Communication method and communication device

Abstract

A communication method and a communication device, the method comprising: a first network element can configure identifications of M first cells and a first AI model to a terminal device, the input of the first AI model comprising channel state information of the M first cells measured by the terminal device, the output of the AI model comprising first beam information for a first access network device, therefore, the terminal equipment can report the information of N beams determined according to the first beam information and recommended by the terminal equipment to the first access network equipment, the AI model is issued through the network, the terminal equipment can select the recommended beam according to the AI model, the overhead brought by beam training of two stages is avoided, and the user experience is improved. And the complexity of beam selection is reduced.

Description

Technical Field

[0001] This application relates to the field of communications, and more specifically, to a beam management method and a communication apparatus. Background Technology

[0002] Beamforming can be understood as the process of finding the optimal beam between a base station and a terminal. Through beamforming, the optimal beam can be determined, thereby ensuring the communication performance between the terminal and the base station. Currently, one method of beamforming is as follows: the terminal first measures multiple wide beams to determine a better wide beam, and then measures multiple thin beams within the direction of that wide beam to determine a better thin beam, i.e., the beam direction for data transmission.

[0003] However, this method requires two stages of beam training, resulting in significant overhead. Summary of the Invention

[0004] This application provides a communication method and communication device that can reduce the overhead of beam training.

[0005] Firstly, a communication method is provided, which can be applied to the terminal device side, for example, to the terminal device or its components (such as chips, circuits, or chip systems).

[0006] The method includes: receiving first configuration information from a first network element, the first configuration information including identifiers of M first cells and information of a first artificial intelligence (AI) model, the first AI model being used to determine the beams used for communication between the terminal device and the first access network device, the input of the first AI model including a first input, the first input being first channel state information of the M first cells measured by the terminal device, the output of the first AI model including first beam information, the first beam information being determined by the terminal device based on the first AI model and the first channel state information, where M is a positive integer; and sending information of N beams to the first access network device, the N beams being beams recommended by the terminal device, the information of the N beams being determined based on the first beam information, where N is a positive integer.

[0007] Based on the above solution, by distributing the AI ​​model over the network, terminal devices can select recommended beams based on the AI ​​model, avoiding the overhead of two-stage beam training. Furthermore, this solution can reduce the complexity of beam selection.

[0008] In conjunction with the first aspect, in some implementations, the first cell is a cell operating in a first frequency range, the first access network device is an access network device operating in a second frequency range, and the highest frequency in the first frequency range is lower than the lowest frequency in the second frequency range.

[0009] Based on the above scheme, this application can predict beam information in the high-frequency range based on channel state information in the low-frequency range, which can simplify the beam management process and reduce the signaling overhead of beam training.

[0010] In conjunction with the first aspect, in some implementations, the first beam information includes at least one of the following: one or more beams of the first access network device; one or more beam combinations, each of the one or more beam combinations including a beam of the first access network device and a beam of the terminal device; one or more beam pairs, each of the one or more beam pairs associated with a beam of the first access network device and a beam of the terminal device; a first signal strength tensor of multiple beams of the first access network device, each position in the first signal strength tensor associated with a beam of the first access network device; and a second signal strength tensor of multiple beam pairs, each position in the second signal strength tensor associated with a beam of the first access network device and a beam of the terminal device.

[0011] Based on the above scheme, the first beam information output by the AI ​​model can include various types of beam-related information related to the first access network device, thus making the scheme applicable to a wider range of scenarios.

[0012] For example, each beam of the terminal device is associated with angle information, and the first configuration information includes the association between each beam and angle information of the terminal device.

[0013] Optionally, the angle information is the angle in the global coordinate system, which includes the angle in the horizontal direction and the angle in the vertical direction.

[0014] In conjunction with the first aspect, in some implementations, the first configuration information includes a first cell identifier list, which contains identifiers of M first cells. The positions of the M first channel state information items in the first input are determined based on the positions of the identifiers of the first cells associated with the first channel state information in the first cell identifier list. For example, the M first channel state information items correspond one-to-one with the M first cells.

[0015] Based on the above scheme, the first configuration information may include a list of first cell identifiers, which helps the terminal device determine the position of the first channel state information in the first input and ensures the performance of the AI ​​model.

[0016] In conjunction with the first aspect, in some implementations, the input to the first AI model also includes a second input, which is the second channel state information between the terminal device and the first access network device.

[0017] Optionally, the method further includes: inputting the first channel state information and the second channel state information into the first AI model to obtain the first beam information.

[0018] Based on the above scheme, for a scenario where the first cell operates in the first frequency range and the first access network device operates in the second frequency range, this application can predict beam information in the high frequency range based on channel state information in the low frequency range and channel state information in the high frequency range. This not only simplifies the beam management process and reduces the signaling overhead of beam training, but also improves the accuracy of beam prediction.

[0019] In conjunction with the first aspect, in some implementations, the first configuration information includes a first reference signal resource identifier list, which includes identifiers of K first reference signal resources. The K first reference signal resources are used by the first access network device to transmit reference signals. The second input includes L second channel state information, wherein the L second channel state information is determined by the terminal device based on the measurement results of L of the K first reference signal resources, where L is less than or equal to K, and both L and K are positive integers.

[0020] Based on the above scheme, the first configuration information may include a first reference signal resource identifier list, which helps the terminal device determine the second channel state information, obtain the second input, and ensure the performance of the AI ​​model.

[0021] For example, the position of the second channel state information in the second input is determined based on the position of the identifier of the first reference signal resource associated with the second channel state information in the first reference signal resource identifier list.

[0022] Based on the above scheme, the first configuration information may include a first reference signal resource identifier list, which helps the terminal device determine the position of the second channel state information in the second input and ensures the performance of the AI ​​model.

[0023] In conjunction with the first aspect, in some implementations, the first configuration information includes a list of third reference signal resource identifiers, which includes P identifiers of third reference signal resources. Each of the P identifiers of the third reference signal resources is associated with the beam of the first access network device, where P is a positive integer.

[0024] Optionally, the information for the N beams includes the indexes of the N beams, or the information for the N beams includes the identifier of the third reference signal resource associated with the N beams.

[0025] Based on the above scheme, the terminal device can report the index of N beams, and also report the identifier of the third reference signal resource associated with N beams, which has greater flexibility.

[0026] Optionally, the first reference signal resource representation list and the third reference signal resource identifier list are the same list.

[0027] This simplifies configuration and improves communication efficiency.

[0028] For example, the identifiers of the P third reference signal resources are associated with the beam of the first access network device, including: the i-th reference signal resource among the identifiers of the P third reference signal resources is associated with the beam i of the first access network device, where i is an integer greater than or equal to 0 and less than or equal to P.

[0029] In conjunction with the first aspect, in some implementations, the method further includes: receiving beam configuration information from a first access network device, the beam configuration information being used to configure the beam of a first signal or a first channel, the beam configuration information including an identifier of a fourth reference signal resource, the fourth reference signal resource being one of P third reference signal resources; determining a fourth beam based on the association relationship between the identifiers of the P third reference signal resources and the beam of the first access network device, the fourth beam being the beam of the first access network device associated with the fourth reference signal resource; and receiving the first signal or the first channel using a fifth beam, wherein the fifth beam is the beam of a terminal device, and the fourth beam is associated with the fifth beam in the first beam information.

[0030] Based on the above scheme, the terminal device can determine the transmitting beam of the first signal or the first channel as the fourth beam based on the association between the identifiers of P third reference signal resources and the beam of the first access network device, and determine the receiving beam of the first signal or the first channel as the fifth beam based on the first beam information. In this way, communication can be carried out based on the predicted beam, thereby improving the efficiency of communication.

[0031] In conjunction with the first aspect, in some implementations, the method further includes: receiving multiple mapping relationships from a first access network device, the multiple mapping relationships including identifiers of multiple first reference signal resources, multiple feature vectors, and multiple second beam information, each of the multiple mapping relationships being: a relationship between an identifier of a first reference signal resource and a feature vector mapping to a second beam information, or a relationship between a group of identifiers of a reference signal resource and a group of feature vectors mapping to a second beam information; sending information of Q beams to the first access network device, the Q beams being beams recommended by the terminal device, the information of the Q beams being determined according to the multiple mapping relationships, where Q is a positive integer.

[0032] Based on the above scheme, the terminal device can receive multiple mapping relationships and report the information of Q beams recommended by the terminal device, which are determined according to the first beam information and multiple mapping relationships. This facilitates the determination of the communication beams between the terminal device and the first access network device and ensures communication performance.

[0033] Optionally, multiple mapping relationships can be retrieved based on information from N beams.

[0034] For example, the second beam information includes at least one of the following: one or more beams of the first access network device; one or more beam combinations, each of the one or more beam combinations including a beam of the first access network device and a beam of the terminal device; one or more beam pairs, each of the one or more beam pairs associated with a beam of the first access network device and a beam of the terminal device; a first signal strength tensor of a plurality of beams of the first access network device, each position in the first signal strength tensor associated with a beam of the first access network device; and a second signal strength tensor of a plurality of beam pairs, each position in the second signal strength tensor associated with a beam of the first access network device and a beam of the terminal device.

[0035] In one implementation, each of the multiple mapping relationships is: the relationship between the identifier of a first reference signal resource and a feature vector is mapped to a second beam information. The method further includes: determining a first feature vector based on the measurement results on the second reference signal resource, where the second reference signal resource is one of K first reference signal resources; determining third beam information based on the identifier of the second reference signal resource, the first feature vector, and the multiple mapping relationships, where the third beam information is one of multiple second beam information; and determining information for Q beams based on the third beam information, where K is a positive integer.

[0036] For example, the measurement result on the second reference signal resource is the second channel state information.

[0037] In conjunction with the first aspect, in some implementations, the first configuration information includes a first reference signal resource identifier list, which includes identifiers of K first reference signal resources, and the K first reference signal resources are used by the first access network device to transmit reference signals.

[0038] Based on the above scheme, the first configuration information may include a first reference signal resource identifier list, which helps the terminal device determine the second channel state information, thereby obtaining the input of the second AI model and ensuring the performance of the AI ​​model.

[0039] In conjunction with the first aspect, in some implementations, the method further includes: receiving second configuration information from a first network element, the second configuration information including information of a second AI model, the input of the second AI model being a second channel state information between a terminal device and a first access network device, and the output of the second AI model including a feature vector, wherein determining the first feature vector based on measurement results on a second reference signal resource includes: determining the second channel state information based on measurement results on the second reference signal resource; and obtaining the first feature vector based on the second channel state information and the second AI model, for example, inputting the second channel state information into the second AI model to obtain the first feature vector.

[0040] Based on the above scheme, the terminal device can obtain the first feature vector for determining Q beams based on the second AI model. In other words, it can additionally use the feature vector in the high-frequency range to predict the beam information in the high-frequency range. This not only simplifies the beam management process and reduces the signaling overhead of beam training, but also improves the accuracy of beam prediction.

[0041] In conjunction with the first aspect, in some implementations, the method further includes: receiving beam configuration information from a first access network device, the beam configuration information being used to configure the beam of a first signal or a first channel, the beam configuration information including an identifier of a fourth reference signal resource; determining a fourth beam based on the association relationship between the identifiers of P third reference signal resources and the beams of the first access network device, the fourth beam being the beam of the first access network device associated with the fourth reference signal resource; and receiving the first signal or the first channel using a fifth beam, wherein the fifth beam is the beam of a terminal device, and the fourth beam is associated with the fifth beam in the third beam information.

[0042] Based on the above scheme, the terminal device can determine the transmitting beam of the first signal or the first channel as the fourth beam based on the association between the identifiers of P third reference signal resources and the beam of the first access network device, and determine the receiving beam of the first signal or the first channel as the fifth beam based on the third beam information. In this way, communication can be carried out based on the predicted beam, thereby improving the efficiency of communication.

[0043] Secondly, a communication method is provided, which can be applied to the first access network device side, for example, to the first access network device or a component of the first access network device (e.g., a chip, circuit, or chip system).

[0044] The method includes: sending first configuration information to a terminal device, the first configuration information including identifiers of M first cells and information of a first AI model, the first AI model being used to determine the beams used for communication between the terminal device and a first access network device, the input of the first AI model including a first input, the first input being first channel state information of the M first cells measured by the terminal device, the output of the first AI model including first beam information, the first beam information being determined by the terminal device based on the first AI model and the first channel state information, where M is a positive integer; receiving information of N beams from the terminal device, the N beams being beams recommended by the terminal device, the information of the N beams being determined based on the first beam information, where N is a positive integer.

[0045] In conjunction with the second aspect, in some implementations, the first cell is a cell operating in a first frequency range, and the first access network device is an access network device operating in a second frequency range, wherein the highest frequency in the first frequency range is lower than the lowest frequency in the second frequency range.

[0046] In conjunction with the second aspect, in some implementations, the first AI model further includes a second input, which is the second channel state information between the terminal device and the first access network device. The information of N beams is determined based on the first beam information, including: the information of N beams is determined based on the first AI model, the first channel state information, and the second channel state information.

[0047] In conjunction with the second aspect, in some implementations, the method further includes: sending beam configuration information to a terminal device, the beam configuration information being used to configure the beam of the first signal or the first channel, the beam configuration information including an identifier of a fourth reference signal resource, the fourth reference signal resource being one of P third reference signal resources; determining a fourth beam based on the association between the identifiers of the P third reference signal resources and the beam of the first access network device, the fourth beam being the beam of the first access network device associated with the fourth reference signal resource; and using the fourth beam to transmit the first signal or the first channel.

[0048] In conjunction with the second aspect, in some implementations, the method further includes: sending multiple mapping relationships to the terminal device, wherein the multiple mapping relationships include identifiers of multiple first reference signal resources, multiple feature vectors, and multiple second beam information, and each mapping relationship is: a relationship between an identifier of a first reference signal resource and a feature vector mapping to a second beam information, or a relationship between a group of identifiers of a reference signal resource and a group of feature vectors mapping to a second beam information; receiving information about Q beams from the terminal device, wherein the Q beams are beams recommended by the terminal device, and the information about the Q beams is determined according to the multiple mapping relationships, where Q is a positive integer. For example, the Q beams are Q out of N beams.

[0049] Optionally, the method further includes: retrieving the multiple mapping relationships based on the information of the N beams.

[0050] Optionally, the method further includes: sending second configuration information to the terminal device, the second configuration information including information of a second AI model, the input of the second AI model being a second channel state information between the terminal device and the first access network device, and the output of the second AI model including a feature vector, wherein the second AI model is used to determine information of Q beams.

[0051] In conjunction with the second aspect, in some implementations, the method further includes: sending beam configuration information to a terminal device, the beam configuration information being used to configure the beam of the first signal or the first channel, the beam configuration information including an identifier of a fourth reference signal resource, the fourth reference signal resource being one of P third reference signal resources; determining a fourth beam based on the association between the identifiers of the P third reference signal resources and the beam of the first access network device, the fourth beam being the beam of the first access network device associated with the fourth reference signal resource; and using the fourth beam to transmit the first signal or the first channel.

[0052] Thirdly, a communication method is provided, which can be applied to the first network element side, for example, to the first network element or its constituent components (e.g., chips, circuits, or chip systems).

[0053] The method includes: sending first configuration information to a terminal device, the first configuration information including identifiers of M first cells and information of a first AI model, the first AI model being used to determine the beam used for communication between the terminal device and a first access network device, the input of the first AI model including a first input, the first input being the first channel state information of the M first cells measured by the terminal device, the output of the first AI model including first beam information, the first beam information being determined by the terminal device based on the first AI model and the first channel state information, where M is a positive integer.

[0054] In conjunction with the third aspect, in some implementations, the method further includes: sending second configuration information to the terminal device, the second configuration information including information of the second AI model, the input of the second AI model being a second channel state information between the terminal device and the first access network device, the output of the second AI model including a feature vector, and the second AI model being used to determine the third beam information.

[0055] Fourthly, a communication device is provided that can be applied to a terminal device, for example, it can be a terminal device or a component of a terminal device (such as a chip, circuit or chip system).

[0056] The device includes: a transceiver unit, configured to receive first configuration information from a first network element, the first configuration information including identifiers of M first cells and information of a first AI model, the first AI model being used to determine the beams used for communication between the terminal device and the first access network device, the input of the first AI model including a first input, the first input being first channel state information of the M first cells measured by the terminal device, the output of the first AI model including first beam information, the first beam information being determined by the terminal device based on the first AI model and the first channel state information, where M is a positive integer; the transceiver unit is also configured to: send information of N beams to the first access network device, the N beams being beams recommended by the terminal device, the information of the N beams being determined based on the first beam information, where N is a positive integer.

[0057] In conjunction with the fourth aspect, in some implementations, the transceiver unit is further configured to: receive beam configuration information from the first access network device, the beam configuration information being used to configure the beam of the first signal or the first channel, the beam configuration information including an identifier of a fourth reference signal resource, the fourth reference signal resource being one of P third reference signal resources; the device further includes: a processing unit configured to determine the fourth beam based on the association relationship between the identifiers of the P third reference signal resources and the beam of the first access network device, the fourth beam being the beam of the first access network device associated with the fourth reference signal resource; the transceiver unit is further configured to: receive the first signal or the first channel using a fifth beam, wherein the fifth beam is the beam of the terminal device, and in the first beam information, the fourth beam is associated with the fifth beam.

[0058] In conjunction with the fourth aspect, in some implementations, the transceiver unit is further configured to: receive multiple mapping relationships from the first access network device, the multiple mapping relationships including identifiers of multiple first reference signal resources, multiple feature vectors, and multiple second beam information, each of the multiple mapping relationships being: a relationship between an identifier of a first reference signal resource and a feature vector mapping to a second beam information, or a relationship between a group of identifiers of a reference signal resource and a group of feature vectors mapping to a second beam information; the transceiver unit is further configured to: send information of Q beams to the first access network device, the Q beams being beams recommended by the terminal device, the information of the Q beams being determined according to the multiple mapping relationships, where Q is a positive integer.

[0059] In one implementation, each of the multiple mapping relationships is: a relationship between the identifier of a first reference signal resource and a feature vector, which is mapped to a second beam information. The processing unit is further configured to: determine a first feature vector based on the measurement results on the second reference signal resource, wherein the second reference signal resource is one of a plurality of first reference signal resources; the processing unit is further configured to: determine third beam information based on the identifier of the second reference signal resource, the first feature vector, and the multiple mapping relationships, wherein the third beam information is one of a plurality of second beam information; the processing unit is further configured to: determine information of Q beams based on the third beam information.

[0060] In conjunction with the fourth aspect, in some implementations, the transceiver unit is further configured to: receive second configuration information from the first network element, the second configuration information including information of the second AI model, the input of the second AI model being a second channel state information between the terminal device and the first access network device, and the output of the second AI model including a feature vector. Specifically, the processing unit is configured to: determine the second channel state information based on measurement results on the second reference signal resource; and obtain a first feature vector based on the second channel state information and the second AI model, for example, by inputting the second channel state information into the second AI model to obtain the first feature vector.

[0061] In conjunction with the fourth aspect, in some implementations, the transceiver unit is further configured to: receive beam configuration information from the first access network device, the beam configuration information being used to configure the beam of the first signal or the first channel, the beam configuration information including the identifier of the fourth reference signal resource; the processing unit is further configured to: determine the fourth beam based on the association relationship between the identifiers of P third reference signal resources and the beam of the first access network device, the fourth beam being the beam of the first access network device associated with the fourth reference signal resource; the transceiver unit is further configured to: receive the first signal or the first channel using the fifth beam, wherein the fifth beam is the beam of the terminal device, and the fourth beam is associated with the fifth beam in the third beam information.

[0062] Fifthly, a communication device is provided that can be applied to a first access network device. For example, the device can be a first access network device or a component of the first access network device (e.g., a chip, circuit, or chip system).

[0063] The device includes: a transceiver unit, configured to send first configuration information to a terminal device, the first configuration information including identifiers of M first cells and information of a first AI model, the first AI model being used to determine the beams used for communication between the terminal device and a first access network device, the input of the first AI model including a first input, the first input being first channel state information of the M first cells measured by the terminal device, the output of the first AI model including first beam information, the first beam information being determined by the terminal device based on the first AI model and the first channel state information, where M is a positive integer; the transceiver unit is also configured to: receive information of N beams from the terminal device, the N beams being beams recommended by the terminal device, the information of the N beams being determined based on the first beam information, where N is a positive integer.

[0064] In conjunction with the fifth aspect, in some implementations, the transceiver unit is further configured to: send beam configuration information to the terminal device, the beam configuration information being used to configure the beam of the first signal or the first channel, the beam configuration information including an identifier of a fourth reference signal resource, the fourth reference signal resource being one of P third reference signal resources; the device further includes: a processing unit configured to determine the fourth beam based on the association relationship between the identifiers of the P third reference signal resources and the beam of the first access network device, the fourth beam being the beam of the first access network device associated with the fourth reference signal resource; the transceiver unit is further configured to: transmit the first signal or the first channel using the fourth beam.

[0065] In conjunction with the fifth aspect, in some implementations, the transceiver unit is further configured to: send multiple mapping relationships to the terminal device, the multiple mapping relationships including identifiers of multiple first reference signal resources, multiple feature vectors, and multiple second beam information, each of the multiple mapping relationships being: a relationship between an identifier of a first reference signal resource and a feature vector mapping to a second beam information, or a relationship between a group of identifiers of a reference signal resource and a group of feature vectors mapping to a second beam information; the transceiver unit is further configured to: receive information of Q beams from the terminal device, the Q beams being beams recommended by the terminal device, the information of the Q beams being determined according to the multiple mapping relationships, where Q is a positive integer.

[0066] Optionally, the device further includes a processing unit for retrieving the multiple mapping relationships based on information from the N beams.

[0067] Optionally, the transceiver unit is further configured to: send second configuration information to the terminal device, the second configuration information including information of the second AI model, the input of the second AI model being a second channel state information between the terminal device and the first access network device, and the output of the second AI model including a feature vector, wherein the second AI model is used to determine the information of Q beams.

[0068] In conjunction with the fifth aspect, in some implementations, the transceiver unit is further configured to: send beam configuration information to the terminal device, the beam configuration information being used to configure the beam of the first signal or the first channel, the beam configuration information including the identifier of the fourth reference signal resource, the fourth reference signal resource being one of P third reference signal resources; the processing unit is further configured to: determine the fourth beam based on the association relationship between the identifiers of the P third reference signal resources and the beam of the first access network device, the fourth beam being the beam of the first access network device associated with the fourth reference signal resource; the transceiver unit is further configured to: transmit the first signal or the first channel using the fourth beam.

[0069] In a sixth aspect, a communication device is provided that can be applied to a first network element side. For example, the device can be the first network element or a component of the first network element (such as a chip, circuit, or chip system).

[0070] The device includes: a transceiver unit for sending first configuration information to a terminal device. The first configuration information includes identifiers of M first cells and information of a first AI model. The first AI model is used to determine the beam used for communication between the terminal device and a first access network device. The input of the first AI model includes a first input, which is the first channel state information of the M first cells measured by the terminal device. The output of the first AI model includes first beam information, which is determined by the terminal device based on the first AI model and the first channel state information. M is a positive integer.

[0071] In conjunction with the sixth aspect, in some implementations, the transceiver unit is further configured to: send second configuration information to the terminal device, the second configuration information including information of the second AI model, the input of the second AI model being a second channel state information between the terminal device and the first access network device, the output of the second AI model including a feature vector, and the second AI model being used to determine the third beam information.

[0072] It should be understood that any details not fully described in aspects two through six may be referred to in aspect one.

[0073] A seventh aspect provides a communication device comprising an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of a computer program or instructions necessary for implementing the functions involved in any of the possible implementations of the first to third aspects described above. The one or more processors are executable to carry out the computer program or instructions, which, when executed, cause the communication device to implement the methods in any of the possible implementations of the first to third aspects described above. The interface circuit is used to implement communication functions within the communication device and / or communication functions between the communication device and other devices or components.

[0074] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0075] In one possible design, the communication device may also include the memory.

[0076] The aforementioned communication device may be an access network device, or a module (e.g., a circuit, chip, or chip system) within an access network device, or a logical node, logical module, or software capable of implementing all or part of the functions of the access network device. The aforementioned communication device may also be a terminal device, or a module (e.g., a circuit, chip, or chip system) within a terminal device, or a logical node, logical module, or software capable of implementing all or part of the functions of the terminal device. The aforementioned communication device may also be a first network element, or a module (e.g., a circuit, chip, or chip system) within a first network element, or a logical node, logical module, or software capable of implementing all or part of the functions of the first network element.

[0077] Eighthly, a communication system is provided, which may include communication devices from at least two of the fourth to sixth aspects.

[0078] Ninth aspect, a computer-readable storage medium is provided that stores computer-readable instructions, which, when read and executed by a computer, cause the computer to perform any of the possible designs of the first to third aspects described above.

[0079] In a tenth aspect, a computer program product is provided, which, when read and executed by a computer, causes the computer to perform any of the possible implementations of the first to third aspects described above.

[0080] Eleventhly, a chip or chip system is provided, comprising: a processor for executing computer programs or instructions in a memory to implement the method in any of the possible implementations of the first to third aspects described above.

[0081] It should be understood that any beneficial effects not fully described in the second to eleventh aspects above can be referred to the first aspect and any of its possible implementations. Attached Figure Description

[0082] Figure 1 This is a schematic diagram of a network architecture applicable to embodiments of this application.

[0083] Figure 2 This is a schematic diagram of a beam training process.

[0084] Figure 3 This is a schematic flowchart of a communication method 300 provided in this application.

[0085] Figure 4 This is a schematic diagram of an AI model provided in this application.

[0086] Figure 5 This is another schematic diagram of an AI model provided in this application.

[0087] Figure 6 This is a schematic diagram illustrating the mapping relationship between the first reference signal resource identifier list and the second output provided in this application.

[0088] Figure 7 This is a schematic diagram of the beam of the first access network device provided in this application.

[0089] Figure 8 This is a schematic diagram of the beam of the terminal device provided in this application.

[0090] Figure 9 This is a schematic flowchart of a communication method 400 provided in this application.

[0091] Figure 10 This is another schematic diagram of an AI model provided in this application.

[0092] Figure 11 This is a schematic flowchart of a communication method 500 provided in this application.

[0093] Figure 12 This is a schematic flowchart of a communication method 600 provided in this application.

[0094] Figure 13 This is a schematic flowchart of a communication method 700 provided in this application.

[0095] Figure 14 This is a schematic block diagram of the communication device 2000 provided in the embodiments of this application.

[0096] Figure 15 This is a schematic block diagram of the communication device 3000 provided in the embodiments of this application. Detailed Implementation

[0097] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0098] The technical solutions of this application can be applied to various communication systems, such as Long Term Evolution (LTE), 5th Generation (5G), New Radio (NR), Internet of Things (IoT), Wireless-Fidelity (WiFi), wireless communication related to the 3rd Generation Partnership Project (3GPP), or other wireless communication that may emerge in the future. This application does not limit these applications.

[0099] The technical solutions provided in this application can also be applied to machine-type communication (MTC), device-to-device (D2D) networks, machine-to-machine (M2M) networks, Internet of Things (IoT) networks, or other networks. IoT networks, for example, can include vehicle-to-everything (V2X) networks. The communication methods in V2X systems are collectively referred to as vehicle-to-X (V2X), where X can represent anything. For example, V2X can include vehicle-to-vehicle (V2V) communication, vehicle-to-infrastructure (V2I) communication, vehicle-to-pedestrian (V2P) communication, or vehicle-to-network (V2N) communication, etc.

[0100] Figure 1 This is a schematic diagram of a network architecture applicable to embodiments of this application. The network architecture may include, but is not limited to, user equipment (UE) and a radio access network (RAN). Optionally, the network architecture may further include one or more of the following: user plane function (UPF), data network (DN), access and mobility management function (AMF), session management function (SMF), and a first network element. The DN may be the Internet. The AMF, SMF, UPF, and first network element are network elements belonging to the core network.

[0101] The following is about Figure 1 A brief introduction to some of the network elements shown in the image is provided.

[0102] 1. User equipment (UE): can also be called terminal equipment, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent, or user device.

[0103] Terminal devices can be devices that provide voice / data to users, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving vehicles, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0104] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0105] Furthermore, in this embodiment, the terminal device can also be a terminal device in an IoT system. IoT is an important component of the future development of information technology. Its main technical feature is to connect objects to the network through communication technology, thereby realizing an intelligent network of human-machine interconnection and object interconnection.

[0106] It should be noted that terminal devices and access network devices can communicate with each other using some air interface technology (such as New Radio (NR) or LTE). Terminal devices can also communicate with each other using some air interface technology (such as NR or LTE).

[0107] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be a device that supports the terminal device in implementing the functions, such as a chip system or a chip. This device can be installed in the terminal device. In this embodiment, the chip system can be composed of chips, or it can include chips and other discrete devices.

[0108] 2. Radio access network (RAN): This provides access to a communication network for authorized users in a specific area. Specifically, it can include wireless network equipment in the 3rd Generation Partnership Project (3GPP) network or access points in non-3GPP networks.

[0109] The RAN manages radio resources, provides access services to user equipment, and forwards control signals and user equipment data between the user equipment and the core network. The RAN can also be exemplified by a base station in a traditional network.

[0110] For example, the access network device in this application embodiment can be any communication device with wireless transceiver function for communicating with user equipment. The access network equipment includes, but is not limited to: evolved NodeB (eNB), baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), access point (AP), wireless relay node, wireless backhaul node, transmission point (TP), or transmission and reception point (TRP) in a wireless fidelity (WIFI) system. It can also be a gNB in ​​a 5G system, such as NR, or a transmission point (TRP or TP), one or a group of antenna panels (including multiple antenna panels) of a base station in a 5G system, or a network node constituting a gNB or transmission point, such as a baseband unit (BBU), or a distributed unit (DU), centralized unit (CU), or radio unit (RU).

[0111] In some deployments, the gNB may include a CU and a DU. Optionally, the gNB may also include an RU. The CU implements some of the gNB's functions, and the DU implements some of the gNB's functions. For example, the CU is responsible for handling non-real-time protocols and services, implementing the functions of the radio resource control (RRC) and packet data convergence protocol (PDCP) layers. The DU is responsible for handling physical layer protocols and real-time services, implementing the functions of the radio link control (RLC), media access control (MAC), and physical (PHY) layers. The RU implements some physical layer processing functions, radio frequency processing, and related functions of active antennas. Since the information in the RRC layer eventually becomes the information in the PHY layer, or is transformed from the information in the PHY layer, in this architecture, higher-layer signaling, such as RRC layer signaling, can also be understood as being sent by the DU, or by the DU+RU. It is understood that access network equipment can be devices that include one or more of the following: CU nodes, DU nodes, and RU nodes. Furthermore, the CU can be classified as an access network device in the radio access network (RAN) or as an access network device in the core network (CN), and this application does not limit this. Optionally, the CU may include a central unit-control plane (CU-CP) and a central unit-user plane (CU-UP). The RU may be included in radio equipment or radio unit, such as in an RRU, AAU, or RRH.

[0112] 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 open-radio access network (O-RAN) system, CU can also be called an open-central unit (O-CU) (open CU); DU can also be called an open-distributed unit (O-DU) (open 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 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 and hardware modules. For ease of description, the following detailed description uses a base station as an example of an access network device.

[0113] The service area or coverage area of ​​an access network device can include one or more cells. Taking the access network device as a base station as an example, in an analog network using an omnidirectional antenna structure, one cell is the coverage area of ​​one base station; while in a digital cellular mobile network using a 120° angle antenna structure, a cell is one-third of the regular hexagonal area covered by each 120° antenna. Therefore, a base station area can contain one or more cells. Not all cells have a dedicated base station, but they must be covered by a specific base station. That is to say, typically one cell is associated with one access network device, and one access network device can be associated with multiple cells. Terminal devices usually reside in a cell or connect to the access network device in a cell. Both access network devices and cells have their own identifiers. For example, in the current 5G network, access network devices can be identified by the base station identifier (gNB ID), and cells can be identified by the physical cell identity (PCI), new radio cell identity (NCI), cell identity (CI), and new radio cell global identifier (NCGI).

[0114] 3. First Network Element: Used to support beam management assisted by artificial intelligence (AI) technology, for example, sending an AI model for beam determination to the terminal device. Exemplarily, the first network element can be a functional network element in the core network. It can be an independent core network element, or it can be coupled with any of the aforementioned core network elements, with the core network element implementing the functions of the first network element. Exemplarily, the first network element can be a base station, such as a first access network device. Optionally, in the O-RAN architecture, the functions of the first network element can be performed by a DU, a CU, or a combination of DU, CU, and RU, without limitation.

[0115] It should be understood that the above Figure 1 The network architecture shown is merely an example, and the network architecture applicable to the embodiments of this application is not limited to this. Any network architecture that can realize the functions of the above-mentioned network elements is applicable to the embodiments of this application.

[0116] In the above network architecture, the N1 interface is the interface between the UE and the AMF; the N2 interface is the interface between the RAN and the AMF network elements, used for transmitting radio parameters and non-access stratum (NAS) signaling; the N3 interface is the interface between the RAN and the UPF network elements, used for transmitting user plane data; the N4 interface is the interface between the SMF and UPF network elements, used for transmitting information such as service policies, tunnel identification information for N3 connections, data buffer indication information, and downlink data notification messages; the N6 interface is the interface between the DN and UPF network elements, used for transmitting user plane data; and the N9 interface is the user plane interface between UPFs, used for transmitting uplink and downlink user data streams between different UPFs.

[0117] It should be understood that Figure 1 The network elements and communication interfaces involved are described using the names specified or expected in the current 5G system protocols as examples, but this does not limit the embodiments of this application to only known communication systems. Therefore, the standard names that appear when describing using the current protocol as an example are functional descriptions. This application does not limit the specific names of network elements, interfaces, or signaling, but only indicates the function of the network element, interface, or signaling, which can be extended to other systems, such as 2G, 3G, 4G, or future communication systems.

[0118] For example, in the current standardization process, the sensing function network element has not yet been formally named, and in future networks, the sensing function network element may have other names.

[0119] It should also be understood that Figure 1 The AMF, SMF, UPF, etc. shown can be understood as network elements in the core network used to implement different functions, such as network slices that can be combined as needed. These core network elements can be independent devices or integrated into the same device to implement different functions. This application does not limit the specific form of the above-mentioned network elements. It should be understood that the network architecture applied to the embodiments of this application is only an example of a network architecture described from the perspective of a traditional point-to-point architecture and a service-oriented architecture. The network architecture applicable to the embodiments of this application is not limited to this. Any network architecture that can implement the functions of the above-mentioned network elements is applicable to the embodiments of this application.

[0120] It should be noted that the aforementioned network elements may also be referred to as entities, devices, apparatuses, or modules, etc., and this application does not specifically limit them.

[0121] To facilitate understanding of the embodiments of this application, some basic concepts involved in this application will be briefly explained.

[0122] 1. Millimeter wave communication

[0123] Millimeter wave bands are generally considered to be electromagnetic wave bands ranging from 30 GHz to 300 GHz. Compared to traditional sub-6 GHz bands, millimeter waves have wider spectrum resources, enabling high data rate transmission. Simultaneously, the shorter wavelength of millimeter waves allows for smaller antenna sizes and easier integration of multiple antennas, making millimeter wave communication a key technology for 5G systems and future communication systems. However, the higher the frequency, the greater the channel fading. Compared to traditional sub-6 GHz bands, millimeter wave bands experience significantly greater channel attenuation. Therefore, equipment communicating in the millimeter wave band needs to utilize beamforming or other techniques, employing specific spatial filtering parameters (or spatial filters, spatial parameters) to concentrate signal energy in a specific direction, i.e., a specific beam direction, thereby increasing the equivalent channel gain between transceivers and ensuring coverage performance and data transmission rates for millimeter wave communication.

[0124] 2. Beam Training

[0125] Generally, we believe that there is a correspondence between beam and spatial filtering parameters under a given antenna structure. Therefore, in this application, the concepts of beam and spatial filtering parameters can be used interchangeably in most scenarios. For example, beam identifier can also be understood as spatial filtering parameter identifier. In the initial stage of establishing a connection between transceiver devices, since the location and channel information between the transceiver devices are usually unknown, the receiving device needs to perform a beam training process to find a suitable beam direction and its corresponding spatial filtering parameters. Currently, the mainstream beamforming technology in NR systems relies on precoding technology under a multi-antenna structure. Precoding is mainly divided into digital precoding and analog precoding. Digital precoding relies on multiple radio frequency (RF) channels, but due to the high cost of RF channels, the beamforming gain achieved by digital precoding using only a small number of RF channels is relatively small. Currently, the beamforming gain of devices mainly relies on analog precoding. Analog precoding refers to the process where a broadband signal passes through a phase shifter before being transmitted through each antenna array. The signal transmitted by each antenna has a different phase difference relative to the original signal. These different phase differences constitute the analog precoding vector, thereby enabling the signal to be concentrated in a specific direction in space. In this analog precoding framework, the analog precoding vector is its spatial filtering parameter. Because in analog precoding, the entire broadband signal on a single symbol can only be transmitted in one beam direction, searching all possible beam directions during beam training consumes a significant amount of time, resulting in high beam training overhead, low transmission efficiency, and poor mobility support.

[0126] Specifically, in the NR system, the beam training process between the base station and the terminal is completed through a channel state information (CSI) reporting process. The main process involves the base station first configuring multiple reference signals for the terminal, including the time-frequency location, reference signal index, number of ports, and port pattern for each reference signal. When transmitting each reference signal, the base station can use different spatial filtering parameters, i.e., transmit the reference signal in different beam directions. The terminal receives each reference signal configured by the base station and measures its reference signal received power (RSRP), then reports the reference signal indexes and corresponding RSRP quantization values ​​of several reference signals with higher RSRPs. After receiving the reported information from the terminal device, the base station, knowing the spatial filtering parameters used to transmit each reference signal, can ultimately determine which spatial filtering parameters and in which directions will enable the terminal device to receive higher-energy signals, thus completing the beam training process.

[0127] In NR, there are two types of reference signals used for beam training. The first type is the synchronization signal / physical broadcast channel block (SSB), and the second type is the non-zero power channel state information reference signal (NZP-CSI-RS). The SSB is a cell-specific periodic reference signal that each base station periodically transmits. It is mainly used for synchronization between terminals and base stations, as well as for base stations to broadcast basic configuration information within the cell. For robust transmission, base stations typically use a thicker beam when transmitting the SSB compared to when transmitting data. The NZP-CSI-RS can be configured for specific terminals, and the beam thickness and shape used for transmitting it are unrestricted.

[0128] like Figure 2 As shown, in a real system, the base station will typically instruct the terminal to periodically select the SSB (e.g., Figure 2 The SSBs 1, 2, and 3 are measured to determine a better wide beam (or coarse beam), and then several NZP-CSI-RS (e.g., ...) are configured for the terminal. Figure 2 The NZP-CSI-RS1, NZP-CSI-RS2, and NZP-CSI-RS3 in the NZP-CSI-RS1, NZP-CSI-RS2, and NZP-CSI-RS3 are used to continue transmitting NZP-CSI-RS using the narrow beam direction within the determined wide beam direction. Then, the better narrow beam direction, i.e. the beam direction for data transmission, is determined based on the NZP-CSI-RS measurement information reported by the terminal.

[0129] Figure 2The two-stage beam training process shown requires searching fewer beams compared to direct beam training based on fine beams, thus reducing the time overhead of beam training to some extent. However, this method relies on SSB measurement information in the first stage. SSBs are cell-specific periodic reference signals with generally fixed and relatively long periods; for example, the transmission period of one round of SSBs (covering all coarse beam directions) in current NR systems ranges from 5ms to 120ms. Therefore, although two-stage beam training significantly reduces the number of beams searched, the relatively fixed period of the SSBs makes the time overhead of the first stage still relatively high. Furthermore, the final determined fine beam direction performance is not optimal. Specifically, since the channel between the base station and the terminal often has multiple paths, when the SSB is transmitted in the wide beam direction in the first stage, there may be multiple strong paths in a wide beam. If the phases of these multiple paths are in a phase cancellation relationship, the RSRP measured by the terminal at the time-frequency position corresponding to the SSB is very small, which leads to the failure to detect effective paths. In other words, the strong signal of the thin beam in the wide beam cannot be detected, resulting in the beam training performance not being optimal.

[0130] 3. AI Model

[0131] The AI ​​models in this application (including the first AI model and the second AI model mentioned below) can be understood as functions with specific structures. Each AI model has corresponding inputs and outputs. For example, the AI ​​model may include fully connected layers, convolutional neural network layers, and transformer modules. Each layer or module may also include activation functions as outputs of that layer or module, or they may be directly output. The first AI model can be used to predict first beam information. Therefore, the information of the first AI model may include information about the aforementioned structure and the parameters within that structure. Specific parameters may include the weights and biases of the fully connected layers, the convolutional kernels and biases of the convolutional neural network layers, etc.

[0132] 4. AI-based beam training

[0133] To address the aforementioned beam training problem, one approach is to input wide-beam information into the AI ​​model to obtain narrow-beam information. However, this approach still requires measuring a considerable number of reference signals under wide beam conditions, and the reduction in signal throughput remains limited.

[0134] In view of this, this application provides a communication method and communication apparatus that can not only determine the communication beam between the terminal device and the access network device through an AI model, but also further reduce overhead.

[0135] Figure 3 This is a schematic flowchart illustrating a communication method provided in this application. Figure 3 As shown, the method 300 includes the following steps.

[0136] S310, the first network element sends the first configuration information to the terminal device, and the terminal device receives the first configuration information accordingly.

[0137] Specifically, the first configuration information includes identifiers for M first cells, where M is a positive integer. In one possible approach, the frequency range in which the first cells operate and the frequency range in which the first access network device operates can belong to different frequency ranges. Optionally, the first cells are cells operating in a first frequency range, and the first access network device is an access network device operating in a second frequency range, where the highest frequency in the first frequency range is lower than the lowest frequency in the second frequency range.

[0138] For example, the first frequency range is a low-frequency range, and the second frequency range is a high-frequency range. Further, the first frequency range is frequency range (FR)1, and the second frequency range is FR2. FR1 typically refers to the frequency range of 410MHz to 7125MHz, also known as the sub-6GHz band, while FR2 typically refers to the frequency range of 24.25GHz to 71GHz. FR2 can be further divided into FR2-1 and FR2-2, where FR2-1 typically refers to 24.25GHz to 52.6GHz, and FR2-2 typically refers to 52.6GHz–71GHz. The second frequency range can also be either FR2-1 or FR2-2.

[0139] Optionally, the first cell can be called a low-frequency cell, and the cell associated with the first access network device can be called a high-frequency cell or a millimeter-wave cell. When the first access network device is a base station, it can be called a high-frequency base station or a millimeter-wave base station.

[0140] Specifically, the first configuration information includes information about the first AI model. The following provides specific examples of the first AI model, namely Example 1 and Example 2. In Example 1, the input to the first AI model is the first input; in Example 2, the input to the first AI model is the first input and the second input.

[0141] Example 1: The input to the first AI model includes a first input, which is the first channel state information of M first cells measured by the terminal device. The output of the first AI model includes first beam information, where M is a positive integer. In this application, a positive integer refers to an integer greater than or equal to 1. In Example 1, the first beam information is determined by the terminal device based on the first AI model and the first channel state information. That is, the terminal device can input the M first channel state information into the first AI model to obtain the first beam information, such as... Figure 4As shown, Figure 4 Taking M=3 as an example, low-frequency neighbor cell 1, low-frequency neighbor cell 2, and low-frequency neighbor cell 3 are all examples of the first cell, and CSI#1-1, CSI#1-2, and CSI#1-3 are all examples of the first channel state information.

[0142] Since there are M cells in the first cell, there can also be M first channel state information items. In other words, the first input can include M first channel state information items, and each of the M first channel state information items corresponds one-to-one with one of the M first cells.

[0143] For example, the first network element can configure M first cells to the terminal device through the first configuration information, and the M first cells can be cells in the first cell identifier list. That is, the first configuration information can include the first cell identifier list, and the first cell identifier list can include the identifiers of the M first cells. Optionally, the first cells in the first cell identifier list (i.e., the M first cells) are the neighboring cells of the terminal device.

[0144] For example, the first access network device is the access network device corresponding to the serving cell of the terminal device. That is, the terminal device is currently working within the coverage area of ​​the first access network device, or the terminal device can communicate with the first access network device, or the cell where the terminal device is stationed or has a connection is the cell of the first access network device.

[0145] Optionally, in a cellular system, there is usually an association between cells and access network devices. A cell is typically served by one access network device, and one access network device can support multiple cells. Therefore, in this application, the M first cells can be replaced by M second access network devices, and the M first channel state information can be replaced by channel state information between the terminal device and the M second access network devices. This M first channel state information can be determined by the terminal device by measuring the reference signals of the M second access network devices. Similarly, the first access network device can be replaced by the second cell, and the second channel state information can be replaced by the channel state information measured by the terminal in the second cell. The first beam information determined by the first AI model can be understood as the beam used for communication within the second cell.

[0146] As one possible implementation, the M first channel state information pieces are determined based on reference signals in the M first cells. That is, a first channel state information piece can be determined using the reference signal of each of the M first cells. Optionally, the first configuration information may also include configuration information of the reference signals in the M first cells. For example, the first configuration information may include the identifiers of the M first cells and the identifiers of the M reference signal resources associated with each of the M first cells. These M reference signal resources are used to transmit reference signals in the M first cells. The channel state information in this application (including the first channel state information and the second channel state information described below) can all be understood as the reference signal measurement results of the terminal device.

[0147] For example, the positions of the M first channel state information items in the first input are determined based on the position of the identifier of the first cell associated with the first channel state information in the first cell identifier list. Alternatively, the first network element can also directly configure the positions of the first channel state information items of the M first cells in the first input. For example, the first configuration information includes the identifiers of the M first cells and the input position index associated with each of the M first cell identifiers.

[0148] Specifically, the M first channel state information items can be mapped to the first input in a default order. For example, the first input is a matrix of X1 rows and Y1 columns, indicating that the first input includes X1 first channel state information items. Each first channel state information item is represented by a vector of length Y1. The first channel state information #1 corresponding to the first first cell in the first cell identifier list (i.e., first cell #1) is mapped to the first row of the first input, the first channel state information #2 corresponding to the second first cell in the first cell identifier list (i.e., first cell #2) is mapped to the second row of the first input, and so on. For example, the first input is a matrix of Y1 rows * X1 columns, indicating that the first input includes X1 first channel state information items. Each first channel state information item is represented by a vector of length Y1. The first channel state information #1 corresponding to the first first cell in the first cell identifier list (i.e., first cell #1) is mapped to the first column of the first input, the first channel state information #2 corresponding to the second first cell in the first cell identifier list (i.e., first cell #2) is mapped to the second column of the first input, and so on. That is, each first channel state information item can be input into different columns of the first input. Optionally, X1 can be equal to M. Optionally, when X1 < M, only the first X1 first channel state information items out of the M first channel state information items can be used as the first input. Optionally, when X1 > M, the values ​​of the second-to-last (X1-M) rows of the first input can be filled with default values ​​(e.g., 0), where X1 and Y1 are both positive integers. Alternatively, if the first configuration information configures the identifiers of M first cells and the input location indexes associated with each of the M first cell identifiers, then the positions of the M first channel state information items in the first input can be determined according to this association. That is, the M first channel state information items are mapped to the first input in the order indicated by the aforementioned association. It should be understood that * in this application represents a multiplication sign, which can also be replaced by × or ·, etc.

[0149] Optionally, due to the influence of the communication environment, for the reference signal of some of the M first cells, the terminal device may not be able to accurately receive the reference signal, or the terminal device may determine that the signal-to-noise ratio of the reference signal is too low. In this case, the terminal device can represent the first channel state information corresponding to this part of the first cells with a default value (e.g., 0) and input it into the first input. For example, in Figure 4 If the terminal device only measures the reference signals of low-frequency neighbor cell 1 and low-frequency neighbor cell 3, then CSI#1-1 and CSI#1-3 can be normally input into the first AI model, and the position of CSI#1-2 can be input using the default value (e.g., 0).

[0150] For example, the first channel state information may be channel response coefficients, multipath information, power (or amplitude, coefficient) delay spectrum, etc., determined based on the reference signal of the first cell. For instance, the first channel state information may be a first delay amplitude spectrum or a first delay power spectrum determined based on the reference signal of the first cell (i.e., reference signals transmitted on M reference signal resources). Specifically, the first delay amplitude spectrum or the first delay power spectrum can be represented by a vector of length Y², where each element is a real number representing the amplitude, power, normalized amplitude, normalized power, etc., of the channel in each delay component. Alternatively, the first channel state information may be a first coefficient delay spectrum determined based on the reference signal of the first cell. The first coefficient delay spectrum can be represented by a vector of length Y², where each element is a complex number representing the coefficient or normalized coefficient of the channel in each delay component, including amplitude and phase information, where Y² is a positive integer. Alternatively, the first coefficient delay spectrum can be represented by a vector of length 2*Y², where Y² values ​​are the real part of the coefficients, and the other Y² values ​​are the imaginary part of the coefficients.

[0151] Example 2: The inputs to the first AI model include a first input and a second input. The first input is described above, and the second input is the second channel state information between the terminal device and the first access network device. The output of the first AI model includes first beam information. In Example 2, the first beam information is determined by the terminal device based on the first AI model, the first channel state information, and the second channel state information. That is, the terminal device can input the first channel state information and the second channel state information into the first AI model to obtain the first beam information, such as... Figure 5 As shown, Figure 5 Taking M=3 as an example, low-frequency neighbor cell 1, low-frequency neighbor cell 2, and low-frequency neighbor cell 3 are all examples of the first cell, and CSI#1-1, CSI#1-2, and CSI#1-3 are all examples of the first channel state information. The serving base station (i.e., the base station associated with the UE's serving cell) represents the first access network device, and the CSI of the serving base station represents the second channel state information.

[0152] Similar to the first channel state information, the second channel state information can also be one or more, for example, L second channel state information, where L is a positive integer. As one possible implementation, the L second channel state information are determined by the terminal device based on measurement results on L first reference signal resources. For example, the second channel state information could be measured channel response coefficients, multipath information, power (or amplitude, coefficient) delay spectrum, etc.

[0153] Optionally, the first configuration information may include a first reference signal resource identifier list, which includes identifiers of K first reference signal resources. The K first reference signal resources are used by the first access network device to transmit reference signals. The L second channel state information is determined by the terminal device based on the measurement results of the L first reference signal resources out of the K first reference signal resources, where K is a positive integer.

[0154] Specifically, the first network element can configure K first reference signal resources to the terminal device through first configuration information, and the K first reference signal resources can be resources in the first reference signal resource identifier list. Furthermore, the first access network device can transmit reference signals on the K first reference signal resources, and correspondingly, the terminal device can receive reference signals on L of the K first reference signal resources, thereby measuring L second channel state information, where L is less than or equal to K.

[0155] For example, the second input has X2 rows or X2 columns, and the first reference signal resource identifier list has K first reference signal resource identifiers to identify the K first reference signal resources. The second channel state information corresponding to the first first reference signal resource (i.e., first reference signal resource #1) in the first reference signal resource identifier list is mapped to the first row or first column of the second input, the second channel state information corresponding to the second first reference signal resource (i.e., first reference signal resource #2) in the first reference signal resource identifier list is mapped to the second row or second column of the second input, and so on. Optionally, X2 can be equal to K. Optionally, when X2 < K, only the second channel state information corresponding to the first X2 first reference signal resource identifiers out of the K first reference signal resource identifiers can be mapped to the second input. Optionally, when X2 > K, the values ​​of the second input's reciprocal (X2-K) rows can be filled with default values ​​(e.g., 0) and then mapped to the second input.

[0156] It should be understood that the first access network device operates in the FR2 frequency band, and the reference signals transmitted by the first access network device are typically transmitted via beams. Therefore, K first reference signal resources can correspond to K beams of the first access network device, meaning that the first access network device can use K different beams to transmit reference signals separately. According to the above method, the second channel state information corresponding to different beams can be determined by the first reference signal resource identifier list and input into the second input.

[0157] It should also be understood that in millimeter-wave communication scenarios, terminal devices typically do not measure all beams within the serving cell of a millimeter-wave base station, but only measure information from a subset of beams (e.g., currently in normal use or their neighboring beams). Therefore, the terminal device can measure the reference signals on L of the K first reference signal resources. That is, the terminal device can receive and measure the L first reference signals respectively, thereby obtaining L second channel state information. Therefore, the L second channel state information can be understood as the channel state information obtained by the terminal device between itself and the first access network device under different beams.

[0158] For example, the position of the second channel state information in the second input is determined based on the position of the identifier of the first reference signal resource associated with the second channel state information in the first reference signal resource identifier list. Specifically, in the second input, the positions of the L second channel state information are the positions of the L first reference signal resources corresponding to the L second channel state information in the K first reference signal resources. That is, the terminal device can input only the second channel state information corresponding to the measured reference signal (i.e., the L second channel state information) into the corresponding positions in the second input, and the other parts of the input can be filled with default values ​​(e.g., 0).

[0159] For example, such as Figure 6 As shown, assuming the first reference signal resource identifier list includes 10 rows or columns (i.e., K = 10), used to identify resource #1, resource #2, ..., resource #10 respectively, and the second input has 13 rows (i.e., X2 = 13), the UE (an example of a terminal device) measures resource #3 and resource #5, obtaining CSI#2-3 and CSI#2-5 respectively, i.e., L = 2. In this case, since X2 > K, the first 10 rows in the second input correspond to resource #1, resource #2, ..., resource #10 respectively, and the values ​​of the last 3 rows in the second input can be set to default values, such as 0. Furthermore, since the UE only measured resources #3 and #5, the position of CSI#2-3 in the second input is the position of resource #3 associated with CSI#2-3 in the second input, which is row 3. The position of CSI#2-5 in the second input is the position of resource #5 associated with CSI#2-5 in the second input, which is row 5. Other positions are filled with default values ​​(e.g., 0) because no corresponding CSI was measured. It should be noted that... Figure 6 The zeros in this context can be interpreted as scalars, vectors consisting entirely of zeros, matrices, or tensors of other shapes. The specific shape can be determined based on the specific format of the channel state information. Optionally, the default values ​​can differ for different input positions.

[0160] Alternatively, the first configuration information can directly configure K first reference signal resource identifiers and the input position index associated with each of the K first reference signal resource identifiers. Then, the position of L second channel state information in the second input can be determined according to the association relationship. In other words, the L second channel state information is mapped to the second input in the order indicated by the association relationship.

[0161] For example, the update frequencies of the first input and the second input can be different. Specifically, when the terminal device communicates with the first access network device, it can measure the reference signal in the first access network device at a shorter period, so the update frequency of the second input can be higher. However, the measurement period for the reference signal of the first cell may be longer, so the update frequency of the first input may be lower. When the terminal device needs to use the first AI model to predict the first beam information, the terminal device uses the latest obtained reference signal measurement result as the first input, or as both the first and second inputs.

[0162] For example, taking the first AI model's input as including a first input and a second input, assuming the UE's measurement period for the reference signal of a low-frequency neighboring cell (an example of the first cell) is 100ms, then the UE (an example of a terminal device) can measure the reference signals of M low-frequency neighboring cells at time points 0ms, 100ms, 200ms, ... Assuming the UE's measurement period for the reference signal of a millimeter-wave base station (an example of the first access network device) is 20ms, then the UE can measure the reference signal of the millimeter-wave base station at time points 0ms, 20ms, 40ms, ... When the UE needs to use the first AI model to predict the first beam information, at time point 0ms, the UE will use the measurement results of the reference signals of the M low-frequency neighboring cells at 0ms as the first input and the measurement results of the reference signals of the millimeter-wave base station at 0ms as the second input. At time point 20ms, the UE will use the measurement results of the reference signals of the M low-frequency neighboring cells at 0ms as the first input and the measurement results of the reference signals of the millimeter-wave base station at 20ms as the second input. At 40ms, the UE will use the reference signal measurement results of M low-frequency neighboring cells from 0ms as the first input and the reference signal measurement results of the millimeter-wave base station from 40ms as the second input. At 100ms, the UE will use the reference signal measurement results of M low-frequency neighboring cells from 100ms as the first input and the reference signal measurement results of the millimeter-wave base station from 100ms as the second input. At 120ms, the UE will use the reference signal measurement results of M low-frequency neighboring cells from 100ms as the first input and the reference signal measurement results of the millimeter-wave base station from 120ms as the second input. At 140ms, the UE will use the reference signal measurement results of M low-frequency neighboring cells from 100ms as the first input and the reference signal measurement results of the millimeter-wave base station from 140ms as the second input.

[0163] In one implementation, the first beam information refers to the beam information predicted by the AI ​​model that can be used for communication between the terminal device and the first access network device. For example, the possible situations of the first beam information are illustrated below. The content of the first beam information can be any one of the following situations, or a combination of the following situations.

[0164] Case 1: The first beam information includes one or more beams of the first access network device. Specifically, in any of the above examples, the output of the first AI model can be one or more beams of the first access network device. The beams of the first access network device can also be referred to as base station-side beams, access network device-side beams, access network device-side beams, or beams on the first access network device side. Optionally, beams can be represented by beam indices; therefore, in Case 1, the output of the first AI model can be one or more beam indices of the first access network device.

[0165] For example, one or more beams of the first access network device can be an index (or identifier) ​​of one or more beams, wherein the index can be a number, which can be an integer or can be converted (e.g., by rounding) to an integer. Alternatively, the index can be an array.

[0166] For example, such as Figure 7 As shown, when the first access network device uses a discrete Fourier transform beamcodebook or a beamcodebook based on physical angles, it can have A1 beams in the horizontal direction and A2 beams in the vertical direction, where A1 and A2 are both positive integers. Figure 7 Each circle in the diagram represents a beam; therefore, the first access network device has a total of A1*A2 beams. In the output of the first AI model, a beam of the first access network device can be represented by a single number, ranging from 1 to A1*A2 (or 0 to A1*A2-1). Each integer indicates a beam of the first access network device, and the mapping from this integer to the beam can be either horizontal to vertical or vertical to horizontal. Alternatively, a beam of the first access network device in the output of the first AI model can be a binary array. The first number in the binary array represents the horizontal beam, with a value range of 1 to A1 (or 0 to A1-1), and the second number in the binary array represents the vertical beam, with a value range of 1 to A2 (or 0 to A2-1). Alternatively, the second number in the binary array represents the horizontal beam, with a value range of 1 to A1 (or 0 to A1-1), and the first number in the binary array represents the vertical beam, with a value range of 1 to A2 (or 0 to A2-1). The binary array composed of these two numbers together indicates a beam of the first access network device.

[0167] Scenario 2: The first beam information includes one or more beam combinations, each of which includes a beam from the first access network device and a beam from the terminal device. Specifically, in any of the above examples, the output of the first AI model can be one or more beam combinations, each including a beam from the first access network device and a beam from the terminal device.

[0168] In this application, the beam of the terminal device can also be referred to as the terminal-side beam or the beam on the terminal device side. Optionally, the beam can be represented by a beam index. Therefore, in case 2, the output of the first AI model can be one or more beam indices of the first access network device and one or more beam indices of the terminal device, wherein the beam index of the first access network device and the beam index of the terminal device are related.

[0169] For example, one or more beams of the first access network device can be indices of one or more beams, specifically represented as in Case 1. For example, one or more beams of the terminal device can be indices of one or more beams, specifically represented in a similar manner to Case 1. That is, the index of a beam of the terminal device can be a number, which can be an integer, or can be converted (e.g., by rounding) to an integer. Alternatively, the index can be an array.

[0170] For example, such as Figure 8 As shown, when the terminal device uses a discrete Fourier transform beamcodebook or a beamcodebook based on physical angles, it can have B1 beams in the horizontal direction and B2 beams in the vertical direction, where B1 and B2 are both positive integers. Figure 8 Each circle in the diagram represents a beam; therefore, the terminal device has a total of B1*B2 beams. In the output of the first AI model, a beam of the terminal device can be represented by a single number, ranging from 1 to B1*B2 (or 0 to B1*B2-1). Each integer indicates a beam of the terminal device, and the mapping from this integer to the beam can be either horizontal to vertical or vertical to horizontal. Alternatively, a beam of the terminal device in the output of the first AI model can be a binary array. The first number in the binary array represents the horizontal beam, with a value range of 1 to B1 (or 0 to B1-1), and the second number in the binary array represents the vertical beam, with a value range of 1 to B2 (or 0 to B2-1). Or, the second number in the binary array represents the horizontal beam, with a value range of 1 to B1 (or 0 to B1-1), and the first number in the binary array represents the vertical beam, with a value range of 1 to B2 (or 0 to B2-1). The binary array composed of these two numbers together indicates a beam of the terminal device.

[0171] Optionally, each beam of the terminal device is associated with angle information, and the first configuration information may include the association between each beam and angle information of the terminal device. For example, the angle information can be an angle in a global coordinate system or an angle in a local coordinate system. Optionally, the beam of the terminal device in the output of the first AI model can directly indicate the angle information of the terminal device's beam. For example, the beam of the terminal device in the output of the first AI model is an array of length 2, where one number in the array indicates the angle of the horizontal beam of the terminal device, and the other number indicates the angle of the vertical beam of the terminal device.

[0172] Optionally, the beams of both the first access network device and the terminal device in the beam combination can be indicated by beam indices. The type of the beam index of the first access network device and the type of the beam index of the terminal device can be the same or different, without restriction. For example, if both the beam index of the first access network device and the beam index of the terminal device are integers, then the first beam information can be represented by a binary array, where one number represents the beam index of the first access network device and the other number represents the beam index of the terminal device. As another example, if both the beam index of the first access network device and the beam index of the terminal device are binary arrays, then the first beam information can be represented by a quaternion array, where two numbers represent the beam index of the first access network device and the other two numbers represent the beam index of the terminal device. Yet another example is where one index of the beam index of the first access network device and the beam index of the terminal device is an integer and the other index is a binary array.

[0173] Optionally, the beam of the first access network device in the beam combination is indicated by the beam index, and the beam of the terminal device is indicated by the beam angle. The beam index of the first access network device can be an integer or a binary array. For example, the first beam information can be represented by a quaternion array, where two numbers represent the beam index of the first access network device, and the other two numbers represent the horizontal and vertical angles corresponding to the beam of the terminal device, respectively.

[0174] Scenario 3: The first beam information includes one or more beam pairs, each of which is associated with a beam from the first access network device and a beam from the terminal device. Specifically, in any of the above examples, the output of the first AI model can be one or more beam pairs, each associated with a beam from the first access network device and a beam from the terminal device.

[0175] In one implementation, a beam pair consists of a transmit beam and a receive beam. When the two beams form a beam pair, the transmitter can use the transmit beam in the beam pair to send information #1 to the receiver, and the receiver can use the receive beam in the beam pair to receive information #1 from the transmitter. That is, the transmitter and receiver can use the beam pair to communicate.

[0176] For example, the output of the first AI model can be one or more beam pair indices, each beam pair index associating a beam from the first access network device and a beam from the terminal device. This association can be mapped according to the beam priority order of the first access network device or the beam priority order of the terminal device.

[0177] For example, such as Figure 7 As shown, the first access network device has a total of A1*A2 beams, as follows: Figure 8 As shown, the terminal device has a total of B1*B2 beams. Therefore, the beams of the first access network device and the beams of the terminal device can form A1*A2*B1*B2 beam pairs. The index of each beam pair can be represented by z, and the value of z is an integer between 1 and A1*A2*B1*B2 (or 0 to A1*A2*B1*B2-1). Each integer is used to indicate one beam of the first access network device and one beam of the terminal device. The mapping relationship between this integer and the beam pair can be mapped in the order of the first access network device beam first and the terminal device beam second, or in the order of the terminal device beam first and the first access network device beam second.

[0178] The difference between Case 2 and Case 3 is that in Case 2, the first AI model directly outputs the beam index of the access network device and the beam index or angle of the terminal device, while in Case 3, the first AI model outputs the index of the beam pair, which can be further converted into the beam of the access network device and the beam of the terminal device based on the index of the beam pair.

[0179] Case 4: The first beam information includes a first signal strength tensor of multiple beams of the first access network device, where each position in the first signal strength tensor is associated with a beam of the first access network device. Specifically, in any of the above examples, the output of the first AI model can be a first signal strength tensor of multiple beams of the first access network device, where each position in the first signal strength tensor is associated with a beam of the first access network device.

[0180] For example, each position in the first signal strength tensor corresponds to a beam of the first access network device, and the elements at each position in the tensor represent the signal strength of the beam of the first access network device corresponding to that position. Therefore, the number of elements in the first signal strength tensor can represent the number of beams of the first access network device. Optionally, the first signal strength tensor can be a one-dimensional tensor, and the length of the one-dimensional tensor can represent the number of beams of the first access network device. For example, as... Figure 7 As shown, the first access network device has a total of A1*A2 beams, and the first signal strength tensor can have A1*A2 elements, with a length of A1*A2. Optionally, the first signal strength tensor can be a two-dimensional tensor, the shape of which can represent the number of beams of the first access network device. For example, as... Figure 7 As shown, the first access network device has a total of A1*A2 beams. The elements in the first signal strength tensor can be A1*A2, and its shape can be A1*A2. The i-th row and j-th column of this two-dimensional tensor represent the signal strength of the beam of the first access network device with beam index (i, j), where i and j are positive integers.

[0181] Scenario 5: The first beam information includes a second signal strength tensor of multiple beam pairs, where each position in the second signal strength tensor is associated with a beam from the first access network device and a beam from the terminal device. Specifically, in any of the above examples, the output of the first AI model can be a second signal strength tensor of multiple beam pairs, where each position in the second signal strength tensor is associated with a beam pair, and each beam pair includes a beam from the first access network device and a beam from the terminal device.

[0182] For example, each position in the second signal strength tensor corresponds to a beam pair, and each element in the tensor represents the signal strength of the beam pair corresponding to that position. That is, it can identify the signal strength (or normalized strength) that the terminal device can receive when the first access network device and the terminal device use the beam pair to send a signal. Therefore, the number of elements in the second signal strength tensor can represent the number of beam pairs.

[0183] Optionally, the first signal strength tensor can be a one-dimensional tensor, the length of which can represent the number of beam pairs. For example, as... Figure 7 As shown, the first access network device has a total of A1*A2 beams, as follows: Figure 8 As shown, the terminal device has a total of B1*B2 beams. Therefore, the second signal strength tensor can have A1*A2*B1*B2 elements, and its length is A1*A2*B1*B2. The position of a certain element in this one-dimensional tensor can be understood as the beam pair index in Case 3. Therefore, the method of mapping the position of a certain element to the specific beams of the first access network device and the terminal device can refer to the method of mapping the beam pair index to the beams of the first access network device and the terminal device in Case 3.

[0184] Optionally, the first signal strength tensor can be a two-dimensional tensor, where the size of one dimension is equal to the number of beams of the first access network device, and the size of the other dimension is equal to the number of beams of the terminal device. For example, as... Figure 7 As shown, the first access network device has a total of A1*A2 beams, as follows: Figure 8As shown, the terminal device has a total of B1*B2 beams. Therefore, the second signal strength tensor can have A1*A2*B1*B2 elements, and its shape can be [C1]*[C2], where C1 = A1*A2 and C2 = B1*B2. The position of each element in the second signal strength tensor can be represented by (c1, c2), where c1 is an integer from 1 to C1 or from 0 to C1-1, and c2 is an integer from 1 to C2 or from 0 to C2-1. Here, c1 can be understood as the beam index of the first access network device, and c2 can be understood as the beam index of the terminal device. The element located at (c1, c2) in the second signal strength tensor can be understood as the signal strength (or normalized strength) that the first access network device can receive when transmitting a signal using the first access network device's beam with beam index c1, and the terminal device can receive a signal using the terminal device's beam with beam index c2. Furthermore, c1 can be associated with the horizontal and vertical beam indices on the access network device side, and the specific method can be referred to in case 1. c2 can be associated with the horizontal and vertical beam indices on the terminal device side, and the specific method can be referred to in case 2.

[0185] Similarly, the first signal strength tensor can be a three-dimensional tensor, where the size of one dimension of the three-dimensional tensor is equal to the number of horizontal beams of the first access network device, the size of another dimension of the three-dimensional tensor is equal to the number of vertical beams of the first access network device, and the size of yet another dimension of the three-dimensional tensor is equal to the number of beams of the terminal device. For example, as Figure 7 As shown, the first access network device has a total of A1*A2 beams, as follows: Figure 8 As shown, the terminal device has a total of B1*B2 beams. Therefore, the second signal strength tensor can have A1*A2*B1*B2 elements, and its shape can be [A1]*[A2]*[C2], where C2 = B1*B2. The position of each element in the second signal strength tensor can then be represented by (a1, a2, c2), where a1 is an integer from 1 to A1 or from 0 to A1-1, a2 is an integer from 1 to A2 or from 0 to A2-1, and c2 is an integer from 1 to C2 or from 0 to C2-1. At this point, a1 can be understood as the horizontal beam index of the first access network device, a2 as the vertical beam index of the first access network device, and c2 as the beam index on the terminal device side. The element in the second signal strength tensor located at (a1, a2, c2) can be understood as the signal strength (or normalized strength) that the first access network device can receive when transmitting signals using the beam of the first access network device side with horizontal beam index a1 and vertical beam index a2, and the terminal device can receive signals using the beam of the terminal device side with beam index c2. Furthermore, c2 can be associated with the horizontal and vertical beam indices on the terminal device side; for details, please refer to Case 2.

[0186] Alternatively, the first signal strength tensor can be a three-dimensional tensor, where the size of one dimension of the three-dimensional tensor is equal to the number of beams of the first access network device, the size of another dimension of the three-dimensional tensor is equal to the number of horizontal beams of the terminal device, and the size of yet another dimension of the three-dimensional tensor is equal to the number of vertical beams of the terminal device. For example, as... Figure 7 As shown, the first access network device has a total of A1*A2 beams, as follows: Figure 8 As shown, the terminal device has a total of B1*B2 beams. Therefore, the second signal strength tensor can have A1*A2*B1*B2 elements, and its shape can be [C1]*[B1]*[B2], where C1 = A1*A2. The position of each element in the second signal strength tensor can then be represented by (c1, b1, b2), where c1 is an integer from 1 to C1 or from 0 to C1-1, b1 is an integer from 1 to B1 or from 0 to B1-1, and b2 is an integer from 1 to B2 or from 0 to B2-1. At this point, b1 can be understood as the horizontal beam index of the terminal device, b2 as the vertical beam index of the terminal device, and c1 as the beam index of the first access network device. The element in the second signal strength tensor located at (c1, b1, b2) can be understood as the signal strength (or normalized strength) that the terminal device can receive when the first access network device transmits a signal using the access network device-side beam with beam index c1 and receives a signal using the terminal device-side beam with horizontal beam index b1 and vertical beam index b2. Furthermore, c1 can be associated with the horizontal and vertical beam indices of the first access network device; for details, please refer to Case 2.

[0187] Similarly, the first signal strength tensor can be a four-dimensional tensor, where the beams of the first access network device and the terminal device are both represented by binary arrays. Specifically, the size of one dimension of this four-dimensional tensor is equal to the number of horizontal beams of the first access network device, the size of another dimension of this four-dimensional tensor is equal to the number of horizontal beams of the terminal device, the size of yet another dimension of this four-dimensional tensor is equal to the number of vertical beams of the first access network device, and the size of yet another dimension of this four-dimensional tensor is equal to the number of vertical beams of the terminal device. For example, as mentioned above regarding... Figure 7 and Figure 8 For example, its shape can be [A1]*[A2]*[B1]*[B2].

[0188] Optionally, the signal strength tensor output in Case 4 can be understood as a probability tensor that each beam is the optimal beam, or a tensor of recommended values ​​for each beam; the signal strength tensor output in Case 5 can be understood as a probability tensor that each beam pair is the optimal beam pair, or a tensor of recommended values ​​for each beam pair. When predicting only the beams on the first access network device side, the form of the first beam can adopt the above-described Case 1 and Case 4. When predicting both the beams on the first access network device side and the beams on the terminal device side simultaneously, the form of the first beam can adopt the above-described Case 2, Case 3, and Case 5.

[0189] The following is a brief explanation of the specific principles of the first AI model. In wireless transmission networks, the channel between devices is mainly affected by factors such as the location of the transceiver and the physical environment (including the location, size, and material properties of scatterers in the environment). For cellular networks (including current 5G networks and future 6G networks), the location of access network devices is generally fixed, and the physical environment is generally relatively stable. Therefore, the channel between access network devices and terminal devices is usually mainly affected by the location of the terminal devices. When the physical environment is complex enough, theoretically, it can be guaranteed that the channel between a specific access network device and a terminal device is a bijection with respect to the terminal location. That is, a terminal location can uniquely correspond to a channel, and a channel can uniquely correspond to a terminal location. Therefore, in the scenario of this application, there are theoretically two mappings. Mapping 1 is that the channel state information between each first cell and the terminal device can be mapped to the location of a specific terminal device, and mapping 2 is that the location of the terminal device can be mapped to the channel state information between the first access network device and the terminal. The first beam information can be determined through the channel state information between the first access network device and the terminal device. Therefore, after cascading these mappings, it can be considered that there is a stable mapping between the channel state information between each first cell and the terminal device and the first beam information. Based on the above principles, the mapping relationship can be represented by a first AI model. Specifically, nodes in the network, such as the first network element, can first determine the structure of a first AI model, and then train the first AI model by collecting a large amount of data (including channel state information and first beam information between each first cell and terminal device), and finally obtain the first AI model.

[0190] S320: The terminal device sends information about N beams to the first access network device.

[0191] Here, N beams are the beams recommended by the terminal device, and the information of the N beams is determined based on the information of the first beam, where N is a positive integer. In other words, the N beams are the beams recommended by the terminal device and used by the first access network device to communicate with the terminal device. It should be understood that the N beams being recommended by the terminal device means that the first access network device may use one or more of the N beams to communicate with the terminal device, or it may choose not to use any of them.

[0192] For example, the information of the N beams is determined based on the first beam information, meaning that the N beams are the N beams of the first access network device included in the first beam information. In other words, the terminal device can report all the beams of the first access network device in the output of the first AI model to the first access network device, or the terminal device can filter the beams of the first access network device in the output of the first AI model to obtain N beams, and then report them to the first access network device.

[0193] For example, as in cases 1, 2, or 3 above, if the first beam information includes N beams of the first access network device, the terminal device can report the indices of the N beams of the first access network device to the first access network device. As another example, as in cases 4 or 5 above, if the first beam information includes the signal strength of one or more beams of the first access network device, the terminal device can determine the N beams with the largest signal strength based on the signal strength, and then report the indices of these N beams to the first access network device. In other words, the information for N beams can include the indices of the N beams.

[0194] Optionally, the first configuration information includes a list of third reference signal resource identifiers, which includes identifiers of P third reference signal resources. Each of the P identifiers of the third reference signal resources has an associated relationship with a beam of the first access network device, where P is a positive integer. This association relationship can be used by the terminal device to report information about N beams, and can also be used by the terminal device to determine its receiving beam when it receives a first channel or a first signal from the first access network device.

[0195] Specifically, the terminal device can report the identifiers of the third reference signal resources associated with N beams to the first access network device. That is, the information of the N beams can include the identifiers of the third reference signal resources associated with the indices of the N beams. For example, as in cases 1, 2, or 3 above, if the first beam information includes N beams of the first access network device, the terminal device can report the identifiers of the third reference signal resources associated with the N beams of the first access network device to the first access network device. As another example, as in cases 4 or 5 above, if the first beam information includes the signal strength of one or more beams of the first access network device, the terminal device can determine the N beams with the largest signal strength based on the signal strength, and then report the identifiers of the third reference signal resources associated with these N beams to the first access network device.

[0196] For example, the identifiers of the P third reference signal resources are associated with the beam of the first access network device, including: the i-th reference signal resource among the P third reference signal resource identifiers is associated with the beam i of the first access network device, where i is an integer greater than or equal to 0 and less than or equal to P. The specific identifier or index (e.g., i) of the beam of the first receiving network device can be found in the relevant description in the first beam information in S310.

[0197] Based on the above scheme, the first network element can configure a first AI model for the terminal device. The input of the first AI model includes the channel state information of M first cells measured by the terminal device, and the output of the AI ​​model includes the first beam information for the first access network device. This enables the terminal device to report information of N beams recommended by the terminal device based on the first beam information to the first access network device. This facilitates the determination of the communication beam between the terminal device and the first access network device and ensures communication performance.

[0198] In addition, the above scheme can use the channel state information of the first cell as the input of the AI ​​model and directly output the first beam information for the first access network device, thus avoiding two stages of beam training and saving beam training overhead.

[0199] In one implementation, the first AI model is used to determine the beam used for communication between the terminal device and the first access network device. In other words, the first beam information output by the first AI model can be used to determine the beam used for communication between the terminal device and the first access network device. The following describes this in detail with reference to S330 and S340.

[0200] Optionally, method 300 further includes: S330, the first access network device sends beam configuration information to the terminal device, and correspondingly, the terminal device receives the beam configuration information.

[0201] The beam configuration information is used to configure the beam of the first signal or the first channel, and this beam configuration information includes the identifier of the fourth reference signal resource. Specifically, it can be understood that the beam configuration information is used to indicate the identifier of the fourth reference signal resource associated with the first access network device transmitting the first signal or the first channel. Therefore, the terminal device can determine the fourth beam based on the identifier of the fourth reference signal resource, and the fourth beam is the beam of the first access network device associated with the fourth reference signal resource. For example, the fourth beam can be one of N beams reported by the terminal device, that is, the first access network device can configure the beam for transmitting the first signal or the first channel to be one of the N beams recommended by the terminal device.

[0202] Optionally, if the first configuration information includes a list of third reference signal resource identifiers, the identifier of the fourth reference signal resource can be one of the third reference signal resource identifiers. That is, the fourth reference signal resource can be one of P third reference signal resources. In this case, the terminal device determines the fourth beam based on the identifier of the fourth reference signal resource, which can also be understood as determining the fourth beam based on the list of third reference signal resource identifiers.

[0203] For example, when the i-th reference signal resource among the P third reference signal resources is associated with the beam i of the first access network device, the terminal device can determine the fourth beam based on the association between the identifiers of the P third reference signal resources and the beam of the first access network device. The fourth beam is the beam of the first access network device associated with the fourth reference signal resource among the P third reference signal resources.

[0204] Optionally, method 300 further includes: S340, the terminal device uses a fifth beam to receive a first signal or a first channel, wherein the fifth beam is a beam of the terminal device, and in the first beam information, the fourth beam is associated with the fifth beam.

[0205] Specifically, the terminal device can determine, based on the first beam information, that the beam associated with the fourth beam is the fifth beam, thereby determining to use the fifth beam to receive the first signal or the first channel. Here, the terminal device determining that the beam associated with the fourth beam is the fifth beam based on the first beam information can be understood as the terminal device determining the beam used for communication between the terminal device and the first access network device using the first beam information.

[0206] In this application, the fourth beam and the fifth beam are associated, which can also be understood as the fourth beam and the fifth beam forming a beam pair, or the fourth beam and the fifth beam being matched, or a corresponding or associated relationship existing between the fourth beam and the fifth beam. For example, if the form of the first beam information adopts case 2, then the first beam information includes one or more beam combinations. In one of the beam combinations, the beam of the corresponding first access network device is the fourth beam, and the beam of the corresponding terminal device is the fifth beam.

[0207] Based on the above scheme, the first beam information can be used to determine the beam used for communication between the terminal device and the first access network device, thus ensuring the communication performance between the terminal device and the first access network device.

[0208] For example, the first reference signal resource identifier list and the third reference signal resource identifier list in this application are the same list. Specifically, when configuring the first network element to the terminal device, it can configure only one of the first and third reference signal resource identifier lists. This list is not only used by the first access network device to send reference signals so that the terminal device can determine the second channel state information (see the second input in S310), but also used to determine the information of N beams when the terminal device reports N beams (see S320), and can also be used to determine the receiving beam of the terminal device when the terminal device receives the first channel or the first signal from the first access network device (see S330). In this way, the configuration can be simplified and the communication efficiency can be improved.

[0209] Figure 9 This is a schematic flowchart illustrating a communication method provided in this application. Figure 9 As shown, the method 400 includes the following steps.

[0210] S410, the first network element sends first configuration information and second configuration information to the terminal device, and the terminal device receives the first configuration information and second configuration information accordingly.

[0211] The specific content of the first configuration information in S410 is basically the same as that in S310, except that the first configuration information in S410 does not include the first reference signal resource identifier list in S310. Specifically, in method 400, the input of the first AI model only includes the first input and does not include the second input, and the output of the first AI model is still the first beam information. That is, the first AI model is as shown in Example 1 of S310, therefore, the first configuration information may not include the first reference signal resource identifier list.

[0212] The second configuration information includes a first reference signal resource identifier list and a second AI model. Specifically, the meaning and content of the first reference signal resource identifier list are the same as in S310, that is, the first reference signal resource identifier list includes identifiers of K first reference signal resources. Therefore, similar to S310, the terminal device can determine L second channel state information based on the measurement results of L of the K first reference signal resources. Specifically, the input to the second AI model is one piece of second channel state information. The specific description of the second channel state information is the same as in S310 and will not be repeated here. The output of the second AI model is a feature vector. That is, the terminal device can input the second channel state information into the second AI model to obtain feature vectors. For L pieces of second channel state information, the terminal device can input them into the second AI model respectively to obtain L feature vectors.

[0213] like Figure 10 As shown, Figure 10 In the middle, the serving base station represents the first access network device, the CSI of the serving base station represents the second channel state information, and the perceived feature represents the feature vector output by the second AI model.

[0214] In this application, the feature vector output by the second AI model can also be called a feature tensor, perceptual feature, channel state information feature, etc. It can be understood as a feature extracted based on the second channel state information, which may not have a clear physical meaning. It can be a one-dimensional or multi-dimensional array, or it can be understood as a tensor.

[0215] S420: The terminal device sends information about N beams to the first access network device.

[0216] Among them, N beams are the beams recommended by the terminal equipment, and the information of the N beams is determined based on the information of the first beam. Specifically, S420 is the same as S320, and will not be described in detail here.

[0217] S430: The first access network device sends multiple mapping relationships to the terminal device, and the terminal device receives multiple mapping relationships accordingly.

[0218] The multiple mapping relationships include identifiers of multiple first reference signal resources, multiple feature vectors, and multiple second beam information. As an example, each mapping relationship is: the relationship between an identifier of a first reference signal resource and a feature vector, mapped to a piece of second beam information, as shown in Table 1. As another example, each mapping relationship is: the relationship between a group of identifiers of a reference signal resource and a group of feature vectors, mapped to a piece of second beam information, as shown in Table 2.

[0219] Table 1

[0220] Identification of the first reference signal resource Feature vector Second beam information Logo 1 Vector 1 Second beam information 1 Logo 2 Vector 2 Second beam information 2 Mark 3 Vector 3 Second beam information 3 … … …

[0221] Taking Table 1 as an example, the relationship between the identifier of a first reference signal resource and the mapping of a feature vector to a second beam information can be understood as an identifier in the first column of Table 1 plus a vector in the second column, which can retrieve a second beam information in the third column.

[0222] Table 2

[0223]

[0224] Taking Table 2 as an example, the relationship between the identifier group of a reference signal resource and the feature vector group mapped to a second beam information can be understood as the identifier group in column 1 and the vector group in column 2 of Table 1 being able to retrieve a second beam information in column 3.

[0225] Optionally, the multiple mapping relationships can be determined by the first access network device based on the information of N beams. For example, the first access network device maintains a mapping relationship table. Based on the information of N beams, the first access network device can send a portion of the mapping relationships associated with the N beams in the mapping relationship table to the terminal device. In this case, Table 1 or Table 2 can be understood as a portion of the contents of the mapping relationship table, and the identifiers of the multiple first reference signal resources in Table 1 or Table 2 can refer to the identifiers of the first reference signal resources associated with the N beams.

[0226] For ease of explanation, the following description uses the example of "each mapping relationship in multiple mapping relationships is: the relationship between the identifier of a first reference signal resource and a feature vector mapped to a second beam information".

[0227] For example, the second beam information includes at least one of the following: one or more beams of the first access network device, one or more beam combinations, one or more beam pairs, a first signal strength tensor of multiple beams of the first access network device, a second signal strength tensor of multiple beam pairs, etc., wherein each beam combination in the one or more beam combinations includes a beam of the first access network device and a beam of the terminal device; each beam pair in the one or more beam pairs is associated with a beam of the first access network device and a beam of the terminal device; each position in the first signal strength tensor is associated with a beam of the first access network device; and each position in the second signal strength tensor is associated with a beam of the first access network device and a beam of the terminal device. Specifically, the specific meanings of the terms one or more beams of the first access network device, one or more beam combinations, one or more beam pairs, the first signal strength tensor of multiple beams of the first access network device, and the second signal strength tensor of multiple beam pairs can be referred to the description of the first beam information in section 310 above, and will not be repeated here.

[0228] S440, the terminal device sends information for Q beams to the first access network device.

[0229] In this configuration, Q beams are recommended by the terminal device, and the information of these Q beams is determined based on multiple mapping relationships. Specifically, the terminal device can determine a first feature vector based on measurement results on the second reference signal resource, then determine the third beam information based on the identifier of the second reference signal resource, the first feature vector, and multiple mapping relationships, and finally determine the information of the Q beams based on the third beam information. In other words, the terminal device can select Q beams from N beams based on multiple mapping relationships and the first feature vector.

[0230] In this table, the second reference signal resource is one of multiple first reference signal resources, and the third beam information is one of multiple second beam information. That is, the terminal device can determine the third beam information based on a specific row in Table 1, where the identifier of the second reference signal resource plus the second feature vector is mapped to the third beam information within that row.

[0231] The second feature vector is one of multiple feature vectors (e.g., vector 1, vector 2, vector 3, vector 4, vector 5, vector 6, etc. in Table 1 or Table 2). The first feature vector can be the same as or similar to the second feature vector. In other words, the terminal device can determine the third beam information based on the second feature vector that is the same as or similar to the first feature vector in multiple mapping relationships.

[0232] Optionally, for the L second channel state information determined by the terminal device, the terminal device can input the L second channel state information into the second AI model respectively, obtaining one first feature vector each time, that is, a total of L first feature vectors can be obtained. Furthermore, the terminal device can search Table 1 or Table 2 to determine D rows, where any row in the D rows satisfies the following condition: the identifiers of the L first reference signal resources measured by the terminal include the reference signal resource identifiers in the first column of that row. Further, for any row in the D rows, the terminal device can obtain the first feature vector or first feature vector group corresponding to one or more second state information associated with the reference signal resource identifier in that row through the second AI model, and then compare the first feature vector or first feature vector group with the second feature vector or second feature vector group in that row. If the difference between the two is less than a preset threshold, then that row can be a candidate row. The terminal device can determine the second beam information in some rows of one or more candidate rows as the third beam information, or it can determine the second beam information in the row with the smallest difference between the first feature vector or first feature vector group and the second feature vector or second feature vector group in the candidate rows as the third beam information.

[0233] Optionally, the information for the Q beams can be determined by the terminal device based on the third beam information. Specifically, similar to S320, if the third beam information includes the Q beams of the first access network device, the terminal device can report the indexes of the Q beams of the first access network device to the first access network device. Alternatively, if the third beam information includes the signal strength of one or more beams of the first access network device, the terminal device can determine the Q beams with the largest signal strength based on the signal strength, and then report the indexes of these Q beams to the first access network device. In other words, the information for the Q beams can include the indexes of the Q beams.

[0234] Optionally, similar to method 300, the first configuration information may include a list of third reference signal resource identifiers. In this case, when the terminal device reports information about Q beams to the first access network device, in addition to reporting the indexes of the Q beams, it may also report the identifiers of the third reference signal resources associated with the Q beams. That is, the information about the Q beams may include the identifiers of the third reference signal resources associated with the indexes of the Q beams. For example, if the third beam information includes Q beams of the first access network device, the terminal device may report the identifiers of the third reference signal resources associated with the Q beams of the first access network device to the first access network device. As another example, if the third beam information includes the signal strength of one or more beams of the first access network device, the terminal device may determine the Q beams with the largest signal strength based on the signal strength, and then report the identifiers of the third reference signal resources associated with these Q beams to the first access network device.

[0235] It should be understood that in method 400, each of the P identifiers of the third reference signal resources is associated with the beam of the first access network device. The aforementioned association can be used by the terminal device to report information of the Q beams, and can also be used by the terminal device to determine the receiving beam of the terminal device when it receives the first channel or the first signal from the first access network device.

[0236] For example, the identifiers of the P third reference signal resources are associated with the beam of the first access network device, including: the i-th reference signal resource among the P third reference signal resource identifiers is associated with the beam i of the first access network device, where i is an integer greater than or equal to 0 and less than or equal to P. The specific identifier or index (e.g., i) of the beam of the first receiving network device can be found in the relevant description in the first beam information in S310.

[0237] For example, the terminal device determines the first feature vector based on the measurement results on the second reference signal resource. Specifically, the terminal device determines the second channel state information based on the measurement results on the second reference signal resource and inputs the second channel state information into the second AI model to obtain the first feature vector.

[0238] Based on the above scheme, the first network element can configure a first AI model and a second AI model for the terminal device. The input of the first AI model is the channel state information of M first cells measured by the terminal device, and the output of the first AI model includes the first beam information for the first access network device. The input of the second AI model is the channel state information between the terminal device and the first access network device, and the output of the second AI model is a feature vector. This allows the terminal device to report the information of Q beams recommended by the terminal device, determined according to the first beam information, the feature vector, and the mapping relationship table, to the first access network device. This facilitates the determination of the communication beams between the terminal device and the first access network device and ensures communication performance.

[0239] In addition, the above scheme can use the channel state information of the first cell as the input of the AI ​​model and directly output the first beam information for the first access network device, thus avoiding two stages of beam training and saving beam training overhead.

[0240] Optionally, in this embodiment, S420 may not be executed, and S430 and S440 may be executed directly after S410. In this case, the first access network device does not determine Table 1 or Table 2 based on the information of N beams reported by the terminal device, but directly issues the mapping relationship table it maintains, so that the terminal device determines the third beam information from the mapping relationship table based on the first beam information and the first feature vector, and then determines the information of Q beams based on the third beam information.

[0241] In one implementation, the first AI model and the second AI model are used to determine the beam used for communication between the terminal device and the first access network device. That is, the first beam information output by the first AI model and the feature vector output by the second AI model can be used to determine the third beam information, which is then used to determine the beam used for communication between the terminal device and the first access network device. The following describes this in detail with reference to S450 and S460.

[0242] Optionally, method 400 further includes: S450, the first access network device sends beam configuration information to the terminal device, and correspondingly, the terminal device receives the beam configuration information.

[0243] The beam configuration information is used to configure the beam of the first signal or the first channel, and this beam configuration information includes the identifier of the fourth reference signal resource. S450 and S330 are basically the same in specific content, except that in S450, the fourth beam can be one of the Q beams reported by the terminal device. That is, the first access network device can configure the beam for sending the first signal or the first channel to the terminal device as one of the Q beams recommended by the terminal device.

[0244] Optionally, if the first configuration information includes a list of third reference signal resource identifiers, the identifier of the fourth reference signal resource can be one of the third reference signal resource identifiers. That is, the fourth reference signal resource can be one of P third reference signal resources. In this case, the terminal device determines the fourth beam based on the identifier of the fourth reference signal resource, which can also be understood as determining the fourth beam based on the list of third reference signal resource identifiers.

[0245] For example, when the i-th reference signal resource among the P identifiers of third reference signal resources is associated with the beam i of the first access network device, the terminal device can determine the fourth beam based on the association between the identifiers of the P third reference signal resources and the beam of the first access network device. The fourth beam is the beam of the first access network device associated with the fourth reference signal resource among the P third reference signal resources.

[0246] Optionally, method 400 further includes: S460, the terminal device uses a fifth beam to receive a first signal or a first channel, wherein the fifth beam is the beam of the terminal device, and in the third beam information, the fourth beam is associated with the fifth beam.

[0247] Specifically, the terminal device can determine that the beam associated with the fourth beam is the fifth beam based on the third beam information, thereby determining to use the fifth beam to receive the first signal or the first channel. Here, the terminal device determining that the beam associated with the fourth beam is the fifth beam based on the third beam information can be understood as the terminal device determining the beam used for communication between the terminal device and the first access network device using the third beam information.

[0248] In this application, the fourth beam and the fifth beam are associated, which can also be understood as the fourth beam and the fifth beam forming a beam pair, or matching the fourth beam and the fifth beam, or having a corresponding or associated relationship. For example, if the third beam information adopts the form of Case 2, then the third beam information includes one or more beam combinations. In one of these beam combinations, the beam of the corresponding first access network device is the fourth beam, and the beam of the corresponding terminal device is the fifth beam.

[0249] Based on the above scheme, the third beam information can be used to determine the beam used for communication between the terminal device and the first access network device, thus ensuring the communication performance between the terminal device and the first access network device.

[0250] For example, similar to method 300, in method 400, the first reference signal resource identifier list and the third reference signal resource identifier list can also be the same list, which can simplify the configuration and improve the efficiency of communication.

[0251] Figure 11 This is a schematic flowchart of a communication method 500 provided in this application. Method 500 can be considered as an implementation of method 300. Figure 11 As shown, the method 500 includes the following steps.

[0252] S501, the high-frequency base station (an example of the first access network device) sends configuration information #1 (an example of the first configuration information) to the UE (an example of the terminal device).

[0253] Configuration information #1 includes the structure and parameters of AI model #1 (an example of the first AI model). The input of AI model #1 is input #1 (an example of the first input). Input #1 includes the CSI of multiple low-frequency neighboring cells (an example of M first channel state information). The output of AI model #1 is the index of beam pairs (an example of first beam information).

[0254] Configuration information #1 also includes a low-frequency neighbor cell identifier list (an example of a first cell identifier list), which includes M low-frequency neighbor cells (an example of M first cells).

[0255] Configuration information #1 also includes list #1 (an example of a list of third reference signal resource identifiers), which includes identifiers of P third reference signal resources.

[0256] S502, the UE determines the index of multiple beam pairs (an example of the first beam information, corresponding to case 3 above), each beam pair including a high-frequency base station beam and a UE beam.

[0257] Specifically, the UE can measure the reference signals of M low-frequency neighboring cells in the low-frequency neighboring cell identifier list to obtain the CSI (an example of M first channel state information) of the M low-frequency neighboring cells.

[0258] Furthermore, the UE inputs the CSIs of M low-frequency neighboring cells into AI model #1 to obtain the indexes of multiple beam pairs.

[0259] S503, the UE sends information about N beams to the high-frequency base station.

[0260] For example, N beams are selected by the UE from multiple beam pairs for use with high-frequency base stations.

[0261] Optionally, the UE can directly report the index of the N beams to the high-frequency base station, or it can report the identifier of the third reference signal resource associated with the N beams to the high-frequency base station.

[0262] S504, the high-frequency base station sends beam configuration information #1 (an example of beam configuration information) to the UE.

[0263] Specifically, beam configuration information #1 indicates signal #1 (an example of the first signal) is associated with identifier #1 of the third reference signal resource (an example of the identifier of the fourth reference signal resource), and the identifier #1 of the third reference signal resource can be used to identify one of the N beams.

[0264] In other words, the identifier #1 of the third reference signal resource can be the information included when the UE reports information of N beams in S503. Therefore, the high-frequency base station can indicate to the UE that the transmission beam of signal #1 is: the beam #1 identified by the identifier #1 of the third reference signal resource (an example of the fourth beam).

[0265] S505, the UE uses beam #2 (an example of the fifth beam) to receive signal #1.

[0266] Specifically, the UE can determine the transmitting beam of signal #1 as beam #1 based on beam configuration information #1. Furthermore, based on the multiple beam pairs determined by the UE in S502, the UE can determine the beam that matches beam #1 as beam #2. In other words, beam #1 and beam #2 are one of the multiple beam pairs determined by the UE. Therefore, the UE can determine to use beam #2 to receive the signal.

[0267] Optionally, S502 to S505 above can be repeated. For example, the repetition period can be the period of reference signals sent by M low-frequency neighboring cells for UE measurement, for example, 20ms.

[0268] Figure 12 This is a schematic flowchart of a communication method 600 provided in this application. Method 600 can be considered as another implementation of method 300. Figure 12 As shown, the method 600 includes the following steps.

[0269] S601, the high-frequency base station (an example of the first access network device) sends configuration information #2 (another example of the first configuration information) to the UE (an example of the terminal device).

[0270] Configuration information #2 includes the structure and parameters of AI model #2 (another example of the first AI model). The inputs of AI model #2 include input #1 (an example of the first input) and input #2 (an example of the second input). Input #1 includes the CSIs of multiple low-frequency neighboring cells (an example of M first channel state information). Input #2 is multiple CSIs of high-frequency base stations (an example of second channel state information). The output of AI model #2 is the index of beam pairs (an example of first beam information).

[0271] Similar to configuration information #1 in S501, configuration information #2 also includes a low-frequency neighbor cell identifier list (an example of the first cell identifier list) and list #1 (an example of the third reference signal resource identifier list).

[0272] In addition, in S601, configuration information #2 also includes list #2 (an example of a list of first reference signal resource identifiers), which may include identifiers of K first reference signal resources. The K first reference signal resources are used by the high-frequency base station to send reference signals to the UE using different beams.

[0273] S602, the UE determines the index of multiple beam pairs (an example of the first beam information, corresponding to case 3 above), each beam pair including a high-frequency base station beam and a UE beam.

[0274] Specifically, the UE can measure the reference signals of M low-frequency neighboring cells in the low-frequency neighboring cell identifier list to obtain the CSI (an example of M first channel state information) of the M low-frequency neighboring cells.

[0275] In addition, the high-frequency base station can use different beams to transmit reference signals on K first reference signal resources. The UE can measure the reference signals on L of the K first reference signal resources to obtain L CSIs (an example of L second channel state information) of the high-frequency base station.

[0276] Furthermore, the UE uses the CSIs of M low-frequency neighboring cells and L high-frequency base stations as input #1 and input #2, respectively. The UE then inputs both input #1 and input #2 into AI model #1 to obtain the indexes of multiple beam pairs.

[0277] S603, the UE sends information about N beams to the high-frequency base station.

[0278] The specific process of S603 can be found in the description in S503.

[0279] S604, the high-frequency base station sends beam configuration information #1 (an example of beam configuration information) to the UE.

[0280] The specific process of S604 can be found in the description of S504.

[0281] S605, the UE uses beam #2 (an example of the fifth beam) to receive signal #1.

[0282] The specific process of S605 can be found in the description of S505.

[0283] Optionally, S602 to S605 above can be executed repeatedly. For example, the repetition period can be the period of the reference signal sent by the high-frequency base station for UE measurement, for example, the period is 100ms.

[0284] Figure 13 This is a schematic flowchart of a communication method 700 provided in this application. Method 700 can be considered as an implementation of method 400. Figure 13 As shown, the method 700 includes the following steps.

[0285] S701, the high-frequency base station (an example of a first access network device) sends configuration information #1 (an example of first configuration information) and configuration information #3 (an example of second configuration information) to the UE (an example of a terminal device).

[0286] The specific content of configuration information #1 is the same as that of S501.

[0287] Configuration information #3 includes the structure and parameters of AI model #3 (an example of the second AI model). The input of AI model #3 is the CSI of the high-frequency base station (an example of the second channel state information), and the output of AI model #3 is a feature vector.

[0288] In addition, configuration information #3 also includes list #2 (an example of a list of first reference signal resource identifiers), which may include identifiers of K first reference signal resources. These K first reference signal resources are used by the high-frequency base station to send reference signals to the UE using different beams.

[0289] S702, the UE determines the index of multiple beam pairs (an example of the first beam information, corresponding to case 3 above), each beam pair including a high-frequency base station beam and a UE beam.

[0290] The specific process of S702 is the same as that of S502.

[0291] S703, the UE sends information about N beams to the high-frequency base station.

[0292] The specific process of S703 is the same as that of S503.

[0293] S704, the high-frequency base station sends multiple mapping relationships to the UE.

[0294] Among them, multiple mapping relationships are determined by the high-frequency base station based on the information of N beams reported by the UE.

[0295] Each of the multiple mapping relationships is: the relationship between the identifier of a first reference signal resource and a feature vector mapped to a second beam information.

[0296] S705, the UE determines the index of multiple beam pairs (an example of third beam information), each beam pair including a high-frequency base station beam and a UE beam.

[0297] Specifically, the high-frequency base station can use different beams to transmit reference signals on K first reference signal resources. The UE can measure the reference signals on L of the K first reference signal resources to obtain L CSIs (an example of L second channel state information) of the high-frequency base station.

[0298] Furthermore, the UE inputs the CSI of the high-frequency base station into the AI ​​model #3 to obtain the first feature vector (an example of the first feature vector).

[0299] Furthermore, the UE uses the first feature vector plus the identifier of the first reference signal resource associated with the CSI of the high-frequency base station to retrieve the index of multiple beam pairs in multiple mapping relationships. The index of these multiple beam pairs is part of the second beam information.

[0300] S706, the UE sends information for Q beams to the high-frequency base station.

[0301] Specifically, the UE can determine the information of Q beams based on the indexes of multiple retrieved beam pairs. For example, the Q beams are all the high-frequency base station beams included in the multiple beam pairs.

[0302] Optionally, the UE can directly report the indexes of the Q beams to the high-frequency base station, or it can report the identifiers of the third reference signal resources associated with the Q beams to the high-frequency base station.

[0303] S707, the high-frequency base station sends beam configuration information #2 (an example of beam configuration information) to the UE.

[0304] Specifically, beam configuration information #2 indicates signal #1 (an example of the first signal) and is associated with identifier #1 of the third reference signal resource (an example of the identifier of the fourth reference signal resource). Identifier #1 of the third reference signal resource can be used to identify one of the Q beams. That is, identifier #1 of the third reference signal resource can be the information included when the UE reports information about the Q beams in S706. Therefore, the high-frequency base station can, based on the UE's report, send the beam of indication signal #1 to the UE as: the beam #1 (an example of the fourth beam) identified by identifier #1 of the third reference signal resource.

[0305] S708, the UE uses beam #2 (an example of the fifth beam) to receive signal #1.

[0306] Specifically, the UE can determine the transmitting beam of signal #1 as beam #1 based on beam configuration information #2. Furthermore, based on the multiple beam pairs determined by the UE in S705, the UE can determine the beam that matches beam #1 as beam #2. In other words, beam #1 and beam #2 are one of the multiple beam pairs determined by the UE in S705. Therefore, the UE can determine to use beam #2 to receive the signal.

[0307] Optionally, S702 to S708 can be repeated. For example, the repetition period of S702 to S703 can be the period of the reference signal transmitted by M low-frequency neighboring cells for UE measurement, for example, 20ms. The repetition period of S705 to S708 can be the period of the reference signal transmitted by the high-frequency base station for UE measurement, for example, 100ms.

[0308] It should be understood that the sequence number of each process in this application does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0309] The above, combined with Figures 1 to 13 The communication method provided in the embodiments of this application is described in detail. The above-described communication method is mainly introduced from the perspective of interaction between terminal devices and network devices. It is understood that, in order to achieve the above functions, the terminal devices and network devices include hardware structures and / or software modules corresponding to the execution of each function.

[0310] It is understood that, in order to implement the functions in the above embodiments, the terminal device and network device include hardware structures and / or software modules corresponding to perform each function. Those skilled in the art should readily recognize that, based on the units and method steps of the various examples described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0311] Figure 14 and Figure 15 This is a schematic block diagram of a communication device provided in the embodiments of this application. These communication devices can be used to implement the functions of the first terminal device or network device in the above method embodiments, and therefore can also achieve the beneficial effects of the above method embodiments. In the embodiments of this application, the communication device can be as follows: Figure 1 The UE shown can also be as follows: Figure 1 The RAN shown can also be Figure 1 The first network element shown can also be a module (such as a chip) applied to the UE, RAN, or the first network element.

[0312] like Figure 14 As shown, the communication device 2000 includes a transceiver unit 2020. The communication device 2000 is used to implement the above-mentioned... Figure 3 or Figure 10 The method embodiment shown illustrates the functions of the first network element, terminal device, or first access network device. Optionally, the communication device 200 further includes a processing unit 2010.

[0313] When the communication device 2000 is used to achieve Figure 3 or Figure 10 In the method embodiment shown, the terminal device (or UE) functions as follows: the transceiver unit 2020 is used to receive first configuration information from a first network element. The first configuration information includes the identifiers of M first cells and information of a first AI model. The first AI model is used to determine the beams used for communication between the terminal device and the first access network device. The input of the first AI model includes a first input, which is the first channel state information of the M first cells measured by the terminal device. The output of the first AI model includes first beam information, which is determined by the terminal device based on the first AI model and the first channel state information, where M is a positive integer. The transceiver unit 2020 is also used to send information of N beams to the first access network device. The N beams are beams recommended by the terminal device, and the information of the N beams is determined based on the first beam information, where N is a positive integer.

[0314] When the communication device 2000 is used to achieve Figure 3 or Figure 10 In the method embodiment shown, the function of the first access network device (or high-frequency base station) is as follows: the transceiver unit 2020 is used to send first configuration information to the terminal device. The first configuration information includes the identifiers of M first cells and information of a first AI model. The first AI model is used to determine the beam used for communication between the terminal device and the first access network device. The input of the first AI model includes a first input, which is the first channel state information of the M first cells measured by the terminal device. The output of the first AI model includes first beam information, which is determined by the terminal device based on the first AI model and the first channel state information. M is a positive integer. The transceiver unit 2020 is also used to receive information of N beams from the terminal device. The N beams are beams recommended by the terminal device. The information of the N beams is determined based on the first beam information. N is a positive integer.

[0315] When the communication device 2000 is used to achieve Figure 3 or Figure 10In the method embodiment shown, the function of the first network element is as follows: the transceiver unit 2020 is used to send first configuration information to the terminal device. The first configuration information includes the identifiers of M first cells and the information of the first AI model. The first AI model is used to determine the beam used for communication between the terminal device and the first access network device. The input of the first AI model includes a first input, which is the first channel state information of the M first cells measured by the terminal device. The output of the first AI model includes first beam information, which is determined by the terminal device based on the first AI model and the first channel state information. M is a positive integer.

[0316] For a more detailed description of the aforementioned processing unit 2010 and transceiver unit 2020, please refer to [link / reference needed]. Figure 3 or Figure 10 The relevant descriptions in the method embodiments shown.

[0317] like Figure 15 As shown, the communication device 3000 includes a processor 3010 and an interface circuit 3020. The processor 3010 and the interface circuit 3020 are coupled to each other. It is understood that the interface circuit 3020 can be a transceiver or an input / output interface. Optionally, the communication device 3000 may also include a memory 3030 for storing instructions executed by the processor 3010, or storing input data required by the processor 3010 to execute instructions, or storing data generated after the processor 3010 executes instructions. Sometimes, the interface circuit 3020 can also be understood as part of the processor 3010, in which case the communication device 3000 includes the processor 3010.

[0318] When the communication device 3000 is used to achieve Figure 3 or Figure 10 In the method shown, the processor 3010 is used to implement the functions of the processing unit 2010, and the interface circuit 3020 is used to implement the functions of the transceiver unit 2020.

[0319] When the aforementioned communication device is a chip applied to a terminal, the terminal chip implements the functions of the terminal in the above method embodiments. The terminal chip receiving information can be understood as the information being first received by other modules in the terminal (such as an RF module or antenna), and then sent to the terminal chip by these modules. The terminal chip sending information can be understood as the information being first sent to other modules in the terminal (such as an RF module or antenna), and then sent by these modules.

[0320] When the aforementioned communication device is a chip used in a base station (such as a high-frequency base station), the base station chip implements the functions of the base station in the above method embodiments. The base station chip receiving information can be understood as the information being first received by other modules in the base station (such as a radio frequency module or antenna), and then sent to the base station chip by these modules. The base station chip sending information can be understood as the information being sent down to other modules in the base station (such as a radio frequency module or antenna), and then sent by these modules.

[0321] When the aforementioned communication device is a chip applied to a first network element, the first network element chip implements the functions of the first network element in the above method embodiments. The first network element chip receiving information can be understood as the information being first received by other modules (such as radio frequency modules or antennas) in the first network element, and then sent to the first network element chip by these modules. The first network element chip sending information can be understood as the information being sent down to other modules (such as radio frequency modules or antennas) in the first network element, and then sent by these modules.

[0322] In this application, entity A sends information to entity B, either directly or indirectly through other entities. Similarly, entity B receives information from entity A, either directly or indirectly through other entities. Entities A and B can be RAN nodes or terminals, or modules within RAN nodes or terminals. Information transmission and reception can be between RAN nodes and terminals, such as between a base station and a terminal; between two RAN nodes, such as between a CU and a DU; or between different modules within a single device, such as between a terminal chip and other modules of the terminal, or between a base station chip and other modules of the base station.

[0323] It is understood that the processor in the embodiments of this application may 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, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0324] The method steps in the embodiments of this application can be implemented in hardware or in software instructions executable by a processor. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. The storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a base station or terminal. The processor and storage medium can also exist as discrete components in a base station or terminal.

[0325] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0326] In the above embodiments, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0327] In this document, "at least one" means one or more. "More than one" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. 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. In the textual description of this application, the character " / " generally indicates that the related objects before and after are in an "or" relationship; in the formulas of this application, the character " / " indicates that the related objects before and after are in a "division" relationship. "Including at least one of A, B, and C" can mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B, and C.

[0328] In this application, "for indication" can include both direct and indirect indication. When describing indication information as indicating A, it can include whether the indication information directly or indirectly indicates A, but does not necessarily mean that the indication information includes A. The information indicated by the indication information is called the information to be indicated. In specific implementation, there are many ways to indicate the information to be indicated. The information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately. Moreover, the sending period and / or sending time of these sub-information can be the same or different. This application does not limit the specific sending method. The sending period and / or sending time of these sub-information can be predefined, for example, predefined according to the protocol, or configured by the transmitting device by sending configuration information to the receiving device. The configuration information can be, but is not limited to, one or a combination of at least two of RRC signaling, MAC layer signaling, and physical layer signaling. MAC layer signaling includes, for example, MAC control elements (CE), and physical layer signaling includes, for example, downlink control information (DCI).

[0329] It should be understood that in the various embodiments of this application, the terms "first," "second," and various numerical designations are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the sequence numbers of the above processes does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

[0330] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0331] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0332] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0333] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0334] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0335] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0336] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A communication method, characterized in that, Applied to terminal devices, including: The terminal device receives first configuration information from a first network element. The first configuration information includes the identifiers of M first cells and information of a first artificial intelligence (AI) model. The first AI model is used to determine the beam used for communication between the terminal device and the first access network device. The input of the first AI model includes a first input, which is the first channel state information of the M first cells measured by the terminal device. The output of the first AI model includes the first beam information, which is determined by the terminal device based on the first AI model and the first channel state information. M is a positive integer. The information of N beams is sent to the first access network device. The N beams are the beams recommended by the terminal device. The information of the N beams is determined based on the information of the first beam, and N is a positive integer.

2. The method according to claim 1, characterized in that, The first cell operates in a first frequency range, and the first access network device operates in a second frequency range. The highest frequency in the first frequency range is lower than the lowest frequency in the second frequency range.

3. The method according to claim 1 or 2, characterized in that, The first beam information includes at least one of the following: One or more beams of the first access network device; One or more beam combinations, each of the one or more beam combinations including a beam from the first access network device and a beam from the terminal device; One or more beam pairs, each of the one or more beam pairs being associated with a beam from the first access network device and a beam from the terminal device; The first signal strength tensor of multiple beams of the first access network device, wherein each position in the first signal strength tensor is associated with a beam of the first access network device; A second signal strength tensor for multiple beam pairs, wherein each position in the second signal strength tensor is associated with a beam of the first access network device and a beam of the terminal device.

4. The method according to claim 3, characterized in that, The first configuration information includes the association between each beam of the terminal device and the angle information.

5. The method according to any one of claims 1 to 4, characterized in that, The first configuration information includes a first cell identifier list, which includes the identifiers of the M first cells. The positions of the M first channel state information items in the first input are determined based on the positions of the identifiers of the first cells associated with the first channel state information in the first cell identifier list.

6. The method according to any one of claims 1 to 5, characterized in that, The input to the first AI model also includes a second input, which is the second channel state information between the terminal device and the first access network device.

7. The method according to claim 6, characterized in that, The first configuration information includes a first reference signal resource identifier list, which includes K identifiers of first reference signal resources. These K first reference signal resources are used by the first access network device to transmit reference signals. The second input includes L pieces of second channel state information. The L second channel state information are determined by the terminal device based on the measurement results on L of the K first reference signal resources, where L is less than or equal to K, and both L and K are positive integers.

8. The method according to claim 6 or 7, characterized in that, The position of the second channel state information in the second input is determined based on the position of the identifier of the first reference signal resource associated with the second channel state information in the first reference signal resource identifier list.

9. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Receive multiple mapping relationships from the first access network device. The multiple mapping relationships include multiple identifiers of first reference signal resources, multiple feature vectors, and multiple second beam information. Each of the multiple mapping relationships is: a relationship between an identifier of a first reference signal resource and a feature vector mapped to a second beam information, or a relationship between a group of identifiers of a reference signal resource and a group of feature vectors mapped to a second beam information. The information of Q beams is sent to the first access network device. The Q beams are beams recommended by the terminal device. The information of the Q beams is determined according to the multiple mapping relationships, and Q is a positive integer.

10. The method according to claim 9, characterized in that, Each of the multiple mapping relationships is: the relationship between the identifier of a first reference signal resource and a feature vector mapped to a second beam information. The method further includes: A first feature vector is determined based on the measurement results on a second reference signal resource, wherein the second reference signal resource is one of the plurality of first reference signal resources; The third beam information is determined based on the identifier of the second reference signal resource, the first feature vector, and the multiple mapping relationships, wherein the third beam information is one of the multiple second beam information; The information of the Q beams is determined based on the third beam information.

11. The method according to claim 10, characterized in that, The method further includes: The system receives second configuration information from the first network element. This second configuration information includes information about a second AI model. The input to the second AI model is second channel state information between the terminal device and the first access network device. The output of the second AI model includes a feature vector. Determining the first feature vector based on the measurement results on the second reference signal resource includes: The second channel state information is determined based on the measurement results on the second reference signal resource; The first feature vector is obtained based on the second channel state information and the second AI model.

12. The method according to any one of claims 1 to 11, characterized in that, The first configuration information includes a list of third reference signal resource identifiers, which includes P identifiers of third reference signal resources. Each of the P identifiers of the third reference signal resources is associated with the beam of the first access network device, where P is a positive integer.

13. The method according to claim 12, characterized in that, The identifiers of the P third reference signal resources are associated with the beam of the first access network device, including: The i-th reference signal resource among the P third reference signal resources is associated with the beam i of the first access network device, where i is an integer greater than or equal to 0 and less than or equal to P.

14. The method according to claim 13, characterized in that, The method further includes: Receive beam configuration information from the first access network device, the beam configuration information being used to configure the beam of the first signal or the first channel, the beam configuration information including the identifier of the fourth reference signal resource, the fourth reference signal resource being one of the P third reference signal resources; The fourth beam is determined based on the association between the identifiers of the P third reference signal resources and the beams of the first access network device. The fourth beam is the beam of the first access network device associated with the fourth reference signal resource. The first signal or the first channel is received using the fifth beam, wherein the fifth beam is the beam of the terminal device, and the fourth beam is associated with the fifth beam in the first beam information.

15. A method of communication, characterized in that, Applied to first access network equipment, including: Send first configuration information to the terminal device. The first configuration information includes the identifiers of M first cells and information of a first AI model. The first AI model is used to determine the beam used for communication between the terminal device and the first access network device. The input of the first AI model includes a first input, which is the first channel state information of the M first cells measured by the terminal device. The output of the first AI model includes the first beam information, which is determined by the terminal device based on the first AI model and the first channel state information. M is a positive integer. The terminal device receives information from N beams, which are recommended beams by the terminal device. The information of the N beams is determined based on the first beam information, where N is a positive integer.

16. The method according to claim 15, characterized in that, The input to the first AI model also includes a second input, which is the second channel state information between the terminal device and the first access network device. The information of the N beams is determined based on the first beam information, including: The information of the N beams is determined based on the first AI model, the first channel state information, and the second channel state information.

17. The method according to claim 15 or 16, characterized in that, The method further includes: Multiple mapping relationships are sent to the terminal device. The multiple mapping relationships include multiple identifiers of first reference signal resources, multiple feature vectors, and multiple second beam information. Each of the multiple mapping relationships is: a relationship between an identifier of a first reference signal resource and a feature vector and a second beam information, or a relationship between a group of identifiers of a reference signal resource and a group of feature vectors and a second beam information. The terminal device receives information from Q beams, which are beams recommended by the terminal device, and the information of the Q beams is determined according to the multiple mapping relationships.

18. The method according to claim 17, characterized in that, The method further includes: Send second configuration information to the terminal device. The second configuration information includes information about a second AI model. The input of the second AI model is a second channel state information between the terminal device and the first access network device. The output of the second AI model includes a feature vector. The second AI model is used to determine the information of the Q beams.

19. The method according to any one of claims 15 to 18, characterized in that, The first configuration information includes a list of third reference signal resource identifiers, which includes P identifiers of third reference signal resources. Each of the P identifiers of the third reference signal resources is associated with the beam of the first access network device, where P is a positive integer.

20. The method according to claim 19, characterized in that, The identifiers of the P third reference signal resources are associated with the beam of the first access network device, including: The i-th reference signal resource among the P third reference signal resources is associated with the beam i of the first access network device, where i is an integer greater than or equal to 0 and less than or equal to P.

21. The method according to claim 20, characterized in that, The method further includes: The beam configuration information is sent to the terminal device. The beam configuration information is used to configure the beam of the first signal or the first channel. The beam configuration information includes the identifier of the fourth reference signal resource, which is one of the P third reference signal resources. The fourth beam is determined based on the association between the identifiers of the P third reference signal resources and the beams of the first access network device. The fourth beam is the beam of the first access network device associated with the fourth reference signal resource. The first signal or the first channel is transmitted using the fourth beam.

22. A method of communication, characterized in that, Applied to the first network element, including: Send first configuration information to the terminal device. The first configuration information includes the identifiers of M first cells and information of a first AI model. The first AI model is used to determine the beam used for communication between the terminal device and the first access network device. The input of the first AI model includes a first input, which is the first channel state information of the M first cells measured by the terminal device. The output of the first AI model includes the first beam information, which is determined by the terminal device based on the first AI model and the first channel state information. M is a positive integer.

23. A communication device, characterized in that, It includes modules or units for performing the method as described in any one of claims 1 to 14, or modules or units for performing the method as described in any one of claims 15 to 21, or modules or units for performing the method as described in claim 22.

24. A communication device, characterized in that, The device includes one or more processors configured to execute a computer program or instructions stored in a memory, causing the device to perform the method of any one of claims 1 to 14, or to perform the method of any one of claims 15 to 21, or to perform the method of claim 22.

25. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions that, when executed by a communication device, implement the method as described in any one of claims 1 to 14, or the method as described in any one of claims 15 to 21, or the method as described in claim 22.

26. A computer program product, characterized in that, Includes a computer program that, when run, implements the method as described in any one of claims 1 to 14, or implements the method as described in any one of claims 15 to 21, or implements the method as described in claim 22.

Images