[0149] As an example, the first QCL type may include some or all of the elements indicating the first QCL relationship, and the second QCL type may be a conventional QCL type. For example, when the first QCL type is QCL type E, the second QCL type includes at least one of conventional QCL types A, B, C, and D.

[0150] In the example above, QCL type E is configured to be used together with any one, any two, or all three types of QCL type B, QCL type C, and QCL type D to better indicate the first QCL relationship and ensure beam consistency.

[0151] As an example, for the DMRS of a PDSCH, the first device may expect the TCI status indication to be of the following QCL type. For example, in a non-zero power (NZP) CSI-RS resource set, this can be configured via the higher-level parameter trs-Info. This parameter can configure the QCL type A corresponding to the CSI-RS resource and, where applicable, the QCL type E for the same CSI-RS resource.

[0152] As an example, when multiple elements indicating the first QCL relationship are added to QCL type D, the CSI-RS resource configured in the NZP CSI-RS resource set via the higher-level parameter trs-Info corresponds to QCL type A, and QCL type D, where applicable, is configured with the same CSI-RS resource.

[0153] Referring again to Figure 4, in step S420, the first device performs a first operation based on the first QCL relationship. That is, when performing the first operation, the first device needs to consider whether the beam or beam set has the first QCL relationship. The first operation can be determining the beam set used for model training and / or model inference, determining multiple optimal beams (also called best beams) in the model prediction results, or determining both the beam set used for model training and / or model inference and multiple optimal beams in the model prediction results.

[0154] In some embodiments, when the elements of the first QCL relation include a beam set ID or other new elements, the first operation can be to determine the beam set for model training and / or model inference. That is, the first device can determine the beam set used for training and inference of the first model based on the first QCL relation including the beam set ID. By introducing the first QCL relation including the beam set ID, the first device can ensure beam consistency during model training and model inference, thereby improving prediction accuracy.

[0155] As an example, the first QCL relationship can be used to determine a first beam set (set B) and / or a second beam set (set A). That is, the first device can use the first QCL relationship to determine set B and / or set A.

[0156] As an example, during the model training and inference processes of the first model, the correlation can be represented by a first QCL relationship. For resources in sets A and B, having a first QCL relationship guarantees the correlation of beams during the model training and inference phases.

[0157] As an example, the beam sets used for model training and / or model inference also satisfy one or more of the following conditions: the first beam set used for model training and the first beam set used for model inference have a first QCL relationship; the second beam set used for model training and the second beam set used for model inference have a first QCL relationship; the first beam set used for model training and the second beam set used for model inference have a first QCL relationship; the first beam set used for model inference and the second beam set used for model inference have a first QCL relationship. As mentioned above, the first beam set is used to determine multiple optimal beams in the second beam set.

[0158] In some embodiments, the first operation may be to determine multiple optimal beams (e.g., K optimal beams, where K is a positive integer) from the model prediction results based on a first QCL relationship. The first QCL relationship may be a dynamic QCL relationship to ensure that the multiple optimal beams have the same or similar channel / spatial characteristics. For example, a dynamic QCL relationship may refer to the system dynamically adjusting the QCL relationship between different beams through channel measurements or AI / ML predictions. The dynamic nature of the QCL relationship lies in its ability to change with channel conditions. Network devices need to dynamically calculate and adjust the QCL state based on channel measurement results or AI / ML model updates.

[0159] As an example, multiple optimal beams share a first QCL relationship, which determines one or more of the following: multiple optimal beams correspond to the same channel characteristics; multiple optimal beams correspond to the same time delay characteristics; multiple optimal beams correspond to the same beam set identifier; multiple optimal beams correspond to the same spatial parameters or spatial filter parameters. Therefore, multiple optimal beams predicted by the AI / ML model can share some or all of the channel characteristics. In other words, when multiple optimal beams are determined based on the first QCL relationship, the first device can share channel information among the beams, thereby reducing the overhead of independent beam measurements. For example, for each combination of Top-K beams, the QCL relationship can be dynamically defined so that the first device can share CSI measurement results among multiple beams.

[0160] As an example, the first QCL relation can be used to output the K optimal beams in the second beam set from the first model output.

[0161] As an example, after the first model outputs the prediction information for all beams in the second beam set, the first QCL relation can be used by the first device to determine the K optimal beams in the second beam set. Through the estimation and calculation of the dynamic QCL relation, the network device can generate a new trigger state for each predicted Top-K beam combination and configure it to the first device along with the corresponding QCL relation.

[0162] It should be understood that when the first operation is to determine multiple optimal beams, the elements of the first QCL relation are unrestricted. For example, the elements of the first QCL relation may include at least one of the beam set ID, time instance, and spatial filter parameters mentioned above. Alternatively, the elements of the first QCL relation may not include new elements, and the first device may determine the optimal beam simply based on conventional QCL elements.

[0163] As an example, AI / ML models can predict Top-K beams based on historical data and real-time measurements, thereby reducing unnecessary beam scanning. Dynamic QCL relationships allow the system to flexibly adjust the correlation between beams based on channel changes and the movement patterns of the first device, improving the system's adaptability. For instance, the AI / ML model located on the first device side can use historical CSI-RS, RSRP measurements, and / or environmental information (such as geographic location information, movement speed, etc.) to predict the most likely Top-K beam in the second beam set.

[0164] As an example, the predicted Top-K beam can be represented as: B pred ={B1, B2, B3, ... B K Based on the predicted Top-K beams, network devices can dynamically determine the QCL relationship between these beams through measurement or channel model analysis. It is assumed that the QCL relationship between beams can be determined based on their channel characteristics (such as angle, delay, Doppler shift, etc.). For example, if multiple beams have similar angular distributions and small or less than a certain threshold delay differences along their propagation paths, then these beams may have a QCL relationship.

[0165] In the example above, the first QCL relationship at time t can be expressed as:

[0166] Among them, B i B j Belongs to B pred B i and B j Having the first QCL relationship indicates that the two beams share the same channel characteristics.

[0167] As an example, multiple optimal beams include a first beam and a second beam, where the difference between the two channel characteristics corresponding to the first beam and the second beam is less than a first threshold. The first threshold is, for example, a threshold δ. If the channel difference between the beams is less than δ, then the two beams can be determined to have a first QCL relationship.

[0168] In some embodiments, the introduction of a first QCL relationship can serve as a new trigger state. Through the calculation of dynamic QCL relationships, the network device can generate a new trigger state for each predicted Top-K beam combination and configure it to the first device along with the corresponding QCL relationship. The new CSI trigger state can include not only the Top-K beam combinations but also the dynamic QCL relationships of these beams.

[0169] As an example, network devices can periodically or non-periodically trigger Top-K beam measurements based on timing or events (such as changes in the speed of the first device or changes in channel conditions) via PDCCH or other control signaling.

[0170] In some embodiments, the first QCL relationship can be used to trigger the first device to perform beam measurements. That is, the first device can perform CSI measurements based on a newly configured trigger state. By introducing a new trigger state with a dynamic QCL relationship, the network device can efficiently predict and measure Top-K beams, reducing signaling overhead and the complexity of CSI measurements. After completing the CSI measurements, the first device feeds back CSI reports for these beams to the network device.

[0171] As an example, determining multiple optimal beams based on the first QCL relationship can be equivalent to introducing a new triggering state with a dynamic QCL relationship for the predicted Top-K beams.

[0172] As an example, when multiple optimal beams have a first QCL relationship at the current time, the first device measures one of the multiple optimal beams, thereby determining the measurement results of multiple optimal beams based on the measurement result of one beam. Since the QCL relationship can indicate that the beams have similar spatial characteristics (such as angle or path delay), the first device can infer the channel state of the other beams among the K optimal beams based on the CSI measurement of one beam. Therefore, determining and measuring multiple optimal beams based on the first QCL relationship can reduce the number of independent CSI measurements, that is, reduce the number of beams that need to be measured independently.

[0173] As an example, when multiple optimal beams do not have a first QCL relationship at the current moment, the first device updates the multiple optimal beams and measures the updated multiple optimal beams. The first device updates the multiple optimal beams so that the updated multiple optimal beams have a first QCL relationship. It should be noted that the network device can also readjust the QCL relationship of the Top-K beams based on periodic channel measurement results or beam updates predicted by AI models. For example, as channel conditions or the first device's movement mode change, the first QCL relationship can be updated periodically or based on event triggers. Furthermore, when the network device detects a significant change in the channel environment (such as an increase in the first device's speed, deterioration of channel quality, etc.), it can immediately update the first QCL relationship and notify the first device via control signaling. When the first QCL relationship is a dynamically adjustable QCL relationship, the system can adaptively respond to changes in the channel environment and the first device's movement mode, thereby improving the accuracy of beam management and selection.

[0174] The preceding text, with reference to Figure 4, described several new elements indicating the first QCL relationship and a method for determining a beam set or predicting multiple optimal beams based on the first QCL relationship. The first QCL relationship can be indicated by TCI information. The TCI information, including TCI states, can be viewed as a specific set of beam or channel configurations used to indicate which beam the first device should use for communication in a specific time instance. In some embodiments, maintaining the consistency of TCI states ensures that TCI states used at different timestamps are associated with the same CSI-RS resource, thereby enabling the first device to demodulate DMRS using the same channel estimation when processing transmissions at different timestamps.

[0175] In some embodiments, with NZP CSI-RS resources configured with trs-Info, the first device can rely on these resources to infer the time-frequency characteristics of the transmission beam (e.g., via QCL type A in Table 2) and potential spatial characteristics (e.g., via QCL type D / QCL type E in Table 2). During inference, the network device can indicate the same CSI-RS resources to the PDSCH as before, and the first device can utilize the already trained beam information without having to re-perform channel measurements and estimates, thus ensuring consistency. If the CSI-RS resources are configured with the higher-layer parameter trs-Info or are reconfigured, the first device can maintain a consistent channel estimate across multiple timestamps by using these reconfigured CSI-RS resources. For example, across multiple timestamps, if the same set of NZP CSI-RS resources is used, and the CSI-RS resources in that set have established channel correlations via QCL type A and QCL type D / QCL type E, the first device can maintain a consistent channel model across these timestamps.

[0176] In some embodiments, when the higher-level parameter trs-Info is not configured, the first device can ensure consistency between different timestamps by combining QCL type E in Table 2 with traditional QCL types. That is, based on the beam set ID, time instance, and spatial filter parameters indicating the first QCL relationship, consistent beam transmission characteristics can still be guaranteed even without repetition of higher-level parameters.

[0177] To reduce transmission overhead, a single beam indication can be used to indicate the TCI status of multiple time instances. That is, the first indication information is an indication of the beam transmission configuration, including multiple transmission configuration indications for the TCI status corresponding to multiple time instances. Especially for BM-Case2, indicating the TCI status of multiple time instances through a single TCI indication signaling can reduce the transmission frequency of DCI without DL allocation, thereby reducing DCI overhead.

[0178] In some embodiments, a network device can provide a beam indication via control signaling, which may be associated with multiple TCI states. This control signaling is also known as the first indication information. With this first indication information, the network device can manage beam selection more flexibly without needing to frequently indicate the detailed configuration of each beam.

[0179] As mentioned earlier, the first indication information can be carried in PDCCH or RRC signaling. RRC signaling can be used for configuration on a longer time scale. For example, network devices can use RRC signaling to pre-configure the usage time of these beams in periodic reports, such as indicating the specific effective time of the TCI status (e.g., a specific time slot or symbol). Alternatively, network devices can use dynamic PDCCH signaling to indicate the beam usage time slot and the TCI status used by the first device in the corresponding time slot during actual transmission.

[0180] In some embodiments, the network device can indicate different TCI states that can be applied in different time instances through first indication information. That is, the network device can notify the first device of the application time slots of each TCI state in different time instances in some way.

[0181] As an example, the system may predefine or configure signaling to indicate time-based application instances for certain beams to the first device. For instance, the network device can use a predefined schedule to indicate the TCI state corresponding to different time instances. In this way, the network device can use different TCI states in different time instances. For each TCI state used in different time instances, the first device needs to know the specific beam corresponding to each TCI state and its effective time.

[0182] As an example, when a network device uses first indication information to indicate multiple TCI states for multiple time instances, the beam application time for each TCI state should be predefined or indicated to the first device. For example, the time window for the first device to perform beam prediction can be configured by the network.

[0183] As an example, the first device can determine the effective time of each TCI state through a timing synchronization mechanism. For instance, during system initialization, the network device can configure a set of beams and their corresponding TCI states via RRC signaling, and instruct different time instances to use these beams. Through predefined time application rules, the system can predefine the mapping rules between a beam indication and different beams in multiple time instances via RRC signaling. Furthermore, the network device can specify that a beam corresponds to different TCI states within a specific time subframe or time slot. After receiving the first indication information, the first device can determine the applied TCI state in each time instance based on the configured rules or signaling, and will automatically apply the corresponding TCI state according to the time instance, without needing to receive a separate beam indication each time.

[0184] As an example, the first indication information can be used by the first device to determine a TCI status table. This TCI status table can include the beam and activation time corresponding to each of multiple TCI states. For instance, the first device can maintain a TCI status table that records the beam and activation time corresponding to each TCI state.

[0185] In the example above, when a network device sends a beam indication via control signaling, the first device can determine the beam that should be used in the current time slot by looking up the TCI status table. By associating a single beam indication with multiple TCI states, the network device can significantly reduce the overhead of frequent control signaling transmissions.

[0186] In the example above, when the beam indication sent by the network device is associated with multiple TCI states, the first device needs to determine which TCI states are present based on the network device's indication and confirm the applicable time according to the TCI state table. For example, for beams in the first beam set, the first device can automatically switch to the beam used by the corresponding TCI state based on the time instance.

[0187] As an example, each beam indicator can be reused across multiple time instances to reduce the need for individual indicators for each time slot or beam, and also to ensure consistency of IDs between the training and inference processes.

[0188] In some embodiments, the first indication information can associate a single beam indication with different beams in multiple time instances. Multiple TCI states in the first indication information can correspond to multiple beams or a single beam. As an example, multiple TCI states correspond one-to-one with multiple beams. As an example, at least two of the multiple TCI states correspond to one beam.

[0189] As an example, multiple beams corresponding to multiple TCIs can be the multiple optimal beams mentioned above.

[0190] In some embodiments, multiple TCI states correspond to multiple time instance beams. Before the first device applies a beam for a particular time instance, the network device may decide whether to change the TCI state of the Tx beam used for transmission.

[0191] To facilitate understanding, the following explanation, in conjunction with Figure 5, illustrates a scenario where multiple TCI states may change. Referring to Figure 5, the AI / ML model can predict the optimal beam for four future time instances T5, T6, T7, and T8 based on measurement results at time points T1, T2, T3, and T4. After model inference, the network can send TCI indication 1 to notify the first device of the multiple TCI states at T5, T6, T7, and T8. If the network decides to change the TCI states of T7 and T8 before the beam application time of T7 and T8, the network will send TCI indication 2 to update the TCI states of T7 and T8.

[0192] In Figure 5, TCI status indicator 1 can be the first indication information, and TCI status indicator 2 can be the second indication information.

[0193] In some embodiments, some or all of the TCI states in the first indication information can be updated based on a dynamic indication. This dynamic indication can be referred to as the second indication information. The second indication information can be used to indicate that at least one of a plurality of TCI states has changed. As an example, the first device can receive the second indication information sent by the network device to determine the latest TCI state.

[0194] As an example, when at least one of the multiple TCI states changes, the first device receives second indication information, which is used by the first device to update at least one TCI state.

[0195] As an example, the second indication information can be carried in physical layer signaling. Physical layer signaling is, for example, the PDCCH. For instance, network devices can dynamically indicate which TCI state each time instance uses via physical layer signaling.

[0196] In some embodiments, the first device may send an uplink reference signal to the second device so that the second device can determine whether multiple TCI states in the first indication information have been adjusted. For example, when the second device is a network device, it may receive the uplink reference signal.

[0197] As an example, the uplink reference signal is, for instance, a sounding reference signal (SRS). The SRS can quickly reflect changes in channel conditions at the first device. Network devices can configure SRS resources for the first device, which can then periodically or on demand transmit SRS. SRS can be transmitted in multiple beam directions, helping network devices measure channel quality from different angles. SRS is typically transmitted via the uplink and can be transmitted across multiple antenna ports to provide network devices with complete channel state information. Network devices evaluate the uplink channel quality using the received SRS. Due to the symmetry between the uplink and downlink channels (especially in Time Division Duplex (TDD) systems), network devices can infer the downlink channel quality based on the SRS measurements.

[0198] As an example, a network device can use SRS to measure the channel of a first device and dynamically adjust the TCI state, thereby enhancing the accuracy and efficiency of beam indication. Dynamically adjusting the TCI state ensures that beam management follows channel changes. The network device can infer the channel conditions of the first device in different directions from the SRS measurement results, including parameters such as channel gain, delay, and Doppler spread in different beam directions. For example, based on the SRS measurement results, the network device can dynamically adjust the beam configuration associated with each TCI state. In other words, the network device can select appropriate beams based on channel measurement results and associate them with different TCI states. Furthermore, by analyzing the SRS signal, the network device can determine which beam directions provide the best channel quality for the first device.

[0199] As an example, a network device can notify a first device to update its TCI state via RRC or PDCCH signaling. Upon receiving the TCI state indication from the network device, the first device can use the appropriate beam for demodulation and decoding of data transmission according to the network device's configuration, thus determining the optimal first beam set. For instance, when the network device selects a new set of TCI states, the first device updates its reception configuration, enabling physical channels such as PDSCH to receive data using the updated beam direction. This mechanism allows for the management and optimization of multiple beams by binding multiple TCI states to different beams.

[0200] For example, by combining beam scanning and SRS feedback, network devices can always select the optimal first beam set and send it to the first device.

[0201] As an example, network devices can be configured to periodically send SRS to dynamically track channel changes and adjust the TCI state in real time. By updating the TCI state in a timely manner, it is possible to ensure that the downlink beam transmission is highly matched with the channel characteristics, especially in environments with high-speed movement or rapidly changing channels.

[0202] The method embodiments of this application have been described in detail above with reference to Figures 1 to 5. The apparatus embodiments of this application are described in detail below with reference to Figures 6 to 8. It should be understood that the descriptions of the apparatus embodiments correspond to the descriptions of the method embodiments; therefore, any parts not described in detail can be referred to the preceding method embodiments.

[0203] Figure 6 is a schematic block diagram of a wireless communication device according to an embodiment of this application. The device 600 can be any of the first devices described above. The first device can be a terminal device. The device 600 shown in Figure 6 includes a transceiver unit 610 and a processing unit 620.

[0204] The transceiver unit 610 can be used to receive first indication information, which is used to indicate a first QCL relationship; the processing unit 620 can be used to perform a first operation according to the first QCL relationship; wherein the first operation is one or more of the following: determining a beam set for model training and / or model inference, wherein the elements of the first QCL relationship include the identifier of the beam set; determining multiple optimal beams in the model prediction results.

[0205] Optionally, the first QCL relation may also include one or more of the following elements: temporal instances associated with model training and / or model inference; spatial filter parameters associated with beam sets.

[0206] Optionally, when the elements of the first QCL relation include spatial filter parameters, the model training and model inference correspond to the same spatial filter, respectively.

[0207] Optionally, the first QCL relationship is indicated by a first QCL type, which is one of the following: QCL type A, QCL type B, QCL type C, QCL type D, and QCL type E.

[0208] Optionally, the first QCL relationship is indicated by a first QCL type. When the first QCL type is QCL type E, the first QCL relationship is also indicated by a second QCL type, which includes at least one of QCL type A, QCL type B, QCL type C, and QCL type D.

[0209] Optionally, the beam sets used for model training and / or model inference also satisfy one or more of the following conditions: the first beam set used for model training and the first beam set used for model inference have a first QCL relationship; the second beam set used for model training and the second beam set used for model inference have a first QCL relationship; the first beam set used for model training and the second beam set used for model inference have a first QCL relationship; the first beam set used for model inference and the second beam set used for model inference have a first QCL relationship; wherein the first beam set is used to determine multiple optimal beams in the second beam set.

[0210] Optionally, the first indication information is an indication information for beam transmission configuration, and the first indication information includes multiple transmission configuration indication TCI states corresponding to multiple time instances.

[0211] Optionally, multiple TCI states correspond one-to-one with multiple beams, or at least two of the multiple TCI states correspond to one beam.

[0212] Optionally, the first indication information is used by the first device to determine the TCI status table, which includes the beam and effective time corresponding to each TCI status among multiple TCI statuses.

[0213] Optionally, the transceiver unit 610 is also configured to transmit an uplink reference signal, which is used to determine whether multiple TCI states need to be adjusted; when at least one of the multiple TCI states changes, it receives second indication information, which is used by the first device to update at least one TCI state.

[0214] Optionally, the second indication information is carried in physical layer signaling.

[0215] Optionally, the multiple optimal beams have a first QCL relationship, which is used to determine one or more of the following: the multiple optimal beams correspond to the same channel characteristics; the multiple optimal beams correspond to the same time delay characteristics; the multiple optimal beams correspond to the same beam set identifier; the multiple optimal beams correspond to the same spatial parameters or spatial filter parameters.

[0216] Optionally, the multiple optimal beams include a first beam and a second beam, and the difference between the two channel characteristics corresponding to the first beam and the second beam is less than a first threshold.

[0217] Optionally, the processing unit 620 is further configured to: measure one of the multiple optimal beams when the multiple optimal beams have a first QCL relationship at the current time; or, update the multiple optimal beams and measure the updated multiple optimal beams when the multiple optimal beams do not have a first QCL relationship at the current time.

[0218] Optionally, the first indication information is carried in one of the following: downlink control information or radio resource control signaling.

[0219] Optionally, the first operation is related to the first model, which is an artificial intelligence or machine learning model.

[0220] Figure 7 is a schematic block diagram of another device for wireless communication according to an embodiment of this application. The device 700 can be any of the second devices described above. The second device is a network device or a terminal device. The device 700 shown in Figure 7 includes a transceiver unit 710.

[0221] The transceiver unit 710 can be used to send first indication information to a first device. The first indication information is used to indicate a first QCL relationship, and the first QCL relationship is used by the first device to perform a first operation. The first operation is one or more of the following: determining a beam set for model training and / or model inference, wherein the elements of the first QCL relationship include an identifier of the beam set; determining multiple optimal beams in the model prediction results.

[0222] Optionally, the first QCL relation may also include one or more of the following elements: temporal instances associated with model training and / or model inference; spatial filter parameters associated with beam sets.

[0223] Optionally, when the elements of the first QCL relation include spatial filter parameters, the model training and model inference correspond to the same spatial filter, respectively.

[0224] Optionally, the first QCL relationship is indicated by a first QCL type, which is one of the following: QCL type A, QCL type B, QCL type C, QCL type D, and QCL type E.

[0225] Optionally, the first QCL relationship is indicated by a first QCL type. When the first QCL type is QCL type E, the first QCL relationship is also indicated by a second QCL type, which includes at least one of QCL type A, QCL type B, QCL type C, and QCL type D.

[0226] Optionally, the beam sets used for model training and / or model inference also satisfy one or more of the following conditions: the first beam set used for model training and the first beam set used for model inference have a first QCL relationship; the second beam set used for model training and the second beam set used for model inference have a first QCL relationship; the first beam set used for model training and the second beam set used for model inference have a first QCL relationship; the first beam set used for model inference and the second beam set used for model inference have a first QCL relationship; wherein the first beam set is used to determine multiple optimal beams in the second beam set.

[0227] Optionally, the first indication information is an indication information for beam transmission configuration, and the first indication information includes multiple transmission configuration indication TCI states corresponding to multiple time instances.

[0228] Optionally, multiple TCI states correspond one-to-one with multiple beams, or at least two of the multiple TCI states correspond to one beam.

[0229] Optionally, the first indication information is used by the first device to determine the TCI status table, which includes the beam and effective time corresponding to each TCI status among multiple TCI statuses.

[0230] Optionally, the transceiver unit 710 is also configured to receive an uplink reference signal, which is used to determine whether multiple TCI states need to be adjusted; when at least one of the multiple TCI states changes, a second indication message is sent, which is used by the first device to update at least one TCI state.

[0231] Optionally, the second indication information is carried in physical layer signaling.

[0232] Optionally, the multiple optimal beams have a first QCL relationship, which is used to determine one or more of the following: the multiple optimal beams correspond to the same channel characteristics; the multiple optimal beams correspond to the same time delay characteristics; the multiple optimal beams correspond to the same beam set identifier; the multiple optimal beams correspond to the same spatial parameters or spatial filter parameters.

[0233] Optionally, the multiple optimal beams include a first beam and a second beam, and the difference between the two channel characteristics corresponding to the first beam and the second beam is less than a first threshold.

[0234] Optionally, the first QCL relationship is also used to trigger the first device to perform beam measurement. When multiple optimal beams have a first QCL relationship at the current time, the protection measurement is performed on one of the multiple optimal beams; or, when multiple optimal beams do not have a first QCL relationship at the current time, the beam measurement is performed on the updated multiple optimal beams.

[0235] Optionally, the first indication information is carried in one of the following: downlink control information or radio resource control signaling.

[0236] Optionally, the first operation is related to the first model, which is an artificial intelligence or machine learning model.

[0237] Figure 8 is a schematic diagram of the structure of a communication device according to an embodiment of this application. The dashed lines in Figure 8 indicate that the unit or module is optional. This device 800 can be used to implement the methods described in the above method embodiments. Device 800 can be a chip, a terminal device, or a network device.

[0238] The apparatus 800 may include one or more processors 810. The processor 810 may support the apparatus 800 in implementing the methods described in the preceding method embodiments. The processor 810 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.

[0239] The apparatus 800 may further include one or more memories 820. The memories 820 store a program that can be executed by the processor 810, causing the processor 810 to perform the methods described in the preceding method embodiments. The memories 820 may be independent of the processor 810 or integrated within the processor 810.

[0240] The device 800 may also include a transceiver 830. The processor 810 can communicate with other devices or chips via the transceiver 830. For example, the processor 810 can send and receive data with other devices or chips via the transceiver 830.

[0241] This application also provides a computer-readable storage medium for storing a program. This computer-readable storage medium can be applied to a terminal device or network device provided in this application embodiment, and the program causes a computer to execute the methods performed by the terminal device or network device in the various embodiments of this application.

[0242] The computer-readable storage medium can be any available medium that a computer can read, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs, DVDs), or semiconductor media (e.g., solid-state disks, SSDs), etc.

[0243] This application also provides a computer program product. The computer program product includes a program. This computer program product can be applied to a terminal device or network device provided in the embodiments of this application, and the program causes a computer to execute the methods performed by the terminal device or network device in the various embodiments of this application.

[0244] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0245] This application also provides a computer program. This computer program can be applied to a terminal device or network device provided in this application, and the computer program causes the computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0246] In this application, the terms "system" and "network" are used interchangeably. Furthermore, the terminology used in this application is only for explaining specific embodiments of the application and is not intended to limit the application. The terms "first," "second," "third," and "fourth," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. In addition, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0247] 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.

[0248] In the embodiments of this application, the term "correspondence" may indicate a direct or indirect correspondence between two things, or an association between two things, or a relationship such as instruction and being instructed, configuration and being configured.

[0249] In the embodiments of this application, "predefined" or "preconfigured" can be implemented by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device (e.g., including terminal devices and network devices). This application does not limit the specific implementation method. For example, predefined can refer to what is defined in the protocol.

[0250] In the embodiments of this application, the term "protocol" may refer to standard protocols in the field of communications, such as LTE protocols, NR protocols, and related protocols applied in future communication systems. This application does not limit the scope of these protocols.

[0251] In the embodiments of this application, determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information.

[0252] 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.

[0253] In the embodiments of this application, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0254] 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.

[0255] 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.

[0256] 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.

[0257] 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

A method for wireless communication, characterized in that, include: The first device receives first indication information, which is used to indicate a first quasi-co-located QCL relationship; The first device performs the first operation based on the first QCL relationship; The first operation is one or more of the following: Determine a beam set for model training and / or model inference, wherein the elements of the first QCL relation include the identifier of the beam set; Identify multiple optimal beams in the model's prediction results. The method according to claim 1, characterized in that, The first QCL relationship also includes one or more of the following elements: Time instances associated with the model training and / or the model inference; Spatial filter parameters associated with the beam set. The method according to claim 2, characterized in that, When the elements of the first QCL relation include the spatial filter parameters, the model training and the model inference correspond to the same spatial filter, respectively. The method according to any one of claims 1-3 is characterized in that, The first QCL relationship is indicated by a first QCL type, which is one of the following: QCL type A, QCL type B, QCL type C, QCL type D, and QCL type E. The method according to any one of claims 1-3 is characterized in that, The first QCL relationship is indicated by a first QCL type. When the first QCL type is QCL type E, the first QCL relationship is also indicated by a second QCL type, which includes at least one of QCL type A, QCL type B, QCL type C and QCL type D. The method according to any one of claims 1-5 is characterized in that, The beam set used for model training and / or model inference also satisfies one or more of the following conditions: The first beam set used for model training and the first beam set used for model inference have the first QCL relationship; The second beam set used for model training and the second beam set used for model inference have the first QCL relationship; The first beam set and the second beam set used for model training have the first QCL relationship; The first beam set and the second beam set used for model inference have the first QCL relationship; The first beam set is used to determine multiple optimal beams in the second beam set. The method according to any one of claims 1-6, characterized in that, The first indication information is an indication information for beam transmission configuration, and the first indication information includes multiple transmission configuration indication TCI states corresponding to multiple time instances. The method according to claim 7, characterized in that, The plurality of TCI states correspond one-to-one with the plurality of beams, or at least two of the plurality of TCI states correspond to one beam. The method according to claim 7 or 8, characterized in that, The first indication information is used by the first device to determine the TCI status table, which includes the beam and activation time corresponding to each of the plurality of TCI statuses. The method according to any one of claims 7-9 is characterized in that, The method further includes: The first device sends an uplink reference signal, which is used to determine whether the plurality of TCI states should be adjusted. When at least one of the plurality of TCI states changes, the first device receives second indication information, which is used by the first device to update the at least one TCI state. The method according to claim 10, characterized in that, The second indication information is carried in physical layer signaling. The method according to any one of claims 1-11, characterized in that, The plurality of optimal beams have the first QCL relationship, which is used to determine one or more of the following: The multiple optimal beams correspond to the same channel characteristics; The multiple optimal beams correspond to the same time delay characteristics; The multiple optimal beams correspond to the same beam set identifier; The multiple optimal beams correspond to the same spatial parameters or spatial filter parameters. The method according to claim 12, characterized in that, The plurality of optimal beams include a first beam and a second beam, wherein the difference between the two channel characteristics corresponding to the first beam and the second beam is less than a first threshold. The method according to any one of claims 1-13 is characterized in that, The first QCL relationship is also used to trigger the first device to perform beam measurement, and the method further includes: When the plurality of optimal beams have the first QCL relationship at the current time, the first device measures one of the plurality of optimal beams; or... When the plurality of optimal beams do not have the first QCL relationship at the current time, the first device updates the plurality of optimal beams and measures the updated plurality of optimal beams. The method according to any one of claims 1-14 is characterized in that, The first indication information is carried in one of the following ways: Information includes: downlink control information and radio resource control signaling. The method according to any one of claims 1-15 is characterized in that, The first operation is related to the first model, which is an artificial intelligence or machine learning model. A method for wireless communication, characterized in that, include: The second device sends a first indication message to the first device. The first indication message is used to indicate a first quasi-co-address QCL relationship. The first QCL relationship is used by the first device to perform a first operation. The first operation is one or more of the following: Determine a beam set for model training and / or model inference, wherein the elements of the first QCL relation include the identifier of the beam set; Identify multiple optimal beams in the model's prediction results. The method according to claim 17, characterized in that, The first QCL relationship also includes one or more of the following elements: Time instances associated with the model training and / or the model inference; Spatial filter parameters associated with the beam set. The method according to claim 18, characterized in that, When the elements of the first QCL relation include the spatial filter parameters, the model training and the model inference correspond to the same spatial filter, respectively. The method according to any one of claims 17-19 is characterized in that, The first QCL relationship is indicated by a first QCL type, which is one of the following: QCL type A, QCL type B, QCL type C, QCL type D, and QCL type E. The method according to any one of claims 17-19 is characterized in that, The first QCL relationship is indicated by a first QCL type. When the first QCL type is QCL type E, the first QCL relationship is also indicated by a second QCL type, which includes at least one of QCL type A, QCL type B, QCL type C and QCL type D. The method according to any one of claims 17-21 is characterized in that, The beam set used for model training and / or model inference also satisfies one or more of the following conditions: The first beam set used for model training and the first beam set used for model inference have the first QCL relationship; The second beam set used for model training and the second beam set used for model inference have the first QCL relationship; The first beam set and the second beam set used for model training have the first QCL relationship; The first beam set and the second beam set used for model inference have the first QCL relationship; The first beam set is used to determine multiple optimal beams in the second beam set. The method according to any one of claims 17-22 is characterized in that, The first indication information is an indication information for beam transmission configuration, and the first indication information includes multiple transmission configuration indication TCI states corresponding to multiple time instances. The method according to claim 23, characterized in that, The plurality of TCI states correspond one-to-one with the plurality of beams, or at least two of the plurality of TCI states correspond to one beam. The method according to claim 23 or 24 is characterized in that, The first indication information is used by the first device to determine the TCI status table, which includes the beam and activation time corresponding to each of the plurality of TCI statuses. The method according to any one of claims 23-25 ​​is characterized in that, The method further includes: The second device receives an uplink reference signal, which is used to determine whether the plurality of TCI states should be adjusted; When at least one of the plurality of TCI states changes, the second device sends a second indication message, which is used by the first device to update the at least one TCI state. The method according to claim 26, characterized in that, The second indication information is carried in physical layer signaling. The method according to any one of claims 17-27 is characterized in that, The plurality of optimal beams have the first QCL relationship, which is used to determine one or more of the following: The multiple optimal beams correspond to the same channel characteristics; The multiple optimal beams correspond to the same time delay characteristics; The multiple optimal beams correspond to the same beam set identifier; The multiple optimal beams correspond to the same spatial parameters or spatial filter parameters. The method according to claim 28, characterized in that, The plurality of optimal beams include a first beam and a second beam, wherein the difference between the two channel characteristics corresponding to the first beam and the second beam is less than a first threshold. The method according to any one of claims 17-29 is characterized in that, The first QCL relationship is also used to trigger the first device to perform beam measurement. When the plurality of optimal beams have the first QCL relationship at the current time, the beam measurement is performed on one of the plurality of optimal beams; or, when the plurality of optimal beams do not have the first QCL relationship at the current time, the beam measurement is performed on the updated plurality of optimal beams. The method according to any one of claims 17-30 is characterized in that, The first indication information is carried in one of the following types of information: downlink control information and radio resource control signaling. The method according to any one of claims 17-31 is characterized in that, The first operation is related to the first model, which is an artificial intelligence or machine learning model. A device for wireless communication, characterized in that, The device is a first device, the device comprising: The transceiver unit is used to receive first indication information, which is used to indicate a first quasi-co-located QCL relationship; Processing unit, configured to perform a first operation based on the first QCL relationship; The first operation is one or more of the following: Determine a beam set for model training and / or model inference, wherein the elements of the first QCL relation include the identifier of the beam set; Identify multiple optimal beams in the model's prediction results. The apparatus according to claim 33 is characterized in that, The first QCL relationship also includes one or more of the following elements: Time instances associated with the model training and / or the model inference; Spatial filter parameters associated with the beam set. The apparatus according to claim 34 is characterized in that, When the elements of the first QCL relation include the spatial filter parameters, the model training and the model inference correspond to the same spatial filter, respectively. The apparatus according to any one of claims 33-35 is characterized in that, The first QCL relationship is indicated by a first QCL type, which is one of the following: QCL type A, QCL type B, QCL type C, QCL type D, and QCL type E. The apparatus according to any one of claims 33-35 is characterized in that, The first QCL relationship is indicated by a first QCL type. When the first QCL type is QCL type E, the first QCL relationship is also indicated by a second QCL type, which includes at least one of QCL type A, QCL type B, QCL type C and QCL type D. The apparatus according to any one of claims 33-37 is characterized in that, The beam set used for model training and / or model inference also satisfies one or more of the following conditions: The first beam set used for model training and the first beam set used for model inference have the first QCL relationship; The second beam set used for model training and the second beam set used for model inference have the first QCL relationship; The first beam set and the second beam set used for model training have the first QCL relationship; The first beam set and the second beam set used for model inference have the first QCL relationship; The first beam set is used to determine multiple optimal beams in the second beam set. The apparatus according to any one of claims 33-38 is characterized in that, The first indication information is an indication information for beam transmission configuration, and the first indication information includes multiple transmission configuration indication TCI states corresponding to multiple time instances. The apparatus according to claim 39 is characterized in that, The plurality of TCI states correspond one-to-one with the plurality of beams, or at least two of the plurality of TCI states correspond to one beam. The apparatus according to claim 39 or 40 is characterized in that, The first indication information is used by the first device to determine the TCI status table, which includes the beam and activation time corresponding to each of the plurality of TCI statuses. The apparatus according to any one of claims 39-41 is characterized in that, The transceiver unit is also used for: Send an uplink reference signal, the uplink reference signal being used to determine whether the plurality of TCI states should be adjusted; When at least one of the plurality of TCI states changes, a second indication is received, which is used by the first device to update the at least one TCI state. The apparatus according to claim 42 is characterized in that, The second indication information is carried in physical layer signaling. The apparatus according to any one of claims 33-43 is characterized in that, The plurality of optimal beams have the first QCL relationship, which is used to determine one or more of the following: The multiple optimal beams correspond to the same channel characteristics; The multiple optimal beams correspond to the same time delay characteristics; The multiple optimal beams correspond to the same beam set identifier; The multiple optimal beams correspond to the same spatial parameters or spatial filter parameters. The apparatus according to claim 44 is characterized in that, The plurality of optimal beams include a first beam and a second beam, wherein the difference between the two channel characteristics corresponding to the first beam and the second beam is less than a first threshold. The apparatus according to any one of claims 33-45 is characterized in that, The first QCL relationship is also used to trigger the first device to perform beam measurement, and the processing unit is further used to: When the plurality of optimal beams have the first QCL relationship at the current time, a measurement is performed on one of the plurality of optimal beams; or... When the plurality of optimal beams do not have the first QCL relationship at the current time, the plurality of optimal beams are updated and the updated plurality of optimal beams are measured. The apparatus according to any one of claims 33-46 is characterized in that, The first indication information is carried in one of the following The information includes: downlink control information and radio resource control signaling. The apparatus according to any one of claims 33-47 is characterized in that, The first operation is related to the first model, which is an artificial intelligence or machine learning model. A device for wireless communication, characterized in that, The device is a second device, and the device includes: A transceiver unit is configured to send first indication information to a first device, the first indication information being used to indicate a first quasi-co-address QCL relationship, the first QCL relationship being used by the first device to perform a first operation; The first operation is one or more of the following: Determine a beam set for model training and / or model inference, wherein the elements of the first QCL relation include the identifier of the beam set; Identify multiple optimal beams in the model's prediction results. The apparatus according to claim 49 is characterized in that, The first QCL relationship also includes one or more of the following elements: Time instances associated with the model training and / or the model inference; Spatial filter parameters associated with the beam set. The apparatus according to claim 50 is characterized in that, When the elements of the first QCL relation include the spatial filter parameters, the model training and the model inference correspond to the same spatial filter, respectively. The apparatus according to any one of claims 49-51 is characterized in that, The first QCL relationship is indicated by a first QCL type, which is one of the following: QCL type A, QCL type B, QCL type C, QCL type D, and QCL type E. The apparatus according to any one of claims 49-51 is characterized in that, The first QCL relationship is indicated by a first QCL type. When the first QCL type is QCL type E, the first QCL relationship is also indicated by a second QCL type, which includes at least one of QCL type A, QCL type B, QCL type C and QCL type D. The apparatus according to any one of claims 49-53 is characterized in that, The beam set used for model training and / or model inference also satisfies one or more of the following conditions: The first beam set used for model training and the first beam set used for model inference have the first QCL relationship; The second beam set used for model training and the second beam set used for model inference have the first QCL relationship; The first beam set and the second beam set used for model training have the first QCL relationship; The first beam set and the second beam set used for model inference have the first QCL relationship; The first beam set is used to determine multiple optimal beams in the second beam set. The apparatus according to any one of claims 49-54 is characterized in that, The first indication information is an indication information for beam transmission configuration, and the first indication information includes multiple transmission configuration indication TCI states corresponding to multiple time instances. The apparatus according to claim 55 is characterized in that, The plurality of TCI states correspond one-to-one with the plurality of beams, or at least two of the plurality of TCI states correspond to one beam. The apparatus according to claim 55 or 56 is characterized in that, The first indication information is used by the first device to determine the TCI status table, which includes the beam and activation time corresponding to each of the plurality of TCI statuses. The apparatus according to any one of claims 55-57 is characterized in that, The transceiver unit is also used for: Receive an uplink reference signal, the uplink reference signal being used to determine whether the plurality of TCI states should be adjusted; When at least one of the plurality of TCI states changes, a second indication message is sent, which is used by the first device to update the at least one TCI state. The apparatus according to claim 58 is characterized in that, The second indication information is carried in physical layer signaling. The apparatus according to any one of claims 49-59 is characterized in that, The plurality of optimal beams have the first QCL relationship, which is used to determine one or more of the following: The multiple optimal beams correspond to the same channel characteristics; The multiple optimal beams correspond to the same time delay characteristics; The multiple optimal beams correspond to the same beam set identifier; The multiple optimal beams correspond to the same spatial parameters or spatial filter parameters. The apparatus according to claim 60 is characterized in that, The plurality of optimal beams include a first beam and a second beam, wherein the difference between the two channel characteristics corresponding to the first beam and the second beam is less than a first threshold. The apparatus according to any one of claims 49-61 is characterized in that, The first QCL relationship is also used to trigger the first device to perform beam measurement. When the plurality of optimal beams have the first QCL relationship at the current time, the beam measurement is performed on one of the plurality of optimal beams; or, when the plurality of optimal beams do not have the first QCL relationship at the current time, the beam measurement is performed on the updated plurality of optimal beams. The apparatus according to any one of claims 49-62 is characterized in that, The first indication information is carried in one of the following types of information: downlink control information and radio resource control signaling. The apparatus according to any one of claims 49-63 is characterized in that, The first operation is related to the first model, which is an artificial intelligence or machine learning model. A communication device, characterized in that, It includes a memory and a processor, the memory being used to store a program, and the processor being used to invoke the program in the memory to perform the method as described in any one of claims 1-32. An apparatus characterized in that, Includes a processor for calling a program from memory to perform the method as described in any one of claims 1-32. 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 1-32. 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 1-32. 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 1-32. A computer program, characterized in that, The computer program causes the computer to perform the method as described in any one of claims 1-32.

Images