Communication method and device

Abstract

The invention discloses a communication method and device. The method comprises the following steps: receiving an estimation measurement result of a first beam set from a terminal device; determining an estimated measurement result of a second beam set according to a first AI model deployed by the network device and the estimated measurement result of the first beam set, the first AI model being an AI model corresponding to the second beam set in at least one AI model deployed by the network device, and the second beam set comprising the first beam set; and determining a first sending beam from the second beam set according to the estimation measurement result of the second beam set. The AI models are deployed on the network device side and the terminal device side, and compared with the mode that the AI models are only deployed on the network device side or the terminal device side, the effect of carrying out beam management in combination with the AI models is improved.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a communication method and apparatus. Background Technology

[0002] In beam management using artificial intelligence (AI) models, these models can be deployed on network devices or terminal devices for training. Once the AI ​​model is trained, it can infer the optimal beam. The set of input beams for the AI ​​model can be called Set B (SetB), and the set of output beams can be called Set A (SetA). When the beams in SetA change, the AI ​​model trained on SetA1 by the network device or terminal device cannot be used on SetA2. Therefore, the network device or terminal device needs to train and store multiple AI models for multiple SetAs.

[0003] For AI models deployed on terminal devices, the terminal devices need to align the SetA on the network device side with the AI ​​model on the terminal device side using association identifiers. If the association identifiers are defined by each network device itself, the terminal device needs to train and store multiple models for different SetA on different network devices, increasing the burden on the terminal device and affecting the beam management effect. If the association identifiers are uniformly defined by each network device, each network device needs to communicate with each other for beamforming implementation. Although this reduces the burden on the terminal device to some extent, it increases the risk of network devices exposing beamforming implementation, affecting the beam management effect. For AI models deployed on network devices, the network device uses the same AI model for beam management across different terminal devices. Therefore, the beam management effect of AI models deployed on network devices is not as good as that of AI models deployed on terminal devices.

[0004] It is evident that the current performance of beam management using AI models deployed in conjunction with terminal or network devices is poor. Summary of the Invention

[0005] This application provides a communication method and apparatus to improve the effectiveness of beam management combined with AI models.

[0006] In a first aspect, embodiments of this application provide a communication method applicable to a network device, such as a network equipment, other devices including network equipment functions, a chip system (or chip), or other functional modules capable of implementing the functions of the network equipment, and such chip system or functional modules are disposed, for example, within the network equipment. The method includes: receiving an estimated measurement result of a first beam set from a terminal device; determining an estimated measurement result of a second beam set based on a first AI model deployed by the network device and the estimated measurement result of the first beam set, wherein the first AI model is an AI model corresponding to the second beam set among at least one AI model deployed by the network device, and the second beam set includes the first beam set; and determining a first transmission beam from the second beam set based on the estimated measurement result of the second beam set.

[0007] In this embodiment, the estimated measurement result of the first beam set can be either the input of an AI model deployed on the network device or the output of an AI model deployed on the terminal device. That is, AI models are deployed on both the network device and terminal device sides; for example, the terminal device side deploys an AI model of SetB-SetA*, and the network device side deploys an AI model of SetA*-SetA. Compared to deploying only the SetB-SetA AI model on the terminal device side, since the AI ​​model with the estimated measurement result of SetA as its output is deployed on the network device side, the terminal device does not need to use association identifiers to align the SetA on the network device side with the AI ​​model on the terminal device side, reducing the burden on the terminal device and lowering the risk of the network device exposing beamforming implementation. Compared to deploying only the SetB-SetA AI model on the network device side, since the AI ​​model with the actual measurement result of SetB as its input is deployed on the terminal device side, the network device uses different AI models for beam management for different terminal devices. This improves the effectiveness of beam management combined with AI models.

[0008] In one possible implementation, the method further includes: sending first information to the terminal device, the first information being used to configure the first beam set and the third beam set, wherein the actual measurement result of the third beam set is the input to the second AI model deployed on the terminal device, and the estimated measurement result of the first beam set is the output of the second AI model.

[0009] In this embodiment, the network device can configure a first beam set and a third beam set for the terminal device, so that the terminal device can input the actual measurement results of the third beam set into the second AI model deployed by the terminal device to obtain the estimated measurement results of the first beam set.

[0010] In one possible implementation, the second AI model is the AI ​​model corresponding to the first cell among at least one AI model deployed by the terminal device, and the first cell is the serving cell of the terminal device.

[0011] In this embodiment, since the channel environment of different cells is different, the terminal device can train and store at least one AI model for at least one cell. For example, AI model 1 is trained for cell 1 and AI model 2 is trained for cell 2, thereby improving the beam management effect of the model deployed by the terminal device.

[0012] In one possible implementation, the estimated measurement results of the first beam set include the estimated measurement results of a portion of the beams in the first beam set; the method further includes: determining the estimated measurement results of the other beams in the first beam set besides the portion of beams as a first threshold.

[0013] In this embodiment, if the terminal device reports the estimated measurement results of a portion of the beams in the first beam set, it indicates that the estimated measurement results of the other beams in the first beam set, excluding the portion of the beams, are relatively small, meaning they have a relatively small impact on the first AI model deployed by the network device. Therefore, the network device can determine the estimated measurement results of the other beams in the first beam set, excluding the portion of the beams, as the first threshold, and use the first AI model deployed by the network device for prediction.

[0014] In one possible implementation, the method further includes: sending second information to the terminal device, the second information being used to configure the second beam set; receiving actual measurement results of the second beam set from the terminal device; and determining the performance of the first AI model based on the actual measurement results of the second beam set and the estimated measurement results of the second beam set.

[0015] In this embodiment, a method is provided for a network device to monitor the performance of a first AI model deployed on the network device, for example, by combining actual measurement results of a second beam set with estimated measurement results of the second beam set output by the first AI model to determine the performance of the first AI model.

[0016] In one possible implementation, the method further includes: if the performance of the first AI model does not meet the first condition, re-determining the AI ​​model corresponding to the second beam set from at least one AI model deployed by the network device.

[0017] In this implementation, if the performance of the first AI model does not meet the first condition, it indicates that the second beam set has changed, or that the first AI model is unusable at the current signal-to-noise ratio. Therefore, it is necessary to redetermine the AI ​​model corresponding to the second beam set.

[0018] In one possible implementation, the method further includes: sending third information to the terminal device, the third information being used to configure the first beam set, the second beam set, and the third beam set, and to instruct the terminal device to report the actual measurement results of the second beam set but not to report the actual measurement results of the first beam set and the third beam set; receiving the actual measurement results of the second beam set from the terminal device; using the actual measurement results of the first beam set in the actual measurement results of the second beam set as input, and the actual measurement results of the second beam set as the target output, to train an AI model and obtain the first AI model.

[0019] In this embodiment, a method is provided for a network device to train a first AI model deployed by the network device, for example, by training the first AI model deployed by the network device based on actual measurement results of a second beam set. The terminal device is also instructed to store the actual measurement results of the first beam set and the third beam set, so that the terminal device can train a second AI model deployed by the terminal device based on the actual measurement results of the first beam set and the third beam set.

[0020] In one possible implementation, the third information includes a first channel state information (CSI) report configuration, a second CSI report configuration, and a third CSI report configuration. The first CSI report configuration is used to configure the first beam set, the second CSI report configuration is used to configure the second beam set, and the third CSI report configuration is used to configure the third beam set. The reporting content of the first CSI report configuration and the third CSI report configuration is configured not to be reported, and the first CSI report configuration is associated with the third CSI report configuration.

[0021] In this embodiment, a method is provided for configuring the first, second, and third beam sets with third information. For example, if the first, second, and third beam sets correspond to different CSI report configurations, the reporting content of the CSI report configurations corresponding to the first and third beam sets is configured not to be reported, indicating that the actual measurement results of the first and third beam sets will not be reported. Furthermore, the CSI report configurations corresponding to the first and third beam sets are associated to indicate that the first and third beam sets correspond to the same AI model.

[0022] In one possible implementation, the third information includes a fourth CSI report configuration and a fifth CSI report configuration, wherein the fourth CSI report configuration is used to configure the second beam set, the fifth CSI report configuration is used to configure the first beam set and the third beam set, and the reporting content of the fifth CSI report configuration is configured not to be reported.

[0023] In this embodiment, a method is provided to configure the first, second, and third beam sets with third information. For example, the second beam set corresponds to one CSI report configuration, and the first and third beam sets correspond to another CSI report configuration, indicating that the first and third beam sets correspond to the same AI model. Furthermore, the reporting content of the CSI report configurations corresponding to the first and third beam sets is configured not to be reported, indicating that the actual measurement results of the first and third beam sets will not be reported.

[0024] In one possible implementation, the fifth CSI report configuration includes a first CSI resource configuration and a second CSI resource configuration, wherein the first CSI resource configuration is used to configure the first beam set, and the second CSI resource configuration is used to configure the third beam set; or, the fifth CSI report configuration includes a third CSI resource configuration, wherein the third CSI resource configuration includes a first resource set and a second resource set, wherein the first resource set is used to configure the first beam set, and the second resource set is used to configure the third beam set.

[0025] In this embodiment, multiple methods are provided for the terminal device to distinguish between the first beam set and the third beam set. For example, the first beam set and the third beam set may correspond to different CSI resource configurations under the same CSI report configuration, or the first beam set and the third beam set may correspond to different resource sets under the same CSI resource configuration under the same CSI report configuration.

[0026] In one possible implementation, the third information includes a sixth CSI report configuration and a seventh CSI report configuration, wherein the sixth CSI report configuration is used to configure the second beam set, the seventh CSI report configuration is used for the third beam set, the reporting content of the seventh CSI report configuration is configured not to be reported, and the sixth CSI report configuration is associated with the seventh CSI report configuration.

[0027] In this embodiment, a method is provided for configuring the first beam set, the second beam set, and the third beam set with third information. For example, the second beam set (including the first beam set) and the third beam set correspond to different CSI report configurations. The reporting content of the CSI report configuration corresponding to the third beam set is configured not to be reported, indicating that the actual measurement results of the third beam set are not reported. Furthermore, the CSI report configurations corresponding to the second beam set (including the first beam set) and the third beam set are associated to indicate that the second beam set (including the first beam set) and the third beam set correspond to the same AI model.

[0028] In one possible implementation, the sixth CSI report configuration includes a fourth CSI resource configuration and a fifth CSI resource configuration, wherein the fourth CSI resource configuration is used to configure the beams in the second beam set other than the first beam set, the fifth CSI resource configuration is used to configure the first beam set, and the identifier of the fifth CSI resource configuration is a first identifier, which is used to indicate that the terminal device needs to store the actual measurement results of the first beam set.

[0029] In this embodiment, a method is provided for the terminal device to distinguish between the first beam set in the second beam set and the beams in the second beam set excluding the first beam set. For example, the first beam set and the beams excluding the first beam set correspond to different CSI resource configurations under the same CSI report configuration. Furthermore, the terminal device is instructed to store the actual measurement results of the first beam set, thereby indicating that the first beam set and the third beam set correspond to the same AI model.

[0030] In one possible implementation, the third information includes an eighth CSI report configuration and a ninth CSI report configuration, wherein the eighth CSI report configuration is used to configure beams in the second beam set other than the first beam set, and the ninth CSI report configuration is used for the first beam set and the third beam set.

[0031] In this embodiment, a method is provided to configure the first beam set, the second beam set, and the third beam set with third information. For example, the beams in the second beam set other than the first beam set correspond to one CSI report configuration, and the first beam set and the third beam set correspond to another CSI report configuration, to indicate that the first beam set and the third beam set correspond to the same AI model.

[0032] In one possible implementation, the ninth CSI report configuration includes a sixth CSI resource configuration and a seventh CSI resource configuration, wherein the sixth CSI resource configuration is used to configure the first beam set, the seventh CSI resource configuration is used to configure the third beam set, and the reporting content of the seventh CSI resource configuration is configured not to report or the identifier of the seventh CSI resource configuration is a second identifier, the second identifier being used to indicate that the terminal device does not need to report the actual measurement results of the third beam set; or, the ninth CSI report configuration includes an eighth CSI resource configuration, wherein the eighth CSI resource configuration includes a third resource set and a fourth resource set, the third resource set is used to configure the first beam set, the fourth resource set is used to configure the third beam set, and the reporting content of the fourth resource set is configured not to report or the identifier of the fourth CSI resource configuration is a second identifier, the second identifier being used to indicate that the terminal device does not need to report the actual measurement results of the third beam set.

[0033] In this embodiment, multiple methods are provided for the terminal device to distinguish between the first beam set and the third beam set. For example, the first beam set and the third beam set may correspond to different CSI resource configurations under the same CSI reporting configuration, or the first beam set and the third beam set may correspond to different resource sets under the same CSI resource configuration under the same CSI reporting configuration. Furthermore, the reporting content of the CSI resource configuration corresponding to the third beam set is configured to not be reported or the identifier is set to a second identifier to indicate that the actual measurement results of the third beam set are not reported.

[0034] Secondly, embodiments of this application also provide a communication method, which can be applied to a terminal device, such as a terminal equipment, or other devices including terminal equipment functions, or a chip system (or chip) or other functional module, which can realize the functions of the terminal equipment, and the chip system or functional module is, for example, disposed in the terminal equipment. The method includes: receiving first information from a network device, the first information being used to configure a first beam set and a third beam set; determining an estimated measurement result of the first beam set based on a second AI model deployed by the terminal device and the actual measurement result of the third beam set, wherein the second AI model is an AI model corresponding to a first cell among at least one AI model deployed by the terminal device, and the first cell is the serving cell of the terminal device; and sending the estimated measurement result of the first beam set to the network device.

[0035] In one possible implementation, the method further includes: determining the performance of the second AI model based on the actual measurement results of the first beam set and the estimated measurement results of the first beam set.

[0036] In one possible implementation, the method further includes: if the performance of the second AI model does not meet the first condition, re-determining the AI ​​model corresponding to the first cell from at least one AI model deployed on the terminal device.

[0037] In one possible implementation, the method further includes: receiving third information from the network device, the third information being used to configure the first beam set, the second beam set, and the third beam set, and to instruct the terminal device to report the actual measurement results of the second beam set but not to report the actual measurement results of the first beam set and the third beam set; sending the actual measurement results of the second beam set to the network device; and storing the actual measurement results of the first beam set and the third beam set.

[0038] In one possible implementation, the third information includes a first CSI report configuration, a second CSI report configuration, and a third CSI report configuration, wherein the first CSI report configuration is used to configure the first beam set, the second CSI report configuration is used to configure the second beam set, and the third CSI report configuration is used to configure the third beam set. The reporting content of the first CSI report configuration and the third CSI report configuration is configured not to be reported, and the first CSI report configuration is associated with the third CSI report configuration.

[0039] In one possible implementation, the third information includes a fourth CSI report configuration and a fifth CSI report configuration, wherein the fourth CSI report configuration is used to configure the second beam set, the fifth CSI report configuration is used to configure the first beam set and the third beam set, and the reporting content of the fifth CSI report configuration is configured not to be reported.

[0040] In one possible implementation, the fifth CSI report configuration includes a first CSI resource configuration and a second CSI resource configuration, wherein the first CSI resource configuration is used to configure the first beam set, and the second CSI resource configuration is used to configure the third beam set; or, the fifth CSI report configuration includes a third CSI resource configuration, wherein the third CSI resource configuration includes a first resource set and a second resource set, wherein the first resource set is used to configure the first beam set, and the second resource set is used to configure the third beam set.

[0041] In one possible implementation, the third information includes a sixth CSI report configuration and a seventh CSI report configuration, wherein the sixth CSI report configuration is used to configure the second beam set, the seventh CSI report configuration is used for the third beam set, the reporting content of the seventh CSI report configuration is configured not to be reported, and the sixth CSI report configuration is associated with the seventh CSI report configuration.

[0042] In one possible implementation, the sixth CSI report configuration includes a fourth CSI resource configuration and a fifth CSI resource configuration, wherein the fourth CSI resource configuration is used to configure the beams in the second beam set other than the first beam set, the fifth CSI resource configuration is used to configure the first beam set, and the identifier of the fifth CSI resource configuration is a first identifier, which is used to indicate that the terminal device needs to store the actual measurement results of the first beam set.

[0043] In one possible implementation, the third information includes an eighth CSI report configuration and a ninth CSI report configuration, wherein the eighth CSI report configuration is used to configure beams in the second beam set other than the first beam set, and the ninth CSI report configuration is used for the first beam set and the third beam set.

[0044] In one possible implementation, the ninth CSI report configuration includes a sixth CSI resource configuration and a seventh CSI resource configuration, wherein the sixth CSI resource configuration is used to configure the first beam set, the seventh CSI resource configuration is used to configure the third beam set, and the reporting content of the seventh CSI resource configuration is configured not to report or the identifier of the seventh CSI resource configuration is a second identifier, the second identifier being used to indicate that the terminal device does not need to report the actual measurement results of the third beam set; or, the ninth CSI report configuration includes an eighth CSI resource configuration, wherein the eighth CSI resource configuration includes a third resource set and a fourth resource set, the third resource set is used to configure the first beam set, the fourth resource set is used to configure the third beam set, and the reporting content of the fourth resource set is configured not to report or the identifier of the fourth CSI resource configuration is a second identifier, the second identifier being used to indicate that the terminal device does not need to report the actual measurement results of the third beam set.

[0045] The beneficial effects of the second aspect and its implementation can be referenced to the beneficial effects of the first aspect and any of its implementations.

[0046] Thirdly, embodiments of this application also provide a communication device. The communication device can be the network device described in the first aspect above. The communication device possesses the functions of the aforementioned network device. The communication device is, for example, a network device, or other device including network device functions, or a chip system (or chip) or other functional module. This chip system or functional module can implement the functions of a network device, and is, for example, disposed within a network device. In one optional implementation, the communication device includes a baseband device and a radio frequency device. In another optional implementation, the communication device includes a processing unit (sometimes also called a processing module) and a transceiver unit (sometimes also called a transceiver module). The transceiver unit can implement both sending and receiving functions. When the transceiver unit implements the sending function, it can be called a sending unit (sometimes also called a sending module), and when the transceiver unit implements the receiving function, it can be called a receiving unit (sometimes also called a receiving module). The sending unit and the receiving unit can be the same functional module, which is called the transceiver unit and can implement both sending and receiving functions; or, the sending unit and the receiving unit can be different functional modules, and the transceiver unit is a collective term for these functional modules.

[0047] In one alternative implementation, the transceiver unit is configured to receive estimated measurement results of a first beam set from a terminal device.

[0048] In one optional implementation, the processing unit is configured to determine the estimated measurement result of the second beam set based on the first artificial intelligence (AI) model deployed by the network device and the estimated measurement result of the first beam set, wherein the first AI model is the AI ​​model corresponding to the second beam set among at least one AI model deployed by the network device, and the second beam set includes the first beam set.

[0049] In an optional implementation, the processing unit is further configured to determine a first transmit beam from the second beam set based on the estimated measurement results of the second beam set.

[0050] Fourthly, embodiments of this application also provide a communication device. The communication device can be the terminal device described in the second aspect above. The communication device possesses the functions of the aforementioned terminal device. The communication device is, for example, a terminal equipment, or other equipment including terminal equipment functions, or a chip system (or chip) or other functional module. The chip system or functional module can implement the functions of the terminal equipment, and the chip system or functional module is, for example, disposed in the terminal equipment. In one optional implementation, the communication device includes a baseband device and a radio frequency device. In another optional implementation, the communication device includes a processing unit (sometimes also called a processing module) and a transceiver unit (sometimes also called a transceiver module). The transceiver unit can implement both sending and receiving functions. When the transceiver unit implements the sending function, it can be called a sending unit (sometimes also called a sending module), and when the transceiver unit implements the receiving function, it can be called a receiving unit (sometimes also called a receiving module). The sending unit and the receiving unit can be the same functional module, which is called the transceiver unit and can implement both sending and receiving functions; or, the sending unit and the receiving unit can be different functional modules, and the transceiver unit is a general term for these functional modules.

[0051] In one optional implementation, the transceiver unit is configured to receive first information from a network device, the first information being used to configure a first beam set and a third beam set.

[0052] In one optional implementation, the processing unit is configured to determine the estimated measurement result of the first beam set based on the second AI model deployed by the terminal device and the actual measurement result of the third beam set, wherein the second AI model is the AI ​​model corresponding to the first cell among at least one AI model deployed by the terminal device, and the first cell is the serving cell of the terminal device.

[0053] In an optional implementation, the transceiver unit is further configured to send the estimated measurement results of the first beam set to the network device.

[0054] Fifthly, a communication device is provided, which can be a network device as described in the first aspect above. The communication device possesses the functions of the aforementioned network device. The communication device is, for example, a network device, or other device including network device functions, or a system-on-a-chip (or chip) or other functional module capable of implementing the functions of a network device, and the system-on-a-chip or functional module is, for example, disposed within a network device. The communication device includes a processor for executing the functions of the network device as described in the first aspect above. Optionally, the communication device further includes a memory. The memory stores a computer program, and the processor is coupled to the memory. When the processor reads the computer program or instructions, it causes the communication device to execute the methods performed by the network device in the aforementioned aspects.

[0055] Sixthly, a communication device is provided, which can be the terminal device described in the second aspect above. The communication device possesses the functions of the terminal device described above. The communication device is, for example, a terminal equipment, or other equipment including the functions of a terminal equipment, or a system-on-a-chip (or chip) or other functional module capable of implementing the functions of a terminal equipment, and the system-on-a-chip or functional module is, for example, disposed in a terminal equipment. The communication device includes a processor for executing the functions of the terminal device described in the second aspect above. Optionally, the communication device further includes a memory. The memory is used to store a computer program, and the processor is coupled to the memory. When the processor reads the computer program or instructions, it causes the communication device to execute the methods executed by the terminal device in the above aspects.

[0056] A seventh aspect provides a communication system including a network device. The network device is used to perform the method described in the first aspect. For example, the network device can be implemented using the communication device described in the third or fifth aspect.

[0057] Optionally, the communication system further includes a terminal device. This terminal device is used to execute the method described in the second aspect above. For example, the terminal device can be implemented using the communication device described in the fourth or sixth aspect.

[0058] Eighthly, a computer-readable storage medium is provided for storing a computer program or instructions that, when executed, cause the methods performed by the terminal device or network device in the above aspects to be implemented.

[0059] Ninthly, a computer program product containing instructions is provided, which, when the computer program or instructions are run on a computer, causes the methods described in the above aspects to be implemented.

[0060] In a tenth aspect, a chip system is provided, including a processor and an interface, the processor being configured to call and execute instructions from the interface to enable the chip system to implement the methods described above. Attached Figure Description

[0061] Figure 1 A schematic diagram of a communication system provided in an embodiment of this application;

[0062] Figure 2 A schematic diagram of a wireless access network intelligent controller provided in an embodiment of this application;

[0063] Figure 3 A schematic diagram of an artificial intelligence module provided in an embodiment of this application;

[0064] Figure 4a This is a schematic diagram illustrating model training for an AI model deployed on a terminal device, provided as an embodiment of this application.

[0065] Figure 4b This is a schematic diagram illustrating model inference based on an AI model deployed on a terminal device, as provided in an embodiment of this application.

[0066] Figure 4c This is a schematic diagram illustrating model training for an AI model deployed on a network device, as provided in an embodiment of this application.

[0067] Figure 4d This is a schematic diagram illustrating model inference based on an AI model deployed on a network device, as provided in an embodiment of this application.

[0068] Figure 5 A flowchart illustrating a communication method provided in an embodiment of this application;

[0069] Figure 6 A flowchart illustrating another communication method provided in an embodiment of this application;

[0070] Figure 7 A flowchart illustrating another communication method provided in an embodiment of this application;

[0071] Figure 8 A flowchart illustrating another communication method provided in an embodiment of this application;

[0072] Figure 9 A schematic diagram of a communication device provided in an embodiment of this application;

[0073] Figure 10 This is a schematic diagram of another communication device provided in an embodiment of this application. Detailed Implementation

[0074] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0075] The technical solutions provided in the embodiments of this application can be applied to communication systems related to the 3rd Generation Partnership Project (3GPP), such as Long Term Evolution (LTE) communication systems, 5th Generation (5G) mobile communication systems (specifically, New Radio (NR) communication systems, or NR communication systems that introduce Multi-Input Multi-Output (MIMO) technology), or they can also be applied to other next-generation mobile communication systems, or other similar communication systems, or communication systems in the future evolution process. Other similar communication systems may include Wireless Fidelity (WiFi), Vehicle-to-Everything (V2X), Internet of Things (IoT) systems, Narrowband Internet of Things (NB-IoT) systems, or the Industrial Internet, etc.

[0076] See Figure 1 This is a schematic diagram of the structure of a communication system provided in an embodiment of this application. Figure 1 As shown, the communication system 1000 may include a radio access network (RAN) 100 and a core network (CN) 200. Optionally, the communication system 1000 may also include the Internet 300.

[0077] The wireless access network 100 includes at least one network device (such as...) Figure 1 Network devices such as 110a and 110b, collectively referred to as network devices 110, and at least one terminal device (such as...) Figure 1 The terminal devices 120a-120j, etc., are collectively referred to as terminal devices 120. The wireless access network 100 may also include other devices, such as wireless repeater devices and / or wireless backhaul devices. Figure 1 (Not shown in the image). Terminal device 120 is connected to network device 110 wirelessly. Network device 110 is connected to core network 200 wirelessly or via wired connection.

[0078] The radio access network 100 can be a 3GPP-related communication system (such as a 5G mobile communication system) or another next-generation mobile communication system (such as a 6G mobile communication system). The radio access network 100 can also be an open RAN (open RAN, O-RAN, or ORAN), a cloud radio access network (CRAN), or a WiFi system. The radio access network 100 can also be a communication system that integrates two or more of the above systems.

[0079] Network device 110, also known as a RAN node, RAN entity, or access node, is used to assist terminal device 120 in achieving wireless access. Network device 110 and its components (such as chips, processing units, or processor modules) can be collectively referred to as network devices. For example, it could be... Figure 1 The network device 110 shown, or it could be Figure 1 The chip (system) in network device 110.

[0080] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a next-generation base station in a 6G mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system, etc. A RAN node can also be a macro base station (such as...) Figure 1 110a), micro base stations or indoor stations (such as Figure 1 RAN nodes can be 110b, relay nodes or donor nodes, or wireless controllers in CRAN scenarios. Optionally, RAN nodes can also be servers, wearable devices, vehicles or in-vehicle equipment, etc. For example, in V2X technology, the RAN node can be a roadside unit (RSU).

[0081] In another possible scenario, multiple RAN nodes can collaborate to assist terminal device 120 in achieving wireless access, with different RAN nodes each implementing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs). The CU can perform the functions of the radio resource control (RRC) protocol and packet data convergence protocol (PDCP) of the base station, and can also perform the functions of the service data adaptation protocol (SDAP). The DU can perform the functions of the radio link control (RLC) layer and medium access control (MAC) layer of the base station, and can also perform some or all of the physical (PHY) layer functions. For specific descriptions of the above protocol layers, please refer to the relevant technical specifications of 3GPP.

[0082] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0083] In different systems, RAN nodes can communicate with different devices. For example, Figure 2As shown, in an ORAN system, RAN nodes (such as CU, DU, or RU) can communicate with the RAN intelligent controller (RIC). RICs include near-real-time RICs (near-RTRIC) and non-real-time RICs (Non-RTRIC).

[0084] Near real-time (NRT) RICs are used for model training and inference. For example, they are used to train artificial intelligence (AI) models and then use these AI models for inference. NRT RICs can obtain information from the network device side and / or the terminal device side from RAN nodes and / or terminal devices. This information can be used as training data or inference data. Optionally, the NRT RIC can deliver inference results to RAN nodes and / or terminal devices. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, the NRT RIC delivers the inference result to the DU, and the DU sends it to the RU.

[0085] Non-real-time RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. Non-real-time RICs can obtain information from the network device side and / or the terminal device side from RAN nodes and / or terminal devices. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminal devices. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, a non-real-time RIC delivers the inference results to a DU, which then forwards them to an RU.

[0086] Near real-time RICs and non-real-time RICs can also be configured as separate network elements. Optionally, near real-time and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be set in RAN nodes (such as CUs or DUs), while non-real-time RICs can be set in operation administration and maintenance (OAM) systems, cloud servers, or other network devices.

[0087] For example, such as Figure 3 As shown, in an ORAN system, network elements are connected via interfaces (e.g., NG, Xn, or F1) or air interfaces. These network element nodes, such as RAN nodes, terminal devices, or one or more devices in the OAM system, are equipped with one or more AI modules (for ease of explanation). Figure 3(Only one is shown in the image). A RAN node can be a single RAN node or multiple RAN nodes, for example, including CU and DU. CU and / or DU can also have one or more AI modules configured. Optionally, a CU can also be split into CU-CP and CU-UP. One or more AI modules are configured in CU-CP and / or CU-UP.

[0088] AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the neural network biases.

[0089] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0090] Terminal equipment 120, also known as terminal, user equipment (UE), mobile station, mobile terminal, etc., and its components (such as chips, processing units, or processor modules) can be collectively referred to as a terminal device. For example, it could be... Figure 1 The terminal device 120 shown, or it could be Figure 1 The terminal device 120 contains a chip (system). The terminal device 120 can be widely used in various scenarios, such as device-to-device (D2D), V2X communication, machine-type communication (MTC), IoT communication, virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, and smart cities. The terminal device 120 can be a mobile phone, tablet, computer with wireless transceiver capabilities, wearable device, vehicle, drone, helicopter, airplane, ship, robot, robotic arm, smart home device, etc.

[0091] In this embodiment, the functions of network device 110 can be executed by modules (such as chips) within network device 110, or by a control subsystem containing the functions of network device 110. This control subsystem containing the functions of network device 110 can be a control center in the aforementioned application scenarios such as smart grids, industrial control, intelligent transportation, and smart cities. Similarly, the functions of terminal device 120 can be executed by modules (such as chips or modems) within terminal device 120, or by a device containing the functions of terminal device 120. This embodiment does not limit the specific technologies or device forms used in network device 110 and terminal device 120.

[0092] The communication system applicable to the embodiments of this application has been briefly introduced above. The relevant technical solutions involved in the embodiments of this application are described below.

[0093] 1) A beam is a communication resource, typically represented by a resource index in protocols. For example, a synchronization signal block (SSB) beam can be represented based on the SSB index. The technique for forming beams is called beamforming. Beamforming refers to adjusting the amplitude and / or phase of a signal so that the radiated signal through an antenna array has a certain directionality. In beamforming, the signal is filtered by a spatial domain transmission filter to achieve amplitude and / or phase adjustment. Different spatial domain transmission filters using different spatial filtering parameters can achieve beams in different directions. Spatial domain transmission filters can also be called spatial filters. From this perspective, a beam can be understood as a spatial filter or spatial parameters.

[0094] The beam used to transmit signals can be called a transmission beam (Txbeam), a spatial domain transmit filter, or spatial transmit parameters (spatial Txparameters). The transmission beam can also refer to the distribution of signal strength in different directions in space after the signal is transmitted through the antenna. From this perspective, the transmission beam can also be a spatial transmission angle (such as azimuth, zenith) or a range of spatial transmission angles (such as azimuth center angle and offset, azimuth uncertainty, azimuth protection range, zenith center angle and offset, zenith uncertainty, zenith protection range, etc.).

[0095] Correspondingly, the beam used to receive signals can be called a reception beam (Rxbeam), a spatial domain receive filter, or spatial receive parameters (spatial Rxparameters). The reception beam can also refer to the signal strength distribution of the wireless signal received from the antenna in different spatial directions. From this perspective, the reception beam can also be a spatial reception angle (such as azimuth, zenith) or a range of spatial reception angles (such as azimuth center angle and offset, azimuth uncertainty, azimuth protection range, zenith center angle and offset, zenith uncertainty, zenith protection range), etc.

[0096] 2) Beam scanning refers to transmitting a beam at a fixed period in a predefined direction within a specific period or time period to cover a specific spatial area. For example, during initial access, terminal equipment needs to synchronize with the system and receive minimum system information. Therefore, SSB is used for scanning and transmission at a fixed period. Channel state information reference signal (CSI-RS) can also use beam scanning technology, but the overhead is too high if all predefined beam directions are to be covered. Therefore, CSI-RS is only transmitted in a specific subset of predefined beam directions based on the location of the terminal equipment being served.

[0097] 3) Beam measurement refers to the process by which network devices or terminal devices measure the quality and characteristics of the received beamformed signal. During beam management, network devices or terminal devices can identify the optimal beam by measuring results such as reference signal receiving power (RSRP), reference signal receiving quality (RSRQ), and signal to interference plus noise ratio (SINR).

[0098] 4) Beam management refers to the establishment and maintenance of a suitable beam pair between network devices and terminal devices. For downlink transmission, the network side needs to select a suitable transmit beam, and the terminal side needs to select a suitable receive beam. Together, they form a beam pair to maintain a good wireless connection. The above beam selection process can also be called service beam selection.

[0099] Beam selection is primarily accomplished through reference signals and corresponding beam measurements. Specifically, the network side configures reference signal resources for the terminal side based on user capabilities and network resources. After configuration, the network side sends the reference signal to the terminal side according to the configuration. The terminal side measures the reference signal and feeds back the measurement results to the network side. The network side then configures the transmission beam based on the measurement results reported by the terminal.

[0100] Currently, in the process of combining AI models for beam management, these AI models can be deployed on network devices or terminal devices for training. Then, after the AI ​​model is trained, the network devices or terminal devices can infer the optimal beam based on the trained AI model.

[0101] For example, an AI model takes as input the actual measurement results of one beam set and outputs the estimated measurement results of another beam set. Network devices or terminal devices then combine the estimated measurement results of the other beam set to select the optimal beam from that set. In this beam set, each beam corresponds to a reference signal, such as an SSB or CSI-RS. The input beam set of the AI ​​model can be an SSB beam set or a CSI-RS beam set, and the output beam set can be a CSI-RS beam set. The input beam set can be a subset of the output beam set, or it may not be a subset of the output beam set. The input beam set can be called set B (SetB), and the output beam set can be called set A (SetA).

[0102] The design of AI models deployed on network devices or terminal devices mainly includes data collection (e.g., collecting training data and / or inference data), model training, model inference, and model performance monitoring. The following sections will introduce AI models deployed on terminal devices and AI models deployed on network devices, respectively.

[0103] A) AI models deployed on terminal devices

[0104] Figure 4a This is a schematic diagram illustrating model training for an AI model deployed on a terminal device, as provided in an embodiment of this application. Figure 4a As shown, the AI ​​model deployed on the terminal device can be trained through the following steps.

[0105] Step 1: The network device configures SetA and SetB for the terminal device simultaneously through the CSI report configuration (ReportConfig) in the RRC message.

[0106] Configuring SetA and SetB can be understood as configuring the reference signal resources for the reference signals corresponding to the beams in SetA and SetB, as well as the reporting method (such as reporting resources and reporting content) for the measurement results of the reference signals corresponding to the beams in SetA and SetB.

[0107] A CSI report configuration can include multiple CSI resource configurations. A CSI resource configuration can include a resource set list. A resource set list can include multiple resource sets, meaning a resource set list can include multiple beam sets.

[0108] When configuring SetA and SetB, network devices need to add indicators or identifiers to allow end devices to distinguish between SetA and SetB. For example, SetA and SetB may belong to different CSI resource configurations under the same CSI reporting configuration, and indicators or identifiers should be added accordingly. Another example is that SetA and SetB may belong to different resource sets under the same CSI resource configuration within the same CSI reporting configuration, and indicators or identifiers should be added accordingly.

[0109] Step 2: The network device sends a reference signal according to the configuration of SetA and SetB, that is, it performs beam scanning on the beams in SetA and SetB.

[0110] Step 3: The terminal device receives reference signals according to the configuration of SetA and SetB, that is, it performs beam measurement on the beams in SetA and SetB. The terminal device obtains and stores the actual measurement results of SetA and SetB.

[0111] Step 4: The network device repeatedly sends the above reference signal. The same terminal device or different terminal devices measure the reference signal multiple times at different locations in the cell. After accumulating enough measurement data, the AI ​​model training is completed on the terminal device or the terminal device-side server.

[0112] Figure 4b This is a schematic diagram illustrating model inference based on an AI model deployed on a terminal device, as provided in an embodiment of this application. Figure 4b As shown, model inference can be performed based on the AI ​​model deployed on the terminal device through the following steps.

[0113] Step 1: The network device configures both SetA and SetB for the terminal device via the CSI report in the RRC message.

[0114] The configuration method for the model inference phase can be the same as that for the model training phase. The difference is that during the model training phase, the terminal device does not measure SetA. The purpose of the network device configuring SetA for the terminal device is for the terminal device to report the estimated measurement result of SetA.

[0115] Step 2: The network device sends a reference signal according to the configuration of SetB, that is, it performs beam scanning on the beams in SetB.

[0116] Step 3: The terminal device receives the reference signal according to the configuration of SetB, that is, it performs beam measurement on the beam in SetB. The terminal device obtains the actual measurement results of SetB and inputs the actual measurement results of SetB into the AI ​​model to obtain the estimated measurement results of SetA.

[0117] Step 4: The terminal device selects the K beams with larger estimated measurement results (i.e., Top-K beams) from SetA according to the configured number of beams to be reported K, and reports the estimated measurement results of the Top-K beams.

[0118] Step 5: Based on the estimated measurement results of the Top-K beams, the network device selects the beam with the largest estimated measurement result (i.e., the Top-1 beam) from the reported Top-K beams as the optimal transmission beam.

[0119] Optionally, the network device performs beam scanning on the Top-K beams, and the terminal device selects the beam with the largest actual measurement result from the Top-K beams (i.e., the Top-1 beam) for reporting.

[0120] Step 6: The network device can repeatedly perform beam scanning on the optimal transmission beam.

[0121] Step 7: The terminal device determines the optimal receiving beam corresponding to the optimal transmitting beam.

[0122] B) AI models deployed on network devices

[0123] Figure 4c This is a schematic diagram illustrating model training for an AI model deployed on a network device, as provided in an embodiment of this application. Figure 4c As shown, the AI ​​model deployed on the network device can be trained through the following steps.

[0124] Step 1: The network device configures both SetA and SetB for the terminal device via the CSI report in the RRC message.

[0125] When configuring SetA and SetB, network devices need to add indicators or identifiers to allow terminal devices to distinguish between SetA and SetB.

[0126] Step 2: The network device sends a reference signal according to the configuration of SetA and SetB, that is, it performs beam scanning on the beams in SetA and SetB.

[0127] Step 3: The terminal device receives the reference signal according to the configuration of SetA and SetB, that is, it performs beam measurement on the beams in SetA and SetB, obtains the actual measurement results of SetA and SetB, and reports them.

[0128] Step 4: The network device repeatedly sends the above reference signal and receives the actual measurement results of the reference signal measured multiple times by the same terminal device or different terminal devices at different locations in the cell. After accumulating enough measurement data, the AI ​​model training is completed on the network device or the server on the network device side.

[0129] Figure 4d This is a schematic diagram illustrating model inference based on an AI model deployed on a network device, as provided in an embodiment of this application. Figure 4b As shown, model inference can be performed based on the AI ​​model deployed on the network device through the following steps.

[0130] Step 1: The network device configures SetB for the terminal device via the CSI report in the RRC message.

[0131] Step 2: The network device sends a reference signal according to the configuration of SetB, that is, it performs beam scanning on the beams in SetB.

[0132] Step 3: The terminal device receives the reference signal according to the configuration of SetB, that is, it performs beam measurement on the beams in SetB. The terminal device obtains the actual measurement results of SetB, and selects all or part of the beams from SetB according to the configured number of beams to be reported, and reports the actual measurement results of all or part of the beams in SetB.

[0133] Step 4: The network device inputs the actual measurement results of all or part of the beams in SetB reported by the terminal device into the AI ​​model to obtain the estimated measurement results of SetA. The beam with the largest estimated measurement result (i.e., the Top-1 beam) is selected as the optimal transmission beam from SetA.

[0134] Optionally, the network device selects the K beams with the largest estimated measurement results from SetA (i.e., the Top-K beams) and performs beam scanning on the Top-K beams, where K is a positive integer. The terminal device selects the beam with the largest actual measurement result from the Top-K beams (i.e., the Top-1 beam) as the optimal transmission beam and reports it.

[0135] Step 6: The network device can repeatedly perform beam scanning on the optimal transmission beam.

[0136] Step 7: The terminal device determines the optimal receiving beam corresponding to the optimal transmitting beam.

[0137] In the model performance monitoring phase, there are currently two most likely ways to monitor the performance of AI models deployed on terminal devices.

[0138] The first method involves network device triggering. The network device configures performance monitoring resources (Configure SetA, or Configure SetA and SetB) and scans the configured beams. After the terminal device takes measurements, it reports the actual measurement results to the network device. Alternatively, the terminal device combines the actual measurement results with the estimated prediction results output by the AI ​​model deployed on the terminal device to calculate performance metrics, and reports the performance metric results to the network device or triggers a performance monitoring event. The network device determines the performance monitoring result based on the reported actual measurement results, the reported performance metrics, or the triggered performance monitoring event.

[0139] The second method involves the terminal device triggering the monitoring. The terminal device first requests performance monitoring resources from the network device, which then configures those resources. After measurement, the terminal device combines the actual measurement results with the estimated prediction results output by the AI ​​model deployed on the terminal device to calculate performance metrics. The terminal device then determines the performance monitoring result based on these metrics.

[0140] For AI models deployed on network devices, the most likely performance monitoring method is currently to trigger the network device, configure performance monitoring resources (configure SetA, or configure SetA and SetB) and scan the configured beams, and after the terminal device measures, it reports the actual measurement results to the network device. The network device combines the actual measurement results with the estimated prediction results output by the AI ​​model deployed on the network device to calculate performance indicators, and determines the performance monitoring results based on the performance indicators.

[0141] Different performance monitoring results will lead to different processing of the AI ​​model, including activation, deactivation, switching, and rollback of the AI ​​model.

[0142] Because the density and distribution of terminal devices within the coverage area of ​​a network device change over time, the beamforming in SetA of the same network device will also change over time. Different network devices implement beamforming differently, and therefore the beamforming in SetA of different network devices will also be different.

[0143] For AI models deployed on terminal devices, when the beam pattern in SetA changes, the AI ​​model trained on SetA1 by the terminal device cannot be used for SetA2. Therefore, the terminal device needs to train and store multiple AI models for multiple SetA. Since the terminal device cannot perceive changes in SetA on the network device side, it needs to use associated identification to align the SetA on the network device side with the AI ​​model on the terminal device side. If the associated identification is defined by each network device itself, the terminal device needs to train and store multiple models for different SetA on different network devices, increasing the burden on the terminal device and affecting the effectiveness of beam management. If the associated identification is uniformly defined by each network device, each network device needs to communicate with each other regarding beamforming implementation. Although this reduces the burden on the terminal device to some extent, it increases the risk of network devices exposing beamforming implementation, affecting the effectiveness of beam management.

[0144] For AI models deployed on network devices, when the beam changes in SetA, the AI ​​model trained on SetA1 cannot be used for SetA2. Therefore, network devices need to train and store multiple AI models for multiple SetA. Network devices can sense changes in SetA on the network device side, so there is no need to configure the aforementioned association identifier. However, since the network device uses the same AI model for beam management across different terminal devices, the efficiency of beam management for different terminal devices using the AI ​​model deployed on the network device is lower than that of the AI ​​model deployed on the terminal device.

[0145] It is evident that the current performance of beam management using AI models deployed in conjunction with terminal or network devices is poor.

[0146] In view of this, embodiments of this application provide a communication method for improving the effectiveness of beam management combined with AI models.

[0147] In the embodiments of this application, "when," "if," and "if" all refer to the device taking corresponding actions under certain objective circumstances, and are not time-limited, nor do they require the device to perform a judgment action, nor do they imply any other limitations. Unless otherwise specified, "if" and "if" can be substituted, and "when" and "in the case of" can be substituted. "When" and "if" / "if" can be substituted.

[0148] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0149] In this document, "used for indication" can include both direct and indirect indication. For example, when descriptive information I is used to indicate information J, it can mean that information I directly indicates information J or indirectly indicates information J, but it does not necessarily mean that information I carries information J.

[0150] Let information J, indicated by information I, be called the information to be indicated. In practice, there are many ways to indicate the information to be indicated, such as, but not limited to, directly indicating the information to be indicated, such as the information itself or its index. It can also be indirectly indicated by indicating other information, where there is a relationship between the other information and the information to be indicated. It can also indicate only a part of the information to be indicated, while the other parts are known or pre-agreed upon. For example, the indication of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) order of various pieces of information, thereby reducing indication overhead to some extent. Simultaneously, common parts of various pieces of information can be identified and indicated uniformly to reduce the indication overhead caused by individually indicating the same information.

[0151] Furthermore, the specific instruction method can also be any existing instruction method, such as, but not limited to, the above-mentioned instruction methods and their various combinations. As described above, for example, when multiple pieces of information of the same type need to be indicated, the instruction methods for different pieces of information may differ. In specific implementation, the required instruction method can be selected according to specific needs. This application embodiment does not limit the selected instruction method. Therefore, the instruction methods involved in this application embodiment should be understood to cover various methods that enable the party to be instructed to obtain the information to be indicated.

[0152] In the embodiments of this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include direct transmission via the air interface or indirect transmission via the air interface by other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which may include direct reception from YY via the air interface or indirect reception from YY via the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0153] Information may undergo necessary processing, such as encoding and modulation, between the source and destination ends, but the destination end can understand the valid information from the source end. Similar statements in the embodiments of this application can be understood in a similar way, and will not be repeated here.

[0154] In this application embodiment, the number of nouns, unless otherwise specified, refers to "singular nouns or plural nouns," that is, "one or more." "At least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " can indicate that the related objects before and after are in an "or" relationship. For example, A / B means: A or B. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c means: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0155] In this application, the ordinal numbers such as "first" and "second" are used to distinguish multiple objects, and are not used to limit the size, content, order, timing, priority, or importance of the multiple objects. For a technical feature, the technical features within that technical feature are distinguished by "A", "B", "C", and "D", and there is no sequential or size order among the technical features described by "A", "B", "C", and "D".

[0156] The solution provided by the embodiments of this application will be described in detail below with reference to the accompanying drawings. In the following description, the communication method provided by the embodiments of this application is applied to... Figures 1-3 The communication system shown is an example. The communication system and application scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of communication systems and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0157] The communication method provided in the embodiments of this application is described below as being executed by a network device and a terminal device.

[0158] When this communication method is implemented by components in a network device and a terminal device, the receiving and transmitting steps can be understood as the component communicating with other components, such as communication between a baseband chip and a radio frequency circuit. In the embodiments of this application, the processing performed by a single execution entity can also be divided into multiple execution entities, which can be logically and / or physically separated. For example, the processing performed by the network device and the terminal device can be divided into execution by at least one of a CU and a DU.

[0159] To facilitate understanding of the embodiments of this application, the first beam set, the second beam set, the third beam set, the first AI model deployed by the network device, and the second AI model deployed by the terminal device involved in the embodiments of this application will be introduced below.

[0160] The first beam set, the second beam set, and the third beam set may each include one or more beams. This application does not limit the number of beams in the first beam set, the second beam set, and the third beam set.

[0161] The first beam set can be referred to as set A* (SetA*), the second beam set can be referred to as set A (SetA), and the third beam set can be referred to as set B (SetB). This application does not limit the names of the first, second, and third beam sets in its embodiments.

[0162] The second beam set may include the first beam set, that is, the first beam set may be a subset of the second beam set. The first beam set may include a third beam set, or may not include the first beam set, that is, the third beam set may or may not be a subset of the first beam set. This application does not limit this aspect.

[0163] The first beam set can be an SSB beam set or a CSI-RS beam set, the second beam set can be a CSI-RS beam set, and the third beam set can be an SSB beam set or a CSI-RS beam set. This application does not limit this specific choice.

[0164] The actual measurement results of the first beam set can be the input to the first AI model deployed by the network device, and the estimated measurement results of the second beam set can be the output of the first AI model deployed by the network device. The first AI model deployed by the network device can be the AI ​​model corresponding to the second beam set among at least one AI model deployed by the network device. The second beam set is the candidate service beam set of the terminal device, that is, the network device can select and determine the transmission beam from the second beam set. The transmission beam is used by the network device to send signals to the terminal device.

[0165] In other words, the network device trains and stores at least one AI model for at least one beam set. For example, AI model 1 is trained for SetA1, and AI model 2 is trained for SetA2. AI model 1 takes the actual measurement results of SetA*1 as input and outputs the estimated measurement results of SetA1 as output. Similarly, AI model 2 takes the actual measurement results of SetA*2 as input and outputs the estimated measurement results of SetA2 as output.

[0166] It is understood that at least one beam set in a beam set may correspond to one AI model, or it may correspond to multiple AI models. This application does not limit this.

[0167] The actual measurement results of the third beam set can be used as input to the second AI model deployed by the terminal device, and the estimated measurement results of the first beam set can be used as output to the second AI model deployed by the terminal device. The second AI model deployed by the terminal device is the AI ​​model corresponding to the first cell among at least one AI model deployed by the terminal device, and the first cell is the serving cell of the terminal device.

[0168] In other words, the terminal device trains and stores at least one AI model for at least one cell. For example, AI model 1 is trained for cell 1, and AI model 2 is trained for cell 2. The input to AI model 1 is the actual measurement result of SetB, and the output of AI model 1 is the estimated measurement result of SetA*1. The input to AI model 2 is the actual measurement result of SetB, and the output of AI model 2 is the estimated measurement result of SetA*2.

[0169] It is understood that at least one cell in a given cell may correspond to one AI model, or it may correspond to multiple AI models. This application does not limit this.

[0170] It is understandable that the input of the second model deployed on the terminal device can always be the actual measurement result of the third beam set. In order to ensure that the input of at least one AI model deployed on the terminal device is always the actual measurement result of the third beam set, the beamforming implementation of the third beam set by different network devices can be the same, or the network device can always configure the third beam set for the terminal device and perform beam scanning on the beams in the third beam set while the first model deployed on the network device and the second model deployed on the terminal device are active.

[0171] See Figure 5 , Figure 5 This is a flowchart illustrating a communication method provided in an embodiment of this application. Figure 5 As shown, the communication method includes the following steps.

[0172] S501, the terminal device sends the estimated measurement result of the first beam set to the network device, and correspondingly, the network device receives the estimated measurement result of the first beam set from the terminal device.

[0173] In this embodiment of the application, the estimated measurement results of the first beam set reported by the terminal device to the network device may include the estimated measurement results of all or part of the beams in the first beam set. The estimated measurement results may include information such as RSRP, RSRQ, and SINR. This embodiment of the application does not limit this.

[0174] One possible implementation, such as Figure 5 As shown, before executing S501, the embodiments of this application may also perform the following steps.

[0175] S501a, The network device sends first information to the terminal device, and correspondingly, the terminal device receives the first information from the network device.

[0176] The first information can be used to configure the first beam set and the third beam set. The first information can be encapsulated or carried in an RRC message, or it can be encapsulated or carried in other messages; this application embodiment does not limit this.

[0177] Configuring the first and third beam sets can be understood as configuring the reference signal resources for the reference signals corresponding to the beams in the first and third beam sets, as well as the reporting method (such as reporting resources and reporting content) for the measurement results of the reference signals corresponding to the beams in the first and third beam sets.

[0178] In order for terminal devices to distinguish between the first beam set and the third beam set, network devices need to add indicators or identifiers when configuring the first beam set and the third beam set.

[0179] For example, the first beam set and the third beam set can belong to different CSI resource configurations under the same CSI report configuration in the RRC message. That is, the first information may include CSI report configuration 1, CSI report configuration 1 may include CSI resource configuration 1 and CSI resource configuration 2, CSI resource configuration 1 can be used to configure the first beam set, and CSI resource configuration 2 can be used to configure the third beam set.

[0180] For example, the first beam set and the third beam set can belong to different resource sets under the same CSI resource configuration under the same CSI report configuration in the RRC message. That is, the first information can include CSI report configuration 1, CSI report configuration 1 can include CSI resource configuration 1, CSI resource configuration 1 can include resource set 1 and resource set 2, resource set 1 can be used to configure the first beam set, and resource set 2 can be used to configure the third beam set.

[0181] S501b: The terminal device determines the estimated measurement result of the first beam set based on the second AI model deployed on the terminal device and the actual measurement results of the third beam set.

[0182] It is understandable that the actual measurement results of the third beam set are the input to the second AI model deployed on the terminal device, and the estimated measurement results of the first beam set are the output of the second AI model deployed on the terminal device.

[0183] To ensure that the terminal device can determine that the actual measurement results of the third beam set are the input to the second AI model deployed on the terminal device, and the estimated measurement results of the first beam set are the output of the second AI model deployed on the terminal device, the network device can send only the reference signals corresponding to the beams in the third beam set to the terminal device according to its configuration, i.e., it only performs beam scanning on the beams in the third beam set. Correspondingly, the terminal device only receives the reference signals corresponding to the beams in the third beam set from the network device according to its configuration, i.e., it only performs beam measurement on the beams in the third beam set, obtaining the actual measurement results of the third beam set. The terminal device can then input the actual measurement results of the third beam set into the second AI model deployed on the terminal device to obtain the actual measurement results of the first beam set.

[0184] It is understandable that after the terminal device determines the estimated measurement results of the first beam set, it can select K1 beams with larger estimated measurement results from the first beam set, based on the configured number of beams to be reported K1, and report the estimated measurement results of these K1 beams to the network device, where K1 is a positive integer. In other words, depending on the configured number of beams to be reported, the estimated measurement results of the first beam set reported by the terminal device to the network device can include the estimated measurement results of all or part of the beams in the first beam set.

[0185] S502. The network device determines the estimated measurement results of the second beam set based on the first AI model deployed by the network device and the estimated measurement results of the first beam set.

[0186] In this embodiment of the application, after the network device receives the estimated measurement results of the first beam set from the terminal device, if the terminal device reports the estimated measurement results of all beams in the first beam set, the network device can input the estimated measurement results of all beams in the first beam set into the first AI model deployed by the network device to obtain the estimated measurement results of the second beam set.

[0187] If the terminal device reports the estimated measurement results of some beams in the first beam set, it means that the estimated measurement results of other beams in the first beam set are small, that is, the impact on the first AI model deployed by the network device is small. Therefore, the network device can determine the estimated measurement results of other beams in the first beam set as the first threshold, and input the estimated measurement results of some beams in the first beam set and the estimated measurement results of other beams in the first beam set into the first AI model deployed by the network device to obtain the estimated measurement results of the second beam set.

[0188] The first threshold can be defined by a standard or it can be pre-configured; this application embodiment does not limit this.

[0189] S503. The network device determines the first transmission beam from the second beam set based on the estimated measurement results of the second beam set.

[0190] In this embodiment of the application, after the network device determines the estimated measurement result of the second beam set, the network device can determine the beam with the largest estimated measurement result from the second beam set as the first transmission beam, i.e. the optimal transmission beam.

[0191] Alternatively, the network device can determine K2 beams with larger estimated measurement results from the second beam set. Here, K2 is a positive integer, and can be standard-defined or pre-configured; this embodiment does not impose such limitations. The network device can send reference signals corresponding to the K2 beams to the terminal device according to its configuration, i.e., perform beam scanning on the K2 beams. Correspondingly, the terminal device can receive the reference signals corresponding to the K2 beams from the network device according to its configuration, i.e., perform beam measurement on the K2 beams to obtain the actual measurement results of the K2 beams. The terminal device can determine the beam with the largest actual measurement result from the K2 beams and report the actual measurement result of that beam to the network device. The network device can determine this beam as the first transmission beam, i.e., the optimal transmission beam.

[0192] It is understandable that network devices can repeatedly scan the optimal transmit beam to allow terminal devices to confirm the optimal receive beam corresponding to the optimal transmit beam.

[0193] One possible implementation, such as Figure 6 As shown, the network device can monitor the performance of the first AI model deployed on the network device through the following steps.

[0194] S601. The network device sends second information to the terminal device, and correspondingly, the terminal device receives the second information from the network device.

[0195] The second information is used to configure the second beam set. This second information may be encapsulated or carried within an RRC message, or it may be encapsulated or carried within other messages; this embodiment does not limit this.

[0196] Configuring the second beam set can be understood as configuring the reference signal resources for the reference signals corresponding to the beams in the second beam set, as well as the reporting method (such as reporting resources and reporting content) for the measurement results of the reference signals corresponding to the beams in the second beam set.

[0197] S602, The terminal device sends the actual measurement results of the second beam set to the network device, and the network device receives the actual measurement results of the second beam set from the terminal device.

[0198] In practice, after the network device configures the second beam set for the terminal device, the network device can send the reference signal corresponding to the beam in the second beam set to the terminal device according to the configuration, that is, perform beam scanning on the beam in the second beam set.

[0199] Accordingly, the terminal device can receive reference signals corresponding to the beams in the second beam set from the network device according to the configuration, that is, perform beam measurement on the beams in the second beam set to obtain the actual measurement results of the second beam set.

[0200] In order for the network device to monitor the performance of the AI ​​model, the terminal device can send the actual measurement results of the second beam set to the network device.

[0201] S603. The network device determines the performance of the first AI model based on the actual measurement results of the second beam set and the estimated measurement results of the second beam set.

[0202] In practice, the network device can determine the actual measurement results of the first beam set from the actual measurement results of the second beam set, input the actual measurement results of the first beam set into the first AI model deployed by the network device, and obtain the estimated measurement results of the second beam set.

[0203] The network device can calculate performance metrics based on the estimated measurement results of the second beam set to determine the performance of the first AI model. The rules for calculating the performance metrics can be standard-defined or pre-configured; this embodiment does not limit this.

[0204] If the performance of the first AI model does not meet the first condition, the network device can re-determine the AI ​​model corresponding to the second beam set from at least one AI model deployed by the network device. The first condition can be standard-defined or pre-configured; this embodiment does not limit its implementation.

[0205] It is understood that the reason why the performance of the first AI model does not meet the first condition may be that the second beam set has changed, or that the first AI model is unusable under the current signal-to-noise ratio. This application embodiment does not limit this.

[0206] One possible implementation, such as Figure 7 As shown, the terminal device can monitor the performance of the second AI model deployed on the terminal device through the following steps.

[0207] S701, the network device sends first information to the terminal device, and correspondingly, the terminal device receives the first information from the network device.

[0208] It is understood that for a detailed description of the first information involved in S701, please refer to the detailed description of the first information in S501a, which will not be repeated here.

[0209] S702. The terminal device can determine the performance of the second AI model based on the actual measurement results of the first beam set and the estimated measurement results of the first beam set.

[0210] In the specific implementation process, after the network device configures the first beam set and the third beam set for the terminal device, the network device can send the reference signals corresponding to the beams in the first beam set and the third beam set to the terminal device according to the configuration, that is, perform beam scanning on the beams in the first beam set and the third beam set.

[0211] Accordingly, the terminal device can receive reference signals corresponding to the beams in the first beam set and the third beam set from the network device according to the configuration, that is, perform beam measurement on the beams in the first beam set and the third beam set to obtain the actual measurement results of the first beam set and the second beam set.

[0212] The terminal device can input the actual measurement results of the third beam set into the second AI model deployed on the terminal device to obtain the estimated measurement results of the first beam set.

[0213] The terminal device can calculate performance indicators based on the actual measurement results and estimated measurement results of the first beam set to determine the performance of the second AI model. The rules for calculating the performance indicators can be standard-defined or pre-configured; this embodiment does not limit this.

[0214] If the performance of the second AI model does not meet the first condition, the terminal device can re-determine the AI ​​model corresponding to the first cell from at least one AI model deployed on the terminal device. The first condition can be standard-defined or pre-configured; this embodiment does not limit its implementation.

[0215] It is understood that the reason why the performance of the second AI model does not meet the first condition may be that the current serving cell of the terminal device has changed, or that the second AI model is unusable under the current signal-to-noise ratio. This application embodiment does not limit this.

[0216] One possible implementation, such as Figure 8 As shown, the network device can train a first AI model deployed by the network device through the following steps, and the terminal device can train a second AI model deployed by the terminal device through the following steps.

[0217] S801. The network device sends third information to the terminal device, and the terminal device receives the third information from the network device accordingly.

[0218] The third information can be used to configure the first beam set, the second beam set, and the third beam set, and to instruct the terminal device to report the actual measurement results of the second beam set but not the actual measurement results of the first beam set and the third beam set. The third information can be encapsulated or carried in an RRC message, or it can be encapsulated or carried in other messages, which is not limited in this embodiment.

[0219] In practice, the third information can instruct the terminal device to report the actual measurement results of the second beam set but not the actual measurement results of the first and third beam sets through one or more of the following methods. This will be described below.

[0220] In Method 1, the third information may include the first channel status information (CSI) report configuration, the second CSI report configuration, and the third CSI report configuration.

[0221] The first CSI report configuration can be used to configure the first beam set, the second CSI report configuration can be used to configure the second beam set, and the third CSI report configuration can be used to configure the third beam set.

[0222] The reporting content of the first and third CSI reports can be configured not to be reported. This means the terminal device can report the actual measurement results of the second beamset; the terminal device can choose not to report the actual measurement results of the first and third beamsets. Furthermore, the terminal device can choose not to store the actual measurement results of the second beamset; the terminal device can store the actual measurement results of the first and third beamsets.

[0223] The first CSI report configuration can be associated with the third CSI report configuration. For example, an association identifier field can be added to both the first and third CSI report configurations. This can be understood as the terminal device being able to determine that the first beam set and the third beam set correspond to an AI model.

[0224] Method 2: The third information may include the fourth CSI report configuration and the fifth CSI report configuration.

[0225] The fourth CSI report configuration can be used to configure the second beam set. The fifth CSI report configuration can be used to configure the first and third beam sets. This can be understood as the terminal device determining that the first and third beam sets correspond to an AI model.

[0226] The fifth CSI report can be configured to not report any content. This means the terminal device can report the actual measurement results of the second beam set; the terminal device can choose not to report the actual measurement results of the first and third beam sets. Furthermore, the terminal device can choose not to store the actual measurement results of the second beam set; the terminal device can store the actual measurement results of the first and third beam sets.

[0227] In order for terminal devices to distinguish between the first beam set and the third beam set, network devices need to add indicators or identifiers when configuring the first beam set and the third beam set.

[0228] For example, the fifth CSI report configuration may include a first CSI resource configuration and a second CSI resource configuration. The first CSI resource configuration can be used to configure a first beam set, and the second CSI resource configuration can be used to configure a third beam set. That is, the first beam set and the third beam set can belong to different CSI resource configurations under the same CSI report configuration in the RRC message.

[0229] For example, the fifth CSI report configuration may include a third CSI resource configuration. This third CSI resource configuration may include a first resource set and a second resource set. The first resource set can be used to configure a first beam set, and the second resource set can be used to configure a third beam set. That is, the first beam set and the third beam set can belong to different resource sets under the same CSI resource configuration within the same CSI report configuration in the RRC message.

[0230] Method 3: The third information may include the sixth CSI report configuration and the seventh CSI report configuration.

[0231] The sixth CSI report configuration can be used to configure the second beam set, and the seventh CSI report configuration can be used for the third beam set.

[0232] The seventh CSI report can be configured to not report any content. This means the terminal device can report the actual measurement results of the second beam set; the terminal device can choose not to report the actual measurement results of the third beam set. Furthermore, the terminal device can choose not to store the actual measurement results of a portion of the beams in the second beam set (i.e., beams other than the first beam set); the terminal device can store the actual measurement results of another portion of the beams in the second beam set (i.e., the first beam set) and the third beam set.

[0233] The sixth CSI report configuration can be associated with the seventh CSI report configuration. For example, an association identifier field can be added to both the sixth and seventh CSI report configurations. This can be understood as the terminal device being able to determine that a portion of the beams in the second beam set (i.e., the first beam set) and the third beam set correspond to an AI model.

[0234] Since the first beam set is a subset of the second beam set, in order for the terminal device to distinguish between the first beam set in the second beam set and the beams in the second beam set other than the first beam set, the network device needs to add an indication or identifier when configuring the second beam set.

[0235] For example, the sixth CSI report configuration may include the fourth CSI resource configuration and the fifth CSI resource configuration. The fourth CSI resource configuration can be used to configure beams in the second beam set other than the first beam set, and the fifth CSI resource configuration can be used to configure the first beam set. The fifth CSI resource configuration is identified by a first identifier, which can be used to indicate that the terminal device needs to store the actual measurement results of the first beam set.

[0236] This can be understood as the terminal device not storing the actual measurement results of the beams in the second beam set other than the first beam set, but the terminal device can store the actual measurement results of the first beam set in the second beam set.

[0237] Method four: The third information may include the configuration of the eighth CSI report and the ninth CSI report.

[0238] Specifically, the eighth CSI report configuration can be used to configure beams in the second beam set other than the first beam set, while the ninth CSI report configuration is used for the first and third beam sets. This can be understood as the terminal device being able to determine that the first and third beam sets correspond to a single AI model.

[0239] In order for terminal devices to distinguish between the first beam set and the third beam set, network devices need to add indicators or identifiers when configuring the first beam set and the third beam set.

[0240] For example, the ninth CSI report configuration may include the sixth CSI resource configuration and the seventh CSI resource configuration. The sixth CSI resource configuration can be used to configure the first beam set, and the seventh CSI resource configuration can be used to configure the third beam set. That is, the first beam set and the third beam set can belong to different CSI resource configurations under the same CSI report configuration in the RRC message.

[0241] The reporting content of the seventh CSI resource configuration is configured to not report or the identifier of the seventh CSI resource configuration is the second identifier. The second identifier is used to indicate that the terminal device does not need to report the actual measurement results of the third beam set.

[0242] For example, the ninth CSI report configuration may include the eighth CSI resource configuration. The eighth CSI resource configuration may include a third resource set and a fourth resource set. The third resource set can be used to configure the first beam set, and the fourth resource set can be used to configure the third beam set. That is, the first beam set and the third beam set can belong to different resource sets under the same CSI resource configuration within the same CSI report configuration in the RRC message.

[0243] The reporting content of the fourth resource set is configured not to be reported, or the identifier of the fourth CSI resource configuration can be a second identifier. The second identifier can be used to indicate that the terminal device does not need to report the actual measurement results of the third beam set.

[0244] This can be understood as follows: the terminal device can report the actual measurement results of all beams in the second beam set (i.e., the first beam set and beams other than the first beam set); the terminal device may not report the actual measurement results of the third beam set. Furthermore, the terminal device may not store the actual measurement results of a portion of the beams in the second beam set (i.e., beams other than the first beam set); the terminal device may store the actual measurement results of another portion of the beams in the second beam set (i.e., beams other than the first beam set) and the third beam set.

[0245] S802, the terminal device sends the actual measurement results of the second beam set to the network device, and stores the actual measurement results of the first beam set and the third beam set. Correspondingly, the network device receives the actual measurement results of the second beam set from the terminal device.

[0246] In the specific implementation process, after the network device configures the first beam set, the second beam set, and the third beam set for the terminal device, the network device can send reference signals corresponding to the beams in the first beam set, the second beam set, and the third beam set to the terminal device according to the configuration, that is, perform beam scanning on the beams in the first beam set, the second beam set, and the third beam set.

[0247] Accordingly, the terminal device can receive reference signals corresponding to the beams in the first beam set, the second beam set, and the third beam set from the network device according to the configuration, that is, perform beam measurement on the beams in the first beam set, the second beam set, and the third beam set to obtain the actual measurement results of the first beam set, the second beam set, and the third beam set.

[0248] In order for the network device to perform AI model training and the terminal device to perform AI model training, the terminal device can send the actual measurement results of the second beam set to the network device, and store the actual measurement results of the first beam set and the third beam set.

[0249] During the AI ​​model training process on the terminal device, the terminal device can use the actual measurement results of the third beam set as input and the actual measurement results of the first beam set as target output to train the AI ​​model and obtain the second AI model.

[0250] It is understandable that the terminal device can repeat the above steps to train the AI ​​model for different cells, obtaining different AI models for different cells. The input to each different AI model is always the actual measurement result of the third beam set. For example, AI model 1 is trained for cell 1, and AI model 2 is trained for cell 2.

[0251] S803, the network device takes the actual measurement results of the first beam set in the actual measurement results of the second beam set as input and the actual measurement results of the second beam set as target output, and trains the AI ​​model to obtain the first AI model.

[0252] During the AI ​​model training process on the terminal device, the network device can determine the actual measurement results of the first beam set from the actual measurement results of the second beam set, use the actual measurement results of the first beam set as input and the actual measurement results of the second beam set as target output, and train the AI ​​model to obtain the first AI model.

[0253] It is understandable that the network device can repeat the above steps to train the AI ​​model for different beam sets, thereby obtaining different AI models corresponding to different beam sets. For example, AI model 1 is trained for SetA1, and AI model 2 is trained for SetA2.

[0254] Based on the above scheme, AI models are deployed on both the network device side and the terminal device side. For example, the terminal device side deploys a SetB-SetA* AI model, and the network device side deploys a SetA*-SetA AI model. Compared to deploying only the SetB-SetA AI model on the terminal device side, since the AI ​​model with the estimated measurement results of SetA as output is deployed on the network device side, the terminal device does not need to use association identifiers to align the SetA on the network device side with the AI ​​model on the terminal device side, reducing the burden on the terminal device and lowering the risk of the network device exposing beamforming implementation. Compared to deploying only the SetB-SetA AI model on the network device side, since the AI ​​model with the actual measurement results of SetB as input is deployed on the terminal device side, the network device uses different AI models for beam management for different terminal devices. This improves the effectiveness of beam management combined with AI models.

[0255] It is understood that the above embodiments of this application can be implemented individually or in combination with each other, and the embodiments of this application are not limited.

[0256] The methods provided in the embodiments of this application above are described using network devices and terminal devices as examples. In this application, each embodiment can be implemented independently or in combination based on certain inherent connections; in each embodiment, different implementation methods can be implemented in combination or independently. To achieve the functions of the methods provided in the embodiments of this application above, the steps executed by the terminal device can be implemented by different functional entities constituting the terminal device. The steps executed by the network device can be implemented by different functional entities constituting the network device. For example, the network device can be a CU-DU architecture, where the CU can generate synchronization signals and the DU can send synchronization signals. To achieve the functions of the methods provided in the embodiments of this application above, the network device and the terminal device can include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is executed in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0257] The methods provided by the embodiments of this application have been described above with reference to the accompanying drawings. The apparatus provided by the embodiments of this application will be described below with reference to the accompanying drawings.

[0258] Based on the same technical concept, embodiments of this application provide a communication device, which includes a module / unit / means for executing the method performed by the device in the above-described method embodiments. This module / unit / means can be implemented in software, or in hardware, or implemented by hardware executing corresponding software.

[0259] For example, see Figure 9 This is a schematic diagram of a communication device 900, which includes a transceiver module 901 and a processing module 902. This device can be the aforementioned network device or terminal device.

[0260] When the device 900 is a network device, the functions of each module of the device 900 are as follows:

[0261] The transceiver module 901 is used to receive the estimated measurement results of the first beam set from the terminal device.

[0262] The processing module 902 is configured to determine the estimated measurement result of the second beam set based on the first artificial intelligence (AI) model deployed by the network device and the estimated measurement result of the first beam set, wherein the first AI model is the AI ​​model corresponding to the second beam set among at least one AI model deployed by the network device, and the second beam set includes the first beam set.

[0263] The processing module 902 is further configured to determine a first transmission beam from the second beam set based on the estimated measurement results of the second beam set.

[0264] In one possible implementation, the transceiver module 901 is further configured to send first information to the terminal device, the first information being used to configure the first beam set and the third beam set, wherein the actual measurement result of the third beam set is the input of the second AI model deployed on the terminal device, and the estimated measurement result of the first beam set is the output of the second AI model.

[0265] In one possible implementation, the second AI model is the AI ​​model corresponding to the first cell among at least one AI model deployed by the terminal device, and the first cell is the serving cell of the terminal device.

[0266] In one possible implementation, the estimated measurement results of the first beam set include the estimated measurement results of a portion of the beams in the first beam set; the processing module 902 is further configured to determine the estimated measurement results of the other beams in the first beam set besides the portion of the beams as a first threshold.

[0267] In one possible implementation, the transceiver module 901 is further configured to send second information to the terminal device, the second information being used to configure the second beam set; receive actual measurement results of the second beam set from the terminal device; and the processing module 902 is further configured to determine the performance of the first AI model based on the actual measurement results of the second beam set and the estimated measurement results of the second beam set.

[0268] In one possible implementation, the processing module 902 is further configured to, if the performance of the first AI model does not meet the first condition, re-determine the AI ​​model corresponding to the second beam set from at least one AI model deployed by the network device.

[0269] In one possible implementation, the transceiver module 901 is further configured to send third information to the terminal device, the third information being used to configure the first beam set, the second beam set, and the third beam set, and to instruct the terminal device to report the actual measurement results of the second beam set but not to report the actual measurement results of the first beam set and the third beam set; and to receive the actual measurement results of the second beam set from the terminal device; the processing module 902 is further configured to use the actual measurement results of the first beam set in the actual measurement results of the second beam set as input, and the actual measurement results of the second beam set as the target output, to train an AI model to obtain the first AI model.

[0270] In one possible implementation, the third information includes a first Channel State Information (CSI) report configuration, a second CSI report configuration, and a third CSI report configuration. The first CSI report configuration is used to configure the first beam set, the second CSI report configuration is used to configure the second beam set, and the third CSI report configuration is used to configure the third beam set. The reporting content of the first CSI report configuration and the third CSI report configuration is configured not to be reported, and the first CSI report configuration is associated with the third CSI report configuration.

[0271] In one possible implementation, the third information includes a fourth CSI report configuration and a fifth CSI report configuration, wherein the fourth CSI report configuration is used to configure the second beam set, the fifth CSI report configuration is used to configure the first beam set and the third beam set, and the reporting content of the fifth CSI report configuration is configured not to be reported.

[0272] In one possible implementation, the fifth CSI report configuration includes a first CSI resource configuration and a second CSI resource configuration, wherein the first CSI resource configuration is used to configure the first beam set, and the second CSI resource configuration is used to configure the third beam set; or, the fifth CSI report configuration includes a third CSI resource configuration, wherein the third CSI resource configuration includes a first resource set and a second resource set, wherein the first resource set is used to configure the first beam set, and the second resource set is used to configure the third beam set.

[0273] In one possible implementation, the third information includes a sixth CSI report configuration and a seventh CSI report configuration, wherein the sixth CSI report configuration is used to configure the second beam set, the seventh CSI report configuration is used for the third beam set, the reporting content of the seventh CSI report configuration is configured not to be reported, and the sixth CSI report configuration is associated with the seventh CSI report configuration.

[0274] In one possible implementation, the sixth CSI report configuration includes a fourth CSI resource configuration and a fifth CSI resource configuration, wherein the fourth CSI resource configuration is used to configure the beams in the second beam set other than the first beam set, the fifth CSI resource configuration is used to configure the first beam set, and the identifier of the fifth CSI resource configuration is a first identifier, which is used to indicate that the terminal device needs to store the actual measurement results of the first beam set.

[0275] In one possible implementation, the third information includes an eighth CSI report configuration and a ninth CSI report configuration, wherein the eighth CSI report configuration is used to configure beams in the second beam set other than the first beam set, and the ninth CSI report configuration is used for the first beam set and the third beam set.

[0276] In one possible implementation, the ninth CSI report configuration includes a sixth CSI resource configuration and a seventh CSI resource configuration, wherein the sixth CSI resource configuration is used to configure the first beam set, the seventh CSI resource configuration is used to configure the third beam set, and the reporting content of the seventh CSI resource configuration is configured not to report or the identifier of the seventh CSI resource configuration is a second identifier, the second identifier being used to indicate that the terminal device does not need to report the actual measurement results of the third beam set; or, the ninth CSI report configuration includes an eighth CSI resource configuration, wherein the eighth CSI resource configuration includes a third resource set and a fourth resource set, the third resource set is used to configure the first beam set, the fourth resource set is used to configure the third beam set, and the reporting content of the fourth resource set is configured not to report or the identifier of the fourth CSI resource configuration is a second identifier, the second identifier being used to indicate that the terminal device does not need to report the actual measurement results of the third beam set.

[0277] Alternatively, when the device 900 is a terminal device, the functions of each module of the device 900 are as follows:

[0278] The transceiver module 901 is used to receive first information from the network device, the first information being used to configure a first beam set and a third beam set;

[0279] The processing module 902 is used to determine the estimated measurement result of the first beam set based on the second AI model deployed on the terminal device and the actual measurement result of the third beam set, wherein the second AI model is the AI ​​model corresponding to the first cell among at least one AI model deployed on the terminal device, and the first cell is the serving cell of the terminal device.

[0280] The transceiver module 901 is also used to send the estimated measurement results of the first beam set to the network device.

[0281] In one possible implementation, the processing module 902 is further configured to determine the performance of the second AI model based on the actual measurement results of the first beam set and the estimated measurement results of the first beam set.

[0282] In one possible implementation, the processing module 902 is further configured to, if the performance of the second AI model does not meet the first condition, re-determine the AI ​​model corresponding to the first cell from at least one AI model deployed on the terminal device.

[0283] In one possible implementation, the transceiver module 901 is further configured to receive third information from the network device, the third information being configured to configure the first beam set, the second beam set, and the third beam set, and to instruct the terminal device to report the actual measurement results of the second beam set but not to report the actual measurement results of the first beam set and the third beam set; to send the actual measurement results of the second beam set to the network device, and to store the actual measurement results of the first beam set and the third beam set.

[0284] In one possible implementation, the third information includes a first Channel State Information (CSI) report configuration, a second CSI report configuration, and a third CSI report configuration. The first CSI report configuration is used to configure the first beam set, the second CSI report configuration is used to configure the second beam set, and the third CSI report configuration is used to configure the third beam set. The reporting content of the first CSI report configuration and the third CSI report configuration is configured not to be reported, and the first CSI report configuration is associated with the third CSI report configuration.

[0285] In one possible implementation, the third information includes a fourth CSI report configuration and a fifth CSI report configuration, wherein the fourth CSI report configuration is used to configure the second beam set, the fifth CSI report configuration is used to configure the first beam set and the third beam set, and the reporting content of the fifth CSI report configuration is configured not to be reported.

[0286] In one possible implementation, the fifth CSI report configuration includes a first CSI resource configuration and a second CSI resource configuration, wherein the first CSI resource configuration is used to configure the first beam set, and the second CSI resource configuration is used to configure the third beam set; or, the fifth CSI report configuration includes a third CSI resource configuration, wherein the third CSI resource configuration includes a first resource set and a second resource set, wherein the first resource set is used to configure the first beam set, and the second resource set is used to configure the third beam set.

[0287] In one possible implementation, the third information includes a sixth CSI report configuration and a seventh CSI report configuration, wherein the sixth CSI report configuration is used to configure the second beam set, the seventh CSI report configuration is used for the third beam set, the reporting content of the seventh CSI report configuration is configured not to be reported, and the sixth CSI report configuration is associated with the seventh CSI report configuration.

[0288] In one possible implementation, the sixth CSI report configuration includes a fourth CSI resource configuration and a fifth CSI resource configuration, wherein the fourth CSI resource configuration is used to configure the beams in the second beam set other than the first beam set, the fifth CSI resource configuration is used to configure the first beam set, and the identifier of the fifth CSI resource configuration is a first identifier, which is used to indicate that the terminal device needs to store the actual measurement results of the first beam set.

[0289] In one possible implementation, the third information includes an eighth CSI report configuration and a ninth CSI report configuration, wherein the eighth CSI report configuration is used to configure beams in the second beam set other than the first beam set, and the ninth CSI report configuration is used for the first beam set and the third beam set.

[0290] In one possible implementation, the ninth CSI report configuration includes a sixth CSI resource configuration and a seventh CSI resource configuration, wherein the sixth CSI resource configuration is used to configure the first beam set, the seventh CSI resource configuration is used to configure the third beam set, and the reporting content of the seventh CSI resource configuration is configured not to report or the identifier of the seventh CSI resource configuration is a second identifier, the second identifier being used to indicate that the terminal device does not need to report the actual measurement results of the third beam set; or, the ninth CSI report configuration includes an eighth CSI resource configuration, wherein the eighth CSI resource configuration includes a third resource set and a fourth resource set, the third resource set is used to configure the first beam set, the fourth resource set is used to configure the third beam set, and the reporting content of the fourth resource set is configured not to report or the identifier of the fourth CSI resource configuration is a second identifier, the second identifier being used to indicate that the terminal device does not need to report the actual measurement results of the third beam set.

[0291] In practical implementation, the above-mentioned device 900 can have various product forms. Several possible product forms are introduced below.

[0292] See Figure 10 The diagram shows another communication device. The communication device 1000 includes a processor 1001, which uses logic circuits or execution instructions to implement the methods executed by the network device or terminal device in the above method embodiments.

[0293] Optionally, the communication device 1000 may further include an interface circuit 1002, which is used to receive signals from other communication devices outside the communication device and transmit them to the processor 1001, or to send signals from the processor 1001 to other communication devices outside the communication device. The processor 1001 and the interface circuit 1002 are coupled to each other. It is understood that the interface circuit 1002 can be a transceiver or an input / output interface.

[0294] Optionally, the communication device 1000 may also include a memory 1003 for storing instructions executed by the processor 1001, or storing input data required by the processor 1001 to execute instructions, or storing data generated after the processor 1001 executes instructions.

[0295] It should be understood that the processor mentioned in the embodiments of this application can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor, implemented by reading software code stored in memory.

[0296] For example, the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0297] It should be understood that the memory mentioned in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0298] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0299] It should be noted that the memories described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0300] Based on the same technical concept, embodiments of this application also provide a computer-readable storage medium storing a computer program or instructions, which, when executed by a processor, causes the methods executed by the network device and the terminal device in the above method embodiments to be implemented.

[0301] Based on the same technical concept, this application also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, cause the methods executed by the network device and the terminal device in the above method embodiments to be implemented.

[0302] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0303] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure One One or more processes and / or boxes Figure One A device that provides the functions specified in one or more boxes.

[0304] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure One One or more processes and / or boxes Figure One The function specified in one or more boxes.

[0305] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure OneOne or more processes and / or boxes Figure One Figure One The steps of the function specified in one or more boxes.

Claims

1. A communication method, characterized in that, include: Receive the estimated measurement results of the first beam set from the terminal device; Based on the first artificial intelligence (AI) model deployed by the network device and the estimated measurement results of the first beam set, the estimated measurement results of the second beam set are determined. The first AI model is the AI ​​model corresponding to the second beam set among at least one AI model deployed by the network device. The second beam set includes the first beam set. Based on the estimated measurement results of the second beam set, the first transmission beam is determined from the second beam set.

2. The method according to claim 1, characterized in that, The method further includes: The terminal device is sent first information, which is used to configure the first beam set and the third beam set. The actual measurement result of the third beam set is the input of the second AI model deployed on the terminal device, and the estimated measurement result of the first beam set is the output of the second AI model.

3. The method according to claim 2, characterized in that, The second AI model is the AI ​​model corresponding to the first cell among at least one AI models deployed by the terminal device, and the first cell is the serving cell of the terminal device.

4. The method according to any one of claims 1-3, characterized in that, The estimated measurement results of the first beam set include the estimated measurement results of a portion of the beams in the first beam set; the method further includes: The estimated measurement results of the other beams in the first beam set, excluding the aforementioned portion of the beams, are determined as the first threshold.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Send second information to the terminal device, the second information being used to configure the second beam set; Receive actual measurement results from the second beam set of the terminal device; The performance of the first AI model is determined based on the actual measurement results of the second beam set and the estimated measurement results of the second beam set.

6. The method according to claim 5, characterized in that, The method further includes: If the performance of the first AI model does not meet the first condition, the AI ​​model corresponding to the second beam set is re-determined from at least one AI model deployed by the network device.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: Send a third message to the terminal device, the third message being used to configure the first beam set, the second beam set, and the third beam set, and to instruct the terminal device to report the actual measurement results of the second beam set but not to report the actual measurement results of the first beam set and the third beam set; Receive actual measurement results from the second beam set of the terminal device; Using the actual measurement results of the first beam set from the actual measurement results of the second beam set as input, and the actual measurement results of the second beam set as the target output, the AI ​​model is trained to obtain the first AI model.

8. The method according to claim 7, characterized in that, The third information includes a first channel state information (CSI) report configuration, a second CSI report configuration, and a third CSI report configuration. The first CSI report configuration is used to configure the first beam set, the second CSI report configuration is used to configure the second beam set, and the third CSI report configuration is used to configure the third beam set. The reporting content of the first CSI report configuration and the third CSI report configuration is configured not to be reported, and the first CSI report configuration is associated with the third CSI report configuration.

9. The method according to claim 7, characterized in that, The third information includes a fourth CSI report configuration and a fifth CSI report configuration. The fourth CSI report configuration is used to configure the second beam set, and the fifth CSI report configuration is used to configure the first beam set and the third beam set. The reporting content of the fifth CSI report configuration is configured not to be reported.

10. The method according to claim 9, characterized in that, The fifth CSI report configuration includes a first CSI resource configuration and a second CSI resource configuration, wherein the first CSI resource configuration is used to configure the first beam set, and the second CSI resource configuration is used to configure the third beam set; or... The fifth CSI report configuration includes a third CSI resource configuration, wherein the third CSI resource configuration includes a first resource set and a second resource set, the first resource set is used to configure the first beam set, and the second resource set is used to configure the third beam set.

11. The method according to claim 7, characterized in that, The third information includes a sixth CSI report configuration and a seventh CSI report configuration. The sixth CSI report configuration is used to configure the second beam set, and the seventh CSI report configuration is used for the third beam set. The reporting content of the seventh CSI report configuration is configured not to be reported, and the sixth CSI report configuration is associated with the seventh CSI report configuration.

12. The method according to claim 11, characterized in that, The sixth CSI report configuration includes a fourth CSI resource configuration and a fifth CSI resource configuration. The fourth CSI resource configuration is used to configure the beams in the second beam set other than the first beam set. The fifth CSI resource configuration is used to configure the first beam set. The identifier of the fifth CSI resource configuration is a first identifier, which is used to indicate that the terminal device needs to store the actual measurement results of the first beam set.

13. The method according to claim 7, characterized in that, The third information includes an eighth CSI report configuration and a ninth CSI report configuration, wherein the eighth CSI report configuration is used to configure the beams in the second beam set other than the first beam set, and the ninth CSI report configuration is used for the first beam set and the third beam set.

14. The method according to claim 13, characterized in that, The ninth CSI report configuration includes a sixth CSI resource configuration and a seventh CSI resource configuration. The sixth CSI resource configuration is used to configure the first beam set, and the seventh CSI resource configuration is used to configure the third beam set. The reporting content of the seventh CSI resource configuration is configured not to report, or the identifier of the seventh CSI resource configuration is a second identifier, which indicates that the terminal device does not need to report the actual measurement results of the third beam set; or... The ninth CSI report configuration includes an eighth CSI resource configuration, wherein the eighth CSI resource configuration includes a third resource set and a fourth resource set. The third resource set is used to configure the first beam set, and the fourth resource set is used to configure the third beam set. The reporting content of the fourth resource set is configured not to report, or the identifier of the fourth CSI resource configuration is a second identifier, which is used to indicate that the terminal device does not need to report the actual measurement results of the third beam set.

15. A communication method, characterized in that, include: Receive first information from a network device, the first information being used to configure a first beam set and a third beam set; Based on the second AI model deployed on the terminal device and the actual measurement results of the third beam set, the estimated measurement results of the first beam set are determined. The second AI model is the AI ​​model corresponding to the first cell among at least one AI model deployed on the terminal device, and the first cell is the serving cell of the terminal device. The estimated measurement results of the first beam set are sent to the network device.

16. The method according to claim 15, characterized in that, The method further includes: The performance of the second AI model is determined based on the actual measurement results of the first beam set and the estimated measurement results of the first beam set.

17. The method according to claim 16, characterized in that, The method further includes: If the performance of the second AI model does not meet the first condition, the AI ​​model corresponding to the first cell is re-determined from at least one AI model deployed on the terminal device.

18. The method according to any one of claims 15-17, characterized in that, The method further includes: The third information received from the network device is used to configure the first beam set, the second beam set, and the third beam set, and to instruct the terminal device to report the actual measurement results of the second beam set but not to report the actual measurement results of the first beam set and the third beam set. The actual measurement results of the second beam set are sent to the network device, and the actual measurement results of the first beam set and the third beam set are stored.

19. The method according to claim 18, characterized in that, The third information includes a first CSI report configuration, a second CSI report configuration, and a third CSI report configuration. The first CSI report configuration is used to configure the first beam set, the second CSI report configuration is used to configure the second beam set, and the third CSI report configuration is used to configure the third beam set. The reporting content of the first CSI report configuration and the third CSI report configuration is configured not to be reported, and the first CSI report configuration is associated with the third CSI report configuration.

20. The method according to claim 18, characterized in that, The third information includes a fourth CSI report configuration and a fifth CSI report configuration. The fourth CSI report configuration is used to configure the second beam set, and the fifth CSI report configuration is used to configure the first beam set and the third beam set. The reporting content of the fifth CSI report configuration is configured not to be reported.

21. The method according to claim 20, characterized in that, The fifth CSI report configuration includes a first CSI resource configuration and a second CSI resource configuration, wherein the first CSI resource configuration is used to configure the first beam set, and the second CSI resource configuration is used to configure the third beam set; or... The fifth CSI report configuration includes a third CSI resource configuration, wherein the third CSI resource configuration includes a first resource set and a second resource set, the first resource set is used to configure the first beam set, and the second resource set is used to configure the third beam set.

22. The method according to claim 18, characterized in that, The third information includes a sixth CSI report configuration and a seventh CSI report configuration. The sixth CSI report configuration is used to configure the second beam set, and the seventh CSI report configuration is used for the third beam set. The reporting content of the seventh CSI report configuration is configured not to be reported, and the sixth CSI report configuration is associated with the seventh CSI report configuration.

23. The method according to claim 22, characterized in that, The sixth CSI report configuration includes a fourth CSI resource configuration and a fifth CSI resource configuration. The fourth CSI resource configuration is used to configure the beams in the second beam set other than the first beam set. The fifth CSI resource configuration is used to configure the first beam set. The identifier of the fifth CSI resource configuration is a first identifier, which is used to indicate that the terminal device needs to store the actual measurement results of the first beam set.

24. The method according to claim 18, characterized in that, The third information includes an eighth CSI report configuration and a ninth CSI report configuration, wherein the eighth CSI report configuration is used to configure the beams in the second beam set other than the first beam set, and the ninth CSI report configuration is used for the first beam set and the third beam set.

25. The method according to claim 24, characterized in that, The ninth CSI report configuration includes a sixth CSI resource configuration and a seventh CSI resource configuration. The sixth CSI resource configuration is used to configure the first beam set, and the seventh CSI resource configuration is used to configure the third beam set. The reporting content of the seventh CSI resource configuration is configured not to report, or the identifier of the seventh CSI resource configuration is a second identifier, which indicates that the terminal device does not need to report the actual measurement results of the third beam set; or... The ninth CSI report configuration includes an eighth CSI resource configuration, wherein the eighth CSI resource configuration includes a third resource set and a fourth resource set. The third resource set is used to configure the first beam set, and the fourth resource set is used to configure the third beam set. The reporting content of the fourth resource set is configured not to report, or the identifier of the fourth CSI resource configuration is a second identifier, which is used to indicate that the terminal device does not need to report the actual measurement results of the third beam set.

26. A communication device, characterized in that, The communication device includes a module for performing the method as described in any one of claims 1 to 14, or a module for performing the method as described in any one of claims 15 to 25.

27. A communication device, characterized in that, The communication device includes a processor, which is configured to perform the method as described in any one of claims 1 to 14, or the method as described in any one of claims 15 to 25.

28. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program that, when run on a computer, causes the method as described in any one of claims 1 to 14 to be performed, or causes the method as described in any one of claims 15 to 25 to be performed.

29. A computer program product, characterized in that, The computer program product includes a computer program that, when run on a computer, causes the method as described in any one of claims 1 to 14 to be performed, or causes the method as described in any one of claims 15 to 25 to be performed.

30. A communication system, characterized in that, The communication system includes a network device and a terminal device, wherein the network device is used to implement the method as described in any one of claims 1 to 14, and the terminal device is used to implement the method as described in any one of claims 15 to 25.

Images