Communication method and related product

Abstract

The embodiment of the invention discloses a communication method and a related product. The method comprises the following steps: receiving resource configuration information and first information; performing measurement based on resources configured by the resource configuration information to obtain a first measurement result; based on the first information, it is determined that the first artificial intelligence model is adopted for prediction based on the first measurement result, the first information comprises first indication information, and the first indication information is used for indicating at least one of the following items: input information of an AI model which needs to be adopted for prediction based on the first measurement result; and predicting output information of the AI model required to be adopted based on the first measurement result. In the embodiment of the invention, based on first information, a first AI model is determined to be used for prediction based on a first measurement result; it can be ensured that at least one of the input information and the output information of the AI model is consistent with at least one of the input information and the output information of the AI model which needs to be adopted for prediction based on the first measurement result.

Description

Technical Field

[0001] This application relates to the field of communications, and in particular, to communication methods and related products. Background Art

[0002] Currently, a user equipment (UE) can use artificial intelligence (AI) technology to predict the quality of unmeasured beams or the beam indexes with better beam quality through a small number of beam measurement results. The generalization of existing AI models is relatively limited. The relatively limited generalization of an AI model means that the AI model can achieve better prediction performance in a specific scenario. However, when the inference and training scenarios of the AI model are different, the prediction accuracy of the AI will be greatly affected. Simply put, when there are significant differences between the input or output of the AI model during training and inference, the prediction accuracy of the AI will be greatly affected. Summary of the Invention

[0003] Embodiments of this application disclose a communication method and related products, which can ensure the consistency of input data when an AI model is trained and inferred.

[0004] In a first aspect, an embodiment of this application provides a communication method, which includes: receiving resource configuration information and first information; performing measurements based on the resources configured by the resource configuration information to obtain a first measurement result; determining, based on the first information, to use a first artificial intelligence (AI) model to make a prediction based on the first measurement result, where the first information includes first indication information, and the first indication information is used to indicate at least one of the following: input information of the AI model required for making a prediction based on the first measurement result; output information of the AI model required for making a prediction based on the first measurement result.

[0005] In an embodiment of this application, based on the first information, it is determined to use a first AI model to make a prediction based on the first measurement result; it can ensure that at least one of the input information and output information of the used AI model is consistent with at least one of the input information and output information of the AI model required for making a prediction based on the first measurement result.

[0006] In a possible implementation, the first indication information is used to indicate the output information of the AI model required for making a prediction based on the first measurement result; the output information of the AI model includes: a resource set corresponding to the output of the AI model.

[0007] In this implementation manner, based on the first indication information, it is possible to know the resources corresponding to the output of the AI model required for prediction based on the first measurement result, and then determine which AI model to use for prediction based on the first measurement result.

[0008] In a possible implementation manner, the first indication information is further used to indicate the input information of the AI model required for prediction based on the first measurement result. The input information of the AI model includes any one of the following: the number of resources in the resource set corresponding to the input of the AI model; the resource index set corresponding to the resource set corresponding to the input of the AI model, where each resource index in the resource index set corresponds to a resource in the resource set corresponding to the output of the AI model; the pattern corresponding to the input of the AI model, the pattern includes a set of index sets; the sampling rate of the number of resources in the resource set corresponding to the input of the AI model relative to the number of resources in the resource set corresponding to the output of the AI model.

[0009] In this implementation manner, based on the first indication information, it is possible to know the resources corresponding to the input of the AI model, so as to determine which AI model to use for prediction based on the first measurement result.

[0010] In a possible implementation manner, the first indication information is used to indicate the input information of the AI model required for prediction based on the first measurement result; the input information of the AI model includes: the resource set corresponding to the input of the AI model.

[0011] In this implementation manner, based on the first indication information, it is possible to know the resources corresponding to the output of the AI model required for prediction based on the first measurement result, and then determine which AI model to use for prediction based on the first measurement result.

[0012] In a possible implementation manner, the first information further includes second indication information, and the second indication information is used to indicate at least one of the following: the association relationship between the index of the resource in the resource set corresponding to the input of the AI model and the input index of the AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the AI model and the output index of the AI model; the association relationship between the input index and the output index of the AI model.

[0013] In this implementation manner, based on the second indication information, at least one of the following can be obtained: the association relationship between the index of the resource in the resource set corresponding to the input of the AI model and the input index of the AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the AI model and the output index of the AI model; the association relationship between the input index and the output index of the AI model, and then determine which AI model to use for prediction based on the first measurement result.

[0014] In a possible implementation manner, the first measurement result includes one or more resource measurement results; the first information further includes third indication information, and the third indication information is used to indicate at least one of the following: the beam shape corresponding to the resource in the resource set corresponding to the input of the AI model, the beam shape corresponding to the resource in the resource set corresponding to the output of the AI model.

[0015] In this implementation manner, based on the third indication information, at least one of the beam shape corresponding to the resource in the resource set corresponding to the input of the AI model and the beam shape corresponding to the resource in the resource set corresponding to the output of the AI model can be obtained, and then determine which AI model to use for prediction based on the first measurement result.

[0016] In a possible implementation manner, the third indication information includes at least one of the following: a plurality of first indexes, a plurality of second indexes; the first index is used to indicate a combination of a beam direction and a beam width, the plurality of first indexes correspond to the resources in the resource set corresponding to the input of the AI model, the second index is used to indicate a combination of a beam direction and a beam width, and the plurality of second indexes correspond to the resources in the resource set corresponding to the output of the AI model.

[0017] In this implementation manner, a plurality of first indexes correspond to the resources in the resource set corresponding to the input of the AI model, and a plurality of second indexes correspond to the resources in the resource set corresponding to the output of the AI model; the beam direction and beam width of the resources in the resource set corresponding to the AI model can be accurately indicated.

[0018] In a possible implementation manner, the third indication information is used to indicate an identifier, and the identifier is used to indicate the network device from which the first information comes, and the identifier includes at least one of the following: a plurality of combinations of beam directions and beam widths corresponding to the resources in the resource set corresponding to the input of the AI model, a plurality of combinations of beam directions and beam widths corresponding to the resources in the resource set corresponding to the output of the AI model.

[0019] In this implementation, the identifier is used to indicate the network device from which the first information comes, so as to determine to perform a prediction based on the AI model from the network device based on the first measurement result.

[0020] In a possible implementation, the third indication information is used to indicate the direction and width of the reference beam, and the angular offsets of multiple beams relative to the reference beam. A part of the multiple beams corresponds to the resources in the resource set corresponding to the input of the AI model, and another part of the multiple beams corresponds to the resources in the resource set corresponding to the output of the AI model.

[0021] In this implementation, the third indication information is used to indicate the direction and width of the reference beam, and the angular offsets of multiple beams relative to the reference beam. Compared with indicating the beam direction and beam width of the resources in the resource set corresponding to the AI model, the overhead can be saved.

[0022] In a possible implementation, the method further includes: sending second information, where the second information includes fourth indication information, and the fourth indication information is used to indicate at least one of the following: the input size of the first AI model, the output size of the first AI model.

[0023] In this implementation, the second information is sent so that the network device can indicate which AI model to use for prediction based on the second information.

[0024] In a possible implementation, the second information further includes fifth indication information, and the fifth indication information is used to indicate any one of the following: the input pattern of the first AI model; the association relationship between the input index and the output index of the first AI model; the beam shape corresponding to the first AI model; the association relationship between the index of the resources in the resource set corresponding to the input of the first AI model and the input index of the first AI model; the association relationship between the index of the resources in the resource set corresponding to the output of the first AI model and the output index of the first AI model.

[0025] In this implementation, the second information further includes fifth indication information so that the network device can indicate which AI model to use for prediction based on the second information.

[0026] In a possible implementation, the method further includes: receiving third information, where the third information includes sixth indication information, and the sixth indication information is used to indicate the input information and output information of the second AI model that needs to be trained based on the communication device, and the first AI model is trained based on the second AI model.

[0027] In a possible implementation, the input information of the second AI model includes: a resource set corresponding to the input of the second AI model; the output information of the second AI model includes: a resource set corresponding to the output of the second AI model.

[0028] In a possible implementation, the output information of the second AI model includes: a resource set corresponding to the output of the second AI model; the input information of the second AI model includes any one of the following: the number of resources in the resource set corresponding to the input of the second AI model, the resource index set corresponding to the resource set corresponding to the input of the second AI model, each resource index in the resource index set corresponding to a resource in the resource set corresponding to the output of the second AI model, the pattern corresponding to the input of the second AI model, the pattern including a set of index sets, and the sampling rate of the number of resources in the resource set corresponding to the input of the second AI model relative to the number of resources in the resource set corresponding to the output of the second AI model.

[0029] In a possible implementation, the third information further includes seventh indication information, and the seventh indication information is used to indicate at least one of the following: the association relationship between the index of the resource in the resource set corresponding to the input of the second AI model and the input index of the second AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the second AI model and the output index of the second AI model; the association relationship between the input index and the output index of the second AI model.

[0030] In a possible implementation, the third information further includes eighth indication information, and the eighth indication information is used to indicate at least one of the following: the beam shape corresponding to the resource in the resource set corresponding to the input of the second AI model, the beam shape corresponding to the resource in the resource set corresponding to the output of the second AI model.

[0031] In a possible implementation, the eighth indication information includes at least one of the following: a plurality of first indexes, a plurality of second indexes; the first index is used to indicate a combination of a beam direction and a beam width, the plurality of first indexes correspond to the resources in the resource set corresponding to the input of the second AI model, the second index is used to indicate a combination of a beam direction and a beam width, and the plurality of second indexes correspond to the resources in the resource set corresponding to the output of the second AI model.

[0032] In a possible implementation, the eighth indication information is used to indicate an identifier, and the identifier is used to indicate the network device from which the third information comes. The identifier includes at least one of the following: combinations of a plurality of beam directions and beam widths corresponding to resources in the resource set corresponding to the input of the second AI model; combinations of a plurality of beam directions and beam widths corresponding to resources in the resource set corresponding to the output of the second AI model.

[0033] In a possible implementation, the eighth indication information is used to indicate the direction and width of a reference beam, and the angular offsets of a plurality of beams relative to the reference beam. A part of the plurality of beams corresponds to resources in the resource set corresponding to the input of the second AI model, and another part of the plurality of beams corresponds to resources in the resource set corresponding to the output of the second AI model.

[0034] In a second aspect, an embodiment of the present application provides another communication method, and the method includes: sending resource configuration information and first information, where the first information includes first indication information, and the first indication information is used to indicate at least one of the following: input information of an AI model required for prediction based on a first measurement result; output information of an AI model required for prediction based on the first measurement result, where the first measurement result is obtained by measuring resources configured based on the resource configuration information; sending a downlink measurement signal, where the downlink measurement signal includes a signal that the communication device needs to measure based on the resources configured based on the resource configuration information.

[0035] In an embodiment of the present application, resource configuration information and first information are sent, and the first indication information is used to indicate at least one of the following: input information of an AI model required for prediction based on a first measurement result; output information of an AI model required for prediction based on the first measurement result; so that at least one of the input information and output information of the AI model used by the communication device for prediction based on the first measurement result is consistent with at least one of the input information and output information of the AI model required for prediction based on the first measurement result.

[0036] In a possible implementation, the first indication information is used to indicate the output information of the AI model required for prediction based on the first measurement result; the output information of the AI model includes: a resource set corresponding to the output of the AI model.

[0037] In this implementation, the first indication information is used to indicate the resources corresponding to the output of the AI model required for prediction based on the first measurement result, so that the communication device can determine which AI model to use for prediction based on the first measurement result.

[0038] In a possible implementation, the first indication information is further used to indicate the input information of the AI model required for prediction based on the first measurement result. The input information of the AI model includes any one of the following: the number of resources in the resource set corresponding to the input of the AI model, the resource index set corresponding to the resource set corresponding to the input of the AI model, each resource index in the resource index set corresponding to one resource in the resource set corresponding to the output of the AI model, the pattern corresponding to the input of the AI model, the pattern including a set of index sets, and the sampling rate of the number of resources in the resource set corresponding to the input of the AI model relative to the number of resources in the resource set corresponding to the output of the AI model.

[0039] In a possible implementation, the first indication information is used to indicate the input information of the AI model required for prediction based on the first measurement result; the input information of the AI model includes: the resource set corresponding to the input of the AI model.

[0040] In a possible implementation, the first information further includes second indication information, and the second indication information is used to indicate at least one of the following: the association relationship between the index of the resource in the resource set corresponding to the input of the AI model and the input index of the AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the AI model and the output index of the AI model; the association relationship between the input index and the output index of the AI model.

[0041] In a possible implementation, the first measurement result includes one or more resource measurement results; the first information further includes third indication information, and the third indication information is used to indicate at least one of the following: the beam shape corresponding to the resource in the resource set corresponding to the input of the AI model, the beam shape corresponding to the resource in the resource set corresponding to the output of the AI model.

[0042] In a possible implementation, the third indication information includes at least one of the following: a plurality of first indexes, a plurality of second indexes; the first index is used to indicate a combination of a beam direction and a beam width, the plurality of first indexes corresponding to the resources in the resource set corresponding to the input of the AI model, and the second index is used to indicate a combination of a beam direction and a beam width, the plurality of second indexes corresponding to the resources in the resource set corresponding to the output of the AI model.

[0043] In a possible implementation, the method further includes: receiving second information, where the second information includes fourth indication information, and the fourth indication information is used to indicate at least one of the following: the input size of the first AI model, the output size of the first AI model.

[0044] In a possible implementation, the second information further includes fifth indication information, and the fifth indication information is used to indicate any one of the following: the input pattern of the AI model; the association relationship between the input index and the output index of the AI model; the beam pattern corresponding to the AI model; the association relationship between the index of the resource in the resource set corresponding to the input of the AI model and the input index of the AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the AI model and the output index of the AI model.

[0045] In a possible implementation, the method further includes: sending third information, where the third information includes sixth indication information, and the sixth indication information is used to indicate the input information and output information of a second AI model that needs to be trained based on the communication device, and the first AI model is trained based on the second AI model.

[0046] In a possible implementation, the input information of the second AI model includes: the resource set corresponding to the input of the second AI model; the output information of the second AI model includes: the resource set corresponding to the output of the second AI model.

[0047] In a possible implementation, the output information of the second AI model includes: the resource set corresponding to the output of the second AI model; the input information of the second AI model includes any one of the following: the number of resources in the resource set corresponding to the input of the second AI model, the resource index set corresponding to the resource set corresponding to the input of the second AI model, each resource index in the resource index set corresponds to a resource in the resource set corresponding to the output of the second AI model, the pattern corresponding to the input of the second AI model, the pattern includes a set of index sets, the sampling rate of the number of resources in the resource set corresponding to the input of the second AI model relative to the number of resources in the resource set corresponding to the output of the second AI model.

[0048] In a possible implementation, the third information further includes seventh indication information, and the seventh indication information is used to indicate at least one of the following: the association relationship between the index of the resource in the resource set corresponding to the input of the second AI model and the input index of the second AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the second AI model and the output index of the second AI model; the association relationship between the input index and the output index of the second AI model.

[0049] In a possible implementation, the third information further includes eighth indication information, and the eighth indication information is used to indicate at least one of the following: the beam shape corresponding to the resource in the resource set corresponding to the input of the second AI model; the beam shape corresponding to the resource in the resource set corresponding to the output of the second AI model.

[0050] In a possible implementation, the eighth indication information includes at least one of the following: a plurality of first indices, a plurality of second indices; the first index is used to indicate a combination of a beam direction and a beam width, the plurality of first indices correspond to the resources in the resource set corresponding to the input of the second AI model, the second index is used to indicate a combination of a beam direction and a beam width, and the plurality of second indices correspond to the resources in the resource set corresponding to the output of the second AI model.

[0051] In a possible implementation, the eighth indication information is used to indicate an identifier, and the identifier is used to indicate the network device from which the third information comes, and the identifier includes at least one of the following: a combination of a plurality of beam directions and beam widths corresponding to the resources in the resource set corresponding to the input of the second AI model; a combination of a plurality of beam directions and beam widths corresponding to the resources in the resource set corresponding to the output of the second AI model.

[0052] In a possible implementation, the eighth indication information is used to indicate the direction and width of a reference beam, and the angular offsets of a plurality of beams relative to the reference beam, and a part of the plurality of beams corresponds to the resources in the resource set corresponding to the input of the second AI model, and another part of the plurality of beams corresponds to the resources in the resource set corresponding to the output of the second AI model.

[0053] In a third aspect, an embodiment of the present application provides a communication device, which has the function of implementing the actions in the method embodiment of the first aspect above. The communication device may be a terminal device, a component of the terminal device (such as a processor, a chip, or a chip system, etc.), or a logic module or software that can implement all or part of the functions of the terminal device. The functions of the communication device can be implemented by hardware or by hardware executing corresponding software, and the hardware or software includes one or more modules or units corresponding to the above functions. In a possible implementation manner, the communication device includes a transceiver module and a processing module, where: the transceiver module is configured to receive resource configuration information and first information; the processing module is configured to perform measurements on the resources configured based on the resource configuration information to obtain a first measurement result; and based on the first information, determine to use a first AI model to make a prediction based on the first measurement result, where the first information includes first indication information, and the first indication information is used to indicate at least one of the following: the input information of the AI model required for making a prediction based on the first measurement result; the output information of the AI model required for making a prediction based on the first measurement result.

[0054] In a possible implementation manner, the transceiver module is further configured to send second information, where the second information includes fourth indication information, and the fourth indication information is used to indicate at least one of the following: the input size of the first AI model, the output size of the first AI model.

[0055] In a possible implementation manner, the transceiver module is further configured to receive third information, where the third information includes sixth indication information, and the sixth indication information is used to indicate the input information and output information of a second AI model that needs to be trained based on the communication device, and the first AI model is trained based on the second AI model.

[0056] For possible implementation manners of the communication device in the third aspect, reference may be made to various possible implementation manners of the first aspect.

[0057] Regarding the technical effects brought by various possible implementation manners of the third aspect, reference may be made to the introduction of the technical effects of the first aspect or various possible implementation manners of the first aspect.

[0058] Fourthly, an embodiment of the present application provides a communication device, which has a function of implementing the actions in the method embodiment of the second aspect above. The communication device may be a network device, a component of a network device (such as a processor, a chip, or a chip system, etc.), or a logic module or software that can implement all or part of the functions of the network device. The function of the communication device may be implemented by hardware or by hardware executing corresponding software, and the hardware or software includes one or more modules or units corresponding to the above functions. In a possible implementation manner, the communication device includes a transceiver module and a processing module, where: the transceiver module is used to send resource configuration information and first information, and the first information includes first indication information, and the first indication information is used to indicate at least one of the following: input information of an AI model required for prediction based on a first measurement result; output information of an AI model required for prediction based on the first measurement result, and the first measurement result is obtained by measuring the resources configured based on the resource configuration information; the processing module is used to generate a downlink measurement signal; the transceiver module is further used to send the downlink measurement signal, and the downlink measurement signal includes a signal that the communication device needs to measure based on the resources configured based on the resource configuration information.

[0059] In a possible implementation manner, the transceiver module is further used to receive second information, and the second information includes fourth indication information, and the fourth indication information is used to indicate at least one of the following: the input size of the first AI model; the output size of the first AI model.

[0060] In a possible implementation manner, the transceiver module is further used to send third information, and the third information includes sixth indication information, and the sixth indication information is used to indicate the input information and output information of a second AI model that the communication device needs to train, and the first AI model is trained based on the second AI model.

[0061] Possible implementation manners of the communication device in the fourth aspect can refer to various possible implementation manners of the second aspect.

[0062] Regarding the technical effects brought by various possible implementation manners of the fourth aspect, reference can be made to the introduction of the technical effects of the second aspect or various possible implementation manners of the second aspect.

[0063] Fifthly, an embodiment of the present application provides another communication device, which includes one or more processors, and the one or more processors are used to process data or signaling so that the methods in the first aspect or the second aspect above are implemented.

[0064] Optionally, the communication device further includes a memory that stores programs or instructions. When the programs or instructions are executed by the processor, the communication device is caused to execute the methods as shown in the first aspect or the second aspect above. Exemplarily, the communication device may be a chip, the processor is a processing circuit in the chip, and the memory is a random access memory or a cache in the chip.

[0065] In a possible implementation, during the execution of the above method, the process of sending information (or signals) in the above method can be understood as a process of outputting information based on the instructions of the processor. When outputting information, the processor outputs the information to the transceiver for transmission by the transceiver. After the information is output by the processor, it may also be subject to other processing before reaching the transceiver. Similarly, when the processor receives input information, the transceiver receives the information and inputs it to the processor. Further, after the transceiver receives the information, the information may be subject to other processing before being input to the processor.

[0066] For operations such as sending and / or receiving involved by the processor, if there is no special indication, or if it does not conflict with its actual role or internal logic in the relevant description, it can generally be understood as an output based on the instructions of the processor.

[0067] During implementation, the above processor may be a processor dedicated to executing these methods, or a processor that executes computer instructions in the memory to execute these methods, such as a general-purpose processor, etc. For example, the processor may also be used to execute a program stored in the memory. When the program is executed, the communication device is caused to execute the methods as shown in the first aspect or any possible implementation manner of the first aspect above.

[0068] In a possible implementation manner, the memory is located outside the above communication device. In a possible implementation manner, the memory is located inside the above communication device.

[0069] In a possible implementation manner, the processor and the memory may also be integrated into one device, that is, the processor and the memory may also be integrated together.

[0070] In a possible implementation manner, the communication device further includes a transceiver, which is used to receive signals, send signals, etc.

[0071] In a sixth aspect, the present application provides another communication device, which includes a processing circuit and an interface circuit. The interface circuit is used to obtain data or output data; the processing circuit is used to execute the methods as shown in the first aspect or the second aspect above.

[0072] Seventh aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions, and when the program instructions are executed, the computer is caused to execute the method as shown in the above first aspect or the above second aspect.

[0073] Eighth aspect, the present application provides a computer program product, which includes a computer program. The computer program includes program instructions, and when the program instructions are executed, the computer is caused to execute the method as shown in the above first aspect or the above second aspect.

[0074] Ninth aspect, the present application provides a chip, including a communication interface and a processor; the communication interface is used for signal transceiver of the chip; the processor is used for executing computer program instructions, so that a communication device including the chip executes the method as shown in the above first aspect or the above second aspect.

[0075] Tenth aspect, an embodiment of the present application provides a communication system, including the communication device as described in the above third aspect or any possible implementation manner of the third aspect, and the communication device as described in the above fourth aspect or any possible implementation manner of the fourth aspect. Description of the Drawings

[0076] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background art, the following will describe the drawings required to be used in the embodiments of the present application or the background art.

[0077] Figure 1 is a schematic diagram of the architecture of the communication system provided by the present application;

[0078] Figure 2 is a flowchart of a communication method provided by an embodiment of the present application;

[0079] Figure 3 is a schematic diagram of the association relationship between a resource index and an input / output index provided by an embodiment of the present application;

[0080] Figure 4 is another flowchart of a communication method provided by an embodiment of the present application;

[0081] Figure 5 is another flowchart of a communication method provided by an embodiment of the present application;

[0082] Figure 6 is a schematic diagram of the structure of a communication device 600 provided by an embodiment of the present application;

[0083] Figure 7 is a schematic diagram of the structure of another communication device 70 provided by an embodiment of the present application;

[0084] Figure 8 This is a schematic structural diagram of another communication device 80 provided by an embodiment of the present application. Detailed implementation manners

[0085] Terms such as "first" and "second" in the description, claims and drawings of the present application are only used to distinguish different objects, rather than to describe a specific order. It can be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and do not limit the scope of the embodiments of the present application. The magnitudes of the serial numbers of the above processes do not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device, etc. that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices, etc.

[0086] As used herein, the term "embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art can explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0087] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. As used in the description and appended claims of the present application, the singular forms "a", "an", "the", "above", "said", "this" are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more of the listed items. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Here, A and B can be singular or plural. The term "plural" used in the present application means two or more. In the written description of the present application, the character " / " generally represents an "or" relationship between the associated objects before and after.

[0088] It can be understood that in the embodiments of the present application, "B corresponding to A" means that there is a corresponding relationship between A and B, and B can be determined according to A. However, it should also be understood that determining (or generating) B based on (or according to) A does not mean that B is determined (or generated) only based on (or according to) A, and B can also be determined (or generated) based on (or according to) A and / or other information.

[0089] It should be understood that in this application, indication includes direct indication (also known as explicit indication) and implicit indication. Among them, directly indicating information A means including this information A; implicitly indicating information A means indicating information A through the correspondence between information A and information B and directly indicating information B. Among them, the correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0090] It should be understood that in this application, information C is used for the determination of information D, which includes both the case where information D is determined only based on information C and the case where it is determined based on information C and other information. In addition, when information C is used for the determination of information D, there may also be an indirect determination case, for example, the case where information D is determined based on information E and information E is determined based on information C.

[0091] In addition, for "network element A sends information A to network element B" in various embodiments of this application, it can be understood that the destination end of this information A or the intermediate network element in the transmission path between the destination ends is network element B, and it can include directly or indirectly sending information to network element B. "Network element B receives information A from network element A" can be understood that the source end of this information A or the intermediate network element in the transmission path between the source ends is network element A, and it can include directly or indirectly receiving information from network element A. Necessary processing may be performed on the information between the source end and the destination end of the information transmission, such as format change, etc., but the destination end can understand the valid information from the source end. Similar expressions in this application can be understood similarly and will not be elaborated here.

[0092] To facilitate the understanding of the solution of this application, the terms and technical solutions involved in the embodiments of this application are first introduced below.

[0093] Beam management: The process of aligning the transmitting and receiving beams of a base station and a user equipment (UE) is called beam management. Since analog beams can only transmit a limited number of shaped beams at the same time and the beam width is relatively narrow, usually only a part of the cell area can be covered. To achieve the signal coverage of the entire cell, a transmission method of jointly scanning multiple beams in the time domain is usually adopted to achieve the complete coverage of the cell. For unicast transmission between the base station and the UE, the maximum link gain can be obtained when the transmitting and receiving beams between the base station and the UE are aligned.

[0094] In Release 15 (R15), the beam management process is divided into six processing aspects: beam selection, beam measurement, beam reporting, beam handover, beam indication, and beam recovery. Regarding beam reporting, the UE needs to detect and estimate the channel quality of multiple beams. However, the UE does not need to report all the measurement results to the base station. It only needs to select the measurement results of M beams for reporting, where M is an integer greater than 0. When M = 1, the UE only reports the best beam among all the downlink beams. When M > 1, the UE can select the best or most suitable M beam measurement results for reporting. With the application of massive antennas, the number of beams has increased sharply. In Release 18, AI technology is used to predict beams, and the quality of unmeasured beams or the beam indices with better beam quality are predicted through a small number of beam measurement results.

[0095] Model training: For the UE-side model, both the training and inference of the model are located on the UE side. The UE needs to configure the resources to be measured through the base station and measure the resources to be measured to obtain model training data. For example, the base station configures multiple beams for the UE to measure, and the UE measures these multiple beams to obtain beam measurement results, which can be used as model training data.

[0096] The network architecture involved in this application will be introduced in detail below.

[0097] The technical solution provided by this application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD), Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication system, 5th generation (5G) communication system or New Radio (NR), and other future communication systems such as 6G. The communication systems applicable to the technical solution provided by this application include at least two entities. One entity (such as a base station) can send downlink beams (i.e., downlink measurement signals), and another entity (such as a user equipment) can receive the downlink beams and predict the quality of unmeasured beams or the beam indices with better beam quality through an AI model based on the beam measurement results. It should be understood that the technical solution provided by this application is applicable to any communication system including the above at least two entities.

[0098] See Figure 1 , Figure 1 which is a schematic diagram of the architecture of the communication system provided by this application. As Figure 1 shown, the communication system includes one or more network devices (such as base stations), Figure 1 and only one network device is taken as an example herein; and one or more user devices connected to the network device, Figure 1 and only four user devices are taken as an example herein, namely User Equipment 1 to User Equipment 4.

[0099] In the embodiments of this application, a user equipment (UE) may also be referred to as a terminal device, an access terminal, a user unit, a user station, a mobile station, a mobile terminal, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent or a user device.

[0100] A terminal device may be a device that provides voice / data. For example, it may be a handheld device, a vehicle-mounted device, etc. with a wireless connection function. Currently, some examples of terminals are: mobile phone, tablet computer, laptop computer, palmtop computer, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), a handheld device with wireless communication function, a computing device or other processing devices connected to a wireless modem, wearable device, a terminal device in a 5G network or a terminal device in a future evolved public land mobile network (PLMN), etc., and the embodiments of this application are not limited thereto.

[0101] By way of example and not limitation, in the embodiments of the present application, the terminal device may also be a wearable device. A wearable device, also known as a wearable intelligent device, is a general term for devices developed by applying wearable technologies to the intelligent design of daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. A wearable device is not only a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable intelligent devices include those with complete functions and large sizes that can achieve complete or partial functions without relying on a smart phone, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to cooperate with other devices such as smart phones, such as various smart bracelets and smart jewelry for physical sign monitoring.

[0102] In the embodiments of the present application, the device for implementing the functions of the terminal device may be the terminal device or a device capable of supporting the terminal device to implement such functions, such as a chip system. This device may be installed in the terminal device or used in matching with the terminal device. In the embodiments of the present application, the chip system may be composed of chips or may include chips and other discrete devices. In the embodiments of the present application, only the case where the device for implementing the functions of the terminal device is the terminal device is taken as an example for illustration, which does not limit the solutions of the embodiments of the present application.

[0103] The network device in the embodiments of the present application can be a device used to communicate with a terminal device. This network device can also be referred to as an access network device or a radio access network device. For example, the network device can be a base station. The network device in the embodiments of the present application can refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station can generally cover various names as follows, or be replaced with the following names, such as: RAN node, Node B, evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, slave station, multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. A base station can be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. A base station can also refer to a communication module, a modem, or a chip disposed in the foregoing device or apparatus. A base station can also be a mobile switching center and a device that undertakes the function of a base station in D2D, V2X, M2M communications, a network-side device in a 6G network, a device that undertakes the function of a base station in a future communication system, etc. A base station can support networks of the same or different access technologies. Optionally, the RAN node can also be a server, a wearable device, a vehicle, or an in-vehicle device, etc. For example, the access network device in vehicle to everything (V2X) technology can be a road side unit (RSU). The embodiments of the present application do not limit the specific technologies and specific device forms adopted by the network device.

[0104] The base station can be fixed or mobile. For example, a helicopter or a drone can be configured to act as a mobile base station, and one or more cells can move according to the position of the mobile base station. In other examples, a helicopter or a drone can be configured to be used as a device for communicating with another base station.

[0105] In some deployments, the network device mentioned in the embodiments of the present application can be a device including a CU, or a DU, or a device including a CU and a DU, or a control plane CU node (Central Unit Control Plane (CU-CP)) and a user plane CU node (Central Unit User Plane (CU-UP)) and a DU node. For example, the network device can include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0106] In some deployments, multiple RAN nodes cooperate to assist a terminal in achieving wireless access, and different RAN nodes respectively implement partial functions of the base station. For example, the RAN node can be a CU, a DU, a CU-CP, a CU-UP, or an RU, etc. The CU and the DU can be set separately, or can also be included in the same network element, such as a BBU. The RU can be included in a radio device or a radio unit, such as included in an RRU, an AAU, or an RRH.

[0107] In the embodiments of the present application, the device for implementing the functions of the network device can be the network device; it can also be a device capable of supporting the network device in implementing the functions, such as a chip system, a hardware circuit, a software module, or a combination of a hardware circuit and a software module. The device can be installed in the network device or used in cooperation with the network device. In the embodiments of the present application, only the case where the device for implementing the functions of the network device is the network device is taken as an example for description, which does not limit the solutions of the embodiments of the present application.

[0108] It should be noted that the network architecture described in the embodiments of the present application is for more clearly explaining the technical solutions of the embodiments of the present application, and does not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those of ordinary skill in the art know that with the evolution of the network architecture and the emergence of new service scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0109] In the embodiments of the present application, the device for implementing the functions of the network device can be the network device; it can also be a device capable of supporting the network device in implementing the functions, such as a chip system. The device can be installed in the network device or used in cooperation with the network device. In the following embodiments, the case where the device for implementing the functions of the network device is the network device and the network device is a base station is taken as an example to describe the technical solutions provided by the embodiments of the present application.

[0110] Figure 1 In the communication system shown, the network device and any user device can be used to execute the method provided in the embodiments of the present application.

[0111] As described in the background section above, the generalization of existing AI models is relatively limited. They can achieve good prediction performance in specific scenarios, but when the inference and training scenarios of the AI model are different, the prediction accuracy of the AI will be greatly affected. Therefore, it is necessary to ensure the consistency of the input data during the training and inference of the AI model to ensure the prediction performance of the AI. The technical solution of the present application can ensure the consistency of the input data during the training and inference of the AI model, thereby ensuring the prediction performance of the AI. The inventive concept of the technical solution of the present application is that the base station instructs the terminal device to predict the input information and / or output information of the AI model used, which can ensure the consistency of the input data during the training and inference of the AI model, thereby ensuring the prediction performance of the AI.

[0112] The following introduces the technical solution provided in the embodiments of the present application with reference to the accompanying drawings.

[0113] Figure 2 It is a flowchart of a communication method provided in an embodiment of the present application. As Figure 2 shown, the method includes:

[0114] 201. The base station sends resource configuration information and first information to the terminal device.

[0115] Correspondingly, the terminal device receives the resource configuration information and the first information from the base station. The resource configuration information and the first information can be carried in the same message or in different messages, which is not limited in the present application. The resource configuration information is used to configure the resources that the terminal device needs to measure, such as beams.

[0116] An example of a base station sending resource configuration information to a terminal device is as follows: Configure the resource sets of set B (model input) and set A (model output) through high-layer signaling; among them, in this example, the base station needs to configure the resource set of set B and the resource set of set A (applicable to the case where the resource set of set B is a subset of the resource set of set A or the resource set of set B is not a subset of the resource set of set A, for example, set B is a wide beam and set A is a narrow beam). For example, the base station configures the resource sets of set B (model input) and set A (model output) through high-layer RRC. The resource set of set B contains multiple time-frequency resources, and the resource set of set A contains multiple time-frequency resources. In one possible implementation, the resource set of set B is a set of beams, and the resource set of set A is also a set of beams. Exemplarily, the terminal device needs to measure the quality of the beams in the resource set of set B; the beams in the resource set of set A are the beams that the terminal device needs to measure. Exemplarily, the resource configuration information may include a first index set and a second index set. A beam form index in the first index set indicates a beam in the resource set of set B, for example, the combination of the beam direction and beam width of the beam; a beam form index in the second index set indicates a beam in the resource set of set A, for example, the combination of the beam direction and beam width of the beam.

[0117] An example of a base station sending resource configuration information to a terminal device is as follows: Configure the resource set of set A through high-layer signaling. At this time, it is necessary to configure a resource set (applicable to the case where set B is a subset of set A); the number of set B can be further configured, and the specific configuration method can be any of the following: Configure the number of resources included in the resource set of set B. For example, 4, 8, 10, etc. The resources in the resource set of set B are any 4, 8, 10, etc. in the resource set of set A, or select resources in set A at equal intervals as the resource set of set B; Configure the pattern corresponding to set B. The pattern includes a set of index sets, for example, [1 3 5 7 9]. Among them, the resources included in set B are the resources corresponding to the indexes in this set of index sets in the resource set of set A; The sampling rate of set B. For example, 1 / 2, 1 / 4, etc. Among them, the number of resources included in set B is 1 / 2, 1 / 4, etc. of the number of resources in the resource set of set A. For example, the resources in the resource set of set B are selected from set A at equal intervals as the resource set of set B. For example, the base station configures the resource sets of set B (model input) and set A (model output) through high-layer RRC. The resource set of set B includes multiple time-frequency resources, and the resource set of set A includes multiple time-frequency resources.

[0118] 202. The terminal device measures based on the resources configured according to the resource configuration information to obtain a first measurement result.

[0119] The first measurement result includes one or more resource measurement results. Exemplarily, the terminal device performs beam measurement based on the resources configured according to the resource configuration information to obtain a beam measurement result, and the beam measurement result may include the quality of multiple beams.

[0120] 203. The terminal device determines to use the first AI model to make a prediction based on the first measurement result according to the first information.

[0121] The above-mentioned first information includes first indication information. The first indication information is used to indicate at least one of the following: the input information of the AI model required for making a prediction based on the first measurement result; the output information of the AI model required for making a prediction based on the first measurement result. Exemplarily, the format of the input information of the first AI model is the same as the format of the input information of the AI model required for making a prediction based on the first measurement result, and the format of the output information of the first AI model is the same as the format of the output information of the AI model required for making a prediction based on the first measurement result.

[0122] In a possible implementation, the first indication information is used to indicate the output information of the AI model required for prediction based on the above first measurement result; the output information of the above AI model includes: the resource set corresponding to the output of the above AI model. Optionally, the above first indication information is further used to indicate the input information of the AI model required for prediction based on the above first measurement result, and the input information of the above AI model includes any one of the following: the number of resources in the resource set corresponding to the input of the above AI model, the resource index set corresponding to the resource set corresponding to the input of the above AI model, each resource index in the above resource index set corresponds to a resource in the resource set corresponding to the output of the above AI model, the pattern corresponding to the input of the above AI model, the above pattern includes a set of index sets, and the sampling rate of the number of resources in the resource set corresponding to the input of the above AI model relative to the number of resources in the resource set corresponding to the output of the above AI model.

[0123] In a possible implementation, the above first indication information is used to indicate the input information of the AI model required for prediction based on the above first measurement result; the input information of the above AI model includes: the resource set corresponding to the input of the above AI model.

[0124] In a possible implementation, the above first information further includes second indication information, and the second indication information is used to indicate at least one of the following: the association relationship between the index of the resource in the resource set corresponding to the input of the above AI model and the input index of the above AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the above AI model and the output index of the above AI model; the association relationship between the input index and the output index of the above AI model. Exemplarily, the second indication information is used to indicate the association relationship between the index of the resource (beam) in the resource set corresponding to the input of the above AI model and the input index of the above AI model, and the association relationship between the index of the resource in the resource set corresponding to the output of the above AI model and the output index of the above AI model. Figure 3 This is a schematic diagram of the association relationship between the resource index and the input / output index provided by the embodiments of the present application. As Figure 3As shown, resource 1 (resource1) in the resource set of set B is associated with the input index n (i.e., input n) of the AI model, resource 8 in the resource set of set B is associated with the input index 2 (i.e., input 2) of the AI model, resource 9 in the resource set of set B is associated with the input index 1 (i.e., input 1) of the AI model, resource 2 in the resource set of set A is associated with the output index 2 (i.e., output 2) of the AI model, resource 5 in the resource set of set A is associated with the output index 1 (i.e., output 1) of the AI model, and resource 7 in the resource set of set A is associated with the output index m (i.e., output m) of the AI model. In a possible implementation, when the resource set of set B is a subset of the resource set of set A, the association relationship between the index of the resource in the resource set corresponding to the input of the AI model and the above-mentioned input index of the AI model, and the association relationship between the index of the resource in the resource set corresponding to the output of the AI model and the above-mentioned output index of the AI model implicitly indicate the association relationship between the input index of the AI model and the above-mentioned output index of the AI model, that is, the indexes of the same resource correspond to the same beam. For example, the input index 3 of the AI model is associated with resource 6, the output index 4 of the AI model is associated with resource 6, and the input index 3 of the AI model is associated with the output index 4 of the AI model. In a possible implementation, when the resource set of set B is a subset of the resource set of set A, the base station can configure the association relationship between the input index of the AI model and the above-mentioned output index of the AI model.

[0125] In a possible implementation, the above first measurement result includes one or more resource measurement results, such as beam measurement results; the above first information further includes third indication information, and the third indication information is used to indicate at least one of the following: the beam shape corresponding to the resources in the resource set corresponding to the input of the above AI model, the beam shape corresponding to the resources in the resource set corresponding to the output of the above AI model. Exemplarily, the third indication information includes at least one of the following: a plurality of first indices, a plurality of second indices; each first index is used to indicate a combination of a beam direction and a beam width, and the plurality of first indices correspond one-to-one to the resources in the resource set corresponding to the input of the above AI model, each second index is used to indicate a combination of a beam direction and a beam width, and the plurality of second indices correspond one-to-one to the resources in the resource set corresponding to the output of the above AI model. It should be noted that any two of the plurality of first indices are different, and any two of the plurality of second indices are different. Exemplarily, the third indication information is used to indicate an identifier, and the identifier is used to indicate the network device from which the above first information comes, and the identifier includes at least one of the following: a plurality of first combinations corresponding to the resources in the resource set corresponding to the input of the above AI model, each first combination includes a beam shape and a beam width, and each first combination corresponds to a resource (beam) in the resource set corresponding to the input of the AI model, a plurality of second combinations corresponding to the resources in the resource set corresponding to the output of the above AI model, each second combination includes a beam shape and a beam width, and each second combination corresponds to a resource (beam) in the resource set corresponding to the output of the AI model. It should be noted that any two of the plurality of first combinations are different, and any two of the plurality of second combinations are different. Exemplarily, the third indication information is used to indicate the direction and width of a reference beam, and the angular offsets of a plurality of beams relative to the reference beam, a part of the plurality of beams corresponds to the resources in the resource set corresponding to the input of the above AI model, and another part of the plurality of beams corresponds to the resources in the resource set corresponding to the output of the above AI model.

[0126] 204. The terminal device uses the first AI model to make a prediction based on the first measurement result to obtain a prediction result.

[0127] In a possible implementation, the first measurement result includes a plurality of resource measurement results, such as beam measurement results; the terminal device uses the first AI model to make a prediction based on the first measurement result to obtain the quality of a plurality of other resources. Exemplarily, the first measurement result includes a plurality of beam measurement results, and the prediction result includes the predicted quality of the unmeasured beams or the beam indices with better beam quality.

[0128] 205. The terminal device sends the prediction result to the base station.

[0129] Correspondingly, the base station receives the prediction result from the terminal device. In one possible implementation, the base station sends a downlink signal or data to the terminal device based on the prediction result.

[0130] In the embodiments of the present application, based on the first information, it is determined to use the first AI model to make a prediction based on the first measurement result; it can be ensured that at least one of the input information and the output information of the used AI model is consistent with at least one of the input information and the output information of the AI model required for making a prediction based on the first measurement result.

[0131] Figure 4 It is a flowchart of another communication method provided by the embodiments of the present application. Figure 4 The method flow in Figure 2 A possible implementation manner of the described method.

[0132] 401. The terminal device sends the second information to the base station.

[0133] Correspondingly, the base station receives the second information from the terminal device. The second information includes the fourth indication information, and the fourth indication information is used to indicate at least one of the following: the input size of the first AI model, the output size of the first AI model. The input size of the first AI model may refer to the number of resources / number of beams corresponding to the input of the first AI model, and the output size of the second AI model may refer to the number of resources / number of beams corresponding to the output of the first AI model. Alternatively, the fourth indication information is used to indicate at least one of the following: the input information of the first AI model, the output information of the first AI model. The input information of the first AI model and the output information of the first AI model can refer to Figure 2 the description of the input information and output information of the AI model in the method flow of

[0134] In a possible implementation, the second information further includes fifth indication information, and the fifth indication information is used to indicate any of the following: the input pattern of the first AI model; the association relationship between the input index and the output index of the first AI model; the beam pattern corresponding to the first AI model; the association relationship between the index of the resource in the resource set corresponding to the input of the first AI model and the input index of the first AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the first AI model and the output index of the first AI model. The input pattern of the first AI model may be a set of resource indices that make up set B, and each resource index indicates a resource (such as a beam) in the resource set of set B. The beam pattern corresponding to the first AI model may include: the beam pattern corresponding to the resource in the resource set corresponding to the input of the first AI model, and the beam pattern corresponding to the resource in the resource set corresponding to the output of the first AI model. Or rather, the beam pattern corresponding to the first AI model may include: the shape of the beam associated with the input of the first AI model, and the shape of the beam associated with the output of the first AI model.

[0135] 402. The base station sends resource configuration information and first information to the terminal device based on the second information.

[0136] Based on the second information, the base station can obtain the input information and output information of one or more AI models that the terminal device can adopt. In a possible implementation, the base station obtains the input information and output information of one or more AI models (including the first AI model) that the terminal device can adopt based on the second information; the base station determines that the terminal device needs to use the first AI model to predict the quality of other resources based on the measured resource measurement results (such as beam measurement results), for example, to predict the quality of other beams; and sends resource configuration information and first information to the terminal device, where the resource configuration information is used to configure the time-frequency resources that the terminal device can use to measure the quality of the beam, and the first information is used to indicate the input information and output information of the first AI model.

[0137] 403. The terminal device measures based on the resources configured by the resource configuration information to obtain a first measurement result.

[0138] Step 403 can refer to Figure 2 Step 202 in

[0139] 404. The terminal device determines to use the first AI model to make a prediction based on the first measurement result according to the first information.

[0140] Step 404 can refer to Figure 2 Step 203 in

[0141] 405. The terminal device uses the first AI model to make a prediction based on the first measurement result, and obtains a prediction result.

[0142] Step 405 can refer to Figure 2 step 204 in

[0143] 406. The terminal device sends the prediction result to the base station.

[0144] In the embodiments of the present application, the terminal device sends second information to the base station. Based on the second information, the base station can obtain the input information and output information of one or more AI models that the terminal device can use, and then send first information to the terminal device. Based on the first information, it is determined to use the first AI model to make a prediction based on the first measurement result; it can be ensured that at least one of the input information and output information of the used AI model is consistent with at least one of the input information and output information of the AI model required for making a prediction based on the first measurement result.

[0145] Figure 5 This is another flowchart of the communication method provided by the embodiments of the present application. Figure 5 The method flow in Figure 2 a possible implementation manner of the method described

[0146] 501. The base station sends third information to the terminal device.

[0147] Correspondingly, the terminal device receives the third information from the base station. The third information includes sixth indication information, and the sixth indication information is used to indicate the input information and output information of the second AI model that the terminal device needs to train. The first AI model is trained based on the second AI model.

[0148] In a possible implementation manner, the input information of the second AI model includes: the resource set corresponding to the input of the second AI model; the output information of the second AI model includes: the resource set corresponding to the output of the second AI model.

[0149] In a possible implementation, the output information of the second AI model includes: the resource set corresponding to the output of the second AI model; the input information of the second AI model includes any one of the following: the number of resources in the resource set corresponding to the input of the second AI model, the resource index set corresponding to the resource set corresponding to the input of the second AI model, each resource index in the resource index set corresponds to a resource in the resource set corresponding to the output of the second AI model, the pattern corresponding to the input of the second AI model, the pattern includes a set of index sets, and the sampling rate of the number of resources in the resource set corresponding to the input of the second AI model relative to the number of resources in the resource set corresponding to the output of the second AI model.

[0150] In a possible implementation, the third information further includes seventh indication information, and the seventh indication information is used to indicate at least one of the following: the association relationship between the index of the resource in the resource set corresponding to the input of the second AI model and the input index of the second AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the second AI model and the output index of the second AI model; the association relationship between the input index and the output index of the second AI model.

[0151] In a possible implementation, the third information further includes eighth indication information, and the eighth indication information is used to indicate at least one of the following: the beam shape corresponding to the resource in the resource set corresponding to the input of the second AI model, the beam shape corresponding to the resource in the resource set corresponding to the output of the second AI model. Exemplarily, the eighth indication information includes at least one of the following: a plurality of first indexes, a plurality of second indexes; the first index is used to indicate a combination of a beam direction and a beam width, the plurality of first indexes correspond to the resources in the resource set corresponding to the input of the second AI model, the second index is used to indicate a combination of a beam direction and a beam width, and the plurality of second indexes correspond to the resources in the resource set corresponding to the output of the second AI model. Exemplarily, the eighth indication information is used to indicate an identifier, and the identifier is used to indicate the network device from which the third information comes, and the identifier includes at least one of the following: a plurality of combinations of beam directions and beam widths corresponding to the resources in the resource set corresponding to the input of the second AI model, a plurality of combinations of beam directions and beam widths corresponding to the resources in the resource set corresponding to the output of the second AI model.

[0152] Step 501 may be the input information and output information of the second AI model that the base station sends to the terminal device during the model training phase. An example of the input information and output information of the second AI model includes one or more of the following:

[0153] The sizes of Set B (model input) and Set A (model output), and two possible ways are as follows:

[0154] Option 1: The resource sets of Set B and Set A configured by high-layer signaling. In this case, two resource sets need to be configured (applicable to the cases where Set B is a subset of Set A and Set B is not a subset of Set A);

[0155] Option 2: Configure the resource set of Set A through high-layer RRC. In this case, one resource set needs to be configured (applicable to the case where Set B is a subset of Set A), and the number of Set B can be further configured. The specific configuration methods include: the number of resources included in Set B, for example, 4, 8, 10, etc.; the pattern of resources in Set B (including a set of index sets), for example, [1 3 5 7 9]; the sampling rate of Set B, for example, 1 / 2, 1 / 4, etc.

[0156] Resource index, and two possible ways are as follows:

[0157] Option 1: The resource index is arranged in the input-output order of the second AI model. For example, the resource index of the first input of the second AI model is 1, the resource index of the second input of the second AI model is 2, and so on;

[0158] Option 2: Associate the resource index and the input-output index, that is, indicate the association relationship between the resource index and the input-output index. For details, refer to Figure 3 and Figure 3 the relevant descriptions;

[0159] Input-output association relationship, and two possible ways are as follows:

[0160] If Set B is a subset of Set A, implicitly indicate the association relationship between the input and output of the second AI model through the resource index. For example, the same resource index corresponds to the same beam;

[0161] If Set B is not a subset of Set A, configure the association relationship between the input and output of the second AI model by the base station;

[0162] Beam shape, and three possible ways are as follows:

[0163] Option 1: The base station indicates one or more beam shape indices, each index indicating a combination of a beam direction and a beam width;

[0164] Option 2: The base station indicates an identifier, which includes a set of combinations of beam directions and beam widths (i.e., multiple combinations of beam directions and beam widths), and this identifier is used to indicate that the current data (i.e., the third information) comes from a certain base station;

[0165] Option 3: The base station indicates the relative offset of the beam shape. For example, taking a certain beam as a reference (i.e., this beam is used as a reference beam), it indicates the offset of the remaining beams relative to this beam (which may include, angle offset, width offset, etc.).

[0166] 502. The base station sends the resource information to be measured to the terminal device.

[0167] Correspondingly, the terminal device receives the resource information to be measured from the base station. The resource information to be measured is used to indicate the resources to be measured by the terminal device, such as beams. The base station sending the resource information to be measured to the terminal device can be that the base station configures the resources to be measured for the terminal device.

[0168] An example of the base station sending the resource information to be measured to the terminal device is as follows: Configure the resource sets of set B (model input) and set A (model output) through high-layer signaling; where, in this example, the base station needs to configure the resource sets of set B and set A (applicable to the case where the resource set of set B is a subset of the resource set of set A and the case where the resource set of set B is not a subset of the resource set of set A). Optionally, the base station also configures the time-frequency resources corresponding to the resource sets of set B (model input) and set A (model output) through high-layer RRC. In a possible implementation, the resource set of set B is a set of beams, and the resource set of set A is also a set of beams. Exemplarily, the terminal device needs to measure the quality of the beams in the resource sets of set B and set A to obtain the model training data; the beams in the resource set of set A are the beams that the terminal device needs to measure. Exemplarily, the resource configuration information may include a first index set and a second index set. A beam form index in the first index set indicates a beam in the resource set of set B, such as the combination of the beam direction and the beam width of this beam; a beam form index in the second index set indicates a beam in the resource set of set A, such as the combination of the beam direction and the beam width of this beam.

[0169] An example of the base station sending resource information to be measured to the terminal device is as follows: Configure the resource set of set A through high-layer signaling. At this time, it is necessary to configure a resource set (applicable to the case where set B is a subset of set A); the number of set B can be further configured. The specific configuration method can be any of the following: Configure the number of resources included in the resource set of set B. For example, 4, 8, 10, etc. The resources in the resource set of set B are any 4, 8, 10, etc. in the resource set of set A; Configure the pattern corresponding to set B. The pattern includes a set of index sets. For example, [1 3 5 7 9]. Among them, the resources included in set B are the resources corresponding to the indexes in the set of index sets in the resource set of set A; The sampling rate of set B. For example, 1 / 2, 1 / 4, etc. Among them, the number of resources included in set B is 1 / 2, 1 / 4, etc. of the number of resources in the resource set of set A. Optionally, the base station also configures the time-frequency resources corresponding to the resource sets of set B (model input) and set A (model output) through high-layer RRC.

[0170] 503. The terminal device measures based on the resources configured according to the resource information to be measured and obtains a second measurement result.

[0171] An example of step 503 is: The terminal device measures the beams in the resource sets of set B and set A and obtains a second measurement result. The second measurement result includes the quality of each beam in the resource set of set B and the quality of each beam in the resource set of set A.

[0172] 504. The terminal device trains a second AI model based on the second measurement result and the third information to obtain a first AI model.

[0173] In a possible implementation, the terminal device obtains model training data based on the second measurement result. In a possible implementation, the terminal device uses the beam measurement result obtained by measuring the beams in the resource set of set B as the input of the second AI model to predict the quality of the beams in the resource set of set A; based on the beam measurement result obtained by measuring the beams in the resource set of set A and the predicted quality of the beams in the resource set of set A, update the parameters of the second AI model, and finally train to obtain the first AI model.

[0174] Steps 501 to 504 illustrate the process of the terminal device training to obtain the first AI model. It should be understood that the base station and the terminal device can adopt a process similar to steps 501 to 504 to train to obtain other AI models, which is not limited in this application.

[0175] 505. The terminal device sends the second information to the base station.

[0176] Correspondingly, the base station receives second information from the terminal device. Step 505 may refer to Step 401.

[0177] Through model training, the terminal device may obtain more than one AI model. Which AI model to use in subsequent inference (or prediction) can be determined through model selection. The second information may be information reported by the terminal device to the base station for the base station to select the AI model used by the terminal device for prediction. The second information may be used to indicate the input information and input information of one or more available (e.g., trained) AI models of the terminal device. Exemplarily, the second information includes the above-mentioned third information. Below, taking the second information used to indicate the input information and output information of the first AI model obtained through training as an example, an introduction is given. An example of the second information includes at least one of the following: the input size and output size of the AI model; the input pattern of the AI model, such as the above-mentioned first index set; the correlation relationship between the input and output of the AI model; beam shape information; resource index method. The beam shape information may include the beam shape corresponding to the resources in the resource set corresponding to the input of the AI model, and the beam shape corresponding to the resources in the resource set corresponding to the output of the AI model. The description of the information in this example of the second information may refer to the information in the example of the input information and output information of the above-mentioned second AI model, which will not be elaborated here.

[0178] 506. Based on the second information, the base station sends resource configuration information and first information to the terminal device.

[0179] Steps 505 and 506 are optional. Steps 505 to 506 may be replaced by: The base station sends resource configuration information and first information to the terminal device.

[0180] 507. The terminal device measures based on the resources configured by the resource configuration information to obtain a first measurement result.

[0181] Step 507 may refer to Figure 2 Step 202 in

[0182] 508. Based on the first information, the terminal device determines to use the first AI model to make a prediction based on the first measurement result.

[0183] Step 508 may refer to Figure 2 Step 203 in

[0184] 509. The terminal device uses the first AI model to make a prediction based on the first measurement result to obtain a prediction result.

[0185] 510. The terminal device sends the prediction result to the base station.

[0186] In an embodiment of the present application, the base station sends reception resource configuration information and first information to the terminal device. Based on the first information, the base station determines to use a first AI model to make a prediction based on the first measurement result; it can ensure that the input information and output information of the adopted AI model are consistent with the input information and output information of the AI model required for making a prediction based on the first measurement result.

[0187] The following introduces the structure of a communication device that can implement the communication method provided in the embodiments of the present application in conjunction with the accompanying drawings. Only a brief description of the communication device is given below. For the implementation details of the solution, reference can be made to the description of the method embodiments above, and details will not be repeated below.

[0188] Figure 6 It is a schematic structural diagram of a communication device 600 provided in an embodiment of the present application. The communication device 600 can correspondingly implement the functions or steps implemented by the base station in each of the above method embodiments, and can also correspondingly implement the functions or steps implemented by the terminal device in each of the above method embodiments. The communication device may include a processing module 610 and a transceiver module 620. In a possible implementation manner, it may further include a storage unit, and the storage unit may be used to store instructions (codes or programs) and / or data. The processing module 610 and the transceiver module 620 may be coupled to the storage unit. For example, the processing module 610 may read the instructions (codes or programs) and / or data in the storage unit to implement the corresponding method. The above-mentioned various units may be independently provided, or may be partially or fully integrated. For example, the transceiver module 620 may include a sending module and a receiving module. The sending module may be a transmitter, and the receiving module may be a receiver. The entity corresponding to the transceiver module 620 may be a transceiver or a communication interface.

[0189] In some possible implementation manners, the communication device 600 can correspondingly implement the behaviors and functions of the base station in the above method embodiments. For example, the communication device 600 may be a base station, or may be a component (such as a chip or a circuit) applied to the base station. The transceiver module 620 may be used to perform Figure 2 , Figure 4 , Figure 5 All the receiving or sending operations performed by the base station in the embodiments of Figure 2 , Figure 4 , Figure 5 . The processing module 610 is used to perform all the operations other than the transceiver operations performed by the base station in the embodiments of

[0190] In some possible implementation manners, the communication device 600 can correspondingly implement the behaviors and functions of the terminal device in the above method embodiments. For example, the communication device 600 may be a terminal device, or may be a component (such as a chip or a circuit) applied to the terminal device. The transceiver module 620 may be used to performFigure 2 , Figure 4 , Figure 5 All the receiving or sending operations performed by the terminal device in the embodiments of Figure 2 , Figure 4 , Figure 5 All the operations other than the transceiver operations performed by the terminal device in the embodiments of

[0191] Figure 7 FIG. 15 is a schematic structural diagram of another communication device 70 provided by an embodiment of the present application. Figure 7 The communication device in Figure 7 may be the above-mentioned base station or the above-mentioned terminal device. As

[0192] shown, the communication device 70 includes at least one processor 710 and a transceiver 720. Figure 2 , Figure 4 , Figure 5 All the receiving or sending operations performed by the base station in the embodiments of Figure 2 , Figure 4 , Figure 5 The transceiver 720 is, for example, used to perform all the receiving or sending operations performed by the base station in the embodiments of

[0193] In some embodiments of the present application, the processor 710 and the transceiver 720 may be used to perform the functions or operations performed by the terminal device. The transceiver 720 is, for example, used to perform Figure 2 , Figure 4 , Figure 5 All the receiving or sending operations performed by the terminal device in the embodiments of Figure 2 , Figure 4 , Figure 5 All the operations other than the transceiver operations performed by the terminal device in the embodiments of

[0194] The transceiver 720 is used to communicate with other devices / devices through a transmission medium. The processor 710 uses the transceiver 720 to receive and send data and / or signaling, and is used to implement the method in the above method embodiments. The processor 710 can implement the function of the processing module 610, and the transceiver 720 can implement the function of the transceiver module 620. Optionally, the transceiver 720 may include a radio frequency circuit and an antenna. The radio frequency circuit is mainly used for the conversion between the baseband signal and the radio frequency signal and the processing of the radio frequency signal. The antenna is mainly used for receiving and sending radio frequency signals in the form of electromagnetic waves.

[0195] Optionally, the communication device 70 may further include at least one memory 730 for storing program instructions and / or data. The memory 730 is coupled to the processor 710. The coupling in the embodiments of the present application is an indirect coupling or communication connection between devices, units or modules, which may be electrical, mechanical or other forms for information interaction between devices, units or modules. The processor 710 may cooperate with the memory 730. The processor 710 may execute the program instructions stored in the memory 730. At least one of the at least one memory may be included in the processor.

[0196] The processor 710 may read the software program in the memory 730, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be wirelessly transmitted, after the processor 710 performs baseband processing on the data to be transmitted, it outputs a baseband signal to the radio frequency circuit, and the radio frequency circuit performs radio frequency processing on the baseband signal and then transmits the radio frequency signal outward in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the radio frequency circuit receives the radio frequency signal through the antenna, converts the radio frequency signal into a baseband signal, and outputs the baseband signal to the processor 710. The processor 710 converts the baseband signal into data and processes the data.

[0197] In another implementation, the above-mentioned radio frequency circuit and antenna may be provided independently of the processor performing baseband processing. For example, in a distributed scenario, the radio frequency circuit and antenna may be independent of the communication device and arranged in a remote manner.

[0198] In the embodiments of the present application, the specific connection medium between the transceiver 720, the processor 710, and the memory 730 is not limited. In the embodiments of the present application Figure 7 it is shown that the memory 730, the processor 710, and the transceiver 720 are connected through a bus 740. The bus is represented by a thick line in Figure 7 The connection manners between other components are only for illustrative purposes and are not to be construed as limitations. The bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 7 only a thick line is used to represent it in

[0199] In the embodiments of the present application, the processor may be one of the following devices: a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or all or part of the circuits for processing functions in the foregoing devices, which can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application may be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0200] Figure 8 FIG. 4 is a schematic structural diagram of another communication device 80 provided by an embodiment of the present application. Figure 8 The communication device in may be the above-mentioned base station or the above-mentioned terminal device. For example Figure 8 As shown Figure 8 The communication device shown includes a logic circuit 801 and an interface 802. Figure 6 The processing module 610 in may be implemented by the logic circuit 801, Figure 6 The transceiver module 620 in may be implemented by the interface 802. Among them, the logic circuit 801 may be a chip, a processing circuit, an integrated circuit, or a system-on-chip (SoC) chip, etc., and the interface 802 may be a communication interface, an input / output interface, etc. In the embodiments of the present application, the logic circuit and the interface may also be coupled to each other. For the specific connection manner between the logic circuit and the interface, the embodiments of the present application do not make limitations.

[0201] In some embodiments of the present application, the logic circuit and the interface may be used to execute the functions or operations performed by the above-mentioned base station, etc.

[0202] In some embodiments of the present application, the logic circuit and the interface may be used to execute the functions or operations performed by the above-mentioned terminal device, etc.

[0203] The present application also provides a computer-readable storage medium, in which a computer program or instruction is stored. When the computer program or instruction runs on a computer, the computer is enabled to execute the method of the above-mentioned embodiments.

[0204] The present application also provides a computer program product, which includes an instruction or a computer program. When the instruction or the computer program runs on a computer, the method in the above-mentioned embodiments is enabled to be executed.

[0205] The present application also provides a communication system, which includes the above-mentioned base station and the above-mentioned terminal device.

[0206] The present application also provides a chip, which includes: a communication interface and a processor; the communication interface is used for signal transceiver of the above chip; the processor is used for executing computer program instructions to enable a communication device including the above chip to execute the method in the above embodiment.

[0207] In the above embodiment, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The above computer program product includes one or more computer programs or instructions. When the above computer program or instructions are loaded and executed on a computer, the processes or functions in the above embodiment of the present application are executed in whole or in part. The above computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device or other programmable devices. The above computer program or instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the above computer program or instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center in a wired or wireless manner. The above computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrating one or more available media. The above available medium may be a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape; it may also be an optical medium, such as a digital video disc; it may also 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 volatile and non-volatile types of storage media.

[0208] Regarding each device and product described in the above embodiments, including modules / units, they can be software modules / units, hardware modules / units, or partly software modules / units and partly hardware modules / units. For example, for each device and product of an application or an integrated chip, each of the modules / units it includes can be implemented in the form of hardware such as circuits, or at least some of the modules / units can be implemented in the form of software programs, which run on the integrated processor inside the chip, and the remaining modules / units can be implemented in the form of hardware such as circuits; for each device and product corresponding to or integrated with a chip module, each of the modules / units it includes can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (such as a chip, a circuit module, etc.) or different components of the chip module. At least some of the modules / units can be implemented in the form of software programs, which run on the integrated processor inside the chip module, and the remaining modules / units can be implemented in the form of hardware such as circuits; for each device and product corresponding to or integrated with a terminal, each of the modules / units it includes can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (such as a chip, a circuit module, etc.) or different components inside the terminal, or at least some of the modules / units can be implemented in the form of software programs, which run on the integrated processor inside the terminal, and the remaining modules / units can be implemented in the form of hardware such as circuits.

[0209] The above communication device (virtual device) can be, for example: a chip, or a chip module, a processor, etc.

[0210] In each embodiment of the present application, if there is no special instruction and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

Claims

1. A communication method, characterized in that, it includes: receiving resource configuration information and first information; performing measurements based on the resources configured according to the resource configuration information to obtain a first measurement result; based on the first information, determining to use a first artificial intelligence (AI) model to make a prediction based on the first measurement result, where the first information includes first indication information, and the first indication information is used to indicate at least one of the following: the input information of the AI model required for making a prediction based on the first measurement result; the output information of the AI model required for making a prediction based on the first measurement result.

2. The method according to claim 1, characterized in that, the first indication information is used to indicate the output information of the AI model required for making a prediction based on the first measurement result; the output information of the AI model includes: the resource set corresponding to the output of the AI model.

3. The method according to claim 2, characterized in that, the first indication information is further used to indicate the input information of the AI model required for making a prediction based on the first measurement result, and the input information of the AI model includes any one of the following: the number of resources in the resource set corresponding to the input of the AI model; the resource index set corresponding to the resource set corresponding to the input of the AI model, where each resource index in the resource index set corresponds to a resource in the resource set corresponding to the output of the AI model; the pattern corresponding to the input of the AI model, the pattern includes a set of index sets; the sampling rate of the number of resources in the resource set corresponding to the input of the AI model relative to the number of resources in the resource set corresponding to the output of the AI model.

4. The method according to claim 1, characterized in that, the first indication information is used to indicate the input information of the AI model required for making a prediction based on the first measurement result; the input information of the AI model includes: the resource set corresponding to the input of the AI model.

5. The method according to any one of claims 1 to 4, characterized in that, the first information further includes second indication information, and the second indication information is used to indicate at least one of the following: the association relationship between the index of the resource in the resource set corresponding to the input of the AI model and the input index of the AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the AI model and the output index of the AI model; the association relationship between the input index and the output index of the AI model.

6. The method according to any one of claims 1 to 5, characterized in that, the first measurement result includes one or more resource measurement results; the first information further includes third indication information, and the third indication information is used to indicate at least one of the following: the beam shape corresponding to the resource in the resource set corresponding to the input of the AI model; the beam shape corresponding to the resource in the resource set corresponding to the output of the AI model.

7. The method according to claim 6, characterized in that, The third indication information includes at least one of the following: a plurality of first indexes, a plurality of second indexes; the first index is used to indicate a combination of a beam direction and a beam width, the plurality of first indexes correspond to resources in a resource set corresponding to an input of the AI model, the second index is used to indicate a combination of a beam direction and a beam width, and the plurality of second indexes correspond to resources in a resource set corresponding to an output of the AI model.

8. The method according to claim 6, wherein, the third indication information is used to indicate an identifier, and the identifier is used to indicate the network device from which the first information comes, and the identifier includes at least one of the following: a combination of a plurality of beam directions and beam widths corresponding to resources in a resource set corresponding to an input of the AI model, a combination of a plurality of beam directions and beam widths corresponding to resources in a resource set corresponding to an output of the AI model.

9. The method according to claim 6, wherein, the third indication information is used to indicate the direction and width of a reference beam, and angular offsets of a plurality of beams relative to the reference beam, a part of the plurality of beams corresponds to resources in a resource set corresponding to an input of the AI model, and another part of the plurality of beams corresponds to resources in a resource set corresponding to an output of the AI model.

10. The method according to any one of claims 1 to 9, wherein, the method further includes: sending second information, where the second information includes fourth indication information, and the fourth indication information is used to indicate at least one of the following: the input size of the first AI model, the output size of the first AI model.

11. The method according to claim 9, wherein, the second information further includes fifth indication information, and the fifth indication information is used to indicate any one of the following: the input pattern of the first AI model; the association relationship between the input index and the output index of the first AI model; the beam shape corresponding to the first AI model; the association relationship between the index of the resources in the resource set corresponding to the input of the first AI model and the input index of the first AI model; the association relationship between the index of the resources in the resource set corresponding to the output of the first AI model and the output index of the first AI model.

12. The method according to any one of claims 1 to 11, wherein, the method further includes: receiving third information, where the third information includes sixth indication information, and the sixth indication information is used to indicate input information and output information of a second AI model that needs to be trained based on the communication device, and the first AI model is trained based on the second AI model.

13. A communication method, wherein, it includes: Send resource configuration information and first information, where the first information includes first indication information, and the first indication information is used to indicate at least one of the following: input information of an AI model required for prediction based on a first measurement result; output information of the AI model required for prediction based on the first measurement result, where the first measurement result is obtained by measuring resources configured based on the resource configuration information. Send a downlink measurement signal, where the downlink measurement signal includes a signal that the communication device needs to measure based on resources configured according to the resource configuration information.

14. The method according to claim 13, wherein, the first indication information is used to indicate output information of an AI model required for prediction based on the first measurement result; the output information of the AI model includes: a resource set corresponding to the output of the AI model.

15. The method according to claim 14, wherein, the first indication information is further used to indicate input information of an AI model required for prediction based on the first measurement result, and the input information of the AI model includes any one of the following: the number of resources in the resource set corresponding to the input of the AI model; a resource index set corresponding to the resource set corresponding to the input of the AI model, where each resource index in the resource index set corresponds to a resource in the resource set corresponding to the output of the AI model; a pattern corresponding to the input of the AI model, where the pattern includes a set of index sets; the sampling rate of the number of resources in the resource set corresponding to the input of the AI model relative to the number of resources in the resource set corresponding to the output of the AI model.

16. The method according to claim 13, wherein, the first indication information is used to indicate input information of an AI model required for prediction based on the first measurement result; the input information of the AI model includes: a resource set corresponding to the input of the AI model.

17. The method according to any one of claims 13 to 16, wherein, the first information further includes second indication information, and the second indication information is used to indicate at least one of the following: the association relationship between the index of the resource in the resource set corresponding to the input of the AI model and the input index of the AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the AI model and the output index of the AI model; the association relationship between the input index and the output index of the AI model.

18. The method according to any one of claims 13 to 17, wherein, the first measurement result includes one or more resource measurement results; the first information further includes third indication information, and the third indication information is used to indicate at least one of the following: the beam shape corresponding to the resource in the resource set corresponding to the input of the AI model; the beam shape corresponding to the resource in the resource set corresponding to the output of the AI model.

19. The method according to claim 6, wherein, The third indication information includes at least one of the following: a plurality of first indexes, a plurality of second indexes; the first index is used to indicate a combination of a beam direction and a beam width, the plurality of first indexes correspond to resources in a resource set corresponding to an input of the AI model, and the second index is used to indicate a combination of a beam direction and a beam width, the plurality of second indexes correspond to resources in a resource set corresponding to an output of the AI model.

20. The method according to any one of claims 13 to 19, wherein, the method further includes: receiving second information, the second information includes fourth indication information, and the fourth indication information is used to indicate at least one of the following: the input size of the first AI model, the output size of the first AI model.

21. The method according to claim 20, wherein, the second information further includes fifth indication information, and the fifth indication information is used to indicate any one of the following: the input pattern of the AI model; the association relationship between the input index and the output index of the AI model; the beam shape corresponding to the AI model; the association relationship between the index of the resource in the resource set corresponding to the input of the AI model and the input index of the AI model; the association relationship between the index of the resource in the resource set corresponding to the output of the AI model and the output index of the AI model.

22. The method according to any one of claims 13 to 21, wherein, the method further includes: sending third information, the third information includes sixth indication information, and the sixth indication information is used to indicate the input information and output information of a second AI model that needs to be trained based on the communication device, and the first AI model is trained based on the second AI model.

23. A communication device, wherein, it includes a module for implementing the method according to any one of claims 1 to 22.

24. A communication device, wherein, it includes a processor, the processor is coupled with a memory, the memory stores computer program instructions, and the processor is used to execute the computer program instructions so that the communication device executes the method according to any one of claims 1 to 22.

25. A chip, wherein, it includes a processor and a communication interface, the processor reads instructions stored on a memory through the communication interface, and executes to make a communication device including the chip execute the method according to any one of claims 1 to 22.

26. A computer-readable storage medium, wherein, the computer-readable storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed, the computer is made to execute the method according to any one of claims 1 to 22.

Images