Method of communication and communication device

Description

METHOD OF COMMUNICATION AND COMMUNICATION DEVICE

[0001] This application claims priority over Chinese Patent Application No. 202310396390.8, filed with the National Intellectual Property Administration of China on April 6, 2023, and entitled COMMUNICATION METHOD AND COMMUNICATION APPARATUS, which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The modalities of this application relate to the field of communication and, more specifically, to a method of communication and a communication apparatus. BACKGROUND

[0003] In a communication system, a network device needs to determine, based on downlink channel state information (CSI), configuration information related to the downlink channel, such as a feature, a modulation and coding scheme (MCS), and precoding that are used to schedule a downlink data channel to an end device. The end device can calculate the downlink CSI by measuring a downlink reference signal and feed the downlink CSI back to the network device using uplink control information (UCI). In this scenario, the CSI obtained by the network device is usually compressed to a high degree, and the CSI accuracy is low. However, in some scenarios, the network device needs to collect CSI with greater precision or accuracy.For example, in an artificial intelligence (AI)-based CSI feedback scenario, high-precision CSI is used as training data to train an AI model, or high-precision CSI is used as monitoring data to monitor the performance of an AI model. Petition 870250105060, dated 11 / 17 / 2025, page 8 / 204 2 / 188

[0004] Therefore, how to enable the network device to obtain high-precision CSI becomes a problem that needs to be solved urgently. SUMMARY

[0005] The embodiments of this application provide a method of communication and a communication apparatus, to enable a network device to obtain high-precision channel information.

[0006] According to a first aspect, a method of communication is provided. The method may be implemented by a terminal device or may be implemented by a chip or a circuit disposed in a terminal device. This is not limited in this application.

[0007] The method includes: generating first channel information, wherein the first channel information includes K segments, K is an integer greater than 1, the length of each of the K segments is less than or equal to a first threshold, one type of first channel information is field truth channel information, and the first channel information is any of the following: a channel response, a channel eigenvector matrix, a pre-encoding matrix, received reference signal power, or a signal-to-interference-plus-noise ratio; and transmitting part or all of the K pieces of UTI to a network device, wherein the K pieces of UTI respectively include the K segments.

[0008] In the solution in this embodiment of this application, the field truth channel information is divided into a plurality of segments and transmitted using a plurality of UCI chunks, so that the network device can obtain channel information with high feedback overheads, i.e., high-precision channel information.

[0009] The first threshold is related to the maximum code length supported by UCI. Petition 870250105060, dated 11 / 17 / 2025, page 9 / 204 3 / 188

[0010] For example, the first channel information can be obtained by performing scalar quantization on the initial channel information. The initial channel information can be channel information obtained by the terminal device through measurement.

[0011] For example, the first channel information can be obtained by performing codebook-based quantization on the initial channel information.

[0012] With reference to the first aspect, in some implementations of the first aspect, the first threshold is less than or equal to the maximum code length supported by UCI.

[0013] The field truth channel information has high accuracy and, consequently, also has high feedback overheads. Feedback overheads can exceed the maximum code length supported by the UCI. In the solution in this embodiment of this application, the length of each segment can be less than the maximum code length supported by the UCI, so that the segments can be transmitted using a plurality of UCI chunks.

[0014] With reference to the first aspect, in some implementations of the first aspect, the first limit is predefined, or the method also includes: receiving the first indication information from the network device, where the first indication information indicates the first limit.

[0015] With reference to the first aspect, in some implementations of the first aspect, the length of each of the at least K-1 segments of the K segments is equal to the first threshold.

[0016] With reference to the first aspect, in some implementations of the first aspect, the method also includes: receiving a second indication piece of information from the network device, where the second indication piece of information indicates a value of K. Petition 870250105060, dated 11 / 17 / 2025, p. 10 / 204 4 / 188

[0017] the terminal device can segment the first channel information based on the value of K.

[0018] With reference to the first aspect, in some implementations of the first aspect, the method also includes: sending third-party indication information to the network device, where the third-party indication information indicates the lengths of the K segments.

[0019] The lengths of the K segments are the lengths of the K UCI chunks. It can be understood that the lengths of all K UCI chunks can be equal or different. Whether the lengths are equal or different can be specifically predefined in a protocol or determined based on information between the network device and the terminal device. When the lengths of all UCIs are the same, the length can be predefined in a protocol, or the network device and the terminal device can be enabled to learn the length based on information between the network device and the terminal device.When the lengths are different, the length of each of the K UCI chunks can be determined according to a predefined rule in a protocol, or the network device and the terminal device can be enabled to learn a transmitted UCI length based on information exchanged between the network device and the terminal device.

[0020] In some scenarios, the network device does not know the length of the K segments, and the terminal device can notify the network device about the length of each segment, so that the network device can decode each UCI chunk to obtain each segment of the channel information.

[0021] With reference to the first aspect, in some implementations of the first aspect, the method also includes: receiving the first uplink resource configuration information from the network device, where the first Petition 870250105060, dated 11 / 17 / 2025, page 11 / 204 5 / 188 uplink resource configuration information indicates a first uplink resource; and transmitting part or all of the K UCI chunks to the network device includes: transmitting the K UCI chunks to the network device using the first uplink resource.

[0022] For example, the first uplink resource can be distributed in J time resource units, and the time resource unit can be one or a combination of a plurality of slots. The first uplink resource can be considered as J uplink resources. J is a positive integer.

[0023] In this way, the K UCI chunks can be transmitted using the first uplink feature scheduled by the network device at a time, to help improve the efficiency of channel information transmission.

[0024] With reference to the first aspect, in some implementations of the first aspect, the method further includes: receiving second uplink resource configuration information from the network device, where the second uplink resource configuration information indicates a second uplink resource; and transmitting part or all of the K UCI chunks to the network device includes: transmitting part of the K UCI chunks to the network device using the second uplink resource.

[0025] With reference to the first aspect, in some implementations of the first aspect, the transmission of part of the K UCI chunks to the network device using the second uplink feature includes: transmitting part of the K UCI chunks and the fourth indication piece of information to the network device using the second uplink feature, where the fourth indication piece of information indicates at least one of the following: a total length of UCI not transmitted among the K UCI chunks, or if the K UCI chunks include non-transmitted UCI. Petition 870250105060, dated 11 / 17 / 2025, page 12 / 204 6 / 188 transmitted; or when the K-piece UCI portion includes the 1st UCI piece among the K-piece UCIs, the fourth indication information indicates at least one of the following: a total length of the first channel information, a total length of non-transmitted UCI among the K-piece UCIs, or if the K-piece UCIs include non-transmitted UCI.

[0026] For example, when the K UCI chunks include untransmitted UCI, the terminal device can expect the network device to escalate to another uplink resource to transmit the untransmitted UCI among the K UCI chunks.

[0027] For example, the terminal device receives uplink resource configuration information sent by the network device, where the uplink resource configuration information may indicate an uplink resource and indicate that the uplink resource is used to transmit UCI.

[0028] For example, when the K UCI chunks include untransmitted UCI, the terminal device can transmit the remaining untransmitted UCI using one or more other subsequent uplink resources, for example, transmitting the untransmitted UCI among the K UCI chunks using an uplink resource used to transmit uplink data.

[0029] In this mode of solution to this request, the terminal device can request an uplink resource from the network device to transmit an untransmitted segment. This helps to properly utilize uplink resources, to avoid wasting resources.

[0030] With reference to the first aspect, in some implementations of the first aspect, the method also includes: receiving configuration information from the third uplink resource of the network device, where the configuration information from the third uplink resource indicates a Petition 870250105060, dated 11 / 17 / 2025, page 13 / 204 7 / 188 third uplink resource; and transmit indication information to the network device using the third uplink resource, where the indication information indicates a total length of the first channel information.

[0031] With reference to the first aspect, in some implementations of the first aspect, the transmission of part or all of the K UTI pieces to the network device includes: transmitting part or all of the K UTI pieces to the network device using a plurality of uplink resources; and the method further includes: receiving fifth indication information from the network device, where the fifth indication information indicates a quantity of UTI pieces transmitted on each of the plurality of uplink resources.

[0032] For example, the fifth indication information may also indicate specific ITU transmitted in each uplink resource.

[0033] For example, the fifth piece of information may indicate a number of a transmitted segment in each uplink resource, for example, including a number for each transmitted segment, or including one or more of the following: an initial number of a transmitted segment, a number of segments, or an ending number. A portion, not indicated by the fifth piece of information, of one or more items may be obtained in another way, for example, predefined in a protocol. A number for each segment indicates a position of the segment among the K segments.

[0034] For example, the plurality of uplink resources can be understood as uplink resources being scheduled by the network device at a plurality of times.

[0035] For example, uplink resource plurality can be understood as a plurality of periodic uplink resources configured by the device of Petition 870250105060, dated 11 / 17 / 2025, p. 14 / 204 8 / 188 network.

[0036] For example, an uplink resource scheduled by the network device at a given time can be distributed across a plurality of time resource units, and the plurality of time resource units can be used as the plurality of uplink resources.

[0037] With reference to the first aspect, in some implementations of the first aspect, the transmission of part or all of the K UTI pieces to the network device includes: transmitting part or all of the K UTI pieces to the network device using a plurality of uplink resources; and the method also includes: sending sixth indication information to the network device, where the sixth indication information indicates a quantity of UTI pieces transmitted on each of the plurality of uplink resources.

[0038] For example, the sixth indication information may also indicate a specific UCI transmitted on each uplink resource, in other words, indicate a position, among the K segments, of a segment included in the UCI transmitted on each uplink resource.

[0039] For example, the sixth piece of information may indicate a number of a transmitted segment in each uplink resource, for example, including a number for each transmitted segment, or including one or more of the following: an initial number of a transmitted segment, a number of segments, or an ending number. A portion, not indicated by the sixth piece of information, of one or more items may be obtained in another way, for example, predefined in a protocol. A number for each segment indicates a position of the segment among the K segments.

[0040] With reference to the first aspect, in some implementations of the first aspect, the transmission of part or all of the K pieces of UTI to the network device includes: Petition 870250105060, dated 11 / 17 / 2025, p. 15 / 204 9 / 188 transmit part or all of the K pieces of UTI to the network device using a plurality of uplink resources; and the method further includes: sending a seventh indication piece of information to the network device, where the seventh indication piece of information indicates that the plurality of uplink resources correspond to the same first channel information.

[0041] For example, the seventh piece of information includes an identifier carried on an uplink resource. Each uplink resource can contain an identifier, and the identifier is used to distinguish between channel information. If two uplink resources carry the same identifier, the information transmitted using the two uplink resources indicates the same channel information. If two uplink resources carry different identifiers, the information transmitted using the two uplink resources indicates different channel information.

[0042] With reference to the first aspect, in some implementations of the first aspect, the transmission of part or all of the K UCI pieces to the network device includes: transmitting part of the K UCI pieces to the network device; and the method further includes: discarding untransmitted UCI from among the K UCI pieces, where the timing starts from a moment when the transmission of the 1st UCI piece from among the K UCI pieces is greater than or equal to one second threshold.

[0043] For example, a timer is started at the moment of transmission of the 1st UCI segment, and if the timer timing is greater than or equal to the second threshold, the untransmitted UCI among the K UCI segments will be discarded. For example, the moment of transmission of the 1st UCI segment can be a transmission start moment or a transmission end moment of the 1st UCI segment, or another moment that uses the initial transmission moment or the final transmission moment. Petition 870250105060, dated 11 / 17 / 2025, page 16 / 204 10 / 188 of the first UCI segment as a reference, provided that the time can represent the duration of channel information transmission using the UCI. This is not limited in this document.

[0044] If the channel information transmission duration is excessively long, the terminal device may determine that the transmission of channel information #3 has failed and discard a remaining segment. This helps to avoid wasting resources.

[0045] With reference to the first aspect, in some implementations of the first aspect, the transmission of part or all of the K UCI chunks to the network device includes: transmitting part of the K UCI chunks to the network device; and the method further includes: discarding untransmitted UCI from among the K UCI chunks, where the timing that begins from a second channel information transmission moment is greater than or equal to a third threshold, and the first channel information is used to measure the accuracy of the second channel information. For example, the second channel information transmission moment may be an initial transmission moment or a final transmission moment of the second channel, or another moment that uses the initial transmission moment or the final transmission moment of the second channel information as a reference, provided that the moment can represent the duration of the second channel information transmission. This is not limited in this document.

[0046] For example, a timer is started at the time of transmission of the second channel information and, if the timer timing is greater than or equal to the third threshold, the untransmitted UCI among the K UCI pieces is discarded.

[0047] The first channel information is used to measure the accuracy of the second channel information. If an excessively long duration has elapsed since the transmission of the second channel information, the actual channel information may have changed, and it is difficult to measure the current performance. Petition 870250105060, dated 11 / 17 / 2025, page 17 / 204 11 / 188 of a model using the first channel information and the second channel information. The terminal device can determine that the transmission of the first channel information failed and discard a remaining segment. This helps to avoid wasting resources.

[0048] According to a second aspect, a method of communication is provided. The method may be implemented by a terminal device or may be implemented by a chip or a circuit disposed in a terminal device. This is not limited in this application.

[0049] The method includes: generating third channel information based on a first feedback configuration, to allow the total length of the third channel information to be less than or equal to the maximum code length supported by the UCI, where one type of third channel information is field truth channel information; transmitting the first UCI to a network device, where the first UCI includes the third channel information; generating fourth channel information based on a second feedback configuration, where the accuracy of the fourth channel information is less than the accuracy of the third channel information, and one type of fourth channel information is not field truth channel information; and transmitting the second UCI to the network device, where the second UCI includes the fourth channel information.

[0050] According to the solution in this embodiment of this application, when the channel information to be fed back by the terminal device is true field channel information, high-precision channel information is generated using the first feedback configuration, and a channel information length is enabled to be less than or equal to the maximum code length supported by the UCI. In this way, both high-precision channel information and other low-precision channel information can be transmitted using the UCI, to allow the network device to obtain the Petition 870250105060, dated 11 / 17 / 2025, page 18 / 204 12 / 188 high-precision channel information.

[0051] The accuracy of channel information can be indicated by a correlation or an error between channel information and reference channel information.

[0052] A higher correlation between channel information and reference channel information indicates greater accuracy of channel information.

[0053] A smaller error between the channel information and the channel information reference information indicates greater accuracy of the channel information.

[0054] The reference channel information of the channel information may be initial channel information corresponding to the channel information, to be more specific, channel information obtained by the terminal device through measurement.

[0055] With reference to the second aspect, in some implementations of the second aspect, the accuracy of the third channel information is greater than or equal to a fourth threshold.

[0056] With reference to the second aspect, in some implementations of the second aspect, the fourth threshold is predefined, or the method also includes: receiving the eighth indication information from the network device, where the eighth indication information indicates the fourth threshold.

[0057] With reference to the second aspect, in some implementations of the second aspect, a configuration item of the first feedback configuration includes at least one of the following: a sub-band configuration of the third channel information, a layer configuration of the third channel information, a quantization precision configuration in a scalar quantization-based feedback mode, a basis configuration in a codebook-based quantization-based feedback mode, or a non-zero coefficient configuration in a codebook-based feedback mode. Petition 870250105060, dated 11 / 17 / 2025, page 19 / 204 13 / 188 codebook-based quantization.

[0058] With reference to the second aspect, in some implementations of the second aspect, a parameter value of a first configuration item in the first feedback configuration item is based on a range of the first configuration item.

[0059] The terminal device can determine a parameter value for each parameter of the first configuration item within the range of the first configuration item.

[0060] The first configuration item can be any of the following: the sub-band configuration of the third channel information, the layer configuration of the third channel information, the quantization precision configuration in feedback mode based on scalar quantization, the basis configuration in feedback mode based on codebook quantization, or the non-zero coefficient configuration in feedback mode based on codebook quantization.

[0061] With reference to the second aspect, in some implementations of the second aspect, the range of the first configuration item is predefined, or the method also includes: receiving the ninth indication information of the network device, where the ninth indication information indicates the range of the first configuration item.

[0062] With reference to the second aspect, in some implementations of the second aspect, the first configuration item includes at least one of the following: the sub-band configuration of the third channel information, the layer configuration of the third channel information, the quantization precision configuration in feedback mode based on scalar quantization, the basis configuration in feedback mode based on codebook quantization, or the non-zero coefficient configuration in the mode of Petition 870250105060, dated 11 / 17 / 2025, page 20 / 204 14 / 188 feedback based on codebook-based quantization; A sub-band configuration range includes at least one of the following: a range of values ​​for a number of sub-bands of the third channel information, a set of combinations of sub-bands of the third channel information, or a range of values ​​for a granularity of sub-bands of the third channel information; A layer configuration range includes at least one of the following: a range of values ​​for a number of third-channel information layers, or a set of combinations of third-channel information layers; A range of quantization precision settings in feedback mode based on scalar quantization includes a range of quantization precision values ​​in feedback mode based on scalar quantization; A base configuration range in codebook-based quantization feedback mode includes at least one of the following: a range of values ​​indicating a quantity of third channel information bases in codebook-based quantization feedback mode, or a set indicating a combination of third channel information bases in codebook-based quantization feedback mode;or a range of non-zero coefficient configuration in codebook-based quantization feedback mode includes at least one of the following: a range of values ​​indicating a quantity of non-zero coefficients of the third channel information in codebook-based quantization feedback mode, or a range of values ​​indicating the non-zero coefficient quantization precision of the third channel information in codebook-based quantization feedback mode.

[0063] With reference to the second aspect, in some Petition 870250105060, dated 11 / 17 / 2025, page 21 / 204 15 / 188 implementations of the second aspect, the parameter values ​​of a plurality of configuration items in the first feedback configuration are based on a correspondence between the parameter values ​​of the plurality of configuration items in the first feedback configuration.

[0064] With reference to the second aspect, in some implementations of the second aspect, a parameter value of a second configuration item in the first feedback configuration is based on a parameter value of a third configuration item in the first feedback configuration and on the correspondence between the parameter values ​​of the plurality of configuration items in the first feedback configuration, and the third configuration item and the second configuration item belong to the plurality of configuration items.

[0065] The second configuration item can be any of the following: the sub-band configuration of the third channel information, the layer configuration of the third channel information, the quantization precision configuration in feedback mode based on scalar quantization, the basis configuration in feedback mode based on codebook quantization, or the non-zero coefficient configuration in feedback mode based on codebook quantization.

[0066] The third configuration item can be any of the following: the sub-band configuration of the third channel information, the layer configuration of the third channel information, the quantization precision configuration in feedback mode based on scalar quantization, the basis configuration in feedback mode based on codebook quantization, or the non-zero coefficient configuration in feedback mode based on codebook quantization. Petition 870250105060, dated 11 / 17 / 2025, page 22 / 204 16 / 188

[0067] The second configuration item and the third configuration item may be different configuration items.

[0068] For example, the parameter value of the third configuration item can be determined by the terminal device.

[0069] For example, the parameter value of the third configuration item can be determined based on a range of the third configuration item.

[0070] It can be understood that the third configuration item may include the first configuration item.

[0071] With reference to the second aspect, in some implementations of the second aspect, the correspondence between the parameter values ​​of the plurality of configuration items is predefined, or the method also includes: receiving the tenth indication information of the network device, where the tenth indication information indicates the correspondence between the parameter values ​​of the plurality of configuration items.

[0072] With reference to the second aspect, in some implementations of the second aspect, the method also includes: sending eleventh indication information to the network device, where the eleventh indication information indicates parameter values ​​of some or all of the configuration items in the first feedback configuration.

[0073] In some scenarios, the values ​​of some or all configuration item parameters can be determined by the terminal device, and the terminal device can notify the network device about the values ​​of some or all configuration item parameters.

[0074] According to a third aspect, a method of communication is provided. The method may be implemented by a terminal device or may be implemented by a chip or a circuit disposed in a terminal device. This is not limited in this application. Petition 870250105060, dated 11 / 17 / 2025, page 23 / 204 17 / 188

[0075] the method includes: generating fifth channel information, where one type of fifth channel information is field truth channel information; and transmitting the fifth channel information to a network device using upper layer signaling.

[0076] With reference to the third aspect, in some implementations of the third aspect, the upper layer signaling includes a first radio resource control (RRC) message.

[0077] With reference to the third aspect, in some implementations of the third aspect, the first RRC message is still used to transmit sixth channel information, and the fifth channel information is used to measure the accuracy of the sixth channel information.

[0078] With reference to the third aspect, in some implementations of the third aspect, the first RRC message indicates an association relationship between the fifth channel information and the sixth channel information, and the fifth channel information is used to measure the accuracy of the sixth channel information.

[0079] For example, the RRC message may also indicate a UTI transmission moment, including the sixth channel information. The UTI transmission moment may be indicated by an identifier of an ICU transmission slot.

[0080] According to a fourth aspect, a method of communication is provided. The method may be implemented by a first device, or it may be implemented by a chip or circuit disposed within a first device. This is not limited to the application.

[0081] The method includes: sending a first training dataset to a second device, where the first training dataset includes T1 chunks of data from Petition 870250105060, dated 11 / 17 / 2025, page 24 / 204 18 / 188 training, and T1 is a positive integer; and send a second set of training data to a third device, where the second set of training data includes T2 pieces of training data, T2 is a positive integer, the second set of training data and the first set of training data are different subsets of a third set of training data, and the third set of training data is used for model training.

[0082] The second device and the third device are different devices.

[0083] In the solution in this embodiment of this application, the first device divides the third training dataset into a plurality of subsets and transmits the plurality of subsets through a plurality of terminal devices, and a device that receives the plurality of subsets can reassemble the plurality of subsets into a training dataset and perform model training based on the reassembled training dataset. This can avoid severe overheads on the air interface of the terminal devices.

[0084] For example, the first device could be a network device, and the second and third devices could be terminal devices.

[0085] For example, the first device could be a server or cloud server, and the second and third devices could be endpoint devices.

[0086] With reference to the fourth aspect, in some implementations of the fourth aspect, sending the first training dataset to the second device includes: sending the first training dataset and the first piece of information to the second device, where the first piece of information indicates an attribute of the first dataset of Petition 870250105060, dated 11 / 17 / 2025, p. 25 / 204 19 / 188 training.

[0087] With reference to the fourth aspect, in some implementations of the fourth aspect, the first training dataset and the first information are transmitted in different ways or messages.

[0088] With reference to the fourth aspect, in some implementations of the fourth aspect, the attribute of the first training dataset includes at least one of the following: an identifier of the third training dataset, an identifier of the first training dataset, a value of T1, positions of the T1 training data chunks in the third training dataset, a quantity of training data in the third training dataset, a minimum value of a quantity of training data that is in the third training dataset and that is sufficient for training, a time domain attribute of the T1 training data chunks, quantization information from the first training dataset, and quantizer information corresponding to the third training dataset.

[0089] A T1 value is a size of the first training dataset.

[0090] With reference to the fourth aspect, in some implementations of the fourth aspect, the method further includes: receiving the first request information from a fifth device, where the first request message is used to request a fifth training dataset, the fifth training dataset includes T3 pieces of training data, T3 is a positive integer and the fifth training dataset is a subset of the third training dataset.

[0091] The fifth device may be the second or third device. Alternatively, the fifth device may be Petition 870250105060, dated 11 / 17 / 2025, p. 26 / 204 20 / 188 another device different from the second device and the third device.

[0092] With reference to the fourth aspect, in some implementations of the fourth aspect, the first request information may include at least one of the following: the identifier of the third training data set, an identifier of the fifth training data set, identifiers of the T3 training data chunks, or an identifier of the received training data.

[0093] According to a fifth aspect, a method of communication is provided. The method may be implemented by a network device or may be implemented by a chip or circuit disposed within a network device. This is not limited to the application hereof.

[0094] The method includes: receiving part or all of the K UTI pieces from a terminal device, where the K UTI pieces respectively include K segments of first channel information, K is an integer greater than 1, a length of each of the K segments is less than or equal to a first threshold, a type of first channel information is field truth channel information, and the first channel information is any of the following: a channel response, a channel eigenvector matrix, a pre-encoding matrix, received reference signal power, or a signal-to-interference-plus-noise ratio; and obtaining, based on part or all of the K UTI pieces, a segment included in part or all of the K UTI pieces.

[0095] With reference to the fifth aspect, in some implementations of the fifth aspect, the first threshold is less than or equal to the maximum code length supported by the UCI.

[0096] With reference to the fifth aspect, in some implementations of the fifth aspect, the first limit is predefined, or the method also includes: send first Petition 870250105060, dated 11 / 17 / 2025, p. 27 / 204 21 / 188 indication information to the terminal device, where the first indication information indicates the first limit.

[0097] With reference to the fifth aspect, in some implementations of the fifth aspect, the length of each of the at least K-1 segments of the K segments is equal to the first threshold.

[0098] With reference to the fifth aspect, in some implementations of the fifth aspect, the method also includes: sending a second indication information to the terminal device, where the second indication information indicates a value of K.

[0099] With reference to the fifth aspect, in some implementations of the fifth aspect, the method also includes: receiving third indication information from the terminal device, where the third indication information indicates the lengths of the K segments.

[00100] With reference to the fifth aspect, in some implementations of the fifth aspect, the method further includes: sending the first uplink resource configuration information to the terminal device, where the first uplink resource configuration information indicates a first uplink resource; and receiving part or all of the K UTI pieces from the terminal device includes: receiving the K UTI pieces from the terminal device using the first uplink resource.

[00101] With reference to the fifth aspect, in some implementations of the fifth aspect, the method further includes: sending second uplink resource configuration information to the terminal device, where the second uplink resource configuration information indicates a second uplink resource; and receiving part or all of the K UTI pieces from the terminal device includes: receiving part of the K UTI pieces from the terminal device using the second uplink resource. Petition 870250105060, dated 11 / 17 / 2025, p. 28 / 204 22 / 188

[00102] With reference to the fifth aspect, in some implementations of the fifth aspect, receiving the K-piece UCI portion from the terminal device using the second uplink feature includes: receiving the K-piece UCI portion and fourth indication information from the terminal device using the second uplink feature, where the fourth indication information indicates at least one of the following: a total length of untransmitted UCI among the K-piece UCIs, or if the K-piece UCIs include untransmitted UCI; or when the K-piece UCI portion includes the 1st UCI portion among the K-piece UCIs, the fourth indication information indicates at least one of the following: a total length of the first channel information, a total length of untransmitted UCI among the K-piece UCIs, or if the K-piece UCIs include untransmitted UCI.

[00103] With reference to the fifth aspect, in some implementations of the fifth aspect, receiving part or all of the K UTI pieces from the terminal device includes: receiving part or all of the K UTI pieces from the terminal device using a plurality of uplink resources; and the method further includes: sending fifth indication information to the terminal device, where the fifth indication information indicates a quantity of UTI pieces transmitted on each of the plurality of uplink resources.

[00104] With reference to the fifth aspect, in some implementations of the fifth aspect, receiving part or all of the K UTI pieces from the terminal device includes: receiving part or all of the K UTI pieces from the terminal device using a plurality of uplink resources; and the method also includes: receiving the sixth indication information from the terminal device, where the sixth indication information indicates a quantity of UTI pieces transmitted on each of the plurality of uplink resources. Petition 870250105060, dated 11 / 17 / 2025, p. 29 / 204 23 / 188

[00105] With reference to the fifth aspect, in some implementations of the fifth aspect, receiving part or all of the K UTI pieces from the terminal device includes: receiving part or all of the K UTI pieces from the terminal device using a plurality of uplink resources; and the method also includes: receiving the seventh indication information from the terminal device, where the seventh indication information indicates that the plurality of uplink resources corresponds to the same first channel information.

[00106] According to a sixth aspect, a method of communication is provided. The method may be implemented by a network device or may be implemented by a chip or circuit located within a network device. This is not limited to the application.

[00107] The method includes: receiving the first UTI from a terminal device, where the first UTI includes third channel information, the third channel information corresponds to a first feedback configuration and one type of third channel information is true-field channel information; and receiving the second UTI from the terminal device, where the second UTI includes fourth channel information, the fourth channel information corresponds to a second feedback configuration, the accuracy of the fourth channel information is less than the accuracy of the third channel information and one type of fourth channel information is not true-field channel information.

[00108] With reference to the sixth aspect, in some implementations of the sixth aspect, the accuracy of the third channel information is greater than or equal to a fourth threshold.

[00109] With reference to the sixth aspect, in some implementations of the sixth aspect, the fourth threshold is predefined, or the method also includes: sending the eighth indication information to the terminal device, where the eighth indication information Petition 870250105060, dated 11 / 17 / 2025, p. 30 / 204 24 / 188 indicates the fourth threshold.

[00110] With reference to the sixth aspect, in some implementations of the sixth aspect, a configuration item of the first feedback configuration includes at least one of the following: a third-channel information sub-band configuration, a third-channel information layer configuration, a quantization precision configuration in a scalar quantization-based feedback mode, a basis configuration in a codebook-based quantization-based feedback mode, or a non-zero coefficient configuration in a codebook-based quantization-based feedback mode.

[00111] With reference to the sixth aspect, in some implementations of the sixth aspect, a parameter value of a first configuration item in the first feedback configuration item is based on a range of the first configuration item.

[00112] With reference to the sixth aspect, in some implementations of the sixth aspect, the range of the first configuration item is predefined, or the method also includes: sending the ninth indication information to the terminal device, where the ninth indication information indicates the range of the first configuration item.

[00113] With reference to the sixth aspect, in some implementations of the sixth aspect, the first configuration item includes at least one of the following: the sub-band configuration of the third channel information, the layer configuration of the third channel information, the quantization precision configuration in scalar quantization-based feedback mode, the basis configuration in codebook-based quantization-based feedback mode, or the non-zero coefficient configuration in codebook-based quantization-based feedback mode; Petition 870250105060, dated 11 / 17 / 2025, page 31 / 204 25 / 188 a sub-band configuration range includes at least one of the following: a range of values ​​for a number of sub-bands of the third channel information, a set of combinations of sub-bands of the third channel information, or a range of values ​​for a granularity of sub-bands of the third channel information; A layer configuration range includes at least one of the following: a range of values ​​for a number of third-channel information layers, or a set of combinations of third-channel information layers; A range of quantization precision settings in feedback mode based on scalar quantization includes a range of quantization precision values ​​in feedback mode based on scalar quantization; A base configuration range in codebook-based quantization feedback mode includes at least one of the following: a range of values ​​indicating a quantity of third channel information bases in codebook-based quantization feedback mode, or a set indicating a combination of third channel information bases in codebook-based quantization feedback mode;or a range of non-zero coefficient configuration in codebook-based quantization feedback mode includes at least one of the following: a range of values ​​indicating a quantity of non-zero coefficients of the third channel information in codebook-based quantization feedback mode, or a range of values ​​indicating the non-zero coefficient quantization precision of the third channel information in codebook-based quantization feedback mode.

[00114] With reference to the sixth aspect, in some implementations of the sixth aspect, the parameter values ​​of a Petition 870250105060, dated 11 / 17 / 2025, page 32 / 204 26 / 188 The plurality of configuration items in the first feedback configuration is based on a correspondence between the parameter values ​​of the plurality of configuration items in the first feedback configuration.

[00115] With reference to the sixth aspect, in some implementations of the sixth aspect, a parameter value of a second configuration item in the first feedback configuration is based on a parameter value of a third configuration item in the first feedback configuration and on the correspondence between the parameter values ​​of the plurality of configuration items in the first feedback configuration, and the third configuration item and the second configuration item belong to the plurality of configuration items.

[00116] With reference to the sixth aspect, in some implementations of the sixth aspect, the correspondence between the parameter values ​​of the plurality of configuration items is predefined, or the method also includes: sending tenth indication information to the terminal device, where the tenth indication information indicates the correspondence between the parameter values ​​of the plurality of configuration items.

[00117] With reference to the sixth aspect, in some implementations of the sixth aspect, the method also includes: receiving eleventh indication information from the terminal device, where the eleventh indication information indicates parameter values ​​of some or all of the configuration items in the first feedback configuration.

[00118] According to a seventh aspect, a method of communication is provided. The method may be implemented by a network device or may be implemented by a chip or circuit disposed within a network device. This is not limited to the application.

[00119] The method includes: receiving fifth channel information Petition 870250105060, dated 11 / 17 / 2025, p. 33 / 204 27 / 188 of a terminal device using upper-layer signaling, where one type of fifth-channel information is field-true channel information; and perform data processing based on the fifth-channel information or forward the fifth-channel information.

[00120] For example, the fifth channel information can be used for model monitoring.

[00121] In another example, the fifth channel information can be used for model training.

[00122] For example, performing data processing based on the fifth channel information may include: performing model training, model monitoring, or similar based on the fifth channel information.

[00123] For example, routing the fifth channel information might include: routing the fifth channel information to another device with an AI module. The AI ​​module is configured to implement a corresponding AI function, for example, model monitoring or model training.

[00124] With reference to the seventh aspect, in some implementations of the seventh aspect, the upper layer signaling includes an initial RRC message.

[00125] With reference to the seventh aspect, in some implementations of the seventh aspect, the first RRC message is used to transmit sixth channel information, and the fifth channel information is used to measure the accuracy of the sixth channel information.

[00126] With reference to the seventh aspect, in some implementations of the seventh aspect, the first RRC message indicates an association relationship between the fifth channel information and the sixth channel information, and the fifth channel information is used to measure the accuracy of the sixth channel information.

[00127] According to an eighth aspect, a method of Petition 870250105060, dated 11 / 17 / 2025, p. 34 / 204 28 / 188 communication is provided. The method can be implemented by a second device, or it can be implemented by a chip or circuit located in a second device. This is not limited to the application in this case.

[00128] The method includes: receiving a first training dataset from a first device, where the first training dataset includes T1 pieces of training data, and T1 is a positive integer; and sending the first training dataset to a fourth device, to allow the fourth device to train a model based on a fourth training dataset, where the fourth training dataset includes at least the first training dataset and a second training dataset, the first training dataset and the second training dataset are different subsets of a third training dataset, the second training dataset includes T2 pieces of training data, and T2 is a positive integer.

[00129] The second set of training data is transmitted to the fourth device via a third device. The second device and the third device are different devices.

[00130] For example, the first device could be a network device, the second and third devices could be endpoint devices, and the fourth device is a server or a cloud server.

[00131] For example, the first device could be a server or a cloud server, the second and third devices could be endpoint devices, and the fourth device is a network device.

[00132] With reference to the eighth aspect, in some implementations of the eighth aspect, receiving the first set of Petition 870250105060, dated 11 / 17 / 2025, page 35 / 204 29 / 188 training data from the first device also includes: receiving the first training data set and the first information from the first device, where the first information indicates an attribute of the first training data set.

[00133] With reference to the eighth aspect, in some implementations of the eighth aspect, the first training data set and the first information are transmitted in different ways or messages.

[00134] With reference to the eighth aspect, in some implementations of the eighth aspect, the attribute of the first training dataset includes at least one of the following: an identifier of the third training dataset, an identifier of the first training dataset, a value of T1, positions of the T1 training dataset pieces in the third training dataset, a quantity of training data in the third training dataset, a minimum value of a quantity of training data that is in the third training dataset and that is sufficient for training, a time domain attribute of the T1 training dataset pieces, quantization information from the first training dataset, and quantizer information corresponding to the third training dataset.

[00135] With reference to the eighth aspect, in some implementations of the eighth aspect, the method further includes: sending the first request information to the first device, where the first request message is used to request a fifth training data set, the fifth training data set includes T3 pieces of training data, T3 is a positive integer and the fifth training data set is a subset of the third training data set.

[00136] With reference to the eighth aspect, in some Petition 870250105060, dated 11 / 17 / 2025, p. 36 / 204 30 / 188 implementations of the eighth aspect, the first request information may include at least one of the following: the identifier of the third training dataset, an identifier of the fifth training dataset, identifiers of the T3 training data chunks, or a received training data identifier.

[00137] According to a ninth aspect, a communication apparatus is provided. The communication apparatus may be a terminal device, or it may be an apparatus, a module, a circuit, a chip or similar disposed in a terminal device, or it may be an apparatus that can be used in cooperation with a terminal device. In a design, the communication apparatus may include modules that are in one-to-one correspondence with the methods / operations / steps / actions described in any of the first, second, third or eighth aspects. The modules may be hardware or software circuits, or they may be implemented using a hardware circuit in combination with software. In a design, the communication apparatus may include a processing module and a communication module.

[00138] The communication module is configured to perform a sending action in the method described in any of the first, second, third, or eighth aspects. The processing module is configured to perform a processing action in the method described in any of the first, second, third, or eighth aspects.

[00139] According to a tenth aspect, a communication apparatus is provided. The communication apparatus may be a network device, or it may be an apparatus, a module, a circuit, a chip or similar disposed in a network device, or it may be an apparatus that can be used in cooperation with a network device. In a project, the communication apparatus Petition 870250105060, dated 11 / 17 / 2025, page 37 / 204 31 / 188 may include modules that are in one-to-one correspondence with the methods / operations / steps / actions described in any of the fourth, fifth, sixth, or seventh aspects. The modules may be hardware or software circuits, or may be implemented using a hardware circuit in combination with software. In a design, the communication apparatus may include a processing module and a communication module.

[00140] The communication module is configured to perform a receiving action in the method described in any of the four aspects, the fifth aspect, the sixth aspect, or the seventh aspect. The processing module is configured to perform a processing action in the method described in any of the fourth aspect, the fifth aspect, the sixth aspect, or the seventh aspect.

[00141] According to an eleventh aspect, a communication apparatus is provided and includes a processor and a storage medium. The storage medium stores instructions.When instructions are executed by the processor, the method according to any one of the first aspect or the possible implementations of the first aspect is implemented, the method according to any one of the second aspect or the possible implementations of the second aspect is implemented, the method according to any one of the third aspect or the possible implementations of the third aspect is implemented, the method according to any one of the fourth aspect or the possible implementations of the fourth aspect is implemented, the method according to any one of the fifth aspect or the possible implementations of the fifth aspect is implemented, the method according to any one of the sixth aspect or the possible implementations of the sixth aspect is implemented, the method according to any one of the seventh aspect or the possible implementations of the seventh aspect is implemented, or the method of. Petition 870250105060, dated 11 / 17 / 2025, p. 38 / 204 32 / 188 according to any of the eighth aspect or the possible implementations of the eighth aspect is implemented.

[00142] According to a twelfth aspect, a communication device is provided and includes a processor. The processor is configured to process data and / or information, to implement the method according to any of the first aspect or the possible implementations of the first aspect, to implement the method according to any of the second aspect or the possible implementations of the second aspect, to implement the method according to any of the third aspect or the possible implementations of the third aspect, to implement the method according to any of the fourth aspect or the possible implementations of the fourth aspect, to implement the method according to any of the fifth aspect or the possible implementations of the fifth aspect, to implement the method according to any of the sixth aspect or the possible implementations of the sixth aspect, to implement the method according to any of the seventh aspect or the possible implementations of the seventh aspect,or implement the method according to any one of the eighth aspect or possible implementations of the eighth aspect. Optionally, the communication device may include up to a communication interface. The communication interface is configured to receive data and / or information and transmit the received data and / or information to the processor. Optionally, the communication interface is further configured to output data and / or information processed by the processor.

[00143] According to a thirteenth aspect, a chip is provided and includes a processor. The processor is configured to execute a program or instructions, to implement the method according to any of the first aspect or the possible implementations of the first aspect, to implement the method according to any of the second aspect or the possible implementations of the second aspect, to implement the Petition 870250105060, dated 11 / 17 / 2025, p. 39 / 204 33 / 188 method according to any of the third aspect or the possible implementations of the third aspect, implement the method according to any of the fourth aspect or the possible implementations of the fourth aspect, implement the method according to any of the fifth aspect or the possible implementations of the fifth aspect, implement the method according to any of the sixth aspect or the possible implementations of the sixth aspect, implement the method according to any of the seventh aspect or the possible implementations of the seventh aspect, or implement the method according to any of the eighth aspect or the possible implementations of the eighth aspect. Optionally, the chip may also include memory, and the memory is configured to store a program or instructions. Optionally, the chip may even include a transceiver.

[00144] According to a fourteenth aspect, a computer-readable storage medium is provided. The computer-readable storage medium includes instructions.When instructions are executed by a processor, the method according to any one of the first aspect or possible implementations of the first aspect is implemented, the method according to any one of the second aspect or possible implementations of the second aspect is implemented, the method according to any one of the third aspect or possible implementations of the third aspect is implemented, the method according to any one of the fourth aspect or possible implementations of the fourth aspect is implemented, the method according to any one of the fifth aspect or possible implementations of the fifth aspect is implemented, the method according to any one of the sixth aspect or possible implementations of the sixth aspect is implemented, the method according to any one of the seventh aspect or possible implementations of the seventh aspect is implemented, or the method according to any one of the eighth aspect or possible implementations of the seventh aspect is implemented. Petition 870250105060, dated 11 / 17 / 2025, page 40 / 204 34 / 188 implementations of the eighth aspect is implemented.

[00145] According to a fifteenth aspect, a computer program product is provided. The computer program product includes computer program code or instructions. When the computer program code or instructions are executed, the method according to any of the first aspect or possible implementations of the first aspect is implemented, the method according to any of the second aspect or possible implementations of the second aspect is implemented, the method according to any of the third aspect or possible implementations of the third aspect is implemented, the method according to any of the fourth aspect or possible implementations of the fourth aspect is implemented, the method according to any of the fifth aspect or possible implementations of the fifth aspect is implemented, the method according to any of the sixth aspect or possible implementations of the sixth aspect is implemented,The method according to any one of the seventh aspect or the possible implementations of the seventh aspect is implemented, or the method according to any one of the eighth aspect or the possible implementations of the eighth aspect is implemented.

[00146] According to a sixteenth aspect, a communication system is provided. The communication system includes one or a combination of the following devices: a communication device to realize any of the first aspect or possible implementations of the first aspect, a communication device to realize any of the second aspect or possible implementations of the second aspect, a communication device to realize any of the third aspect or possible implementations of the third aspect, a communication device to realize any of the fourth aspect or possible implementations of the fourth aspect, a communication device to realize any of the fifth aspect or possible implementations of the fifth aspect. Petition 870250105060, dated 11 / 17 / 2025, p. 41 / 204 35 / 188 possible implementations of the fifth aspect, a communication device to realize any of the sixth aspect or the possible implementations of the sixth aspect, a communication device to realize any of the seventh aspect or the possible implementations of the seventh aspect, or a communication device to realize any of the eighth aspect or the possible implementations of the eighth aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[00147] FIG. 1 is a diagram of a possible application structure in a communication system.

[00148] Fig. 2 is a diagram of another possible application structure in a communication system.

[00149] fig. 3 is a diagram of a communication system to which the modalities of this application are applicable.

[00150] fig. 4 is a diagram of another communication system to which the modalities of this application are applicable.

[00151] Fig. 5 is a block diagram of an autoencoder.

[00152] Fig. 6 is a diagram of an AI application structure.

[00153] fig. 7 is a schematic flowchart of a communication method according to a modality of this request.

[00154] fig. 8 is a codebook-based feedback diagram according to an embodiment of this application.

[00155] fig. 9 is a schematic flowchart of another communication method according to a modality of this request.

[00156] fig. 10 is a schematic flowchart of yet another method of communication according to a modality of this request.

[00157] fig. 11 is a schematic flowchart of yet another method of communication according to a modality of this request.

[00158] fig. 12 is a diagram of an application scenario according to a modality of this request.

[00159] Fig. 13 is a diagram of another application scenario. Petition 870250105060, dated 11 / 17 / 2025, p. 42 / 204 36 / 188 according to one of the options of this request.

[00160] FIG. 14 is a block diagram of a communication device according to an embodiment of this application; and

[00161] FIG. 15 is a block diagram of another communication device according to an embodiment of this application. DESCRIPTION OF THE DEVELOPMENTS

[00162] The following describes the technical solutions of this application with reference to the attached drawings.

[00163] The technical solutions provided in this application can be applied to various communication systems, for example, a fifth-generation (5G) or new radio (NR) system, a long-term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD) system, a wireless local area network (WLAN) system, a satellite communication system, a future communication system, for example, a sixth-generation (6G) mobile communication system, or a system integrating a plurality of systems.The technical solutions provided in this application can be further applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), an Internet of Things (IoT) communication system, or other communication systems.

[00164] A network element in a communication system can send a signal to another network element or receive a signal from another network element. The signal may include information, signaling, data, or similar. The network element may alternatively be replaced by an entity, a network entity, a device, a communication device, or a module. Petition 870250105060, dated 11 / 17 / 2025, page 43 / 204 37 / 188 of communication, a node, a communication node, or similar. In the present disclosure, the network element is used as an example for description. For example, the communication system may include at least one terminal device and at least one network device. The network device may send a downlink signal to the terminal device and / or the terminal device may send an uplink signal to the network device. It may be understood that the terminal device in the present disclosure may be replaced by a first network element, the network device may be replaced by a second network element, and the terminal device and the network device perform a corresponding communication method in the present disclosure.

[00165] In embodiments of this application, the terminal device may also be referred to as user equipment (UE), an access terminal, a subscriber unit, a subscriber station, a mobile station, a mobile console, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent or a user appliance.

[00166] A terminal device can be a device that provides voice or data, for example, a portable device or a vehicle-mounted device with a wireless connection function. Currently, some examples of terminals are a mobile phone, a tablet, a notebook, a palmtop, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, and a wireless terminal in security. Petition 870250105060, dated 11 / 17 / 2025, page 44 / 204 38 / 188 transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, a mobile phone, a cordless phone, a phone with Session Initiation Protocol (SIP), a wireless local loop (WLL) station, a personal digital assistant (PDA), a portable device with wireless communication function, a computing device or other processing device connected to a wireless modem, a wearable device, a terminal device on a 5G network, and a terminal device on a future evolved public land mobile network (PLMN). This is not limited to the embodiments of this application.

[00167] By way of example and not limitation, in embodiments of this application, the terminal device may alternatively be a wearable device. A wearable device may also be called a smart wearable device and is a general term for a wearable device that is intelligently designed and developed for everyday use using wearable technology, for example, eyeglasses, gloves, a watch, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. A wearable device is not only a hardware device but also implements a powerful function through software support, data exchange, and cloud interaction.In a broad sense, wearable smart devices include both full-featured, large-scale devices that can implement complete or partial functions without relying on smartphones, for example, smartwatches or smart glasses, and devices that focus only on one type of application function and need to be used in cooperation with other devices, such as smartphones, for example, various smart bracelets or smart jewelry used for. Petition 870250105060, dated 11 / 17 / 2025, page 45 / 204 39 / 188 monitor physical signs.

[00168] In embodiments of this application, an apparatus for implementing a terminal device function may be a terminal device, or it may be an apparatus that can support a terminal device in implementing the function, for example, a chip system, where the apparatus may be mounted on the terminal device or used in cooperation with the terminal device. In some embodiments of this application, the chip system may include a chip or it may include a chip and another discrete component. In embodiments of this application, an example in which the apparatus for implementing the terminal device function is a terminal device is used merely for description and does not constitute any limitation to the solutions in embodiments of this application.

[00169] In some embodiments of this application, the network device may be a device for communication with the terminal device. The network device may also be called an access network device or a radio access network device. For example, the network device may be a base station. In embodiments of this application, the network device may be a radio access network (RAN) node (or device) that connects the terminal device to a wireless network.The term base station can encompass any of the following names in a broad sense or can be replaced by the following names: for example, a NodeB, an evolved NodeB (eNB), a next-generation NodeB (gNB), a relay station, an access point, a transmission reception point (TRP), a transmission point (TP), a primary station, a secondary station, a multi-pattern radio node (MSR), a home base station, a network controller, an access node, a radio node, an access point (AP), a node of. Petition 870250105060, dated 11 / 17 / 2025, p. 46 / 204 40 / 188 transmission, a transceiver node, a baseband unit (BBU), a remote radio unit (RRU), an active antenna unit (AAU), a remote radio head (RRH), a central unit (CU), a distributed unit (DU), a radio unit (RU), and a positioning node. The base station may be a macro base station, a micro base station, a relay node, a donor node, or similar, or a combination thereof. Alternatively, the base station may be a communication module, a modem, or a chip disposed within the aforementioned device or apparatus. Alternatively, the base station may be a mobile switching center, a device performing a base station function in D2D, V2X, or M2M communication, a network-side device in a 6G network, a device performing a base station function in a future communication system, or similar.The base station can support networks of the same access technology or different access technologies. Optionally, the RAN node can be a server, a wearable device, a vehicle, a vehicle-mounted device, or similar. For example, an access network device in a vehicle-to-everything (V2X) technology could be a roadside unit (RSU). A specific technology and a specific device form factor used for the network device are not limited in embodiments of this application.

[00170] The base station can be fixed or mobile. For example, a helicopter or an unmanned aerial vehicle can be configured as a mobile base station, and one or more cells can move based on the position of the mobile base station. In other examples, a helicopter or an unmanned aerial vehicle can be configured as a device for communication with another base station. Petition 870250105060, dated 11 / 17 / 2025, page 47 / 204 41 / 188

[00171] In some deployments, the network device mentioned in embodiments of this application may be a device including a CU or a DU, or a device including a CU and a DU, or a device including a central unit-control plane (CU-CP) node, a central unit-user plane (CU-UP) node, and a DU node. For example, the network device may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[00172] In some deployments, a plurality of RAN nodes cooperate to assist the terminal in implementing radio access, and different RAN nodes separately implement some base station functions. For example, the RAN node can be a CU, a DU, a CU-CP, a CU-UP, or a RU. The CU and DU can be discarded separately or can be included in the same network element, for example, a BBU. The RU can be included in a radio frequency device or in a radio frequency unit, for example, included in an RRU, an AAU, or an RRH.

[00173] The RAN node can support one or more categories of fronthaul interfaces, and different fronthaul interfaces correspond to DUs and RUs with different functions. If a fronthaul interface between DU and RU is a common public radio interface (CPRI), the DU will be configured to implement one or more baseband functions, and the RU will be configured to implement one or more radio frequency functions. If a fronthaul interface between DU and RU is an enhanced common public radio interface (eCPRI), compared to the CPRI implementation, some downlink baseband functions and / or uplink baseband functions will be moved from the DU to the RU for implementation. Different ways of dividing DU and RU correspond to different categories. Petition 870250105060, dated 11 / 17 / 2025, p. 48 / 204 42 / 188 (category, Cat) of eCPRIs, for example, eCPRI Cat A, B, C, D, E and F.

[00174] eCPRI Cat A is used as an example. For downlink transmission, the split is performed at the layer mapping stage. The DU is configured to implement the layer mapping and one or more functions before the layer mapping (to be specific, one or more of encoding, rate matching, scrambling, modulation, and layer mapping) and other functions (e.g., one or more of RE mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition) after the layer mapping are moved to the RU for implementation. For uplink transmission, the split is performed at the RE demapping stage.A DU is configured to implement unmapping, and one or more functions before unmapping (specifically, one or more of the following functions: decoding, rate reduction matching, decoding, demodulation, discrete inverse Fourier transform (IDFT), channel equalization, and RE unmapping) and other functions (e.g., one or more digital BF or Fast Fourier Transform (FFT) / CP removal) after unmapping are moved to RU for implementation. It may be understood that, for job descriptions of DUs and RUs corresponding to various eCPRI categories, one may refer to the eCPRI protocol. The details are not described here.

[00175] In a possible design, a processing unit to implement a baseband function in the BBU is called a baseband high (BBH) unit, and a processing unit to implement a baseband function in the RRU, AAU, or RRH is called a baseband low (BBL) unit. Petition 870250105060, dated 11 / 17 / 2025, page 49 / 204 43 / 188

[00176] In different systems, the CU (or CU-CP and CU-UP), DU, or RU may have different names, but a person skilled in the art can understand the meaning of the names. For example, in an ORAN system, the CU may also be called O-CU (open CU), the DU may also be called O-DU, the CU-CP may also be called O-CU-CP, the CU-UP may also be called O-CU-UP, and the RU may also be called O-RU. Any of the CU (or CU-CP and CU-UP), DU, and RU in this application may be implemented using a software module, a hardware module, or a combination of a software module and a hardware module.

[00177] In embodiments of this application, an apparatus for implementing a network device function may be a network device, or it may be an apparatus that can support a network device in implementing the function, for example, a chip system, a hardware circuit, a software module, or a combination of a hardware circuit and a software module, wherein the apparatus may be mounted on the network device or used in cooperation with the network device. In embodiments of this application, an example in which the apparatus for implementing the network device function is a network device is used merely for description and does not constitute any limitation to the solutions in embodiments of this application.

[00178] The network device and / or the terminal device may be deployed on land, including an indoor or outdoor scenario and a portable or vehicle-mounted scenario; or they may be deployed on water; or they may be deployed on an airplane, a balloon, and a satellite in the air. The scenarios in which the network device and the terminal device are located are not limited in embodiments of this application. Furthermore, the terminal device and the network device may be hardware devices; or they may be software functions run on dedicated hardware, or software functions run on general-purpose hardware, for example, virtualized functions instantiated on a Petition 870250105060, dated 11 / 17 / 2025, page 50 / 204 44 / 188 platform (for example, a cloud platform); or they may be entities comprising a dedicated or general-purpose hardware device and a software function. Specific forms of terminal device and network device are not limited in this application.

[00179] In a wireless communication network, for example, in a mobile communication network, the services supported by the network are increasingly diversified and, therefore, the requirements that need to be met are increasingly diversified. For example, the network needs to be able to support ultra-high throughput, ultra-low latency, and / or massive connections. This capability makes network planning, network configuration, and / or resource scaling increasingly complex. Furthermore, as the network has increasingly powerful functions, for example, supporting an increasingly higher spectrum and new technologies such as higher-order multiple-input multiple-output (MIMO) technology, beamforming, and / or beam management, network power efficiency becomes an important research topic.These new requirements, scenarios, and resources pose unprecedented challenges to network planning, operation, and maintenance, as well as efficient operation. To address these challenges, artificial intelligence technology can be introduced into the wireless communication network to implement network intelligence.

[00180] To support AI technology on a wireless network, an AI node can be introduced into the network.

[00181] Optionally, the AI ​​node can be deployed in one or more of the following positions in the communication system: an access network device, a terminal device, a central network device, or similar. Alternatively, the AI ​​node can be deployed independently, for example, deployed in a position other than any of the Petition 870250105060, dated 11 / 17 / 2025, page 51 / 204 45 / 188 previous devices, for example, a host or a cloud server in an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system. The other devices can be, for example, one or more of the following: a network device, a terminal device, a network element of a core network, or similar.

[00182] It can be understood that the number of AI nodes is not limited in this request. For example, when there is a plurality of AI nodes, the plurality of AI nodes can be achieved through function-based division. For example, different AI nodes are responsible for different functions.

[00183] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in a hardware device, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (e.g., a cloud platform). A specific form of AI node is not limited in this application.

[00184] The AI ​​node can be an AI network element or an AI module.

[00185] FIG. 1 is a diagram of a possible application structure in a communication system. As shown in FIG. 1, the network elements in the communication system are connected via an interface (e.g., NG or Xn) or an air interface. One or more AI modules (for clarity, only one AI module is shown in FIG. 1) are deployed on these network element nodes, for example, one or more of the following devices: a central network device, an access network node (RAN node), a terminal, or an OAM. The access network node may serve as an independent RAN node or may include a plurality of RAN nodes, for example, including a CU and a DU. One or more AI modules may also be deployed on the CU. Petition 870250105060, dated 11 / 17 / 2025, page 52 / 204 46 / 188 and / or in the DU. Optionally, the CU can be divided into CU-CP and CU-UP. One or more AI modules are deployed in the CU-CP and / or in the CU-UP.

[00186] The AI ​​module is configured to implement a corresponding AI function. AI modules deployed on different network elements may be the same or different. An AI module template is configured based on different parameters, and the AI ​​module may implement different functions. The AI ​​module template may be configured based on one or more of the following parameters: a structure parameter (e.g., at least one of the following: a number of layers in a neural network, a width of a neural network, a connection ratio between layers, a neuron weight, a neuron activation function, or a bias in an activation function), an input parameter (e.g., an input parameter type and / or an input parameter dimension), or an output parameter (e.g., an output parameter type and / or an output parameter dimension). The bias in the activation function may also be called a neural network bias.

[00187] An AI module can have one or more models. A model can obtain an output through inference, where the output includes one or more parameters. Learning processes, training processes, 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.

[00188] Fig. 2 is a diagram of a possible application structure in a communication system. As shown in FIG. 2, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be AI modules shown in FIG. 1 and is configured to implement an AI-related function. The RIC includes a near-real-time RIC (near-RT RIC) and a non-real-time RIC (non-RT RIC). Petition 870250105060, dated 11 / 17 / 2025, page 53 / 204 47 / 188 Non-real-time RIC primarily processes non-real-time information, for example, latency-insensitive data. Data latency can be several seconds. Near-real-time RIC primarily processes near-real-time information, for example, latency-sensitive data. Data latency is tens of milliseconds.

[00189] Near real-time RIC is used for model training and inference; for example, it is configured to train an AI model and perform inference using the AI ​​model. The near real-time RIC can obtain network-side and / or terminal-side information from a RAN node (e.g., a CU, a CU-CP, a CU-UP, a DU, and / or an RU) and / or a terminal. The information can be used as training data or inference data. Optionally, the near real-time RIC can deliver an inference result to the RAN node and / or the terminal. Optionally, the CU and the DU can exchange an inference result, and / or the DU and the RU can exchange an inference result. For example, the near real-time RIC delivers an inference result to the DU, and the DU sends the inference result to the RU.

[00190] Non-real-time RICs are also used for model training and inference; for example, they are configured to train an AI model and perform inference using the model. Non-real-time RICs can obtain network-side and / or terminal-side information from the RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or the terminal. The information can be used as training data or inference data, and an inference result can be delivered to the RAN node and / or the terminal. Optionally, the CU and DU can exchange an inference result, and / or the DU and RU can exchange an inference result. For example, the non-real-time RIC delivers an inference result to the DU, and the DU sends the inference result to the RU. Petition 870250105060, dated 11 / 17 / 2025, page 54 / 204 48 / 188

[00191] Near real-time RIC and non-real-time RIC can be deployed independently as a network element. Optionally, near real-time RIC and non-real-time RIC can alternatively serve as part of another device. For example, near real-time RIC is deployed on the RAN node (e.g., CU or DU), and non-real-time RIC is deployed on an OAM, a cloud server, a core network device, or another network device.

[00192] Fig. 3 is a diagram of a communication system to which a communication method according to an embodiment of this application is applicable. As shown in FIG. 3, the communication system 100 may include at least one network device, for example, a network device 110 shown in FIG. 3. The communication system 100 may further include at least one terminal device, for example, a terminal device 120 and a terminal device 130 shown in FIG. 3. The network device 110 may communicate with the terminal device (for example, the terminal device 120 and the terminal device 130) by means of a radio link. Communication devices, for example, the network device 110 and the terminal device 120, in the communication system may communicate with each other using a multi-antenna technology.

[00193] Fig. 4 is a diagram of another communication system to which a communication method according to an embodiment of this application is applicable. Compared with communication system 100 shown in FIG. 3, communication system 200 shown in FIG. 4 further includes an AI network element 140. The AI ​​network element 140 is configured to perform an AI-related operation, for example, building a training dataset or training an AI model.

[00194] In one possible implementation, network device 110 could send data related to AI model training to AI network element 140, and AI network element Petition 870250105060, dated 11 / 17 / 2025, page 55 / 204 49 / 188 140 constructs a training dataset and trains the AI ​​model. For example, the data related to training the AI ​​model might include data reported by the terminal device. The AI ​​network element 140 might send the result of an AI model-related operation to network device 110, and network device 110 forwards the result of the AI ​​model-related operation to the terminal device. For example, the result of the AI ​​model-related operation might include at least one of the following: a trained AI model, an evaluation result, or a test result for the model, and the like. For example, part of the trained AI model might be deployed on network device 110, and the other part might be deployed on the terminal device. Alternatively, the trained AI model might be deployed on network device 110. Alternatively, the trained AI model might be deployed on the terminal device.

[00195] It should be understood that, in FIG. 4, the fact that the AI ​​network element 140 is directly connected to the network device 110 is used only as an example for description. In another scenario, the AI ​​network element 140 may alternatively be connected to the terminal device. Alternatively, the AI ​​network element 140 may be connected to both the network device 110 and the terminal device. Alternatively, the AI ​​network element 140 may be connected to the network device 110 via a third-party network element. A connection relationship between the AI ​​network element and another network element is not limited in embodiments of this application.

[00196] The AI ​​network element 140 can alternatively be deployed on a network device and / or a terminal device as a module, for example, deployed on network device 110 or on the terminal device shown in FIG. 3.

[00197] It should be noted that FIG. 3 and FIG. 4 are merely simplified example diagrams to facilitate understanding. By Petition 870250105060, dated 11 / 17 / 2025, p. 56 / 204 50 / 188 For example, the communication system may also include another device, for example, it may also include a wireless relay device and / or a wireless backhaul device, which are / are not shown in FIG. 3 and FIG. 4. During actual application, the communication system may include a plurality of network devices and may also include a plurality of terminal devices. Quantities of network devices and terminal devices included in the communication system are not limited in embodiments of this application.

[00198] To facilitate understanding of the modal solutions in this application, terms that may be used in modalities of this application are described below.

[00199] (1) AI Model

[00200] An AI model is an algorithm or computer program that can implement an AI function. The AI ​​model represents a mapping relationship between an input and an output of the model. One type of AI model can be a neural network, a linear regression model, a decision tree model, a support vector machine (SVM), a Bayesian network, a Q-learning model, or another machine learning (ML) model.

[00201] (2) Bilateral Model

[00202] The bilateral model may also be called a bilateral model, cooperative model, dual model, two-sided model, or similar. The bilateral model is a model that includes a plurality of submodels. The plurality of submodels included in the model must correspond to each other. The plurality of submodels may be deployed on different nodes.

[00203] The modalities of this application refer to an encoder for compressing CSI and a decoder for recovering compressed CSI. The encoder and decoder are used in cooperation. It can be understood that the encoder and decoder are AI models that correspond to each other. An encoder can Petition 870250105060, dated 11 / 17 / 2025, page 57 / 204 51 / 188 include one or more AI models, and a decoder corresponding to the encoder also includes one or more AI models. An encoder and a decoder that are used in cooperation include the same number of AI models, and the AI ​​models included in the encoder are in a one-to-one correspondence with the AI ​​models included in the decoder.

[00204] In one possible design, an encoder and decoder set that are used in cooperation may specifically be two parts of the same autoencoder (AE), for example, as shown in FIG. 5. An AE model in which an encoder and a decoder are deployed separately on different nodes is a typical bilateral model. The encoder and decoder of the AE model are usually an encoder and a decoder that are trained together and used in cooperation. The encoder processes an input V to obtain a processed result z, and the decoder can decode the output z of the encoder into an expected output V'.

[00205] The autoencoder is an unsupervised learning neural network and is characterized by the use of input data as label data. Therefore, the autoencoder can also be understood as a self-supervised learning neural network. The autoencoder can be configured to compress and retrieve data. For example, the encoder in the autoencoder can compress (encode) data A to obtain data B, and the decoder in the autoencoder can uncompress (decode) data B to obtain data A through retrieval. Alternatively, this can be understood as the decoder being an inverse operation of the encoder.

[00206] For example, the AI ​​model in the modalities of this application may include an encoder and a decoder. The Petition 870250105060, dated 11 / 17 / 2025, page 58 / 204 The 52 / 188 encoder and decoder are used in cooperation. It can be understood that the encoder and decoder are AI models that correspond to each other. The encoder and decoder can be deployed separately on a terminal device and on a network device.

[00207] Alternatively, the AI ​​model in embodiments of this application may be a single-sided model, and the AI ​​model may be deployed on an end device or on a network device.

[00208] (3) Neural network (NN)

[00209] A neural network is a specific form of AI or machine learning implementation. According to the universal approximation theorem, a neural network can approximate any continuous function in theory, so the neural network has the ability to learn any mapping.

[00210] A neural network can include a neuron. The neuron can be a unit of operation that uses xs and an intercept of 1 as input. The neural network is a network formed by the connection of many individual neurons. To be more specific, an output of one neuron can be an input to another neuron. An input to each neuron can be connected to a local receptive field of a previous layer to extract a feature from the local receptive field. The local receptive field can be a region that includes several neurons.

[00211] For example, one type of AI model is a neural network. The AI ​​model in the present disclosure may be a deep neural network (DNN). Based on a network construction mode, the DNN may include a feedforward neural network (FNN), a convolutional neural network (CNN), a recurrent neural network (RNN), and the like.

[00212] (4) Training dataset and inference data Petition 870250105060, dated 11 / 17 / 2025, page 59 / 204 53 / 188

[00213] In the field of machine learning, a ground truth is generally considered to be accurate or true data.

[00214] The training dataset is used to train an AI model. The training dataset may include an input to the AI ​​model or include an input to the AI ​​model and a target output of the AI ​​model. The training dataset includes one or more pieces of training data. The training data may include a training sample input to the AI ​​model or may include the target output of the AI ​​model. The target output may also be called a label, sample label, or sample label. The label is a ground truth.

[00215] In the field of communication, the training dataset may include simulation data collected by a simulation platform, or it may include experimental data collected in an experimental setting, or it may include real measurement data collected on a real communication network. Because the geographical environments and channel conditions in which the data are generated are different (e.g., indoor / outdoor environments, movement speeds, frequency bands, or antenna configurations are different), the collected data may be classified when they are obtained. For example, data with the same channel propagation environment and the same antenna configuration are classified into one type.

[00216] Model training essentially consists of learning some features from the training data. During the training of an AI model (e.g., a neural network model), since an output of the AI ​​model is expected to be as close as possible to a predicted value that is actually expected, a predicted value of an current network can be compared with a target value that is actually expected, and then a weight vector of each layer of the Petition 870250105060, dated 11 / 17 / 2025, page 60 / 204 54 / 188 The AI ​​model is updated based on the difference between the predicted value and the target value (certainly, before the first update, an initialization process is usually performed; to be more specific, the parameters are pre-configured for all layers of the AI ​​model). For example, if the predicted value of the network is large, the weight vector is adjusted to decrease the predicted value, and the adjustment is performed continuously until the AI ​​model can obtain, through prediction, the actually expected target value or a value very close to the actually expected target value. Therefore, how to obtain, through comparison, a difference between a predicted value and a target value needs to be predefined. This is a loss function or an objective function. The loss function and the objective function are important equations for measuring the difference between a predicted value and a target value. The loss function is used as an example.A larger output value (loss) of the loss function indicates a greater difference. In this case, training the AI ​​model is a loss minimization process, to make a loss function value less than a threshold or to make a loss function value meet a target requirement. For example, the AI ​​model is a neural network, and tuning a parameter of the neural network model includes tuning at least one of the following parameters: a number of layers in the neural network, a width of the neural network, a weight of a neuron, or a parameter in a neuron's activation function.

[00217] Inference data can be used as input for a trained AI model and used for inference by the AI ​​model. During model inference, inference data is fed into the AI ​​model to obtain a corresponding output, i.e., an inference result.

[00218] (5) AI model design

[00219] AI model design mainly includes a data collection phase (e.g., data collection from Petition 870250105060, dated 11 / 17 / 2025, page 61 / 204 55 / 188 training and / or inference data), a model training phase and a model inference phase, and may also include a phase of applying the inference result.

[00220] Fig. 6 shows an AI application structure.

[00221] In the data collection phase, a data source is used to provide a set of training data and inference data. In the model training phase, the training data provided by the data source is analyzed or trained to obtain an AI model. The AI ​​model represents a mapping relationship between an input and an output of the model. Obtaining the AI ​​model through learning using a model training node is equivalent to obtaining the mapping relationship between the model's input and output through learning using the training data. In the model inference phase, the AI ​​model obtained through training in the model training phase is used to perform inference based on the inference data provided by the data source, to obtain an inference result.This phase can also be understood as follows: Inference data is fed into the AI ​​model to obtain an output through the AI ​​model, where the output is the result of the inference. The inference result may indicate a configuration parameter used (executed) by an actor object and / or an operation performed by the actor object. The inference result is published in the inference result application phase. For example, the inference result can be planned by an actor entity in a unified manner. For example, the actor entity can send the inference result to one or more actor objects (e.g., a network device or a terminal device) for execution. In another example, the actor entity can provide additional feedback on the model's performance to the data source to facilitate subsequent model updates and training. Petition 870250105060, dated 11 / 17 / 2025, page 62 / 204 56 / 188

[00222] It can be understood that a communication system may include a network element with an artificial intelligence function. The previous phases related to the AI ​​model design can be performed by one or more network elements with the artificial intelligence function. In one possible design, the AI ​​function (e.g., an AI module or an AI entity) can be configured on an existing network element in the communication system to implement an AI-related operation, for example, AI model training and / or inference. For example, the existing network element could be a network device or a terminal device. Alternatively, in another possible design, an independent network element could be introduced into the communication system to perform an AI-related operation, for example, AI model training. The independent network element could be called an AI network element, AI node, or similar.The name is not limited in the modalities of this application. For example, the AI ​​network element can be directly connected to a network device in the communication system or it can be indirectly connected to the network device through a third-party network element. The third-party network element can be a central network element, such as an authentication management function (AMF) network element or a user plane function (UPF) network element, an operation administration and maintenance (OAM) element, a cloud server, or another network element. This is not limited. For example, the standalone network element can be deployed on one or more sides of a network device, one side of an endpoint device, or one side of a central network. Optionally, the standalone network element can be deployed on a cloud server.For example, the AI ​​140 network element is introduced into the communication system shown in FIG. 4. Petition 870250105060, dated 11 / 17 / 2025, pp. 63 / 204 57 / 188

[00223] Training processes for different models can be deployed on different devices or nodes, or they can be deployed on the same device or node. Inference processes for different models can be deployed on different devices or nodes, or they can be deployed on the same device or node. For example, a model training phase is performed by a terminal device. After training a matching encoder and decoder, the terminal device can send a model parameter from the decoder to a network device. For example, a model training phase is performed by a network device. After training a matching encoder and decoder, the network device can indicate a model parameter from the encoder to a terminal device. For example, a model training phase is performed by an independent AI network element.After training a matching encoder and decoder, the AI ​​network element can send a model parameter from the encoder to a terminal device and a model parameter from the decoder to a network device. Then, a model inference phase corresponding to the encoder is performed on the terminal device, and a model inference phase corresponding to the decoder is performed on the network device.

[00224] The model parameter may include one or more of the following: a model structure parameter (e.g., a number of model layers and / or a weight), a model input parameter (e.g., an input dimension or a number of input ports), or a model output parameter (e.g., an output dimension or a number of output ports). The input dimension can be understood to be the size of a piece of input data. For example, when the input data is a sequence, a dimension of Petition 870250105060, dated 11 / 17 / 2025, page 64 / 204 58 / 188, the corresponding input to the sequence, can indicate the length of the sequence. The number of input ports can be a number of pieces of input data. Similarly, the output dimension can be the size of a piece of output data. For example, when the output data is a sequence, an output dimension corresponding to the sequence can indicate the length of the sequence. The number of output ports can be a number of pieces of output data.

[00225] (6) Channel State Information

[00226] In a communication system (for example, an LTE communication system or an NR communication system), a network device needs to determine, based on the CSI, settings such as a resource, an MCS, and pre-coding that are used to scale a downlink data channel to a terminal device. CSI can be understood as channel information, and it is information that can indicate a channel characteristic or channel quality.

[00227] CSI measurement means that a receiving end obtains channel information based on a reference signal sent by a transmitting end, i.e., it estimates channel information using a channel estimation method. For example, the reference signal may include one or more channel state information reference signals (CSI-RS), a synchronization signal / physical broadcast channel block (SSB), a sounding reference signal (SRS), a demodulation reference signal (DMRS), or similar signals. CSI-RS, SSB, DMRS, and similar signals can be used to measure downlink CSI. SRS, DMRS, and similar signals can be used to measure uplink CSI.

[00228] An FDD communication scenario is used as an example. Petition 870250105060, dated 11 / 17 / 2025, page 65 / 204 59 / 188 In an FDD communication scenario, an uplink channel and a downlink channel are not reciprocal; that is, reciprocity between an uplink channel and a downlink channel cannot be guaranteed. Therefore, the network device typically sends a downlink reference signal to the terminal device, and the terminal device performs channel or interference measurement based on the received downlink reference signal to estimate the downlink CSI. The terminal device generates a CSI report in a manner predefined in a protocol or in a manner configured by the network device and sends the CSI report back to the network device so that the network device obtains the downlink CSI.

[00229] For example, CSI may include at least one of the following: a channel quality indicator (CQI), a precoding matrix indicator (PMI), a rank indicator (RI), a CSI-RS resource indicator (CRI), a layer indicator (LI), reference signal received power (RSRP), a signal-to-interference plus noise ratio (SINR), or similar. The signal-to-interference plus noise ratio may also be called the signal-to-interference-plus-noise ratio.

[00230] ri indicates a quantity, recommended by the terminal device, of downlink transmission layers. CQI indicates a modulation and coding scheme, determined by the terminal device, that can be supported under a given channel condition. PMI indicates the precoding recommended by the terminal device. A quantity, indicated by PMI, of precoding layers corresponds to RI.

[00231] It should be understood that RI, CQI, PMI and similar Petition 870250105060, dated 11 / 17 / 2025, page 66 / 204 The 60 / 188 values ​​indicated by the CSI report are only recommended values ​​provided by the terminal device, and the network device may perform downlink transmission based on some or all of the information indicated by the CSI report. Alternatively, the network device may perform downlink transmission without consulting the information indicated by the CSI report.

[00232] An AI technology is introduced into a wireless communication network to achieve an AI model-based CSI feedback mode. The terminal device compresses and feeds back the CSI using an AI model, and the network device retrieves the compressed CSI using an AI model. A sequence (e.g., a bit sequence) is transmitted in AI-based CSI feedback, and the overheads are lower than the CSI overheads in conventional CSI feedback.

[00233] Fig. 5 is used as an example. In FIG. 5, an encoder can be a CSI generator, and a decoder can be a CSI reconfigurator. The encoder can be deployed on the terminal device and the decoder can be deployed on the network device. The terminal device can generate CSI feedback information z based on the raw CSI information V using the encoder. The terminal device reports a CSI report, where the CSI report may include CSI feedback information, for example. The network device can reconstruct CSI information using the decoder to obtain CSI recovery information V'.

[00234] Raw CSI V information can be obtained by the terminal device through CSI measurement. For example, raw CSI V information may include a channel response from a downlink channel or an eigenvector matrix (the matrix including eigenvectors) from a downlink channel. The encoder processes the eigenvector matrix of the downlink channel to obtain the CSI z feedback information. Petition 870250105060, dated 11 / 17 / 2025, p. 67 / 204 61 / 188 In other words, performing a compression operation and / or a quantization operation on an eigenvector matrix based on a codebook in a related solution is replaced by the encoder processing the eigenvector matrix to obtain the CSI z feedback information. The terminal device reports the CSI feedback information, for example. The network device processes the CSI z feedback information using the decoder to obtain the CSI V' recovery information.

[00235] Examples of a training process and an inference process for the AI ​​model in the modalities of this application are described below.

[00236] The training data for training the AI ​​model includes a training sample and a sample label. For example, the training sample is channel information determined by the terminal device, and the sample label is real channel information, i.e., field truth CSI. When the encoder and decoder belong to the same autoencoder, the training data can include only the training sample, i.e., the training sample is the sample label.

[00237] In the field of wireless communication, CSI field truth can be a high-precision CSI.

[00238] A specific training process is as follows: A model training node processes channel information, i.e., the training sample, using the encoder, to obtain CSI feedback information; processes the feedback information using the decoder, to obtain retrieved channel information, i.e., CSI recovery information; and then calculates a difference between the CSI recovery information and a corresponding sample label, i.e., a loss function value, and updates the encoder and decoder parameters based on the loss function value, to Petition 870250105060, dated 11 / 17 / 2025, page 68 / 204 62 / 188 minimize the difference between the retrieved channel information and the corresponding sample label, that is, minimize the loss function. For example, the loss function could be a minimum mean square error (MSE) or a cosine similarity. The previous operations can be repeated to obtain an encoder and a decoder that meet a target requirement. The model training node can be the terminal device, the network device, or another network element with an AI function in the communication system.

[00239] It should be understood that the previous example, in which the AI ​​model is used for CSI compression, is used for description purposes only, and during CSI feedback, the AI ​​model can alternatively be used in another scenario. For example, the AI ​​model can be used for CSI forecasting, to be more specific, predicting channel information at one or more future time points based on channel information measured at one or more historical time points. A specific purpose of the AI ​​model in the CSI feedback scenario is not limited to the modalities of this application.

[00240] (7) uci

[00241] UCI is a signaling or assistance information, different from the service load, sent by a terminal device to a network device. UCI can be relayed to the network device via a physical uplink control channel (PUCCH) or a physical uplink shared channel (PUSCH).

[00242] In a protocol, the UCI content includes at least one of the following: an escalation request, a hybrid automatic repeat request acknowledgment (HARQ-ACK), CSI feedback information, a configured grant (CG) UCI, or similar. When the Petition 870250105060, dated 11 / 17 / 2025, page 69 / 204 63 / 188 payload is greater than 11 bits, so polar encoding is generally used for the UCI.

[00243] An example where the UTI content is CSI feedback information is used below as an example to describe a UTI determination process.

[00244] CSI feedback information is represented by a CSI report. CSI feedback information can be divided into two parts: a part 1 (part 1) and a part 2 (part 2). In other words, the CSI report can be divided into two parts. The two parts can be used respectively to generate two UCI bit sequences. The UCI bit sequence 1 corresponds to part 1 and includes an RI, a CQI, a number of non-zero coefficients, and the like. The UCI bit sequence 2 corresponds to part 2 and includes a PMI.

[00245] Table 1 shows an example of a mapping order for mapping parts 1 of CSI reports to UCI bit sequences. Table 2 shows an example of a mapping order for mapping parts 2 of CSI reports to UCI bit sequences.

[00246] For example, as shown in Table 1, in the 1st UCI bit sequence, parts 1 of n CSI reports are sorted based on the sequence numbers of the n CSI reports. αθ1) indicates the 1st bit of the 1st UCI bit sequence, ^1) indicates the 2nd bit of the 1st UCI bit sequence and, by analogy, α^λ indicates a ^(1)-th bit of the 1st UCI bit sequence. A(1J-1 ^(1)) indicates a length of the 1st UCI bit sequence and Λ(1) is a positive integer. n is a positive integer. A part 2 can be divided into three groups: a group 0, a group 1, and a group 2. For example, as shown in Table 2, in the 2nd UCI bit sequence, the groups 0 in parts 2 of n CSI reports are sorted based on Petition 870250105060, dated 11 / 17 / 2025, pp. 70 / 204 64 / 188 in the sequence numbers of the n CSI reports, and then groups 1 and groups 2 of the n CSI reports are classified based on the sequence numbers of the n CSI reports. Group 0 may include i11, i12, and i18j, where i11 indicates spatial domain base selection information, i12 indicates oversampling selection information, and i18j indicates a coefficient with the highest value among non-zero coefficients in each layer. Group 1 may include a portion of i2 3j, i1 5, ij6j, and i2 4j, a portion of i2 5j, and a portion of i1 7j, where i2 3j indicates reference amplitude information, i1 5 indicates common frequency domain base selection information, ij6j indicates frequency domain base selection information in each layer, i2,4,j indicates amplitude information for each coefficient in each layer, i2 5j indicates phase information for each coefficient in each layer, and i1 7j indicates non-zero coefficient selection information in each layer. Group 2 may include another portion of i2,4,j, another portion of i2,5,j, and another portion of i^7, j. q^2 indicates the 1st bit of the UCI bit sequence, q12 indicates the 2nd bit of the UCI bit sequence, and by analogy, q(2) indicates A(2J-1) is the 2-th bit of the 2-bit sequence of UCI bits. 2 indicates a length of the 2-bit sequence of UCI bits and 2 is a positive integer. Table 1 UCI Bit Sequence CSI Report Sequence Number (1) qo Part 1 of a CSI report #1 (1) Part 1 of a CSI report #2 «1 (1) q ... Part 1 of a CSI report #n „ (1) «3 n (1) q 4(1)-1 Petition 870250105060, dated 11 / 17 / 2025, p. 71 / 204 65 / 188 Table 2 UCI bit sequence CSI report sequence number a(2) Uq (2) al a.' (2) a^ a (2) a^(2)_l Wideband in part 2 of CSI report #1 or group 0 in part 2 of CSI report #1 if part 2 exists in CSI report #1 Wideband in part 2 of CSI report #2 or group 0 in part 2 of CSI report #2 if part 2 exists in CSI report #2 ... Wideband in part 2 of CSI report #n or group 0 in part 2 of CSI report #n if part 2 exists in CSI report #n Subband in part 2 of CSI report #1 or group 1 and group 2 in part 2 of CSI report #1 if part 2 exists in CSI report #1 Subband in part 2 of CSI report #2 or group 1 and group 2 in part 2 of CSI report #2 if Part 2 exists in CSI report #2...Sub-band in part 2 of CSI report #n or group 1 and group 2 in part 2 of CSI report #n if part 2 exists in CSI report #n.

[00247] In the previous scenario, CSI feedback is mainly used by the network device to perform precoding, beam management, scheduling, or other operations. In this scenario, high-precision CSI is generally not required. Therefore, the CSI actually returned by the terminal device to the network device is usually compressed to a high degree and has low precision. In a codebook-based CSI feedback mode, to improve CSI feedback accuracy, some codebooks with high feedback overheads can be used, for example, a codebook of type (type) in release (R) 16 Petition 870250105060, dated 11 / 17 / 2025, page 72 / 204 66 / 188 of the 3GPP protocol and a codebook in a version later than R16. In this case, a CSI report is usually ported in a PUSCH. In an NR system, polar coding is used for UCI channel coding. The protocol supports a maximum code length of 1706 bits for polar coding, and the protocol supports a maximum CSI feedback overhead of approximately 800 bits. The maximum CSI feedback overhead supported in the protocol is less than the maximum code length supported in the protocol for polar coding. The CSI report can be transmitted using UCI. However, in some scenarios, for example, in an AI-based CSI feedback scenario, the network device needs to collect channel information with greater precision or accuracy.

[00248] For example, channel information can be used as training data to train an AI model. The training data for the AI ​​model can include a training sample and / or a sample label. Channel information can be used as a training sample and / or sample label. Typically, higher precision or accuracy of the channel information indicates a better training effect of the model. If CSI is reported to the network device in the previous mode, for example, a feedback mode based on the R16 codebook, the CSI accuracy obtained by the network device will be low, and a well-performing AI model can hardly be obtained by training using the CSI obtained by the network device as training data. As another example, channel information can be used as monitoring data to monitor the performance of an AI model.Specifically, channel information can be used for comparison with a model output to determine model performance. Greater precision or accuracy of channel information indicates greater accuracy in the model performance determination result. If CSI is reported to the network device in the previous mode... Petition 870250105060, dated 11 / 17 / 2025, pp. 73 / 204 67 / 188 for example, a feedback mode based on the R16 codebook, the CSI accuracy obtained by the network device will be low, and the model performance can hardly be accurately assessed using the CSI obtained by the network device as a basis for determining model performance.

[00249] High-precision channel information is generally larger than CSI feedback in a current CSI feedback mode. To be more specific, higher overheads are required to transmit high-precision channel information and may exceed the maximum code length limitation supported in the protocol for polar coding, and therefore high-precision channel information cannot be feedback using UCI.

[00250] In view of this, this application provides a communication method and a communication apparatus to enable a network device to obtain high-precision channel information and facilitate subsequent data transmission between the network device and a terminal device. The communication method can be applied to the previous communication system, for example, the FDD communication scenario. Furthermore, optionally, the communication method can alternatively be applied to a TDD communication scenario. This is not limited to the present disclosure.

[00251] It should be understood that, in this request, the indication includes a direct indication (also called an explicit indication) and an implicit indication. Directly indicating information A means including information A. Implicitly indicating information A means indicating information A by directly indicating information B and based on a correspondence between information A and information B. The correspondence between information A and information B may be predefined, pre-stored, pre-recorded, or pre-configured.

[00252] It should be understood that, in this request, the information C Petition 870250105060, dated 11 / 17 / 2025, p. 74 / 204 68 / 188 is used to determine information D, including that information D is determined solely based on information C, and also including that information D is determined based on information C and other information. Furthermore, the information C used to determine information D may also include a case of indirect determination. For example, information D is determined based on information E, and information E is determined based on information C.

[00253] Furthermore, in embodiments of this application, that a network element A sends information A to a network element B may be understood as that a destination end of information A or an intermediate network element in a transmission path between network element A and the destination end is network element B, and may include the direct or indirect sending of information to network element B; and that a network element B receives information A from a network element A may be understood as that a source end of information A or an intermediate network element in a transmission path between network element B and the source end is network element A, and may include the direct or indirect receiving of information from network element A. The information may undergo the necessary processing, for example, a format change, between the source end for sending the information and the destination end.However, the destination may understand valid information from the source end. Similar descriptions in this request may be understood similarly, and the details are not described here.

[00254] The solutions in the modalities of this application can be applied to pre-coding, beam management, or other scenarios.

[00255] Fig. 7 is a schematic flowchart of a communication method in accordance with this request. Petition 870250105060, dated 11 / 17 / 2025, pp. 75 / 204 69 / 188

[00256] As shown in FIG. 7, method 500 may include the following steps.

[00257] 510: A terminal device generates channel #1 information (an example of third channel information) based on a first feedback configuration, where the total length of the channel #1 information is less than or equal to the maximum code length supported by the UCI, and the channel #1 information is field truth channel information.

[00258] 520: Transmit UCI #1 (an example of the first UCI) to a network device, where UCI #1 corresponds to channel #1 information.

[00259] In this application modality, UCI is information used before encoding. A UCI chunk can be understood as a sequence of UCI bits used before encoding; to be more specific, a sequence of bits in which channel encoding must be performed independently. After passing through channel encoding, the UCI can be transmitted using an uplink feature.

[00260] For example, the uplink resource can be a PUCCH or a PUSCH.

[00261] That UCI #1 corresponds to channel #1 information indicates that channel #1 information is transmitted as an independent UCI. To be more specific, the UCI includes the content of channel #1 information. Transmitting UCI #1 is transmitting channel #1 information using UCI #1. The total length of channel #1 information can be understood as a quantity of bits of channel #1 information, that is, a length of UCI #1.

[00262] In this type of request, the terminal device generating channel information can also be understood as the terminal device generating a CSI report, and the Petition 870250105060, dated 11 / 17 / 2025, pp. 76 / 204 The 70 / 188 CSI report indicates channel information. Correspondingly, the terminal device transmitting channel information to the network device using UCI can also be understood as the terminal device transmitting a CSI report to the network device using UCI, indicating channel information.

[00263] True field channel information is high-precision channel information. A specific definition method can be determined by the network device or predefined.

[00264] Field truth channel information can also be called field truth CSI.

[00265] For example, field truth channel information can be channel information whose accuracy is greater than or equal to a threshold #1. The threshold can be specified by the network device or predefined.

[00266] In an AI-based feedback mode, CSI field truth can be used as any one or more of the following information from an AI model: target CSI, label CSI, input CSI, or similar.

[00267] For example, CSI ground truth can be used as training data during AI model training. For example, CSI ground truth can be used as a training sample input for the AI ​​model and / or a target output of the AI ​​model. The target output may also be called a label, sample label, ground truth, target, or something similar.

[00268] For example, CSI field truth can be used as a target output of the AI ​​model during AI model testing, to be more specific, used to measure the performance of the AI ​​model.

[00269] For example, CSI field truth can be used Petition 870250105060, dated 11 / 17 / 2025, p. 77 / 204 71 / 188 as a target output of the AI ​​model during AI model performance monitoring, to be more specific, used to measure the performance of the AI ​​model.

[00270] For example, the AI ​​model includes a CSI generator and a CSI reconfigurator. The terminal device can perform channel measurements based on a reference signal sent by the network device to obtain raw CSI information (i.e., initial channel information). The terminal device processes the raw CSI information based on the CSI generator to generate CSI feedback information and feeds the CSI feedback information back to the network device using a CSI report. The network device reconstructs the CSI feedback information using the CSI reconfigurator to obtain CSI recovery information. The terminal device can send the channel information #1 obtained from the raw CSI information to the network device.The network device can evaluate the accuracy of CSI recovery information based on CSI recovery information and channel #1 information, to assess the performance of the AI ​​model. It should be understood that the foregoing descriptions are merely examples and do not constitute any limitation to the solution in this embodiment of this application.

[00271] Optionally, method 500 may also include steps 530 and 540 (not shown in the figure).

[00272] 530: The terminal device generates channel #2 information (an example of fourth channel information) based on a second feedback configuration, where channel #2 information is not true field channel information, and the accuracy of channel #2 information is less than the accuracy of channel #1 information.

[00273] 540: The terminal device transmits UCI #2 (an example of a second UCI) to the network device, where UCI #2 corresponds to channel #2 information. Petition 870250105060, dated 11 / 17 / 2025, pp. 78 / 204 72 / 188

[00274] For example, channel #2 information may be compressed CSI reported in a conventional mode (e.g., based on an R16 codebook). For another example, channel #2 information may be CSI feedback information reported in an AI-based feedback mode.

[00275] In other words, when the channel information to be fed back by the terminal device is true-field channel information, high-precision channel information is generated using the first feedback configuration, and the total length of the channel information may be less than or equal to the maximum code length supported by the UCI; or when the channel information to be fed back by the terminal device is not true-field channel information, low-precision channel information is generated using the second feedback configuration, and correspondingly, the feedback overheads of the channel information are less than the feedback overheads of the channel information generated based on the first feedback configuration.

[00276] That UCI #2 corresponds to channel #2 information indicates that channel #2 information is transmitted as an independent UCI. To be more specific, the UCI includes the content of channel #2 information. Transmitting UCI #2 means transmitting channel #2 information using UCI #2.

[00277] In the solution in this embodiment of this application, when the channel information to be fed back by the terminal device is field truth channel information, high-precision channel information is generated using the first feedback configuration, and a channel information length is enabled to be less than or equal to the maximum code length supported by the UCI. In this way, both high-precision channel information and other low-precision channel information can be transmitted using the UCI, to allow the network device to obtain the Petition 870250105060, dated 11 / 17 / 2025, pp. 79 / 204 73 / 188 high-precision channel information.

[00278] In this type of request, channel information can also be called CSI. CSI is information used to represent a channel state.

[00279] For example, a channel information type can be any of the following: a channel response, an eigenvector matrix of a channel, a pre-coding matrix, an RSRP, a SINR, or similar.

[00280] The channel response can also be called the channel matrix. The channel eigenvector matrix is ​​a matrix that includes channel eigenvectors.

[00281] The channel information type can be predefined. Alternatively, the channel information type can be configured by the network device.

[00282] One dimension of channel information is related to the type of channel information.

[00283] For example, if the channel information is a spatial domain or frequency domain channel response, the channel information can be represented by a matrix with a dimension of NtxNrxF. Ntx indicates a number of antenna ports of the network device and Ntx is a positive integer. Nrx indicates a number of antenna ports of the terminal device and Nrx is a positive integer. F indicates bandwidth. Bandwidth can be represented by a number of bandwidth units, for example, a number of resource blocks (RB) or a number of sub-bands. F is a positive integer.

[00284] For example, if the channel information is the matrix of eigenvectors of the channel, the channel information can be represented by a matrix with a dimension of NtxX NclassificationxF. Nclassification indicates a number of rankings of an eigenvector, a number of layers, or a number of flows. Petition 870250105060, dated 11 / 17 / 2025, pp. 80 / 204 74 / 188 ^classification is a positive integer.

[00285] To facilitate description, in this embodiment of this application, an example in which the channel information is the eigenvector matrix of the channel is used primarily for description and does not constitute any limitation to the solution in this embodiment of this application.

[00286] The terminal device can generate, based on the initial channel information, channel information to be fed back to the network device, for example, channel information #1 or channel information #2.

[00287] For example, initial channel information may be raw CSI obtained by the terminal device through measurement.

[00288] For example, initial channel information may be CSI that has not undergone overhead adjustment. For example, initial channel information may be CSI that is not compressed and / or quantized.

[00289] Channel #1 information and channel #2 information can be understood as channel information actually fed back by the terminal device.

[00290] In step 510, the terminal device can report channel #2 information to the network device in a plurality of feedback modes. In other words, the terminal device can process the initial channel information in a plurality of feedback modes to generate channel #2 information to be fed back to the network device. A channel information feedback mode can also be called a format in which the terminal device returns channel information.

[00291] Feedback mode 1 and feedback mode 2 are used below as examples to describe the channel information feedback mode. Petition 870250105060, dated 11 / 17 / 2025, page 81 / 204 75 / 188 [002 92] Feedback mode 1: a scalar quantization mode.

[00293] Reporting channel information in scalar quantization mode means performing scalar quantization on the channel information and returning quantized channel information to the network device using a CSI report.

[00294] For example, scalar quantization is performed on an element in the initial channel information, and the quantized data is sent back to the network device using a CSI report. The quantized data can be used as channel information #1. For example, the initial channel information is an eigenvector array of a channel, and the channel eigenvector array is an array with a dimension of NtxX ^classification XF. Scalar quantization is performed on each element in the array with a dimension of NtxX NclassificationX F, and a result obtained through scalar quantization is sorted in a predefined order to obtain channel information #1.

[00295] For example, a type of scalar quantization can include any of the following: N-bit scalar quantization, 16-float quantization, 32-float quantization, 8-integer quantization, or similar. N can be a positive integer.For example, N can be any integer between 1 and 8.

[00296] In scalar quantization-based feedback mode, feedback overheads can be controlled based on scalar quantization precision or similar. For example, feedback overheads are reduced by using lower quantization precision.

[00297] Feedback mode 2: a codebook-based quantization mode.

[00298] Reporting channel information in codebook-based quantization mode means processing the information Petition 870250105060, dated 11 / 17 / 2025, pp. 82 / 204 76 / 188 channel based on a codebook and return the processed channel information to the network device using a CSI report.

[00299] the codebook is a codebook for CSI feedback.

[00300] For example, the codebook can be a codebook defined in an NR protocol for CSI feedback. For example, the codebook can be any of the following: a type I codebook in R15 of the 3GPP protocol, a type II codebook in R15 of the 3GPP protocol, an enhanced type II codebook in R16 of the 3GPP protocol, a codebook in R17 of the 3GPP protocol, a codebook in R18 of the 3GPP protocol, or similar.

[00301] The preceding descriptions are merely examples. In another implementation, the codebook for CSI feedback may alternatively be another codebook. For example, a codebook format defined in the protocol and a user-defined codebook parameter may be used in the codebook for CSI feedback. The user-defined codebook parameter is one or more groups of user-defined codebook parameters. As another example, a user-defined codebook format and a user-defined codebook parameter may be used in the codebook for CSI feedback.

[00302] FIG. 8 is a feedback diagram based on the etype II codebook in R16 of the 3GPP protocol.

[00303] As shown in FIG. 8, a fundamental principle for reporting channel information based on the etype II codebook in R16 is to decompose an eigenvector matrix in each layer into three matrices that are multiplied. One dimension of the eigenvector matrix in each layer is NtxxNsb, where Nsb indicates a number of sub-bands and Nsb is a positive integer. For ease of description, the three matrices are called Petition 870250105060, dated 11 / 17 / 2025, pp. 83 / 204 77 / 188 spatial domain basis matrix, coefficient matrix, and frequency domain basis matrix. One dimension of the spatial domain basis matrix is ​​Ntxx Ntx, one dimension of the coefficient matrix is ​​NtxxNsb, and one dimension of the frequency domain basis matrix is ​​Nsbx Nsb. Because the coefficient matrix includes a large number of coefficients with small values, dimension reduction can be performed on the spatial domain basis matrix, the coefficient matrix, and the frequency domain basis matrix. For example, a column vector from the spatial domain basis corresponding to a coefficient with a large value in the coefficient matrix is ​​retained in the spatial domain basis matrix, and a column vector from the frequency domain basis corresponding to a coefficient with a large value in the coefficient matrix is ​​retained in the frequency domain basis matrix.For example, the spatial domain basis column vectors 2L are selected from the spatial domain basis matrix, the frequency domain basis row vectors R are selected from the frequency domain basis matrix, and 2L x R are determined as the coefficients in the coefficient matrix that correspond to the spatial domain basis column vectors 2L and the frequency domain basis row vectors R. P non-zero coefficients are selected from the 2L x R coefficients. P is a positive integer less than or equal to 2L x R. Scalar quantization is performed on each of the P non-zero coefficients. L is a positive integer and R is a positive integer.

[00304] The spatial domain basis matrix and the frequency domain basis matrix are defined by the codebook. The spatial domain basis matrix and the frequency domain basis matrix can be discrete Fourier transform (DFT) matrices or matrices obtained by transforming a DFT matrix. The terminal device can feed back the column vectors of Petition 870250105060, dated 11 / 17 / 2025, pages 84 / 204 78 / 188 selected spatial domain base, selected frequency domain baseline vectors, selected non-zero coefficients, and non-zero coefficient values ​​using a CSI report. The spatial domain base column vector can also be called the spatial domain base. The frequency domain baseline vector can also be called the frequency domain base. The terminal device only needs to notify the network device about a specific selected spatial domain base, a specific selected frequency domain base, a specific selected non-zero coefficient, and a non-zero coefficient value, so that the network device can obtain the channel information.

[00305] In the etype II codebook-based feedback mode in R16, the content fed back by the terminal device includes il,l, il,2, il,5, il,6,i, il,7,^^ , where il is a layer identifier and a value of l is 1, 2, ..., or ^classification. Gj indicates spatial domain base selection information, il2 indicates oversampling selection information, il8i indicates a coefficient with the highest value among the non-zero coefficients in each layer, i2 3i indicates reference amplitude information, il 5 indicates common frequency domain base selection information, ii6i indicates frequency domain base selection information in each layer, i2,4,i indicates amplitude information for each coefficient in each layer, i2 51 indicates phase information for each coefficient in each layer, and il 7i indicates non-zero coefficient selection information in each layer. layer·

[00306] il le il 2indicam a specific selected spatial domain base.il 5e and il 6i indicate a specific selected frequency domain base in each layer. il lil 2, il 5, and il6i can be collectively referred to as information from. Petition 870250105060, dated 11 / 17 / 2025, pages 85 / 204 79 / 188 base selection. i17 is an identifier of a non-zero coefficient selected in an l-th layer. To be more specific, i17i can indicate a specific non-zero coefficient selected in each layer. i18i can indicate a coefficient with the highest value among non-zero coefficients in each layer. i23i, i24i, and i25i can indicate a value for each non-zero coefficient. i17i and i18i can be collectively called coefficient selection information. i2,3i, i2,4i, i2,5i can be collectively called coefficient value information. The values ​​of L, P, and R can be determined by the etype II codebook parameters in R16.

[00307] For example, the initial channel information is a matrix of eigenvectors of a channel. For example, the initial channel information is processed based on the codebook, to decompose an eigenvector matrix in each layer into three matrices that are multiplied. The spatial domain bases 2L are selected from a spatial domain basis matrix, the frequency domain bases R are selected from a frequency domain basis matrix, and 2% x R coefficients in a coefficient matrix that correspond to the spatial domain bases 2L and the frequency domain bases R are determined. P non-zero coefficients are selected from 2% x R coefficients. Scalar quantization is performed on each of the P non-zero coefficients.The channel information that can be determined based on the selected spatial domain bases, the selected frequency domain bases, the selected non-zero coefficients, and the values ​​of the non-zero coefficients is channel information #1; to be more specific, the channel information actually fed back by the terminal device. The terminal device notifies the network device about the selected spatial domain bases, the selected frequency domain bases, the... Petition 870250105060, dated 11 / 17 / 2025, pages 86 / 204 80 / 188 non-zero coefficients selected and the values ​​of the non-zero coefficients, so that the network device can obtain channel #1 information.

[00308] As described above, in the solution in this embodiment of this application, a codebook format defined in the protocol and a user-defined codebook parameter can be used in the codebook. For example, a codebook format defined by the etype II codebook in R16 and user-defined codebook parameters, such as L, P, and R values, can be used in the codebook in this embodiment of this application.

[00309] In codebook-based quantization feedback mode, feedback overheads can be controlled by adjusting a number of selected bases, a number of non-zero coefficients, quantization precision of non-zero coefficients, or similar. For example, feedback overheads are reduced by using one or more of the following: fewer bases, fewer non-zero coefficients, lower quantization precision of non-zero coefficients, or something similar.

[00310] A feedback mode used by the terminal device can be predefined, or a feedback mode used by the terminal device can be configured by the network device. For example, whether feedback mode 1 or feedback mode 2 should be used by the terminal device can be predefined or can be configured by the network device.

[00311] The feedback overheads of the channel information can be adjusted in several ways. In other words, the channel information actually fed back by the terminal device can be adjusted in several ways.

[00312] A method 1 through a method 4 are used below as examples to describe a way to adjust the feedback overheads of channel information. For example, the Petition 870250105060, dated 11 / 17 / 2025, page 87 / 204 81 / 188 feedback overheads of channel information can be adjusted in one or more of ways 1 to 4.

[00313] Method 1: Adjust a bandwidth dimension of channel information #1.

[00314] A smaller bandwidth dimension of channel #1 information indicates lower feedback overheads for channel #1 information.

[00315] In method 1, the bandwidth dimension of channel #1 information is smaller than the bandwidth dimension of the initial channel information. To be more specific, feedback overheads are reduced by reducing the bandwidth dimension of the channel information actually passed to the network device.

[00316] For example, a portion of the sub-bands can be selected from a plurality of sub-bands of the initial channel information and fed back to the network device. A quantity of sub-bands of channel information #1 is a quantity of the sub-band portion.

[00317] The number of sub-bands in channel #1 information is less than the number of sub-bands in the initial channel information.

[00318] For example, the number of sub-bands of the initial channel information is Nsb, and Nsbl sub-bands are selected from the Nsb sub-bands and fed back to the network device. The number of sub-bands of channel information #1 is Ns#l, where Nsb} is a positive integer less than Ns#.

[00319] In this way, feedback overheads can be controlled by selecting a number of sub-bands from the initial channel information. Channel information feedback overheads can be reduced by reducing the number of channel information sub-bands actually fed back to the network device. Petition 870250105060, dated 11 / 17 / 2025, pp. 88 / 204 82 / 188

[00320] For example, the granularity of a sub-band of the channel information can be increased. A sub-band granularity of channel information #1 is an increased sub-band granularity of channel information.

[00321] In this case, the granularity of the sub-band of the channel #1 information is greater than the granularity of the sub-band of the initial channel information.

[00322] A higher granularity of sub-bands of channel #1 information indicates a smaller number of sub-bands of channel #1 information and lower overhead for transmitting channel #1 information, i.e., lower feedback overheads.

[00323] For example, the granularity of the sub-band can be represented by a number of feature blocks in a sub-band.

[00324] For example, the sub-band granularity of the initial channel information is 4 RBs, the number of sub-bands is a positive integer closest to Nrb / 4, and the bandwidth of the initial channel information is NrbRBs, where Nrb is a positive integer. The increased sub-band granularity is 6 RBs. In other words, the sub-band granularity of channel information #1 is 6 RBs. The number of sub-bands of channel information #1 is a positive integer closest to Nrb / 6.

[00325] In this way, feedback overheads can be controlled by the granularity of the sub-band of channel information #1. A quantity of sub-bands of channel information fed back to the network device can be reduced by increasing the granularity of a sub-band, to reduce feedback overheads.

[00326] Method 2: Adjust a number of layers of channel information #1. Petition 870250105060, dated 11 / 17 / 2025, pp. 89 / 204 83 / 188

[00327] For example, a portion of the layers can be selected from a plurality of initial channel information layers and fed back to the network device. The number of layers in channel information #1 is a portion of the layers. In this case, the number of layers in channel information #1 is less than the number of layers in the initial channel information.

[00328] For example, the number of initial channel information layers is 2, and one layer is selected from the two layers and fed back to the network device. The number of channel information layers #1 is 1.

[00329] A smaller number of channel #1 information layers indicates lower feedback overheads for channel #1 information.

[00330] In this way, feedback overheads can be controlled by the number of channel information layers #1. Channel information feedback overheads can be reduced by reducing the number of channel information layers actually fed back to the network device.

[00331] Method 3: Adjust the precision of the scalar quantization.

[00332] Optionally, step 510 may include: performing scalar quantization on the initial channel information based on the first feedback configuration to generate channel information #1.

[00333] In other words, channel information is reported in scalar quantization mode.

[00334] For example, the data in the initial channel information is in float16 format, and each piece of data in the initial channel information is converted to int8 format in scalar quantization mode. The data in channel information #1 is in int8 format. Petition 870250105060, dated 11 / 17 / 2025, pp. 90 / 204 84 / 188

[00335] Channel #1 information is obtained through scalar quantization. Lower quantization precision of scalar quantization indicates lower feedback overheads for channel #1 information.

[00336] In this way, feedback overheads can be controlled by the quantization precision of the scalar quantization. Feedback overheads of channel information can be reduced by reducing the scalar quantization precision.

[00337] Method 1 and method 3 can be used in combination. To be more specific, the number of sub-bands in channel #1 information is less than the number of sub-bands in the initial channel information, and channel #1 information is obtained through scalar quantization.

[00338] For example, step 510 may include: performing scalar quantization on channel information #1-1 to generate channel information #1, where channel information #1-1 is a part of the plurality of sub-bands of the initial channel information.

[00339] A portion of the sub-bands is selected from the plurality of sub-bands of the initial channel information to obtain channel information #1-1, and scalar quantization is performed on each element in channel information #1-1, where the quantized channel information #1-1 is channel information #1.

[00340] For example, step 510 might include: performing scalar quantization on the initial channel information to obtain channel information #1-2; and selecting a portion of the subbands from a plurality of subbands of channel information #1-2 to generate channel information #1, where the selected portion of the subbands from channel information #1-2 is channel information #1.

[00341] In this way, feedback overheads can be Petition 870250105060, dated 11 / 17 / 2025, pp. 91 / 204 85 / 188 controlled by a number of sub-bands selected from the initial channel information (i.e., the number of sub-bands from channel information #1) and by the precision of the scalar quantization.

[00342] For example, step 510 might include: increasing the granularity of the sub-band of the initial channel information to obtain channel information #1-3; and performing scalar quantization on each element in channel information #1-3 to generate channel information #1.

[00343] In this way, feedback overheads can be controlled by the granularity of the sub-band of channel #1 information and by the precision of the scalar quantization.

[00344] For example, step 510 might include: increasing the sub-band granularity of the initial channel information to obtain channel information #1-3; selecting a portion of the sub-bands from a plurality of sub-bands of channel information #1-3 to obtain channel information #1-4; and performing scalar quantization on each element in channel information #1-4 to generate channel information #1.

[00345] In this way, feedback overheads can be controlled by a number of sub-bands selected from the initial channel information, the granularity of the sub-band of channel information #1 and the precision of the scalar quantization.

[00346] It should be understood that the preceding descriptions are merely examples, and method 1 and method 3 may alternatively be combined in another way. This is not limited to this embodiment of this application.

[00347] Method 2 and method 3 can be used in combination. To be more specific, the number of layers of channel #1 information is less than the number of layers of the initial channel information, and channel #1 information is obtained through scalar quantization. Petition 870250105060, dated 11 / 17 / 2025, pp. 92 / 204 86 / 188

[00348] For example, step 510 may include: performing scalar quantization on channel information #1-5 to generate channel information #1, where channel information #1-5 is a part of the plurality of layers of the initial channel information.

[00349] The layer portion is selected from the plurality of layers of the initial channel information to obtain channel information #1-5, and scalar quantization is performed on each element in channel information #1-5, where the quantized channel information #1-5 is channel information #1.

[00350] In this way, feedback overheads can be controlled by the number of channel #1 information layers and the accuracy of scalar quantization.

[00351] It should be understood that the preceding descriptions are merely examples, and method 2 and method 3 may alternatively be combined in another way. This is not limited to this modality of this application.

[00352] Method 4: Adjust a related quantization setting based on the codebook.

[00353] Optionally, step 510 may include: processing the initial channel information based on the first feedback configuration and a codebook to generate channel information #1.

[00354] In other words, channel information is reported in a codebook-based mode. For specific descriptions, see feedback mode 2 above. The details are not described again in this document.

[00355] Channel #1 information is obtained through codebook-based quantization. During codebook-based quantization, channel #1 information is represented by a selected basis and a different coefficient. Petition 870250105060, dated 11 / 17 / 2025, pp. 93 / 204 87 / 188 of zero selected. A smaller number of selected bases indicates lower precision of channel #1 information and lower overhead for transmitting channel #1 information. A smaller number of selected non-zero coefficients indicates lower precision of channel #1 information and lower overhead for transmitting channel #1 information. Lower non-zero quantization coefficient precision indicates lower precision of channel #1 information and lower overhead for transmitting channel #1 information.

[00356] In this way, feedback overheads can be controlled by a number of selected bases, a number of selected non-zero coefficients, and the quantization precision of non-zero coefficients. Feedback overheads of channel information can be reduced by reducing the number of selected bases, the number of selected non-zero coefficients, or the quantization precision of the non-zero coefficient.

[00357] Method 1 and Method 4 can be used in combination. To be more specific, the number of sub-bands in channel #1 information is less than the number of sub-bands in the initial channel information, and channel #1 information is obtained through codebook-based quantization.

[00358] For example, step 510 might include: performing codebook-based quantization on channel information #1-6 to obtain channel information #1, where channel information #1-6 is a part of the plurality of sub-bands of the initial channel information.

[00359] The sub-band portion is selected from the plurality of sub-bands of the initial channel information to obtain channel information #1-6, and codebook-based quantization is performed on channel information #1-6, where the processed channel information is channel information #1.

[00360] In this way, feedback overheads can be Petition 870250105060, dated 11 / 17 / 2025, pp. 94 / 204 88 / 188 controlled by a number of sub-bands selected from the initial channel information, a number of bases selected, a number of non-zero coefficients selected, and quantization precision of non-zero coefficients.

[00361] For example, step 510 may include: increasing the sub-band granularity of the initial channel information to obtain channel information #1-7; and codebook-based quantization is performed on channel information #1-7, where the processed channel information is channel information #1.

[00362] In this way, feedback overheads can be controlled by the granularity of the sub-band of channel #1 information, a number of selected bases, a number of selected non-zero coefficients, and the quantization precision of non-zero coefficients.

[00363] It should be understood that the preceding descriptions are merely examples, and method 1 and method 4 may alternatively be combined in another way. This is not limited to this modality of this application.

[00364] Method 2 and Method 4 can be used in combination. To be more specific, the number of layers of channel #1 information is less than the number of layers of the initial channel information, and channel #1 information is obtained through codebook-based quantization.

[00365] For example, step 510 might include: performing codebook-based quantization on channel information #1-8 to generate a CSI report, where channel information #1-8 is part of the plurality of layers of the initial channel information.

[00366] The layer portion is selected from the plurality of layers of the initial channel information to obtain channel information #1-8, and the quantization is based on the book of Petition 870250105060, dated 11 / 17 / 2025, pages 95 / 204 The 89 / 188 code is performed on channel information #1-8, where the processed channel information is channel information #1.

[00367] In this way, feedback overheads can be controlled by the number of channel #1 information layers, the number of selected bases, the number of selected non-zero coefficients, and the quantization precision of non-zero coefficients.

[00368] It should be understood that the previous descriptions are merely examples, and method 2 and method 4 may alternatively be combined in another way. This is not limited to this modality of this application.

[00369] The feedback overheads for channel information are based on a feedback configuration. The feedback overheads for channel information #1 are based on the first feedback configuration. The feedback overheads for channel information #2 are based on the second feedback configuration.

[00370] The first feedback configuration is different from the second feedback configuration.

[00371] A configuration item in the first feedback configuration can be the same as or different from a configuration item in the second feedback configuration.

[00372] The feedback overheads of channel #1 information can be adjusted by adjusting the parameter values ​​of one or more configuration items in the first feedback configuration.

[00373] For example, the configuration item for the first feedback configuration may include one or more of the following: a sub-band configuration of channel #1 information, a layer configuration of channel #1 information, a quantization precision configuration in feedback mode based on scalar quantization, a configuration Petition 870250105060, dated 11 / 17 / 2025, pp. 96 / 204 90 / 188 basis in codebook-based quantization-based feedback mode, a non-zero coefficient setting in codebook-based quantization-based feedback mode, or similar.

[00374] For example, the sub-band configuration of channel #1 information may indicate one or more of the following: the number of sub-bands of channel #1 information, a sub-band of channel #1 information, the granularity of the sub-band of channel #1 information, or similar.

[00375] In other words, the sub-band configuration of channel information #1 may indicate one or more of the following: a number of sub-bands in the initial channel information that are actually fed back to the network device, a specific sub-band in the initial channel information that is actually fed back to the network device, a granularity of sub-bands in the channel information that are actually fed back to the network device, or something similar.

[00376] For example, the channel information layer #1 configuration may indicate one or more of the following: the number of channel information layers #1, an identifier for a channel information layer #1, or similar.

[00377] In other words, the configuration of the channel information layer #1 may indicate one or more of the following: a number of layers in the initial channel information that are actually fed back to the network device, a specific layer in the initial channel information that is actually fed back to the network device, and the like.

[00378] The quantization precision setting in feedback mode based on scalar quantization can indicate the quantization precision used for scalar quantization when channel #1 information is obtained through scalar quantization.

[00379] the basic configuration in codebook-based quantization-based feedback mode is a Petition 870250105060, dated 11 / 17 / 2025, pp. 97 / 204 91 / 188 related configuration to represent a base of channel #1 information, i.e., a related configuration of a selected base, when channel #1 information is obtained through codebook-based quantization.

[00380] For example, the basis setting in codebook-based quantization feedback mode may indicate one or more of the following: a number of bases selected in codebook-based quantization feedback mode, a base selected in codebook-based quantization feedback mode, or similar. The basis may include a space domain basis and a frequency domain basis.

[00381] In other words, the basis configuration in codebook-based quantization feedback mode can indicate one or more of the following: a number of bases selected during codebook-based quantization, a specific selected base, and the like.

[00382] a non-zero coefficient setting in codebook-based quantization feedback mode is a related setting to represent a non-zero coefficient of channel #1 information, i.e., a related setting of a selected non-zero coefficient, when channel #1 information is obtained through codebook-based quantization.

[00383] For example, the non-zero coefficient setting in codebook-based quantization feedback mode may indicate one or more of the following: a number of non-zero coefficients selected in codebook-based quantization feedback mode, a non-zero coefficient selected in codebook-based quantization feedback mode, non-zero coefficient quantization precision selected in codebook-based quantization feedback mode Petition 870250105060, dated 11 / 17 / 2025, pp. 98 / 204 92 / 188 based on codebook or similar.

[00384] In other words, the non-zero coefficient setting in codebook-based quantization feedback mode may indicate one or more of the following: a number of non-zero coefficients selected during codebook-based quantization, a specific selected non-zero coefficient, quantization precision used to quantize the non-zero coefficient, and the like.

[00385] The first feedback configuration can be predefined, or it can be configured by the network device, or it can be determined by the terminal device.

[00386] One way to determine the first feedback configuration is described below based on example 1 to example 3.

[00387] Example 1:

[00388] In example 1, all parameter values ​​in the first feedback configuration are predefined or configured by the network device. The channel information reported by the terminal device based on the first feedback configuration is channel information #1. In this case, the size of channel information #1 is predefined or determined by the network device.

[00389] For example, any one or more of the following may be predefined or may be configured by the network device: the number of sub-bands of channel #1 information, an identifier of the sub-band of channel #1 information, the granularity of the sub-band of channel #1 information, the number of layers of channel #1 information, the identifier of the layer of channel #1 information, the quantization precision in scalar quantization-based feedback mode, the number of bases selected in codebook-based quantization-based feedback mode, Petition 870250105060, dated 11 / 17 / 2025, pp. 99 / 204 93 / 188 a basis identifier in codebook-based quantization feedback mode, the number of non-zero coefficients in codebook-based quantization feedback mode, a non-zero coefficient identifier in codebook-based quantization feedback mode, the quantization precision of the non-zero coefficient in codebook-based quantization feedback mode, or similar.

[00390] For example, all parameter values ​​in the first feedback configuration are predefined.

[00391] Alternatively, all parameter values ​​in the first feedback configuration are set by the network device.

[00392] Alternatively, some of the parameter values ​​in the first feedback configuration are predefined, and the other part of the parameter values ​​is configured by the network device.

[00393] Optionally, before step 510, step 500 may also include: The terminal device receives indication information #1 sent by the network device, where indication information #1 indicates some or all of the parameter values ​​in the first feedback configuration.

[00394] Example 2:

[00395] In example 2, the parameter values ​​of one part of the configuration items in the first feedback configuration are predefined or configured by the network device, and the parameter values ​​of the other part of the configuration items are determined by the terminal device. The terminal device can report channel information based on the first feedback configuration.

[00396] In one possible implementation, a size range Petition 870250105060, dated 11 / 17 / 2025, pages 100 / 204 94 / 188 of the channel #1 information is predefined or determined by the network device. The terminal device can determine a specific size of the channel #1 information within the range. The range of the channel #1 information size is a feedback overhead range.

[00397] The following are examples for description with reference to example 2-1 and example 2-3.

[00398] Example 2-1:

[00399] The ranges for part or all configuration items in the first feedback configuration are configured by the network device or are predefined. The terminal device can determine parameter values ​​for part or all configuration items within the ranges for part or all configuration items.

[00400] For example, the ranges of all configuration items in the first feedback configuration are configured by the network device or are predefined, and the terminal device can determine parameter values ​​for all configuration items within the ranges of the configuration items.

[00401] In this case, a range of channel #1 information size is predefined or determined by the network device. The terminal device can determine a specific size of channel #1 information within the range.

[00402] For another example, the ranges of one part of the configuration items in the first feedback configuration are configured by the network device or are predefined, and the parameter values ​​of the other part of the configuration items are determined by the network device or are predefined. The terminal device can determine parameter values ​​of the configuration items part within the ranges of the configuration items part. Petition 870250105060, dated 11 / 17 / 2025, pages 101 / 204 95 / 188

[00403] In this case, a range of channel #1 information size is predefined or determined by the network device. The terminal device can determine a specific size of channel #1 information within the range.

[00404] Optionally, method 500 may also include: The terminal device determines a parameter value of a first configuration item in the first feedback configuration based on a range of the first configuration item.

[00405] The terminal device determines the parameter value of the first configuration item based on the range of the first configuration item.

[00406] The first configuration item only indicates that a range of the configuration item is specified by the network device or is predefined, but does not constitute other limitations. In other words, among the configuration items in the first feedback configuration, a configuration item whose range is specified by the network device or a configuration item whose range is predefined can be referred to as the first configuration item.

[00407] The first configuration item may include some or all of the configuration items in the first feedback configuration.

[00408] For example, the first configuration item may include one or more of the following: the sub-band configuration of channel #1 information, the layer configuration of channel #1 information, the quantization precision configuration in feedback mode based on scalar quantization, the base configuration in feedback mode based on codebook quantization, the non-zero coefficient configuration in feedback mode based on codebook quantization, or similar. Petition 870250105060, dated 11 / 17 / 2025, pages 102 / 204 96 / 188

[00409] The terminal device can notify the network device about a parameter value determined by the terminal device.

[00410] Optionally, method 500 may also include: The terminal device sends indication information #2 (an example of the eleventh indication information) to the network device, where indication information #2 indicates parameter values ​​for some or all configuration items. For example, some or all configuration items may include the first configuration item.

[00411] For example, indication information #2 may indicate one or more of the following: the sub-band of channel information #1, the layer of channel information #1, the quantization precision in scalar quantization-based feedback mode, the base in codebook-based quantization-based feedback mode, the selected non-zero coefficient in codebook-based quantization-based feedback mode, the quantization precision of the selected non-zero coefficient in codebook-based quantization-based feedback mode, or similar.

[00412] In other words, indication information #2 may indicate one or more of the following: a specific selected sub-band, a specific selected layer, scalar quantization precision, a specific selected basis, a specific selected non-zero coefficient, non-zero coefficient quantization precision, or similar.

[00413] The interval of the first configuration item can be configured by the network device or can be predefined.

[00414] Optionally, before step 510, step 500 may also include: The terminal device receives indication information #3 (an example of ninth indication information) Petition 870250105060, dated 11 / 17 / 2025, pp. 103 / 204 97 / 188 sent by the network device, where indication information #3 indicates the range of the first configuration item.

[00415] Next, we describe the scope of the first configuration item with reference to examples.

[00416] The first configuration item may include the sub-band configuration of channel information #1.

[00417] A range of the sub-band configuration of channel #1 information may include at least one of the following: a range of values ​​for the number of sub-bands of channel #1 information, a set of combinations of sub-bands of channel #1 information, or a range of values ​​for the granularity of sub-bands of channel #1 information.

[00418] The range of values ​​for the number of sub-bands can be a range of continuous values ​​or a range of discontinuous values. The terminal device can determine a specific value from the range of values, to be specific, determine a selected number of sub-bands, and then determine a specific sub-band to be selected. The indication information #2 can indicate a sub-band selected by the terminal device.

[00419] For example, the range of values ​​for the number of sub-bands in channel #1 information can be as follows: The number of sub-bands in channel #1 information is greater than or equal to 1 and less than or equal to 3. In this case, the number of sub-bands selected by the terminal device from the initial channel information is greater than or equal to 1 and less than or equal to 3. For example, the terminal device selects one sub-band from the plurality of sub-bands in the initial channel information for feedback.

[00420] For another example, the range of values ​​for the number of sub-bands in channel #1 information could be {2, 4}. In this case, the number of sub-bands selected by the terminal device from the initial channel information could be 2. Petition 870250105060, dated 11 / 17 / 2025, pages 104 / 204 98 / 188 or 4. For example, the terminal device selects four subbands from the plurality of subbands of the initial channel information for feedback.

[00421] An element in the set of sub-band combinations of channel information #1 may be a sub-band combination that can be selected by the terminal device. The terminal device may determine a specific element of the set, to be more specific, determine a specific sub-band combination to be used. Indication information #2 may indicate a sub-band selected by the terminal device.

[00422] Combinations may include equal or different numbers of sub-bands.

[00423] For example, a combination of sub-bands can be represented by a combination of sub-band numbers.

[00424] For example, the set of sub-band combinations from channel information #1 could be {(1, 3), (1, 4)}. In this case, a sub-band selected by the terminal device from the initial channel information could be a sub-band numbered 1 and a sub-band numbered 4, or a sub-band numbered 1 and a sub-band numbered 3. For example, the terminal device selects sub-band numbered 1 and sub-band numbered 4 from the initial channel information and feeds the sub-bands back to the network device.

[00425] The range of values ​​for the sub-band granularity can be a range of continuous values ​​or a range of discontinuous values. The terminal device can determine a specific value from the range of values, to be more specific, determine a selected sub-band granularity. The indication information #2 can indicate the sub-band granularity.

[00426] For example, the range of values ​​for the granularity of the sub-band of channel #1 information could be as follows: A Petition 870250105060, dated 11 / 17 / 2025, pages 105 / 204 99 / 188 The granularity of the sub-band of channel #1 information is greater than or equal to 5 RBs. In this case, the terminal device can determine that the granularity of the sub-band of channel #1 information is greater than or equal to 5 RBs. For example, the terminal device determines that the granularity of the sub-band of channel #1 information is 6 RBs.

[00427] For another example, the range of values ​​for the granularity of the sub-band of channel #1 information can be {4, 6}. In this case, the terminal device can determine that the granularity of the sub-band of channel #1 information is 4 or 6. For example, the terminal device can determine that the granularity of the sub-band of channel #1 information is 6 RBs.

[00428] It should be understood that the above range is merely an example and does not constitute any limitation to the solution in this modality of this request.

[00429] The first configuration item may include configuring the channel information layer #1.

[00430] A range of the channel information #1 layer configuration can include at least one of the following: a range of values ​​for the number of channel information #1 layers or a set of combinations of channel information #1 layers.

[00431] The range of values ​​for the number of layers can be a continuous range of values ​​or a discontinuous range of values. The terminal device can determine a specific value from the range of values, to be specific, determine a selected number of layers, and then determine a specific layer to be selected. The indication information #2 can indicate a layer selected by the terminal device.

[00432] For example, the range of values ​​for the number of layers of information in channel #1 could be as follows: The number of layers of information in channel #1 is greater than or equal to Petition 870250105060, dated 11 / 17 / 2025, pages 106 / 204 100 / 188 to 1 and less than or equal to 2. In this case, the number of layers selected by the terminal device from the initial channel information is greater than or equal to 1 and less than or equal to 2. For example, the terminal device selects one layer from the plurality of initial channel information layers for feedback.

[00433] For another example, the range of values ​​for the number of layers of channel information #1 can be {1, 3}. In this case, the number of layers selected by the terminal device from the initial channel information can be 1 or 3. For example, the terminal device selects one layer from the plurality of layers of initial channel information for feedback.

[00434] An element in the set of layer combinations of channel information #1 can be a layer combination that can be selected by the terminal device. The terminal device can determine a specific element of the set, that is, determine a specific layer combination to be used. The indication information #2 can indicate a layer selected by the terminal device.

[00435] Combinations can include equal or different numbers of layers.

[00436] For example, a combination of layers can be represented by a combination of layer numbers.

[00437] For example, the set of layer combinations from channel information #1 could be {(1, 2), (1, 3)}. In this case, a layer selected by the terminal device from the initial channel information could be a layer numbered 1 and a layer numbered 2, or a layer numbered 1 and a layer numbered 3. For example, the terminal device selects layer numbered 1 and layer numbered 2 from the initial channel information and passes the layers to the network device.

[00438] It should be understood that the above track is merely a Petition 870250105060, dated 11 / 17 / 2025, pages 107 / 204 101 / 188 example and does not constitute any limitation to the solution in this modality of this request.

[00439] The first configuration item may include the quantization precision setting in feedback mode based on scalar quantization.

[00440] A range of quantization precision setting in feedback mode based on scalar quantization can be a range of quantization precision values ​​in feedback mode based on scalar quantization.

[00441] The terminal device can determine a specific value from the range of values, to be more specific, determine the quantization precision to be used. Indication information #2 can indicate the quantization precision to be used by the terminal device in feedback mode based on scalar quantization.

[00442] For example, the range of values ​​for quantization precision can be represented by a set of scalar quantization types.

[00443] For example, the range of values ​​for quantization precision in scalar quantization-based feedback mode can be {int8, float16}. In this case, the terminal device can determine that an element in channel information #1 is in either int8 or float16 format. For example, the terminal device converts an element in the initial channel information to int8 format.

[00444] It should be understood that the above range is merely an example and does not constitute any limitation to the solution in this modality of this request.

[00445] The first configuration item may include the basic configuration in feedback mode based on codebook-based quantization.

[00446] A range of the base configuration in the mode of Petition 870250105060, dated 11 / 17 / 2025, pages 108 / 204 102 / 188 codebook-based quantization feedback may include at least one of the following: a range of values ​​of the quantity of bases selected in codebook-based quantization feedback mode, or a set of base combinations in codebook-based quantization feedback mode.

[00447] The range of values ​​for the number of bases in codebook-based quantization feedback mode can be a range of continuous values ​​or a range of discontinuous values. The terminal device can determine a specific value from the range of values, to be specific, determine a selected number of bases, and then determine a specific base to be selected. Indication information #2 can indicate a base selected by the terminal device.

[00448] For example, the range of values ​​for the number of bases selected in codebook-based quantization feedback mode can be represented by a range of values ​​for a number of spatial domain bases selected and a range of values ​​for a number of frequency domain bases selected.

[00449] For example, the range of values ​​for the number of bases selected in codebook-based quantization feedback mode may include: The number of spatial domain bases selected is greater than or equal to 5 and less than or equal to 10, and the number of frequency domain bases selected is greater than or equal to 5 and less than or equal to 10. For example, the terminal device selects six spatial domain bases from spatial domain bases defined in a codebook and selects eight frequency domain bases.

[00450] For another example, the range of values ​​for the number of bases selected in feedback mode based on Petition 870250105060, dated 11 / 17 / 2025, pages 109 / 204 103 / 188 codebook-based quantization may include: The range of values ​​for the number of spatial domain bases selected is {6, 8, 10}, and the range of values ​​for the number of frequency domain bases selected is {6, 8, 10}. For example, the terminal device selects six spatial domain bases from spatial domain bases defined in a codebook and selects eight frequency domain bases.

[00451] For example, the range of values ​​of the selected base quantities in codebook-based quantization feedback mode can be represented by a set of combinations of selected spatial domain base quantities and selected frequency domain base quantities.

[00452] For example, the range of values ​​for the number of bases selected in codebook-based quantization feedback mode can include {(6, 8), (8, 6), (6, 10)}. In each combination, the 1st item can be a number of selected spatial domain bases and the 2nd item can be a number of selected frequency domain bases. The 1st combination is six spatial domain bases and eight frequency domain bases, and so on. For example, the terminal device selects the 1st combination of spatial domain bases defined in a codebook; to be specific, it selects six spatial domain bases and eight frequency domain bases.

[00453] An element in the set of basis combinations selected in codebook-based quantization feedback mode can be a basis combination that can be selected by the terminal device. The terminal device can determine a specific element of the set, to be more specific, determine a specific basis combination to be used. The indication information #2 can indicate a basis selected by the terminal device. For example, the Petition 870250105060, dated 11 / 17 / 2025, pp. 110 / 204 104 / 188 indication information #2 may indicate a number from a combination. For another example, indication information #2 may indicate a number from a base.

[00454] Combinations can include equal or different quantities of bases.

[00455] For example, a selected base combination can be represented by a combination of base numbers.

[00456] For example, a selected set of basis combinations may include a selected set of spatial domain basis combinations and a selected set of frequency domain basis combinations.

[00457] For example, the set of spatial domain basis combinations can be {(1, 2, 3), (1, 3, 4)}, and the set of frequency domain basis combinations can be {(2, 3, 4), (1, 2, 4)}. The terminal device selects the 1st element from the set of spatial domain basis combinations and selects the 2nd element from the set of frequency domain basis combinations. To be specific, the terminal device selects a spatial domain basis numbered 1, a spatial domain basis numbered 2, a spatial domain basis numbered 3, a frequency domain basis numbered 1, a frequency domain basis numbered 2, and a frequency domain basis numbered 4.

[00458] For example, a selected set of basis combinations may include a set of spatial domain basis combinations and frequency domain basis combinations.

[00459] For example, the set of basis combinations could be {[(1, 2, 3), (2, 3, 4)], [(1, 3, 4), (1, 2, 4)]}. The first item in each element is a spatial domain basis combination, and the second item in each element is a frequency domain basis combination. The terminal device selects the first element from the set. To be specific, the terminal device selects a spatial domain basis numbered 1, a frequency domain basis Petition 870250105060, dated 11 / 17 / 2025, pp. 111 / 204 105 / 188 spatial numbered 2, a spatial domain numbered 3, a frequency domain numbered 2, a frequency domain numbered 3, and a frequency domain numbered 4.

[00460] It should be understood that the above range is merely an example and does not constitute any limitation to the solution in this modality of this request.

[00461] The first configuration item may include setting a non-zero coefficient in feedback mode based on codebook-based quantization.

[00462] A range of non-zero coefficient configuration in codebook-based quantization feedback mode may include at least one of the following: a range of values ​​of a quantity of non-zero coefficients selected in codebook-based quantization feedback mode, or a range of values ​​of non-zero coefficient quantization precision selected in codebook-based quantization feedback mode.

[00463] The range of values ​​for the number of non-zero coefficients selected in codebook-based quantization feedback mode can be a range of continuous values ​​or a range of discontinuous values. The terminal device can determine a specific value from the range of values, to be specific, determine a selected number of non-zero coefficients, and then determine a specific non-zero coefficient to be selected. Indication information #2 can indicate a non-zero coefficient selected by the terminal device.

[00464] For example, the range of values ​​of the quantity of non-zero coefficients selected in feedback mode based on codebook-based quantization Petition 870250105060, dated 11 / 17 / 2025, pp. 112 / 204 106 / 188 may include: The number of non-zero coefficients is greater than or equal to 5 and less than or equal to 10. For example, the terminal device selects six non-zero coefficients from coefficients corresponding to the selected frequency domain and space domain bases.

[00465] For another example, the range of values ​​for the number of non-zero coefficients selected in codebook-based quantization feedback mode may include: The range of values ​​for the number of non-zero coefficients is {6, 8, 10}. For example, the terminal device selects six non-zero coefficients from coefficients corresponding to the selected frequency domain and space domain bases.

[00466] The first configuration item may include non-zero coefficient quantization precision selected in feedback mode based on codebook-based quantization.

[00467] A range of non-zero coefficient quantization precision selected in codebook-based quantization feedback mode can be a range of values ​​of non-zero coefficient quantization precision selected in codebook-based quantization feedback mode.

[00468] The terminal device can determine a specific value from the range of values, to be more specific, determine the quantization precision to be used. Indication information #2 can indicate the non-zero coefficient quantization precision used by the terminal device in feedback mode based on codebook-based quantization.

[00469] For example, the range of values ​​for quantization precision can be represented by a set of scalar quantization types. Petition 870250105060, dated 11 / 17 / 2025, pp. 113 / 204 107 / 188 [O0470] For example, the range of values ​​for the non-zero coefficient quantization precision in codebook-based quantization feedback mode can be {int8, float16}. In this case, the terminal device can determine whether to convert the non-zero coefficient to an int8 or float16 format.

[00471] It should be understood that the above range is merely an example and does not constitute any limitation to the solution in this modality of this request.

[00472] Example 2-2:

[00473] A correspondence between parameter values ​​of some or all configuration items in the first feedback configuration can be predefined or can be determined by the network device. The terminal device can determine specific values ​​of some of the parameters in the first feedback configuration and determine specific values ​​of the corresponding parameters based on the correspondence between the parameter values ​​of some or all configuration items.

[00474] For example, a correspondence between parameter values ​​of all configuration items in the first feedback configuration can be predefined or can be determined by the network device. The terminal device can determine specific values ​​for a portion of the parameters in the first feedback configuration and determine specific values ​​for the corresponding parameters based on the correspondence between all configuration items.

[00475] In this case, a range of channel #1 information size is predefined or determined by the network device. The terminal device can determine a specific size of channel #1 information within the range.

[00476] Optionally, method 500 may include: The Petition 870250105060, dated 11 / 17 / 2025, pp. 114 / 204 The 108 / 188 terminal device determines parameter values ​​for a plurality of configuration items in the first feedback configuration based on a correspondence between the parameter values ​​of the plurality of configuration items.

[00477] Specifically, a parameter value of a second configuration item in the first feedback configuration is based on a parameter value of a third configuration item in the first feedback configuration and on the correspondence between the parameter values ​​of the plurality of configuration items in the first feedback configuration, and the third configuration item and the second configuration item belong to the plurality of configuration items.

[00478] The terminal device can determine the value of the second configuration item parameter based on the value of the third configuration item parameter and the correspondence.

[00479] For example, the parameter value of the third configuration item can be determined by the terminal device.

[00480] To be specific, the terminal device determines a portion of the parameter values ​​of the plurality of configuration items, for example, the parameter value of the third configuration item; and determines a corresponding parameter value, for example, the parameter value of the second configuration item, based on the portion of the parameter values ​​and the correspondence between the parameter values ​​of the plurality of configuration items.

[00481] For example, the plurality of configuration items may include at least two of the following: the sub-band configuration of channel #1 information, the layer configuration of channel #1 information, the quantization precision configuration in feedback mode based on scalar quantization, the base configuration in feedback mode based on codebook quantization, the non-zero coefficient configuration in feedback mode with Petition 870250105060, dated 11 / 17 / 2025, pages 115 / 204 109 / 188 based on quantization based on codebooks or similar.

[00482] The terminal device can notify the network device about a parameter value determined by the terminal device.

[00483] Optionally, method 500 may also include: The terminal device sends indication information #2 to the network device, where indication information #2 indicates parameter values ​​for some or all configuration items. For example, some or all configuration items may include a plurality of configuration items.

[00484] The correspondence between the parameter values ​​of the plurality of configuration items can be predefined or can be configured by the network device.

[00485] Optionally, before step 510, step 500 may also include: The terminal device receives indication information #4 (an example of the tenth indication information) sent by the network device, where indication information #4 indicates the correspondence between the parameter values ​​of the plurality of configuration items.

[00486] Table 3 shows an example of a correspondence between a layer configuration parameter value and a sub-band configuration parameter value. Specifically, Table 3 shows an example of a correspondence between the number of layers of channel information #1, a number of ports, and the number of sub-bands of channel information #1. The number of ports can be configured by the network device. Table 3 Petition 870250105060, dated 11 / 17 / 2025, pages 116 / 204 110 / 188 Number of ports Number of layers fed back to the network device Number of sub-bands fed back to the network device 1 16 1 16 2 16 2 8 3 32 1 8 4 32 2 4

[00487] For example, the terminal device can determine the number of layers of channel #1 information and determine the number of sub-bands of channel #1 information based on the number of layers and the correspondence shown in Table 3. For example, the number of ports configured by the network device is 16; and the terminal device determines that the number of layers of channel #1 information is 1 and determines, based on the correspondence shown in Table 3, that the number of sub-bands of channel #1 information is 16.

[00488] Alternatively, the terminal device can determine the number of sub-bands of channel #1 information and determine the number of layers of channel #1 information based on the number of sub-bands and the correspondence shown in Table 3. For example, the number of ports configured by the network device is 32; and the terminal device determines that the number of sub-bands of channel #1 information is 8 and determines, based on the correspondence shown in Table 3, that the number of layers of channel #1 information is 1.

[00489] It should be understood that Table 3 is merely an example and does not constitute any limitation to the solution in this embodiment of this application. For example, the plurality of configuration items may alternatively be other configuration items. For example, in this embodiment of this application, the Petition 870250105060, dated 11 / 17 / 2025, pp. 117 / 204 111 / 188 The correspondence between the parameter values ​​of the plurality of configuration items may alternatively be a correspondence between parameter values ​​of configuration items of another quantity. For example, the correspondence between the parameter values ​​of the plurality of configuration items may be a correspondence between the number of layers of channel #1 information, the number of sub-bands of channel #1 information, and the quantization precision in feedback mode based on scalar quantization.For another example, the correspondence between the parameter values ​​of the plurality of configuration items could be a correspondence between the number of layers of channel information #1, the number of non-zero coefficients selected in the codebook-based quantization feedback mode, and the quantization precision of non-zero coefficients selected in the codebook-based quantization feedback mode. For another example, the correspondence between the parameter values ​​of the plurality of configuration items could include a correspondence between the number of layers of channel information #1 and a combination of layers of channel information #1.

[00490] For example, indication information #2 may indicate a match, used by the terminal device, in the matching between the parameter values ​​of the plurality of configuration items. For example, a number of matches is predefined or a number of matches is configured by the network device. Indication information #2 may include the number of matches used by the terminal device. The network device may determine, based on the number of matches used by the terminal device, a parameter value used by the terminal device. Table 3 is used as an example. The number of ports Petition 870250105060, dated 11 / 17 / 2025, pages 118 / 204 The 112 / 188 configuration set by the network device is 16. The terminal device determines that the number of layers to be fed back to the network device is 1 and determines, based on the matching 1 shown in Table 3, that the number of sub-bands to be fed back to the network device is 16. The terminal device sends a number from the matching in Table 3, i.e., a number 1, to the network device to notify the network device that the terminal device uses matching 1. The numbering method in Table 3 is merely an example and does not constitute any limitation to the solution in this embodiment of this application.

[00491] For descriptions of indication information #2, see example 2-1. The details are not described again in this document.

[00492] Example 2-1 and Example 2-2 can be used interchangeably in combination. For example, the third configuration item can be the first configuration item, and the parameter value of the third configuration item can be determined based on a range of the third configuration item. For specific descriptions, see Example 21.

[00493] Example 2-3:

[00494] A range of accuracy for channel #1 information is configured by the network device or is predefined. The terminal device can determine, within the range of accuracy of channel #1 information, parameter values ​​for some or all of the configuration items in the first feedback configuration.

[00495] In this case, a range of channel #1 information size is predefined or determined by the network device. The terminal device can determine a specific size of channel #1 information within the range.

[00496] Optionally, method 500 may also include: The Petition 870250105060, dated 11 / 17 / 2025, pp. 119 / 204 The 113 / 188 terminal device determines the parameter values ​​for some or all configuration items in the first feedback configuration based on a threshold #1 (an example of a fourth threshold). The accuracy of the channel #1 information is greater than or equal to threshold #1.

[00497] The terminal device can notify the network device about a parameter value determined by the terminal device.

[00498] Optionally, method 500 may also include: The terminal device sends indication information #2 to the network device, where indication information #2 indicates parameter values ​​for some or all of the configuration items.

[00499] For descriptions of indication information #2, see example 2-1. The details are not described again in this document.

[00500] Optionally, before step 510, step 500 may also include: The terminal device receives indication information #5 (an example of eighth indication information) sent by the network device, where indication information #5 indicates the accuracy range of channel information #1, for example, it indicates threshold #1.

[00501] The accuracy of channel information can be indicated by a correlation or an error between the channel information and the reference channel information.

[00502] The reference channel information of the channel information may be initial channel information corresponding to the channel information, to be more specific, channel information obtained by the terminal device through measurement.

[00503] A higher correlation between channel information and reference channel information indicates greater accuracy of channel information. Petition 870250105060, dated 11 / 17 / 2025, pages 120 / 204 114 / 188

[00504] A smaller error between the channel information and the reference information of the channel information indicates greater accuracy of the channel information.

[00505] For example, the accuracy of channel #1 information can be represented by a correlation between channel #1 information and initial channel information.

[00506] For example, the accuracy of channel #1 information may be a generalized cosine similarity (generalized cosine similarity, GCS) or a generalized cosine squared similarity (generalized cosine squared similarity, SGCS) between channel #1 information and the initial channel information.

[00507] The SGCS is used as an example. For example, threshold #1 is 0.9, and the accuracy range of channel #1 information is a range of SGCS^0.9. The terminal device can determine the first feedback setting based on the actual status of channel #1 information, for example, overheads of channel #1 information, importance of each part of the initial channel information, and a similarity between different parts of the initial channel information, to allow the SGCS between channel #1 information and the initial channel information to be greater than or equal to 0.9.

[00508] For example, the accuracy of channel #1 information can be represented by an error between channel #1 information and the initial channel information.

[00509] For example, the accuracy of channel #1 information can be represented by a normalized mean square error (NMSE) between channel #1 information and the initial channel information.

[00510] The accuracy of channel #1 information can alternatively be represented by an error between channel #1 information and the initial channel information. A Petition 870250105060, dated 11 / 17 / 2025, pp. 121 / 204 115 / 188 accuracy range of channel #1 information may be as follows: The error between channel #1 information and the initial channel information is less than or equal to threshold #2. In this case, indication information #5 may alternatively indicate threshold #2.

[00511] If a feedback configuration is predefined, for example, the network device indicates a feedback configuration #1, the terminal device can determine whether to adjust feedback configuration #1. The terminal device can also send indication information to the network device to notify the network device whether the terminal device has adjusted feedback configuration #1. If feedback configuration #1 is adjusted, the indication information can indicate an adjusted feedback configuration #1, i.e., the first feedback configuration.

[00512] For example, the terminal device can determine, based on the overheads of channel #1 information in feedback configuration #1, whether to adjust feedback configuration #1. If the overheads of channel #1 information in feedback configuration #1 exceed the maximum code length supported by the UCI, feedback configuration #1 will be adjusted within the accuracy range of channel #1 information, so that the overheads of channel #1 information fall within a code length range supported by the UCI. If the overheads of channel #1 information in feedback configuration #1 are within a code length supported by the UCI, feedback configuration #1 can be used as the first feedback configuration.

[00513] The plurality of implementations in example 2 can be used independently or in combination.

[00514] For example, example 2-1 and example 2-2 are combined. A correspondence between parameter values ​​of Petition 870250105060, dated 11 / 17 / 2025, pp. 122 / 204 116 / 188 a portion of the configuration items in the first feedback configuration is configured by the network device or is predefined, and ranges of a plurality of configuration items in the first feedback configuration different from the portion of configuration items that are configured by the network device or are predefined.

[00515] For example, example 2-1 and example 2-3 are combined. The ranges of a portion of the configuration items in the first feedback configuration are configured by the network device or are predefined, and the accuracy range of channel information #1 is configured by the network device or is predefined.

[00516] For example, example 2-2 and example 2-3 are combined. A match between parameter values ​​of a portion of the configuration items in the first feedback configuration is configured by the network device or is predefined, and the accuracy range of channel #1 information is configured by the network device or is predefined.

[00517] For example, example 2-1, example 2-2, and example 2-3 are combined. A match between parameter values ​​of a portion of the configuration items in the first feedback configuration is configured by the network device or is predefined, ranges of a plurality of configuration items in the first feedback configuration different from the portion of configuration items are configured by the network device or are predefined, and the accuracy range of channel information #1 is configured by the network device or is predefined.

[00518] Example 3:

[00519] The terminal device determines the initial feedback configuration and then reports channel information based on the initial feedback configuration.

[00520] In example 3, the terminal device has freedom Petition 870250105060, dated 11 / 17 / 2025, pp. 123 / 204 117 / 188 total. For example, the terminal device can determine, based on the actual status of channel #1 information, for example, the overhead of channel #1 information, the importance of each part of the initial channel information, and a similarity between different parts of the initial channel information, to adjust the feedback overheads in one or more of the previous ways from 1 to 4, i.e., the terminal device can determine the first feedback configuration.

[00521] Optionally, method 500 may also include: The terminal device sends indication information #2 to the network device, where indication information #2 indicates parameter values ​​for some or all of the configuration items in the first feedback configuration.

[00522] If a feedback configuration is predefined, for example, the network device indicates a feedback configuration #1, the terminal device can determine whether to adjust feedback configuration #1. The terminal device can also send indication information to the network device to notify the network device whether the terminal device has adjusted feedback configuration #1. If feedback configuration #1 is adjusted, the indication information can indicate an adjusted feedback configuration #1, i.e., the first feedback configuration.

[00523] For example, the terminal device can determine, based on the overheads of channel #1 information in feedback configuration #1, whether to adjust feedback configuration #1. If the overheads of channel #1 information in feedback configuration #1 exceed the maximum code length supported by the UCI, feedback configuration #1 will be adjusted to bring the overheads of channel #1 information within a code length range supported by the UCI. If the overheads of Petition 870250105060, dated 11 / 17 / 2025, pages 124 / 204 If the 118 / 188 channel information #1 in feedback configuration #1 is within a code length range supported by the UCI, feedback configuration #1 can be used as the first feedback configuration.

[00524] In this mode of this request, channel #1 information can be transmitted using a UCI chunk.

[00525] In the solution in this embodiment of this application, the first feedback configuration allows the feedback overheads of the channel information to remain within the code length range supported by the UCI and ensures the accuracy of the channel information fed back to the network device. In this way, the terminal device reports channel information based on the first feedback configuration, to help ensure that the network device can obtain high-precision channel information using the UCI.

[00526] Fig. 9 is a schematic flowchart of another communication method according to a modality of this request.

[00527] As shown in FIG. 9, method 700 may include the following steps.

[00528] 710: A terminal device generates channel #3 information (an example of first channel information), where channel #3 information includes K segments, and K is an integer greater than 1. One type of channel #3 information is field truth channel information. The length of each segment is less than or equal to the limit #3 (an example of first limit). Channel #3 information is any of the following: a channel response, an eigenvector matrix of a channel, a pre-encoding matrix, an RSRP, or a SINR.

[00529] 720: The terminal device transmits part or all of the K UTI pieces to a network device, where the K UTI pieces correspond respectively to the K segments.

[00530] In this type of application, the ICU is a Petition 870250105060, dated 11 / 17 / 2025, pp. 125 / 204 119 / 188 information used before encoding. A UCI chunk can be understood as a sequence of UCI bits used before encoding; to be more specific, a sequence of bits on which channel encoding must be performed independently. After channel encoding is performed on the K UCI chunks separately, the K encoded UCI chunks can be transmitted using an uplink feature.

[00531] For example, the uplink resource can be a PUCCH or a PUSCH.

[00532] The fact that the K UCI chunks correspond respectively to the K segments indicates that each segment is transmitted as an independent UCI, that is, each UCI chunk includes the content of one segment. Channel encoding can be performed on the K segments separately. Transmitting the K UCI chunks is transmitting the K segments using the K UCI chunks respectively. The lengths of the K segments can be understood as the number of bits in the K segments, to be more specific, the number of bits in the K UCI chunks corresponding to the K segments.

[00533] For example, channel #3 information could be part 2 in a CSI report.

[00534] For example, threshold #3 is related to the maximum code length supported by the UCI. In other words, threshold #3 is determined based on the maximum code length supported by the UCI.

[00535] The maximum code length supported by UCI is a maximum code length supported by UCI that has not undergone channel coding.

[00536] Optionally, threshold #3 is less than or equal to the maximum code length supported by UCI.

[00537] For example, threshold #3 can be predefined or can be configured by the network device. Petition 870250105060, dated 11 / 17 / 2025, pp. 126 / 204 120 / 188

[00538] Optionally, the terminal device may receive indication information #10 (an example of first indication information) sent by the network device, and indication information #10 indicates threshold #3.

[00539] In the solution in this embodiment of this application, the field truth channel information is divided into a plurality of segments and transmitted using a plurality of UCI chunks, so that the network device can obtain channel information with high feedback overheads, i.e., high-precision channel information.

[00540] The field truth channel information has high accuracy and, consequently, also has high feedback overheads. The feedback overheads can exceed the maximum code length supported by the UCI. In the solution in this embodiment of this application, the length of each segment can be less than the maximum code length supported by the UCI, so that the segments can be transmitted using a plurality of UCI chunks.

[00541] For example, channel #3 information can be obtained by performing scalar quantization on the initial channel information.

[00542] For example, channel #3 information can be obtained by performing codebook-based quantization on the initial channel information.

[00543] For a specific feedback mode, see the descriptions in method 500. The details are not described again in this document. Alternatively, channel #3 information can be obtained in another feedback mode.

[00544] The K segments of channel #3 information can also be called the K parts of channel #3 information. To be more specific, channel #3 information is divided into K parts. Petition 870250105060, dated 11 / 17 / 2025, pp. 127 / 204 121 / 188

[00545] The lengths of the K segments can be equal or different. To be more specific, the K UCI chunks can include equal or different quantities of bits.

[00546] The following describes a method of division into K segments with reference to example 71 to example 73.

[00547] Example 71:

[00548] Optionally, the K segments can be determined based on the content of the K segments.

[00549] To be specific, the terminal device can segment channel #3 information based on specific information included in each segment.

[00550] For example, the content of each of the K segments can be predefined or can be configured by the network device.

[00551] In one possible implementation, channel #3 information can be obtained by performing scalar quantization on the initial channel information.

[00552] Optionally, a channel information dimension #3 obtained through scalar quantization is the same as a channel information dimension that has not undergone scalar quantization.

[00553] For example, channel #3 information could be a two-dimensional array with a dimension of FX Ntx. F indicates bandwidth. Ntx indicates the number of antenna ports on the network device.

[00554] For example, channel #3 information could be a three-dimensional array with a dimension of FX NtxX Nclassification. Nclassification indicates the number of classifications of an eigenvector.

[00555] For example, channel #3 information can be a three-dimensional matrix with a dimension of FX NtvX Nrv. Nrv indicates tx ixix, a quantity of antenna ports on the terminal device. Petition 870250105060, dated 11 / 17 / 2025, pages 128 / 204 122 / 188 [0055 6] the content of each of the K segments can be an element of the previous array. The terminal device can segment channel #3 information based on a specific element included in each segment.

[00557] For example, the content of each segment can be indicated by a dimension range corresponding to the segment. The dimension range corresponding to the segment is a range, in each dimension, of content included in the segment. The content of each segment is within the dimension range corresponding to the segment.

[00558] A dimension range corresponding to each segment can be predefined or can be configured by the network.

[00559] For example, the dimension range can be a continuous range or a discontinuous range.

[00560] An example where channel information #3 is a three-dimensional array with a dimension of FX NtxX Nclassification is below for description. To facilitate description, an example where the dimension indices of channel information #3 are consecutive indices is used below for description.

[00561] For example, a band of dimension corresponding to a segment m among the K segments may include at least one of the following: an xm-th sub-band for a (xm+1—1)-th sub-band, a ym-th network device antenna port for a (ym+1—1)-th network device antenna port, or a zm-th flow for a (zm+1—1)-th flow. xm, xm+1—1, ym, ym-1—1, zm, and zm+1—1 are positive integers. xm indicates a minimum value of a sub-band index in segment m, ym indicates a minimum value of a network device antenna port index in segment m, and zm indicates a minimum value of a flow index in segment m.

[00562] For example, the dimension range corresponding to segment m among the K segments may include the xm-th sub Petition 870250105060, dated 11 / 17 / 2025, pp. 129 / 204 123 / 188 band to the (xm+1— 1 )-th sub-band, the ym-th antenna port of the network device to the (ym+1— 1)-th antenna port of the network device and the zm-th stream to the (zm+1— 1)-th stream. Segment m includes an element, in channel information #3, that corresponds to a sub-band index within [xm, xm+1—1], a network device antenna port index within [ym, ym+1—1], and a flow index within [zm, Zm+1—1].

[00563] For another example, a range of dimension corresponding to a segment m among the K segments may include at least one of the following: xm' sub-bands starting from an xmth sub-band, ym' network device antenna ports starting at a ymth network device antenna port, or zm' flows from a zmth flow. xm', ym', and zm' are positive integers.

[00564] The preceding descriptions are merely examples of ways to represent a continuous band. A dimension band can also be represented in another way. This is not limited in this embodiment of this application. For example, the dimension band corresponding to segment m may include at least one of the following: a set of sub-bands, a set of network device antenna ports, or a set of streams. The elements of the set may be inconsecutive.

[00565] Alternatively, the content of each of the K segments can be determined by the terminal device.

[00566] For example, for channel #3 information obtained through scalar quantization, the terminal device can determine a dimension range corresponding to each segment.

[00567] In this case, the terminal device can notify the network device about the dimension range corresponding to each segment.

[00568] Furthermore, an order of elements in a segment Petition 870250105060, dated 11 / 17 / 2025, pages 130 / 204 124 / 188 can be predefined or configured by the network device. The order of elements in the segment is an order of elements in the corresponding UCI.

[00569] For example, in a segment, the elements in channel information #3 that belong to the segment are sorted sequentially in the following order: an ascending order of frequency domain indices, an ascending order of network device antenna port indices, and an ascending order of flow indices.

[00570] For example, for elements in segment m, the frequency domain indices are xm for xm+1—1, the network device antenna port indices are ym for ym+1—1, and the flow indices are zm for zm+1—1. After being sequentially sorted in ascending order of frequency domain indices, in ascending order of network device antenna port indices, and in ascending order of flow indices, the elements in segment m can be expressed as follows:(xm,ym,zm) ,(xm+1, ym,zm) , ···,(xm+1—1,ym,zm) ,(xm,ym+1,zm) ,(xm+1, ym+1, zm) , ···,(xm+1—1,ym+1, zm) ,(xm,ym+ 2, zm) ,(xm+ 1, ym+ 2, zm) , ···,(xm+1—1,ym+ 2, zm) , ···,(xm+1—1,ym+1— 1,zm ) ,(xm ,ym ,zm+ 1) ,(xm+ 1,ym ,zm+ 1), ···,(xm+1— 1,ym ,zm+1),(xm,ym+ 1, zm+ 1),(xm+ 1, ym+ 1, zm+1), ···,(xm+1 1,ym+ 1,zm+1), (xm, ym+ 2, zm+ 1),(xm+ 1, 1%+2, zm+1), ...,(xm+1 1, ym+2,zm+ 1), ...,( xm+1 -1,ym+1 -1,zm+1), ···,( xm+1 -1,ym+1 -1,zm+1 -1).

[00571] For another example, in a segment, the elements in channel information #3 that belong to the segment are sorted sequentially in the following order: an ascending order of network device antenna port indices, an ascending order of frequency domain indices, and an ascending order of flow indices.

[00572] For another example, in a segment, the elements in channel information #3 that belong to the segment are Petition 870250105060, dated 11 / 17 / 2025, pp. 131 / 204 125 / 188 sorted sequentially in the following order: a descending order of network device antenna port indices, a descending order of frequency domain indices, and a descending order of flow indices.

[00573] It should be understood that the previous descriptions are merely examples and do not constitute any limitation to the solution in this modality of this request.

[00574] Alternatively, the order of elements in a segment can be determined by the terminal device. In this case, the terminal device can notify the network device about the order of elements in a segment.

[00575] In one possible implementation, channel #3 information can be obtained by performing codebook-based quantization on the initial channel information.

[00576] For channel #3 information obtained through codebook-based quantization, the content of channel #3 information may include at least one of the following: basis selection information, coefficient selection information, coefficient phase information, coefficient amplitude information, or similar.

[00577] The basis selection information indicates a specific selected basis. The coefficient selection information indicates a specific selected non-zero coefficient. The coefficient amplitude information and the coefficient phase information can be collectively referred to as coefficient value information. The coefficient value information indicates a non-zero coefficient value.

[00578] For example, channel #3 information may include one or more of the following: i^, i^, i^i, i23l, ^5, ii6l, i24l, i25l, or i17,i. i1,1 indicates spatial domain base selection information, i12 indicates oversampling selection information, i18i indicates a coefficient with the highest value among the coefficients. Petition 870250105060, dated 11 / 17 / 2025, pp. 132 / 204 126 / 188 non-zero in each layer, i2 3j indicates reference amplitude information, i1 5 indicates common frequency domain base selection information, ij6j indicates frequency domain base selection information in each layer, i2,4,j indicates amplitude information for each coefficient in each layer, i2 5j indicates phase information for each coefficient in each layer, and i1 7j indicates non-zero coefficient selection information in each layer. Base selection information may include i11, i12, i-^, and i1t6,i·. Coefficient selection information may include i1 7j. Coefficient phase information may include i2 5j. Coefficient amplitude information may include i2 4j.

[00579] The content of each segment can be predefined or configured by the network. To be more specific, specific information that is in channel information #3 and that is included in each segment is determined in a predefined way or through configuration by the network.

[00580] For example, a segment can include one or more content items.

[00581] For example, among the K segments, a segment 1 might include basis selection information and coefficient selection information, a segment 2 might include coefficient amplitude information, and a segment 3 might include coefficient phase information.

[00582] For example, a segment may alternatively include a portion of the content of a content item. To be specific, a content item may be distributed across a plurality of segments.

[00583] For example, among the K segments, a segment 1 might include base selection information and coefficient selection information, a segment 2 might include coefficient amplitude information, a segment 3 might include a part Petition 870250105060, dated 11 / 17 / 2025, pp. 133 / 204 127 / 188 of the coefficient phase information and a segment 4 may include another part of the coefficient phase information.

[00584] It should be understood that the preceding content of the segments is merely an example and does not constitute any limitation to the solution in this modality of this request.

[00585] Alternatively, the content of each of the K segments can be determined by the terminal device.

[00586] In this case, the terminal device can notify the network device about the content of each segment.

[00587] In addition, the content order of a segment can be predefined or configured by the network device.

[00588] For example, a segment 1 among the K segments includes basis selection information and coefficient selection information, and a content order of segment 1 could be as follows: spatial domain basis selection information, oversampling selection information, common frequency domain basis selection information, frequency domain basis selection information in each layer, a coefficient with a higher value among non-zero coefficients in each layer, and non-zero coefficient selection information in each layer.

[00589] Alternatively, an order of the plurality of content items can be determined by the terminal device. In this case, the terminal device can notify the network device about the order of the plurality of content items.

[00590] Example 72:

[00591] Optionally, step 710 may include: The terminal device generates channel #3 information and segments channel #3 information based on segment length, or segments channel #3 information based on K. The content of channel #3 information is sorted in first order.

[00592] In other words, the content of the information of Petition 870250105060, dated 11 / 17 / 2025, pp. 134 / 204 128 / 188 channel #3 is sorted in the first order, and then the information from channel #3 is segmented based on the length of each segment or based on a quantity K of segments.

[00593] The first order can be predefined or configured by the network device.

[00594] Next, we describe the first order with reference to examples.

[00595] In one possible implementation, channel #3 information can be obtained by performing scalar quantization on the initial channel information.

[00596] For channel #3 information obtained through scalar quantization, the content of channel #3 information may include an element of the previous matrix. The first order may be determined based on an index of each dimension of the matrix.

[00597] For example, channel #3 information is a three-dimensional array with a dimension of FxNtxxNrank. For example, the elements in the three-dimensional array are sorted sequentially according to the following rule (a first-order example): an ascending order of frequency domain indices, an ascending order of network device antenna port indices, and an ascending order of flow indices.

[00598] For example, frequency domain indices are 1 to F, network device antenna port indices are 1 to Ntx, and flow indices are 1 to Nrank. After being sorted in first order, channel #3 information can be expressed as follows: (1, 1, 1), (2, 1, 1), ..., (F, 1, 1), (1, 2, 1), (2, 2, 1), ..., (F, 2, 1), (1, 3, 1), (2, 3, 1), ..., (F, 3, 1), ..., (F, Ntx, 1), (1, 1, 2), (2, 1, 2), ..., (F, 1, 2), (1, 2, 2), (2, 2, 2), ..., (F, 2, 2), (1, 3, 2), (2, 3, 2), ..., (F, 3, 2), ..., (F, Nkx, 2), ..., (F, Nkx, ^classification).

[00599] (1, 1, 1) indicates an element corresponding to a frequency domain index 1, an antenna gate index. Petition 870250105060, dated 11 / 17 / 2025, pages 135 / 204 129 / 188 of the network device and a flow index 1. (2, 1, 1) indicates an element corresponding to a frequency domain index 2, to the antenna port index 1 of the network device and to the flow index 1. By analogy, (F, Ntx, Nclassification) indicates an element corresponding to a frequency domain index F, an antenna port index Ntx of the network device and a flow index Nclassification.

[00600] For example, channel #3 information is a two-dimensional array with a dimension of FX Ntx. For example, the elements in the two-dimensional array are sorted sequentially according to the following rule (a first-order example): an ascending order of frequency domain indices and an ascending order of network device antenna port indices.

[00601] For example, channel #3 information is a three-dimensional array with a dimension of FxNtxxNrx· For example, the elements in the three-dimensional array are sorted sequentially according to the following rule (a first-order example): an ascending order of frequency domain indices, an ascending order of network device antenna port indices, and an ascending order of terminal device antenna port indices.

[00602] It should be understood that the previous descriptions are merely examples and the first order may alternatively be another order. This is not limited to this modality of this request.

[00603] In one possible implementation, channel #3 information can be obtained by performing codebook-based quantization on the initial channel information.

[00604] For channel #3 information obtained through codebook-based quantization, the content of channel #3 information may include at least one of the following: Petition 870250105060, dated 11 / 17 / 2025, pp. 136 / 204 130 / 188 base selection information, coefficient selection information, coefficient value information and similar.

[00605] For example, channel #3 information may include one or more of the following: 1^, i1,2, i^, i^, i^, i^, 12,4,2, i2,5,2, or i1 72. i1 1 indicates spatial domain base selection information, i12 indicates oversampling selection information, i182 indicates a coefficient with the highest value among the non-zero coefficients in each layer, i2 32 indicates reference amplitude information, i15 indicates common frequency domain base selection information, ii62 indicates frequency domain base selection information in each layer, i2 42 indicates amplitude information for each coefficient in each layer, i2,5,2 indicates phase information for each coefficient in each layer, and i17l indicates non-zero coefficient selection information in each layer.

[00606] For example, the first order may be as follows: the spatial domain base selection information, the oversampling selection information, the coefficient with the highest value among the non-zero coefficients in each layer, the reference amplitude information in each layer, the common frequency domain base selection information, the frequency domain base selection information in each layer, a portion of the amplitude information for each coefficient in each layer, a portion of the phase information for each coefficient in each layer, a portion of the non-zero coefficient selection information in each layer, another portion of the amplitude information for each coefficient in each layer, another portion of the phase information for each coefficient in each layer, and another portion of the non-zero coefficient selection information in each layer.

[00607] For another example, the first order could be the following order: the domain base selection information Petition 870250105060, dated 11 / 17 / 2025, pp. 137 / 204 131 / 188 spatial, oversampling selection information, common frequency domain basis selection information, frequency domain basis selection information in each layer, non-zero coefficient selection information in each layer, the coefficient with the highest value among the non-zero coefficients in each layer, reference amplitude information, amplitude information for each coefficient in each layer, and phase information for each coefficient in each layer.

[00608] It should be understood that the first order is merely an example of an order and does not constitute any limitation to the content of channel #3 information. For example, if channel #3 information does not include one of the previous contents, the content may be ignored when channel #3 information is classified in the first order. For example, channel #3 information includes spatial domain base selection information, oversampling selection information, the coefficient with the highest value among the non-zero coefficients in each layer, reference amplitude information, common frequency domain base selection information, frequency domain base selection information in each layer, amplitude information for each coefficient in each layer, and phase information for each coefficient in each layer.The first order can be as follows: spatial domain base selection information, oversampling selection information, common frequency domain base selection information, frequency domain base selection information in each layer, the coefficient with the highest value among the non-zero coefficients in each layer, reference amplitude information, amplitude information for each coefficient in each layer, and phase information for each coefficient in each layer.

[00609] For example, the first order can be determined Petition 870250105060, dated 11 / 17 / 2025, pp. 138 / 204 132 / 188 alternatively by the terminal device. In this case, the terminal device can notify the network device of the first order.

[00610] below describes a way to divide, by the terminal device, the information from channel #3 into a plurality of segments based on the length of a segment with reference to examples.

[00611] In this case, a value of K can be determined based on the total length of the channel #3 information and the length of each segment. The total length of the channel #3 information is a number of bits to represent the channel #3 information.

[00612] In one possible implementation, the segment length can be predefined. The length of each segment is less than or equal to the maximum code length supported by UCI.

[00613] For example, threshold #3 can indicate lengths of at least K-1 segments between the K segments. Threshold #3 can be predefined.

[00614] For example, the lengths of at least K-1 segments among the K segments are threshold #3.

[00615] The terminal device can split channel #3 information based on threshold #3, where the lengths of the K-1 segments are threshold #3, and the length of a remaining segment can be determined based on the total length of channel #3 information and the total length of the K-1 segments. The length of the remaining segment is less than or equal to threshold #3.

[00616] K can be determined based on threshold #3 and the total length of channel #3 information. For example, K-1 can be a quotient of q divided by Q. q indicates the total length of channel #3 information. N is an integer greater than Petition 870250105060, dated 11 / 17 / 2025, pp. 139 / 204 133 / 188 1. The length of the remaining segment is q-Qx(K-1)f, to be more specific, a remainder of q divided by Q. Q indicates the length of each of the K-1 segments, and Q is a positive integer. q indicates the total length of the information from channel #3, and q is an integer greater than 1.

[00617] In another possible implementation, the segment length can be configured by the network device.

[00618] For example, threshold #3 can indicate lengths of at least K-1 segments between the K segments. Threshold #3 can be configured by the network device. For a specific segmentation method, see the previous descriptions. The details are not described again in this document.

[00619] For example, method 700 may also include: The terminal device receives indication information #6 sent by the network device, where indication information #6 indicates segment lengths. The segment lengths may be different. For example, indication information #6 may indicate a set of candidate segment lengths.

[00620] In one possible implementation, a segment length range can be predefined.

[00621] For example, threshold #3 can indicate a maximum segment length value. Threshold #3 can be preset.

[00622] The terminal device can determine the length of each segment, so that the length of each segment is less than or equal to threshold #3.

[00623] For example, threshold #3 could be the maximum code length supported by UCI.

[00624] In another possible implementation, a segment length range can be configured by the network device.

[00625] the segment length interval can be Petition 870250105060, dated 11 / 17 / 2025, pages 140 / 204 134 / 188 explicitly configured.

[00626] For example, threshold #3 may indicate a maximum segment length value. Threshold #3 can be configured by the network device.

[00627] For a specific method of segmentation in this case, please refer to the previous descriptions. The details are not described again in this document.

[00628] For example, the network device can directly indicate a length range of a transmitted segment on each of the K uplink resources used to transmit channel #3 information. The K uplink resources are used respectively to transmit the K UCI chunks.

[00629] K uplink resources can be understood as uplink resources scheduled by the network device in K moments. Alternatively, the K uplink resources can be understood as K periodic uplink resources configured by the network device. Alternatively, an uplink resource scheduled by the network device at one moment is distributed in K time resource units. The time resource unit can be one or a combination of a plurality of slots. The K uplink resources can be understood as the K time resource units.

[00630] The segment length range can be set implicitly.

[00631] For example, method 700 may also include: The terminal device receives the uplink resource configuration information #1 sent by the network device, where the uplink resource configuration information #1 indicates K uplink resources used to transmit channel information #3, and the K uplink resources are used respectively to transmit the Petition 870250105060, dated 11 / 17 / 2025, pp. 141 / 204 135 / 188 K pieces of UCI. The terminal device determines the length of each segment based on each uplink resource and an MCS. In this case, the K uplink resources can be understood as K time resource units on an uplink resource scheduled by the network device at a given time.

[00632] For example, an uplink resource may include a plurality of resource elements (REs). The terminal device may determine, based on the MCS and the number of REs in the uplink resource that are used to transmit the UCI, a number of bits that can be transmitted using the uplink resource and then determine a number of unencoded bits that can be carried on the uplink resource. This number can be used as a UCI length that can be carried on the uplink resource, in other words, a maximum value of a segment length that can be carried on the uplink resource.The terminal device can determine the length of each segment based on the maximum segment length that can be carried on the uplink resource, so that the length of each segment is less than or equal to the UCI length that can be carried on an uplink resource used to transmit the segment.

[00633] The following describes a way to divide, by the terminal device, the information from channel #3 into a plurality of K-based segments with reference to examples.

[00634] In one possible implementation, a value for K can be predefined.

[00635] In one possible implementation, a value of K can be configured by the network device.

[00636] For example, the network device knows the total length of channel #3 information and can configure Petition 870250105060, dated 11 / 17 / 2025, pp. 142 / 204 136 / 188 an appropriate value of K based on the total length of channel #3 information. For example, a feedback configuration corresponding to channel #3 information can be predefined or can be configured by the network device. In this case, the network device knows the total length of channel #3 information and can configure an appropriate value of K based on the total length of channel #3 information.

[00637] In another example, the network device knows a total length range of channel #3 information and can set an appropriate value of K based on the total length range of channel #3 information. For example, a parameter range in a feedback configuration corresponding to channel #3 information can be predefined or can be configured by the network device. In this case, the network device knows the total length range of channel #3 information and can set an appropriate value of K based on the total length range of channel #3 information.

[00638] Optionally, method 700 also includes: The network device sends indication information #8 (an example of second indication information) to the terminal device, where indication information #8 indicates the value of K.

[00639] The network device can explicitly configure the value of K. In other words, indication information #8 can explicitly indicate the value of K. For example, indication information #8 includes the value of K.

[00640] The network device may alternatively implicitly set the value of K. In other words, indication information #8 may implicitly indicate the value of K.

[00641] For example, method 700 may also include: The terminal device receives uplink resource configuration information #1 sent by the device of Petition 870250105060, dated 11 / 17 / 2025, pp. 143 / 204 137 / 188 network.

[00642] In this case, the uplink resource configuration information #1 can be used as indication information #8. The network device can implicitly configure the value of K using a number of staggered uplink resources used to transmit channel information #3. The number of uplink resources used to transmit channel information #3, i.e., a number of time resource units, is the value of K. That is, one UCI chunk is transmitted on each uplink resource by default.

[00643] The terminal device can determine a way to split the information from channel #3, to obtain the K segments.

[00644] For example, the lengths of the first K-1 segments among the K segments are Q, Q = \q / K], and the length of the last segment is q — Q x (6 — 1) . q indicates the total length of the channel #3 information, and q is an integer greater than 1. ” | indicates a rounding symbol.

[00645] For example, channel #3 information includes 2000 bits, K=2, one of the two segments includes the first 1000 bits and the other segment includes the last 1000 bits.

[00646] For example, the terminal device can alternatively perform the division at any position to obtain the K segments, provided that the length of each of the K segments is less than threshold #3.

[00647] In another possible implementation, a value of K and a segment length can alternatively be completely determined by the terminal device.

[00648] The previous case, in which the network device configures a segmentation method, can be understood as a correspondence between channel #3 information and the UCI or a correspondence between the K pieces of UCI is configured by Petition 870250105060, dated 11 / 17 / 2025, pages 144 / 204 138 / 188 network device.

[00649] The previous case, in which the terminal device determines a segmentation method, can be understood as a correspondence between channel #3 information and the UCI or a correspondence between the K UCI segments is determined by the terminal device and indicated to the network device. For example, the terminal device can notify the network device about at least one of the following: a K value or the lengths of the K segments.

[00650] Example 73:

[00651] Optionally, step 710 may include: The terminal device generates channel #3 information and segments channel #3 information based on the boundaries of various pieces of information within channel #3 information. The content of channel #3 information is sorted in first order.

[00652] A piece of information in channel information #3 is the shortest piece of information with a physical meaning. In other words, each segment includes one or more pieces of information.

[00653] This helps ensure the integrity of information in a segment.

[00654] For channel #3 information obtained through scalar quantization, a piece of information can be an element. For example, during scalar quantization, the initial channel information is quantized into 4 bits. In this case, each element in channel #3 information is represented by 4 bits, and 4 bits representing an element are a piece of information. 4 bits belonging to the same element are in the same segment.

[00655] For channel #3 information obtained through codebook-based quantization, information can be any of the following: spatial domain base selection information, oversampling selection information, reference amplitude information in each layer, Petition 870250105060, dated 11 / 17 / 2025, pages 145 / 204 139 / 188 frequency domain base selection information in each layer, amplitude information for each coefficient, phase information for each coefficient, or similar. The phase information for each coefficient is used as an example. Bits belonging to the same coefficient's phase information are in the same segment.

[00656] Example 73 can be used in combination with some implementations in Example 72. Examples are used below for description.

[00657] For example, the terminal device can divide channel #3 information based on a length range for each segment and a boundary for each piece of information in channel #3 information.

[00658] In this case, the length of each segment is within a segment length range, and the segment includes one or more pieces of information.

[00659] For channel #3 information obtained through scalar quantization, if bits belonging to the same element are included in two segments, when a range of one segment length is reached, all bits belonging to the element may be distributed to the first segment or to the last segment.

[00660] For example, for channel #3 information obtained through scalar quantization, channel #3 information includes a total of 12 bits, and each element in channel #3 information is represented by 4 bits. The length of each segment is less than or equal to 6 bits. For example, segment 1 includes 6 bits, segment 2 includes 2 bits, and segment 3 includes 4 bits. In this case, bits belonging to the same element are included in two segments: segment 1 and segment 2. All bits belonging to the element can be distributed to segment 2.

[00661] For channel #3 information obtained via Petition 870250105060, dated 11 / 17 / 2025, pages 146 / 204 140 / 188 codebook-based quantization: if bits of the same piece of information are included in two segments, when a range of the length of one segment is reached, all bits of the information can be distributed to the first segment or to the last segment.

[00662] For example, for channel #3 information obtained through codebook-based quantization, if phase information bits of the same coefficient are included in two segments, all phase information bits of the coefficient can be distributed to the first segment or to the last segment.

[00663] For example, the terminal device can split the information from channel #3 based on K and a boundary for each piece of information in the information from channel #3.

[00664] In this case, each segment includes one or more pieces of information, and the information from channel #3 is divided into a total of K segments.

[00665] For specific descriptions, please refer to the previous descriptions. The details are not described again in this document.

[00666] In some of the previous implementations, the length of each segment is determined by the terminal device. In this case, the network device does not know the length of each segment, and the terminal device can notify the network device about the length of each segment, that is, notify the network device about the length of each UCI chunk.

[00667] Optionally, the terminal device can send indication information #9 (an example of third indication information) to the network device, to indicate the length of each of the K UCI chunks, or to indicate the length of each of the K segments. Petition 870250105060, dated 11 / 17 / 2025, pages 147 / 204 141 / 188

[00668] In this way, the network device can decode each piece of UCI to obtain each segment of channel #3 information.

[00669] The K UCI chunks can be transmitted using J uplink resources. J is a positive integer.

[00670] Next, we describe an uplink feature used to transmit the K UCI chunks with reference to examples.

[00671] The K UCI chunks can be transmitted using the same uplink feature. That is, J=1.

[00672] Alternatively, the K UCI chunks can be transmitted using an uplink feature plurality. That is, J>1.

[00673] The plurality of uplink resources can be understood as uplink resources scheduled by the network device at a plurality of times. Alternatively, the plurality of uplink resources can be understood as a plurality of periodic uplink resources configured by the network device. Alternatively, an uplink resource scheduled by the network device at one time can be distributed across a plurality of time resource units. The time resource unit can be one or a combination of a plurality of slots. The plurality of uplink resources can be understood as the plurality of time resource units.

[00674] In this case, even if the length of channel #3 information exceeds the limitation of the length of the UCI that can be carried on an uplink resource, the remaining part of the channel #3 information does not need to be discarded, and the K pieces of UCI can be transmitted respectively using a plurality of uplink resources, so that the network device can obtain the complete channel information. Petition 870250105060, dated 11 / 17 / 2025, pages 148 / 204 142 / 188 #3. Additionally, if the length of a segment exceeds the UCI length limitation that can be carried on an uplink resource, the segment can be transmitted using a plurality of uplink resources, so that the network device can obtain the complete channel information #3.

[00675] When J>1, one or more of the K UCI chunks can be transmitted on each uplink resource. The amounts of UCI transmitted on all uplink resources can be the same or different.

[00676] For an uplink resource, the network device can decode each UCI chunk based on a number of UCI chunks transmitted on the uplink resource and a length of each UCI chunk transmitted on the uplink resource, to obtain K segments included in the UCI transmitted on the uplink resource.

[00677] If the network device does not know the number of UCI chunks transmitted on each uplink resource or the length of each UCI chunk, the terminal device may notify the network device of the number of UCI chunks transmitted on each uplink resource and / or the length of each UCI chunk, so that the network device can decode the UCI transmitted on each uplink resource.

[00678] Next we describe a case where J=1 with reference to examples.

[00679] For example, K can be configured by the network device or it can be predefined. In this case, the network device knows the value of K. The terminal device divides the channel #3 information based on the value of K, and the lengths of the K segments are determined by the terminal device. In this case, the terminal device can notify the network device about the lengths of the K segments transmitted in a Petition 870250105060, dated 11 / 17 / 2025, pp. 149 / 204 143 / 188 uplink resource.

[00680] For another example, the lengths of the K-1 segments between the K segments can be configured by the network device or can be predefined, and the length of a remaining segment and a K value are determined by the terminal device based on the lengths of the K-1 segments and the total length of channel information #3. If the network device does not know the total length of channel information #3 or the K value, the terminal device can notify the network device of at least two of the following: the length of the remaining segment, the K value, or the total length of channel information #3.

[00681] In another example, a maximum segment length value is configured by the network device or is predefined. The terminal device splits the channel #3 information so that the length of each segment is less than or equal to the maximum segment length value. The terminal device can notify the network device about the length of each segment. The terminal device can also notify the network device about a K value or a total length of the channel #3 information.

[00682] Next, we describe a case where J>1 with reference to examples.

[00683] For example, the number of UCI chunks transmitted on each uplink resource can be configured by the network device or can be predefined.

[00684] Optionally, the network device can send indication information #11 (an example of fifth indication information) to the terminal device, where indication information #11 indicates a number of segments transmitted on each uplink resource. The number of segments transmitted on each uplink resource is a number of UCI chunks transmitted on each resource of Petition 870250105060, dated 11 / 17 / 2025, pages 150 / 204 144 / 188 ascending link.

[00685] For example, a specific segment transmitted on each of the J uplink resources can be predefined or can be configured by the network device.

[00686] Optionally, the #11 indicator may also indicate an identifier of a transmitted segment on each uplink resource. In other words, the #11 indicator may also indicate a specific segment transmitted on each uplink resource. For example, the #11 indicator may indicate a number of a transmitted segment on each uplink resource, including a number for each transmitted segment, or one or more of the following: a starting number of the transmitted segment, a number of segments, or a final number of the transmitted segment. A portion of one or more items, not indicated by the #11 indicator, may be obtained in another way, for example, predefined in a protocol. A number for each segment may indicate a position of the segment among the K segments. In other words, the numbers of the K segments may indicate an order of the K segments.The information indicated by #11 may indicate an order of segments transmitted on each uplink resource, indicating the number of segments transmitted on each uplink resource.

[00687] The previous case in which the network device performs the configuration can be understood as a match between channel #3 information and the uplink resource or a match between the plurality of uplink resources is configured by the network device.

[00688] Alternatively, the terminal device can determine, based on a UCI length that can be carried on each of the J uplink resources, a number of segments to be transmitted on each resource. Petition 870250105060, dated 11 / 17 / 2025, pp. 151 / 204 145 / 188 uplink, to ensure that the total length of UCI transmitted on each uplink resource is less than or equal to the length of UCI that can be carried on the uplink resource.

[00689] The terminal device can notify the network device about a number of UCI chunks transmitted on each uplink resource.

[00690] Optionally, the terminal device can send indication information #14 (an example of sixth indication information) to the network device, where indication information #14 can indicate the number of UCI chunks transmitted on each uplink resource.

[00691] Optionally, the indication information #14 may also indicate a UCI identifier transmitted on each uplink resource, in other words, indicate a specific UCI transmitted on each uplink resource.

[00692] In other words, the terminal device can notify the network device about an order of segments transmitted on each uplink resource, to be specific, notify the network device about a position, among the K segments, of a segment included in the UCI transmitted on each uplink resource.

[00693] For example, the indication information #14 may indicate a number of a transmitted segment in the uplink resource, for example, including a number for each transmitted segment, or one or more of the following information: a starting number of the transmitted segment, a number of segments, or a final number of the transmitted segment. A portion, not indicated by the indication information #14, of one or more items may be obtained in another way, for example, predefined in a protocol. A number for each segment indicates a position of the segment among the K segments. The numbers of the K segments may indicate an order of the K segments. Petition 870250105060, dated 11 / 17 / 2025, pp. 152 / 204 146 / 188

[00694] The length of UCI that can be carried on each uplink resource can be predefined or configured by the network device.

[00695] Furthermore, if the network device does not know the length of a transmitted segment on each uplink resource, the terminal device can notify the network device of the length of the transmitted segment on each uplink resource. For example, the lengths of K segments can be determined by the terminal device. In this case, the terminal device can notify the network device of the length of the transmitted segment on each uplink resource.

[00696] Optionally, the terminal device can send indication information #15 (an example of seventh indication information) to the network device, where indication information #15 indicates that the plurality of uplink resources correspond to the same channel information #3.

[00697] In other words, indication information #15 may indicate specific uplink resources used to transmit channel information #3.

[00698] The terminal device can notify the network device about the channel information to which the information transmitted on each uplink resource belongs. In other words, the terminal device can notify the network device about specific uplink resources on which the same channel information is transmitted.

[00699] For example, each uplink resource can contain an identifier, and the identifier is used to distinguish between channel information. If two uplink resources carry the same identifier, the information transmitted using the two uplink resources indicates the same channel information. If two uplink resources Petition 870250105060, dated 11 / 17 / 2025, pages 153 / 204 147 / 188 uplinks carry different identifiers; the information transmitted using the two uplink resources indicates different channel information. The identifier can be used as indication information #15.

[00700] The previous case, in which the terminal device notifies the network device about specific uplink resources used to transmit UCI, a quantity of UCI chunks transmitted on each uplink resource and specific UCI transmitted on each uplink resource, can be understood as a match between channel #3 information and the uplink resource or a match between the plurality of uplink resources is determined by the UE and indicated to a base station.

[00701] When J is greater than 1, the uplink resource types J can be the same or different.

[00702] For example, J uplink resources can be resources dedicated to transmitting channel information. A resource dedicated to transmitting channel information is a resource used to transmit only channel information, without transmitting uplink data.

[00703] For example, J uplink resources can be resources reused for channel information and uplink data. A resource reused for channel information and uplink data indicates that the uplink resource can be used to transmit channel information and uplink data.

[00704] For example, when J is greater than 1, some uplink resources may be resources dedicated to transmitting channel information, and other uplink resources may be resources reused for both channel information and uplink data.

[00705] In one possible implementation, the terminal device Petition 870250105060, dated 11 / 17 / 2025, pages 154 / 204 148 / 188 receives uplink resource configuration information #2 (an example of first uplink resource configuration information) sent by the network device, where uplink resource configuration information #2 indicates an uplink resource #1 (an example of first uplink resource) used to transmit channel information #3. Step 720 may include: The terminal device transmits the K UCI chunks on uplink resource #1.

[00706] Optionally, the uplink resource configuration information #2 can further indicate whether uplink resource #1 can be used to transmit UCI. When uplink resource #1 can be used to transmit UCI, the terminal device can transmit the K UCI chunks on uplink resource #1.

[00707] For example, uplink resource #1 can be considered as an uplink resource.

[00708] For example, uplink resource #1 can be distributed across J time resource units, and uplink resource #1 can be considered as J uplink resources. To be more specific, the network device schedules J uplink resources at a time. For example, configuration information for uplink resource #2 can indicate a number of segments transmitted in each time resource unit and / or a specific segment transmitted in each time resource unit. That is, configuration information for uplink resource #2 can be used as indication information #11.

[00709] In another possible implementation, the network device can configure J periodic uplink resources. Each periodicity includes an uplink resource used to transmit UCI. The network device can decode UCI on each uplink resource based on a quantity Petition 870250105060, dated 11 / 17 / 2025, pages 155 / 204 149 / 188 of UCI chunks transmitted on the uplink resource and a length of each UCI chunk transmitted on the uplink resource, to obtain a segment included in the UCI transmitted on the uplink resource.

[00710] In one possible implementation, the terminal device receives uplink resource configuration information #3 (an example of second uplink resource configuration information) sent by the network device, where uplink resource configuration information #3 indicates an uplink resource #2 (an example of second uplink resource). Step 720 may include: The terminal device transmits a portion of the K UCI chunks on uplink resource #2.

[00711] Optionally, the uplink resource configuration information #3 can further indicate whether uplink resource #2 can be used to transmit UCI. When uplink resource #2 can be used to transmit UCI, the terminal device can transmit a portion of the K UCI chunks on uplink resource #2.

[00712] The uplink resource #2 can be considered as an uplink resource, and the uplink resource #2 belongs to the J uplink resources.

[00713] For example, uplink resource #2 may be the 1st uplink resource used to transmit the K UCI chunks, and step 720 may include: The terminal device transmits, on uplink resource #2, UCI, between the K UCI chunks, which are included in the first k segments between the K segments, where k is a positive integer.

[00714] The first K pieces of UCI are the first K pieces of UCI transmitted between the K pieces of UCI.

[00715] Optionally, the uplink resource configuration information #3 may also indicate a Petition 870250105060, dated 11 / 17 / 2025, pages 156 / 204 150 / 188 quantity of UCI chunks transmitted on uplink resource #2 and / or specific UCI, among the K UCI chunks, that must be transmitted. For example, the configuration information for uplink resource #3 might indicate a number of UCI chunks transmitted on uplink resource #2. The configuration information for uplink resource #3 could be used as indication information #11.

[00716] In addition, the terminal device transmitting the portion of the K UCI chunks on uplink resource #2 may include: The terminal device transmits the portion of the K UCI chunks and indication information #12 (an example of fourth indication information) on uplink resource #2. Indication information #12 indicates at least one of the following: a total length of untransmitted UCI among the K UCI chunks, or whether the K UCI chunks include untransmitted UCI. Alternatively, when the portion of the K UCI chunks includes the 1st UCI chunk, indication information #12 indicates at least one of the following: a total length of channel information #3, a total length of untransmitted UCI among the K UCI chunks, or whether the K UCI chunks include untransmitted UCI.

[00717] It can be indicated in several ways whether the K pieces of UCI include non-transmitted UCI.

[00718] For example, indication information #12 may indicate a quantity of UCI chunks transmitted on uplink resource #2 and / or a UCI identifier, to be specific, indicate a specific UCI transmitted on uplink resource #2. The network device can determine if there is untransmitted UCI based on the quantity of UCI chunks transmitted on uplink resource #2, a quantity of UCI chunks transmitted, and a K value. If the K value is determined by the terminal device, the terminal device can notify the network device of the value of Petition 870250105060, dated 11 / 17 / 2025, pages 157 / 204 151 / 188 K. In this case, the referral information #12 and the referral information #14 may be the same information.

[00719] For example, indication information #12 can directly indicate whether there is untransmitted UCI. For example, if there is untransmitted UCI, a corresponding signaling bit might be 1; or if there is no untransmitted UCI, a signaling bit might be 0.

[00720] For example, indication information #12 indicates at least one of the following: a total length of untransmitted UCI among the K UCI chunks, an identifier indicating whether the K UCI chunks include untransmitted UCI, a quantity of UCI chunks transmitted on the uplink resource #2, or a UCI identifier.

[00721] The 1st UCI chunk is the 1st UCI chunk transmitted among the K UCI chunks, or UCI used to transmit a segment classified first in channel information #3. For example, the 1st UCI chunk might be the UCI included in the 1st segment among the K segments.

[00722] Indication information #12 can be used as independent UCI and transmitted along with part of the K UCI pieces in uplink resource #2.

[00723] Untransmitted UCI is a non-transmitted segment.

[00724] Alternatively, the terminal device can transmit indication information #12 using another uplink feature.

[00725] For example, when the K UCI chunks include untransmitted UCI, the terminal device can expect the network device to escalate to another uplink resource to transmit the untransmitted UCI among the K UCI chunks.

[00726] For example, the terminal device receives uplink resource configuration information #31 sent by the network device, where the information of Petition 870250105060, dated 11 / 17 / 2025, pages 158 / 204 152 / 188 uplink resource configuration #31 indicates an uplink resource, and indicates that the uplink resource is used to transmit UCI. The uplink resource may be a resource dedicated to UCI transmission.

[00727] In addition, the configuration information for uplink resource #31 may also indicate a number of UCI chunks transmitted on the uplink resource and / or specific UCI, from among the remaining UCIs, that should be transmitted. The configuration information for uplink resource #31 may be used as indication information #12.

[00728] Alternatively, when the K UCI chunks include untransmitted UCI, the terminal device may transmit the remaining untransmitted UCI using one or more other subsequent uplink resources, for example, transmitting the untransmitted UCI among the K UCI chunks using an uplink resource used to transmit uplink data. That is, the remaining UCI is transmitted using an uplink resource reused for both UCI and uplink data.

[00729] Optionally, method 700 may also include: The terminal device receives uplink resource configuration information #4 sent by the network device, where uplink resource configuration information #4 (an example of third uplink resource configuration information) indicates an uplink resource #3 (an example of third uplink resource). The terminal device transmits indication information #13 on uplink resource #3, where indication information #13 indicates the total length of channel information #3.

[00730] In this case, the uplink resource #3 does not belong to the J uplink resources. Petition 870250105060, dated 11 / 17 / 2025, pages 159 / 204 153 / 188

[00731] For example, the terminal device may expect the network device to escalate to another uplink resource to transmit the K UCI chunks.

[00732] For example, the terminal device receives uplink resource configuration information #41 sent by the network device, where the uplink resource configuration information #41 indicates an uplink resource, and indicates that the uplink resource is used to transmit UCI. The uplink resource may be a resource dedicated to UCI transmission.

[00733] In this mode of solution to this request, the terminal device can request an uplink resource from the network device to transmit an untransmitted segment. This helps to properly utilize uplink resources, to avoid wasting resources.

[00734] Optionally, step 720 may include: The terminal device transmits part of the K UCI pieces to the network device. Method 700 may also include: discarding untransmitted UCI from among the K UCI pieces, where the timing starts from a moment when the transmission of the 1st UCI piece from among the K UCI pieces is greater than or equal to threshold #5 (an example of a second threshold).

[00735] In other words, from the initial moment of transmission of a CSI report of channel #3 information, if the transmission duration of a transmitted segment between the K segments is greater than or equal to threshold #5, an untransmitted segment between the K segments will be discarded, in other words, the untransmitted segment should no longer be transmitted.

[00736] For example, a timer #1 is started at the moment of transmission of the 1st UCI chunk, and if the timing of timer #1 is greater than or equal to threshold #5, the untransmitted UCI among the K UCI chunks is discarded. Petition 870250105060, dated 11 / 17 / 2025, pages 160 / 204 154 / 188

[00737] For example, the transmission time of the 1st UCI segment may be a transmission start time or a transmission end time of the 1st UCI segment, or another time that uses the transmission start time or the transmission end time of the 1st UCI segment as a reference, provided that the time can represent the duration of channel information transmission using the UCI. This is not limited in this document.

[00738] In another example, it is determined whether the duration between the initial transmission time of a segment and the initial transmission time of the CSI report for channel information #3 is greater than or equal to threshold #5. If so, the segment and all remaining segments are discarded. If not, the segment must be transmitted.

[00739] If the transmission duration of channel #3 information is excessively long, the terminal device may determine that the transmission of channel #3 information has failed and discard a remaining segment. This helps to avoid wasting resources.

[00740] Optionally, step 720 may include: The terminal device transmits part of the K UCI chunks to the network device. Method 700 may further include: discarding untransmitted UCI from among the K UCI chunks, where the timing that begins from a transmission moment of a CSI report of channel information #4 (an example of second channel information) is greater than or equal to threshold #6 (an example of a third threshold), and channel information #3 is used to measure the accuracy of channel information #4.

[00741] Alternatively, channel information #3 can be referred to as the corresponding label for channel information #4.

[00742] Channel information #4 and channel information #3 are channel information that have a match. Petition 870250105060, dated 11 / 17 / 2025, pp. 161 / 204 155 / 188

[00743] For example, channel information #4 and channel information #3 may correspond to the same initial channel information. To be specific, channel information #4 and channel information #3 may be obtained based on the same initial channel information.

[00744] Optionally, the terminal device can send indication information #16 to the network device, where indication information #16 can indicate specific channel information #4 corresponding to channel information #3. For example, indication information #16 can indicate an index of a CSI report to send channel information #4, an index of a resource to send channel information #4, an index of a reference signal to measure channel information #4, or an index of a resource to send the reference signal.

[00745] For example, the resource index for sending channel #4 information could be a transmission slot identifier for the resource for transmitting channel #4 information.

[00746] For example, the resource index for sending the reference signal can be an identifier of a transmission slot of the resource for transmitting the reference signal.

[00747] For example, the transmission slot identifier can be represented by an identifier of an initial transmission slot, or it can be represented by an identifier of an initial transmission slot and a number of transmission slots. The transmission slot identifier can alternatively be represented by an identifier of a final transmission slot and a number of transmission slots. The transmission slot identifier can alternatively be represented by an identifier of an initial transmission slot and an identifier of a final transmission slot. Alternatively, the transmission slot identifier of Petition 870250105060, dated 11 / 17 / 2025, pages 162 / 204 156 / 188 transmission can be represented by a bitmap (bitmap) of the transmission slot.

[00748] Optionally, at least one segment in channel information #3 and in channel information #4 may be sent on the same uplink resource. For example, the UCI used to transmit channel information #4 and the 1st UCI segment used to send channel information #3 are sent on the same uplink resource.

[00749] For example, channel #4 information can be CSI compressed reported in a conventional mode (e.g., based on an R16 codebook).

[00750] For another example, channel #4 information could be channel information reported in an AI-based feedback mode. To be more specific, channel #4 information could be obtained based on an AI model.

[00751] For example, the AI ​​model can be a bilateral model. A submodel, deployed on the end device, of the bilateral model can be used to generate channel information to be fed back to the network device. A submodel deployed on the network device can be used to reconstruct channel information. In other words, in the bilateral model, the channel information fed back to the network device can be generated by a submodel of the AI ​​model.

[00752] For example, the AI ​​model may include a CSI generator and a CSI reconfigurator. The CSI generator may be deployed on the endpoint device and the CSI reconfigurator may be deployed on the network device. The endpoint device may generate CSI feedback information, i.e., channel information to be fed back to the network device, based on the initial channel information using the CSI generator, and feed the channel information back to the network device using a CSI report. The network device may reconstruct CSI information using the CSI reconfigurator. Petition 870250105060, dated 11 / 17 / 2025, pp. 163 / 204 157 / 188 to obtain CSI recovery information. CSI recovery information can be used like channel #4 information.

[00753] For specific descriptions of the CSI generator and CSI reconfigurator, please refer to the previous descriptions. To avoid repetition, the details will not be described again in this document.

[00754] It should be understood that the preceding descriptions are merely an example and that the AI ​​model may be another type of model. This is not limited in this embodiment of this application. For ease of description, in this embodiment of this application, an example in which the AI ​​model includes the CSI generator and the CSI reconfigurator is used primarily for description and does not constitute any limitation to the solution in this embodiment of this application.

[00755] In this case, the use of channel #3 information to measure the accuracy of channel #4 information can also be understood as channel #3 information being used to measure the performance of the AI ​​model, i.e., it is used for model monitoring. To be more specific, when channel #3 information is used for model monitoring, during the transmission of channel #3 information, if the elapsed time since the transmission of channel #4 information is greater than or equal to threshold #6, the terminal device can determine that the transmission of channel #3 information has failed and discard a remaining segment, in other words, not transmit any more of an untransmitted segment.

[00756] For example, the transmission time of channel #4 information could be an initial transmission time of channel #4 information. Alternatively, the transmission time of channel #4 information could be a completion time of channel #4 information transmission. Alternatively, the transmission time of Petition 870250105060, dated 11 / 17 / 2025, pp. 164 / 204 158 / 188 channel #4 may be another time that uses an initial or final transmission time of channel #4 information as a reference, provided that the time can represent the duration of the transmission of channel #4 information. This is not limited to the scope of this document.

[00757] During the transmission of channel #3 information, if the duration between the current moment and the moment of transmission of channel #4 information is greater than or equal to threshold #6, an untransmitted segment will be discarded.

[00758] For example, a timer #2 is started at the time of transmission of channel #4 information, and if the timing of timer #2 is greater than or equal to threshold #6, the untransmitted UCI among the K UCI chunks is discarded.

[00759] In another example, it is determined whether the duration between the initial moment of transmission of a segment and the moment of transmission of channel #4 information is greater than or equal to threshold #6. If so, the segment and all remaining segments are discarded. If not, the segment must be transmitted.

[00760] Channel #3 information is used to measure the accuracy of Channel #4 information. If an excessively long duration has elapsed since the transmission of Channel #4 information, the actual channel information may have changed, and it is difficult to measure the current performance of a model using both Channel #3 and Channel #4 information. The terminal device may determine that the transmission of Channel #3 information has failed and discard a remaining segment. This helps to avoid wasting resources.

[00761] FIG. 10 shows yet another method of communication according to a modality of this request.

[00762] As shown in FIG. 10, method 800 may include the following steps.

[00763] 810: A terminal device generates information from Petition 870250105060, dated 11 / 17 / 2025, pages 165 / 204 159 / 188 channel #5 (an example of fifth channel information), where a type of channel #5 information is field truth channel information.

[00764] 820: The terminal device transmits channel #5 information to a network device using upper-layer signaling.

[00765] Channel #5 information can be used for model monitoring, model training, or similar purposes.

[00766] The network device can perform data processing based on channel #5 information or forward channel #5 information.

[00767] For example, performing data processing based on channel #5 information may include: performing model training or model monitoring based on channel #5 information.

[00768] For example, forwarding channel #5 information might include: forwarding channel #5 information to another device with an AI module. The AI ​​module is configured to implement a corresponding AI function, for example, model monitoring or model training. For example, the AI ​​module could be the RIC shown in FIG. 2.

[00769] For example, channel #5 information can be obtained by performing scalar quantization on the initial channel information.

[00770] For example, channel #5 information can be obtained by performing codebook-based quantization on the initial channel information.

[00771] For example, channel #5 information can be generated based on a first feedback configuration. In this case, channel #5 information and channel #1 information can be the same channel information.

[00772] For a specific feedback mode, see Petition 870250105060, dated 11 / 17 / 2025, pages 166 / 204 160 / 188 as described in method 500. The details are not described again in this document. Alternatively, channel #5 information can be generated in another way.

[00773] In the solution in this embodiment of this application, channel information can be transmitted using upper-layer signaling, so that the network device can obtain channel information with high overheads, i.e., high-precision channel information.

[00774] Optionally, upper-layer signaling includes an RRC message or a medium access control element (MAC CE).

[00775] To facilitate the description, in this type of request, the RRC message is mainly used as an example for description.

[00776] An RRC message can be used to transmit one or more channel information of a field truth channel information type.

[00777] Optionally, the RRC message (an example of a first RRC message) can be used later to transmit channel #6 information (an example of sixth channel information), and channel #5 information is used to measure the accuracy of channel #6 information.

[00778] Alternatively, channel information #5 can be referred to as the corresponding label for channel information #6.

[00779] In other words, channel #5 information and channel #6 information can be transmitted in the same RRC message.

[00780] Channel information #5 and channel information #6 are channel information that have a match. For specific descriptions, see channel information #4 and channel information #3 in the previous descriptions. Petition 870250105060, dated 11 / 17 / 2025, pages 167 / 204 161 / 188

[00781] For example, channel #6 information could be AI-based feedback channel information. In this case, channel #5 information could be used for model monitoring.

[00782] If channel #6 information is not transmitted in the RRC message, the terminal device may further notify the network device about an association relationship between channel #5 information and channel #6 information. To be more specific, the terminal device may notify the network device about two pieces of channel information that correspond to each other.

[00783] Optionally, the RRC message may also indicate the association relationship between channel #5 information and channel #6 information.

[00784] For example, the RRC message may also indicate UCI, including channel #6 information.

[00785] In other words, the RRC message may also indicate specific UCI information that includes channel #6 information corresponding to channel #5 information.

[00786] For example, the UCI including channel #6 information can be indicated by a UCI transmission time. To be more specific, the RRC message can also indicate the UCI transmission time, including channel #6 information. The UCI transmission time can be indicated by a UCI transmission slot identifier.

[00787] The transmission slot identifier can be represented by an identifier of an initial transmission slot, or it can be represented by an identifier of an initial transmission slot and a number of transmission slots. Alternatively, the transmission slot identifier can be represented by an identifier of a final transmission slot and a number of transmission slots. Petition 870250105060, dated 11 / 17 / 2025, pages 168 / 204 162 / 188 transmission. The transmission slot identifier may alternatively be represented by an identifier for an initial transmission slot and an identifier for an final transmission slot. Alternatively, the transmission slot identifier may be represented by a bitmap of the transmission slot.

[00788] For example, the UCI transmission time can be represented by an identifier of an initial UCI transmission slot and a number of transmission slots. For another example, the UCI transmission time can be represented by an identifier of an initial UCI transmission slot and an identifier of a final UCI transmission slot. As yet another example, the UCI transmission time can be represented by a bitmap of a UCI transmission slot. For example, the UCI transmission time can be represented by an identifier of a final UCI transmission slot and a number of transmission slots.

[00789] For another example, the RRC message may also indicate an index of a reference signal used to measure channel #6 information, or an index of a resource used to send the reference signal, for example, an identifier of a transmission slot of the resource.

[00790] It should be understood that the preceding descriptions are merely examples, and the terminal device may alternatively indicate the association relationship between channel #5 information and channel #6 information in another way. For example, the terminal device may send further indication information to indicate an uplink resource to transmit channel #5 information and an uplink resource to transmit channel #6 information. For example, the uplink resource may contain an identifier, and the channel information transmitted on uplink resources with the same identifier is Petition 870250105060, dated 11 / 17 / 2025, pp. 169 / 204 163 / 188 channel information that has a match.

[00791] Optionally, the RRC message may also indicate common assistance information #1 from one or more channel information pieces of the field truth channel information type that are transmitted using the RRC message, and the one or more channel information pieces of the field truth channel information type include channel information #5.

[00792] For example, service information #1 can be represented in the form of an ID. For example, service information #1 may include one or more of the following: a terminal device vendor ID, a terminal device model ID, a terminal device type ID, or similar. For another example, service information #1 may include one or more of the following: a chip vendor ID, a chip type ID, a chip model ID, or similar.

[00793] For example, support information #1 can be represented as specific content. For example, support information #1 might include one or more of the following: a terminal device vendor, a terminal device type, a terminal device model, or similar. For another example, support information #1 might include one or more of the following: a chip vendor, a chip type, a chip model, or something similar.

[00794] Optionally, the RRC message may also indicate assistance information #2 from channel information #5. Assistance information #2 is specific assistance information for channel information #5.

[00795] For example, assistance information #2 can be represented in the form of an ID. For example, assistance information #2 can include an ID of a CSI measurement moment and / or an ID of a CSI measurement reference signal setting. The CSI measurement moment can be a moment Petition 870250105060, dated 11 / 17 / 2025, pages 170 / 204 164 / 188 measurement of the initial channel information corresponding to channel information #5.

[00796] For example, assistance information #2 can be represented as specific content. Assistance information #2 may include a CSI measurement time, accuracy of channel information #5, and / or similar.

[00797] The following describes an RRC message for transmitting channel information of the field truth channel information type with reference to examples.

[00798] For example, an RRC information element for transmitting channel information #5 may be a CSI-groundtruth message. Each CSI-groundtruth message may include one or more channel information pieces of the field-truth channel information type, and channel information of the field-truth channel information type may be indicated by a CSI-groundtruth.

[00799] For example, a CSI-groundtruth-message may also include at least one of the following: a message identifier (ID), or common assistance #1 information from one or more CSI field truth pieces in the message.

[00800] Each CSI-groundtruth can include a piece of channel information of the field truth channel information type.

[00801] In addition, the CSI-groundtruth from CSI may also include an ID from channel information #5.

[00802] In addition, the CSI-groundtruth from CSI may also include channel #6 information, or a UCI identifier used to transmit channel #6 information.

[00803] In addition, the CSI-groundtruth from CSI may also include assistance information #2 from channel information #5. Petition 870250105060, dated 11 / 17 / 2025, pp. 171 / 204 165 / 188

[00804] Furthermore, research has found that a large amount of training data is generally required to train an AI. If the training data is transmitted using a terminal device, serious overhead will occur at the terminal device's air interface.

[00805] In view of this, one embodiment of this request provides a further method of communication. A training dataset is divided into a plurality of subsets, and the plurality of subsets is transmitted to a training device via a plurality of terminal devices, respectively, to avoid severe overheads on the air interface of the terminal devices.

[00806] FIG. 11 shows a method of communication according to a modality of this request.

[00807] As shown in FIG. 11, method 900 may include the following steps.

[00808] 910: A second device receives a first training dataset from a first device. The first training dataset includes T1 chunks of training data, and T1 is a positive integer. The first training dataset is a subset of a third training dataset. The third training dataset is used for model training.

[00809] 920: A third device receives a second training dataset from the first device. The second training dataset includes T2 pieces of training data, and T2 is a positive integer. The second training dataset is a subset of the third training dataset. The second training dataset and the first training dataset are different subsets of the third training dataset. Petition 870250105060, dated 11 / 17 / 2025, pages 172 / 204 166 / 188

[00810] Optionally, method 900 may also include steps 930 to 950. 930: The second device sends the first set of training data to a fourth device.

[00811] 940: The third device sends the second set of training data to the fourth device.

[00812] 950: The fourth device trains a model based on a fourth training dataset. The fourth training dataset includes at least the first training dataset and the second training dataset.

[00813] It should be noted that the step numbers in method 900 are merely for ease of description and do not constitute any limitation on the order in which the steps in method 900 are performed. For example, steps 910 and 920 can be performed simultaneously, and steps 930 and 940 can be performed simultaneously.

[00814] Each piece of training data is a training sample input for an AI model, or each piece of training data is a training sample and a corresponding label.

[00815] For example, a training sample can be a piece of channel information. For example, a type of channel information can be any of the following: field truth channel information, a channel response, an eigenvector matrix of a channel, a pre-coding matrix, or similar.

[00816] In the solution in this embodiment of this application, the first device divides the third training dataset into a plurality of subsets and transmits the plurality of subsets through a plurality of terminal devices, and a device that receives the plurality of subsets can reassemble the plurality of subsets into a training dataset and perform the training of Petition 870250105060, dated 11 / 17 / 2025, pp. 173 / 204 167 / 188 model based on the reassembled training dataset. This can avoid severe overhead in the air interface of the terminal devices.

[00817] In some scenarios, a network device needs to send a training dataset to an end device, to allow the end device to train an AI model.

[00818] For example, the first device could be a network device, the second and third devices could be endpoint devices, and the fourth device is a server or a cloud server.

[00819] End devices from the same vendor or of the same model can generally use the same AI model, and model training is usually performed by a server from the end device vendor. As shown in FIG. 12, a network device divides a training dataset #1 (an example of the third training dataset) into a plurality of subsets, for example, a subset #1, a subset #2, and a subset #3 in FIG. 12; and transmits, through a plurality of end devices, for example, an end device #1, an end device #2, and an end device #3 in FIG. 12, the plurality of subsets to an end device server, so that the server can receive the plurality of subsets and reassemble the plurality of subsets into a training dataset #2 (an example of the fourth training dataset).

[00820] It should be understood that a number of subsets obtained by division and a number of devices in FIG. 12 are merely examples and do not constitute any limitation to the solution in this embodiment of this application.

[00821] In some scenarios, a terminal device can send a training dataset to a device Petition 870250105060, dated 11 / 17 / 2025, pp. 174 / 204 168 / 188 network, and the network device trains an AI model.

[00822] For example, the first device could be a server or a cloud server, the second and third devices could be endpoint devices, and the fourth device is a network device.

[00823] The network device can be a network device in which one or more AI modules are deployed.

[00824] For example, the network device can be one or more of the following devices shown in FIG. 1: the main network device, the network access node (RAN node), or the OAM. For example, the AI ​​module can be the RIC shown in FIG. 2, for example, a near real-time RIC or a non-real-time RIC. For example, the near real-time RIC is deployed on the RAN node (e.g., a CU or a DU), and the non-real-time RIC is deployed on the OAM, the cloud server, the main network device, or another network device. The RIC can obtain, from the RAN node (e.g., the CU, a CU-CP, a CU-UP, a DU, and / or a RU), subsets of a plurality of endpoint devices, reassemble the subsets into a training dataset #2, and perform training based on training dataset #2.

[00825] For example, near real-time RIC and non-real-time RIC can be deployed independently as a network element, and the network device can be either near real-time RIC or non-real-time RIC.

[00826] As shown in FIG. 13, an end-user server divides a training dataset #1 into a plurality of subsets and transmits the plurality of subsets to a network device via a plurality of end-user devices (e.g., the second device and the third device), so that the network device can receive the plurality of subsets and reassemble the plurality of subsets into a dataset. Petition 870250105060, dated 11 / 17 / 2025, pp. 175 / 204 169 / 188 training, for example, training dataset #2.

[00827] To facilitate description, in method 900, an example in which the first device is a network device is used primarily for description and does not constitute any limitation to the solution in this embodiment of this application.

[00828] The solution in this embodiment of this application can be applied to a training scenario independent of a bilateral model. A CSI feedback model is used below as an example for description. The CSI feedback model includes a CSI generator and a CSI reconfigurator. The first device trains a first CSI feedback model, where the first CSI feedback model includes a first CSI generator and a first CSI reconfigurator.

[00829] For example, an input and an output from a first trained CSI generator can be used as training data in the third training data set. Specifically, the input from the first CSI generator can be used as a training sample, and the output from the first CSI generator can be used as a label corresponding to the training sample. The fourth device can train a second CSI generator based on the fourth training data set, to allow the second CSI generator to produce CSI feedback information that is the same as the CSI feedback information produced by the first CSI generator. The first CSI generator corresponds to the first CSI reconfigurator, and the training data for the second CSI generator are obtained based on the input and output of the first CSI generator. In this way, a second trained CSI generator can be used in cooperation with the first CSI reconfigurator.For example, the first device is a RIC or a network device that includes a RIC, and the RIC can train the first CSI feedback model. Furthermore, Petition 870250105060, dated 11 / 17 / 2025, pp. 176 / 204 170 / 188 the RIC obtains the output of the first trained CSI generator. The input and output of the first trained CSI generator can be used as training data in the third training data set and sent to a plurality of terminal devices via a RAN node or sent directly to a plurality of terminal devices.

[00830] For example, an input and an output from a first trained CSI reconfigurator can be used as training data in the third training data set. The input from the first CSI reconfigurator can be used as a training sample, and the output from the first CSI reconfigurator can be used as a label corresponding to the training sample. The fourth device can train a second CSI reconfigurator based on the fourth training data set, to allow the second CSI reconfigurator to produce CSI reconstruction information that is the same as the CSI reconstruction information produced by the first CSI reconfigurator. The first CSI generator corresponds to the first CSI reconfigurator, and the training data for the second CSI reconfigurator are obtained based on the input and output of the first CSI reconfigurator.Thus, a second trained CSI reconfigurator can be used in cooperation with the first CSI generator. For example, the first device is a RIC or a network device that includes a RIC, and the RIC can train the first CSI feedback model. Furthermore, the RIC obtains the output of the first trained CSI reconfigurator. The input and output of the first trained CSI reconfigurator can be used as training data in the third training dataset and sent to a plurality of terminal devices via a RAN node or sent directly to a plurality of terminal devices.

[00831] Optionally, step 910 may include: The second Petition 870250105060, dated 11 / 17 / 2025, pages 177 / 204 Device 171 / 188 receives the first training dataset and the first device information. The first information indicates an attribute of the first training dataset.

[00832] The first training data set and the first information can be transmitted in the same message or they can be transmitted in different ways or messages. For example, the first information is transmitted using an air interface message, and the first training data set is transmitted using a message that is not defined in a protocol.

[00833] The attribute of the first training dataset may include at least one of the following: an identifier of the third training dataset, an identifier of the first training dataset, a value of T1, positions of the T1 training data chunks in the third training dataset, a quantity of training data in the third training dataset, a minimum value of a quantity of training data that is in the third training dataset and that is sufficient for training, a time domain attribute of the T1 training data chunks, quantization information from the first training dataset, and quantizer information corresponding to the third training dataset.

[00834] The value of T1 is a size of the first training dataset, to be more specific, an amount of training data in the first training dataset.

[00835] For example, the positions of the T1 training data chunks in the third training data set can be represented in the following ways.

[00836] For example, the third dataset of Petition 870250105060, dated 11 / 17 / 2025, pp. 178 / 204 172 / 188 training can be divided into a plurality of subsets. An identifier is defined for each subset, and the subset identifier can indicate a position of the subset in the third training dataset. The identifier of the first training dataset or an identifier of a subset included in the first training dataset can indicate the positions of the T1 training data chunks in the third training dataset.

[00837] For another example, identifiers are defined for all training data in the third training data set. An identifier for each piece of training data can indicate a position of the training data in the third training data set. The identifiers for the T1 training data pieces can indicate the positions of the T1 training data pieces in the third training data set.

[00838] For another example, consecutive identifiers are defined for all training data in the third training data set. An identifier for each piece of training data can indicate a position of the training data in the third training data set. An identifier for any of the T1 pieces of training data can indicate the positions of the T1 pieces of training data in the third training data set. For example, an identifier for the 1st piece of training data among the T1 pieces of training data, or an identifier for the last piece of training data among the T1 pieces of training data, can indicate the positions of the T1 pieces of training data in the third training data set.

[00839] The minimum value w of the amount of training data that is in the third training dataset and that is sufficient for training is a minimum amount w of training data required for training the model. Petition 870250105060, dated 11 / 17 / 2025, pp. 179 / 204 173 / 188 w is less than or equal to the amount of training data in the third training dataset. w is a positive integer. When the amount of training data received by the fourth device is greater than or equal to w, the dataset can be considered successfully received and model training can begin.

[00840] For example, when T1 is greater than 1, the time domain attribute of the T1 training data chunks may include at least one of the following: if the T1 training data chunks are time-domain continuous training data, training data identifiers among the T1 training data chunks that are time-domain continuous, a time interval or periodicity between training data among the T1 training data chunks that are time-domain continuous, or a motion speed of a terminal device.

[00841] If the training data are continuous in the time domain, it indicates whether the training data are correlated in the time domain. For example, the training data are channel information. If a plurality of training data pieces is a plurality of channel information pieces obtained by the same device through periodic measurement, the plurality of training data pieces will be training data that are continuous in the time domain.

[00842] The identifiers of the training data, among the T1 pieces of training data, which are continuous in the time domain, indicate specific training data, among the T1 pieces of training data, which are continuous in the time domain.

[00843] A time domain attribute of training data plays an important role in the performance of an AI model, including a time domain dimension. The AI ​​model including a time domain dimension indicates Petition 870250105060, dated 11 / 17 / 2025, pages 180 / 204 174 / 188 that an input and an output of the AI ​​model are correlated with time. For example, the AI ​​model that includes a time domain dimension might be an AI model used for CSI prediction or an AI model used for time domain channel information compression. For specific descriptions, see the previous descriptions. The details are not described again in this document.

[00844] The quantization information from the first training dataset indicates a training data quantization mode in the first training dataset.

[00845] For example, the quantization information of the first training dataset may include at least one of the following: quantization precision in a scalar quantization-based feedback mode, basis selection information in a codebook-based quantization-based feedback mode, coefficient selection information in a codebook-based quantization-based feedback mode, coefficient quantization precision in a codebook-based quantization mode, or similar.

[00846] For example, the training data in the first training dataset might be channel information obtained through scalar quantization. In this case, the quantization information from the first training dataset might include the quantization accuracy in feedback mode based on scalar quantization.

[00847] For another example, the training data in the first training d...

Claims

1. A communication method characterized in that it comprises: generating first channel information, wherein the first channel information comprises K segments, K is an integer greater than 1, the length of each of the K segments is less than or equal to a first threshold, one type of the first channel information is field truth channel information, and the first channel information is any of the following: a channel response, a channel eigenvector matrix, a precoding matrix, received reference signal power, or a signal-to-interference-plus-noise ratio; and transmitting part or all of the K pieces of uplink control information (UCI) to a network device, wherein the K pieces of UCI comprise respectively the K segments. 2- A method according to claim 1, characterized in that the first threshold is less than or equal to a maximum code length supported by the UCI.

3. A method according to claim 1 or 2, characterized in that the first threshold is predefined, or the method further comprises: receiving the first indication information from the network device, wherein the first indication information indicates the first threshold.

4. A method, according to any one of claims 1 to 3, characterized in that the length of each of the at least K-1 segments of the K segments is equal to the first threshold.

5. Method, according to claim 1 or 2, characterized in that the method further comprises: receiving second indication information from the network device, wherein the second indication information indicates a value Petition 870250090147, dated 03 / 10 / 2025, page 37 / 67 2 / 9 of K. 6- A method according to any one of claims 1 to 5, characterized in that the method further comprises: sending a third indication piece of information to the network device, wherein the third indication piece of information indicates the lengths of the K segments.

7. A method according to any one of claims 1 to 6, characterized in that the method further comprises: receiving the first uplink resource configuration information from the network device, wherein the first uplink resource configuration information indicates a first uplink resource; and transmitting part or all of the K pieces of uplink control information (UCI) to the network device comprises: transmitting the K pieces of UCI to the network device using the first uplink resource.

8. A method according to any one of claims 1 to 6, characterized in that the method further comprises: receiving second uplink resource configuration information from the network device, wherein the second uplink resource configuration information indicates a second uplink resource; and transmitting part or all of the K pieces of uplink control information (UCI) to the network device comprises: transmitting part of the K pieces of UCI to the network device using the second uplink resource.

9. Method according to claim 8, characterized in that the transmission of part of the K UCI pieces to the network device using the second uplink feature comprises: transmitting part of the K UCI pieces and the fourth indication information to the network device using the second uplink feature, wherein the fourth indication information indicates at least one of the following: a total length of untransmitted UCI among the K UCI pieces, or if the K UCI pieces comprise untransmitted UCI; or when part of the K UCI pieces comprises the 1st UCI piece among the K UCI pieces, the fourth indication information indicates at least one of the following: a total length of the first channel information, a total length of untransmitted UCI among the K UCI pieces, or if the K UCI pieces comprise untransmitted UCI.

10. A method according to any one of claims 1 to 6, characterized in that the transmission of part or all of the K uplink control information (UCI) pieces to the network device comprises: transmitting part or all of the K UCI pieces to the network device using a plurality of uplink resources; and the method further comprises: receiving fifth indication information from the network device, wherein the fifth indication information indicates a quantity of UCI pieces transmitted on each of the plurality of uplink resources. 11.A method, according to any one of claims 1 to 6, characterized in that the transmission of part or all of the K uplink control information (UCI) pieces to the network device comprises: transmitting part or all of the K UCI pieces to the network device using a plurality of uplink resources; and the method further comprises: sending the sixth indication information to the network device, wherein the sixth indication information indicates a quantity of UCI pieces transmitted in each of the plurality of uplink resources.

12. A method, according to any one of claims 1 to 6, characterized in that the transmission of part or all of the K uplink control information (UCI) pieces to the network device comprises: transmitting part or all of the K UCI pieces to the network device using a plurality of uplink resources; and the method further comprises: sending the sixth indication information to the network device, wherein the sixth indication information indicates a quantity of UCI pieces transmitted in each of the plurality of uplink resources.39 / 67 4 / 9 of all K pieces of uplink control information UCI to the network device comprises: transmitting part or all of the K pieces of UCI to the network device using a plurality of uplink resources; and the method further comprises: sending the seventh indication information to the network device, wherein the seventh indication information indicates that the plurality of uplink resources corresponds to the same first channel information. 13.A method, according to any one of claims 1 to 12, characterized in that the transmission of part or all of the K uplink control information (UCI) pieces to the network device comprises: transmitting part of the K UCI pieces to the network device; and the method further comprises: discarding untransmitted UCI from among the K UCI pieces, wherein the timing begins from a transmission moment of the 1st UCI piece among the K UCI pieces that is greater than or equal to one second threshold. 14.A method, according to any one of claims 1 to 12, characterized in that the transmission of part or all of the K uplink control information (UCI) pieces to the network device comprises: transmitting part of the K UCI pieces to the network device; and the method further comprises: discarding untransmitted UCI from among the K UCI pieces, wherein the timing starting from a second channel information transmission moment is greater than or equal to a third threshold, and the first channel information is used to measure the accuracy of the second channel information.

15. A communication method, characterized in that it comprises: generating third channel information based on a first Petition 870250090147, dated 03 / 10 / 2025, p.40 / 67 5 / 9 feedback configuration, to enable a total length of the third channel information to be less than or equal to a maximum code length supported by the UCI, wherein one type of third channel information is field truth channel information; transmit first UCI to a network device, wherein the first UCI comprises the third channel information; generate fourth channel information based on a second feedback configuration, wherein the accuracy of the fourth channel information is less than the accuracy of the third channel information, and one type of fourth channel information is not field truth channel information; and transmit the second UCI to the network device, wherein the second UCI comprises the fourth channel information.

16. Method, according to claim 15, characterized in that the accuracy of the third channel information is greater than or equal to a fourth threshold. 17.A method according to claim 16, characterized in that the fourth threshold is predefined, or the method further comprises: receiving eighth indication information from the network device, wherein the eighth indication information indicates the fourth threshold.

18. A method according to any one of claims 15 to 17, characterized in that a configuration item of the first feedback configuration comprises at least one of the following: a sub-band configuration of the third channel information, a layer configuration of the third channel information, a quantization precision configuration in a scalar quantization-based feedback mode, a basis configuration in a codebook-based quantization-based feedback mode, or a non-zero coefficient configuration in a codebook-based quantization-based feedback mode. Petition 870250090147, dated 10 / 03 / 2025, p.41 / 67 6 / 9 19. Method, according to any one of claims 15 to 18, characterized in that a parameter value of a first configuration item in the first feedback configuration item is based on a range of the first configuration item.

20. Method, according to claim 19, characterized in that the range of the first configuration item is predefined, or the method further comprises: receiving the ninth indication information from the network device, wherein the ninth indication information indicates the range of the first configuration item.

21. Communication method, characterized in that it comprises: generating fifth channel information, wherein one type of fifth channel information is field truth channel information; transmitting fifth channel information to a network device using upper layer signaling. 22.Communication method, characterized in that it comprises: sending a first set of training data to a second device, wherein the first set of training data comprises T1 pieces of training data, and T1 is a positive integer; and sending a second set of training data to a third device, wherein the second set of training data comprises T2 pieces of training data, T2 is a positive integer, the second set of training data and the first set of training data are different subsets of a third set of training data, and the third set of training data is used for model training. 23 Communication method, characterized in that Petition 870250090147, dated 03 / 10 / 2025, p.42 / 67 7 / 9 comprises: receiving part or all of the K UTI pieces from a terminal device, wherein the K UTI pieces comprise respectively K segments of first channel information, K is an integer greater than 1, a length of each of the K segments is less than or equal to a first threshold, a type of first channel information is field truth channel information, and the first channel information is any of the following: a channel response, a channel eigenvector matrix, a pre-encoding matrix, received reference signal power, or a signal-to-interference-plus-noise ratio; and obtaining, based on part or all of the K UTI pieces, a segment comprised in part or all of the K UTI pieces. 24.A communication method characterized in that it comprises: receiving a first UCI from a terminal device, wherein the first UCI comprises third channel information, the third channel information corresponds to a first feedback configuration, and one type of the third channel information is true-field channel information; and receiving a second UCI from the terminal device, wherein the second UCI comprises fourth channel information, the fourth channel information corresponds to a second feedback configuration, the accuracy of the fourth channel information is less than the accuracy of the third channel information, and one type of the fourth channel information is not true-field channel information. 25.A communication method characterized by the fact that it comprises: receiving fifth channel information from a terminal device using upper-layer signaling, wherein one type of fifth channel information is field truth channel information; Petition 870250090147, dated 10 / 03 / 2025, page 43 / 67 8 / 9 performing data processing based on the fifth channel information or forwarding the fifth channel information. 26.A communication method, characterized in that the method comprises: receiving a first training dataset from a first device, wherein the first training dataset comprises T1 training dataset pieces, and T1 is a positive integer; and sending the first training dataset to a fourth device, to enable the fourth device to train a model based on a fourth training dataset, wherein the fourth training dataset comprises at least the first training dataset and a second training dataset, the first training dataset and the second training dataset are different subsets of a third training dataset, the second training dataset comprises T2 training dataset pieces, and T2 is a positive integer. 27.Computer-readable storage medium, characterized in that the computer-readable storage medium comprises instructions, and when the instructions are run by a processor, the method as defined in any one of claims 1 to 26 is implemented.

28. Communication apparatus, characterized in that the communication apparatus comprises a processor and a storage medium, the storage medium stores instructions and, when the instructions are run by the processor, the communication apparatus is enabled to perform the method as defined in any one of claims 1 to 26.

29. Chip, characterized in that it comprises a processor, wherein the processor is configured to run a program or instructions, to implement the method as defined in any one of claims 1 to 26.

30. Communication system, characterized in that it comprises one or a combination of the following communication devices: a communication device for carrying out the method as defined in any one of claims 1 to 26.

Images