Method and apparatus in a node for wireless communication

Abstract

The invention provides a method and a device in a node for wireless communication. The method comprises: receiving first information, the first information comprising a beam number M, sending a beam measurement report in a first mode, the beam measurement report comprising a beam measurement result based on a first model and corresponding beam indication information; wherein the beam indication information corresponds to the beam number M and a number threshold; the beam indication information is indicated by candidate resource information in a resource set, the resource set comprises a first beam set and / or a second beam set, and the first model corresponds to the first beam set and the second beam set.

Description

[0001] This application is a national phase application based on the international application number PCT / CN2025 / 086806 filed on April 2, 2025. Technical Field

[0002] The present application relates to the field of communication technology, and more particularly, to a method and apparatus in a node for wireless communication. Background Art

[0003] In 5G NR (new radio, NR), beam management (BM) is a key technology, especially in high-frequency bands (such as millimeter wave) communications. In certain beam management scenarios, terminal devices can use models to predict downlink transmit beams and report them to network equipment. This model must be trained before inference predictions can be performed. However, there is a certain time gap between the training and inference phases. Especially when radio parameters in the network change, the probability of errors in the model inference phase is high. Therefore, how to ensure model consistency during the training and inference phases is a pressing technical issue. Summary of the Invention

[0004] The present application provides a method and apparatus in a node for wireless communication. The following introduces various aspects of the present application.

[0005] In a first aspect, a method is provided in a first node for wireless communication, comprising: receiving first information, wherein the first information includes a beam number M, where M is a positive integer; sending a beam measurement report in a first mode, wherein the beam measurement report includes a beam measurement result based on a first model and corresponding beam indication information; wherein the beam indication information corresponds to the beam number M and a quantity threshold; the beam indication information is indicated by candidate resource information in a resource set, the resource set includes a first beam set and / or a second beam set, and the first model corresponds to the first beam set and the second beam set.

[0006] In a second aspect, a method is provided in a second node for wireless communication, comprising: sending first information, wherein the first information includes the number of beams M, where M is a positive integer; receiving a beam measurement report in a first mode, wherein the beam measurement report includes a beam measurement result based on a first model and corresponding beam indication information; wherein the beam indication information corresponds to the number of beams M and a quantity threshold; the beam indication information is indicated by candidate resource information in a resource set, wherein the resource set includes a first beam set and / or a second beam set, and the first model corresponds to the first beam set and the second beam set.

[0007] In a third aspect, a first node used for wireless communication is provided, comprising a transceiver, a memory and a processor, wherein the memory is used to store programs, the processor is used to call the programs in the memory and control the transceiver to receive or send signals so that the first node executes the method described in the first aspect.

[0008] In a fourth aspect, a second node used for wireless communication is provided, comprising a transceiver, a memory and a processor, wherein the memory is used to store programs, and the processor is used to call the programs in the memory and control the transceiver to receive or send signals so that the second node executes the method described in the second aspect.

[0009] In a fifth aspect, an embodiment of the present application provides a communication system, which includes the first node and / or the second node described above. In another possible design, the system may also include other devices that interact with the first node or the second node in the solution provided in the embodiment of the present application.

[0010] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program enables a computer to execute part or all of the steps in the methods of the above aspects.

[0011] In a seventh aspect, embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to perform some or all of the steps of the methods described in each of the above aspects. In some implementations, the computer program product can be a software installation package.

[0012] In an eighth aspect, an embodiment of the present application provides a chip comprising a memory and a processor, wherein the processor can call and run a computer program from the memory to implement some or all of the steps described in the methods of the above aspects.

[0013] In certain beam management scenarios, terminal devices can report CSI using resource subsets configured by the network. This approach is applicable to large beam sets, reduces the UCI overhead associated with separate CRI / SSBRI reporting, and improves flexibility. Alternatively, terminal devices can report CSI using a bitmap index, which reduces the number of bits and therefore the UCI overhead. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 FIG. 1 is a diagram illustrating an example of a system architecture of a wireless communication system to which embodiments of the present application may be applied.

[0015] Figure 2 Schematic diagram of a network architecture to which the embodiments of the present application can be applied.

[0016] Figure 3A and Figure 3B FIG. 1 is a schematic diagram of a wireless protocol stack structure to which an embodiment of the present application may be applied.

[0017] Figure 4 Schematic diagram of neurons in a neural network to which embodiments of the present application may be applied.

[0018] Figure 5 Schematic diagram of a neural network to which embodiments of the present application may be applied.

[0019] Figure 6 Schematic diagram of a convolutional neural network to which the embodiments of the present application can be applied.

[0020] Figure 7 The figure is a schematic flowchart of a data collection signaling process to which an embodiment of the present application can be applied.

[0021] Figure 8 Schematic diagram of the model processing process to which the embodiment of the present application can be applied.

[0022] Figure 9 A flowchart of a method in a first node and a second node for wireless communication provided in an embodiment of the present application.

[0023] Figure 10 yes Figure 9 A schematic diagram of another possible implementation of the method shown.

[0024] Figure 11 A schematic structural diagram of a first node for wireless communication provided in an embodiment of the present application.

[0025] Figure 12 A schematic structural diagram of a second node for wireless communication provided in an embodiment of the present application.

[0026] Figure 13 It is a structural diagram of a communication device provided in an embodiment of the present application.

[0027] Figure 14 A schematic diagram of the hardware modules of the communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] Communication system architecture

[0029] The wireless communication system of the embodiment of the present application may include a network device and a terminal device. The network device may be a device that communicates with the terminal device. The network device may provide communication coverage for a specific geographical area and may communicate with the terminal devices located within the coverage area.

[0030] Figure 1 The wireless communication system 100 is exemplarily shown to include a network device 110 and multiple terminal devices, such as terminal devices 120a to 120j in the figure. Optionally, the wireless communication system 100 may include multiple network devices, and each network device may include another number of terminal devices within its coverage area, which is not limited in this embodiment of the present application.

[0031] Optionally, the wireless communication system may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiments of the present application.

[0032] It should be understood that the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: fifth-generation (5G) systems or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, enhanced long term evolution (LTE-A) systems, enhanced 5G (5G advanced) systems, low-power communication systems, etc. The technical solutions provided in the present application can also be applied to future communication systems, such as sixth-generation (6G) mobile communication systems, satellite communication systems, and the like.

[0033] In communication technologies prior to NR, a terminal device could operate in a mode that supported multiple communication technologies simultaneously, with each technology corresponding to a specific multiple access method. However, with the evolution of NR and subsequent communication technologies, a single communication system can now support multiple multiple access methods.

[0034] It should be understood that the multiple access method is also called the multiple access method or multiple access technology, which refers to a technology that solves how to efficiently share a wireless resource (such as time / frequency / space / carrier) when multiple users access the network in a network (such as a mobile communication cell or a wireless local area network). That is, when multiple users share a wireless resource, it is divided according to time, frequency, space, coding, subcarrier, etc., so that different users can use (or access) the divided resource in different division methods to communicate. Occupying different divided resources is like having different addresses, and the same wireless resource can have multiple addresses, so it is called multiple access. Multiple access methods are roughly divided into two categories: orthogonal multiple access (OMA), that is, there is no interference between users; non-orthogonal multiple access (NOMA), where the signal of each user may interfere with that of other users.

[0035] The multiple access methods involved in this application include but are not limited to the following: frequency division multiple access (FDMA), time division multiple access (TDMA), code division multiple access (CDMA), space division multiple access (SDMA), carrier sense multiple access with collision avoidance (CSMA / CA), non-orthogonal multiple access (NOMA), orthogonal frequency division multiple access (OFDMA), single-carrier frequency division multiple access (SC-FDMA) and other multiple access methods.

[0036] The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description. However, these technologies can also be applied to applications other than NR systems, such as 6th Generation (6G) communication systems. A wireless communication system includes terminal devices and network-side devices.

[0037] The terminal device may be a mobile phone, tablet personal computer, laptop computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, vehicle-mounted equipment (VUE), pedestrian terminal (PUE), smart home (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM or self-service machine, etc. Wearable devices include smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Optionally, the UE can be used to act as a base station. For example, a UE can act as a scheduling entity that provides sidelink signals between UEs in V2X or D2D. For example, a cell phone and a car communicate with each other using sidelink signals. Cell phones and smart home devices communicate with each other without relaying communication signals through a base station. In addition, a terminal can also support multiple communication modes, i.e., a multi-mode terminal, and this application is also applicable to multi-mode terminals. It should be noted that the embodiments of this application do not limit the specific type of terminal device.

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

[0039] Network-side devices may include access network devices or core network devices. Access network devices may also be referred to as radio access network devices, radio access network (RAN), radio access network functions, or radio access network units. Access network devices may include base stations, WLAN access points, or WiFi nodes. A base station may broadly cover various names as follows, or be replaced with the following names, such as: 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-standard 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 radiohead (RRH), central unit (CU), distributed unit (DU), positioning node, network communication device, etc. A base station may be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. A base station may also refer to a communication module, modem, or chip used to be set in the aforementioned device or apparatus. A base station may also be a mobile switching center and 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 may support networks with the same or different access technologies. The embodiments of this application do not limit the specific technology and specific device form used by network devices.

[0040] It should be understood that 6G systems will adopt more flexible and efficient multiple access methods. For example, non-orthogonal multiple access (NOMA) technology transmits data from multiple users simultaneously within the same frequency band and utilizes differences between users to optimize resource allocation and interference management. Technologies such as sparse codebooks and multi-element modulation can be used to improve spectrum efficiency and transmission performance. Multiple access methods based on interleaving multiple access, multi-user shared access, resource-based extended multiple access, and UMA (unsourced multiple access) are also proposed.

[0041] The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used for the systems and radio technologies mentioned above as well as other systems and radio technologies.

[0042] It is worth noting that a base station 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 based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0043] In some deployments, the network device in the embodiments of the present application may refer to a CU or a DU, or the network device may include a CU and a DU. The gNB may also include an AAU.

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

[0045] In addition, 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; they can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenarios in which network devices and terminal devices are located.

[0046] It should be understood that all or part of the functions of the communication device in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (such as a cloud platform).

[0047] Figure 2A schematic diagram of a network architecture 200 of an embodiment of the present application is exemplarily shown. The network architecture 200 illustrates the network architecture of a 5G NR / LTE / LTE-A system. The 5G NR / LTE / LTE-A network architecture may also be referred to as a 5G system (5G system, 5GS) / evolved packet system (Evolved Packet System, EPS) network architecture. The network architecture 200 includes at least one of a network device 110, a terminal device 120, a 5G core network (5G core network, 5GC) / evolved packet core (EPC) 210, a home subscriber server (HSS) / unified data management (UDM) 220, and an Internet service 230. Figure 2 The network device and terminal device in the figure are illustrated by taking RAN and UE as examples respectively.

[0048] like Figure 2As shown, the network device 110 provides user plane protocol and control plane protocol termination towards the terminal device 120. The network device 110 is connected to the 5GC / EPC 210 via the S1 / NG interface. The 5GC / EPC 210 includes a mobility management entity (MME) / authentication management field (AMF) / session management function (SMF) 211, other MME / AMF / SMF 214, a service gateway (S-GW) / user plane function (UPF) 212, and a packet data network gateway (P-GW) / UPF 213. The MME / AMF / SMF 211 is a control node that handles signaling between the terminal device 120 and the 5GC / EPC 210. Generally, the MME / AMF / SMF 211 provides bearer and connection management. All user Internet Protocol (IP) packets are routed through S-GW / UPF 212, which is itself connected to P-GW / UPF 213. The P-GW provides UE IP address allocation and other functions. P-GW / UPF 213 is connected to Internet Services 230. Internet Services 230 includes operator-specific Internet Protocol services, which may include the Internet, intranet, IP Multimedia Subsystem (IMS), and packet-switched streaming services. While network architecture 200 provides packet-switched services, those skilled in the art will readily appreciate that the various concepts presented herein can be extended to networks providing circuit-switched services or other cellular networks.

[0049] Figure 3A and Figure 3B A schematic diagram of the wireless protocol stack structure of an embodiment of the present application is shown respectively. Figure 3A and Figure 3B Let's take the 5G wireless protocol stack as an example. The 5G wireless protocol stack is divided into two planes: the user plane (UP) protocol stack and the control plane (CP) protocol stack. The user plane protocol stack is the protocol cluster used for user data transmission, and the control plane protocol stack is the protocol cluster used for control signaling transmission in the 5G system. The names of the various protocol stack layers are as follows:

[0050] like Figure 3AAs shown in the figure, the user plane protocol stack includes, from top to bottom, the service data adaptation protocol (SDAP) layer, the packet data convergence protocol (PDCP) layer, the radio link control (RLC) layer, the medium access control (MAC) layer, and the physical (PHY) layer.

[0051] like Figure 3B As shown in FIG, the control plane protocol stack includes, from top to bottom, a non-access stratum (NAS); a radio resource control (RRC) layer, a PDCP layer, an RLC layer, a MAC layer, and a PHY layer.

[0052] It should be understood that the different layers in the aforementioned protocol stack have different functions, and that communication between terminal devices and network devices is achieved through inter-layer interaction. With the development of artificial intelligence (AI) technology, AI-assisted computing has penetrated into the processing and implementation methods of the aforementioned protocol stack. For example, AI algorithms can be applied to the scheduling algorithms of the MAC layer and the encoding and decoding algorithms of the PHY layer to improve the performance of communication algorithms.

[0053] As an example, Figure 3A and Figure 3B The wireless protocol architecture in is applicable to the first node in this application.

[0054] As an example, Figure 3A and Figure 3B The wireless protocol architecture in is applicable to the second node in this application.

[0055] It should be understood that certain functions in the wireless protocol architecture can also be implemented in one or more devices. For example, the functions of different layers in the control plane protocol stack can be combined and implemented by multiple nodes on the network side.

[0056] It should be understood that the interpretation of the terminology in the embodiments of the present application can refer to the specification protocols TS36 series, TS37 series and TS38 series of the 3rd Generation Partnership Project (3GPP), but can also refer to the specification protocols of the Institute of Electrical and Electronics Engineers (IEEE).

[0057] For ease of understanding, some relevant technical knowledge involved in the embodiments of this application is first introduced. The following related technologies can be combined with the technical solutions of the embodiments of this application as optional solutions, and they all fall within the scope of protection of the embodiments of this application. The embodiments of this application include at least part of the following contents.

[0058] Neural Networks

[0059] AI research, exemplified by neural networks, has achieved remarkable results in many fields and will continue to impact people's lives and production for a long time to come. A neural network can be understood as a computational model consisting of multiple interconnected neuron nodes. In a neural network, the strength of the connections between nodes can be expressed as weighted values corresponding to the input signals, also known as parameters. Each neuron node performs a weighted summation of different input signals and generates an output using a specific activation function. Neurons can implement nonlinear mapping based on activation functions.

[0060] by Figure 4 The neuron shown in the figure is used as an example to introduce the neuron. The input of the neuron can be recorded as A, each dimension of the input is recorded as aj, and the corresponding weighted value is recorded as wj, where the value of j is 1, 2, ..., n. The input of the neuron can also set a bias term for adjusting the output, such as Figure 4 The constant 1 in is denoted by b (the corresponding weight value is b). The weight value and the summation unit (SU) together enhance or weaken the input. The output of SU can be input into the activation function f to obtain the output t.

[0061] Common neural networks include convolutional neural network (CNN), recurrent neural network (RNN), deep neural network (DNN), etc.

[0062] Combined with the following Figure 5 A neural network applicable to the embodiments of the present application is introduced. Figure 5 The neural network shown can be divided into three categories according to the positions of different layers: input layer 510, hidden layer 520, and output layer 530. Generally speaking, the first layer is the input layer 510, the last layer is the output layer 530, and the intermediate layers between the first and last layers are all hidden layers 520.

[0063] The input layer 510 is used to input data, where the input data can be, for example, a received signal received by a receiver. The hidden layer 520 is used to process the input data, for example, decompress the received signal. Hidden layers can also be called intermediate layers. The output layer 530 is used to output processed output data, for example, a decompressed signal.

[0064] See also Figure 5 A neural network consists of multiple layers, each of which contains multiple neurons. The neurons between layers can be fully connected or partially connected. For connected neurons, the output of the neurons in the previous layer can serve as the input of the neurons in the next layer.

[0065] For ease of understanding, let's take CNN as an example and combine it with Figure 6 The following is an example of multiple layers in a neural network. CNN is a deep neural network with a convolutional structure. Figure 6 As shown, the structure of CNN may include an input layer 610, a convolutional layer 620, a pooling layer 630, a fully connected layer 640, and an output layer 650. The convolutional layer 620, the pooling layer 630, and the fully connected layer 640 are intermediate layers of the CNN.

[0066] Each convolution layer 620 may include a plurality of convolution operators, also known as kernels, which can be viewed as filters that extract specific information from the input signal. The convolution operator is essentially a parameter matrix, which is usually predefined. In practical applications, the parameter values in these parameter matrices require extensive training to help the CNN make correct predictions. When a CNN has multiple convolution layers, the initial convolution layer often extracts more general features, which can also be called low-level features. As the depth of the CNN increases, the features extracted by the subsequent convolution layers become increasingly complex.

[0067] Pooling layer 630, in order to reduce the number of training parameters and the size of the space for extracting information, it is often necessary to periodically introduce a pooling layer after the convolution layer. The pooling layer can be introduced in many ways, for example, Figure 6 The shown convolutional layer is followed by a pooling layer, or multiple convolutional layers can be followed by one or more pooling layers.

[0068] The fully connected layer 640 is used to generate the final output information. Since the convolution layer 620 and the pooling layer 630 are only responsible for extracting features and reducing the parameters brought by the input data, the processing of the convolution layer 620 and the pooling layer 630 is not sufficient to generate the required output information, so the fully connected layer 640 needs to be introduced. Generally, the fully connected layer 640 can also include multiple hidden layers, and the parameters contained in the multiple hidden layers can be pre-trained based on the relevant training data of the specific task type. For example, the task type may include decoding the data signal received by the receiver. For another example, the task type may also include channel estimation based on the pilot signal received by the receiver.

[0069] Following the multiple hidden layers included in the fully connected layer 640, the final layer of the CNN, the output layer 650, is used to output the results. Typically, the output layer 650 is provided with a loss function (e.g., a loss function similar to categorical cross entropy) to calculate the prediction error, or to evaluate the degree of difference between the result output by the CNN model (also known as the predicted value) and the ideal result (also known as the true value).

[0070] It should be noted that if Figure 6 The CNN shown is only an example of a convolutional neural network. In specific applications, the convolutional neural network can also exist in the form of other network models, which is not limited in the embodiments of the present application.

[0071] Combined with the above Figures 4 to 6 This paper introduces neural networks that can be applied to AI. For example, a neural network model, as an AI / ML model, can be used for beam management in wireless communication networks.

[0072] Beam management

[0073] In modern wireless communication systems, beam management is a key technology for ensuring signal quality and user experience. For example, in 5G NR networks, beam management improves signal coverage and communication performance by optimizing the direction of radio beams. With technological advancements, mobile communication technologies (such as 5G Advanced (5G-A)) have introduced AI / ML-based beam prediction technology in their protocols to further enhance network performance.

[0074] In a wireless communication system, a terminal device can acquire a beam (also referred to as a spatial beam) to enable a wireless connection between the terminal device and a wireless network. For example, the terminal device can perform beam scanning on available beams transmitted by the wireless network and measure the properties of the beams. Beam properties include signal strength and signal quality. For example, after performing beam scanning, the terminal device can also perform beam refinement to achieve a set of potentially narrower beams for wireless connection to the wireless network. Beams can not only enable a wireless connection between the terminal device and the wireless network, but also achieve high directional accuracy and high signal quality for wireless signal transmission between the terminal device and the wireless network.

[0075] 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 one of the research directions. The goals of this research include exploring how to enhance the advantages of the air interface. For example, the relevant performance of the air interface can be enhanced by enhancing support for AI / ML algorithms. Another example is to reduce the complexity and / or overhead of the air interface by enhancing support for AI / ML algorithms.

[0076] Research into AI / ML technologies can also enhance beam management (BM) capabilities. For example, AI / ML enhancements related to beam management can reduce overhead and latency in beam measurement and reporting. For example, AI / ML models can be used to predict beams, improving air interface transmission efficiency.

[0077] The entire process of applying AI / ML models for enhancement includes model training, model inference, and model monitoring. During this process, the trained AI / ML model generates a set of outputs based on a set of inputs. The inputs can be a set of beam measurements, while the outputs can be a set of beams that are different from or larger than the inputs.

[0078] During model inference, the AI / ML model can predict the best beam from a set of different / larger beam groups based on a set of beam measurements.

[0079] 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. The model may be referred to as a UE-side model. For example, the AI model is located at the UE, and the AI model training and / or the AI model inference may be performed at the UE or by the UE. When the UE supports beam prediction in the spatial domain and / or time domain, i.e., BM-Case1 and / or BM-Case2, for AI / ML enhancements related to beam management, the spatial domain beam prediction use case (BM-Case1) and the time domain beam prediction use case (BM-Case2) mainly support reducing overhead, reducing beam measurement and reporting delays. Among them, BM-Case1 refers to the spatial domain DL beam prediction of beam group A based on the measurement results of beam group B; BM-Case2 refers to the time DL beam prediction of beam group A based on the historical measurement results of beam group B.

[0080] As an example, a terminal device can use the beams in Set B (also called Beam Group B) as input to an ML model. The ML model can predict the best beam in Set A (also called Beam Group A), which is not fully measured by the terminal device.

[0081] In the above example, Set B may be the beam set that the terminal device first measures, also known as the training beam set. Set B may also be multiple beams transmitted by a base station (e.g., a gNB). Each beam can correspond to a different direction or angle to cover multiple spatial directions. Each beam may also correspond to a measurement signal, used to obtain a measurement value, such as reference signal received power (RSRP). Set B provides preliminary environmental information and channel conditions for the model.

[0082] In the above example, Set A can be the beam group required for prediction during the inference phase, also known as the inference beam set. Set A typically contains more beams than Set B, or the beam directions may be more concentrated. The AI / ML model can use measurements from Set B to predict the optimal beam in Set A, improving data transmission efficiency.

[0083] 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 device 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, 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, and set B as the measurement resource can be transmitted only in the measurement window.

[0084] Optionally, 64 or even more beams can be used as the size of beam set A. For future-oriented networks, network devices will be able to transmit 64 narrower beams with higher directivity. 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.

[0085] Optionally, the network device can send multiple reference signals, such as the channel state information (CSI) reference signal (CSI-reference signal, CSI-RS), synchronization signal block (SSB), etc. It should be noted that SSB can also represent synchronization signal / physical broadcast channel block (SS / PBCHblock). SSB can include primary synchronization signal (PSS) and secondary synchronization signal (SSS).

[0086] Optionally, the terminal device estimates the channel quality of each beam by measuring the RSRP of the received CSI-RS / SSS.

[0087] Optionally, during the model training process, the AI / ML model can adjust its weights by minimizing the loss function so that the model can accurately predict the best beam in set A from the RSRP measurement results of set B.

[0088] In some embodiments, AI / ML can be located on a 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. For example, the AI model is located at the base station, and AI model training and / or inference using the AI model can be performed at or by the base station to generate the optimal beam.

[0089] In some embodiments, the network can fully control the data collection process for model training on the terminal device side, including the initiation, termination, and management of data collection and data transmission.

[0090] As an example, when a terminal device utilizes 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 terminal device needs to ensure consistency between the training phase and the inference phase models.

[0091] Compared with other beam management technologies, through beam management that supports AI / ML technology, terminal devices can experience reduced latency, reduced overhead, reduced power consumption and improved signal quality based on beam prediction.

[0092] In related communication technologies, AI / ML model-based beam management, channel state information (CSI) feedback enhancement, and positioning accuracy enhancement have gradually entered the corresponding standards or protocols and become mainstream. Specifically, the general framework based on AI / ML models controls the data collection, model training, function / model specification, model delivery / transfer, model inference operations, function / model selection / activation / deactivation / switching and fallback operations, function / model monitoring, model updates, and terminal device capabilities of AI / ML models through life cycle management (LCM). This communication framework is integrated into certain standards.

[0093] For beam management, AI / ML models enable 5G network equipment (e.g., gNBs) to more accurately predict and adjust beam directions than traditional solutions, optimizing resource utilization and user experience. 3GPP has proposed two AI / ML-based beam management (BM) use cases in its protocols: BM-Case 1 and BM-Case 2.

[0094] BM-Case 1 predicts the downlink beams in Set A based on the beam measurements in Set B. Based on the current measurement results, the optimal beam is predicted and beam management is performed in real time.

[0095] BM-Case 2 performs time-domain prediction of the downlink beams in Set A based on historical beam measurement results in Set B. Based on these historical measurement results, the optimal beam predictions for multiple subsequent time slots are inferred and beam management is performed based on the predictions for the current time slot.

[0096] In the two use cases above, Set B corresponds to the input of the AI / ML prediction model, and Set A corresponds to the output of the AI / ML prediction model.

[0097] For BM-Case1, set B can be a subset of set A or different from set A. As an example, if set B and set A have an intersection, set A can be the full set or subset of CSI reference signal (CSI-reference signal, CSI-RS) resources. If set A is the full set, it can correspond to the initial access or failed reconstruction phase of beam management. If set A is a subset, it can correspond to the beam optimization phase. In this scenario, the physical meaning of AI / ML-based beam prediction is to extract channel features in the training phase and predict overall spatial information through partial spatial information in the inference phase. As another example, if set A and set B do not have an intersection, set B can be a wide beam corresponding to the synchronization signal and PBCH block (SSB), while set A is a narrow beam under wide beam angular coverage. In this scenario, the physical meaning of AI / ML-based beam prediction is to extract channel features in the training phase and predict high-precision information through a smaller amount of low-precision spatial information in the inference phase.

[0098] For BM-Case2, the model input is the measurement results of the latest K (K ≥ 1) measurement instances, and the model output is F prediction results for F (F ≥ 1) future time slots. Compared to the reporting rules of the sub-use case in BM-Case1, each measurement instance is additionally timestamped, and all other rules are the same. Therefore, this embodiment of the application does not distinguish between the two sub-use cases of BM-Case1 and BM-Case2; both are applicable.

[0099] Based on the deployment location of the AI / ML model, each sub-use case can be divided into network (NW) side model and terminal device side model scenarios. Figures 7 and 8 The NW side model and terminal device side model scenarios applicable to the embodiments of the present application are introduced.

[0100] For the network side model, the embodiments of the present application are applicable to the LCM stages such as data collection, model reasoning and performance monitoring of the network side model scenario. Figure 7 This is a schematic flow chart of the data collection signaling process. Figure 7Includes steps S710 to S740. Figure 7 The terminal device in the example is UE, and the network device is gNB or the AI model deployed on the gNB side.

[0101] At S710, the terminal device sends a capability report to the network device. The terminal device performs capability reports under LCM scheduling. The request data collection phase begins, and the network device performs LCM operations such as model or function selection based on the capability report.

[0102] In step S720, the network device sends a reference signal (RS) or related measurement resource set and report configuration (RS and report configuration) to the terminal device. Under LCM scheduling, the network device side will collect data for model training. Subsequently, the network device side configures CSI-ResourceConfig and CSI-ReportConfig to configure the measurement resource set and terminal device report. The configuration includes the configuration of the CSI-RS / SSB measurement beam resource set of the current set A for beam scanning. At the same time, it also includes configuration information of the report reported by the terminal device, such as report trigger type, report settings, measurement object, report content, etc. In the data collection phase for training, set A can be used as a measurement set to provide ground-truth for AI / ML model training. In the case where there is no intersection between set A and set B, set B needs to be included in the measurement set for measurement to provide input for the model.

[0103] In step S730, the network device transmits set A and / or set B to the terminal device. The network device performs beam scanning of the current resource set according to the configuration, and the terminal device measures the CSI-RS / SSB signal.

[0104] In step S740, the terminal device sends a data report to the network device. The terminal device reports beam-related information according to the report configuration. This information includes the reference signal received power (RSRP) measured by the physical layer and / or the corresponding resource index. The RSRP measured by the physical layer is the RSRP of layer 1 (L1) (L1-RSRP).

[0105] In related communication technologies, AI / ML model-based beam management, channel state information (CSI) feedback enhancement, and positioning accuracy enhancement have gradually entered the corresponding standards or protocols and become mainstream. Specifically, the general framework based on AI / ML models controls the data collection, model training, function / model specification, model delivery / transfer, model inference operations, function / model selection / activation / deactivation / switching and fallback operations, function / model monitoring, model updates, and terminal device capabilities of AI / ML models through life cycle management (LCM). This communication framework is integrated into certain standards.

[0106] For beam management, AI / ML models enable 5G network equipment (e.g., gNBs) to more accurately predict and adjust beam directions than traditional solutions, optimizing resource utilization and user experience. 3GPP has proposed two AI / ML-based beam management (BM) use cases in its protocols: BM-Case 1 and BM-Case 2.

[0107] BM-Case 1 predicts the downlink beams in Set A based on the beam measurements in Set B. Based on the current measurement results, the optimal beam is predicted and beam management is performed in real time.

[0108] BM-Case 2 performs time-domain prediction of the downlink beams in Set A based on historical beam measurement results in Set B. Based on these historical measurement results, the optimal beam predictions for multiple subsequent time slots are inferred and beam management is performed based on the predictions for the current time slot.

[0109] In the two use cases above, Set B corresponds to the input of the AI / ML prediction model, and Set A corresponds to the output of the AI / ML prediction model.

[0110] For BM-Case1, set B can be a subset of set A or different from set A. As an example, if set B and set A have an intersection, set A can be the full set or a subset of CSI reference signal (CSI-Reference Signal, CSI-RS) resources. If set A is the full set, it can correspond to the initial access or failed reconstruction phase of beam management. If set A is a subset, it can correspond to the beam optimization phase. In this scenario, the physical meaning of AI / ML-based beam prediction is to extract channel features in the training phase and predict overall spatial information through partial spatial information in the inference phase. As another example, if set A and set B do not have an intersection, set B can be a wide beam corresponding to the synchronization signal and PBCH block (SSB), while set A is a narrow beam under wide beam angular coverage. In this scenario, the physical meaning of AI / ML-based beam prediction is to extract channel features in the training phase and predict high-precision information through a smaller amount of low-precision spatial information in the inference phase.

[0111] For BM-Case2, the model input is the measurement results of the latest K (K ≥ 1) measurement instances, and the model output is F prediction results for F (F ≥ 1) future time slots. Compared to the reporting rules for the BM-Case1 use case, each measurement instance is additionally timestamped, and all other aspects are the same. Therefore, the present embodiment does not distinguish between BM-Case1 and BM-Case2 use cases; both are applicable.

[0112] Figure 8 This is a schematic diagram of the specific workflow of the entire process of model processing on the terminal device side. Figure 8 As shown, in this process, the network device mainly performs beam scanning and beam indication, and the terminal device mainly performs beam reporting.

[0113] See also Figure 8 During the model training phase, the network device collects sufficient data for model training. When the model converges and the prediction performance indicators meet the requirements, the model inference phase begins. At this point, the network device can use Set B as the measurement set for CSI resource and reporting configuration.

[0114] Figure 8 This is explained from the perspective of the interaction between the terminal device (such as UE) and the network (NW). The network side uses 4 beams as an example. Figure 8It can be seen that the entire process may include a model training process, a model inference process, and a reporting process. The model training process includes S810 and S820, and the model inference process includes S830 and S840.

[0115] In S810, the terminal device reports training-related information (UE report training-related information).

[0116] At S820 , the network side performs beam scanning based on four beams.

[0117] In S830, the terminal device reports inference-related information (UEreport inference-relatedinformation).

[0118] In S840, the network side selects two beams from four beams to perform beam scanning based on the report from the terminal device.

[0119] At S850 , the terminal device reports the optimal K beams (top-K beam report).

[0120] At S860, the network side performs beam scanning based on the beam in the beam report. Figure 8 It can be seen that the two beams used for beam scanning by the network side in step S860 may be different from the two beams used for beam scanning in step S840.

[0121] At S870, the terminal device sends a beam report so that the network side can determine the optimal beam.

[0122] At S880, the network side sends a beam indication to the terminal device.

[0123] In other words, the network device scans the beams in Set B based on resource configuration. The terminal device measures the current resource set and reports the measurement results to the network device. The network device-side model uses the measurement results fed back by the terminal device as input to the AI / ML model. The trained model performs inference based on the input. The model outputs predicted values for the beams in Set A, such as the predicted L1-RSRP value for each beam or the predicted probability of each beam being a top-K beam. The network device performs beam management based on the predicted results. During the inference phase, the LCM periodically initiates model performance monitoring, configures the predicted top-K beams as the measurement set, and performs beam scanning. The terminal device measures and reports the measurement results. Upon receiving the measurement results, the network device calculates performance indicators and adjusts LCM operations.

[0124] In the above process, the terminal device needs to report beam reports for multiple beams to support multi-beam transmission. Frequent beam information feedback increases signaling overhead and device power consumption. In particular, when the number of beams M configured for network equipment exceeds 4, the amount of beam information that the terminal device needs to report increases, resulting in increased signaling overhead. Within the AI / ML-driven Beam Management (BM) framework, it is necessary to consider enhancing the L1-RSRP quantization reporting strategy to make it more flexible and efficient, so as to meet the CSI reporting requirements of different network network configurations.

[0125] Based on this, an embodiment of the present application proposes a method in a node for wireless communication, thereby reducing UCI load overhead and resource occupancy and improving the flexibility of beam management.

[0126] It should be noted that the embodiments of the present application can not only solve the flexibility problem of the beam reporting mechanism based on the AI / ML model, but also solve the flexibility problem of beam management in other scenarios. In addition, the method of the embodiments of the present application is not limited to the UE-side model, but can also be used for the NW-side model, or can also be used for the dual-side model of the UE side and the NW side.

[0127] For ease of understanding, the following Figure 9 The method in the first node for wireless communication proposed in an embodiment of the present application is described. Figure 9 The method shown is introduced from the perspective of the interaction between the first node and the second node. Figure 9 The method shown includes S910 to S920.

[0128] As an embodiment, the first node may be any terminal device, for example, Figure 1 The terminal device 120 is shown.

[0129] As an embodiment, the first node may be a network-controlled repeater (NCR).

[0130] As an embodiment, the first node may be a relay, such as a relay terminal.

[0131] As an example, the first node may be any communication device that supports model performance monitoring. For example, the first node may be a UE with monitoring capabilities. In another example, the first node may include a terminal device and any processing device that supports performance monitoring. In some embodiments, the first node may be a network device. For example, the first node may be a base station.

[0132] In some embodiments, the first node supports enhanced functionality based on AI / ML operations. For example, the first node has enhanced beam management and / or performance monitoring functionality based on AI / ML operations.

[0133] In some embodiments, a first model is deployed on the first node to implement beam prediction. When the second node is a network device, the first node performs beam prediction. When the second node is a terminal device, the first node performs side beam prediction.

[0134] As an example, the first model is a model that supports AI algorithms or ML, that is, the first model is an AI / ML model.

[0135] As an example, the beam prediction implemented by the first model can be BM-Case1 mentioned above, or BM-Case2, or other use cases, or other beam prediction types in the future, which are not limited here.

[0136] In some embodiments, the first node side is deployed with a first model. 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 a server that directly communicates with the terminal device.

[0137] In some embodiments, the second node can be any network device that communicates with the first node, or a terminal device that communicates with the first node. When the first node is a terminal device and is within the coverage area of the network device, the second node can be a network device. When the first node is a network device, the second node can be a terminal device that communicates with the network device. In a sideline communication system, when the first node communicates with other terminal devices, the second node can also be another terminal device.

[0138] In some embodiments, the second node can monitor the first node's processing of the first model. For example, the second node can determine whether the current phase is the training phase or the inference phase of the first model based on a report sent by the first node, or can determine the performance monitoring results of the first model based on a report sent by the first node. In another example, the second node can assist the first node in monitoring the performance of the first model.

[0139] In some embodiments, the second node supports AI / ML operations. The first model may be deployed on the second node side.

[0140] In some embodiments, the second node may send multiple beams to the first node multiple times to facilitate the first node to perform measurements and perform model training, model inference and / or model monitoring on the first model based on the measurement results.

[0141] In the above embodiment, 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.

[0142] See also Figure 9 At S910, a first node receives first information. The first information includes the number of beams, where the number M of beams is a positive integer.

[0143] In a possible embodiment, the first information may be beam report configuration (CSI-Report config) information from the second node. Figure 10 As shown, the beam report configuration information includes not only the configuration information of the first beam set and the second beam set, but also the number M of beams (ie, expected Top-M beam information).

[0144] In one possible embodiment, the beam report configuration information is used to request beam information for the first M beams with the largest L1 RSRP and L1-RSRP measurement values in the measurement resource set. The number of beams M may be configured by the second node (e.g., the gNB). For example, the number of beams M may support 4, 6, 8, 12, 16, or 32.

[0145] In some embodiments, the first information may be carried in control signaling. As an example, the first indication information may be carried in one of the following: a media access control element (MAC CE), downlink control information (DCI), or radio resource control (RRC) signaling. For example, the network device may send the beam report configuration information via RRC signaling.

[0146] In some embodiments, new RRC parameters may be added, as shown in the following table:

[0147]

[0148]

[0149]

[0150] At S920 , the first node sends a beam measurement report in a first mode, where the beam measurement report includes a beam measurement result and corresponding beam indication information.

[0151] In some embodiments, the beam indication information corresponds to the beam number M and the number threshold; the beam indication information is indicated by candidate resource information in a resource set, the resource set includes a first beam set and / or a second beam set, and the first model corresponds to the first beam set and the second beam set.

[0152] In some embodiments, the beam measurement results may be obtained after processing based on the first model. The beam measurement results may include RSRP and SNR of each beam.

[0153] In some embodiments, the beam indication information may be used to indicate candidate resources in a resource set. The beam indication information may be beam index information, wherein the beam indication information may be a bitmap index of the candidate resources in the resource set, or the beam indication information may be a resource subset index of the candidate resources in the resource set, or the beam indication information may be a bitmap index and a resource subset index of the candidate resources in the resource set.

[0154] In some embodiments, the bitmap index of the candidate resource in the resource set may refer to the bitmap index of multiple selected beams in the resource set.

[0155] In some embodiments, the resource subset index of the candidate resource in the resource set may be a resource subset index list preconfigured by the second node. For example, the UE reports CSI based on the resource subset preconfigured by the NW, rather than directly sending CRI / SSBRI. Because the resource subset can include a fixed beam pattern, the NW's beam prediction is more stable. For example, if the UE sends {Sub-Set Index 1, Sub-Set Index 2, ...} in the beam measurement report, this solution is applicable to large-scale beam sets and reduces the UCI overhead caused by separate CRI / SSBRI reporting.

[0156] In some embodiments, the candidate resources in the resource set may be indexed by CRI (CSI-RS indicator) and SSBRI (SSB / PBCH resource block indicator), that is, indexed by CRI / SSBRI.

[0157] In some embodiments, when M ≤ L1, the beam indication information is indicated by indicating the resource subset index of the M target beams in the resource set; when L1 < M ≤ L2, the beam indication information is indicated by indicating the bitmap index of the M target beams in the resource set; when M ≥ L2 or the number of future time instances increases to a set value, the beam indication information is indicated by the bitmap index and resource subset index of the M target beams in the resource set, where L1 is a first threshold, L2 is a second threshold, L1 < L2, L1 and L2 are positive integers, and the quantity threshold includes the first threshold and / or the second threshold. In other words, the beam indication information is determined based on the number of beams M and the quantity threshold.

[0158] In one example, when M is 4, the UE uses the existing CSI feedback mechanism to directly report the first 4 CRIs or SSB RIs.

[0159] In one example, when M is 6 or 8, the UE selects the largest M measured values from the measured resource set L1-RSRP and directly reports the CRI or SSB RI corresponding to these M measured values. For example, if M is 6, the UE selects the largest six measured values from the measured resource set L1-RSRP and directly reports the CRI or SSB RI corresponding to these six measured values. For example, the UE sends: {CRI_1, CRI_2, CRI_3, CRI_4, CRI_5, CRI_6}. Optionally, the CRI / SSBRI uses variable size encoding to reduce the UCI load.

[0160] In one example, when M is 12, the UE reports CSI based on resource subsets preconfigured by the network worker (NW), rather than directly sending CRI / SSBRI. For example, the UE sends: {Sub-Set Index 1, Sub-Set Index 2, ..., Sub-Set Index 12}. In this example, the NW can dynamically adjust the resource subsets based on UE feedback, providing more flexible configuration.

[0161] In one example, when M is 16 or 32, the beam indication information is indicated by a bitmap index indicating the M target beams in the resource set, which can reduce the number of bits in a single CSI report. For example, the bitmap index is [1,1,0,1], where 1 indicates that the transmit beam is selected and 0 indicates that the transmit beam is not selected.

[0162] In some embodiments, when M is large or the number of future time instances increases to a set value, the beam indication information is indicated by the bitmap index and resource subset index of the M target beams in the resource set. This example can be applied to the case where M is 16 or 32, reducing the number of bits in a single CSI report.

[0163] In some embodiments, to optimize UCI feedback overhead, an X dB selection mechanism can be introduced: the UE reports beams whose L1-RSRP is within X dB of the maximum measured value. Up to M beams are reported within the X dB gap: if the L1RSRP of the beams in setB is above the threshold, these beams can be reported. The remaining beams can be omitted from the report, thereby reducing UCI overhead. In addition, in order to obtain a unique CSI report, it is optionally necessary to maintain a fixed number of reported beams (lower than the number of measured beams). For example, the UE sends: {CRI_1, CRI_2, CRI_3, CRI_4, CRI_5}, that is, the UE reports 5 beams with L1-RSRP>Max-3dB, where Max is the maximum measured value.

[0164] In some embodiments, in the beam prediction scenario of BM-Case2, the first node may report beam information by dynamically selecting a hybrid method of CRI / SSBRI (beam index) and bitmap index. The specific rules are as follows: Case 1, a small number of beams (M is small): directly reuse the CRI / SSB RI encoding of BM-Case1 to reduce the parsing complexity on the network (NW) side. Case 2, a large number of beams (M is large): use bitmap compression indication to reduce the uplink control information (UCI) bit overhead. Case 3, multiple time instances (T increases): combine CRI / SSB RI and bitmap index to balance accuracy and efficiency.

[0165] In some embodiments, key parameters for determining the bitmap index or resource subset index include at least one of: the number M of candidate beams in the first information; the number of beams measured by the first node; or the number of future time instances of beam measurement reports.

[0166] In some embodiments, the beam indication information is indicated by a time-layered bitmap and CRI / SSB RI indicating the M target beams in the resource set. The CRI / SSBRI can be the index of the key beam, such as the four stable beams {CRI_1, CRI_2, CRI_3, CRI_4}. This method can reduce UCI overhead. The use of CRI / SSBRI for stable beams can ensure prediction accuracy, while the time-layered bitmap can improve dynamic adaptability. The time-layered bitmap is shown in the following table:

[0167]

[0168] In some embodiments, the beam indication information is indicated by a compressed bitmap and CRI / SSB RI. This embodiment is mainly applicable to scenarios with ultra-large scale M (such as M≥32) and a large number of time instances (such as T≥8). For example, the number of measurement beams (N) is 32, the number of reported beams (M) is 16, and the number of future time instances is 8. The first 6 beams with larger measurement values are indicated by CRI / SSB RI, such as {CRI_1, CRI_2, CRI_3, CRI_4, CRI_5, CRI_6}, and the 10 beams with the second largest measurement values are represented by a Huffman compressed bitmap. For example, 0000111100001111 is compressed to 110 1001 0111 after Huffman encoding. The advantage of this embodiment is that Huffman encoding significantly reduces the number of UCI bits, and the CRI / SSB RI of the key beams can ensure the reliability of network-side analysis.

[0169] In some embodiments, the first mode may be any one of the following beam management modes: BM-Case1, BM-Case2, BM-Case3, BM-Case4, BM-Case5, BM-Case6, BM-Case7, or BM-Case8.

[0170] In some embodiments, the value of the number of beams M is related to at least one of the following key parameters: signal quality, channel change rate, first node capability information, historical beam prediction accuracy, or UCI feedback overhead. For example, the UE / gNB may dynamically adjust the value of M based on one or more of the following key parameters: signal quality, channel change rate, UE speed, historical beam prediction accuracy, UCI feedback overhead, NW-configured X dB threshold, or UE capability information.

[0171] For example, when the SNR is high, the UE can report more beams to improve the stability of AI / ML prediction. When the SNR is low, the UE can report fewer beams to reduce the UCI burden. For another example, when the channel changes drastically (such as UE moving at high speed), fewer beams can be reported (M value is small) because the timeliness of the prediction is reduced; when the channel is stable, more beams can be reported (M value is large) to improve the learning ability of the NW end. For another example, for low-speed UEs (such as stationary or slow-moving UEs), more beams can be reported (M value is large); for UEs moving at high speed, fewer beams can be reported (M value is small) to avoid redundant feedback.

[0172] For example, if the AI prediction accuracy is high (such as accuracy > 95%), M can be reduced (such as M = 4); if the accuracy is low (such as accuracy < 80%), M can be increased (such as M = 8, 12, 16). For another example, if UCI resources are limited, the UE needs to reduce M to optimize overhead; if the NW allows a higher number of bits, the UE can increase M. If the NW allows a larger X (such as X = 5dB) dB threshold, the UE can reduce M because some weaker beams do not need to be reported. If the UE has stronger computing power (such as an AI processing unit), a larger M (such as M = 32) can be reported. Alternatively, M can be dynamically selected based on rules, such as adjusting M based on a preset threshold, setting multiple parameter adjustment thresholds under different conditions, such as RSRP> RSPRtarget1, ΔRSRP<1.5 and prediction accuracy> 95%, then M = 16.

[0173] In beam management, the first node needs to report channel state information (CSI) to the second node. Due to the dynamic nature of the wireless channel and resource limitations (such as uplink signaling capacity and UE power consumption), the original channel information cannot be directly transmitted with high precision. Therefore, the reported information needs to be optimized. The optimization methods include quantization optimization, differential coding, and compression algorithms. Among them, the role of quantization optimization is to convert continuous analog information into a discrete digital bit stream while retaining key information as much as possible. Differential coding reports the change in beam information (differential value) rather than the complete beam information. The use of compression algorithms (such as entropy coding) can reduce the transmission overhead of beam information. With regard to quantization optimization, the embodiments provided in this application can reduce quantization error while ensuring the accuracy of beam information.

[0174] The embodiments provided in this application enable the first node to support more flexible and efficient RSRP quantization, as well as support differential L1-RSRP reporting with traditional quantization step and range. Specifically, it can support: larger quantization step and smaller quantization range. In order to optimize the L1-RSRP reporting mechanism of AI / ML in beam management, the embodiments of this application reduce UCI (uplink control information) overhead by enhancing the quantization strategy while maintaining high beam prediction accuracy. The core goal of the enhanced quantization strategy is to introduce a larger quantization step to reduce beam prediction loss while reducing overhead. Or introduce a dynamic quantization strategy to adaptively adjust the quantization step according to UE conditions or network requirements. Or optimize the joint use of differential L1-RSRP and absolute L1-RSRP to improve overall reporting efficiency.

[0175] In some embodiments, a configurable larger quantization step size can be introduced according to the channel environment of the first node, network requirements, and the requirements of the AI beam prediction model, and the quantization step size can be adaptively and dynamically adjusted. For example, the NW (network side) can send quantization step size configurations to the UE, such as standard mode, enhanced mode, and flexible mode. Among them, the standard mode can support existing step sizes: such as 1dB for the best beam and 2dB for the difference; the enhanced mode can support new step sizes: such as 2dB for the best beam and 4dB for the difference (reducing UCI overhead); the flexible mode can support adaptive step sizes, such as adjusting the quantization step size based on UE feedback. In a high SNR environment (i.e., a stable channel), a larger quantization step size (such as 4dB) can be used to reduce the number of reported bits. In a low SNR environment (i.e., large channel fluctuations), a smaller quantization step size (~1-2dB) can be used to improve prediction accuracy.

[0176] In some embodiments, feature parameters can be input into a second model (such as a reinforcement learning model) to obtain the quantization step size output by the second model. This embodiment is an adaptive quantization driven by AI on the UE side, such as inputting SNR, channel quality (CQI), historical beam selection data or UE motion status into the second model to output the corresponding optimal quantization step size (such as 1dB, 2dB or 4dB). Optionally, a dynamic adjustment strategy can also be combined. For example, if the historical Top-1 prediction accuracy loss is <5%, the quantization step size is relaxed (reducing UCI overhead); if the prediction accuracy drops too fast (such as >5%), the quantization step size is reduced to improve the accuracy.

[0177] For example, the names and descriptions of some characteristic parameters are shown in the following table.

[0178]

[0179] In some embodiments, the maximum RSRP value in the beam measurement report is quantized into a 7-bit value in the range of [-140, -44] dBm with a 1 dB step, and the differential RSRP is quantized into a 4-bit value with a 2 dB step.

[0180] It should be understood that a 7-bit binary number can represent a maximum of 2=128 different values. The number of RSRP values that can be represented: -44-(-140)=96 (dB), 96 values with 1dB steps can just be taken within the range of 7 bits (128 possible values). A 4-bit binary number can represent a maximum of 2=16 different values. For BM-case2, the RSRP value of the quantified reasoning result in the report at multiple future time instances is based on the maximum RSRP value predicted for all time instances as the reference RSRP, and the differential RSRP in the report is calculated relative to the reference RSRP. The report can also indicate the time instance information of the beam with the maximum RSRP.

[0181] In some embodiments, the beam measurement report is quantized using differential L1-RSRP quantization and / or absolute L1-RSRP quantization strategies. For example, in high channel quality (high SNR) scenarios, differential L1-RSRP (such as a quantization step of 4dB) is used to reduce uplink feedback; in low channel quality (low SNR) scenarios, absolute L1-RSRP (such as a quantization step of 1dB or 2dB) is used to improve accuracy.

[0182] In some embodiments, the first node may receive configuration information indicating a quantization step size for the beam measurement report; the quantization step size is determined based on at least one of the first node's channel environment, network requirements, or requirements of the first model. The configuration information may be carried via RRC signaling and indicates the available quantization step sizes for the first node. For example, the network node may configure the UE to adopt a hybrid mode, using absolute L1-RSRP for the top N best beams and differential L1-RSRP for the remaining beams.

[0183] As mentioned above, there is a certain time interval between the training phase and the inference phase. Changes in radio parameters / conditions may cause errors in the inference phase. The training model will be continuously revised based on the results of model monitoring. This application also aims to ensure the consistency of the model in the training phase and the inference phase. Compared with other beam management technologies, by utilizing AI / ML-enabled beam management, terminal devices can experience reduced latency, reduced overhead, reduced power consumption, and improved signal quality.

[0184] In a possible embodiment, the terminal device receives the first configuration information. As an example, the terminal device may receive the first configuration information sent by the network device. As an example, the terminal device may receive the first configuration information indicated by higher-layer signaling.

[0185] The first configuration information is used to indicate an association ID, which may also be referred to as a correlation ID. The association ID is used to indicate the use of a consistent resource index during the model training and model inference phases of the first model, or the association ID is used to indicate the use of a consistent resource index within a certain time window during the model training and model inference phases of the first model. By introducing the association ID mechanism, the consistency of the model training and inference processes can be determined. As an example, during the training and inference process of the first model, the association ID is used to ensure consistency between the first beam set and the second beam set.

[0186] As an example, for the first beam set, the difference between the first pointing direction and the first beam width of the physical beam associated with the first beam set during the training phase of the first model and the second pointing direction and the second beam width of the physical beam associated with the first beam set during the training phase of the first model is within a predefined tolerance range.

[0187] As an example, for the second beam set, the difference between the third pointing direction and the third beam width of the physical beam associated with the second beam set during the training phase of the first model and the fourth pointing direction and the fourth beam width of the physical beam associated with the second beam set during the training phase of the first model is within a predefined tolerance range.

[0188] In some embodiments, for the UE-side model in beam management, the UE supports the case where the UE can assume the same association ID during training and inference: the correlation ID can be configured at least within the CSI framework or configured outside the framework, and the correlation ID can also be indicated by other signals and / or other procedures. The UE can assume that DL Tx beams or beam sets / lists associated with the same association ID have similar properties. For the beam prediction of the UE-side AI / ML model, consider at least one of the following aspects to ensure consistency between training and inference of the NW-side additional conditions (regarding the consistency of set A and set B) of UE inference:

[0189] First, order / index consistency: During training and inference, the resource order (e.g., resource index consistency) of beams in Set B and Set A must be consistent. Index allocation rules: A1: A fixed mapping table can be used to maintain the same beam index mapping during training and inference. Unique identifiers (UUIDs) are used to label beam resources in Set A and Set B to prevent index drift. The network (NW) can provide index mappings in signaling to ensure that UEs use consistent resource indexes during training and inference. The base station (BS) periodically broadcasts the index mapping table, and UEs can update indexes based on this table. Historical index buffering: The UE maintains index mappings for a period of time to prevent index inconsistencies caused by short-term channel fluctuations. A2: Time-synchronized index management can be used. This can be based on a sliding window mechanism: Due to the rapidly changing wireless environment of the UE, a sliding window algorithm can be used to maintain index consistency within a certain time window. If the index changes, the UE uses the most recently matched index in the historical window to reduce inference errors. Alternatively, a time synchronization strategy can be used: a unified timestamp is used during training and inference to ensure data source consistency. Alternatively, synchronous frame numbering may be used, and the UE and BS may compare frame numbers to ensure index consistency.

[0190] Second, beam shape consistency: For each set A resource, the difference between the pointing direction and beam width of the physical beam associated with the set A resource during training and the pointing direction and beam width of the physical beam associated with the same set A resource during inference should be within a predefined tolerance range. Similarly, for each set B resource, the difference between the pointing direction and beam width of the physical beam associated with the set B resource during training and the physical beam associated with the same set B resource during inference should be within a predefined tolerance range.

[0191] Third, beam direction consistency: During the training phase, the beam directions corresponding to each set of A and B resources are recorded. During the inference phase, the direction drift in the current environment is calculated and compensated. Kalman filtering-based direction prediction can be used to use historical direction data to predict the optimal direction of the current beam.

[0192] θpred=αθprev+(1-α)θcurrent

[0193] Where α is a smoothing factor that ensures that the direction change is within the allowed range. θpred is the predicted beam angle, θprev is the previous beam angle, and θcurrent is the current beam angle.

[0194] Fourth, beam width consistency: During the training phase, the beam width is recorded. During the inference phase, the deviation of the beam width in the current environment is calculated. If it exceeds the threshold, the UE's beamforming algorithm is adjusted to make it close to the beam width during training.

[0195] For AI / ML-based CSI prediction, the total number of CPU limits and CPU usage for each CSI report, since CSI reports can carry AI / ML inference results. Typically, the CPU determination behavior is also defined based on the priority value of the CSI report. When the UE is configured to process multiple CSI reports, there may be a situation where the UE must send two conflicting CSI reports, that is, if the time occupancy of the physical channel scheduled to carry the CSI report overlaps in at least one OFDM symbol transmitted by the same CC, then it can be said that the two CSI reports have conflicted. Therefore, the UE can follow some priority rules to decide which CSI reports have higher or lower priority. In the traditional design, the UE selects to process up to M CSI reports (with the highest priority) so that the total CPU resources required do not exceed the available CPU. The remaining NM CSI reports (with the lowest priority) are not updated. Since AI / ML-based BM utilizes the CSI framework, it is important to discuss potential issues related to scenarios where CSI reports may involve one or more beam prediction reports. To adapt to AI / ML-enabled CSI reporting, the embodiments of the present application introduce new strategies to determine the priority of CSI reports.

[0196] In a possible embodiment, when N beam measurement reports and the inference results of the first model need to be sent simultaneously, the first node determines the final priority of the N beam measurement reports; wherein the final priority of any one of the N beam measurement reports is related to the weighted sum of the initial priority of the beam measurement report and the priority of the inference result of the first model.

[0197] In some embodiments, the weight value of the initial priority of a single beam measurement report and the weight value of the first model inference result priority are determined based on at least one of CPU occupancy, network side requirements, and measurement report dependency.

[0198] For example, a dynamic weight is assigned to each CSI report (including traditional CSI and AI / ML inference results), and is adjusted based on business needs and computing resource allocation:

[0199] The priority of traditional CSI reports is α, the priority of AI / ML inference results is β, and the total priority of calculations is γ;

[0200] γ=w1*α+w2*β

[0201] Among them, w1 and w2 can be dynamically adjusted according to CPU usage, network side requirements, and measurement report dependencies.

[0202] One embodiment is an adaptive priority adjustment mechanism, which requires real-time monitoring of UE CPU usage (including the UE's current CPU occupancy, available computing resources), and current CSI reporting requirements (CSI requests from the network side, service types), combined with historical CSI reporting data (past CSI reporting modes, validity of reasoning results). The processing capacity of the CSI report is dynamically adjusted based on these parameters. When the CPU occupancy is low: the UE is allowed to send traditional CSI and AI / ML reasoning results at the same time. When CPU resources are tight, if the AI reasoning result depends on the measurement report, the measurement report is prioritized. If the gain of the AI reasoning is greater than the traditional CSI report, the reasoning report is prioritized. If the AI reasoning result can be approximated by historical data, the priority is lowered.

[0203] In some embodiments, the initial priority of the beam measurement report is related to at least one of report type, network requirements, timeliness of report, CPU computing resources, report redundancy, first model inference gain, and first node motion state.

[0204] The factors affecting the priority of CSI reports are shown in the table below:

[0205]

[0206] Based on the above decision factors, CSI reports can be classified and rules can be used to determine their priorities. For example: Set the priority of the report as P: Highest priority (P > 0.8), applicable to critical measurement data (which must be used for network optimization or AI inference), CSI reports with low latency requirements (such as critical business services), and CSI reports requested by the network. Medium priority (0.5 < P ≤ 0.8), important but non-critical measurement reports, CSI reports partially supplemented by historical data, and AI inference reports that can be processed when computing resources permit. Low priority (P ≤ 0.5): CSI reports that can be inferred from historical data, redundant CSI data that can be discarded when computing resources are tight, and non-critical CSI reports with low-impact services.

[0207] Based on the prediction results of the AI model, the UE can adjust the priority allocation strategy: Calculate the priority weight of each CSI report: The weight of the priority is related to the value of measurement data, inference accuracy, historical trend, inference gain, computing resource consumption, and network demand. Different priority thresholds can be set: High priority (P > 0.8): CSI reports that must be sent (critical measurement data, key outputs of AI inference). Medium priority (0.5 < P ≤ 0.8): Important CSI reports (measurement results that can be supplemented by historical data). Low priority (P ≤ 0.5): CSI reports that can be ignored or delayed (redundant information). When the CPU load is high, reduce the update frequency of low-priority CSI reports. Allow AI inference reports to be compressed or approximated within an acceptable error range to reduce computing overhead. The network can send feedback to the UE to indicate which CSI reports are more important on the core network side, so that the UE can optimize resource allocation. If a certain CSI report is discarded for a long time or the system performance is affected after priority adjustment, the AI / ML model will automatically learn and adjust the weight calculation method.

[0208] For beam prediction (BM) applications, the dynamic priority adjustment strategy can be further optimized: Short-term prediction priority: When the network environment changes rapidly (such as user movement), increase the priority of real-time AI inference results. When the channel is stable, reduce the priority of real-time reports and use historical data to supplement. Multi-level priority framework: Highest priority: CSI measurement reports closely related to AI inference. Medium priority: Traditional CSI reports updated periodically. Low priority: Redundant measurement data, or data that can be compensated by AI inference. When CPU resources are tight, prioritize critical CSI reports and AI inference tasks. Continuously optimize the CSI report strategy using machine learning to improve communication efficiency. By extending the priority rules through these strategies, ensure that AI / ML-enabled CSI reports can efficiently manage CPU resources and meet the network-side requirements.

[0209] As described above in conjunction with Figures 1 to 10 ,the method embodiments of this application are described in detail. Next, in conjunction with Figures 11 to 14 , the device embodiment of the present application is described in detail. It should be understood that the description of the method embodiment corresponds to the description of the device embodiment, so for parts not described in detail, reference can be made to the previous method embodiment.

[0210] Figure 11 The embodiment of the present application provides a first node for wireless communication. The first node may be a terminal device or a network device. Figure 11 As shown, the first node 1100 includes a first transceiver module 1110 .

[0211] The first transceiver module 1110 is configured to receive first information, where the first information includes the number of beams M, where M is a positive integer; and send a beam measurement report in a first mode, where the beam measurement report includes a beam measurement result based on the first model and corresponding beam indication information.

[0212] The beam indication information corresponds to the beam number M and the quantity threshold; the beam indication information is indicated by the candidate resource information in the resource set, the resource set includes a first beam set and / or a second beam set, and the first model corresponds to the first beam set and the second beam set.

[0213] In some possible embodiments, the beam indication information is indicated by candidate resource information in a resource set, including at least one of the following:

[0214] The beam indication information is indicated by a bitmap index of a candidate resource in a resource set;

[0215] The beam indication information is indicated by a resource subset index of the candidate resources in the resource set;

[0216] The beam indication information is indicated by a beam index of a candidate resource in the resource set.

[0217] In some possible embodiments, when M≤L1, the beam indication information is indicated by indicating a resource subset index of the M target beams in the resource set;

[0218] When L1<M≤L2, the beam indication information is indicated by a bitmap index indicating M target beams in the resource set;

[0219] When M≥L2 or the number of future time instances increases to a set value, the beam indication information is indicated by the bitmap index and resource subset index of the M target beams in the resource set, where L1 is the first threshold, L2 is the second threshold, L1<L2, L1 and L2 are positive integers, and the quantity threshold includes the first threshold and / or the second threshold.

[0220] In some possible embodiments, the beam measurement report is used to perform a first operation;

[0221] The first operation includes at least one of the following: determining a beam set for training the first model; determining a beam set for inferring the first model; and determining multiple optimal beams in the prediction results of the first model.

[0222] Some possible embodiments further include a first processing module 1120 configured to determine that a key parameter of the bitmap index or resource subset index includes at least one of the following:

[0223] The number M of candidate beams in the first information;

[0224] the number of beams measured by the first node;

[0225] Or, the number of future time instances for beam measurement reports.

[0226] In some possible embodiments, the value of M is related to at least one of the following key parameters: signal quality, channel change rate, capability information of the first node, historical beam prediction accuracy, or UCI feedback overhead.

[0227] In some possible embodiments, the first mode is any one of the following beam management modes: BM-Case1, BM-Case2, BM-Case3, BM-Case4, BM-Case5, BM-Case6, BM-Case7 or BM-Case8.

[0228] As an embodiment, the first transceiver module 1110 may be a transceiver 1330, and the first processing module 1120 may be a processor 1310. The first node 1100 may further include a memory 1320, as specifically shown in FIG16 .

[0229] Figure 12 A second node for wireless communication provided in an embodiment of the present application. The second node may be a device or entity used for positioning on the network side, such as a gNB. Figure 12 As shown, the second node 1200 includes a second transceiver module 1210 .

[0230] The second transceiver module 1210 is configured to send first information, where the first information includes the number of beams M, where M is a positive integer; and receive a beam measurement report in a first mode, where the beam measurement report includes a beam measurement result based on the first model and corresponding beam indication information.

[0231] The beam indication information corresponds to the beam number M and the quantity threshold; the beam indication information is indicated by the candidate resource information in the resource set, the resource set includes a first beam set and / or a second beam set, and the first model corresponds to the first beam set and the second beam set.

[0232] In some possible embodiments, the beam indication information is indicated by candidate resource information in the resource set, including at least one of the following: the beam indication information is indicated by a bitmap index of the candidate resource in the resource set; the beam indication information is indicated by a resource subset index of the candidate resource in the resource set; the beam indication information is indicated by a beam index of the candidate resource in the resource set.

[0233] As an embodiment, when M≤L1, the beam indication information is indicated by indicating a resource subset index of the M target beams in the resource set;

[0234] When L1<M≤L2, the beam indication information is indicated by a bitmap index indicating M target beams in the resource set;

[0235] When M≥L2 or the number of future time instances increases to a set value, the beam indication information is indicated by the bitmap index and resource subset index of the M target beams in the resource set, where L1 is the first threshold, L2 is the second threshold, L1<L2, L1 and L2 are positive integers, and the quantity threshold includes the first threshold and / or the second threshold.

[0236] As an embodiment, the beam measurement report is used to perform a first operation;

[0237] The first operation includes at least one of the following: determining a beam set for training the first model; determining a beam set for inferring the first model; and determining multiple optimal beams in the prediction results of the first model.

[0238] As an embodiment, the maximum RSRP value in the beam measurement report is quantized into a 7-bit value in the range of [-140, -44] dBm with a 1 dB step, and the differential RSRP is quantized into a 4-bit value with a 2 dB step.

[0239] As an embodiment, the value of M is related to at least one of the following key parameters: signal quality, channel change rate, capability information of the first node, historical beam prediction accuracy, or UCI feedback overhead.

[0240] As an embodiment, the first mode is any one of the following beam management modes: BM-Case1, BM-Case2, BM-Case3, BM-Case4, BM-Case5, BM-Case6, BM-Case7 or BM-Case8.

[0241] As an embodiment, the second transceiver module 1210 may be a transceiver 1330. The second node 1200 may further include a memory 1320 and a processor 1310, specifically as follows: Figure 13 shown.

[0242] Figure 13 It is a schematic structural diagram of a communication device according to an embodiment of the present application. Figure 13 The dotted line in the figure indicates that the unit or module is optional. The apparatus 1300 can be used to implement the method described in the above method embodiment. The apparatus 1300 can be a chip, a user equipment or a network device.

[0243] The device 1300 may include one or more processors 1310. The processor 1310 may support the device 1300 to implement the method described in the method embodiment above. The processor 1310 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 another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0244] The apparatus 1300 may further include one or more memories 1320. The memories 1320 store programs that can be executed by the processor 1310, causing the processor 1310 to perform the methods described in the above method embodiments. The memories 1320 may be independent of the processor 1310 or integrated into the processor 1310.

[0245] The apparatus 1300 may further include a transceiver 1330. The processor 1310 may communicate with other devices or chips via the transceiver 1330. For example, the processor 1310 may transmit and receive data with other devices or chips via the transceiver 1330.

[0246] Figure 14 The hardware module diagram of the communication device provided in the embodiment of the present application. Specifically, Figure 14 A block diagram is shown of a first communication device 1450 and a second communication device 1410 communicating with each other in an access network.

[0247] The first communication device 1450 includes a controller / processor 1459, a memory 1460, a data source 1467, a transmit processor 1468, a receive processor 1456, a multi-antenna transmit processor 1457, a multi-antenna receive processor 1458, a transmitter / receiver 1454 and an antenna 1452.

[0248] The second communication device 1410 includes a controller / processor 1475, a memory 1476, a data source 1477, a receive processor 1470, a transmit processor 1416, a multi-antenna receive processor 1472, a multi-antenna transmit processor 1471, a transmitter / receiver 1418 and an antenna 1420.

[0249] During transmission from the second communications device 1410 to the first communications device 1450, at the second communications device 1410, upper layer data packets from the core network or from a data source 1477 are provided to a controller / processor 1475. The core network and data source 1477 represent all protocol layers above the L2 layer. The controller / processor 1475 implements L2 layer functionality. During transmission from the second communications device 1410 to the first communications device 1450, the controller / processor 1475 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation to the first communications device 1450 based on various priority metrics. The controller / processor 1475 is also responsible for retransmission of lost packets and signaling to the first communications device 1450. The transmit processor 1416 and the multi-antenna transmit processor 1471 implement various signal processing functions for the L1 layer (i.e., the physical layer). The transmit processor 1416 implements coding and interleaving to facilitate forward error correction at the second communication device 1410, as well as mapping of signal constellations based on various modulation schemes (e.g., binary phase shift keying, quadrature phase shift keying, M-phase shift keying, and M-quadrature amplitude modulation). The multi-antenna transmit processor 1471 performs digital spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming on the coded and modulated symbols to generate one or more spatial streams. The transmit processor 1416 then maps each spatial stream to a subcarrier, multiplexes it with a reference signal (e.g., a pilot) in the time and / or frequency domain, and then uses an inverse fast Fourier transform to generate a physical channel carrying the time-domain multicarrier symbol stream. The multi-antenna transmit processor 1471 then performs transmit analog precoding / beamforming operations on the time-domain multicarrier symbol stream. Each transmitter 1418 converts the baseband multi-carrier symbol stream provided by the multi-antenna transmit processor 1471 into a radio frequency stream, and then provides it to a different antenna 1420 .

[0250] During transmission from the second communications device 1410 to the first communications device 1450, each receiver 1454 at the first communications device 1450 receives a signal via its corresponding antenna 1452. Each receiver 1454 recovers the information modulated onto the RF carrier and converts the RF stream into a baseband multi-carrier symbol stream, which is provided to the receive processor 1456. The receive processor 1456 and the multi-antenna receive processor 1458 implement various L1 layer signal processing functions. The multi-antenna receive processor 1458 performs receive analog precoding / beamforming operations on the baseband multi-carrier symbol stream from the receiver 1454. The receive processor 1456 uses a fast Fourier transform to convert the baseband multi-carrier symbol stream, after the receive analog precoding / beamforming operations, from the time domain to the frequency domain. In the frequency domain, the receive processor 1456 demultiplexes the physical layer data signal and reference signal, where the reference signal is used for channel estimation. The data signal undergoes multi-antenna detection in the multi-antenna receive processor 1458 to recover any spatial streams destined for the first communications device 1450. The symbols on each spatial stream are demodulated and recovered in the receive processor 1456, and soft decisions are generated. The receive processor 1456 then decodes and deinterleaves the soft decisions to recover the upper layer data and control signals transmitted by the second communication device 1410 on the physical channel. The upper layer data and control signals are then provided to the controller / processor 1459. The controller / processor 1459 implements the functions of the L2 layer. The controller / processor 1459 may be associated with a memory 1460 that stores program codes and data. The memory 1460 may be referred to as a computer-readable medium. During transmission from the second communication device 1410 to the first communication device 1450, the controller / processor 1459 provides demultiplexing between transport and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover the upper layer data packets from the second communication device 1410. The upper layer data packets are then provided to all protocol layers above the L2 layer. Various control signals may also be provided to the L3 layer for L3 processing.

[0251] During transmission from the first communications device 1450 to the second communications device 1410, upper layer data packets are provided to the controller / processor 1459 at the first communications device 1450 using a data source 1467. The data source 1467 represents all protocol layers above the L2 layer. Similar to the transmission functionality at the second communications device 1410 described in the transmission from the second communications device 1410 to the first communications device 1450, the controller / processor 1459 implements header compression, encryption, packet segmentation and reordering, and multiplexing between logical and transport channels, implementing L2 layer functions for both the user plane and the control plane. The controller / processor 1459 is also responsible for retransmission of lost packets and signaling to the second communications device 1410. The transmit processor 1468 performs modulation mapping and channel coding, while the multi-antenna transmit processor 1457 performs digital multi-antenna spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming. The transmit processor 1468 then modulates the resulting spatial stream into a multi-carrier / single-carrier symbol stream. After analog precoding and beamforming operations in the multi-antenna transmit processor 1457, the stream is provided to different antennas 1452 via the transmitter 1454. Each transmitter 1454 first converts the baseband symbol stream provided by the multi-antenna transmit processor 1457 into a RF symbol stream before providing it to the antenna 1452.

[0252] During a transmission from the first communication device 1450 to the second communication device 1410, the functionality at the second communication device 1410 is similar to the reception functionality at the first communication device 1450 described for the transmission from the second communication device 1410 to the first communication device 1450. Each receiver 1418 receives a radio frequency signal via its corresponding antenna 1420, converts the received radio frequency signal into a baseband signal, and provides the baseband signal to a multi-antenna receive processor 1472 and a receive processor 1470. The receive processor 1470 and the multi-antenna receive processor 1472 collectively implement the L1 layer functionality. The controller / processor 1475 implements the L2 layer functionality. The controller / processor 1475 may be associated with a memory 1476 that stores program codes and data. The memory 1476 may be referred to as a computer-readable medium. During transmission from the first communications device 1450 to the second communications device 1410, the controller / processor 1475 provides demultiplexing between transport and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover upper layer data packets from the first communications device 1450. The upper layer data packets from the controller / processor 1475 can be provided to the core network or all protocol layers above the L2 layer, and various control signals can also be provided to the core network or L3 for L3 processing.

[0253] As an embodiment, the first communication device 1450 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used together with the at least one processor.

[0254] As an embodiment, the first communication device 1450 includes: a memory storing a computer-readable instruction program, and the computer-readable instruction program generates an action when executed by at least one processor.

[0255] As an embodiment, the first communication device 1450 corresponds to the first node in this application.

[0256] As an embodiment, the second communication device 1410 corresponds to the second node in this application.

[0257] As an embodiment, the first communication device 1450 is a user equipment, which can serve as a relay node.

[0258] As an embodiment, the first communication device 1450 is a Network Control Relay (NCR).

[0259] As an embodiment, the first communication device 1450 is a relay wireless repeater.

[0260] As an embodiment, the first communication device 1450 is a relay.

[0261] As an embodiment, the second communication device 1410 is a location management function (LMF).

[0262] As an embodiment, the first communication device 1450 corresponds to the first node in this application, and the controller / processor 1159 is used to execute the above method.

[0263] The present application also provides a computer-readable storage medium for storing a program. The computer-readable storage medium can be applied to a terminal or network device provided in the present application, and the program enables a computer to execute the methods performed by the terminal device, network device, or core network entity in various embodiments of the present application.

[0264] The present application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to a terminal or network device provided in the present application, and the program causes a computer to execute the methods performed by the terminal device, network device, or core network entity in various embodiments of the present application.

[0265] The present application also provides a computer program that can be applied to a terminal or network device provided in the present application, and enables a computer to execute the methods performed by the terminal device, network device, or core network entity in various embodiments of the present application.

[0266] It should be understood that the terms "system" and "network" in this application can be used interchangeably. In addition, the terms used in this application are only used to explain the specific embodiments of this application and are not intended to limit this application. The terms "first", "second", "third", and "fourth" in the specification and claims of this application and the accompanying drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0267] In the embodiments of this application, the term "indication" may refer to a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" may refer to a direct indication of B, e.g., B can obtain information through A; it may refer to an indirect indication of B, e.g., A indicates C, e.g., B can obtain information through C; or it may refer to an association between A and B.

[0268] In the embodiment of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0269] In the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and indication, configuration and configuration, etc.

[0270] In the embodiments of the present application, "pre-defined" or "pre-configured" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., including a user device and a network device). The present application does not limit the specific implementation method. For example, pre-defined may refer to information defined in a protocol.

[0271] In the embodiments of the present application, the “protocol” may refer to a standard protocol in the communications field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and the present application does not limit this.

[0272] In the embodiments of this application, the term "and / or" is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0273] In various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean 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 the present application.

[0274] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0275] The units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0276] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0277] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. 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 computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be read by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0278] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method in a first node for wireless communication, characterized in that The method comprises: Receive first information, where the first information includes a beam number M, where M is a positive integer; Sending a beam measurement report in a first mode, the beam measurement report including a beam measurement result based on the first model and corresponding beam indication information; The beam indication information corresponds to the beam number M and the quantity threshold; the beam indication information is indicated by the candidate resource information in the resource set, the resource set includes a first beam set and / or a second beam set, and the first model corresponds to the first beam set and the second beam set.

2. The method according to claim 1, characterized in that The beam indication information is indicated by candidate resource information in a resource set, including at least one of the following: The beam indication information is indicated by a bitmap index of a candidate resource in a resource set; The beam indication information is indicated by a resource subset index of the candidate resources in the resource set; The beam indication information is indicated by a beam index of a candidate resource in the resource set.

3. The method according to claim 1 or 2, characterized in that include: When M≤L1, the beam indication information is indicated by indicating the resource subset index of the M target beams in the resource set; When L1<M≤L2, the beam indication information is indicated by a bitmap index indicating M target beams in the resource set; When M≥L2 or the number of future time instances increases to a set value, the beam indication information is indicated by the bitmap index and resource subset index of the M target beams in the resource set, where L1 is the first threshold, L2 is the second threshold, L1<L2, L1 and L2 are positive integers, and the quantity threshold includes the first threshold and / or the second threshold.

4. The method according to any one of claims 1 to 3, characterized in that The beam measurement report is used to perform a first operation; The first operation includes at least one of the following: determining a beam set for training the first model; determining a beam set for inferring the first model; and determining multiple optimal beams in the prediction results of the first model.

5. The method according to claim 2 or 3, characterized in that The key parameters for determining the bitmap index or resource subset index include at least one of the following: The number M of candidate beams in the first information; the number of beams measured by the first node; Or, the number of future time instances for beam measurement reports.

6. The method according to any one of claims 1 to 5, characterized in that The value of M is related to at least one of the following key parameters: signal quality, channel change rate, capability information of the first node, historical beam prediction accuracy, or UCI feedback overhead.

7. The method according to any one of claims 1 to 6, characterized in that The first mode is any one of the following beam management modes: BM-Case1, BM-Case2, BM-Case3, BM-Case4, BM-Case5, BM-Case6, BM-Case7 or BM-Case8.

8. The method according to any one of claims 1 to 7, characterized in that The maximum RSRP value in the beam measurement report is quantized into a 7-bit value within the range of [-140, -44] dBm with a step size of 1 dB, and the differential RSRP is quantized into a 4-bit value with a step size of 2 dB.

9. The method according to any one of claims 1 to 8, characterized in that Also includes: receiving configuration information, where the configuration information is used to indicate a quantization step size of the beam measurement report; The quantization step size is determined according to at least one of a channel environment of the first node, a network requirement, or a requirement of the first model.

10. The method according to any one of claims 1 to 9, characterized in that Also includes: inputting feature parameters into the second model; Obtain a quantization step size output by the second model, where the characteristic parameter includes at least one of the following: signal-to-noise ratio, RSRP change rate, speed of the first node, channel prediction error, historical prediction accuracy, or UCI overhead.

11. The method according to any one of claims 1 to 10, characterized in that Also includes: The beam measurement report is quantized using a differential L1-RSRP quantization and / or an absolute L1-RSRP quantization strategy.

12. The method according to any one of claims 1 to 11, characterized in that Receive first configuration information, where the first configuration information is used to indicate an association identifier ID; The association ID is used to indicate that a consistent resource index is used during the model training and model reasoning stages of the first model, or the association ID is used to indicate that a consistent resource index is used within a certain time window during the model training and model reasoning stages of the first model.

13. The method according to claim 12, characterized in that For the first beam set, a difference between a first pointing direction and a first beamwidth of a physical beam associated with the first beam set during a training phase of the first model and a second pointing direction and a second beamwidth of the physical beam associated with the first beam set during the training phase of the first model is within a predefined tolerance range; For the second beam set, the difference between the third pointing direction and the third beam width of the physical beam associated with the second beam set during the training phase of the first model and the fourth pointing direction and the fourth beam width of the physical beam associated with the second beam set during the training phase of the first model is within a predefined tolerance range.

14. The method according to any one of claims 1 to 13, characterized in that Also includes: When it is necessary to simultaneously send measurement reports of multiple beams and the inference result of the first model, determining final priorities of the measurement reports of the multiple beams; The final priority of the measurement report of any one of the measurement reports of the multiple beams is related to the weighted sum of the initial priority of the measurement report of the beam and the priority of the first model inference result.

15. The method according to claim 14, characterized in that The weight value of the initial priority of the measurement report of the beam and the weight value of the priority of the first model inference result are determined based on at least one of CPU occupancy, network side requirements, and measurement report dependence.

16. The method according to claim 14, characterized in that The initial priority of the beam measurement report is related to at least one of report type, network requirements, timeliness of report, CPU computing resources, report redundancy, first model reasoning gain and first node motion state.

17. A method in a second node for wireless communication, characterized in that: include: Sending first information, where the first information includes the number of beams M, where M is a positive integer; receiving a beam measurement report in a first mode, the beam measurement report including a beam measurement result based on the first model and corresponding beam indication information; The beam indication information corresponds to the beam number M and the quantity threshold; the beam indication information is indicated by the candidate resource information in the resource set, the resource set includes a first beam set and / or a second beam set, and the first model corresponds to the first beam set and the second beam set.

18. The method according to claim 17, characterized in that The beam indication information is indicated by the candidate resource information in the resource set, including at least one of the following: the beam indication information is indicated by the bitmap index of the candidate resource in the resource set; the beam indication information is indicated by the resource subset index of the candidate resource in the resource set; the beam indication information is indicated by the beam index of the candidate resource in the resource set.

19. The method according to claim 17 or 18, characterized in that include: When M≤L1, the beam indication information is indicated by indicating the resource subset index of the M target beams in the resource set; When L1<M≤L2, the beam indication information is indicated by a bitmap index indicating M target beams in the resource set; When M≥L2 or the number of future time instances increases to a set value, the beam indication information is indicated by the bitmap index and resource subset index of the M target beams in the resource set, where L1 is the first threshold, L2 is the second threshold, L1<L2, L1 and L2 are positive integers, and the quantity threshold includes the first threshold and / or the second threshold.

20. The method according to any one of claims 17 to 19, characterized in that The beam measurement report is used to perform a first operation; The first operation includes at least one of the following: determining a beam set for training the first model; determining a beam set for inferring the first model; and determining multiple optimal beams in the prediction results of the first model.

21. The method according to claim 18 or 19, characterized in that The key parameters for determining the bitmap index or resource subset index include at least one of the following: The number M of candidate beams in the first information; The number of beams measured by the first node; Or, the number of future time instances for beam measurement reports.

22. The method according to any one of claims 17 to 21, characterized in that The value of M is related to at least one of the following key parameters: signal quality, channel change rate, capability information of the first node, historical beam prediction accuracy, or UCI feedback overhead.

23. The method according to any one of claims 17 to 22, characterized in that The first mode is any one of the following beam management modes: BM-Case1, BM-Case2, BM-Case3, BM-Case4, BM-Case5, BM-Case6, BM-Case7 or BM-Case8.

24. The method according to any one of claims 17 to 23, characterized in that The maximum RSRP value in the beam measurement report is quantized into a 7-bit value within the range of [-140, -44] dBm with a step size of 1 dB, and the differential RSRP is quantized into a 4-bit value with a step size of 2 dB.

25. The method according to any one of claims 17 to 24, characterized in that Also includes: receiving configuration information, where the configuration information is used to indicate a quantization step size of the beam measurement report; The quantization step size is determined according to at least one of a channel environment of the first node, a network requirement, or a requirement of the first model.

26. The method according to any one of claims 17 to 25, characterized in that Sending first configuration information, where the first configuration information is used to indicate an association identifier ID; The association ID is used to indicate that a consistent resource index is used during the model training and model reasoning stages of the first model, or the association ID is used to indicate that a consistent resource index is used within a certain time window during the model training and model reasoning stages of the first model.

27. The method according to claim 26, characterized in that For the first beam set, a difference between a first pointing direction and a first beamwidth of a physical beam associated with the first beam set during a training phase of the first model and a second pointing direction and a second beamwidth of the physical beam associated with the first beam set during the training phase of the first model is within a predefined tolerance range; For the second beam set, the difference between the third pointing direction and the third beam width of the physical beam associated with the second beam set during the training phase of the first model and the fourth pointing direction and the fourth beam width of the physical beam associated with the second beam set during the training phase of the first model is within a predefined tolerance range.

28. A first node for wireless communication, characterized in that: include: A first transceiver module is configured to receive first information, where the first information includes a beam number M, where M is a positive integer; Sending a beam measurement report in a first mode, the beam measurement report including a beam measurement result based on the first model and corresponding beam indication information; The beam indication information corresponds to the beam number M and the quantity threshold; the beam indication information is indicated by the candidate resource information in the resource set, the resource set includes a first beam set and / or a second beam set, and the first model corresponds to the first beam set and the second beam set.

29. The first node according to claim 28, characterized in that The beam indication information is indicated by candidate resource information in a resource set, including at least one of the following: The beam indication information is indicated by a bitmap index of a candidate resource in a resource set; The beam indication information is indicated by a resource subset index of the candidate resources in the resource set; The beam indication information is indicated by a beam index of a candidate resource in the resource set.

30. The first node according to claim 28 or 29, characterized in that include: When M≤L1, the beam indication information is indicated by indicating the resource subset index of the M target beams in the resource set; When L1<M≤L2, the beam indication information is indicated by a bitmap index indicating M target beams in the resource set; When M≥L2 or the number of future time instances increases to a set value, the beam indication information is indicated by the bitmap index and resource subset index of the M target beams in the resource set, where L1 is the first threshold, L2 is the second threshold, L1<L2, L1 and L2 are positive integers, and the quantity threshold includes the first threshold and / or the second threshold.

31. The first node according to any one of claims 28 to 30, characterized in that The beam measurement report is used to perform a first operation; The first operation includes at least one of the following: determining a beam set for training the first model; determining a beam set for inferring the first model; and determining multiple optimal beams in the prediction results of the first model.

32. The first node according to claim 29 or 30, characterized in that The invention also includes a first processing module, which is used to determine that the key parameters of the bitmap index or resource subset index include at least one of the following: The number M of candidate beams in the first information; the number of beams measured by the first node; Or, the number of future time instances for beam measurement reports.

33. The first node according to any one of claims 28 to 32, characterized in that The value of M is related to at least one of the following key parameters: signal quality, channel change rate, capability information of the first node, historical beam prediction accuracy, or UCI feedback overhead.

34. The first node according to any one of claims 28 to 33, characterized in that The first mode is any one of the following beam management modes: BM-Case1, BM-Case2, BM-Case3, BM-Case4, BM-Case5, BM-Case6, BM-Case7 or BM-Case8.

35. A second node for wireless communication, characterized in that: include: A second transceiver module is configured to send first information, where the first information includes a beam number M, where M is a positive integer; receiving a beam measurement report in a first mode, the beam measurement report including a beam measurement result based on the first model and corresponding beam indication information; The beam indication information corresponds to the beam number M and the quantity threshold; the beam indication information is indicated by the candidate resource information in the resource set, the resource set includes a first beam set and / or a second beam set, and the first model corresponds to the first beam set and the second beam set.

36. The second node according to claim 35, characterized in that The beam indication information is indicated by the candidate resource information in the resource set, including at least one of the following: the beam indication information is indicated by the bitmap index of the candidate resource in the resource set; the beam indication information is indicated by the resource subset index of the candidate resource in the resource set; the beam indication information is indicated by the beam index of the candidate resource in the resource set.

37. The second node according to claim 35 or 36, characterized in that include: When M≤L1, the beam indication information is indicated by indicating the resource subset index of the M target beams in the resource set; When L1<M≤L2, the beam indication information is indicated by a bitmap index indicating M target beams in the resource set; When M≥L2 or the number of future time instances increases to a set value, the beam indication information is indicated by the bitmap index and resource subset index of the M target beams in the resource set, where L1 is the first threshold, L2 is the second threshold, L1<L2, L1 and L2 are positive integers, and the quantity threshold includes the first threshold and / or the second threshold.

38. The second node according to any one of claims 35 to 37, characterized in that: The beam measurement report is used to perform a first operation; The first operation includes at least one of the following: determining a beam set for training the first model; determining a beam set for inferring the first model; and determining multiple optimal beams in the prediction results of the first model.

39. The second node according to claim 36 or 37, characterized in that: The maximum RSRP value in the beam measurement report is quantized into a 7-bit value within the range of [-140, -44] dBm with a step size of 1 dB, and the differential RSRP is quantized into a 4-bit value with a step size of 2 dB.

40. The second node according to any one of claims 35 to 39, characterized in that: The value of M is related to at least one of the following key parameters: signal quality, channel change rate, capability information of the first node, historical beam prediction accuracy, or UCI feedback overhead.

41. The second node according to any one of claims 35 to 40, characterized in that: The first mode is any one of the following beam management modes: BM-Case1, BM-Case2, BM-Case3, BM-Case4, BM-Case5, BM-Case6, BM-Case7 or BM-Case8.

42. A node used for wireless communication, characterized in that The node comprises a transceiver, a memory and a processor, wherein the memory is used to store a program, and the processor is used to call the program in the memory and control the transceiver to receive or send a signal so that the node executes the method according to any one of claims 1 to 16 or 17 to 27.

43. A communication device, characterized in that The device comprises a processor configured to call a program from a memory so as to cause the device to execute the method according to any one of claims 1 to 16 or 17 to 27.

44. A chip, characterized in that The device comprises a processor configured to call a program from a memory so that a device equipped with the chip executes the method according to any one of claims 1 to 16 or 17 to 27.

45. A computer-readable storage medium, characterized in that A program is stored thereon, the program causing a computer to execute the method according to any one of claims 1-16 or 17-27.

46. A computer program product, characterized in that The method comprises a program for causing a computer to execute the method according to any one of claims 1 to 16 or 17 to 27.

47. A computer program, characterized in that The computer program causes a computer to execute the method according to any one of claims 1 to 16 or 17 to 27.

Images