Data collection method and communication apparatus

Abstract

A data collection method and a communication apparatus. In the method, a first device sends a first reference signal, the first reference signal being used for channel measurement, and the first reference signal corresponding to first channel information; and subsequently, the first device receives first feedback information representing first sub-channel information corresponding to the first channel information, wherein the first sub-channel information is a first subset of the first channel information, or the first sub-channel information is determined on the basis of at least one second subset of the first channel information, granularity information corresponding to the first sub-channel information is used for describing the granularity of at least one dimension parameter among dimension parameters of the first channel information, and the first feedback information is used for at least one of model monitoring, model training, or model fine-tuning. The method can improve the data collection efficiency of channel information in a scenario in which air interface resources are limited.

Description

Data collection method and communication apparatus

[0001] This application claims priority to the Chinese Patent Application No. 202510382257.6, filed on March 27, 2025, and entitled "Data collection method and communication apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication, and more particularly, to a data collection method and a communication apparatus. BACKGROUND

[0003] To realize the effective deployment of an artificial intelligence (AI) model in an actual communication system, a model life cycle management process is needed, including functions such as data collection, model monitoring, model fine-tuning, model switching, etc. Among them, data collection is the basis for completing functions such as model training, monitoring, fine-tuning, etc. However, for the data collection of a channel measurement model, in the case of tight air interface resources, channel information may not be able to be fed back, resulting in the inability to collect channel data, so it is a problem to be solved to realize the data collection of channel information in the air interface resource limited scenario. SUMMARY

[0004] The present application provides a data collection method and a communication apparatus, so as to improve the data collection efficiency of channel information in the air interface resource limited scenario.

[0005] In a first aspect, a data collection method is provided, which can be executed by a first communication apparatus. The first communication apparatus can be a first device, or can be a component (such as a chip or circuit, which can be a modem chip, also known as a baseband chip, or a system on chip (SoC) or system in package (SIP) chip containing a modem core, etc.) for the first device, or can also be a logic module or software capable of realizing part or all functions of the first device, etc., which is not limited in the present application.

[0006] The method comprises: sending a first reference signal, the first reference signal being used for channel measurement, the first reference signal corresponding to first channel information; and receiving first feedback information, the first feedback information representing first sub-channel information corresponding to the first channel information, the first sub-channel information being a first subset of the first channel information, or the first sub-channel information being determined according to at least one second subset of the first channel information, the first sub-channel information corresponding to granularity information used to describe feedback granularity of at least one dimension parameter in a dimension parameter of the first channel information, the first feedback information being used for at least one of model monitoring, model training or model fine-tuning.

[0007] In the technical solution, the first feedback information received by the first device represents sub-channel information, which can effectively reduce feedback overhead of each data collection and improve data collection efficiency of a channel matrix in a limited air interface resource scenario. Specifically, according to the current feedback mode, the entire channel information needs to be fed back each time, which occupies too much air interface resource and has large collection overhead. When the air interface resource is tight, the current measured channel information cannot be fed back in time. However, according to the technical solution provided in the present application, although the entire channel information cannot be fed back each time, sub-channel information of the channel information can be reported. After multiple feedbacks, channel data of the channel information can also be collected, thereby improving data collection efficiency.

[0008] In some implementations of the first aspect, the first feedback information is used to obtain label data of the model.

[0009] For example, the first feedback information can be directly used for the above-mentioned model operation (i.e., at least one of model monitoring, model training or model fine-tuning); or, the first sub-channel information can be obtained based on the first feedback information, and then the first sub-channel information is used for the model operation; or, the first feedback information or the first sub-channel information can be processed, and the information obtained after processing is used for the model operation. The information used for the above-mentioned model operation in the present application can be regarded as label data of the model. The label data refers to data used to judge accuracy of an output of the model. Therefore, the first feedback information in the present application can be used to obtain the label data of the model.

[0010] In some implementations of the first aspect, the first channel information is channel information of the first reference signal corresponding to a first time unit.

[0011] It can be understood that the first reference signal is used for channel measurement, the first reference signal corresponds to the first channel information, that is, the first reference signal is used for channel measurement on the first channel to obtain the first channel information, the first channel is a channel between the terminal device and the network device, and the first channel information is channel information of the first reference signal corresponding to a first time unit. The first feedback information is used for at least one of model monitoring, model training or model fine-tuning.

[0012] In some implementations of the first aspect, the first channel information is used to characterize channel information on the first resource, and the first subset of the first sub-channel information is used to characterize channel information on the second resource, and the second resource is a subset of the first resource.

[0013] In some implementations of the first aspect, the first resource is a resource in at least one of a time domain, a frequency domain, and a spatial domain, and the second resource has the same dimension as the first resource.

[0014] In some implementations of the first aspect, the dimension parameter used to describe the first channel information comprises one or more of the following: antenna port information of the network device, frequency domain sub-band information corresponding to the first channel information, or antenna port information of the terminal device.

[0015] In some implementations of the first aspect, the dimension parameter used to describe the number of antenna ports of the network device or the terminal device comprises one or more of the following: horizontal antenna information, vertical antenna information, or polarization information.

[0016] In some implementations of the first aspect, the method further comprises: receiving first indication information, and the first indication information indicates the first sub-channel information. Optionally, the fourth indication information comprises an identifier of the first sub-channel information.

[0017] Optionally, the fourth indication information indicates the first sub-channel information in the form of a bitmap. For example, each bit corresponds to a sub-channel information, and different values of the bits are used to indicate the corresponding sub-channel information. For example, the bit corresponding to the first sub-channel information has a value of “1”, and the bits corresponding to other sub-channel information have a value of “0”.

[0018] In the above technical solution, the first device can receive multiple feedback information, and the first device can determine which sub-channel information in the multiple feedbacks can be regarded as the same channel sequence based on the first indication information corresponding to the multiple feedback information, so that the first device can accurately process the multiple feedback data.

[0019] In some implementations of the first aspect, the method further comprises: sending second indication information, and the second indication information is used to indicate the determination of the first sub-channel information.

[0020] In the above technical solution, when there is a shortage of air interface resources, for example, the first device can send the second indication information to indicate that the first sub-channel information is determined based on the second indication information.

[0021] In some implementations of the first aspect, the method further comprises: sending second indication information, wherein the second indication information is used to indicate target feature information of data collection.

[0022] For example, if the second indication information indicates the time domain feature information of the tag data, it indicates that the data collection (feedback of the first subchannel information) pays more attention to the time domain feature of the channel. For another example, if the second indication information indicates the spatial domain feature information of the tag data, it indicates that the data collection (feedback of the first subchannel information) pays more attention to the spatial domain feature of the channel.

[0023] In some implementations of the first aspect, the method further includes transmitting granularity information.

[0024] In some implementations of the first aspect, the transmitting or receiving the first configuration information includes transmitting the first configuration information if the first reference signal is a downlink reference signal, or receiving the first configuration information if the first reference signal is an uplink reference signal.

[0025] In some implementations of the first aspect, the transmitting or receiving the first configuration information includes transmitting the first configuration information if the first reference signal is a downlink reference signal, or receiving the first configuration information if the first reference signal is an uplink reference signal.

[0026] In some implementations of the first aspect, the method further includes receiving second feedback information, the second feedback information representing second subchannel information corresponding to the first channel information.

[0027] In the above technical solution, the information related to the first channel information can be fed back in batches, so that the feedback overhead of each data collection can be reduced.

[0028] In some implementations of the first aspect, the method further includes transmitting or receiving second configuration information, the second configuration information indicating that N feedback information corresponding to the first channel information corresponding to the first reference signal is fed back, N being a positive integer greater than 1, the N feedback information including the first feedback information and the second feedback information.

[0029] In some implementations of the first aspect, the transmitting or receiving the second configuration information includes transmitting the second configuration information if the first reference signal is a downlink reference signal, or receiving the second configuration information if the first reference signal is an uplink reference signal.

[0030] In a second aspect, a data collection method is provided, which can be executed by a second communication device. The second communication device can be a second device, or a component (such as a chip or circuit, which can be a modem chip, or a baseband chip, or a system on chip (SoC) or a system in package (SIP) chip containing a modem core, etc.) for the second device, or a logic module or software capable of realizing part or all of the functions of the second device, etc., which are not limited in the present application.

[0031] The method comprises: receiving a first reference signal, the first reference signal being used for channel measurement, the first reference signal corresponding to first channel information; and sending first feedback information, the first feedback information representing first sub-channel information corresponding to the first channel information, the first sub-channel information being a first subset of the first channel information, or the first sub-channel information being determined according to at least one second subset of the first channel information, feedback granularity information corresponding to the first sub-channel information being used to describe a feedback granularity of at least one dimension parameter in a dimension parameter of the first channel information, and the first feedback information being used for at least one of model monitoring, model training, or model fine-tuning.

[0032] It can be understood that the second aspect corresponds to the first aspect described above, and the technical effects and part of the description can be referred to the description of the first aspect.

[0033] In some implementations of the second aspect, the first feedback information is used to obtain label data of the model.

[0034] In some implementations of the second aspect, the first channel information is channel information corresponding to the first reference signal at a first time unit.

[0035] In some implementations of the second aspect, the first channel information is used to represent channel information on a first resource, and a subset corresponding to the first sub-channel information is used to represent channel information on a second resource, the second resource being a subset of the first resource.

[0036] In some implementations of the second aspect, the first resource comprises a first frequency domain resource, and the second resource comprises a second frequency domain resource, the second frequency domain resource being a subset of the first frequency domain resource.

[0037] In some implementations of the second aspect, the dimension parameter describing the first channel information comprises one or more of the following: antenna port information of the network device, frequency domain sub-band information corresponding to the first channel information, or antenna port information of the terminal device.

[0038] In some implementations of the second aspect, the dimension parameter describing the number of antenna ports of the network device or the terminal device comprises one or more of the following: horizontal antenna information, vertical antenna information, or polarization information.

[0039] In some implementations of the second aspect, the method further comprises: sending first indication information, the first indication information indicating the first sub-channel information.

[0040] In some implementations of the second aspect, the method further comprises: receiving second indication information, the second indication information being used to indicate determination of the first sub-channel information.

[0041] In some implementations of the second aspect, the method further includes: receiving second indication information, the second indication information being used to indicate target feature information for data collection.

[0042] In some implementations of the second aspect, the method further includes receiving granularity information.

[0043] In some implementations of the second aspect, receiving or sending first configuration information, the first configuration information including configuration information of a first reference signal; receiving the first reference signal includes: receiving the first reference signal based on the first configuration information.

[0044] For example, if the first reference signal is a downlink reference signal, then the first configuration information is received; if the first reference signal is an uplink reference signal, then the first configuration information is sent.

[0045] In some implementations of the second aspect, the method further includes: sending second feedback information, the second feedback information representing second sub-channel information corresponding to the first channel information.

[0046] In some implementations of the second aspect, the method further includes: receiving or sending second configuration information, the second configuration information indicating N feedback information corresponding to the first channel information corresponding to the feedback first reference signal, where N is a positive integer greater than 1, and the N feedback information includes the first feedback information and the second feedback information.

[0047] For example, if the first reference signal is a downlink reference signal, then the second configuration information is received; if the first reference signal is an uplink reference signal, then the second configuration information is sent.

[0048] Thirdly, a data collection method is provided, which can be executed by a first communication device. The first communication device can be a first device, or a component for the first device (such as a chip or circuit, which can be a modem chip, also known as a baseband chip, or a system-on-a-chip (SoC) or SIP chip containing a modem core, etc.), or a logic module or software capable of implementing some or all of the functions of the first device, etc., and this application does not limit it in this regard.

[0049] The method includes: receiving a first reference signal, the first reference signal being used for channel measurement, the first reference signal corresponding to first sub-channel information of first channel information, the first sub-channel information being a first subset of the first channel information, or the first sub-channel information being the same as channel information obtained based on at least one second subset of the first channel information, the granularity information corresponding to the first sub-channel information being used to describe the granularity of at least one dimension parameter among the dimension parameters of the first channel information; and obtaining the first sub-channel information based on the first reference signal, the first sub-channel information being used for at least one of model monitoring, model training, or model fine-tuning.

[0050] In the technical solution, the first device can collect sub-channel information based on the first reference signal, thereby improving the data collection efficiency and accuracy of channel information in a limited air interface resource scenario. Specifically, the measurement based on the first reference signal in the present application can focus power on part of the space-frequency time position, thereby improving the signal-to-noise ratio of receiving the first reference signal, and further improving the accuracy of channel measurement.

[0051] In some implementations of the third aspect, the first sub-channel information is used for obtaining label data of the model.

[0052] In some implementations of the third aspect, the first channel information is channel information corresponding to the first time unit of the first channel. It can be understood that the first channel is a channel between the network device and the terminal device. For example, the first channel information is used for at least one of input data, output data, and label data of the model.

[0053] In some implementations of the third aspect, the first channel information is used for representing channel information on the first resource, and the subset corresponding to the first sub-channel information is used for representing channel information on the second resource, and the second resource is a subset of the first resource.

[0054] In some implementations of the third aspect, the first resource includes a first frequency domain resource, and the second resource includes a second frequency domain resource, and the second frequency domain resource is a subset of the first frequency domain resource.

[0055] In some implementations of the third aspect, the dimension parameter for describing the first channel information includes one or more of the following: antenna port information of the network device, frequency domain sub-band information corresponding to the first matrix, or antenna port information of the terminal device.

[0056] In some implementations of the third aspect, the dimension parameter for describing the number of antenna ports of the sending device or the terminal device includes one or more of the following: horizontal antenna information, vertical antenna information, or polarization information.

[0057] In some implementations of the third aspect, the method further includes: sending or receiving third configuration information, the third configuration information being determined based on the granularity information, and the third configuration information including configuration information of the first reference signal; and receiving the first reference signal, including receiving the first reference signal based on the configuration information of the first reference signal.

[0058] For example, if the first reference signal is an uplink reference signal, the third configuration information is sent, and if the first reference signal is a downlink reference signal, the third configuration information is received.

[0059] In the above technical solution, since the first sub-channel information corresponding to the first reference signal corresponds to the granular information, the third configuration information (or the configuration information of the first reference signal) in this application can be regarded as being determined based on the granular information.

[0060] In some implementations of the third aspect, the third configuration information also includes indication information of a reference signal mode, where the reference signal mode is a data collection mode.

[0061] In some implementations of the third aspect, before receiving the first reference signal, the method further includes: sending third indication information, the third indication information indicating first reference weight information, the first reference weight information being used to determine the weights and / or resources corresponding to a reference signal whose mode is a data collection mode to be sent subsequently, and the first reference signal being a reference signal of the data collection mode.

[0062] In some implementations of the third aspect, the configuration information of the first reference signal includes first offset information, which is used to indicate the offset information of the weights and / or resources corresponding to the first reference signal relative to the first reference weights in at least one of the time domain, frequency domain, and spatial domain, wherein the weights and / or resources corresponding to the first reference signal are determined based on the first reference weight information and the first offset information.

[0063] The above technical solution provides a specific implementation method for determining the weight or / or resources for transmitting the first reference signal based on the first reference weight information.

[0064] In some implementations of the third aspect, the first reference weight information corresponds to a weight set in at least one dimension of the time domain, frequency domain, and spatial domain, and the configuration information of the first reference signal includes fifth indication information, which indicates at least one weight in at least one weight set corresponding to the first reference weight information. The weight and / or resources corresponding to the first reference signal are determined based on the first reference weight information and the fifth indication information.

[0065] For example, the fifth indication information indicates the identifier or index of at least one weight in at least one weight set corresponding to the first reference signal weight information. Taking the frequency domain dimension as an example, the weight information of the first reference signal in the frequency domain dimension can be determined based on the weight set in the first reference weight information in the frequency domain dimension and the identifier in the fifth indication information corresponding to the weight set in the frequency domain dimension.

[0066] The above technical solution provides another specific implementation method for determining the weight or / or resources for transmitting the first reference signal based on the first reference weight information.

[0067] In some implementations of the third aspect, the third configuration information includes indication information of a reference signal mode, which is either a non-codebook mode or an antenna selection mode.

[0068] In some implementations of the third aspect, the method further includes: receiving fourth indication information, the fourth indication information indicating the first sub-channel information.

[0069] Optionally, the fourth indication information includes the identifier of the first sub-channel information.

[0070] Optionally, the fourth indication information indicates the first sub-channel information using a bitmap. For example, each bit corresponds to one sub-channel information, and different bit values ​​indicate the corresponding sub-channel information. For instance, the bit corresponding to the first sub-channel information is "1", and the bits corresponding to other sub-channel information are "0".

[0071] In the above technical solution, when the reference signal mode is a data collection mode, a non-codebook mode, or an antenna selection mode, the first device can determine whether the first sub-channel information measured based on the first reference signal and the sub-channel information measured in the past can be regarded as the same channel sequence based on the identifier of the sub-channel information corresponding to the first reference signal, thereby enabling the network device to accurately process the sub-channel information estimated multiple times.

[0072] Fourthly, a data collection method is provided, which can be executed by a second communication device. The second communication device can be a second device, or a component for the second device (such as a chip or circuit, which can be a modem chip, also known as a baseband chip, or a system-on-a-chip (SoC) or SIP chip containing a modem core, etc.), or a logic module or software capable of implementing some or all of the functions of the second device, etc., and this application does not limit this.

[0073] The method includes: transmitting a first reference signal, the first reference signal being used for channel measurement, the first reference signal corresponding to a first sub-channel information of first channel information, the first sub-channel information being a first subset of the first channel information, or the first sub-channel information being the same as channel information obtained based on at least one second subset of the first channel information, granularity information corresponding to the first sub-channel information being used to describe the granularity of at least one dimension parameter among the dimension parameters of the first channel information, and the first sub-channel information being used for at least one of model monitoring, model training, or model fine-tuning.

[0074] It is understood that the fourth aspect corresponds to the third aspect mentioned above, and the technical effects and some explanations can be found in the description of the third aspect mentioned above.

[0075] In some implementations of the fourth aspect, the first sub-channel information is used to acquire the model's tag data.

[0076] In some implementations of the fourth aspect, the first channel information is the channel information corresponding to the first channel in the first time unit. It can be understood that the first channel is the channel between the network device and the terminal device. For example, the first channel information is used to obtain at least one of the model's input data, output data, and label data.

[0077] In some implementations of the fourth aspect, the first channel information is used to characterize the channel information on the first resource, and the subset corresponding to the first sub-channel information is used to characterize the channel information on the second resource, wherein the second resource is a subset of the first resource.

[0078] In some implementations of the fourth aspect, the first resource includes a first frequency domain resource, and the second resource includes a second frequency domain resource, wherein the second frequency domain resource is a subset of the first frequency domain resource.

[0079] In some implementations of the fourth aspect, the dimensional parameters describing the first channel information include one or more of the following: antenna port information of the network device, frequency domain sub-band information corresponding to the first channel information, and antenna port information of the terminal device.

[0080] In some implementations of the fourth aspect, the dimensional parameters describing the number of antenna ports of a network device or terminal device include one or more of the following: horizontal antenna information, vertical antenna information, and polarization information.

[0081] In some implementations of the fourth aspect, the method further includes: receiving or sending third configuration information, the third configuration information being determined based on granularity information, the third configuration information including configuration information of the first reference signal; and sending the first reference signal, including: sending the first reference signal based on the configuration information of the first reference signal.

[0082] For example, if the first reference signal is an uplink reference signal, then the third configuration information is received; if the first reference signal is a downlink reference signal, then the third configuration information is sent.

[0083] In some implementations of the fourth aspect, the third configuration information also includes indication information of a reference signal mode, where the reference signal mode is a data collection mode.

[0084] In some implementations of the fourth aspect, before receiving the first reference signal, the method further includes: receiving third indication information, the third indication information indicating first reference weight information, the first reference weight information being used to determine the weights and / or resources corresponding to a reference signal whose mode is a data collection mode to be transmitted subsequently, and the first reference signal being a reference signal of the data collection mode.

[0085] In some implementations of the fourth aspect, the configuration information of the first reference signal includes first offset information, which indicates the offset of the weights and / or resources corresponding to the first reference signal relative to the first reference weight information in at least one of the time domain, frequency domain, and spatial domain, wherein the weights and / or resources corresponding to the first reference signal are determined based on the first reference weight information and the first offset information.

[0086] In some implementations of the fourth aspect, the first reference weight information corresponds to a weight set in at least one dimension of the time domain, frequency domain, and spatial domain, and the configuration information of the first reference signal includes fifth indication information, which indicates at least one weight in at least one weight set corresponding to the first reference weight information. The weight and / or resources corresponding to the first reference signal are determined based on the first reference weight information and the fifth indication information.

[0087] In some implementations of the fourth aspect, the third configuration information includes indication information of a reference signal mode, which is either a non-codebook mode or an antenna selection mode.

[0088] In some implementations of the fourth aspect, the method further includes: sending fourth indication information, which indicates the first sub-channel information.

[0089] Optionally, the fourth indication information includes the identifier of the first sub-channel information.

[0090] Optionally, the fourth indication information indicates the first sub-channel information using a bitmap. For example, each bit corresponds to one sub-channel information, and different bit values ​​indicate the corresponding sub-channel information. For instance, the bit corresponding to the first sub-channel information is "1", and the bits corresponding to other sub-channel information are "0".

[0091] Fifthly, a communication apparatus is provided for performing the methods provided in the first or third aspect. Specifically, the apparatus may include units and / or modules for performing the methods in any of the first or third aspects or any possible implementations of the first or third aspects, such as processing units and / or communication units.

[0092] In one implementation, the device is a first device. When the device is a first device, the communication unit can be a transceiver or an input / output interface; the processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0093] In another implementation, the device is a chip, chip system, or circuit used in the first device. When the device is a chip, chip system, or circuit used in the first device, the communication unit may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; the processing unit may be at least one processor, processing circuit, or logic circuit.

[0094] A sixth aspect provides a communication apparatus for performing the methods provided in the second or fourth aspect. Specifically, the apparatus may include units and / or modules for performing the methods in any of the second or fourth aspects or any possible implementations of the second or fourth aspects, such as processing units and / or communication units.

[0095] In one implementation, the device is a second device. When the device is a second device, the communication unit can be a transceiver or an input / output interface; the processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0096] In another implementation, the device is a chip, chip system, or circuit used in a second device. When the device is a chip, chip system, or circuit used in a second device, the communication unit may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; the processing unit may be at least one processor, processing circuit, or logic circuit.

[0097] A seventh aspect provides a communication device comprising: at least one processor coupled to at least one memory for storing computer programs or instructions, and at least one processor for calling and executing the computer programs or instructions from the at least one memory, such that the communication device performs a method in any of the first or third aspects or any possible implementation of the first or third aspect.

[0098] The aforementioned communication device may be the first device, or the communication module in the first device, or the circuit or chip in the first device responsible for communication functions, or the functional module in the first device capable of calling and executing programs.

[0099] Eighthly, a communication device is provided, the device comprising: at least one processor coupled to at least one memory, the at least one memory for storing computer programs or instructions, and the at least one processor for calling and executing the computer programs or instructions from the at least one memory, such that the communication device performs a method in any of the second or fourth aspects or any possible implementation of the second or fourth aspects.

[0100] The aforementioned communication device may be a second device, or a communication module in the second device, or a circuit or chip in the second device responsible for communication functions, or a functional module in the second device capable of calling and executing programs.

[0101] Ninthly, a processor is provided for executing the methods provided in the foregoing aspects.

[0102] Unless otherwise specified, or if it does not contradict its actual function or internal logic in the relevant description, the transmission and acquisition / reception operations involved in the processor can be understood as processor output and reception, input and other operations, or as transmission and reception operations performed by radio frequency circuits and antennas. This application does not limit them in this regard.

[0103] In a tenth aspect, a computer-readable storage medium is provided that stores program code for execution by a device, the program code including methods for performing any one of the first to fourth aspects or any possible implementation thereof.

[0104] Eleventhly, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to perform any one of the first to fourth aspects and any possible implementation thereof.

[0105] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface, the processor reading instructions stored in a memory through the communication interface and executing any one of the first to fourth aspects or any possible implementation of the first to fourth aspects.

[0106] Optionally, as one implementation, the chip also includes a memory storing computer programs or instructions. The processor is used to execute the computer programs or instructions stored in the memory. When the computer programs or instructions are executed, the processor is used to execute any one of the first to fourth aspects or any possible implementation of the first to fourth aspects.

[0107] In a thirteenth aspect, a communication system is provided, the communication system including at least one of the first device and the second device described above. Attached Figure Description

[0108] Figure 1 is a schematic diagram of a possible application framework in a communication system.

[0109] Figure 2 is a schematic diagram of a possible application framework in a communication system.

[0110] Figure 3 is a schematic diagram of a communication system applicable to an embodiment of this application.

[0111] Figure 4 is a schematic diagram of another communication system applicable to embodiments of this application.

[0112] Figure 5 is a schematic flowchart of a data collection method 500 proposed in this application.

[0113] Figure 6 is a schematic diagram of the first / second channel matrix.

[0114] Figure 7 is a schematic diagram of the submatrices of the first channel matrix at different times.

[0115] Figure 8 is a priority diagram of the submatrices of the first feedback channel matrix.

[0116] Figure 9 is a schematic flowchart of a data collection method 900 proposed in this application.

[0117] Figure 10 is a schematic diagram of sub-channel information determined based on reference signals at different times.

[0118] Figure 11 is a schematic block diagram of a communication device 1100 provided in an embodiment of this application.

[0119] Figure 12 is a schematic block diagram of a communication device 1200 provided in an embodiment of this application.

[0120] Figure 13 is a schematic structural diagram of the chip 30 provided in this application.

[0121] Figure 14 is a schematic diagram of the structure of the AI ​​processor 2100 provided in this application. Detailed Implementation

[0122] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0123] Before introducing the embodiments of this application, the following points should be made first.

[0124] 1. In the description of the embodiments of this application, unless otherwise stated, "a plurality of" means two or more.

[0125] 2. In the various embodiments of this application, unless otherwise specified or logically conflicting, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0126] 3. The various numerical designations used in this application are for descriptive convenience only and are not intended to limit the scope of this application. The order of the serial numbers used in this application does not imply the sequence of execution; the execution order of each process should be determined by its function and internal logic. For example, the terms "first," "second," and "third," as well as various numerical designations (e.g., #1, #2, etc.) in the specification, claims, and drawings of this application are used to distinguish similar objects and are not used to limit the size, content, order, timing, priority, or importance of multiple objects. For example, instruction information #1 and instruction information #2 do not indicate differences in the amount of information, content, priority, or importance.

[0127] 4. The terms “comprising” and “having” and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are expressly listed, but may include other steps or units that are not expressly listed or that are inherent to such process, method, product or device.

[0128] 5. In the embodiments of this application, "network element A sends information A to network element B" can be understood as network element B being the destination of information A or an intermediate network element in the transmission path between the destination and network element B, which may include sending information directly or indirectly to network element B. "Network element B receives information A from network element A" can be understood as network element A being the source of information A or an intermediate network element in the transmission path between the source and network element A, which may include receiving information directly or indirectly from network element A. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be understood in a similar way and will not be elaborated further here.

[0129] In other words, sending and receiving can be done between devices, such as between terminal device #1 and terminal device #2, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via a bus, wiring, or interface.

[0130] 6. In the embodiments of this application, the indication includes direct indication (also known as explicit indication) and implicit indication. Direct indication information A refers to information A; implicit indication information A refers to indicating information A through the correspondence between information A and information B and direct indication information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0131] 7. In the embodiments of this application, information C is used to determine information D, which includes determining information D based solely on information C, and also determining it based on information C and other information. Furthermore, information C can also be used to indirectly determine information D, for example, information D is determined based on information E, and information E is determined based on information C.

[0132] 8. In the embodiments of this application, “when…”, “if” and “if” all refer to the network element making corresponding processing under certain objective circumstances. They are not time limits, nor do they require the network element to make a judgment action when it is implemented, nor do they mean that there are other limitations.

[0133] 9. In the embodiments of this application, "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it can also be understood that determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0134] 10. The arrows or boxes indicated by dashed lines in the schematic diagrams in the accompanying drawings of this application represent optional steps or optional modules.

[0135] The technical solutions provided in this application can be applied to various communication systems, such as: 5th generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, satellite communication systems, future communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0136] The technical solutions provided in this application can be applied to various communication systems, such as: 5th generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, satellite communication systems, future communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0137] In a communication system, a device can send signals to or receive signals from another device. These signals can include information, signaling, or data. The device can also be replaced by an entity, network entity, network element, communication equipment, communication module, node, communication node, etc. This disclosure uses a device as an example. For instance, a communication system can include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device. It is understood that the terminal device in this application can be replaced by a first device, and the network device can be replaced by a second device, both performing the corresponding data collection methods described in this disclosure.

[0138] In the embodiments of this application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user apparatus.

[0139] Terminal devices can be devices that provide voice / data, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving vehicles, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0140] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0141] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be any device capable of supporting the terminal device in implementing those functions, such as a chip system. This device can be installed in or used in conjunction with the terminal device. In this embodiment, the chip system can consist of chips or include chips and other discrete components. This embodiment only uses the terminal device as an example to illustrate the device for implementing the functions of the terminal device, and does not constitute a limitation on the solutions of this embodiment.

[0142] The network device in this application embodiment can be a device for communicating with a terminal device. This network device can also be called an access network device or a wireless access network device, such as a base station. In this application embodiment, the network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, motor slide retainer (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, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, equipment performing base station functions in D2D, V2X, and M2M communications, network-side equipment in 6G networks, and equipment performing base station functions in future communication systems. A base station can support networks using the same or different access technologies. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technologies or equipment forms used in the network equipment.

[0143] In some deployments, the network devices mentioned in the embodiments of this application may be devices including CU, DU, or CU and DU, or devices with control plane CU nodes (central unit-control plane (CU-CP)) and user plane CU nodes (central unit-user plane (CU-UP)) and DU nodes. For example, the network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0144] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio frequency units, such as RRUs, AAUs, or RRHs.

[0145] RAN nodes can support one or more types of fronthaul interfaces, each corresponding to a DU and RU with different functions. If the fronthaul interface between the DU and RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and RU is another type of interface, relative to CPRI, some downlink and / or uplink baseband functions, such as, for downlink, precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix addition (CP), are moved from the DU to the RU; and for uplink, digital beamforming (BF), or one or more of fast Fourier transform (FFT) / cyclic prefix removal (CP), are moved from the DU to the RU. In one possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the segmentation between DU and RU differs, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0146] Taking eCPRI Cat A as an example, for downlink transmission, the DU is configured to implement one or more functions before and after layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping), while other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more functions of inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) are moved to the RU. For uplink transmission, the DU is configured to implement one or more functions before and after demapping (i.e., decoding, rate matching de-matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and demapping), while other functions after demapping (e.g., digital BF or one or more functions of fast Fourier transform (FFT) / removing CP) are moved to the RU. It is understandable that the functional descriptions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol, and will not be elaborated here.

[0147] In one possible design, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0148] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an open-radio access network (O-RAN) system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0149] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself; it can also be an apparatus capable of supporting the network device in implementing those functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This apparatus can be installed in the network device or used in conjunction with the network device. In this embodiment, the example of a network device being used to implement the functions of a network device is provided only and does not constitute a limitation on the solutions described in this embodiment.

[0150] Network devices and / or terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, or software functions running on dedicated hardware or general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0151] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, leading to increasingly diverse requirements. For example, networks need to support ultra-high speeds, ultra-low latency, and / or massive connectivity. This characteristic makes network planning, network configuration, and / or resource scheduling increasingly complex. Furthermore, as network functions become more powerful, such as supporting higher spectrum levels, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming, and / or supporting beam management, network energy efficiency has become a hot research topic. These new requirements, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation, and efficient operation. To meet these challenges, artificial intelligence technology can be introduced into wireless communication networks to achieve network intelligence.

[0152] To support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0153] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network devices, terminal devices, or core network devices, etc. Alternatively, the AI ​​node can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminal devices, or core network elements, etc.

[0154] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0155] It can also be understood that AI nodes can be independent devices, integrated into the same device to implement different functions, or network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the AI ​​nodes described above. AI nodes can be AI network elements, AI entities, or AI modules.

[0156] Figure 1 illustrates a possible application framework in a communication system. As shown in Figure 1, network elements in the communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more operation, administration, and maintenance (OAM) devices, are equipped with one or more AI modules (only one is shown in Figure 1 for clarity). The access network node can be a single RAN node or can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be equipped with one or more AI modules. Optionally, the CU can be further divided into CU-CP and CU-UP. One or more AI models are configured in the CU-CP and / or CU-UP.

[0157] The AI ​​module is used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., type and / or dimension of input parameters), or output parameters (e.g., type and / or dimension of output parameters). The bias in the activation function can also be referred to as the neural network bias.

[0158] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0159] Figure 2 illustrates a possible application framework in a communication system. As shown in Figure 2, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​modules 117 and 118 shown in Figure 1, used to implement AI-related functions. The RIC includes near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0160] The near real-time RIC is used for model training and inference. For example, it can be used to train an AI model and then use that AI model for inference. The near real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data. Optionally, the near real-time RIC can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the near real-time RIC delivers the inference result to the DU, and the DU sends it to the RU.

[0161] The non-real-time RIC is also used for model training and inference. For example, it can be used to train an AI model and then use that model for inference. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the non-real-time RIC delivers the inference results to the DU, which then forwards them to the RU.

[0162] The near real-time RIC and non-real-time RIC can also be set up as separate network elements. Optionally, the near real-time RIC and non-real-time RIC can also be part of other devices. For example, the near real-time RIC can be set in the RAN node (e.g., in CU, DU), while the non-real-time RIC can be set in the OAM, cloud server, core network device, or other network device.

[0163] Figure 3 is a schematic diagram of a communication system applicable to the data collection method of this application embodiment. As shown in Figure 3, the communication system 100 may include at least one network device, such as network device 110 shown in Figure 3; the communication system 100 may also include at least one terminal device, such as terminal device 120 and terminal device 130 shown in Figure 3. Network device 110 and terminal devices (such as terminal device 120 and terminal device 130) can communicate via a wireless link. The communication devices in this communication system, for example, network device 110 and terminal device 120, can communicate via multi-antenna technology.

[0164] Figure 4 is a schematic diagram of another communication system applicable to the data collection method of this application embodiment. Compared with the communication system 100 shown in Figure 3, the communication system 200 shown in Figure 4 also includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building training datasets or training AI models.

[0165] In one possible implementation, network device 110 can send data related to the training of the AI ​​model to AI network element 140, which then constructs a training dataset and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. AI network element 140 can send the results of operations related to the AI ​​model to network device 110, which then forwards them to the terminal device. For example, the results of operations related to the AI ​​model may include at least one of the following: a trained AI model, model evaluation results, or test results. Exemplarily, a portion of the trained AI model may be deployed on network device 110, and another portion on the terminal device. Alternatively, the trained AI model may be deployed on network device 110. Or, the trained AI model may be deployed on the terminal device.

[0166] It should be understood that Figure 4 is only used as an example of the AI ​​network element 140 being directly connected to the network device 110. In other scenarios, the AI ​​network element 140 can also be connected to a terminal device. Alternatively, the AI ​​network element 140 can be connected to both the network device 110 and a terminal device simultaneously. Alternatively, the AI ​​network element 140 can also be connected to the network device 110 through a third-party network element. This application embodiment does not limit the connection relationship between the AI ​​network element and other network elements.

[0167] AI element 140 can also be set as a module in network devices and / or terminal devices, for example, in network device 110 or terminal device shown in Figure 3.

[0168] It should be noted that Figures 3 and 4 are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 3 and 4. In practical applications, the communication system may include multiple network devices or multiple terminal devices. The embodiments of this application do not limit the number of network devices and terminal devices included in the communication system.

[0169] To facilitate understanding of the solutions in the embodiments of this application, the terms that may be involved in the embodiments of this application are explained below.

[0170] 1. Artificial Intelligence (AI): This refers to enabling machines to learn, accumulate experience, and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and chess. AI can be understood as the intelligence exhibited by machines created by humans. Generally, AI refers to the technology of using computer programs to represent human intelligence. The goals of AI include understanding intelligence by constructing computer programs that demonstrate symbolic reasoning or logical reasoning.

[0171] 2. Reference signal (RS): A known signal provided by the transmitter to the receiver for channel estimation or channel detection.

[0172] For example, the reference signal may include one or more of the following: channel state information reference signal (CSI-RS), synchronizing signal / physical broadcast channel block (SSB), sounding reference signal (SRS), or demodulation reference signal (DMRS).

[0173] For example, if the sending end is a network device and the receiving end is a terminal device, then the reference signal is called the downlink reference signal; otherwise, it is called the uplink reference signal. CSI-RS, SSB, and DMRS can be used as downlink reference signals, while SRS and DMRS can be used as uplink reference signals.

[0174] 3. Port: Also known as an antenna port, an antenna port is a logical concept; there is no direct correspondence between an antenna port and a physical antenna. An antenna port is typically associated with a reference signal, and its meaning can be understood as a transmit / receive interface on the channel through which the reference signal passes. For low frequencies, one antenna port may correspond to one or more physical antennas (a physical antenna can refer to a digital port or an antenna element). These physical antennas jointly transmit the reference signal, and the receiver can treat them as a whole without needing to distinguish between the individual physical antennas.

[0175] 4. Channel Information: Channel information refers to information related to the channel between the first device and the second device (e.g., terminal device and network device), which is information about the path and / or the measured channel obtained by the device through channel measurement.

[0176] For example, channel information can be a channel matrix, a channel eigenvector, or other channel-related data, without limitation.

[0177] For example, channel information can also be called channel state information.

[0178] 5. Channel Matrix: This application applies to the data collection of the channel matrix; therefore, the channel matrix is ​​defined first. The dimensional parameters used to describe the channel matrix include one or more of the following: sampling count, antenna port information of the network device, antenna port information of the terminal device, and frequency domain sub-band information corresponding to the channel between the network device and the terminal device (hereinafter referred to as the first channel). Among these, the antenna port information includes the specific port and the number of ports, and the frequency domain sub-band information includes the specific sub-band and the number of sub-bands.

[0179] Collecting data from the channel matrix can be understood as sampling the first channel at multiple time units. If sampling is performed at P time units, the number of samplings is P. The channel information of the first channel at any time unit can be represented as a channel matrix of dimension (Rx, nSub, Tx), and the channel information of the first channel at N time units can be represented as a channel matrix of dimension (P, Rx, nSub, Tx), where Rx is the number of antenna ports of the terminal device, nSub is the number of frequency domain subbands of the first channel, and Tx is the number of antenna ports of the network device.

[0180] For example, the time unit can be a slot.

[0181] For example, the dimensional parameters used to describe the antenna port information of a network device or terminal device include one or more of the following: horizontal antenna information, vertical antenna information, and polarization information. The horizontal / vertical antenna information includes the specific antenna and the number of antennas, while the polarization information includes the polarization direction and the number of polarizations.

[0182] For example, taking the dimensional parameters of a network device's antenna port information, which include horizontal antenna information, vertical antenna information, and polarization information, the number of antenna ports Tx of the network device can also be described using (number of polarizations, number of vertical antennas, number of horizontal antennas). If the network device's antennas are a non-uniform antenna array, then a correspondence between the non-uniform antenna array and Tx can be defined.

[0183] 6. Channel Eigenvectors: The eigenvectors obtained by mathematically decomposing the channel matrix (such as eigenvalue decomposition or singular value decomposition) are called channel eigenvectors. For example, when performing eigenvalue decomposition on the channel matrix, the resulting eigenvectors can be used for beamforming or signal preprocessing. The signal can be transmitted along the main eigenvector directions of the channel matrix, thereby maximizing the signal-to-noise ratio and optimizing transmission performance.

[0184] Based on the description in the background section, this application proposes a data collection method that can effectively solve the aforementioned technical problems. The data collection method is described in detail below.

[0185] Figure 5 is a schematic flowchart of a data collection method 500 proposed in this application. Method 500 can be executed by a first device and a second device, or by a module and / or device (e.g., a chip or integrated circuit) with corresponding functions installed in the first device and the second device, without limitation.

[0186] The first device can be a network-side device, such as a base station, and the second device can be a terminal-side device, such as a terminal device. Alternatively, the first device can be a terminal-side device, and the second device can be a network-side device.

[0187] Network-side devices can be network devices, modules (such as chips) within network devices, software (such as control subsystems) containing network device functions, or other devices that communicate with network devices.

[0188] The terminal-side device can be a terminal device, a module (such as a chip) in a terminal device, software containing terminal device functions (such as a control subsystem), or other devices that communicate with the terminal device.

[0189] The following explanation uses the first device and the second device as examples. The method includes the following steps.

[0190] S510, the first device sends a first reference signal to the second device. The first reference signal is used for channel measurement and corresponds to first channel information. Correspondingly, the second device receives the first reference signal from the first device.

[0191] For example, if the first device is a network device and the second device is a terminal device, then the first reference signal is a downlink reference signal; if the first device is a terminal device and the second device is a network device, then the first reference signal is an uplink reference signal.

[0192] The first reference signal is used for channel measurement and corresponds to the first channel information. This can also be understood as follows: the first reference signal is used to perform channel measurement on the first channel, which is the channel between the terminal device and the network device. The first channel information is the channel information corresponding to the first reference signal in the first time unit. In other words, performing channel measurement on the first channel based on the first reference signal yields the first channel information, which is the channel information corresponding to the first channel in the first time unit.

[0193] For example, the first channel information can be the first channel matrix, or it can be the first channel eigenvector.

[0194] For example, the dimensional parameters describing the first channel information include one or more of the following: antenna port information of the network device, frequency domain sub-band information corresponding to the first channel information, and antenna port information of the terminal device. Further, the dimensional parameters describing the antenna port information of the terminal device or network device include one or more of the following: horizontal antenna information, vertical antenna information, and polarization information. For descriptions of each parameter in the above dimensional parameters, please refer to the description in Terminology Explanation 5, which will not be repeated here.

[0195] It is understood that the first device and the second device can respectively send and receive the first reference signal based on the configuration information of the first reference signal. For example, the first device sends the first reference signal based on the first configuration information, which includes the configuration information of the first reference signal; correspondingly, the second device receives the first reference signal based on the first configuration information.

[0196] Optionally, the first configuration information also includes configuration information for a second reference signal. The second reference signal is used for channel measurement and corresponds to second channel information. Similar to the first reference signal, it can also be understood that: performing channel measurement on the first channel based on the second reference signal yields a second channel matrix, which represents the channel information of the first channel in the second time unit. Optionally, the second reference signal can also be configured using other configuration information; this application is not limited to a configuration method where the same configuration information corresponds to multiple reference signals.

[0197] For example, the first configuration information can be pre-configured, or it can be sent by the network device to the terminal device, without limitation.

[0198] S520, the second device sends first feedback information to the first device. The first feedback information represents first sub-channel information corresponding to the first channel information. The first sub-channel information is a first subset of the first channel information, or it is determined based on at least one second subset of the first channel information. The granularity information corresponding to the first sub-channel information is used to describe the granularity of at least one dimension parameter in the dimension parameters of the first channel information. The first feedback information is used for at least one of model monitoring, model training, or model fine-tuning. Correspondingly, the first device receives the first feedback information from the second device.

[0199] It is understood that this application provides two methods for determining the first sub-channel information. The first method is to directly use a portion of the first channel information as the first sub-channel information (i.e., the first sub-channel information is a first subset of the first channel information). The second method is to process at least a portion of the first channel information to obtain the first sub-channel information (i.e., the first sub-channel information is determined based on at least one second subset of the first channel information).

[0200] The first sub-channel information is determined based on at least one second subset of the first channel information. This can be understood as the first sub-channel information being a function of at least one second subset of the first channel information, or the first sub-channel information and at least one second subset of the first channel information satisfying a first relationship. For example, the first relationship can be a functional relationship, a vector relationship, or a tabular relationship, etc.

[0201] Furthermore, the granularity information corresponding to the first sub-channel information can be understood as the first sub-channel information satisfying this granularity information, that is, the granularity of the first sub-channel information is the same as the granularity indicated by the granularity information, or in other words, the granularity of the first sub-channel information is the granularity indicated by the granularity information. In this embodiment, since the first sub-channel information is related to the feedback information, the granularity information can also be called feedback granularity information. For example, the feedback granularity information includes frequency domain granularity. If the frequency domain granularity indicated by the feedback granularity information is Q RBs with resource blocks (RBs) as the frequency domain unit, then the first sub-channel information is the channel information of Q RBs, and its frequency domain granularity is consistent with the feedback granularity information; if the frequency domain granularity indicated by the feedback granularity information is S sub-bands with sub-bands as the frequency domain unit, then the first sub-channel information is the channel information of S sub-bands, and its frequency domain granularity is consistent with the feedback granularity information.

[0202] Furthermore, since the first sub-channel information satisfies the feedback granularity information, optionally, the second device can obtain the feedback granularity information before sending the first feedback information. For example, the feedback granularity information on the second device side can be pre-set, or it can be sent by the first device to the second device, or multiple feedback granularities can be predefined, and the first device can select one of the multiple feedback granularities to send to the second device. For example, if the second device is a terminal device, and the feedback granularity information is sent by the first device to the second device (i.e., indicated by the network device to the terminal device), then the feedback granularity information can be carried in the first configuration information or sent in separate or other information.

[0203] Optionally, the second device can divide the first channel information based on feedback granularity information to obtain the subset required to determine the first sub-channel information, and then determine the first sub-channel information based on the two methods for determining the first sub-channel information provided in this application.

[0204] Optionally, the second device can divide the first channel information based on the feedback granularity information to obtain multiple subsets that satisfy the feedback granularity information. Then, the second device can select the desired subset from the multiple subsets to determine the first sub-channel information based on the two methods for determining the first sub-channel information provided in this application.

[0205] In this application, the first channel information is used to characterize the channel information on the first resource, and the subset corresponding to the first sub-channel information is used to characterize the channel information on the second resource, where the second resource is a subset of the first resource. It can be understood that if the first sub-channel information is a first subset, then the corresponding subset here is the first subset; if the first sub-channel information is determined based on at least one second subset, then the corresponding subset here is the second subset.

[0206] Optionally, the first resource includes resources in at least one of the time domain, frequency domain, and spatial domain dimensions, and the second resource has the same dimension as the first resource. For example, the first resource includes a first frequency domain resource, and the second resource includes a second frequency domain resource, where the second frequency domain resource is a subset of the first frequency domain resource.

[0207] Optionally, the second device may feed back the sub-channel information corresponding to the first channel information to the first device in multiple stages. For example, the method may further include: the second device sending second feedback information to the first device, the second feedback information representing the second sub-channel information corresponding to the first channel information. Optionally, the granularity information corresponding to the second sub-channel information is the same as the granularity information corresponding to the first sub-channel information. Alternatively, the feedback granularity information corresponding to the second sub-channel information can be determined using a similar method and process to determining the feedback granularity information corresponding to the first sub-channel information.

[0208] Optionally, the first device can inform the second device of the number of times to send feedback information. For example, further, the method includes: the first device sending second configuration information to the second device, the second configuration information indicating N feedback messages corresponding to the first channel information corresponding to the first reference signal, where N is a positive integer greater than 1. Correspondingly, the second device receives the second configuration information from the first device. It can be understood that the N feedback messages fed back by the second device based on the second configuration information include the aforementioned first and second feedback messages.

[0209] The following examples illustrate the process of determining the first sub-channel information, using the first channel information as the first channel matrix and the first channel feature vector.

[0210] (1) The first channel information is the first channel matrix.

[0211] For example, the dimension parameters describing the first channel matrix include the number of antenna ports Tx of the network device, the number of frequency domain sub-bands nSub corresponding to the first channel information, and the number of antenna ports Rx of the terminal device. That is, the first channel matrix is ​​a channel matrix with dimension (Rx, nSub, Tx), where Rx, nSub, and Tx are all integers greater than or equal to 1.

[0212] For example, the feedback granularity information includes at least one of R_Sub, R_Rx, and R_Tx, where R_Sub indicates that nSub subbands can be equally divided into R_sub sub-parts, R_Rx indicates that Rx terminal device antenna ports can be equally divided into R_Rx sub-parts, and R_Tx indicates that Tx network device antenna ports can be equally divided into R_Tx sub-parts. R_Sub, R_Rx, and R_Tx are all integers greater than or equal to 1.

[0213] For example, if the feedback granularity information includes R_Sub, R_Rx, and R_Tx, the first channel matrix can be split based on this feedback granularity information to obtain multiple sub-matrices (i.e., a subset) with dimensions (Rx / R_Rx, nSub / R_sub, Tx / R_Tx). Each sub-matrix satisfies the feedback granularity information. Referring to Figure 6, the first channel matrix is ​​shown in Figure 6. The feedback granularity information includes R_Sub = 2, R_Rx = 3, and R_Tx = 1. A subset of the first channel matrix after splitting is shown by the dashed box in Figure 6. It can be seen that, according to the given feedback granularity information, the first channel matrix in Figure 6 can be split into 6 sub-matrices. The sub-matrix corresponding to the dashed box in Figure 6 is one of these 6 sub-matrices.

[0214] For example, the feedback granularity information can also include R_Txh and R_Txv, meaning that R_Tx can be further divided into R_Txh and R_Txv for feedback. If the antenna port Tx of the network device is composed of a 2D antenna array of Txh rows and Txv columns, R_Txh indicates that the horizontal dimension of the Txh row antenna can be equally divided into R_Txh sub-parts, and R_Txv indicates that the vertical dimension of the Txv column antenna can be equally divided into R_Txv sub-parts.

[0215] In one possible implementation (hereinafter referred to as the first implementation), the second device can use a sub-matrix of the first channel matrix (i.e., an example of a first subset of the first channel information) as the first sub-channel information, then encode and compress the first sub-channel information, and then send the compressed amount of the first sub-channel information to the first device in the first feedback information.

[0216] In another possible implementation (hereinafter referred to as the second implementation), the second device can obtain the first sub-channel information based on at least one sub-matrix of the first channel matrix (i.e., an example of at least one second subset of the first channel information), then encode and compress the first sub-channel information, and then send the compressed amount of the first sub-channel information to the first device in the first feedback information.

[0217] For example, the two implementation methods described above can use a codebook similar to R16 to encode and compress the information of the first sub-channel.

[0218] Optionally, the first feedback information can represent at least one sub-channel information, and the at least one sub-channel information includes the first sub-channel information. It is understood that the above two implementations are merely examples of how the first feedback information represents a sub-channel information. For example, after the first channel information is split, six sub-matrices are obtained, namely sub-matrices #1 to #6. Based on these six sub-matrices, multiple sub-channel information represented by the feedback information can be obtained. These multiple sub-channel information include sub-channel information #11 to #13, where sub-channel information #11 is sub-matrice #1 of the first channel matrix, sub-channel information #12 is determined based on sub-matrices #2 and #3 of the first channel matrix, and sub-channel information #13 is determined based on sub-matrices #4, #5, and #6 of the first channel matrix.

[0219] Optionally, when air interface resources are sufficient, the second device can feed back all sub-matrices of the first channel matrix based on the first implementation method; when air interface resources are scarce, the second device can feed back some sub-matrices of the first channel matrix based on the first implementation method, or the second device can feed back some or all sub-matrices of the first channel matrix based on the second implementation method, or the second device can feed back some or all sub-matrices of the first channel matrix based on both the first and second implementation methods.

[0220] It can be understood that the first channel matrix is ​​the channel information corresponding to the first channel in the first time unit. In practical scenarios, the second device can obtain the channel matrix corresponding to the first channel in multiple time units based on the corresponding reference signal, such as the second reference signal described in S510. The second reference signal corresponds to the second channel matrix, which is the channel information of the first channel in the second time unit. For example, if the first channel matrix is ​​a channel matrix with dimensions (Rx, nSub, Tx), then the second channel matrix is ​​also a channel matrix with dimensions (Rx, nSub, Tx). The second device can also feed back sub-matrices of the second channel matrix based on the above two implementation methods, which will not be elaborated here.

[0221] To facilitate understanding, the following example illustrates the sub-matrices of the channel matrix corresponding to the first channel across multiple time units, based on the first implementation method. It can be understood that in the first implementation method, the sub-channel information represented by the feedback information is the sub-matrix. As shown in Figure 7, when air interface resources are insufficient, partial sub-matrices of the channel matrix corresponding to the first channel across multiple time units can be fed back. For example, the feedback granularity information includes R_Rx, where R_Rx = Rx. Therefore, for a channel matrix with dimensions (Rx, nSub, Tx) for a single measurement, it can be divided into Rx sub-matrices with dimensions (1, nSub, Tx) based on the feedback granularity information. That is, one sub-matrix corresponds to one terminal device antenna port. As shown in Figure 7, Rx = 4, indicating four terminal device antenna ports, numbered 0, 1, 2, and 3 respectively. Each column includes four cells, which represent the channel matrix corresponding to the first channel in one time unit. Each cell represents a sub-matrix (i.e., one sub-channel information) within this channel matrix, and one sub-matrix corresponds to one antenna port of the terminal device. In the diagram, gray-filled squares represent feedback submatrices, and white squares represent non-feedback submatrices. It can be seen that the diagram shows a total of 6 feedback events for channel information. The first feedback event feeds back the submatrix corresponding to port (0,1) in channel matrix #1; the second feedback event feeds back the submatrix corresponding to port (0,1,2) in channel matrix #2; the third feedback event feeds back the submatrix corresponding to port (2,3) in channel matrix #3; the fourth feedback event feeds back the submatrix corresponding to port 1 in channel matrix #4; the fifth feedback event feeds back the submatrix corresponding to port (0,1) in channel matrix #5; and the sixth feedback event feeds back the submatrix corresponding to port 2 in channel matrix #6.

[0222] It is understandable that, in the case of insufficient air interface resources, different numbers of sub-matrices can be fed back based on the current air interface resource status.

[0223] Based on the above description, when air interface resources are insufficient, some sub-matrices need to be discarded. Therefore, the second device can determine the priority of each feedback sub-matrix in order to determine which sub-matrices to feed back this time.

[0224] Optionally, before the second device sends feedback information, the first device may send indication information #1 corresponding to the feedback information to the second device. Indication information #1 is used to indicate the determination of at least one sub-channel information represented by the feedback information. For example, indication information #1 is used to indicate the target feature information for data collection, or in other words, the feature information that data collection prioritizes. The target feature information for data collection includes one or more of the following: time-domain information, spatial-domain information, and frequency-domain information. For example, spatial-domain information includes antenna port information of network devices and / or terminal devices. For example, frequency-domain information includes sub-band information. An example is given below with reference to Figure 8.

[0225] The first six feedbacks in Figure 8 are the same as in Figure 7. The following explanation, based on Figure 8, explains which submatrices of channel matrix #7 are fed back during the seventh feedback. It can be seen that in the first six feedbacks, the submatrix corresponding to port 0 received feedback 3 times, the submatrix corresponding to port 1 received feedback 4 times, the submatrix corresponding to port 2 received feedback 3 times, and the submatrix corresponding to port 3 received feedback 1 time. As shown in Figure 8, if indication information #1 indicates the temporal characteristics of data collection (i.e., data collection focuses more on the temporal characteristics of the channel), then the submatrix of the port with the most cumulative feedbacks can be given higher priority; that is, the submatrix corresponding to port 1 has the highest priority. If indication information #1 indicates the spatial characteristics of data collection (i.e., data collection focuses more on the feature diversity of the spatial dimension), then the submatrix of the port with the fewest cumulative feedbacks can be given higher priority; for example, the submatrix of port 3 has the highest priority.

[0226] Furthermore, to enable the first device to accurately process the data carried in multiple feedback messages, the second device can send an indication message #2 corresponding to each feedback message to the first device each time feedback occurs. Indication message #2 indicates the identifier or number of at least one sub-channel information represented by the current feedback message. For example, if indication message #2 includes the number of at least one sub-channel information represented by the current feedback message, then the first device can consider sub-matrices with the same sub-channel information number in multiple feedbacks as the same channel sequence, thereby enabling the first device to accurately process multiple feedback data. The numbering of sub-channel information is explained below in conjunction with the first and second channel matrices.

[0227] As described above, for example, the first channel matrix and the second channel matrix can both be channel matrices with dimensions (Rx, nSub, Tx) as shown in Figure 6. Then, the two channel matrices are split based on the feedback granularity information to obtain the same number of submatrices. First, the submatrices with the same position in the two channel matrices are defined to have the same number.

[0228] For example, based on the first implementation, the first device receives first feedback information and third feedback information. The first feedback information is used to characterize the first sub-channel information, which is the sub-matrix numbered 1 in the first channel matrix (i.e., the channel matrix corresponding to the first channel in the first time unit). The third feedback information is used to characterize the third sub-channel information, which is the sub-matrix numbered 1 in the second channel matrix (i.e., the channel matrix corresponding to the first channel in the second time unit). When the second device feeds back the first sub-channel information and the third sub-channel information, it assigns the same number to these two sub-channel information. For example, if the indication information #2 corresponding to the first feedback information indicates that the number of the first sub-channel information is A, then the indication information #2 corresponding to the third feedback information also indicates that the number of the third sub-channel information is A. That is, the first sub-channel information and the third sub-channel information can be regarded as the same channel sequence.

[0229] For example, based on the second implementation, the first feedback information is used to characterize the first sub-channel information, which is determined by sub-matrices numbered 1 and 2 in the first channel matrix, and the first sub-channel information and sub-matrices numbered 1 and 2 in the first channel matrix satisfy the first relationship. The third feedback information is used to characterize the third sub-channel information, which is determined by sub-matrices numbered 1 and 2 in the second channel matrix, and the third sub-channel information and sub-matrices numbered 1 and 2 in the second channel matrix satisfy the first relationship. Then, when the second device feeds back the first sub-channel information and the third sub-channel information, it assigns the same number to these two sub-channel information. For example, if the indication information #2 corresponding to the first feedback information indicates that the number of the first sub-channel information is B, then the indication information #2 corresponding to the third feedback information also indicates that the number of the third sub-channel information is B. For example, the first feedback information is used to characterize the first sub-channel information, which is determined by sub-matrices numbered 1 and 2 in the first channel matrix. The first sub-channel information and sub-matrices numbered 1 and 2 in the first channel matrix satisfy a first relationship. The third feedback information is used to characterize the third sub-channel information, which is determined by sub-matrices numbered 1 and 2 in the second channel matrix. The third sub-channel information and sub-matrices numbered 1 and 2 in the second channel matrix satisfy a second relationship. Although the first and third sub-channel information are both determined based on sub-matrices with the same number in their corresponding channel matrices, the relationships between the sub-channel information and the sub-matrices are different. Therefore, when the second device feeds back the first and third sub-channel information, it assigns different numbers to these two sub-channel information. For example, the indication information #2 corresponding to the first feedback information indicates that the number of the first sub-channel information is B, and the indication information #2 corresponding to the third feedback information indicates that the number of the third sub-channel information is C.

[0230] Taking Figure 8 as an example, since one submatrix corresponds to one antenna port of the second device, the submatrix number fed back in this example can be the port number corresponding to the submatrix. For example, the two submatrix numbers fed back in the first instance are (0,1), the three submatrix numbers fed back in the second instance are (0,1,2), the submatrix numbers fed back in the third instance are (2,3), the one submatrix numbered in the fourth instance is 1, the two submatrix numbers fed back in the fifth instance are (0,1), and the one submatrix numbered in the sixth instance is 2. Among them, the submatrix numbered 0 in the first, second, and fifth instances belongs to channel sequence #1, the submatrix numbered 1 in the first, second, fourth, and fifth instances belongs to channel sequence #2, the submatrix numbered 2 in the second, third, and sixth instances belongs to channel sequence #3, and the submatrix numbered 3 in the third instance belongs to channel sequence #4. For example, the submatrix numbering can be determined by the second device itself. The four cells in each column of Figure 8 can also be numbered A, B, C, and D from top to bottom. The first device does not need to know the correspondence between the submatrix numbering and the specific antenna port. It only needs to determine whether the submatrix of multiple feedbacks can be regarded as a channel sequence based on the numbering of the submatrix (i.e., subchannel information) represented by each feedback information.

[0231] Let's take channel sequence #1 as an example to illustrate the dimension of the channel sequence. Based on the feedback information from the first feedback, the first device can obtain the submatrix numbered 0. Therefore, the dimension of channel sequence #1 is (1, Port, nSub, Tx). Then, based on the feedback information from the second feedback, the first device can obtain the submatrix numbered 0, so the dimension of channel sequence #1 is updated from (1, Port, nSub, Tx) to (2, Port, nSub, Tx). Similarly, based on the feedback information from the fifth feedback, the first device obtains the submatrix numbered 0, so the dimension of channel sequence #1 is updated from (2, Port, nSub, Tx) to (3, Port, nSub, Tx).

[0232] Currently, the channel matrix obtained from each measurement of the first channel has a high dimension, resulting in significant overhead for direct collection and excessive air interface resource consumption. When air interface resources are scarce, it is impossible to promptly report the currently measured channel matrix. Based on the above solution, the terminal device can decompose the channel matrix based on feedback granularity information and report the decomposed sub-matrices, thereby improving the data collection efficiency of the channel matrix in scenarios with limited air interface resources. For example, taking Figure 7 as an example, with the current feedback method, since each feedback requires reporting the entire channel matrix, but due to limited air interface resources, the first six feedbacks will not report any data. However, based on the technical solution proposed in this application, although each feedback cannot report the entire channel matrix, it can report a portion of the corresponding sub-matrices. After six feedbacks, the channel data corresponding to the first channel can also be collected, thereby improving the data collection efficiency of the channel matrix in scenarios with limited air interface resources.

[0233] (2) The first channel information is the first channel feature vector.

[0234] For example, the first device is a network device, the second device is a terminal device, and the dimension parameters describing the first channel feature vector include the number of antenna ports Tx of the network device and the number of frequency domain sub-bands nSub corresponding to the first channel feature vector. That is, the first channel feature vector is a channel feature vector with dimension (nSub, Tx).

[0235] The following is a possible implementation method for determining the first sub-channel information based on the first channel feature vector, including the following steps.

[0236] 1) Determine the first channel feature vector.

[0237] For example, the covariance H*H is calculated based on the channel matrix H in each of the nSub subbands. H Then, average the results within the sub-band (that is, average the channel covariance matrices of all resource elements (REs) within the sub-band), and then calculate the averaged H*H. H Perform eigenvalue decomposition (EVD) to obtain the U matrix U1 of the sub-band; multiply U1 by H to obtain V1, which is the channel feature vector of a sub-band. Perform the above operation on all sub-bands to obtain the channel feature determination for all sub-bands.

[0238] It can be understood that the feature vector of each sub-band is a column vector, and the length of the column vector is equal to the number of antenna ports Tx. The channel feature vectors of all sub-bands can be concatenated together to obtain the first channel feature vector.

[0239] 2) The second device acquires the information of the first sub-channel.

[0240] For example, the feedback granularity information includes R_Sub and / or R_Tx, where R_Sub indicates that nSub subbands can be equally divided into R_sub subparts, and R_Tx indicates that Tx network device antenna ports can be equally divided into R_Tx subparts.

[0241] For example, the feedback granularity information includes R_Sub, where R_Sub = nSub. Then, by partitioning the first channel feature vector based on this feedback granularity information, at least one sub-vector of dimension (1, Tx) can be obtained (i.e., another example of a subset). It can be understood that in this example, one sub-vector is the channel feature vector of one sub-band.

[0242] Optionally, the first sub-channel information is the channel feature vector of one of the nSub sub-bands. For example, the first sub-channel information is sub-band V1.

[0243] Optionally, the first sub-channel information is determined based on the channel feature vectors of a portion of the nSub sub-bands.

[0244] For example, the first sub-channel information is obtained by weighting the channel feature vectors of some sub-bands in nSub sub-bands.

[0245] Example 2: Taking the first sub-channel information corresponding to a sub-band as an example, the first sub-channel information is the sub-band spatial basis matrix W1 generated based on the feature vector V1 of a certain sub-band.

[0246] In one implementation, V1 is projected onto a spatial discrete Fourier transform (DFT) basis, and the top 2L DFT basis vectors are selected as the spatial basis W1 based on the projected energy and / or average energy, where L is a set threshold.

[0247] Example 3: Taking the first sub-channel information corresponding to a sub-band as an example, the first sub-channel information is a sparse matrix W2 generated based on the channel feature vector V1 of a certain sub-band.

[0248] In one implementation, based on the spatial basis W1 obtained in Example 2, W2 = W1 can be obtained. H *V1.

[0249] For example, when providing feedback on W2, W2 can be quantified before being provided back.

[0250] Example 4: Taking the first sub-channel information corresponding to a sub-band as an example, the first sub-channel information is the sub-band spatial basis matrix W1 and sparse matrix W2 generated based on the channel feature vector V1 of a certain sub-band.

[0251] In one implementation, based on the sparse matrix W2 = W1 in Example 3... H From *V1, we know that V1 = W1 * W2, so V1 can be represented by W1 and W2.

[0252] Optionally, the R16 codebook can be used to encode and compress the first sub-channel information. Then, the second device can send the compressed amount of the first sub-channel information to the first device along with the first feedback information.

[0253] It is understandable that the main difference between the first sub-channel information in (2) and the first sub-channel information in (1) lies in the type of sub-channel information. The feedback / indication method of the first sub-channel information in (2) is the same as that of the first sub-channel information in (1), so it will not be repeated here.

[0254] Optionally, the method further includes:

[0255] S530, the first device performs at least one of model monitoring, model training, or model fine-tuning based on the first feedback information.

[0256] For example, the first feedback information can be directly used for the above model operations (i.e., at least one of model monitoring, model training, or model fine-tuning); or, the first sub-channel information can be obtained based on the first feedback information, and then the first sub-channel information can be used for model operations; or, the first feedback information or the first sub-channel information can be processed, and the information obtained after processing can be used for model operations.

[0257] In this application, the information used for model operation can be considered as the model's label data, which refers to data used to determine the accuracy of the model's output. Therefore, the first sub-channel information or the first feedback information can be used to obtain the model's label data.

[0258] In one possible implementation, the first device obtains multiple sub-channel information based on multiple feedback messages, and obtains multiple channel sequences based on the multiple sub-channel information. For example, the multiple channel sequences include channel sequence #1, channel sequence #2, and channel sequence #3. Then, the network device can use channel sequence #1, channel sequence #2, and channel sequence #3 as training data to train the model (i.e., model training), or the network device can use channel sequence #1, channel sequence #2, and channel sequence #3 respectively to verify whether the model can work (i.e., model monitoring). If it cannot work, at least one of the following is performed: retraining the model or fine-tuning the model.

[0259] For example, the model can be a model for channel measurement, a channel compression feedback model, a channel recovery model, or a joint model of channel compression and channel recovery models. For instance, if the model is a channel compression model, the input is channel information, and the output is compressed channel information; if the model is a channel recovery model, the input is compressed channel information, and the output is the recovered, decompressed channel matrix or channel eigenvector.

[0260] Optionally, other devices may also directly or indirectly obtain the first feedback information or the first sub-channel information, or information processed from the first feedback information, from the first device, and perform the above-mentioned model operations based on the obtained information. For example, other devices may be over-the-top (OTT) devices, or the host of an OTT system, or a cloud server, or a data collection device, without limitation.

[0261] Figure 9 is a schematic flowchart of a data collection method 900 proposed in this application. The method 900 can be performed by a first device and a second device, or by a module and / or device (e.g., a chip or integrated circuit) with corresponding functions installed in the first device and the second device, without limitation.

[0262] The first device can be a network-side device, such as a base station, and the second device can be a terminal-side device, such as a terminal device. Alternatively, the first device can be a terminal-side device, and the second device can be a network-side device.

[0263] Network-side devices can be network devices, modules (such as chips) within network devices, software (such as control subsystems) containing network device functions, or other devices that communicate with network devices.

[0264] The terminal-side device can be a terminal device, a module (such as a chip) in a terminal device, software containing terminal device functions (such as a control subsystem), or other devices that communicate with the terminal device.

[0265] The following explanation uses the first device and the second device as examples. The method includes the following steps.

[0266] The method includes the following steps.

[0267] S910, the second device sends a first reference signal to the first device. The first reference signal is used for channel measurement and corresponds to a first sub-channel information of the first channel information. The first sub-channel information is a first subset of the first channel information, or the first sub-channel information is the same as channel information obtained from at least one second subset of the first channel information. The granularity information corresponding to the first sub-channel information is used to describe the granularity of at least one dimension parameter in the dimension parameters of the first channel information. Correspondingly, the first device receives the first reference signal from the second device.

[0268] For example, if the first device is a network device and the second device is a terminal device, then the first reference signal is an uplink reference signal; if the first device is a terminal device and the second device is a network device, then the first reference signal is a downlink reference signal.

[0269] The first reference signal is used for channel measurement. The first reference signal corresponds to the first sub-channel information of the first channel information. It can also be understood as: the first sub-channel information of the first channel information can be obtained by performing channel measurement on the first channel based on the first reference signal. The first channel is the channel between the terminal device and the network device. The first channel information is the channel information corresponding to the first channel in the first time unit.

[0270] In the above description, the first sub-channel information is the same as the channel information obtained from at least one second subset of the first channel information. This can also be understood as the first sub-channel information being a function of at least one second subset of the first channel information, or the first sub-channel information and at least one second subset of the first channel information satisfying a first relationship. For example, the first relationship can be a functional relationship, a vector relationship, or a tabular relationship, etc. For instance, in this embodiment, the first sub-channel information can be seen as the second device transmitting a first reference signal using precoding, and then the first device obtaining it based on the received first reference signal. In this case, precoding achieves preprocessing of the channel information. Expressed as a formula, Y = H * S (where Y is the received signal and S is the reference signal). The second device obtains H based on Y and S. Therefore, if the first reference signal is transmitted through precoding, then Y = H * P * S, where P is the precoding matrix. The first device obtains H * P (i.e., the first sub-channel information) based on Y and S, which is the channel information preprocessed by P.

[0271] It can be seen that the main difference between this method and method 500 is that in method 500, the device receiving the first reference signal obtains the first channel information corresponding to the first channel in the first time unit based on the first reference signal, and then determines the first sub-channel information that satisfies the feedback granularity information based on a subset of the first channel information. In contrast, the channel information obtained by the device receiving the first reference signal in this application can be understood as the first sub-channel information determined by method 500. Simply put, method 500 first obtains the first channel information and then obtains the first sub-channel information based on the first channel information, while this method directly obtains the first sub-channel information based on the first reference signal.

[0272] For example, the first channel information can be the first channel matrix, or it can be the first channel eigenvector.

[0273] For example, the dimension parameters describing the first channel information include one or more of the following: antenna port information of the network device, frequency domain sub-band information corresponding to the first channel matrix, and antenna port information of the terminal device. For example, the dimension parameters describing the antenna port information of the terminal device or network device include one or more of the following: horizontal antenna information, vertical antenna information, and polarization information. For details on the above dimension parameters, please refer to the description in S510; they will not be repeated here.

[0274] In this application, the first channel information is used to characterize the channel information on the first resource, and the subset corresponding to the first sub-channel information is used to characterize the channel information on the second resource, where the second resource is a subset of the first resource. It can be understood that if the first sub-channel information is a first subset, then the corresponding subset here is the first subset; if the first sub-channel information is determined based on at least one second subset, then the corresponding subset here is the second subset.

[0275] Optionally, the first resource includes resources in at least one of the time domain, frequency domain, and spatial domain dimensions, and the second resource has the same dimension as the first resource. For example, the first resource includes a first frequency domain resource, and the second resource includes a second frequency domain resource, where the second frequency domain resource is a subset of the first frequency domain resource.

[0276] It is understood that the first device and the second device can receive and transmit the reference signal respectively based on the configuration information of the first reference signal. For example, the second device transmits the first reference signal based on third configuration information, which includes the configuration information of the first reference signal; correspondingly, the first device receives the first reference signal based on the third configuration information.

[0277] Optionally, the third configuration information can be pre-configured, or it can be sent by the network device to the terminal device; there is no limitation. For example, the network device can determine the third configuration information based on granularity information and then send this third configuration information to the terminal device. Further, for example, the network device can determine the third configuration information based on granularity information and the channel quality of the first channel. For example, the network device predefines multiple granularity information types, and the network device can select one granularity information from among these types based on the channel quality of the first channel, and then determine the third configuration information based on that granularity information.

[0278] Optionally, the third configuration information also includes configuration information for a second reference signal. The second reference signal corresponds to the second sub-channel information of the second channel information. This can also be understood as follows: by performing channel measurements on the first channel based on the second reference signal, the second sub-channel information of the second channel information can be obtained. This second channel information is the channel information of the first channel corresponding to the second time unit. Optionally, the second reference signal can also be configured using other configuration information. This application is not limited to a configuration method where the same configuration information corresponds to multiple reference signals.

[0279] The granularity information corresponding to the first sub-channel information in the above description can be understood as the first sub-channel information satisfying this granularity information. Since the first sub-channel information is obtained based on the first reference signal, and the first reference signal is configured based on the third configuration information, the granularity information in this embodiment can also be called configuration granularity information.

[0280] It is understandable that the configuration granularity information in this method and the feedback granularity information in method 500 can be considered the same information. It is also understandable that the different names are only for distinguishing the function of the corresponding granularity information. For a description of the configuration granularity information, please refer to the description of the feedback granularity information in method 500; it will not be repeated here.

[0281] Optionally, if in uplink transmission, i.e., the first device is a network device, the second device is a terminal device, and the reference signal is an uplink reference signal, the third configuration information may further include indication information of the reference signal mode. The reference signal mode indicated by this indication information may be a conventional reference signal model, or it may be the data collection mode proposed in this application.

[0282] For example, the reference signal mode can be one of the following: codebook mode, non-codebook mode, or antenna selection mode.

[0283] For example, the reference signal is SRS. The network device can determine the SRS configuration information based on the configuration granularity information and channel quality in Table 1. The SRS configuration information includes the SRS mode. For example, the channel quality in Table 1 is represented by the signal-to-noise ratio (SNR). A high SNR can mean that the SNR is greater than or equal to a preset threshold V1, and a low SNR can mean that the SNR is less than or equal to a preset threshold V2, where V1 is greater than or equal to V2. The specific values ​​of V1 and V2 are not limited in this application.

[0284] Table 1

[0285] The following section uses SRS as the reference signal and provides a brief description of the various reference signal modes mentioned above.

[0286] 1) Codebook Mode: The basic design principle of uplink transmission based on codebook mode is that the network device determines the precoding information for uplink transmission. This precoding information can include the number of layers (rank) and the corresponding precoding matrix. To select a suitable precoding information, the network device can probe the wireless channel from the terminal's antenna port to the network-side receiving antenna. To enable channel probership, terminal devices using codebook-based Physical Uplink Shared Channel (PUSCH) transmission often need to be configured with a multi-port SRS. By measuring the SRS, the network device can probe the channel and, based on the probe results, further determine the appropriate number of layers and the corresponding precoding matrix. Upon receiving the SRS resource indicator (SRI) from the network device, the terminal device determines which beams are used for PUSCH transmission. Simultaneously, based on the received precoding information, the terminal device decides how to transmit uplink data on these beams selected by the SRI.

[0287] When transmitting codebooks uplink, SRS does not use the precoding matrix, while PUSCH does. When a terminal device is configured to use SRS as codebook, the terminal device can only be configured with a maximum of two resource sets. The SRI and the Precoding Matrix Indicator (PMI) are needed to jointly indicate the port and codebook on the terminal device side.

[0288] 2) Non-codebook mode: Codebook-based uplink transmission involves the network measuring uplink reference signals and informing the terminal how to perform precoding. Non-codebook-based precoding, on the other hand, involves the terminal measuring downlink signals to obtain precoding information. The terminal device obtains M precoding directions based on the downlink reference signals, and transmits M SRSs in each of these directions. The network device measures these M SRS reference signals and selects N SRSs accordingly. It then sends the identifiers (IDs) of these N SRS reference signals to the terminal device via SRI to indicate the N precoding directions corresponding to these SRS reference signals. The terminal device determines the precoding matrix to use when performing PUSCH based on these N precoding directions.

[0289] 3) Antenna Selection Mode: The number of receive and transmit antennas for different terminal devices can be determined by the capabilities of the terminal devices. Common combinations include 1 transmit antenna and 2 receive antennas, 1 transmit antenna and 4 receive antennas, 2 transmit antennas and 4 receive antennas, etc., meaning the number of receive and transmit antennas for a terminal device is generally not equal. In this mode, in order to obtain downlink channel state information (CSI), the network device can allow the terminal device to switch different antenna ports to transmit SRS. The Usage configuration for this type of SRS Resource Set is antenna switching, which can also be called antenna selection.

[0290] 4) Data Collection Mode: The data collection mode proposed in this application differs from the non-codebook mode in that the network device measures the M SRS reference signals, selects N SRS from them, and sends the IDs of these N SRS reference signals to the terminal device via SRI to indicate the N precoding directions corresponding to these N SRS reference signals. The terminal device determines the precoding matrix to be used when transmitting the next SRS based on these N precoding directions. Based on the data collection mode, the channel sub-matrix in the precoding directions with higher signal-to-noise ratio can be obtained.

[0291] Optionally, the reference signal mode is a data collection mode. Before sending the first reference signal, the method further includes: receiving indication information #3 from the network device, whereby indication information #3 indicates first reference weight information. The first reference weight information is used to determine the weights and / or resources corresponding to the reference signal whose reference signal mode is data collection mode to be sent subsequently. It can be understood that the third configuration information includes the configuration information of the first reference signal; therefore, the first reference signal is a reference signal in the data collection mode.

[0292] For example, the first reference weight information corresponds to weight information in at least one dimension of the time domain, frequency domain, and spatial domain. Specifically, the spatial domain weight information indicates the precoding information referenced by the transmitted uplink reference signal; the time domain weight information indicates the time domain position referenced by the transmitted uplink reference signal and the corresponding orthogonal covering codes (OCCs); and the frequency domain weight information indicates the frequency domain position referenced by the transmitted uplink reference signal and the corresponding OCCs.

[0293] One possible implementation is, as mentioned in the explanation of data collection mode terminology, to determine the first reference weight information by configuring M uplink reference signals. For example, if the first reference weight information corresponds to the weight information in the spatial dimension, this spatial dimension weight information can correspond to the M precoding directions corresponding to the M reference signals in the above data collection mode.

[0294] The following example illustrates how to determine the weights and / or resources corresponding to the transmission of the first reference signal based on the first reference weight information.

[0295] Option 1: The configuration information of the first reference signal includes first offset information. The first offset information is used to indicate the offset information of the weights and / or resources corresponding to the first reference signal relative to the first reference weight information in at least one of the time domain, frequency domain, and spatial domain. The weights and / or resources corresponding to the first reference signal are determined based on the first reference weight information and the first offset information.

[0296] The time-domain (or frequency-domain) offset information can be understood as the offset value that needs to be shifted from the time-domain (or frequency-domain) position indicated by the first reference weight information. For example, if the time-domain weight information corresponding to the first reference weight information indicates time slots 3 and 4 in system frame 0, and the time-domain offset information indicated by the first offset information is a frame offset value Δy = 1, then the time-domain resources corresponding to the first reference signal are time slots 3 and 4 in system frame 1 after being shifted based on the time-domain offset information.

[0297] Furthermore, the first reference weight information includes spatial dimension weight information. As mentioned earlier, this spatial dimension weight information can correspond to the M precoding directions corresponding to the M reference signals in the data collection mode described above. Based on the description of the data collection mode, the network device measures M SRS reference signals and selects N SRS signals accordingly. It then sends the IDs of these N SRS reference signals to the terminal device via SRI. For example, in this scheme, the spatial offset information can be understood as the IDs of the selected N reference signals (i.e., the N SRS signals). Based on the IDs of the N reference signals, the terminal device can select N precoding directions corresponding to the N reference signals from the M precoding directions. Subsequently, the terminal device can determine the precoding information used to send the first reference signal (i.e., determine the weight information corresponding to the first reference signal in the spatial dimension) based on these N precoding directions.

[0298] It is understood that this application does not limit the name of the first offset information.

[0299] For example, the first reference weight information corresponds to weight information in the time domain, frequency domain, and spatial domain dimensions. The first offset information is used to indicate the offset information of the weight corresponding to the first reference signal and / or the resource relative to the first reference weight in the time domain, frequency domain, and spatial domain dimensions. Then, the terminal device can determine resource #1 based on the weight information in the time domain and frequency domain dimensions of the first reference weight information and the total time-frequency resources (for example, the weight information in the time domain and frequency domain dimensions of the first reference weight information can be the index of the time domain and frequency domain resources in the total time-frequency resources). Then, the terminal device can determine resource #2 based on resource #1 and the offset information in the time and frequency domains of the first offset information. Resource #2 is the time-frequency resource for transmitting the first reference signal. Additionally, the terminal device can also determine the precoding information used to transmit the first reference signal based on the weight information of the first reference weight information and the offset information in the spatial domain dimension of the first offset information. Correspondingly, the network device receives the first reference signal on resource #2.

[0300] For example, the total time-frequency resources can be the bandwidth that the user can use for data transmission and channel measurement (such as the bandwidth part (BWP)), or it can be the full bandwidth of the communication system (such as the common resource block (CRB)).

[0301] Option 2: The first reference weight information corresponds to a weight set in at least one dimension of the time domain, frequency domain, and spatial domain. The configuration information of the first reference signal includes indication information #5, which indicates at least one weight in at least one weight set corresponding to the first reference weight information. The weight and / or resources corresponding to the first reference signal are determined based on the first reference weight information and indication information #5.

[0302] For example, indication information #5 indicates the identifier or index of at least one weight in at least one weight set corresponding to the first reference signal weight information. Taking the time domain (or frequency domain) dimension as an example, in this scheme, the first reference weight information corresponds to a weight set in the time domain (or frequency domain) dimension, and indication information #5 indicates at least one weight in the weight set in the time domain (or frequency domain) dimension. For example, indication information #5 contains the identifier or index of at least one weight in the weight set in the time domain (or frequency domain) dimension. The terminal device can obtain the corresponding weight information from the corresponding weight set based on the identifier or index, and the terminal device determines the time domain (or frequency domain) resources for transmitting the first reference signal based on the obtained weight information.

[0303] Furthermore, similar to Scheme 1, the first reference weight information corresponds to the weight set in the spatial dimension. This weight set in the spatial dimension consists of the M precoding directions corresponding to the M reference signals in the aforementioned data collection mode. Based on the description of the aforementioned data collection mode, the network device measures the M SRS reference signals and selects N SRS signals accordingly. It then sends the identifiers (IDs) of these N SRS reference signals to the terminal device via SRI. For example, in this scenario, the identifier in the spatial dimension of the indication information #5 can be the IDs of the N uplink reference signals (i.e., the N SRS signals). Based on the IDs of the N uplink reference signals, the terminal device can select the N precoding directions corresponding to the N uplink reference signals from the M precoding directions. Subsequently, the terminal device can determine the precoding information (i.e., the weight information of the first reference signal in the spatial dimension) used to transmit the first reference signal based on these N precoding directions.

[0304] For example, the first reference weight information corresponds to a weight set in at least one dimension of the time domain, frequency domain, and spatial domain. The configuration information of the first reference signal includes indication information #5, which indicates the identifier of at least one weight in the at least one weight set corresponding to the first reference signal weight information. The terminal device determines the weight information of the first reference signal in the time domain dimension based on the weight set in the time domain dimension of the first reference weight information and the identifier in indication information #5 corresponding to the weight set in the time domain dimension, and / or determines the weight information of the first reference signal in the frequency domain dimension based on the weight set in the frequency domain dimension of the first reference weight information and the identifier in indication information #5 corresponding to the weight set in the frequency domain dimension. Then, based on the weight information of the first reference signal in the time domain and frequency domain dimensions and the total resources, resource #3 is determined. Resource #3 is the time-frequency domain resource for the terminal device to transmit the first reference signal. In addition, the terminal device can also determine the weight information of the first reference signal in the spatial domain dimension itself based on the weight set in the spatial domain dimension corresponding to the first reference weight information and the identifier in indication information #5 corresponding to the weight set in the spatial domain dimension. Correspondingly, the network device receives the first reference signal on resource #3.

[0305] S920, the first device determines first sub-channel information based on the first reference signal, and the first sub-channel information is used for at least one of model monitoring, model training or model fine-tuning.

[0306] The following example illustrates the process of determining the first sub-channel information using the first channel information as the first channel matrix.

[0307] For example, the dimension parameters describing the first channel matrix include the number of antenna ports Tx of the network device, the number of frequency domain sub-bands nSub corresponding to the first channel matrix, and the number of antenna ports Rx of the terminal device. That is, the first channel matrix is ​​a channel matrix with dimension (Rx, nSub, Tx).

[0308] For example, the configuration granularity information includes at least one of R_Sub, R_Rx, and R_Tx, where R_Sub indicates that nSub subbands can be equally divided into R_sub sub-parts, R_Rx indicates that Rx terminal device antenna ports can be equally divided into R_Rx sub-parts, and R_Tx indicates that Tx network device antenna ports can be equally divided into R_Tx sub-parts. Referring to Figure 6, the first channel matrix is ​​shown in Figure 6. The configuration granularity information includes R_Sub = 2, R_Rx = 3, and R_Tx = 1. According to the given configuration granularity information, the first channel matrix in Figure 6 can be divided into 6 sub-matrices (i.e., an example of a subset). For example, the first sub-channel information can be one of the 6 sub-matrices, or the first sub-channel information is the same as the channel information obtained from at least one of the 6 sub-matrices.

[0309] For example, the configuration granularity information can also include R_Txh and R_Txv, meaning that R_Tx can be further divided into R_Txh and R_Txv for configuration, that is, the first sub-channel information can also be more fine-grained channel information.

[0310] It can be understood that the first reference signal corresponds to the first sub-channel information of the first channel matrix. The first channel matrix is ​​the channel information of the first channel in the first time unit. In practical applications, the first device can obtain the sub-channel information of the channel information of the first channel in multiple time units based on the corresponding reference signal, such as the second reference signal described in S910. The second reference signal corresponds to the second sub-channel information of the second channel matrix. The second channel matrix is ​​the channel information of the first channel in the second time unit. For example, if the first channel matrix is ​​a matrix with dimension (Rx, nSub, Tx), then the second channel matrix is ​​also a channel matrix with dimension (Rx, nSub, Tx).

[0311] Similar to method 500, in order for the first device to accurately process the multiple sub-channel matrices determined based on multiple reference signals, the first device can first determine which sub-channel information among the multiple sub-channel information can be considered as the same channel sequence. Optionally, the second device can send indication information #4 to the first device. Indication information #4 indicates the identifier or number of the sub-channel information determined based on the current reference signal. Based on indication information #4, the first device can determine which sub-channel information among the sub-channel information determined based on the current reference signal and the historically determined sub-channel information can be considered as the same channel sequence. An example is given below with reference to Figure 10.

[0312] For example, the configuration granularity information includes R_Rx, where R_Rx = Rx. The dimension of the channel matrix corresponding to each time unit is (Rx, nSub, Tx). The sub-channel information obtained by channel measurement based on the reference signal configured with the configuration granularity information is at least one sub-matrix of the corresponding channel matrix, with the dimension of the sub-matrix being (1, nSub, Tx). Optionally, one sub-channel information corresponds to at least one port of the terminal device. For ease of description and understanding, the following example uses one sub-channel information as one sub-matrix. Since one sub-channel information corresponds to one antenna port of the second device in this scenario, the sub-channel information number can be the corresponding antenna port number. The gray squares in Figure 10 represent the sub-channel information obtained by the first device based on different reference signals. In Figure 10, the indication information #4 corresponding to reference signal #1 indicates that the sub-channel information number determined based on reference signal #1 is 0, the indication information #4 corresponding to reference signal #2 indicates that the sub-channel information number determined based on reference signal #2 is 3, and the indication information #4 corresponding to reference signal #3 indicates that the sub-channel information number determined based on reference signal #3 is... 3. The indication information #4 corresponding to reference signal #4 indicates that the sub-channel information determined based on reference signal #4 is numbered 1; the indication information #4 corresponding to reference signal #5 indicates that the sub-channel information determined based on reference signal #5 is numbered 0; and the indication information #4 corresponding to reference signal #6 indicates that the sub-channel information determined based on reference signal #6 is numbered 3. Therefore, based on the indication information #4 corresponding to these reference signals, the first device can know that the sub-matrix with the number 0 corresponding to these reference signals belongs to channel sequence #1, the sub-matrix with the number 1 belongs to channel sequence #2, and the sub-matrix with the number 2 belongs to channel sequence #3. Thus, it can accurately process multiple sub-channel information determined based on multiple reference signals.

[0313] Optionally, since the sub-channel information corresponding to reference information #3 and the sub-channel information corresponding to reference signal #2 are both numbered 3, the indication information #4 corresponding to reference signal #3 may not be sent. The first device assumes that the sub-channel information corresponding to reference information #3 and the sub-channel information corresponding to reference signal #2 belong to the same channel sequence.

[0314] For example, the indication information #4 can also use 1 bit to indicate whether the sub-channel information fed back this time can be regarded as the same channel sequence as the sub-channel information fed back previously. For example, 0 indicates that the sub-channel information fed back this time can be regarded as the same channel sequence as the sub-channel information fed back previously, 1 indicates that the sub-channel information fed back this time cannot be regarded as the same channel sequence as the sub-channel information fed back previously, and vice versa.

[0315] For example, indication information #4 can be indicated using E bits. For instance, if E=3, then a maximum of 8 different sub-channel information can be indicated; and if E=2, then a maximum of 4 different sub-channel information can be indicated.

[0316] For example, when the reference signal is an uplink reference signal, the following explains whether to send indication information #4, depending on the situation.

[0317] 1) If the reference signal mode is codebook mode, and the network device knows the port on which the terminal device sends the reference signal, then based on the known information, the network device can determine which sub-channel information among the multiple sub-channel information determined by multiple uplink reference signals can be regarded as the same channel sequence. Therefore, the terminal device does not need to send indication information #4.

[0318] 2) If non-codebook mode or data collection mode is used, since the spatial weight information used by the terminal device to send the reference signal can be determined by itself, the change of the spatial weight used may cause the first sub-channel information estimated by the network device to be different, and the network device may not know the weight information. Therefore, the terminal device can send indication information #4.

[0319] 3) If antenna selection mode is used, since the network device may not know which antenna port the terminal device selects each time to send the uplink reference signal, the terminal device can send indication information #4.

[0320] Optionally, the method further includes:

[0321] S930, the first device performs at least one of model monitoring, model training, or model fine-tuning based on the first sub-channel information.

[0322] For example, the first sub-channel information can be directly used for the above model operations (i.e., at least one of model monitoring, model training, or model fine-tuning); or, the first sub-channel information can be processed and the processed information can be used for model operations.

[0323] In this application, the information used for model operations can be considered as the model's label data, which refers to data used to determine the accuracy of the model's output. Therefore, the first sub-channel information can be used to obtain the model's label data.

[0324] In one possible implementation, the first device obtains multiple channel sequences based on multiple sub-channel information obtained multiple times. For example, the multiple channel sequences include channel sequence #1, channel sequence #2, and channel sequence #3. Then, the network device can use channel sequence #1, channel sequence #2, and channel sequence #3 as training data to train the model (i.e., model training). Alternatively, the network device can use channel sequence #1, channel sequence #2, and channel sequence #3 respectively to verify whether the model can work (i.e., model monitoring). If it cannot work, at least one of the following is performed: retraining the model or fine-tuning the model.

[0325] For example, the model can be a model for channel measurement, a channel compression feedback model, a channel recovery model, or a joint model of channel compression and channel recovery models. For instance, if the model is a channel compression model, the input is channel information, and the output is compressed channel information; if the model is a channel recovery model, the input is compressed channel information, and the output is the recovered, decompressed channel matrix or channel eigenvector.

[0326] Optionally, other devices may also directly or indirectly obtain the first feedback information or the first sub-channel information, or information processed from the first feedback information, from the first device, and perform the above-mentioned model operations based on the obtained information. For example, other devices may be over-the-top (OTT) devices, or the host of an OTT system, or a cloud server, or a data collection device, without limitation.

[0327] Based on the above scheme, the reference signal transmitted by the second device can support the first device in collecting sub-channel information based on the received reference signal, thereby improving the efficiency and accuracy of channel information data collection in scenarios with limited air interface resources. Specifically, the reference signal transmitted in this method can focus power on a portion of the spatial frequency time position, thereby improving the signal-to-noise ratio of the received reference signal and thus improving the accuracy of channel estimation.

[0328] It is understood that the data collection method proposed in this application is not limited to data collection of channel matrices, but can also be applied to data collection of other types of matrices besides channel matrices, such as received signal matrices or transmitted signal matrices, and this application does not limit this. The dimensional parameters used to describe the received signal matrix also include information about the receiving antenna and / or subcarriers.

[0329] It is understood that the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0330] It is also understood that the above embodiments are mainly illustrated using devices in existing network architectures as examples. It is understood that the specific form of the device is not limited in the embodiments of this application. For example, any device that can achieve the same function in the future is applicable to the embodiments of this application.

[0331] It is understood that in the above-described method embodiments, the methods and operations implemented by the device (such as the first device and the second device mentioned above) can also be implemented by components of the device (such as chips or circuits).

[0332] The method provided by the embodiments of this application has been described in detail above with reference to Figures 1 to 10. The above method is mainly described from the perspective of the interaction between the first device and the second device. It can be understood that, in order to realize the above functions, the first device and the second device include hardware structures and / or software modules corresponding to perform each function.

[0333] Those skilled in the art will recognize that, based on the units and algorithm steps described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is implemented in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0334] The communication device provided in the embodiments of this application will be described below with reference to Figures 11 and 12. It is understood that the description of the device embodiments corresponds to the description of the method embodiments; therefore, for details not described in detail, please refer to the above method embodiments. For brevity, some details will not be repeated. The embodiments of this application can divide the device into functional modules according to the above method examples. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated modules can be implemented in hardware or as software functional modules. It should be noted that the module division in the embodiments of this application is illustrative and only represents one logical functional division; other division methods may exist in actual implementation. The following description uses the division of functional modules according to each function as an example.

[0335] The method provided in this application has been described in detail above. The communication device provided in this application is described below. In one possible implementation, the device is used to implement the steps or processes corresponding to the second device in the above method embodiments. In another possible implementation, the device is used to implement the steps or processes corresponding to the first device in the above method embodiments.

[0336] Figure 11 is a schematic block diagram of a communication device 1100 provided in an embodiment of this application. As shown in Figure 11, the device 1100 may include a communication unit 1110 and a processing unit 1120. The communication unit 1110 can communicate with the outside world, and the processing unit 1120 is used to perform control or processing functions. The communication unit 1110 may also be referred to as a communication interface or a transceiver unit.

[0337] In one possible design, the device 1100 can implement the steps or processes corresponding to those performed by the first device in the above method embodiments, wherein the processing unit 1120 is used to perform processing-related operations of the first device in the above method embodiments, and the communication unit 1110 is used to perform transmission-related operations of the first device in the above method embodiments.

[0338] In another possible design, the device 1100 can implement the steps or processes corresponding to those performed by the second device in the above method embodiments, wherein the communication unit 1110 is used to perform the receiving-related operations of the second device in the above method embodiments, and the processing unit 1120 is used to perform the processing-related operations of the second device in the above method embodiments.

[0339] It is understood that the device 1100 here is embodied in the form of a functional unit. The term "unit" here may refer to an application-specific integrated circuit (ASIC), electronic circuitry, a processor (e.g., a shared processor, a proprietary processor, or a group processor, etc.) and memory for executing one or more software or firmware programs, combined logic circuitry, and / or other suitable components that support the described functions.

[0340] The apparatus 1100 of each of the above-described schemes has the function of implementing the corresponding steps performed by the device in the above-described methods. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions; for example, a communication unit can be replaced by a transceiver (e.g., the transmitting unit in the communication unit can be replaced by a transmitter, and the receiving unit in the communication unit can be replaced by a receiver), and other units, such as processing units, can be replaced by a processor, each executing the transmission and reception operations and related processing operations in each method embodiment.

[0341] Furthermore, the aforementioned communication unit can also be a transceiver circuit (e.g., it may include a receiving circuit and a transmitting circuit), and the processing unit can be a processing circuit. In the embodiments of this application, the device in FIG11 can be the device in the foregoing embodiments, or it can be a chip or a chip system, such as a system on chip (SoC). The communication unit can be an input / output circuit or a communication interface; the processing unit is a processor, microprocessor, or integrated circuit integrated on the chip. No limitation is made here.

[0342] Figure 12 is a schematic block diagram of a communication device 1200 provided in an embodiment of this application. Optionally, the communication device 1200 may be a chip or a chip system. Optionally, in this application, the chip system may be composed of chips or may include chips and other discrete devices.

[0343] As shown in Figure 12, the communication device 1200 can be used to implement the functions of any device (e.g., the second device, the first device) in the communication system described in the foregoing examples. The communication device 1200 may include at least one processor 2010. Optionally, the processor 2010 is coupled to a memory, which may be located within the device, integrated with the processor, or located outside the device. For example, the communication device 1200 may also include at least one memory 2020. The memory 2020 stores the computer programs, computer programs or instructions, and / or data necessary for implementing any of the above examples; the processor 2010 may execute the computer programs stored in the memory 2020 to complete the methods in any of the above examples.

[0344] The communication device 1200 may also include a communication interface 2030, through which the communication device 1200 can interact with other devices. For example, the communication interface 2030 may be a transceiver, circuit, bus, module, pin, or other type of communication interface. When the communication device 1200 is a chip-based device or circuit, the communication interface 2030 in the device 1200 may also be an input / output circuit, capable of inputting information (or receiving information) and outputting information (or sending information). The processor 2010 may be an integrated processor, microprocessor, integrated circuit, or logic circuit, etc., and the processor can determine the output information based on the input information.

[0345] In one example, when the communication device 1200 is applied to the second device, the processor 2010 can be used to implement the processing function of the second device in the above embodiments, and the communication interface 2030 can be used to implement the sending and receiving function of the second device in the above embodiments.

[0346] In another example, when the communication device 1200 is applied to the first device, the processor 2010 can be used to implement the processing function of the first device in the above embodiments, and the communication interface 2030 can be used to implement the sending and receiving function of the first device in the above embodiments.

[0347] The coupling in this application refers to indirect coupling or communication connection between devices, units, or modules, which can be electrical, mechanical, or other forms, used for information exchange between devices, units, or modules. The processor 2010 may operate in conjunction with the memory 2020 and the communication interface 2030. This application does not limit the specific connection medium between the processor 2010, the memory 2020, and the communication interface 2030.

[0348] Optionally, as shown in Figure 12, the processor 2010, memory 2020, and communication interface 2030 are interconnected via a bus 2040. Optionally, the bus may include buses of the types such as address bus, data bus, and control bus. Furthermore, for ease of illustration, Figure 12 shows one bus 2040, but does not indicate that there is only one bus or only one type of bus.

[0349] Figure 13 is a schematic structural diagram of the chip 30 provided in this application. The chip 30 includes a processing circuit 31 and a communication circuit 32. The processing circuit 31 can be a logic circuit, integrated circuit, etc., and the communication circuit 32 can be an input / output circuit, input / output interface, interface circuit, etc., capable of inputting information (or receiving information) or outputting information (or sending information). The chip 30 can execute the methods performed by the network-side device or the terminal-side device in the various embodiments of this application. The processing circuit 31 can be one or more processors, or all or part of the circuitry used for control or processing in one or more processors. Optionally, the functions on the terminal side or the network side can be deployed in different parts of the chip.

[0350] It is understood that the processor in the embodiments of this application may be one or more of the following devices, or all or part of the circuitry of the following devices for processing functions: a central processing unit (CPU), a processor for AI, or other general-purpose processors, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0351] For example, the processor used for AI can be one or more of the following: graphics processing unit (GPU), neural processing unit (NPU), tensor processing unit (TPU), and data processing unit (DPU).

[0352] For example, one possible implementation of a processor for AI could be the AI ​​processor 2100 shown in Figure 14.

[0353] Figure 14 is a schematic diagram of the structure of the AI ​​processor 2100 provided in this application. As shown in the figure, the AI ​​processor 2100 may include one or more of the following: an AI core, a digital vision pre-processing (DVPP) module, a task scheduler (TS), an L3 cache, an AI CPU, a control CPU, an L2 cache, a universal serial bus (USB) interface, a network card, a peripheral component interconnect express (PCIe) interface (PCIe is a high-speed serial computer expansion bus standard), a double data rate (DDR) / high bandwidth memory (HBM) interface, a generational input / output (GPIO) / inter-integrated circuit (I2C) bus, etc. It is understood that the specific meanings of these terms are well known to those skilled in the art and will not be elaborated here.

[0354] It is understandable that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0355] For example, the memory in the embodiments of this application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0356] In addition, this application also provides a computer-readable storage medium storing computer instructions, which, when executed on a computer, cause operations and / or processes performed by a first device or a second device in the various method embodiments of this application to be executed.

[0357] This application also provides a computer program product, which includes computer program code or instructions. When the computer program code or instructions are run on a computer, the operations and / or processes performed by the first device or the second device in the various method embodiments of this application are executed.

[0358] Furthermore, this application also provides a chip including processing circuitry. A memory for storing a computer program is provided independently of the chip, and the processing circuitry is used to execute the computer program stored in the memory, such that operations and / or processes performed by a first device or a second device in any method embodiment are performed.

[0359] Furthermore, the chip may also include a communication interface. The communication interface may be an input / output interface or an interface circuit, etc. Furthermore, the chip may also include a memory.

[0360] In addition, this application also provides a communication system, including a first device and a second device as described in the embodiments of this application.

[0361] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0362] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for example, the division of units is merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, the functional units in the various embodiments of this application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0363] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0364] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.

[0365] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A data collection method, characterized in that, include: A first reference signal is transmitted, the first reference signal being used for channel measurement, and the first reference signal corresponding to first channel information; Receive first feedback information, the first feedback information characterizing first sub-channel information corresponding to the first channel information, the first sub-channel information being a first subset of the first channel information, or the first sub-channel information being determined based on at least one second subset of the first channel information, the granularity information corresponding to the first sub-channel information being used to describe the feedback granularity of at least one dimension parameter among the dimension parameters of the first channel information, and the first feedback information being used for at least one of model monitoring, model training, or model fine-tuning.

2. The method according to claim 1, characterized in that, The first feedback information is used to obtain the model's label data.

3. The method according to claim 1 or 2, characterized in that, The first channel information is the channel information corresponding to the first reference signal in the first time unit.

4. The method according to any one of claims 1 to 3, characterized in that, The first channel information is used to characterize the channel information on the first resource, and the subset corresponding to the first sub-channel information is used to characterize the channel information on the second resource, wherein the second resource is a subset of the first resource.

5. The method according to claim 4, characterized in that, The first resource includes a first frequency domain resource, and the second resource includes a second frequency domain resource, wherein the second frequency domain resource is a subset of the first frequency domain resource.

6. The method according to any one of claims 1 to 5, characterized in that, The dimensional parameters describing the first channel information include one or more of the following: antenna port information of the network device, frequency domain sub-band information corresponding to the first channel information, or antenna port information of the terminal device.

7. The method according to claim 6, characterized in that, The dimension parameters describing the number of antenna ports of the network device or the terminal device include one or more of the following: horizontal antenna information, vertical antenna information, or polarization information.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Receive first indication information, which indicates the first sub-channel information.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: Send a second indication message, which is used to indicate the determination of the first sub-channel information.

10. The method according to any one of claims 1 to 8, characterized in that, The method further includes: Send a second instruction message, which is used to indicate the target feature information for data collection.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: Send the granularity information.

12. The method according to any one of claims 1 to 11, characterized in that, The method further includes: Send or receive first configuration information, the first configuration information including configuration information of the first reference signal; The transmission of the first reference signal includes: The first reference signal is sent based on the first configuration information.

13. The method according to any one of claims 1 to 12, characterized in that, The method further includes: Receive second feedback information, which represents the second sub-channel information corresponding to the first channel information.

14. The method according to claim 13, characterized in that, The method further includes: Send or receive second configuration information, the second configuration information indicating N feedback information corresponding to the first channel information corresponding to the first reference signal, where N is a positive integer greater than 1, and the N feedback information includes the first feedback information and the second feedback information.

15. A data collection method, characterized in that, include: Receive a first reference signal, the first reference signal being used for channel measurement, the first reference signal corresponding to first channel information; Send first feedback information, the first feedback information representing the first sub-channel information corresponding to the first channel information, the first sub-channel information being a first subset of the first channel information, or the first sub-channel information being determined based on at least one second subset of the first channel information, the granularity information corresponding to the first sub-channel information being used to describe the feedback granularity of at least one dimension parameter among the dimension parameters of the first channel information, and the first feedback information being used for model monitoring or model training or model fine-tuning.

16. The method according to claim 15, characterized in that, The first feedback information is used to obtain the model's label data.

17. The method according to claim 15 or 16, characterized in that, The first channel information is the channel information corresponding to the first reference signal in the first time unit.

18. The method according to any one of claims 15 to 17, characterized in that, The first channel information is used to characterize the channel information on the first resource, and the subset corresponding to the first sub-channel information is used to characterize the channel information on the second resource, wherein the second resource is a subset of the first resource.

19. The method according to claim 18, characterized in that, The first resource includes a first frequency domain resource, and the second resource includes a second frequency domain resource, wherein the second frequency domain resource is a subset of the first frequency domain resource.

20. The method according to any one of claims 15 to 19, characterized in that, The dimensional parameters describing the first channel information include one or more of the following: antenna port information of the network device, frequency domain sub-band information corresponding to the first channel information, or antenna port information of the terminal device.

21. The method of claim 20, wherein, The dimension parameters describing the number of antenna ports of the network device or the terminal device include one or more of the following: horizontal antenna information, vertical antenna information, or polarization information.

22. The method according to any one of claims 15 to 21, characterized in that, The method further includes: Send a first indication message, which indicates the first sub-channel information.

23. The method according to any one of claims 15 to 22, characterized in that, The method further includes: Receive second indication information, which is used to indicate the determination of the first sub-channel information.

24. The method according to any one of claims 15 to 22, characterized in that, The method further includes: Receive second instruction information, which is used to indicate the target feature information for data collection.

25. The method according to any one of claims 15 to 24, characterized in that, The method further includes: Receive the granularity information.

26. The method of any one of claims 15-25, wherein, The method further includes: Send or receive first configuration information, the first configuration information including configuration information of the first reference signal; Receiving the first reference signal includes: The first reference signal is received based on the first configuration information.

27. The method according to any one of claims 15 to 26, characterized in that, The method further includes: Send a second feedback message, which represents the second sub-channel information corresponding to the first channel information.

28. The method of claim 27, wherein, The method further includes: Send or receive second configuration information, the second configuration information indicating N feedback information corresponding to the first channel information corresponding to the first reference signal, where N is a positive integer greater than 1, and the N feedback information includes the first feedback information and the second feedback information.

29. A data collection method, characterized by, include: A first reference signal is received, the first reference signal is used for channel measurement, the first reference signal corresponds to a first sub-channel information of the first channel information, the first sub-channel information is a first subset of the first channel information, or the first sub-channel information is the same as the channel information obtained according to at least one second subset of the first channel information, and the granularity information corresponding to the first sub-channel information is used to describe the granularity of at least one dimension parameter in the dimension parameters of the first channel information. The first sub-channel information is obtained based on the first reference signal, and the first sub-channel information is used for at least one of model monitoring, model training, or model fine-tuning.

30. The method according to claim 29, characterized in that, The first sub-channel information is used to obtain the model's label data.

31. The method according to claim 29 or 30, characterized in that, The first channel information is the channel information corresponding to the first channel in the first time unit.

32. The method according to any one of claims 29 to 31, characterized in that, The first channel information is used to characterize the channel information on the first resource, and the subset corresponding to the first sub-channel information is used to characterize the channel information on the second resource, wherein the second resource is a subset of the first resource.

33. The method according to claim 32, characterized in that, The first resource is a first frequency domain resource, and the second resource is a second frequency domain resource, which is a subset of the first frequency domain resource.

34. The method according to any one of claims 29 to 33, characterized in that, The dimensional parameters describing the first channel information include one or more of the following: antenna port information of the network device, frequency domain sub-band information corresponding to the first channel information, or antenna port information of the terminal device.

35. The method according to claim 34, characterized in that, The dimension parameters describing the number of antenna ports of the transmitting device or the terminal device include one or more of the following: horizontal antenna information, vertical antenna information, or polarization information.

36. The method according to any one of claims 29 to 35, characterized in that, The method also includes: Send third configuration information, which is determined based on the granularity information, and includes configuration information for the first reference signal. Receiving the first reference signal includes: The first reference signal is received based on the third configuration information.

37. The method according to claim 36, characterized in that, The third configuration information also includes indication information for a reference signal mode, which is a data collection mode.

38. The method according to claim 37, characterized in that, Before receiving the first reference signal, the method further includes: Send a third indication message, the third indication message indicating a first reference weight information, the first reference weight information being used to determine the weights and / or resources used by the reference signal mode of the data collection mode to be sent subsequently, the first reference signal being the reference signal of the data collection mode.

39. The method according to claim 38, characterized in that, The configuration information of the first reference signal includes first offset information, which is used to indicate the offset information of the weights and / or resources corresponding to the first reference signal relative to the first reference weights in at least one of the time domain, frequency domain, and spatial domain. The weights and / or resources corresponding to the first reference signal are determined based on the first reference weight information and the first offset information.

40. The method according to claim 38, characterized in that, The first reference weight information corresponds to a weight set in at least one dimension of the time domain, frequency domain, and spatial domain. The configuration information of the first reference signal includes fifth indication information, which indicates at least one weight in at least one weight set corresponding to the first reference weight information. The weight and / or resources corresponding to the first reference signal are determined based on the first reference weight information and the fifth indication information.

41. The method according to claim 36, characterized in that, The third configuration information includes indication information of the reference signal mode, which is either a non-codebook mode or an antenna selection mode.

42. The method according to any one of claims 37 to 41, characterized in that, The method further includes: Receive fourth indication information, which includes the identifier of the first sub-channel information.

43. A data collection method, characterized in that, include: A first reference signal is transmitted, the first reference signal being used for channel measurement, the first reference signal corresponding to a first sub-channel information of the first channel information, the first sub-channel information being a first subset of the first channel information, or the first sub-channel information being the same as channel information obtained based on at least one second subset of the first channel information, the granularity information corresponding to the first sub-channel information being used to describe the granularity of at least one dimension parameter in the dimension parameters of the first channel information, and the first sub-channel information being used for at least one of model monitoring, model training, or model fine-tuning.

44. The method according to claim 43, characterized in that, The first sub-channel information is used to obtain the model's label data.

45. The method according to claim 43 or 44, characterized in that, The first channel information is the channel information corresponding to the first channel in the first time unit.

46. ​​The method according to any one of claims 43 to 45, characterized in that, The first channel information is used to characterize the channel information on the first resource, and the subset corresponding to the first sub-channel information is used to characterize the channel information on the second resource, wherein the second resource is a subset of the first resource.

47. The method according to claim 46, characterized in that, The first resource is a first frequency domain resource, and the second resource is a second frequency domain resource, which is a subset of the first frequency domain resource.

48. The method according to any one of claims 43 to 47, characterized in that, The dimensional parameters describing the first channel information include one or more of the following: antenna port information of the network device, frequency domain sub-band information corresponding to the first channel information, or antenna port information of the terminal device.

49. The method according to claim 48, characterized in that, The dimension parameters describing the number of antenna ports of the network device or the terminal device include one or more of the following: horizontal antenna information, vertical antenna information, or polarization information.

50. The method according to any one of claims 43 to 49, characterized in that, The method also includes: Receive or send third configuration information, which is determined based on the granularity information, and includes configuration information of the first reference signal. The transmission of the first reference signal includes: The first reference signal is sent based on the third configuration information.

51. The method according to claim 50, characterized in that, The third configuration information also includes indication information for a reference signal mode, which is a data collection mode.

52. The method according to claim 51, characterized in that, Before sending the first reference signal, the method further includes: Receive third indication information, the third indication information indicating first reference weight information, the first reference weight information being used to determine the weights and / or resources used by the reference signal mode of the data collection mode to be sent subsequently, the first reference signal being the reference signal of the data collection mode.

53. The method according to claim 52, characterized in that, The configuration information of the first reference signal includes first offset information, which is used to indicate the offset information of the weights and / or resources corresponding to the first reference signal relative to the first reference weights in at least one of the time domain, frequency domain, and spatial domain. The weights and / or resources corresponding to the first reference signal are determined based on the first reference weight information and the first offset information.

54. The method according to claim 52, characterized in that, The first reference weight information corresponds to a weight set in at least one dimension of the time domain, frequency domain, and spatial domain. The configuration information of the first reference signal includes fifth indication information, which indicates at least one weight in at least one weight set corresponding to the first reference weight information. The weight and / or resources corresponding to the first reference signal are determined based on the first reference weight information and the fifth indication information.

55. The method according to claim 50, characterized in that, The third configuration information includes indication information of the reference signal mode, which is either a non-codebook mode or an antenna selection mode.

56. The method according to any one of claims 51 to 55, characterized in that, The method further includes: Send a fourth indication message, which includes the identifier of the first sub-channel information.

57. A communication device, characterized in that, It includes modules or units for performing the method of any one of claims 1 to 14, or modules or units for performing the method of any one of claims 15 to 28, or modules or units for performing the method of any one of claims 29 to 42, or modules or units for performing the method of any one of claims 43 to 56.

58. A communication device, characterized in that, The method includes at least one processor, which, through logic circuitry or by executing code instructions, causes the method of any one of claims 1 to 14 to be implemented, or causes the method of any one of claims 15 to 28 to be implemented, or causes the method of any one of claims 29 to 42 to be implemented, or causes the method of any one of claims 43 to 56 to be implemented.

59. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions that, when executed, cause the method as described in any one of claims 1 to 14 to be implemented, or cause the method as described in any one of claims 15 to 28 to be implemented, or cause the method as described in any one of claims 29 to 42 to be implemented, or cause the method as described in any one of claims 43 to 56 to be implemented.

60. A computer program product, characterized in that, Includes a computer program that, when run, causes the method as described in any one of claims 1 to 14 to be implemented, or causes the method as described in any one of claims 15 to 28 to be implemented, or causes the method as described in any one of claims 29 to 42 to be implemented, or causes the method as described in any one of claims 43 to 56 to be implemented.

61. A communication system, characterized in that, Includes at least one of a first device for performing the method as described in any one of claims 1 to 14 and a second device for performing the method as described in any one of claims 15 to 28. or, It includes at least one of a first device for performing the method as described in any one of claims 29 to 42 and a second device for performing the method as described in any one of claims 43 to 56.

Images