Communication methods and communication devices

Abstract

Embodiments of the present invention provide a communication method and a communication apparatus. The method comprises the steps of: generating first channel information, wherein the first channel information comprises K segments, where K is an integer greater than 1, the length of each of the K segments is less than or equal to a first threshold, the type of the first channel information is ground truth channel information, and the first channel information is one of a channel response, a channel eigenvector matrix, a precoding matrix, a reference signal received power, or a signal-to-interference plus noise ratio; and transmitting some or all of the K uplink control information (UCI) to a network device, wherein each of the K UCIs comprises the K segments. The solution in the embodiment of the present invention may be applied to a communication system having AI / ML capabilities to enable a network device to acquire high-precision channel information.

Description

[Technical Field]

[0001] This application claims priority to Chinese Patent Application No. 202310396390.8, entitled “Communication Method and Communication Apparatus,” filed with the China National Intellectual Property Administration on April 6, 2023, which is incorporated herein by reference in its entirety.

[0002] Embodiments of this application relate to the field of communications, and more specifically, to communications methods and communications devices. [Background technology]

[0003] In a communication system, network devices need to determine downlink channel-related configuration information, such as resources, modulation and coding schemes (MCS), and precoding used to schedule downlink data channels for terminal devices, based on downlink channel state information (CSI). Terminal devices may calculate downlink CSI by measuring downlink reference signals and feed back the downlink CSI to the network device using uplink control information (UCI). In this scenario, the CSI acquired by the network device is usually significantly compressed, resulting in low accuracy. However, in some scenarios, network devices need to collect CSI with higher accuracy or precision. 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 as monitoring data to monitor the performance of an AI model.

[0004] Therefore, how to enable network devices to acquire high-precision CSI is an urgent issue that needs to be resolved. [Overview of the project]

[0005] Embodiments of the present invention provide a communication method and a communication apparatus to enable a network device to acquire high-precision channel information.

[0006] According to the first aspect, a communication method is provided. The method may be performed by a terminal device, or by a chip or circuit located within the terminal device. This is not limited to the present invention.

[0007] The method comprises the steps of: generating first channel information, wherein the first channel information comprises K segments, where K is an integer greater than 1, the length of each of the K segments is less than or equal to a first threshold, the type of the first channel information is ground truth channel information, and the first channel information is one of a channel response, a channel eigenvector matrix, a precoding matrix, a reference signal received power, or a signal-to-interference plus noise ratio; and transmitting some or all of the K UCIs to a network device, wherein each of the K UCIs comprises K segments.

[0008] In the solution of this embodiment of the present application, ground truth channel information is divided into multiple segments and transmitted using multiple UCIs, and as a result, the network device can acquire channel information with high feedback overhead, i.e., high-precision channel information.

[0009] The first threshold relates to the maximum code length supported by UCI.

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

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

[0012] In relation 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] Ground truth channel information has high accuracy and, consequently, high feedback overhead. This feedback overhead may exceed the maximum code length supported by UCI. In the solution of this embodiment, the length of each segment may be less than the maximum code length supported by UCI, and as a result, segments can be transmitted using multiple UCIs.

[0014] In relation to the first embodiment, in some implementations of the first embodiment, the first threshold is predefined, or the method further comprises the step of receiving first instruction information from a network device, wherein the first instruction information indicates a first threshold.

[0015] In relation to the first embodiment, in some implementations of the first embodiment, the length of each of at least K-1 segments out of K segments is equal to a first threshold.

[0016] In relation to the first embodiment, in some implementations of the first embodiment, the method further comprises the step of receiving second instruction information from a network device, wherein the second instruction information indicates a value of K.

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

[0018] In relation to the first embodiment, in some implementations of the first embodiment, the method further comprises the step of transmitting third instruction information to a network device, wherein the third instruction information indicates the length of K segments.

[0019] The length of K segments is the length of K UCIs. It can be understood that the total length of the K UCIs may be the same or different. Whether the lengths are the same or different may be determined specifically by a predetermined protocol or by information between network devices and terminal devices. If the total length of the UCIs is the same, the length may be predetermined by a predetermined protocol, or network devices and terminal devices may be able to recognize the length based on information between them. If the lengths are different, the length of each of the K UCIs may be determined according to a predetermined rule in the protocol, or network devices and terminal devices may be able to recognize the length of the transmitted UCI based on information between them.

[0020] In some scenarios, the network device is unaware of the lengths of the K segments, and the terminal device may inform the network device of the length of each segment, so that the network device can decode each UCI to obtain each segment of channel information.

[0021] In relation to the first embodiment, in some implementations of the first embodiment, the method further comprises the step of receiving first uplink resource configuration information from a network device, where the first uplink resource configuration information indicates a first uplink resource; and the step of transmitting some or all of K UCIs to a network device comprises the step of transmitting K UCIs to a network device using the first uplink resource.

[0022] For example, the first uplink resource may be distributed across J time resource units, where each time resource unit may be one or a combination of multiple slots. The first uplink resource may be considered as J uplink resources, where J is a positive integer.

[0023] In this way, K UCIs can be transmitted using a first uplink resource that is scheduled in a single step by the network device, which helps to improve channel information transmission efficiency.

[0024] In relation to the first embodiment, in some implementations of the first embodiment, the method further comprises the step of receiving second uplink resource configuration information from a network device, where the second uplink resource configuration information indicates a second uplink resource; and the step of transmitting some or all of K UCIs to a network device comprises the step of transmitting some of K UCIs to a network device using the second uplink resource.

[0025] In relation to the first embodiment, in some implementations of the first embodiment, the step of transmitting a portion of K UCIs to a network device using a second uplink resource includes the step of transmitting a portion of K UCIs and a fourth instruction information to a network device using a second uplink resource, wherein the fourth instruction information indicates at least one of the following: the total length of the untransmitted UCI among the K UCIs, or whether the K UCIs include an untransmitted UCI; or, if a portion of the K UCIs includes the first UCI among the K UCIs, the fourth instruction information indicates at least one of the following: the total length of the first channel information, the total length of the untransmitted UCI among the K UCIs, or whether the K UCIs include an untransmitted UCI.

[0026] For example, if K UCIs include untransmitted UCIs, the terminal device may wait for the network device to schedule another uplink resource to transmit the untransmitted UCIs among the K UCIs.

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

[0028] For example, if K UCIs include untransmitted UCIs, a terminal device may transmit the remaining untransmitted UCIs by using one or more other subsequent uplink resources, for example, by using uplink resources used to transmit uplink data to transmit the untransmitted UCIs among the K UCIs.

[0029] In the solution of this embodiment of the present application, the terminal device may request uplink resources from the network device to transmit untransmitted segments. This helps to make appropriate use of uplink resources and avoid resource waste.

[0030] In relation to the first embodiment, in some implementations of the first embodiment, the method further comprises the steps of: receiving third uplink resource configuration information from a network device, wherein the third uplink resource configuration information indicates a third uplink resource; and transmitting instruction information to a network device using the third uplink resource, wherein the instruction information indicates the total length of the first channel information.

[0031] In relation to the first embodiment, in some implementations of the first embodiment, the step of transmitting some or all of K UCIs to a network device includes the step of transmitting some or all of K UCIs to a network device by using a plurality of uplink resources; and the method further includes the step of receiving a fifth instruction information from a network device, wherein the fifth instruction information indicates the number of UCIs to be transmitted in each of the plurality of uplink resources.

[0032] For example, the fifth instruction information may further indicate the specific UCI to be transmitted at each uplink resource.

[0033] For example, the fifth instruction information may indicate the number of segments transmitted at each uplink resource, including, for example, the number of each segment to be transmitted, or one or more of the start number, number of segments, or end number of the segments to be transmitted. The portion of one or more items not indicated by the fifth instruction information may be obtained in another way, for example, by being predefined in the protocol. The number of each segment indicates the position of that segment among K segments.

[0034] For example, multiple uplink resources can be understood as uplink resources that are scheduled multiple times by a network device.

[0035] For example, multiple uplink resources may be understood as multiple periodic uplink resources composed of network devices.

[0036] For example, an uplink resource scheduled in a single operation by a network device may be distributed across multiple time resource units, and these multiple time resource units may be used as multiple uplink resources.

[0037] In relation to the first embodiment, in some implementations of the first embodiment, the step of transmitting some or all of K UCIs to a network device includes the step of transmitting some or all of K UCIs to a network device by using a plurality of uplink resources; and the method further includes the step of transmitting a sixth instruction information to a network device, wherein the sixth instruction information indicates the number of UCIs to be transmitted in each of the plurality of uplink resources.

[0038] For example, the sixth instruction information may further indicate the specific UCI transmitted at each uplink resource, in other words, it may indicate the location of the segment included in the UCI transmitted at each uplink resource among the K segments.

[0039] For example, the sixth instruction information may indicate the number of segments transmitted at each uplink resource, including, for example, the number of each segment to be transmitted, or one or more of the start number, number of segments, or end number of the segments to be transmitted. The portion of one or more items not indicated by the sixth instruction information may be obtained in another way, for example, by being predefined in the protocol. The number of each segment indicates the position of that segment among K segments.

[0040] In relation to the first embodiment, in some implementations of the first embodiment, the step of transmitting some or all of K UCIs to a network device includes the step of transmitting some or all of K UCIs to a network device by using a plurality of uplink resources; and the method further includes the step of transmitting a seventh instruction information to a network device, wherein the seventh instruction information indicates that the plurality of uplink resources correspond to the same first channel information.

[0041] For example, the seventh instruction information includes an identifier carried by the uplink resource. Each uplink resource may carry an identifier, which is used to distinguish channel information. If two uplink resources carry the same identifier, the information transmitted using these two uplink resources will indicate the same channel information. If two uplink resources carry different identifiers, the information transmitted using these two uplink resources will indicate different channel information.

[0042] In relation to the first embodiment, in some implementations of the first embodiment, the step of transmitting some or all of K UCIs to a network device comprises the step of transmitting some of the K UCIs to a network device; and the method further comprises the step of discarding untransmitted UCIs among the K UCIs, wherein the timing starting from the transmission time of the first UCI among the K UCIs is greater than or equal to a second threshold.

[0043] For example, the timer is started at the time of transmission of the first UCI, and if the timer timing is greater than or equal to a second threshold, any untransmitted UCIs among the K UCIs are discarded. For example, the time of transmission of the first UCI may be the start or end of transmission of the first UCI, or another time that is based on the start or end of transmission of the first UCI, provided that such time can represent the duration for which channel information is transmitted using the UCI. This is not limited to the foregoing.

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

[0045] In relation to the first embodiment, in some implementations of the first embodiment, the step of transmitting some or all of K UCIs to a network device comprises the step of transmitting some of the K UCIs to a network device; and the method further comprises the step of discarding the untransmitted UCIs among the K UCIs, wherein the timing starting from the transmission time of the second channel information 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 transmission time of the second channel information may be the start or end of the transmission of the second channel information, or another time using the start or end of the transmission of the second channel information as a reference, provided that the time can represent the duration of transmission of the second channel information. This is not limited herein.

[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 a third threshold, any untransmitted UCIs among the K UCIs are discarded.

[0047] The first channel information is used to measure the accuracy of the second channel information. If an excessively long time has elapsed since the transmission of the second channel information, the actual channel information may have changed, making it difficult to measure the current performance of the model using the first and second channel information. The terminal device may determine that the transmission of the first channel information has failed and discard the remaining segment. This helps to avoid wasting resources.

[0048] According to a second aspect, a communication method is provided. The method may be performed by a terminal device, or by a chip or circuit located within the terminal device. This is not limited to the present invention.

[0049] The method comprises the steps of: generating third channel information based on a first feedback configuration so that the total length of the third channel information is less than or equal to the maximum code length supported by the UCI, wherein the type of the third channel information is ground truth channel information; transmitting the first UCI to a network device, wherein the first UCI includes the third channel information; generating fourth channel information based on a second feedback configuration, wherein the precision of the fourth channel information is lower than that of the third channel information, and the type of the fourth channel information is not ground truth channel information; and transmitting the second UCI to a network device, wherein the second UCI includes the fourth channel information.

[0050] According to the solution in this embodiment of the present application, when the channel information fed back by the terminal device is ground truth channel information, high-precision channel information can be generated by using the first feedback configuration, and the length of the channel information can be less than or equal to the maximum code length supported by UCI. In this way, both high-precision channel information and other low-precision channel information can be transmitted using UCI, and network devices can acquire the high-precision channel information.

[0051] The accuracy of channel information may be indicated by the correlation or error between the channel information and the reference channel information of the channel information.

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

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

[0054] The reference channel information for channel information may be the initial channel information corresponding to the channel information, specifically, the channel information acquired by the terminal device through measurement.

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

[0056] In relation to the second aspect, in some implementations of the second aspect, the fourth threshold is predefined, or the method further comprises the step of receiving an eighth instruction information from a network device, where the eighth instruction information indicates the fourth threshold.

[0057] In relation to the second aspect, in some implementations of the second aspect, the components of the first feedback configuration include at least one of the following: a subband configuration of the third channel information, a layer configuration of the third channel information, a quantization accuracy configuration in a feedback mode based on scalar quantization, a base configuration in a feedback mode based on codebook-based quantization, or a non-zero coefficient configuration in a feedback mode based on codebook-based quantization.

[0058] In relation to the second aspect, in some implementations of the second aspect, the parameter value of the first component within the components of the first feedback configuration is based on the range of the first component.

[0059] The terminal device may determine the parameter values ​​of each parameter of the first component within the scope of the first component.

[0060] The first component may be any one of the following: a subband configuration of the third channel information, a layer configuration of the third channel information, a quantization accuracy configuration in a feedback mode based on scalar quantization, a base configuration in a feedback mode based on codebook-based quantization, or a non-zero coefficient configuration in a feedback mode based on codebook-based quantization.

[0061] In relation to the second aspect, in some implementations of the second aspect, the scope of the first component is predefined, or the method further comprises the step of receiving ninth instruction information from a network device, where the ninth instruction information indicates the scope of the first component.

[0062] In relation to the second aspect, in some implementations of the second aspect, the first component includes at least one of the following: a subband configuration of the third channel information, a layer configuration of the third channel information, a quantization precision configuration in a feedback mode based on scalar quantization, a base configuration in a feedback mode based on codebook-based quantization, or a non-zero coefficient configuration in a feedback mode based on codebook-based quantization; the range of the subband configuration includes at least one of the following: a range of values ​​for the number of subbands of the third channel information, a set of subband combinations of the third channel information, or a range of values ​​for the subband granularity of the third channel information; the range of the layer configuration includes at least one of the following: a range of values ​​for the number of layers of the third channel information, or a set of layer combinations of the third channel information; in a feedback mode based on scalar quantization The range of the quantization precision configuration includes a range of values ​​for the quantization precision in the feedback mode based on scalar quantization; the range of the basis configuration in the feedback mode based on codebook-based quantization includes at least one of a range of values ​​indicating the number of bases of the third channel information in the feedback mode based on codebook-based quantization, or a set indicating the basis combinations of the third channel information in the feedback mode based on codebook-based quantization; or the range of the non-zero coefficient configuration in the feedback mode based on codebook-based quantization includes at least one of a range of values ​​indicating the number of non-zero coefficients of the third channel information in the feedback mode based on codebook-based quantization, or a range of values ​​indicating the non-zero coefficient quantization precision of the third channel information in the feedback mode based on codebook-based quantization.

[0063] In relation to the second aspect, in some implementations of the second aspect, the parameter values ​​of multiple components in the first feedback configuration are based on the correspondence between the parameter values ​​of multiple components in the first feedback configuration.

[0064] In relation to the second aspect, in some implementations of the second aspect, the parameter value of the second component in the first feedback configuration is based on the correspondence between the parameter value of the third component in the first feedback configuration and the parameter values ​​of multiple components in the first feedback configuration, wherein the third component and the second component belong to multiple components.

[0065] The second component may be any one of the following: a subband configuration of the third channel information, a layer configuration of the third channel information, a quantization accuracy configuration in a feedback mode based on scalar quantization, a base configuration in a feedback mode based on codebook-based quantization, or a non-zero coefficient configuration in a feedback mode based on codebook-based quantization.

[0066] The third component may be any one of the following: a subband configuration of the third channel information, a layer configuration of the third channel information, a quantization accuracy configuration in a feedback mode based on scalar quantization, a base configuration in a feedback mode based on codebook-based quantization, or a non-zero coefficient configuration in a feedback mode based on codebook-based quantization.

[0067] The second and third components may be different components.

[0068] For example, the parameter value of the third component may be determined by the terminal device.

[0069] For example, the parameter value of the third component may be determined based on the range of the third component.

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

[0071] In relation to the second aspect, in some implementations of the second aspect, the correspondence between the parameter values ​​of a plurality of components is predefined, or the method further comprises the step of receiving a 10th instruction information from a network device, wherein the 10th instruction information indicates the correspondence between the parameter values ​​of a plurality of components.

[0072] In relation to the second aspect, in some implementations of the second aspect, the method further comprises the step of transmitting 11th instruction information to a network device, wherein the 11th instruction information indicates parameter values ​​for some or all of the components in the first feedback configuration.

[0073] In some scenarios, some or all of the parameter values ​​for the configuration items may be determined by the terminal device, and the terminal device may notify the network device of some or all of the parameter values ​​for the configuration items.

[0074] According to a third aspect, a communication method is provided. The method may be performed by a terminal device, or by a chip or circuit located within the terminal device. This is not limited to the present invention.

[0075] The method comprises the steps of generating a fifth channel information, where the type of the fifth channel information is ground truth channel information; and transmitting the fifth channel information to a network device using upper-layer signaling.

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

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

[0078] In relation to the third aspect, in some implementations of the third aspect, the first RRC message indicates the correspondence 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 further indicate the transmission time of the UCI, which includes a sixth channel. The transmission time of the UCI may be indicated by the identifier of the UCI transmission slot.

[0080] A fourth aspect provides a communication method, which may be performed by a first device or by a chip or circuit located within the first device. This is not limited to the present invention.

[0081] The method involves the steps of: sending a first training dataset to a second device, where the first training dataset contains T1 training data points, where T1 is a positive integer; and sending a second training dataset to a third device, where the second training dataset contains T2 training data points, where T2 is a positive integer; the second and first training datasets being distinct subsets of the third training dataset, the third training dataset being used for model training; and It is equipped with.

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

[0083] In the solution of this embodiment of the present application, the first device divides the third training dataset into multiple subsets, transmits the multiple subsets through multiple terminal devices, and the devices receiving the multiple subsets reassemble the multiple subsets into a training dataset and perform model training based on the reassembled training dataset. This avoids the significant air interface overhead of the terminal devices.

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

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

[0086] In relation to the fourth aspect, in some implementations of the fourth aspect, the step of sending a first training dataset to a second device includes the step of sending the first training dataset and first information to the second device, where the first information indicates the attributes of the first training dataset.

[0087] In relation 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] In relation to the fourth aspect, in some implementations of the fourth aspect, the attributes of the first training dataset include at least one of the following: an identifier for the third training dataset, the identifier for the first training dataset, the value of T1, the positions of T1 training data in the third training dataset, the amount of training data in the third training dataset, the minimum amount of training data in the third training dataset that is sufficient for training, the time-domain attributes of T1 training data, quantization information for the first training dataset, and quantizer information corresponding to the third training dataset.

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

[0090] In relation to the fourth aspect, in some implementations of the fourth aspect, the method further comprises the step of receiving first request information from a fifth device, where the first request information is used to request a fifth training dataset, the fifth training dataset containing T3 training data, where 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 a different device from the second and third devices.

[0092] In relation to the fourth aspect, in some implementations of the fourth aspect, the first request information may include at least one of the identifiers of the third training dataset, the identifier of the fifth training dataset, the identifiers of T3 training data, or the identifier of the received training data.

[0093] According to a fifth aspect, a communication method is provided. The method may be performed by a network device, or by a chip or circuit located within a network device. This is not limited to the present invention.

[0094] The method comprises the steps of receiving some or all of K UCIs from a terminal device, where each of the K UCIs contains K segments of first channel information, where K is an integer greater than 1, the length of each of the K segments is less than or equal to a first threshold, the type of first channel information is ground truth channel information, and the first channel information is one of the following: channel response, channel eigenvector matrix, precoding matrix, reference signal received power, or signal-to-interference plus noise ratio; and acquiring segments contained in some or all of the K UCIs based on some or all of the K UCIs.

[0095] In relation 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 UCI.

[0096] In relation to the fifth aspect, in some implementations of the fifth aspect, the first threshold is predefined, or the method further comprises the step of transmitting first instruction information to a terminal device, wherein the first instruction information indicates a first threshold.

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

[0098] In relation to the fifth aspect, in some implementations of the fifth aspect, the method further comprises the step of transmitting a second instruction information to a terminal device, wherein the second instruction information indicates a value of K.

[0099] In relation to the fifth aspect, in some implementations of the fifth aspect, the method further comprises the step of receiving third instruction information from a terminal device, wherein the third instruction information indicates the lengths of K segments.

[0100] In relation to the fifth aspect, in some implementations of the fifth aspect, the method further comprises the step of transmitting first uplink resource configuration information to a terminal device, wherein the first uplink resource configuration information indicates a first uplink resource; and the step of receiving some or all of K UCIs from the terminal device comprises the step of receiving K UCIs from the terminal device by using the first uplink resource.

[0101] In relation to the fifth aspect, in some implementations of the fifth aspect, the method further comprises the step of transmitting a second uplink resource configuration information to a terminal device, wherein the second uplink resource configuration information indicates a second uplink resource; and the step of receiving some or all of K UCIs from the terminal device comprises the step of receiving some of K UCIs from the terminal device by using the second uplink resource.

[0102] In relation to the fifth aspect, in some implementations of the fifth aspect, the step of receiving a portion of K UCIs from a terminal device by using a second uplink resource includes the step of receiving a portion of K UCIs and a fourth instruction information from a terminal device by using a second uplink resource, wherein the fourth instruction information indicates at least one of the following: the total length of the untransmitted UCI among the K UCIs, or whether the K UCIs include an untransmitted UCI; or, if a portion of the K UCIs includes the first UCI among the K UCIs, the fourth instruction information indicates at least one of the following: the total length of the first channel information, the total length of the untransmitted UCI among the K UCIs, or whether the K UCIs include an untransmitted UCI.

[0103] In relation to the fifth aspect, in some implementations of the fifth aspect, the step of receiving some or all of K UCIs from a terminal device has the step of receiving some or all of K UCIs from a terminal device by using a plurality of uplink resources; and the method further comprises the step of transmitting fifth instruction information to a terminal device, wherein the fifth instruction information indicates the number of UCIs transmitted in each of the plurality of uplink resources.

[0104] In relation to the fifth aspect, in some implementations of the fifth aspect, the step of receiving some or all of K UCIs from a terminal device has the step of receiving some or all of K UCIs from a terminal device by using a plurality of uplink resources; and the method further comprises the step of receiving a sixth instruction information from a terminal device, wherein the sixth instruction information indicates the number of UCIs transmitted in each of the plurality of uplink resources.

[0105] In relation to the fifth aspect, in some implementations of the fifth aspect, the step of receiving some or all of K UCIs from a terminal device is to use a plurality of uplink resources to receive some or all of K UCIs from a terminal device; and the method further comprises the step of receiving a seventh instruction information from a terminal device, wherein the seventh instruction information indicates that the plurality of uplink resources correspond to the same first channel information.

[0106] According to a sixth aspect, a communication method is provided. The method may be performed by a network device, or by a chip or circuit located within a network device. This is not limited to the present invention.

[0107] The method comprises the steps of: receiving a first UCI from a terminal device, wherein the first UCI includes a third channel information, the third channel information corresponds to a first feedback configuration, and the type of the third channel information is ground truth channel information; and receiving a second UCI from a terminal device, wherein the second UCI includes a fourth channel information, the fourth channel information corresponds to a second feedback configuration, the precision of the fourth channel information is lower than that of the third channel information, and the type of the fourth channel information is not ground truth channel information.

[0108] In relation to the sixth aspect, in some implementations of the sixth aspect, the accuracy of the third channel information is greater than or equal to the fourth threshold.

[0109] In relation to the sixth aspect, in some implementations of the sixth aspect, the fourth threshold is predefined, or the method further comprises the step of transmitting an eighth instruction information to a terminal device, where the eighth instruction information indicates the fourth threshold.

[0110] In relation to the sixth aspect, in some implementations of the sixth aspect, the components of the first feedback configuration include at least one of the following: a subband configuration of the third channel information, a layer configuration of the third channel information, a quantization accuracy configuration in a feedback mode based on scalar quantization, a base configuration in a feedback mode based on codebook-based quantization, or a non-zero coefficient configuration in a feedback mode based on codebook-based quantization.

[0111] In relation to the sixth aspect, in some implementations of the sixth aspect, the parameter value of the first component within the components of the first feedback configuration is based on the range of the first component.

[0112] In relation to the sixth aspect, in some implementations of the sixth aspect, the scope of the first component is predetermined, or the method further comprises the step of transmitting a ninth instruction information to a terminal device, where the ninth instruction information indicates the scope of the first component.

[0113] In relation to the sixth aspect, in some implementations of the sixth aspect, the first component includes at least one of a subband configuration of the third channel information, a layer configuration of the third channel information, a quantization precision configuration in a feedback mode based on scalar quantization, a base configuration in a feedback mode based on codebook-based quantization, or a non-zero coefficient configuration in a feedback mode based on codebook-based quantization; the range of the subband configuration includes at least one of a value range for the number of subbands of the third channel information, a set of subband combinations of the third channel information, or a value range for the subband granularity of the third channel information; the range of the layer configuration includes at least one of a value range for the number of layers of the third channel information, or a set of layer combinations of the third channel information; in a feedback mode based on scalar quantization The range of the quantization precision configuration includes a range of values ​​for the quantization precision in the feedback mode based on scalar quantization; the range of the basis configuration in the feedback mode based on codebook-based quantization includes at least one of a range of values ​​indicating the number of bases of the third channel information in the feedback mode based on codebook-based quantization, or a set indicating the basis combinations of the third channel information in the feedback mode based on codebook-based quantization; or the range of the non-zero coefficient configuration in the feedback mode based on codebook-based quantization includes at least one of a range of values ​​indicating the number of non-zero coefficients of the third channel information in the feedback mode based on codebook-based quantization, or a range of values ​​indicating the non-zero coefficient quantization precision of the third channel information in the feedback mode based on codebook-based quantization.

[0114] In relation to the sixth aspect, in some implementations of the sixth aspect, the parameter values ​​of multiple components in the first feedback configuration are based on the correspondence between the parameter values ​​of multiple components in the first feedback configuration.

[0115] In relation to the sixth aspect, in some implementations of the sixth aspect, the parameter value of the second component in the first feedback configuration is based on the correspondence between the parameter value of the third component in the first feedback configuration and the parameter values ​​of multiple components in the first feedback configuration, wherein the third component and the second component belong to multiple components.

[0116] In relation to the sixth aspect, in some implementations of the sixth aspect, the correspondence between the parameter values ​​of a plurality of components is predefined, or the method further comprises the step of transmitting a 10th instruction information to a terminal device, wherein the 10th instruction information indicates the correspondence between the parameter values ​​of a plurality of components.

[0117] In relation to the sixth aspect, in some implementations of the sixth aspect, the method further comprises the step of receiving eleventh instruction information from a terminal device, wherein the eleventh instruction information indicates parameter values ​​for some or all of the components in the first feedback configuration.

[0118] According to the seventh aspect, a communication method is provided. The method may be performed by a network device, or by a chip or circuit located within a network device. This is not limited to the present invention.

[0119] The method comprises the steps of: receiving fifth channel information from a terminal device using upper-layer signaling, wherein the type of fifth channel information is ground truth channel information; and performing data processing based on the fifth channel information or transferring the fifth channel information.

[0120] For example, the fifth channel information may be used for model monitoring.

[0121] In another example, the fifth channel information may be used for model training.

[0122] For example, performing data processing based on the fifth channel information may include performing model training, model monitoring, or similar operations based on the fifth channel information.

[0123] For example, transferring the fifth channel information may include transferring the fifth channel information to another device having an AI module. The AI ​​module is configured to implement corresponding AI functions, such as model monitoring or model training.

[0124] In relation to the seventh aspect, in some implementations of the seventh aspect, the upper-layer signaling includes a first RRC message.

[0125] In relation to the seventh aspect, in some implementations of the seventh aspect, the first RRC message is further used to transmit sixth channel information, and the fifth channel information is used to measure the accuracy of the sixth channel information.

[0126] In relation to the seventh aspect, in some implementations of the seventh aspect, the first RRC message indicates the correspondence 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.

[0127] According to the eighth aspect, a communication method is provided. The method may be performed by a second device, or by a chip or circuit located within the second device. This is not limited to the present invention.

[0128] The method comprises the steps of: receiving a first training dataset from a first device, wherein the first training dataset contains T1 training data points, where T1 is a positive integer; and sending the first training dataset to a fourth device, enabling the fourth device to train a model based on a fourth training dataset, wherein the fourth training dataset contains at least the first training dataset and a second training dataset, where the first and second training datasets are distinct subsets of the third training dataset, and the second training dataset contains T2 training data points, where T2 is a positive integer.

[0129] The second training dataset is transmitted to the fourth device via the third device. The second and third devices are different devices.

[0130] For example, the first device may be a network device, the second and third devices may be terminal devices, and the fourth device may be a server or cloud server.

[0131] For example, the first device may be a server or a cloud server, the second and third devices may be terminal devices, and the fourth device may be a network device.

[0132] In relation to the eighth aspect, in some implementations of the eighth aspect, the step of receiving a first training dataset from a first device further comprises the step of receiving the first training dataset and first information from the first device, where the first information indicates the attributes of the first training dataset.

[0133] In relation to the eighth aspect, in some implementations of the eighth aspect, the first training dataset and the first information are transmitted in different ways or messages.

[0134] In relation to the eighth aspect, in some implementations of the eighth aspect, the attributes of the first training dataset include at least one of the following: an identifier for the third training dataset, the identifier for the first training dataset, the value of T1, the positions of T1 training data in the third training dataset, the amount of training data in the third training dataset, the minimum amount of training data in the third training dataset that is sufficient for training, the time-domain attributes of T1 training data, quantization information for the first training dataset, and quantizer information corresponding to the third training dataset.

[0135] In relation to the eighth aspect, in some implementations of the eighth aspect, the method further comprises the step of sending first request information to a first device, where the first request information is used to request a fifth training dataset, the fifth training dataset containing T3 training data, where T3 is a positive integer, and the fifth training dataset is a subset of the third training dataset.

[0136] In relation to the eighth aspect, in some implementations of the eighth aspect, the first request information may include at least one of the identifiers of the third training dataset, the identifier of the fifth training dataset, the identifiers of T3 training data, or the identifier of the received training data.

[0137] According to the ninth aspect, a communication device is provided. The communication device may be a terminal device, or a device, module, circuit, chip or similar located within a terminal device, or a device that can be used in conjunction with a terminal device. In the design, the communication device may include a module that has a one-to-one correspondence with the operation / stage / operation of the method described in any one of the first, second, third, or eighth aspects. The module may be a hardware circuit or software, or may be implemented by using a hardware circuit in combination with software. In the design, the communication device may include a processing module and a communication module.

[0138] The transmitting module is configured to perform a transmitting operation in the manner described in any one of the first, second, third, or eighth aspects. The processing module is configured to perform a processing operation in the manner described in any one of the first, second, third, or eighth aspects.

[0139] According to the tenth aspect, a communication device is provided. The communication device may be a network device, or a device, module, circuit, chip or similar located within a network device, or a device that can be used in conjunction with a network device. In the design, the communication device may include a module that has a one-to-one correspondence with the operation / stage / operation of the method described in any one of the fourth, fifth, sixth, or seventh aspects. The module may be a hardware circuit or software, or may be implemented by using a hardware circuit in combination with software. In the design, the communication device may include a processing module and a communication module.

[0140] The receiving module is configured to perform receiving operations in the manner described in any one of the fourth, fifth, sixth, or seventh embodiments. The processing module is configured to perform processing operations in the manner described in any one of the fourth, fifth, sixth, or seventh embodiments.

[0141] According to the eleventh aspect, a communication device is provided which includes a processor and a storage medium. The storage medium stores instructions. When an instruction is executed by the processor, a method according to the first aspect or one of the possible implementations of the first aspect is implemented; a method according to the second aspect or one of the possible implementations of the second aspect is implemented; a method according to the third aspect or one of the possible implementations of the third aspect is implemented; a method according to the fourth aspect or one of the possible implementations of the fourth aspect is implemented; a method according to the fifth aspect or one of the possible implementations of the fifth aspect is implemented; a method according to the sixth aspect or one of the possible implementations of the sixth aspect is implemented; a method according to the seventh aspect or one of the possible implementations of the seventh aspect is implemented; or a method according to the eighth aspect or one of the possible implementations of the eighth aspect is implemented.

[0142] According to the twelfth aspect, a communication device including a processor is provided. The processor is configured to process data and / or information to implement a method according to any one of the first aspect or a possible implementation of the first aspect, a method according to any one of the second aspect or a possible implementation of the second aspect, a method according to any one of the third aspect or a possible implementation of the third aspect, a method according to any one of the fourth aspect or a possible implementation of the fourth aspect, a method according to any one of the fifth aspect or a possible implementation of the fifth aspect, a method according to any one of the sixth aspect or a possible implementation of the sixth aspect, a method according to any one of the seventh aspect or a possible implementation of the seventh aspect, or a method according to any one of the eighth aspect or a possible implementation of the eighth aspect. Optionally, the communication device may further include a communication interface. The communication interface is configured to receive data and / or information and to transmit the received data and / or information to the processor. Optionally, the communication interface may be configured to output data and / or information to be processed by the processor.

[0143] According to the 13th aspect, a chip including a processor is provided. The processor is configured to execute a program or instructions to implement a method according to any one of the first aspect or a possible implementation of the first aspect, a method according to any one of the second aspect or a possible implementation of the second aspect, a method according to any one of the third aspect or a possible implementation of the third aspect, a method according to any one of the fourth aspect or a possible implementation of the fourth aspect, a method according to any one of the fifth aspect or a possible implementation of the fifth aspect, a method according to any one of the sixth aspect or a method according to any one of the seventh aspect or a method according to any one of the seventh aspect, or an eighth aspect or a method according to any one of the eighth aspect. Optionally, the chip may further include memory, which is configured to store a program or instructions. Optionally, the chip may further include a transceiver.

[0144] According to the 14th aspect, a computer-readable storage medium is provided. The computer-readable storage medium includes instructions. When an instruction is executed by a processor, a method according to any one of the first aspect or a possible implementation of the first aspect is implemented; a method according to any one of the second aspect or a possible implementation of the second aspect is implemented; a method according to any one of the third aspect or a possible implementation of the third aspect is implemented; a method according to any one of the fourth aspect or a possible implementation of the fourth aspect is implemented; a method according to any one of the fifth aspect or a possible implementation of the fifth aspect is implemented; a method according to any one of the sixth aspect or a possible implementation of the sixth aspect is implemented; a method according to any one of the seventh aspect or a possible implementation of the seventh aspect is implemented; or a method according to any one of the eighth aspect or a possible implementation of the eighth aspect is implemented.

[0145] According to the 15th 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, a method according to any one of the first aspect or a possible implementation of the first aspect is implemented; a method according to any one of the second aspect or a possible implementation of the second aspect is implemented; a method according to any one of the third aspect or a possible implementation of the third aspect is implemented; a method according to any one of the fourth aspect or a possible implementation of the fourth aspect is implemented; a method according to any one of the fifth aspect or a possible implementation of the fifth aspect is implemented; a method according to any one of the sixth aspect or a possible implementation of the sixth aspect is implemented; a method according to any one of the seventh aspect or a possible implementation of the seventh aspect is implemented; or a method according to any one of the eighth aspect or a possible implementation of the eighth aspect is implemented.

[0146] According to the 16th aspect, a communication system is provided. The communication system includes one or a combination of communication devices for performing any one of the first aspect or possible implementations of the first aspect, a communication device for performing any one of the second aspect or possible implementations of the second aspect, a communication device for performing any one of the third aspect or possible implementations of the third aspect, a communication device for performing any one of the fourth aspect or possible implementations of the fourth aspect, a communication device for performing any one of the fifth aspect or possible implementations of the fifth aspect, a communication device for performing any one of the sixth aspect or possible implementations of the sixth aspect, a communication device for performing any one of the seventh aspect or possible implementations of the seventh aspect, or a communication device for performing any one of the eighth aspect or possible implementations of the eighth aspect. [Brief explanation of the drawing]

[0147] [Figure 1] This is a diagram of possible application frameworks within a communication system.

[0148] [Figure 2]This is a diagram of another possible application framework within a communication system.

[0149] [Figure 3] This is a diagram of a communication system to which an embodiment of the present invention can be applied.

[0150] [Figure 4] This is a diagram of another communication system to which the embodiments of the present invention can be applied.

[0151] [Figure 5] This is a block diagram of an autoencoder.

[0152] [Figure 6] This is a diagram of an AI application framework.

[0153] [Figure 7] This is a schematic flowchart of a communication method according to one embodiment of the present invention.

[0154] [Figure 8] This is a diagram of codebook-based feedback according to one embodiment of the present invention.

[0155] [Figure 9] This is a schematic flowchart of another communication method according to one embodiment of the present invention.

[0156] [Figure 10] This is a schematic flowchart of yet another communication method according to one embodiment of the present invention.

[0157] [Figure 11] This is a schematic flowchart of yet another communication method according to one embodiment of the present invention.

[0158] [Figure 12] This is a diagram illustrating an application scenario according to one embodiment of the present invention.

[0159] [Figure 13] This is a diagram illustrating another application scenario according to one embodiment of the present invention.

[0160] [Figure 14] This is a block diagram of a communication device according to one embodiment of the present invention.

[0161] [Figure 15] This is a block diagram of another communication device according to one embodiment of the present invention. [Modes for carrying out the invention]

[0162] The technical solution of this application will be described below with reference to the attached drawings.

[0163] The technical solutions provided in this application may be applied to various communication systems, such as 5th generation (5G) or new radio (NR) systems, long-term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, satellite communication systems, future communication systems such as 6th generation (6G) mobile communication systems, or systems integrating multiple systems. The technical solutions provided in this application may further be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), Internet of Things (IoT) communication systems, or other communication systems.

[0164] Network elements within a communication system may transmit signals to or receive signals from other network elements. Signals may include information, signaling, data, or similar. Network elements may be replaced by entities, network entities, devices, communication devices, communication modules, nodes, communication nodes, or similar. In this disclosure, network elements are used as illustrative examples. For example, a communication system may include at least one terminal device and at least one network device. The network device may transmit downlink signals to the terminal device, and / or the terminal device may transmit uplink signals to the network device. The terminal device in this 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 network device may perform the corresponding communication methods in this disclosure.

[0165] In the embodiments of this application, the terminal device may also be referred to as user equipment (UE), access terminal, subscriber unit, subscriber station, mobile station, mobile console, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user equipment.

[0166] A terminal device may be a device that provides voice or data, such as a handheld device or in-vehicle device with wireless connectivity. Currently, some examples of terminals include mobile phones, tablet computers, notebook computers, palmtop computers, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, Session Initiation Protocol (SIP) phones, wireless local loop (WLL) stations, and personal digital assistants (PDIs). Examples include assistant, PDA®, handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in 5G networks, and terminal devices in future advanced public land mobile networks (PLMNs). This is not limited to the embodiments of the present application.

[0167] As an example, and not an limitation, in the embodiments of this application, the terminal device may alternatively be a wearable device. A wearable device may also be called a wearable intelligent device, and is a general term for wearable devices such as eyeglasses, gloves, watches, clothing, and shoes that are intelligently designed and developed for everyday wear by using wearable technology. A wearable device is a portable device that is worn directly on the user's body or integrated into clothing or accessories. A wearable device is not only a hardware device but also implements powerful functionality through software support, data exchange, and cloud interaction. In a broad sense, a wearable intelligent device includes full-featured, large devices that can implement all or part of their functionality without relying on a smartphone, such as a smartwatch or smart glasses, and devices that focus on only one type of application function and need to be used in conjunction with other devices, such as a smartphone, such as various smart bands or smart jewelry used to monitor physical signs.

[0168] In embodiments of the present application, the device for implementing the functions of a terminal device may be a terminal device, or a device capable of supporting the terminal device in the implementation of functions, such as a chip system, wherein the device may be mounted on or used in conjunction with the terminal device. In embodiments of the present application, the chip system may include a chip, or include a chip and other discrete components. The example in embodiments of the present application where the device for implementing the functions of a terminal device is a terminal device is used for illustrative purposes only and does not constitute a limitation on the solutions in embodiments of the present application.

[0169] In embodiments of the present application, the network device may be a device for communicating with terminal devices. The network device may also be referred to as an access network device or a wireless access network device. For example, the network device may be a base station. In embodiments of the present application, the network device may be a radio access network (RAN) node (or device) that connects terminal devices to a wireless network. A base station may broadly encompass any of the following names, or may be replaced by the following names: for example, NodeB (NodeB), evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmission reception point (TRP), transmission point (TP), primary station, secondary station, motor slide retainer (MSR) node, home base station, network controller, access node, radio node, access point (AP) node, transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), and positioning node. A 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, a base station may be a communication module, modem, or chip located within the aforementioned device or apparatus.A base station may alternatively be a mobile switching center, a device performing the functions of a base station in D2D, V2X, or M2M communications, a network-side device in a 6G network, a device performing the functions of a base station in a future communication system, or similar. A base station may support networks of the same or different access technologies. Optionally, a RAN node may alternatively be a server, a wearable device, a vehicle, an in-vehicle device, or similar. For example, an access network device in vehicle-to-everything (V2X) technology may be a roadside unit (RSU). Specific technologies and device configurations used for network devices are not limited to the embodiments of this application.

[0170] Base stations may be fixed or mobile. For example, a helicopter or unmanned aerial vehicle may be configured as a mobile base station, and one or more cells may move based on the location of the mobile base station. In another example, a helicopter or unmanned aerial vehicle may be configured as a device for communicating with another base station.

[0171] In some developments, the network device referred to in the embodiments of the present application may be a device including a CU or DU, or a device including a CU and a DU, or a device including a CU-control plane (central unit-control plane, CU-CP) node, a CU-user plane (central unit-user plane, CU-UP) node, and a DU node. For example, the network device may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0172] In some deployments, multiple RAN nodes work together to support terminals in implementing radio access, while different RAN nodes independently implement several functions of the base station. For example, RAN nodes may be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs may be located separately or included in the same network element, e.g., a BBU. RUs may be included in radio frequency devices or radio frequency units, e.g., RRUs, AAUs, or RRHs.

[0173] A RAN node may support one or more categories of fronthaul interfaces, where different fronthaul interfaces correspond to DUs and RUs with different functions. When the fronthaul interface between a DU and a RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. When the fronthaul interface between a DU and a RU is an enhanced common public radio interface (eCPRI), several downlink baseband functions and / or uplink baseband functions are moved from the DU to the RU for implementation, compared to the CPRI implementation. Different methods of dividing the DU and RU correspond to different categories (category, Cat) of eCPRI, e.g., eCPRI Cat A, B, C, D, E, and F.

[0174] eCPRI Cat A is used as an example. In downlink transmission, splitting is performed in layer mapping. The DU is configured to implement layer mapping, and one or more functions prior to layer mapping (specifically, one or more of encoding, rate matching, scrambling, modulation, and layer mapping), and other functions after layer mapping has been moved to the RU for implementation (e.g., one or more of RE mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition). In uplink transmission, splitting is performed in RE mapping demapping. The DU is configured to implement demapping, and one or more functions prior to demapping (specifically, one or more of the following functions: decoding, rate matching demapping, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and RE demapping), and other functions after demapping has been moved to the RU for implementation (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP rejection). For descriptions of the functions of DUs and RUs corresponding to various categories of eCPRI, it may be understood that one should refer to the eCPRI protocol. Details are not provided here.

[0175] In possible designs, the processing unit for implementing baseband functionality within the BBU is referred to as the baseband high (BBH) unit, and the processing unit for implementing baseband functionality within the RRU, AAU, or RRH is referred to as the baseband low (BBL) unit.

[0176] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have alternative names, but a person skilled in the art will be able to understand the meaning of these names. For example, in an ORAN system, CU may also be called O-CU (open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any one of CU (or CU-CP and CU-UP), DU, or 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.

[0177] In embodiments of the present application, the device for implementing the functions of a network device may be a network device, or a device capable of supporting the network device in the implementation of said functions, such as a chip system, hardware circuitry, software module, or a combination of hardware circuitry and software module, wherein the device may be mounted on a network device or used in conjunction with a network device. The example in embodiments of the present application where the device for implementing the functions of a network device is a network device is used for illustrative purposes only and does not constitute a limitation on the solutions in embodiments of the present application.

[0178] Network devices and / or terminal devices may be deployed on the ground, including indoor or outdoor scenarios and handheld or vehicle-mounted scenarios; or on water; or in the air on airplanes, balloons, and satellites. The scenarios in which network devices and terminal devices are deployed are not limited to the embodiments of this application. In addition, terminal devices and network devices may be hardware devices; or software functions running on dedicated hardware, or software functions running on general-purpose hardware, such as virtualized functions instantiated on a platform (e.g., a cloud platform); or entities including dedicated or general-purpose hardware devices and software functions. The specific forms of terminal devices and network devices are not limited in this application.

[0179] In wireless communication networks, for example, in mobile communication networks, the services supported by the network are becoming increasingly diverse, and therefore, the requirements that need to be met are also becoming increasingly diverse. For example, the network needs to be able to support ultra-high speed, ultra-low latency, and / or a large number of connections. These characteristics make network planning, network configuration, and / or resource scheduling increasingly complex. In addition, as networks have increasingly powerful capabilities, such as support for increasingly higher spectrums, and support for new technologies such as high-order multiple-input multiple-output (MIMO) technology, beamforming, and / or beam management, network energy saving has become a hot research topic. These new requirements, scenarios, and characteristics create unprecedented challenges in network planning, operation and maintenance, and efficient operation. To address these challenges, artificial intelligence technologies may be introduced into wireless communication networks to implement network intelligence.

[0180] To support AI technology within wireless networks, AI nodes may be further deployed into the network.

[0181] Optionally, an AI node may be deployed in one or more of the following locations within the communication system: access network devices, terminal devices, core network devices, or similar. Alternatively, an AI node may be deployed independently, for example, in a location other than one of the aforementioned devices, such as a host or cloud server in an over-the-top (OTT) system. An AI node may communicate with other devices within the communication system, which may be one or more of the following: network devices, terminal devices, network elements of the core network, or similar.

[0182] It should be understood that the number of AI nodes is not limited in this application. For example, if there are multiple AI nodes, they may be obtained through a function-based partitioning. For example, different AI nodes may perform different functions.

[0183] It can be further understood that an AI node may be an independent device, or may be integrated into the same device to implement different functions, or may be a network element within a hardware device, or may be a software function running on dedicated hardware, or may be a virtualized function instantiated on a platform (e.g., a cloud platform). The specific form of an AI node is not limited herein.

[0184] An AI node may be an AI network element or an AI module.

[0185] Figure 1 is a diagram of possible application frameworks within a communication system. As shown in Figure 1, network elements within the communication system are connected through interfaces (e.g., NG or Xn) or air interfaces. One or more AI modules (for clarity, only one AI module is shown in Figure 1) are deployed in one or more of these network element nodes, e.g., the following devices: core network devices, access network nodes (RAN nodes), terminals, or OAMs. An access network node may function as an independent RAN node or may include multiple RAN nodes, e.g., a CU and a DU. One or more AI modules may be deployed within a CU and / or a DU. Optionally, a CU may be further divided into a CU-CP and a CU-UP. One or more AI modules are deployed within a CU-CP and / or a CU-UP.

[0186] An AI module is configured to implement a corresponding AI function. AI modules deployed within different network elements may be the same or different. The models of AI modules are constructed based on different parameters, and AI modules may implement different functions. The models of AI modules may be constructed based on one or more of the following parameters: structural parameters (e.g., the number of layers in the neural network, the width of the neural network, the connectivity between layers, the weights of neurons, the activation function of neurons, or the bias of the activation function), input parameters (e.g., the type of input parameters and / or the dimensions of the input parameters), or output parameters (e.g., the type of output parameters and / or the dimensions of the output parameters). The bias of the activation function may also be referred to as the bias of the neural network.

[0187] A single AI module may have one or more models. A single model may obtain one output through inference, the output including one or more parameters. The learning, training, or inference processes of different models may be deployed on different nodes or devices, or on the same node or device.

[0188] Figure 2 is a diagram of possible application frameworks within a communication system. As shown in Figure 2, the communication system includes a RAN intelligent controller (RIC). For example, the RIC may be AI modules 117 and 118 shown in Figure 1, and is configured to implement AI-related functions. The RIC includes near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as delay-insensitive data. The delay of such data may be several seconds. Real-time RICs primarily process near-real-time information, such as delay-sensitive data. The delay of such data may be tens of milliseconds.

[0189] A quasi-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 quasi-real-time RIC may acquire network-side information and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information may be used as training data or inference data. Optionally, the quasi-real-time RIC may distribute inference results to RAN nodes and / or terminals. Optionally, CU and DU may exchange inference results, and / or DU and RU may exchange inference results. For example, the quasi-real-time RIC distributes inference results to the DU, and the DU transmits inference results to the RU.

[0190] 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 that model. Non-real-time RICs may acquire network-side information and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information may be used as training data or inference data, and the inference results may be distributed to RAN nodes and / or terminals. Optionally, CUs and DUs may exchange inference results, and / or DUs and RUs may exchange inference results. For example, a non-real-time RIC distributes inference results to a DU, and the DU sends inference results to an RU.

[0191] Quasi-real-time RICs and non-real-time RICs may, alternatively, be deployed independently as network elements. Optionally, quasi-real-time RICs and non-real-time RICs may, alternatively, function as part of another device. For example, a quasi-real-time RIC may be deployed on a RAN node (e.g., a CU or DU), while a non-real-time RIC may be deployed on an OAM, cloud server, core network device, or another network device.

[0192] Figure 3 is a diagram of a communication system to which a communication method according to one embodiment of the present invention may be applied. As shown in Figure 3, the communication system 100 may include at least one network device, for example, the network device 110 shown in Figure 3. The communication system 100 may further include at least one terminal device, for example, terminal devices 120 and 130 shown in Figure 3. The network device 110 may communicate with the terminal devices (for example, terminal devices 120 and 130) via a wireless link. The communication devices, for example, the network device 110 and terminal device 120 in the communication system, may communicate with each other using multi-antenna technology.

[0193] FIG. 4 is a diagram of another communication system to which the communication method according to an embodiment of the present application is applicable. Compared with the communication system 100 shown in FIG. 3, the communication system 200 shown in FIG. 4 further includes an AI network element 140. The AI network element 140 is configured to execute AI-related operations, for example, constructing a training data set or training an AI model.

[0194] In a possible implementation, the network device 110 may send data related to the training of the AI model to the AI network element 140, and the AI network element 140 constructs a training data set and trains the AI model. For example, the data related to the training of the AI model may include data reported by the terminal device. The AI network element 140 may send the results of the operations related to the AI model to the network device 110, and the network device 110 transfers the results of the operations related to the AI model to the terminal device. For example, the results of the operations related to the AI model may include at least one of a trained AI model, an evaluation result or a test result of the model, and the like. For example, a part of the trained AI model may be deployed on the network device 110, and another part may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 110. Alternatively, the trained AI model may be deployed on the terminal device.

[0195] In FIG. 4, it should be understood that the direct connection of the AI network element 140 to the network device 110 is merely used as an example for illustration purposes. In another scenario, the AI network element 140 may alternatively be connected to a 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 through a third-party network element. The connection relationship between the AI network element and another network element is not limited in the embodiments of the present application.

[0196] Alternatively, the AI network element 140 may be deployed as a module on the network device and / or the terminal device, for example, on the network device 110 or the terminal device shown in FIG. 3.

[0197] It should be noted that FIGS. 3 and 4 are merely schematic diagrams of examples for ease of understanding. For example, the communication system may further include another device, for example, a wireless relay device and / or a wireless backhaul device not shown in FIGS. 3 and 4. In actual application, the communication system may include a plurality of network devices and may also include a plurality of terminal devices. The number of network devices and terminal devices included in the communication system is not limited in the embodiments of the present application.

[0198] To facilitate understanding of the solution means in the embodiments of the present application, the terms that may be used in the embodiments of the present application will be described below.

[0199] (1) AI model

[0200] An AI model is an algorithm or computer program capable of implementing AI functionality. An AI model represents a mapping relationship between the model's inputs and outputs. The type of AI model may be a neural network, linear regression model, decision tree model, support vector machine (SVM), Bayesian network, Q-learning model, or another machine learning (ML) model.

[0201] (2) Bi-directional model

[0202] A bilateral model may also be called a bilateral model, collaborative model, dual model, or two-side model. A bilateral model is a model that includes multiple submodels. The multiple submodels included in the model must be consistent with each other. The multiple submodels may be deployed on different nodes.

[0203] Embodiments of the present invention relate to an encoder for compressing CSI and a decoder for decompressing the compressed CSI. The encoder and decoder are used in conjunction. It can be understood that the encoder and decoder are compatible AI models. One encoder may include one or more AI models, and a decoder compatible with the encoder may also include one or more AI models. The encoder and decoder used in conjunction include the same number of AI models, and there is a one-to-one correspondence between the AI ​​models included in the encoder and the AI ​​models included in the decoder.

[0204] In possible designs, the set of encoders and decoders used in conjunction may specifically be two parts of the same autoencoder (AE), as shown in Figure 5, for example. An AE model in which the encoder and decoder are deployed separately on different nodes is a typical bilateral model. The encoder and decoder in an AE model are usually jointly trained and used in conjunction. The encoder processes the input V to obtain the processed result z, and the decoder can decode the encoder's output z into a predicted output V'.

[0205] An autoencoder is an unsupervised learning neural network characterized by using input data as label data. Therefore, an autoencoder may also be understood as a self-supervised learning neural network. An autoencoder may be configured to compress and decompress data. For example, an encoder within an autoencoder may compress (encode) data A to obtain data B, and a decoder within an autoencoder may decompress (decode) data B to obtain data A through decompression. Alternatively, this may be understood as the decoder performing the inverse operation of the encoder.

[0206] For example, the AI ​​model in the embodiments of this application may include an encoder and a decoder. The encoder and decoder are used in conjunction with each other. It may be understood that the encoder and decoder are a mutually compatible AI model. The encoder and decoder may be deployed separately on terminal devices and network devices.

[0207] Alternatively, the AI ​​model in the embodiment of the present invention may be a one-sided model, and the AI ​​model may be deployed on a terminal device or a network device.

[0208] (3) Neural network (NN)

[0209] A neural network is a specific implementation of AI or machine learning. According to the universal approximation theorem, a neural network can theoretically approximate any continuous function, and as a result, it has the ability to learn any mapping.

[0210] A neural network may include neurons. Neurons are x s The unit of operation may use the intercept of 1 as input. A neural network is a network formed by connecting many individual neurons together. Specifically, the output of one neuron may be the input for another neuron. The input for each neuron may be connected to the local receptive field of the previous layer, thereby extracting the features of the local receptive field. The local receptive field may be a region containing several neurons.

[0211] For example, one type of AI model is a neural network. The AI ​​model in this disclosure may be a deep neural network (DNN). Based on the network construction mode, a DNN may include a feedforward neural network (FNN), a convolutional neural network (CNN), a recurrent neural network (RNN), and similar types.

[0212] (4) Training dataset and inference data

[0213] In the field of machine learning, ground truth is generally considered to be accurate or true data.

[0214] A training dataset is used to train an AI model. The training dataset may contain inputs for the AI ​​model, or it may contain inputs for the AI ​​model and the AI ​​model's target output. The training dataset may contain one or more training data points. The training data may contain training samples that are input to the AI ​​model, or it may contain the AI ​​model's target output. The target output may also be referred to as a label, sample label, or label sample. The label is ground truth.

[0215] In the field of communications, training datasets may include simulation data collected by a simulation platform, experimental data collected in experimental scenarios, or actual measurement data collected within an actual communications network. Because the geographical environment and channel conditions under which the data is generated differ, for example, indoor / outdoor environments, mobile speeds, frequency bands, or antenna configurations, the collected data may be classified as they are acquired. For example, data with the same channel propagation environment and the same antenna configuration may be classified into one type.

[0216] Model training is to essentially learn some features of the training data from the training data. During the training of an AI model (for example, a neural network model), it is expected that the output of the AI model will be as close as possible to the actually predicted value. Therefore, the predicted value of the current network can be well compared with the actually predicted target value. Next, the weight vector of each layer of the AI model is updated based on the difference between the predicted value and the target value. (Of course, before the first update, an initialization process is usually executed. Specifically, parameters are preconfigured for all layers of the AI model). For example, when the predicted value of the network is large, the weight vector is adjusted to lower the predicted value, and the adjustment is continuously executed until the AI model can obtain a value that is actually predicted or a value that is quite close to the actually predicted target value through prediction. Therefore, it is necessary to define in advance "how to obtain the difference between the predicted value and the target value through comparison". This is the loss function or objective function. The loss function and the objective function are important formulas for measuring the difference between the predicted value and the target value. The loss function is used as an example. A larger output value (loss) of the loss function indicates a larger difference. In this case, the training of the AI model is a process of minimizing the loss so that the value of the loss function is smaller than the threshold or the value of the loss function meets the target requirements. For example, the AI model is a neural network, and adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers of the neural network, the width of the neural network, the weight of the neuron, or the parameters in the activation function of the neuron.

[0217] Inference data is used as the input for the trained AI model and may be used for inference by the AI model. During model inference, the inference data is input into the AI model, and the corresponding output, that is, the inference result, is obtained.

[0218] (5) AI Model Design

[0219] AI model design primarily includes a data collection phase (e.g., collection of training data and / or inference data), a model training phase, and a model inference phase, and may further include an inference result application phase.

[0220] Figure 6 shows the AI ​​application framework.

[0221] In the data collection phase, a data source is used to provide training datasets 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 the mapping relationship between the model's inputs and outputs. Obtaining an AI model through learning using the model training node is equivalent to obtaining the mapping relationship between the model's inputs and outputs 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 inference results. This phase may be understood as follows: inference data is input to the AI ​​model, and an output is obtained through the AI ​​model, where the output is the inference result. The inference result may indicate configuration parameters used (executed) by actor objects, and / or actions performed by actor objects. The inference result is exposed in the inference result application phase. For example, the inference result may be planned in a unified manner by actor entities. For example, an actor entity may send its inference results to one or more actor objects (e.g., a network device or a terminal device) for execution. In another example, the actor entity may further feed back the model's performance to a data source to facilitate subsequent model updates and training.

[0222] It can be understood that the communication system may include network elements having artificial intelligence capabilities. The aforementioned phases relating to AI model design may be performed by one or more network elements having artificial intelligence capabilities. In a possible design, the AI ​​functionality (e.g., an AI module or AI entity) may be configured within an existing network element in the communication system to implement AI-related operations, e.g., AI model training and / or inference. For example, the existing network element may be a network device or a terminal device. Alternatively, in another possible design, a separate network element may be introduced into the communication system to perform AI-related operations, e.g., AI model training. The separate network element may be referred to as an AI network element, an AI node, etc. Such names are not limited to the embodiments of this application. For example, the AI ​​network element may be directly connected to a network device in the communication system, or indirectly connected to a network device through a third-party network element. Third-party network elements may be core network elements such as an authentication management function (AMF) network element, a user plane function (UPF) network element, operation administration and maintenance (OAM), a cloud server, or another network element. This is not limited to these. For example, an independent network element may be deployed on one or more of the following: the network device side, the terminal device side, or the core network side. Optionally, an independent network element may be deployed on a cloud server. For example, the AI ​​network element 140 is deployed in the communication system shown in Figure 4.

[0223] The training process for different models may be deployed on different devices or nodes, or on the same device or node. The inference process for different models may be deployed on different devices or nodes, or on the same device or node. For example, the model training phase is performed by a terminal device. The terminal device may train a mutually compatible encoder and decoder, and then send the decoder's model parameters to the network device. For example, the model training phase is performed by a network device. The network device may train a mutually compatible encoder and decoder, and then send the encoder's model parameters to the terminal device. For example, the model training phase is performed by independent AI network elements. The AI ​​network elements may train a mutually compatible encoder and decoder, and then send the encoder's model parameters to the terminal device and the decoder's model parameters to the network device. Next, the model inference phase corresponding to the encoder is performed on the terminal device, and the model inference phase corresponding to the decoder is performed on the network device.

[0224] Model parameters may include one or more of the following: structural parameters of the model (e.g., the number of layers in the model, and / or weights), input parameters of the model (e.g., input dimensions, or the number of input ports), or output parameters of the model (e.g., output dimensions, or the number of output ports). It can be understood that the input dimension may be the size of a single input data. For example, if the input data is a sequence, the input dimension corresponding to the sequence may indicate the length of the sequence. The number of input ports may be the number of input data. Similarly, the output dimension may be the size of a single output data. For example, if the output data is a sequence, the output dimension corresponding to the sequence may indicate the length of the sequence. The number of output ports may be the number of output data.

[0225] (6) Channel status information

[0226] In a communication system (e.g., an LTE or NR communication system), network devices need to determine configurations such as resources, MCS, and precoding used to schedule downlink data channels for terminal devices based on the CSI. The CSI is understood to be channel information, which may indicate channel characteristics or channel quality.

[0227] CSI measurement means that the receiving end obtains channel information based on a reference signal transmitted by the transmitting end, that is, it estimates channel information using a channel estimation method. For example, the reference signal may include one or more of the following: channel state information reference signal (CSI-RS), synchronization signal / physical broadcast channel block (SSB), sounding reference signal (SRS), demodulation reference signal (DMRS), or similar. CSI-RS, SSB, DMRS, and similar may be used to measure downlink CSI. SRS, DMRS, and similar may be used to measure uplink CSI.

[0228] An FDD communication scenario is used as an example. In an FDD communication scenario, the uplink channel and downlink channel are not inversely related; in other words, inverseness between the uplink channel and downlink channel cannot be guaranteed. Therefore, the network device typically sends a downlink reference signal to the terminal device, which then performs channel measurement 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 the protocol or configured by the network device, and feeds the CSI report back to the network device, which then obtains the downlink CSI.

[0229] For example, CSI may include at least one of the following: channel quality indicator (CQI), precoding matrix indicator (PMI), rank indicator (RI), CSI-RS resource indicator (CRI), layer indicator (LI), reference signal received power (RSRP), signal-to-interference plus noise ratio (SINR), or similar. The signal-to-interference plus noise ratio may also be referred to as the signal-to-interference-plus-noise ratio.

[0230] RI indicates the number of downlink transmission layers recommended by the terminal device. CQI indicates the modulation and coding schemes that can be supported under the current channel conditions, as determined by the terminal device. PMI indicates the precoding recommended by the terminal device. The number of precoding layers indicated by PMI corresponds to RI.

[0231] The RI, CQI, PMI, and similar values ​​shown in the CSI report are merely recommendations provided by the terminal device, and it should be understood that network devices may perform downlink transmissions based on some or all of the information shown in the CSI report. Alternatively, network devices may perform downlink transmissions without referring to the information shown in the CSI report.

[0232] AI technology is introduced into wireless communication networks to acquire an AI model-based CSI feedback mode. Terminal devices use the AI ​​model to compress and feed back CSI, and network devices use the AI ​​model to restore the compressed CSI. Sequences (e.g., bit sequences) are transmitted in AI-based CSI feedback, and the overhead is lower than that of conventional CSI feedback.

[0233] Figure 5 is used as an example. In Figure 5, the encoder may be a CSI generator, and the decoder may be a CSI reconfigurator. The encoder may be deployed on a terminal device, and the decoder may be deployed on a network device. The terminal device may generate CSI feedback information z based on CSI unprocessed information V by using the encoder. The terminal device reports a CSI report, which may include the CSI feedback information z. The network device may reconstruct the CSI information by using the decoder to obtain CSI restored information V'.

[0234] Raw CSI information V may be acquired by a terminal device through CSI measurement. For example, raw CSI information V may include the channel response of the downlink channel or the eigenvector matrix (matrix containing eigenvectors) of the downlink channel. The encoder processes the eigenvector matrix of the downlink channel to obtain CSI feedback information z. In other words, performing compression and / or quantization operations on the eigenmatrix based on a codebook in the relevant solution is replaced by the encoder processing the eigenmatrix to obtain CSI feedback information z. The terminal device reports the CSI feedback information z. The network device processes the CSI feedback information z using a decoder to obtain CSI restored information V'.

[0235] The following describes further examples of training and inference processes for AI models in embodiments of the present invention.

[0236] Training data for training an AI model includes training samples and sample labels. For example, training samples are channel information determined by the terminal device, and sample labels are the actual channel information, i.e., ground truth CSI. If the encoder and decoder belong to the same autoencoder, the training data may include only training samples; in other words, training samples are sample labels.

[0237] In the field of wireless communication, ground truth CSI can be a high-precision CSI.

[0238] The specific training process is as follows: The model training node processes channel information, i.e., training samples, using an encoder to obtain CSI feedback information; processes the feedback information using a decoder to obtain reconstructed channel information, i.e., reconstructed CSI information; then calculates the difference between the reconstructed CSI information and the corresponding sample labels, i.e., the value of the loss function; and updates the encoder and decoder parameters based on the value of the loss function to minimize the difference between the reconstructed channel information and the corresponding sample labels, i.e., minimize the loss function. For example, the loss function may be the mean square error (MSE) or cosine similarity. The above operation may be repeated to obtain an encoder and decoder that satisfy the target requirements. The model training node may be a terminal device, a network device, or another network element with AI functionality within a communication system.

[0239] The aforementioned example of using an AI model for CSI compression is for illustrative purposes only, and it should be understood that AI models may be used alternatively in other scenarios during CSI feedback. For example, an AI model may be used for CSI prediction, specifically for predicting channel information at one or more future points in time based on channel information measured at one or more historical points in time. The specific purposes of the AI ​​model in a CSI feedback scenario are not limited to the embodiments of this application.

[0240] (7) UCI

[0241] UCI is support information or signaling other than service load transmitted from a terminal device to a network device. UCI may be reported to the network device via a physical uplink control channel (PUCCH) or a physical uplink shared channel (PUSCH).

[0242] In the protocol, the content of the UCI includes at least one of the following: scheduling request, hybrid automatic repeat request acknowledgement (HARQ-ACK), CSI feedback information, configured grant (CG)-UCI, or similar. When the load is greater than 11 bits, polar coding is typically used for the UCI.

[0243] To illustrate the process of determining the UCI, an example is used below in which the content of the UCI is CSI feedback information.

[0244] CSI feedback information is represented by a CSI report. The CSI feedback information may be divided into two parts: Part 1 and Part 2. In other words, the CSI report may be divided into two parts. Each of the two parts may be used to generate two UCI bit sequences. The first UCI bit sequence corresponds to Part 1 and includes RI, CQI, the number of non-zero coefficients, and similar. The second UCI bit sequence corresponds to Part 2 and includes PMI.

[0245] Table 1 shows an exemplary mapping sequence for mapping part 1 of the CSI report to the UCI bit sequence. Table 2 shows an exemplary mapping sequence for mapping part 2 of the CSI report to the UCI bit sequence.

[0246] For example, as shown in Table 1, in the first UCI bit sequence, parts 1 of n CSI reports are sorted based on the sequence numbers of the n CSI reports. (1) This indicates the first bit of the first UCI bit sequence, a1 (1)represents the second bit of the first UCI bit sequence, and by analogy,

Number

number

[0247] In the scenario described above, CSI feedback is primarily used by network devices to perform precoding, beam management, scheduling, or other operations. In this scenario, high-precision CSI is typically not required. Therefore, the CSI actually fed back by terminal devices to network devices is usually significantly compressed and has low precision. In codebook-based CSI feedback mode, to improve CSI feedback precision, some codebooks with high feedback overhead, such as the type codebooks in release (R) 16 of the 3GPP® protocol and codebooks in releases later than R16, may be used. In this case, the CSI report is typically carried by PUSCH. In NR systems, polar coding is used for channel coding in UCI. 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 smaller than the maximum code length supported in the protocol for polar coding. The CSI report may be transmitted using UCI. However, in some scenarios, such as AI-based CSI feedback scenarios, network devices need to collect channel information with higher accuracy or precision.

[0248] For example, channel information may be used as training data for training an AI model. The training data for the AI ​​model may include training samples and / or sample labels. Channel information may be used as training samples and / or sample labels. Generally, higher accuracy or precision of channel information indicates better model training effectiveness. In the aforementioned mode, for example, when CSI is reported to a network device in R16 codebook-based feedback mode, the accuracy of the CSI acquired by the network device is low, and it is almost impossible to obtain a well-performing AI model through training using the CSI acquired as training data by the network device. In another example, channel information may be used as monitoring data for monitoring the performance of an AI model. Specifically, channel information may be used for comparison with the model's output to determine model performance. Higher accuracy or precision of channel information indicates higher accuracy in determining model performance. In the aforementioned modes, for example, in R16 codebook-based feedback mode, when CSI is reported to the network device, the accuracy of the CSI acquired by the network device is low, making it almost impossible to accurately evaluate model performance by using the CSI acquired by the network device as the basis for determining model performance.

[0249] High-precision channel information is typically greater than the CSI feedback in the current CSI feedback mode. Specifically, the higher overhead required to transmit high-precision channel information may exceed the limit of the maximum code length supported in the protocol for polar coding, and therefore, high-precision channel information cannot be fed back using UCI.

[0250] With this in mind, the present invention provides a communication method and a communication apparatus to enable network devices to acquire high-precision channel information and to facilitate subsequent data transmission between network devices and terminal devices. The communication method may be applied to the aforementioned communication systems, for example, FDD communication scenarios. In addition, optionally, the communication method may be applied to TDD communication scenarios, but is not limited to this disclosure.

[0251] In this application, it should be understood that such instructions include both direct (also called explicit) and implicit instructions. Directly indicating information A means including information A. Implicitly indicating information A means indicating information A by directly indicating information B and based on the correspondence between information A and information B. The correspondence between information A and information B may be predefined, pre-stored, pre-burned, or pre-configured.

[0252] In this application, it should be understood that the use of information C to determine information D includes cases where information D is determined solely on information C, and cases where information D is determined on information C and other information. In addition, the use of information C to determine information D may further include cases where it is determined indirectly. For example, information D is determined on information E, and information E is determined on information C.

[0253] In addition, in embodiments of the present application, "Network element A transmits information A to network element B" may be understood as network element B being the destination end of information A, or an intermediate network element in the transmission path between network element A and the destination end, and may include transmitting the information directly or indirectly to network element B; and "Network element B receives information A from network element A" may be understood as network element A being the source end of information A, or an intermediate network element in the transmission path between network element B and the source end, and may include receiving the information directly or indirectly from network element A. The information may undergo necessary processing, such as format changes between the source end and the destination end for transmitting the information. However, the destination end may understand valid information from the source end. Similar descriptions in the present application may be understood similarly and will not be described in detail here.

[0254] The solutions in the embodiments of this application may be applied to precoding, beam management, or other scenarios.

[0255] Figure 7 is a schematic flowchart of the communication method according to the present invention.

[0256] As shown in Figure 7, method 500 may include the following steps:

[0257] 510: The terminal device generates channel information #1 (an example of third channel information) based on a first feedback configuration, where the total length of channel information #1 is less than or equal to the maximum code length supported by UCI, and channel information #1 is ground truth channel information.

[0258] 520: The stage of transmitting UCI#1 (an example of the first UCI) to the network device, where UCI#1 corresponds to channel information #1.

[0259] In this embodiment of the present application, UCI is information used before encoding. A single UCI may be understood as a single UCI bit sequence used before encoding, specifically, a bit sequence in which channel coding is performed independently. The UCI may be transmitted after channel coding using uplink resources.

[0260] For example, the uplink resource may be PUCCH or PUSCH.

[0261] The fact that UCI#1 corresponds to channel information#1 indicates that channel information#1 is transmitted as an independent UCI. Specifically, the UCI contains the contents of channel information#1. Transmitting UCI#1 means transmitting channel information#1 using UCI#1. The total length of channel information#1 can be understood as the number of bits in channel information#1, i.e., the length of UCI#1.

[0262] In this embodiment of the present application, the generation of channel information by a terminal device may be understood as the terminal device generating a CSI report, and the CSI report indicating the channel information. Correspondingly, the transmission of channel information to a network device by a terminal device using UCI may be understood as the terminal device transmitting a CSI report indicating the channel information to a network device using UCI.

[0263] Ground truth channel information is high-precision channel information. The specific definition method may be determined by the network device or may be predefined.

[0264] Ground Truth Channel information can also be referred to as Ground Truth CSI.

[0265] For example, ground truth channel information may be channel information with an accuracy greater than or equal to threshold #1. This threshold may be specified by the network device or predefined.

[0266] In AI-based feedback mode, the ground truth CSI may be used as one or more of the following pieces of information in the AI ​​model: target CSI, label CSI, input CSI, or similar.

[0267] For example, ground-truth CSI may be used as training data during the training of an AI model. For example, ground-truth CSI may be used as training samples input to an AI model and / or as the target output of the AI ​​model. The target output may also be referred to as labels, sample labels, ground-truth, target, or the like.

[0268] For example, ground truth CSI may be used as the target output of an AI model during testing, specifically to measure the performance of the AI ​​model.

[0269] For example, ground truth CSI may be used as the target output of an AI model during performance monitoring of the AI ​​model; specifically, it may be used to measure the performance of the AI ​​model.

[0270] For example, the AI ​​model includes a CSI generator and a CSI reconfigurator. A terminal device may perform channel measurements based on a reference signal transmitted by a 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 a CSI reconfigurator to obtain restored CSI information. The terminal device may transmit channel information #1 obtained based on the raw CSI information to the network device. The network device may evaluate the accuracy of the restored CSI information #1 based on the restored CSI information and channel information #1 to evaluate the performance of the AI ​​model. The above description is merely an example and should not be considered a limitation on the solution in this embodiment of the present application.

[0271] Optionally, method 500 may further include steps 530 and 540 (not shown in the figure).

[0272] 530: The terminal device generates channel information #2 (an example of fourth channel information) based on a second feedback configuration, where channel information #2 is not ground truth channel information, and the accuracy of channel information #2 is lower than the accuracy of channel information #1.

[0273] 540: The terminal device transmits UCI#2 (an example of a second UCI) to the network device, where UCI#2 corresponds to channel information #2.

[0274] For example, channel information #2 may be compressed CSI reported in conventional mode (e.g., based on the R16 codebook). In another example, channel information #2 may be CSI feedback information reported in AI-based feedback mode.

[0275] In other words, if the channel information fed back by the terminal device is ground truth channel information, the first feedback configuration can generate high-precision channel information, and the total length of the channel information can be less than or equal to the maximum code length supported by UCI; or, if the channel information fed back by the terminal device is not ground truth channel information, the second feedback configuration can generate low-precision channel information, and accordingly, the feedback overhead of the channel information is lower than the feedback overhead of the channel information generated based on the first feedback configuration.

[0276] The fact that UCI#2 corresponds to channel information#2 indicates that channel information#2 is transmitted as an independent UCI. Specifically, the UCI contains the content of channel information#2. Transmitting UCI#2 means transmitting channel information#2 using UCI#2.

[0277] In the solution of this embodiment, when the channel information fed back by the terminal device is ground truth channel information, high-precision channel information can be generated by using the first feedback configuration, and the length of the channel information can be less than or equal to the maximum code length supported by UCI. In this way, both high-precision channel information and other low-precision channel information can be transmitted using UCI, and network devices can acquire high-precision channel information.

[0278] In this embodiment of the present application, channel information may also be referred to as CSI. CSI is information that represents the channel state.

[0279] For example, the type of channel information may be any one of the following: channel response, channel eigenvector matrix, precoding matrix, RSRP, SINR, or similar.

[0280] The channel response can also be called the channel matrix. The channel eigenvector matrix is ​​a matrix that contains the channel's eigenvectors.

[0281] The type of channel information may be predefined. Alternatively, the type of channel information may be configured by the network device.

[0282] The dimensions of channel information are related to the type of channel information.

[0283] For example, if the channel information is a spatial domain or frequency domain channel response, the channel information is N tx ×N rx It may be represented by a matrix having dimension ×F. tx This indicates the number of antenna ports on the network device, N tx N is a positive integer. rx This indicates the number of antenna ports on the terminal device, N rx F is a positive integer. F represents the bandwidth. The bandwidth may be expressed in terms of the number of bandwidth units, for example, the number of resource blocks (RBs) or the number of subbands. F is a positive integer.

[0284] For example, if the channel information is the eigenvector matrix of the channel, then the channel information is N tx ×N rank It may be represented by a matrix having dimension ×F. rank This indicates the number of ranks of the eigenvectors, the number of layers, or the number of streams. rank is a positive integer.

[0285] For the sake of clarity, the example in this embodiment of the present application where the channel information is the eigenvector matrix of the channel is used primarily for illustrative purposes and does not constitute a limitation on the solution in this embodiment of the present application.

[0286] The terminal device may generate channel information, such as channel information #1 or channel information #2, which is fed back to the network device, based on the initial channel information.

[0287] For example, the initial channel information may be unprocessed CSI acquired by the terminal device through measurement.

[0288] For example, the initial channel information may be CSI that has not undergone overhead adjustment. For example, the initial channel information may be CSI that has not been compressed and / or quantized.

[0289] Channel information #1 and channel information #2 can be understood as channel information that is actually fed back by the terminal device.

[0290] In step 510, the terminal device may report channel information #2 to the network device in multiple feedback modes. In other words, the terminal device may process the initial channel information in multiple feedback modes to generate channel information #2 that is fed back to the network device. The channel information feedback mode may also be referred to as the format in which the terminal device feeds back the channel information.

[0291] To illustrate the channel information feedback modes, feedback mode 1 and feedback mode 2 are used as examples below.

[0292] Feedback mode 1: Scalar quantization mode.

[0293] Reporting channel information in scalar quantization mode means performing scalar quantization on the channel information and feeding the quantized channel information back to the network device using a CSI report.

[0294] For example, scalar quantization is performed on the elements in the initial channel information, and the quantized data is fed back to the network device using a CSI report. The quantized data may be used as channel information #1. For example, the initial channel information is the channel eigenvector matrix, and the channel eigenvector matrix is ​​N tx ×N rank It is a matrix with dimension ×F. The scalar quantization is N tx ×N rank This process is performed on each element of a matrix with dimension ×F, and the results obtained through scalar quantization are sorted in a predetermined order to obtain channel information #1.

[0295] For example, the type of scalar quantization may include any one of the following: N-bit scalar quantization, float-16 quantization, float32 quantization, integer-8 quantization, or similar. N may be a positive integer. For example, N may be any integer between 1 and 8.

[0296] In a feedback mode based on scalar quantization, the feedback overhead may be controlled based on the quantization precision of the scalar quantization, or similar. For example, the feedback overhead can be reduced by using a lower quantization precision.

[0297] Feedback mode 2: Codebook-based quantization mode.

[0298] Reporting channel information in codebook-based quantization mode means processing the channel information based on the codebook and feeding the processed channel information back to the network device using CSI reports.

[0299] The codebook is a codebook for CSI feedback.

[0300] For example, the codebook may be a codebook defined in the NR protocol for CSI feedback. For example, the codebook may be any one of the following: the Type I codebook in R15 of the 3GPP® protocol, the Type II codebook in R15 of the 3GPP® protocol, the enhanced type (etype) II codebook in R16 of the 3GPP® protocol, the codebook in R17 of the 3GPP® protocol, the codebook in R18 of the 3GPP® protocol, or similar.

[0301] The above explanation is merely an example. In a different implementation, the codebook for CSI feedback may be a different codebook. For example, the codebook format defined in the protocol and the user-defined codebook parameters may be used in the codebook for CSI feedback. The user-defined codebook parameters are one or more user-defined codebook parameters. In another example, the user-defined codebook format and the user-defined codebook parameters may be used in the codebook for CSI feedback.

[0302] Figure 8 shows the feedback based on the etype II codebook in 3GPP protocol R16.

[0303] As shown in Figure 8, the main principle for reporting channel information based on the etype II codebook in R16 is to decompose the eigenvector matrix in each layer into three matrices that are multiplied together. The dimension of the eigenvector matrix in each layer is N tx ×N sb And here, N sb This indicates the number of subbands, N sbn is a positive integer. For ease of explanation, these three matrices are called the spatial basis matrix, the coefficient matrix, and the frequency domain matrix. The dimension of the spatial basis matrix is ​​N tx ×N tx The dimension of the coefficient matrix is ​​N tx ×N sb The dimension of the frequency domain basis matrix is ​​N sb ×N sb Therefore, since the coefficient matrix contains many coefficients with small values, dimensionality reduction may be performed on the spatial domain basis matrix, the coefficient matrix, and the frequency domain matrix. For example, spatial domain basis column vectors corresponding to large coefficients in the coefficient matrix are preserved in the spatial domain basis matrix, and frequency domain basis column vectors corresponding to large coefficients in the coefficient matrix are preserved in the frequency domain basis matrix. For example, 2L spatial domain basis column vectors are selected from the spatial domain basis matrix, and R frequency domain basis row vectors are selected from the frequency domain basis matrix, and 2L × R coefficients in the coefficient matrix are determined corresponding to the 2L spatial domain basis column vectors and R frequency domain basis row vectors. P non-zero coefficients are selected from the 2L × R coefficients, where P is a positive integer less than or equal to 2L × R. Scalar quantization is performed on each of the P non-zero coefficients, where L is a positive integer and R is a positive integer.

[0304] The spatial domain basis matrices and frequency domain basis matrices are defined by the codebook. The spatial domain basis matrices and frequency domain basis matrices may be discrete Fourier transform (DFT) matrices, or matrices obtained by transforming DFT matrices. The terminal device may use a CSI report to feed back the selected spatial domain basis column vectors, selected frequency domain basis row vectors, selected non-zero coefficients, and the values ​​of the non-zero coefficients. The spatial domain basis column vectors may also be called spatial domain basis vectors. The frequency domain basis row vectors may also be called frequency domain basis vectors. The terminal device only needs to notify the network device of specific selected spatial domain basis vectors, specific selected frequency domain basis vectors, specific selected non-zero coefficients, and the values ​​of the non-zero coefficients, and as a result, the network device can obtain channel information.

[0305] In the feedback mode based on the etype II codebook in R16, the content that is fed back by the terminal device is i 1,1 ,i 1,2 ,i 1,5 ,i 1,6,l ,i 1,7,l ,i 1,8,l ,i 2,3,l ,i 2,4,l ,i 2,5,l This includes, where l is the layer identifier, and the value of l is 1, 2, ..., or N rank i 1,1 This indicates spatial domain basis selection information, i 1,2 This indicates oversampling selection information, i 1,8,l This indicates the coefficient with the maximum value among the non-zero coefficients in each layer, i 2,3,l This indicates the reference amplitude information, i 1,5 This indicates common frequency domain basis selection information, i 1,6,l This shows the frequency domain basis selection information for each layer, i 2,4,l This shows the amplitude information of each coefficient in each layer, i 2,5,l This shows the phase information of each coefficient in each layer, i 1,7,l This shows the non-zero coefficient selection information for each layer.

[0306] i 1,1 and i 1,2 indicate a specific selected spatial domain basis. i 1,5 and i 1,6,l indicate a specific selected frequency domain basis in each layer. i 1,1 , i 1,2 , i 1,5 and i 1,6,l may be collectively referred to as basis selection information. i 1,7,l is an identifier of non-zero coefficients selected in the l-th layer. Specifically, i 1,7,l may indicate a specific non-zero coefficient selected in each layer. i 1,8,l may indicate a coefficient having the maximum value among non-zero coefficients in each layer. i 2,3,l , i 2,4,l and i 2,5,l may indicate the value of each non-zero coefficient. i 1,7,l and i 1,8,l may be collectively referred to as coefficient selection information. i 2,3,l , i 2,4,l and i 2,5,l may be collectively referred to as coefficient value information. The values of L, P, and R may be determined by the codebook parameters of the etype II codebook in R16.

[0307] For example, the initial channel information is the channel's eigenvector matrix. For example, the initial channel information is processed based on the codebook, and the eigenvector matrix in each layer is decomposed into three matrices that are multiplied together. 2L spatial basis vectors are selected from the spatial basis matrix, and R frequency domain basis vectors are selected from the frequency domain basis matrix, determining 2L × R coefficients in the coefficient matrix corresponding to the 2L spatial basis vectors and R frequency domain basis vectors. P non-zero coefficients are selected from the 2L × 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 basis vectors, selected frequency domain basis vectors, selected non-zero coefficients, and the values ​​of the non-zero coefficients is channel information #1, specifically the channel information that is actually fed back by the terminal device. The terminal device notifies the network device of the selected spatial basis vectors, selected frequency domain basis vectors, selected non-zero coefficients, and the values ​​of the non-zero coefficients, and as a result, the network device can obtain channel information #1.

[0308] As described above, in the solution of this embodiment of the present application, the codebook format defined in the protocol and the codebook parameters defined by the user may be used in the codebook. For example, the codebook format defined by the etype II codebook in R16 and the codebook parameters defined by the user, such as the values ​​L, P, and R, may be used in the codebook of this embodiment of the present application.

[0309] In a feedback mode based on codebook-based quantization, feedback overhead may be controlled by adjusting the number of selected bases, the number of non-zero coefficients, the non-zero coefficient quantization precision, or similar factors. For example, feedback overhead can be reduced by using one or more of the following: fewer bases, fewer non-zero coefficients, lower non-zero coefficient quantization precision, or similar factors.

[0310] The feedback mode used by the terminal device may be predefined, or the feedback mode used by the terminal device may be configured by the network device. For example, whether feedback mode 1 or feedback mode 2 is used by the terminal device may be predefined, or configured by the network device.

[0311] The feedback overhead of channel information may be adjusted in multiple ways. In other words, the channel information actually fed back by the terminal device may be adjusted in multiple ways.

[0312] Methods 1 through 4 are used below as examples to explain how to adjust the feedback overhead of channel information. For example, the feedback overhead of channel information may be adjusted using one or more of methods 1 through 4.

[0313] Method 1: Adjust the bandwidth dimension of channel information #1.

[0314] The smaller bandwidth dimension of channel information #1 indicates lower feedback overhead for channel information #1.

[0315] In Method 1, the bandwidth dimension of channel information #1 is smaller than the bandwidth dimension of the initial channel information. Specifically, the feedback overhead is reduced by reducing the bandwidth dimension of the channel information that is actually fed back to the network device.

[0316] For example, a portion of the subbands may be selected from multiple subbands in the initial channel information and fed back to the network device. The number of subbands in channel information #1 is a portion of the number of subbands.

[0317] The number of subbands in channel information #1 is smaller than the number of subbands in the initial channel information.

[0318] For example, the number of sub-bands of the initial channel information is N sb and N sb1 sub-bands are selected from N sb sub-bands and fed back to the network device. The number of sub-bands of channel information #1 is N sb1 where N sb1 is a positive integer smaller than N sb .

[0319] Thus, the feedback overhead can be controlled by the number of sub-bands selected from the initial channel information. The feedback overhead of the channel information may be reduced by reducing the number of sub-bands of the channel information actually fed back to the network device.

[0320] For example, the sub-band granularity of the channel information may be increased. The sub-band granularity of channel information #1 is the increased sub-band granularity of the channel information.

[0321] In this case, the sub-band granularity of channel information #1 is larger than the sub-band granularity of the initial channel information.

[0322] The larger sub-band granularity of channel information #1 indicates fewer sub-bands of channel information #1 and lower overhead for transmitting channel information #1, that is, lower feedback overhead.

[0323] For example, the sub-band granularity may be represented by the number of resource blocks of the sub-band.

[0324] For example, the sub-band granularity of the initial channel information is 4 RBs, the number of sub-bands is the positive integer closest to N rb / 4, and the bandwidth of the initial channel information is N rb / 4 RBs, where N rb / 4 is a positive integer. The raised subband granularity is 6 RBs. In other words, the subband granularity of channel information #1 is 6 RBs. The number of subbands in channel information #1 is N rb It is the closest positive integer to / 6.

[0325] Thus, feedback overhead can be controlled by the subband granularity of channel information #1. By increasing the subband granularity, the number of subbands of channel information fed back to the network device can be reduced, thereby reducing feedback overhead.

[0326] Method 2: Adjust the number of layers in channel information #1.

[0327] For example, a portion of the layers may be selected from multiple layers of the initial channel information and fed back to the network device. The number of layers in channel information #1 is the number of a portion of the layers. In this case, the number of layers in channel information #1 is smaller than the number of layers in the initial channel information.

[0328] For example, the initial channel information has two layers, and one layer is selected from these two layers and fed back to the network device. The channel information #1 has one layer.

[0329] Fewer layers of channel information #1 indicate lower feedback overhead for channel information #1.

[0330] Thus, the feedback overhead can be controlled by the number of layers of channel information #1. The feedback overhead of channel information may be reduced by reducing the number of layers of channel information that are actually fed back to the network device.

[0331] Method 3: Adjust the quantization precision of scalar quantization.

[0332] Optionally, step 510 may include a step of generating channel information #1 by performing scalar quantization on the initial channel information based on a first feedback configuration.

[0333] In other words, channel information is reported in scalar quantization mode.

[0334] For example, the data in the initial channel information is in float16 format, and each data point in the initial channel information is converted to int8 format in scalar quantization mode. The data in channel information #1 is in int8 format.

[0335] Channel information #1 is obtained through scalar quantization. The lower quantization precision of scalar quantization results in lower feedback overhead for channel information #1.

[0336] Thus, feedback overhead can be controlled by the quantization precision of scalar quantization. The feedback overhead of channel information may be reduced by reducing the quantization precision of scalar quantization.

[0337] Methods 1 and 3 may be used in combination. Specifically, the number of subbands in channel information #1 is smaller than the number of subbands in the initial channel information, and channel information #1 is obtained through scalar quantization.

[0338] For example, step 510 may include a step of performing scalar quantization on channel information #1-1 to generate channel information #1, where channel information #1-1 is part of several subbands of the initial channel information.

[0339] To obtain channel information #1-1, a portion of the subband is selected from multiple subbands of the initial channel information, and scalar quantization is performed on each element in channel information #1-1, where the quantized channel information #1-1 is channel information #1.

[0340] For example, step 510 may include the steps of performing scalar quantization on the initial channel information to obtain channel information #1-2; and selecting a portion of subbands from a plurality of subbands of channel information #1-2 to generate channel information #1, where the portion of subbands selected from channel information #1-2 is channel information #1.

[0341] Thus, the feedback overhead can be controlled by the number of subbands selected from the initial channel information (i.e., the number of subbands in channel information #1) and the precision of the scalar quantization.

[0342] For example, step 510 may include a step of increasing the subband granularity of the initial channel information to obtain channel information #1-3, and a step of performing scalar quantization on each element in channel information #1-3 to generate channel information #1.

[0343] Thus, feedback overhead can be controlled by the subband granularity and scalar quantization accuracy of channel information #1.

[0344] For example, step 510 may include steps of increasing the subband granularity of the initial channel information to obtain channel information #1-3; selecting a portion of subbands from multiple subbands 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.

[0345] Thus, feedback overhead can be controlled by the number of subbands selected from the initial channel information, the subband granularity of channel information #1, and the precision of scalar quantization.

[0346] The above description is merely an example, and it should be understood that Method 1 and Method 3 may be combined in other ways. This is not limited to the present embodiment of the application.

[0347] Methods 2 and 3 may be used in combination. Specifically, the number of layers for channel information #1 is smaller than the number of layers for initial channel information, and channel information #1 is obtained through scalar quantization.

[0348] For example, step 510 may include a step of performing scalar quantization on channel information #1-5 to generate channel information #1, where channel information #1-5 are parts of multiple layers of initial channel information.

[0349] To obtain channel information #1-5, a portion of the layers is selected from multiple layers of initial channel information, and scalar quantization is performed on each element within channel information #1-5, where the quantized channel information #1-5 is channel information #1.

[0350] Thus, the feedback overhead can be controlled by the number of layers of channel information #1 and the precision of scalar quantization.

[0351] The above description is merely an example, and it should be understood that methods 2 and 3 may be combined in other ways. This is not limited to the present embodiment of the application.

[0352] Method 4: Adjust the related configurations for codebook-based quantization.

[0353] Optionally, step 510 may include a step of processing initial channel information based on a first feedback configuration and codebook to generate channel information #1.

[0354] In other words, channel information is reported in codebook-based mode. For a specific explanation, please refer to Feedback Mode 2 mentioned above. Further details will not be explained here.

[0355] Channel information #1 is obtained through codebook-based quantization. During codebook-based quantization, channel information #1 is represented by selected basis and selected non-zero coefficients. Fewer selected bases indicate lower precision of channel information #1 and lower overhead for transmitting channel information #1. Fewer selected non-zero coefficients indicate lower precision of channel information #1 and lower overhead for transmitting channel information #1. Lower non-zero coefficient quantization precision indicates lower precision of channel information #1 and lower overhead for transmitting channel information #1.

[0356] Thus, feedback overhead can be controlled by the number of selected bases, the number of selected non-zero coefficients, and the non-zero coefficient quantization precision. The feedback overhead of channel information may be reduced by reducing the number of selected bases, the number of selected non-zero coefficients, or the non-zero coefficient quantization precision.

[0357] Methods 1 and 4 may be used in combination. Specifically, the number of subbands in channel information #1 is smaller than the number of subbands in the initial channel information, and channel information #1 is obtained through codebook-based quantization.

[0358] For example, step 510 may include a step of performing codebook-based quantization on channel information #1-6 to obtain channel information #1, where channel information #1-6 are parts of multiple subbands of the initial channel information.

[0359] To obtain channel information #1-6, a portion of the subbands is selected from multiple subbands of the initial channel information, and codebook-based quantization is performed on channel information #1-6, where the processed channel information is channel information #1.

[0360] Thus, feedback overhead can be controlled by the number of subbands selected from the initial channel information, the number of selected bases, the number of selected non-zero coefficients, and the non-zero coefficient quantization precision.

[0361] For example, step 510 may include the steps of increasing the subband granularity of the initial channel information to obtain channel information #1-7, and performing codebook-based quantization on channel information #1-7, where the processed channel information is channel information #1.

[0362] Thus, the feedback overhead can be controlled by the subband granularity of channel information #1, the number of selected bases, the number of selected non-zero coefficients, and the non-zero coefficient quantization precision.

[0363] The above description is merely an example, and it should be understood that methods 1 and 4 may be combined in other ways. This is not limited to the present embodiment of the application.

[0364] Methods 2 and 4 may be used in combination. Specifically, the number of layers for channel information #1 is smaller than the number of layers for initial channel information, and channel information #1 is obtained through codebook-based quantization.

[0365] For example, step 510 may include a step of performing codebook-based quantization on channel information #1-8 to generate a CSI report, where channel information #1-8 is part of multiple layers of initial channel information.

[0366] To obtain channel information #1-8, a portion of the layers is selected from multiple layers of initial channel information, and codebook-based quantization is performed on channel information #1-8, where the processed channel information is channel information #1.

[0367] Thus, the feedback overhead can be controlled by the number of layers of channel information #1, the number of selected bases, the number of selected non-zero coefficients, and the non-zero coefficient quantization precision.

[0368] The above description is merely an example, and it should be understood that methods 2 and 4 may be combined in other ways. This is not limited to the present embodiment of the application.

[0369] The feedback overhead for channel information is based on the feedback configuration. The feedback overhead for channel information #1 is based on the first feedback configuration. The feedback overhead for channel information #2 is based on the second feedback configuration.

[0370] The first feedback structure is different from the second feedback structure.

[0371] The components of the first feedback configuration may be the same as or different from the components of the second feedback configuration.

[0372] The feedback overhead of channel information #1 may be adjusted by adjusting the parameter values ​​of one or more components of the first feedback configuration.

[0373] For example, the components of the first feedback configuration may include one or more of the following: a subband configuration of channel information #1, a layer configuration of channel information #1, a quantization accuracy configuration in a feedback mode based on scalar quantization, a base configuration in a feedback mode based on codebook-based quantization, a non-zero coefficient configuration in a feedback mode based on codebook-based quantization, or similar.

[0374] For example, the subband configuration of channel information #1 may represent one or more of the following: the number of subbands of channel information #1, the subbands of channel information #1, the subband granularity of channel information #1, or similar.

[0375] In other words, the subband configuration of channel information #1 may indicate one or more of the following: the number of subbands in the initial channel information that are actually fed back to the network device, a specific subband in the initial channel information that is actually fed back to the network device, the subband granularity of the channel information that is actually fed back to the network device, or the same.

[0376] For example, the layer configuration of channel information #1 may indicate one or more of the following: the number of layers of channel information #1, the identifiers of the layers of channel information #1, or similar identifiers.

[0377] In other words, the layer configuration of channel information #1 may indicate one or more of the following: the 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 so on.

[0378] If channel information #1 is obtained through scalar quantization, the quantization precision configuration in the feedback mode based on scalar quantization may indicate the quantization precision used for scalar quantization.

[0379] If channel information #1 is obtained through codebook-based quantization, the basis construct in the feedback mode based on codebook-based quantization is the associated construct for representing the basis of channel information #1, i.e., the associated construct of the selected basis.

[0380] For example, the basis configuration in a codebook-based quantization feedback mode may represent one or more of the following: the number of bases selected in the codebook-based quantization feedback mode, the bases selected in the codebook-based quantization feedback mode, or similar. The basis may include spatial domain bases and frequency domain bases.

[0381] In other words, the basis configuration in a feedback mode based on codebook-based quantization may represent one or more of the number of bases selected during codebook-based quantization, specific selected bases, and similar elements.

[0382] If channel information #1 is obtained through codebook-based quantization, the non-zero coefficient configuration in the feedback mode based on codebook-based quantization is the associated configuration for representing the non-zero coefficients of channel information #1, i.e., the associated configuration of the selected non-zero coefficients.

[0383] For example, a non-zero coefficient configuration in a codebook-based quantization feedback mode may represent one or more of the following: the number of non-zero coefficients selected in the codebook-based quantization feedback mode, the non-zero coefficients selected in the codebook-based quantization feedback mode, the non-zero coefficient quantization precision selected in the codebook-based quantization feedback mode, or similar.

[0384] In other words, a non-zero coefficient configuration in a feedback mode based on codebook-based quantization may represent one or more of the following: the number of non-zero coefficients selected during codebook-based quantization, specific selected non-zero coefficients, the quantization precision used to quantize the non-zero coefficients, and so on.

[0385] The first feedback configuration may be predefined, configured by a network device, or determined by a terminal device.

[0386] Below, we will explain the method for determining the first feedback configuration based on Examples 1 to 3.

[0387] Example 1

[0388] In Example 1, all parameter values ​​within 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.

[0389] For example, one or more of the following may be predefined or configured by a network device: the number of subbands in channel information #1, the identifiers of the subbands in channel information #1, the subband granularity in channel information #1, the number of layers in channel information #1, the identifiers of the layers in channel information #1, the quantization precision in the feedback mode based on scalar quantization, the number of bases selected in the feedback mode based on codebook-based quantization, the identifiers of the bases in the feedback mode based on codebook-based quantization, the number of non-zero coefficients in the feedback mode based on codebook-based quantization, the identifiers of the non-zero coefficients in the feedback mode based on codebook-based quantization, the non-zero coefficient quantization precision in the feedback mode based on codebook-based quantization, or similar.

[0390] For example, all parameter values ​​within the first feedback configuration are predefined.

[0391] Alternatively, all parameter values ​​within the first feedback configuration are configured by the network device.

[0392] Alternatively, some of the parameter values ​​in the first feedback configuration are predefined, while other parts of the parameter values ​​are configured by the network device.

[0393] Optionally, prior to step 510, step 500 may further include a step in which a terminal device receives instruction information #1 transmitted by a network device, where instruction information #1 indicates some or all of the parameter values ​​in a first feedback configuration.

[0394] Example 2

[0395] In Example 1, the parameter values ​​of some components within the first feedback configuration are predefined or configured by the network device, while the parameter values ​​of other components are determined by the terminal device. The terminal device may report channel information based on the first feedback configuration.

[0396] In possible implementations, the size range of channel information #1 is predetermined or determined by the network device. The terminal device may determine the specific size of channel information #1 within that range. The size range of channel information #1 is the range of feedback overhead.

[0397] Below, we provide examples for explanation related to Examples 2-1 to 2-3.

[0398] Example 2-1

[0399] Some or all of the components within the first feedback configuration are configured or predefined by the network device. The terminal device may determine some or all of the parameter values ​​of the components within the range of some or all of the components.

[0400] For example, the entire range of the configuration items within the first feedback configuration may be configured or predefined by the network device, and the terminal device may determine all parameter values ​​of the configuration items within the range of the configuration items.

[0401] In this case, the size range of channel information #1 is predetermined or determined by the network device. The terminal device may determine the specific size of channel information #1 within that range.

[0402] In another example, the range of a portion of a component in the first feedback configuration is configured or predefined by the network device, and the parameter values ​​of other portions of the component are determined or predefined by the network device. The terminal device may determine some of the parameter values ​​of the component within a certain range of the component.

[0403] In this case, the size range of channel information #1 is predetermined or determined by the network device. The terminal device may determine the specific size of channel information #1 within that range.

[0404] Optionally, method 500 may further include the step of a terminal device determining a parameter value of a first component in a first feedback configuration based on the range of the first component.

[0405] The terminal device determines the parameter values ​​of the first component based on the range of the first component.

[0406] The term "first" within the first component merely indicates that the scope of the component is indicated or predefined by the network device, and does not constitute any other limitation. In other words, among the components in the first feedback configuration, components whose scope is indicated or predefined by the network device may be referred to as the first component.

[0407] The first component may include some or all of the components within the first feedback configuration.

[0408] For example, the first component may include one or more of the following: a subband configuration of channel information #1, a layer configuration of channel information #1, a quantization accuracy configuration in a feedback mode based on scalar quantization, a base configuration in a feedback mode based on codebook-based quantization, a non-zero coefficient configuration in a feedback mode based on codebook-based quantization, or similar.

[0409] A terminal device may notify a network device of parameter values ​​determined by the terminal device.

[0410] Optionally, method 500 may further include the step of a terminal device transmitting instruction information #2 (an example of 11th instruction information) to a network device, where instruction information #2 indicates parameter values ​​for some or all of the configuration items. For example, some or all of the configuration items may include the first configuration item.

[0411] For example, instruction information #2 may indicate one or more of the following: a subband of channel information #1, a layer of channel information #1, quantization precision in a feedback mode based on scalar quantization, a basis in a feedback mode based on codebook-based quantization, a non-zero coefficient selected in a feedback mode based on codebook-based quantization, a non-zero coefficient quantization precision selected in a feedback mode based on codebook-based quantization, or similar.

[0412] In other words, instruction information #2 may indicate one or more of the following: a specific selected subband, a specific selected layer, the quantization precision of a scalar quantization, a specific selected basis, a specific selected non-zero coefficient, the non-zero coefficient quantization precision, or similar.

[0413] The scope of the first component may consist of network devices or may be predefined.

[0414] Optionally, prior to step 510, step 500 may further include a step in which a terminal device receives instruction information #3 (an example of ninth instruction information) transmitted by a network device, where instruction information #3 indicates the scope of the first component.

[0415] The scope of the first component will be explained below in relation to the example.

[0416] The first component may include the subband configuration of channel information #1.

[0417] The range of subband configuration of channel information #1 may include at least one of the following: the range of the number of subbands of channel information #1, the set of subband combinations of channel information #1, or the range of subband granularity of channel information #1.

[0418] The range of values ​​for the number of subbands may be a continuous or discontinuous range. The terminal device may determine a specific value from this range, specifically, it may determine a selected number of subbands and then determine a specific subband to be selected. Instruction information #2 may indicate the subband selected by the terminal device.

[0419] For example, the range of values ​​for the number of subbands in channel information #1 may be as follows: The number of subbands in channel information #1 is greater than or equal to 1 and less than or equal to 3. In this case, the number of subbands 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 subband from multiple subbands of the initial channel information for feedback.

[0420] In another example, the value range for the number of subbands in channel information #1 may be {2, 4}. In this case, the number of subbands selected by the terminal device from the initial channel information may be 2 or 4. For example, the terminal device selects 4 subbands from the multiple subbands of the initial channel information for feedback.

[0421] The elements in the set of subband combinations in channel information #1 may be subband combinations that can be selected by the terminal device. The terminal device may determine a specific element from the set, specifically, a specific subband combination to be used. Indication information #2 may indicate the subband selected by the terminal device.

[0422] The combination may include the same or different number of subbands.

[0423] For example, a subband combination may be represented by a combination of subband numbers.

[0424] For example, the set of subband combinations for channel information #1 may be {(1,3),(1,4)}. In this case, the subbands selected by the terminal device from the initial channel information may be the subband numbered 1 and the subband numbered 4, or the subband numbered 1 and the subband numbered 3. For example, the terminal device selects the subband numbered 1 and the subband numbered 4 from the initial channel information and feeds these subbands back to the network device.

[0425] The subband granularity range may be a continuous or discontinuous range. The terminal device may determine a specific value from this range, specifically, it may determine a selected subband granularity. Indication information #2 may indicate the subband granularity.

[0426] For example, the range of values ​​for the subband granularity of channel information #1 may be as follows: The subband granularity of channel information #1 is greater than or equal to 5 RBs. In this case, the terminal device may determine that the subband granularity of channel information #1 is greater than or equal to 5 RBs. For example, the terminal device may determine that the subband granularity of channel information #1 is 6 RBs.

[0427] In another example, the subband granularity range for channel information #1 may be {4, 6}. In this case, the terminal device may determine that the subband granularity of channel information #1 is 4 or 6. For example, the terminal device may determine that the subband granularity of channel information #1 is 6 RBs.

[0428] Please understand that the scope described above is merely an example and does not constitute a limitation on the solution provided in this embodiment of the present application.

[0429] The first component may include the layered structure of channel information #1.

[0430] The range of the layer configuration of channel information #1 may include at least one of the value range of the number of layers in channel information #1 or the set of layer combinations of channel information #1.

[0431] The range of values ​​for the number of layers may be a continuous or discontinuous range. The terminal device may determine a specific value from this range, specifically by determining a selected number of layers, and then by determining a specific layer to be selected. Instruction information #2 may indicate the layer selected by the terminal device.

[0432] For example, the range of values ​​for the number of layers in channel information #1 may be as follows: The number of layers in channel information #1 is greater than or equal 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 multiple layers of the initial channel information for feedback.

[0433] In another example, the range of the number of layers in channel information #1 may be {1, 3}. In this case, the number of layers selected by the terminal device from the initial channel information may be 1 or 3. For example, the terminal device selects one layer from multiple layers of the initial channel information for feedback.

[0434] The elements in the set of layer combinations in channel information #1 may be layer combinations that can be selected by the terminal device. The terminal device may decide on a specific element from the set, specifically, a specific layer combination to be used. Instruction information #2 may indicate the layer to be selected by the terminal device.

[0435] The combination may include the same or different number of layers.

[0436] For example, a layer combination may be represented by a combination of layer numbers.

[0437] For example, the set of layer combinations for channel information #1 may be {(1,2),(1,3)}. In this case, the layers selected by the terminal device from the initial channel information may be the layer numbered 1 and the layer numbered 2, or the layer numbered 1 and the layer numbered 3. For example, the terminal device selects the layer numbered 1 and the layer numbered 2 from the initial channel information and feeds these layers back to the network device.

[0438] Please understand that the scope described above is merely an example and does not constitute a limitation on the solution provided in this embodiment of the present application.

[0439] The first component may include a quantization accuracy configuration in a feedback mode based on scalar quantization.

[0440] The range of the quantization accuracy configuration in the feedback mode based on scalar quantization may be the range of values ​​for the quantization accuracy in the feedback mode based on scalar quantization.

[0441] The terminal device may determine a specific value from the given range, specifically, it may determine the quantization precision to be used. Instruction information #2 may indicate the quantization precision used by the terminal device in a feedback mode based on scalar quantization.

[0442] For example, the range of quantization precision values ​​may be represented by a set of scalar quantization types.

[0443] For example, the range of quantization precision in a feedback mode based on scalar quantization may be {int8, float16}. In this case, the terminal device may determine that the elements in channel information #1 are in either int8 or float16 format. For example, the terminal device converts the elements in the initial channel information to int8 format.

[0444] Please understand that the scope described above is merely an example and does not constitute a limitation on the solution provided in this embodiment of the present application.

[0445] The first component may include a base configuration in a feedback mode based on codebook-based quantization.

[0446] The range of base configurations in the codebook-based quantization feedback mode may include at least one of the range of values ​​of the number of bases selected in the codebook-based quantization feedback mode or the set of base combinations in the codebook-based quantization feedback mode.

[0447] The range of values ​​for the base number in a feedback mode based on codebook-based quantization may be a continuous or discontinuous range. The terminal device may determine a specific value from this range, specifically, by determining the base of the selected number and then by determining a specific basis to be selected. Instruction information #2 may indicate the basis selected by the terminal device.

[0448] For example, the range of values ​​for the number of bases selected in a feedback mode based on codebook-based quantization may be expressed by the range of values ​​for the number of selected spatial domain bases and the range of values ​​for the number of selected frequency domain bases.

[0449] For example, the range of values ​​for the number of bases selected in a feedback mode based on codebook-based quantization may include the number of selected spatial domain bases being greater than or equal to 5 and less than or equal to 10, and the number of selected frequency domain bases being greater than or equal to 5 and less than or equal to 10. For example, a terminal device selects six spatial domain bases and eight frequency domain bases from the spatial domain bases defined in the codebook.

[0450] In another example, the range of values ​​for the number of bases selected in a feedback mode based on codebook-based quantization may include a range of values ​​for the number of selected spatial domain bases being {6, 8, 10} and a range of values ​​for the number of selected frequency domain bases being {6, 8, 10}. For example, a terminal device selects six spatial domain bases and eight frequency domain bases from the spatial domain bases defined in the codebook.

[0451] For example, the range of values ​​for the number of bases selected in a feedback mode based on codebook-based quantization may be represented by a set of combinations of the number of selected spatial domain bases and the number of selected frequency domain bases.

[0452] For example, the range of values ​​for the number of bases selected in a feedback mode based on codebook-based quantization may include {(6,8),(8,6),(6,10)}. In each combination, the first item may be the number of selected spatial domain bases, and the second item may be the number of selected frequency domain bases. The first combination is six spatial domain bases and eight frequency domain bases, and so on. For example, a terminal device selects the first combination from the spatial domain bases defined in the codebook, specifically six spatial domain bases and eight frequency domain bases.

[0453] In a feedback mode based on codebook-based quantization, the elements in the set of basis combinations selected may be basis combinations that can be selected by the terminal device. The terminal device may determine a specific element from the set, specifically, a specific basis combination to be used. Indicator information #2 may indicate a basis selected by the terminal device. For example, indicator information #2 may indicate a combination number. In another example, indicator information #2 may indicate a basis number.

[0454] The combinations may include the same or different numbers of bases.

[0455] For example, the selected basis combination may be represented by a combination of base indices.

[0456] For example, the selected set of basis combinations may include a selected set of spatial domain basis combinations and a selected set of frequency domain basis combinations.

[0457] For example, the set of spatial domain basis combinations may be {(1,2,3),(1,3,4)}, and the set of frequency domain basis combinations may be {(2,3,4),(1,2,4)}. The terminal device selects the first element from the set of spatial domain basis combinations and the second element from the set of frequency domain basis combinations. Specifically, the terminal device selects the spatial domain basis numbered 1, the spatial domain basis numbered 2, the spatial domain basis numbered 3, the frequency domain basis numbered 1, the frequency domain basis numbered 2, and the frequency domain basis numbered 4.

[0458] For example, the selected set of basis combinations may include sets of combinations of spatial domain bases and frequency domain bases.

[0459] For example, the set of basis combinations may be {[(1,2,3),(2,3,4)],[(1,3,4),(1,2,4)]}. The first item within each element is a spatial domain basis combination, and the second item within each element is a frequency domain basis combination. The terminal device selects the first element from the set. Specifically, the terminal device selects the spatial domain basis numbered 1, the spatial domain basis numbered 2, the spatial domain basis numbered 3, the frequency domain basis numbered 2, the frequency domain basis numbered 3, and the frequency domain basis numbered 4.

[0460] Please understand that the scope described above is merely an example and does not constitute a limitation on the solution provided in this embodiment of the present application.

[0461] The first component may include a non-zero coefficient configuration in a feedback mode based on codebook-based quantization.

[0462] The range of non-zero coefficient configurations in the codebook-based quantization feedback mode may include at least one of the following: a range of values ​​for the number of non-zero coefficients selected in the codebook-based quantization feedback mode, or a range of values ​​for the non-zero coefficient quantization precision selected in the codebook-based quantization feedback mode.

[0463] The range of values ​​for the number of non-zero coefficients selected in the feedback mode based on codebook-based quantization may be a continuous or discontinuous range. The terminal device may determine a specific value from this range, specifically by determining the number of non-zero coefficients selected and then determining a specific non-zero coefficient to be selected. Instruction information #2 may indicate the non-zero coefficient selected by the terminal device.

[0464] For example, the range of values ​​for the number of non-zero coefficients selected in a feedback mode based on codebook-based quantization may include a number of non-zero coefficients greater than or equal to 5 and less than or equal to 10. For example, a terminal device selects six non-zero coefficients from coefficients corresponding to selected frequency-domain and spatial-domain basis sets.

[0465] In another example, the range of values ​​for the number of non-zero coefficients selected in a feedback mode based on codebook-based quantization may include a range of {6, 8, 10} for the number of non-zero coefficients. For example, a terminal device selects six non-zero coefficients from coefficients corresponding to selected frequency-domain and spatial-domain bases.

[0466] The first component may include a non-zero coefficient quantization precision selected in a feedback mode based on codebook-based quantization.

[0467] The range of non-zero coefficient quantization precision selected in the feedback mode based on codebook-based quantization may be the range of values ​​for the non-zero coefficient quantization precision selected in the feedback mode based on codebook-based quantization.

[0468] The terminal device may determine a specific value from the given range, specifically, it may determine the quantization precision to be used. Instruction information #2 may indicate the non-zero coefficient quantization precision used by the terminal device in a feedback mode based on codebook-based quantization.

[0469] For example, the range of quantization precision values ​​may be represented by a set of scalar quantization types.

[0470] For example, the range of non-zero coefficient quantization precision in a feedback mode based on codebook-based quantization may be {int8, float16}. In this case, the terminal device may decide to convert the non-zero coefficients to either int8 or float16 format.

[0471] Please understand that the scope described above is merely an example and does not constitute a limitation on the solution provided in this embodiment of the present application.

[0472] Example 2-2

[0473] The correspondence between some or all parameter values ​​of the components in the first feedback configuration may be predefined or determined by the network device. The terminal device may determine specific values ​​for some of the parameters in the first feedback configuration and determine specific values ​​for corresponding parameters based on the correspondence between some or all of the parameter values ​​of the components.

[0474] For example, the correspondence between all the parameter values ​​of the components in the first feedback configuration may be predefined or determined by the network device. The terminal device may determine specific values ​​for some of the parameters in the first feedback configuration and then determine specific values ​​for the corresponding parameters based on the correspondence between all the components.

[0475] In this case, the size range of channel information #1 is predetermined or determined by the network device. The terminal device may determine the specific size of channel information #1 within that range.

[0476] Optionally, method 500 may include a step in which a terminal device determines the parameter values ​​of a plurality of components in a first feedback configuration based on the correspondence between the parameter values ​​of the plurality of components.

[0477] Specifically, the parameter values ​​of the second component in the first feedback configuration are based on the correspondence between the parameter values ​​of the third component in the first feedback configuration and the parameter values ​​of multiple components in the first feedback configuration, and the third and second components belong to multiple components.

[0478] The terminal device may determine the parameter values ​​of the second component based on the parameter values ​​of the third component and the corresponding relationships.

[0479] For example, the parameter value of the third component may be determined by the terminal device.

[0480] Specifically, the terminal device determines the parameter values ​​of multiple components, for example, a portion of the parameter values ​​of a third component; and, based on the portion of the parameter values ​​and the correspondence between the parameter values ​​and the multiple components, determines the corresponding parameter value, for example, the parameter value of a second component.

[0481] For example, multiple components may include at least two of the following: a subband configuration of channel information #1, a layer configuration of channel information #1, a quantization accuracy configuration in a feedback mode based on scalar quantization, a base configuration in a feedback mode based on codebook-based quantization, a non-zero coefficient configuration in a feedback mode based on codebook-based quantization, or similar.

[0482] A terminal device may notify a network device of parameter values ​​determined by the terminal device.

[0483] Optionally, method 500 may further include the step of a terminal device transmitting instruction information #2 to a network device, where instruction information #2 indicates parameter values ​​for some or all of the configuration items. For example, some or all of the configuration items may include multiple configuration items.

[0484] The correspondence between parameter values ​​of multiple configuration items may be predefined or configured by the network device.

[0485] Optionally, prior to step 510, step 500 may further include a step in which a terminal device receives instruction information #4 (an example of a 10th instruction information) transmitted by a network device, where instruction information #4 indicates the correspondence between parameter values ​​of multiple configuration items.

[0486] Table 3 shows an exemplary correspondence between the parameter values ​​of the layer configuration and the parameter values ​​of the subband configuration. Specifically, Table 3 shows an exemplary correspondence between the number of layers, the number of ports, and the number of subbands of channel information #1. The number of ports may be comprised of network devices. Table 3 [Table 3]

[0487] For example, a terminal device may determine the number of layers in channel information #1 and, based on the number of layers and the correspondence shown in Table 3, determine the number of subbands in channel information #1. For example, the number of ports configured by the network device is 16; the terminal device determines that the number of layers in channel information #1 is 1 and, based on the correspondence shown in Table 3, determines that the number of subbands in channel information #1 is 16.

[0488] Alternatively, the terminal device may determine the number of subbands in channel information #1 and, based on the number of subbands and the correspondence shown in Table 3, determine the number of layers in channel information #1. For example, the number of ports configured by the network device is 32; the terminal device determines that the number of subbands in channel information #1 is 8 and, based on the correspondence shown in Table 3, determines that the number of layers in channel information #1 is 1.

[0489] Table 3 is merely an example and should not be considered a limitation on the solution in this embodiment of the Application. For example, multiple components may be alternatively other components. For example, in this embodiment of the Application, the correspondence between the parameter values ​​of multiple components may be alternatively the correspondence between the parameter values ​​of a different number of components. For example, the correspondence between the parameter values ​​of multiple components may be the correspondence between the number of layers of channel information #1, the number of subbands of channel information #1, and the quantization accuracy in the feedback mode based on scalar quantization. In another example, the correspondence between the parameter values ​​of multiple components may be the correspondence between the number of layers of channel information #1, the number of non-zero coefficients selected in the feedback mode based on codebook-based quantization, and the non-zero coefficient quantization accuracy selected in the feedback mode based on codebook-based quantization. In yet another example, the correspondence between the parameter values ​​of multiple components may include the number of layers of channel information #1 and the correspondence between the layer combinations of channel information #1.

[0490] For example, instruction information #2 may indicate a correspondence between parameter values ​​of multiple components that is used by the terminal device. For example, the correspondence number may be predefined, or the correspondence number may be configured by the network device. Instruction information #2 may include the correspondence number used by the terminal device. The network device may determine the parameter value used by the terminal device based on the correspondence number used by the terminal device. Table 3 is used as an example. The number of ports configured by the network device is 16. The terminal device determines that the number of layers fed back to the network device is 1, and determines that the number of subbands fed back to the network device is 16 based on correspondence 1 shown in Table 3. The terminal device transmits the number of the first correspondence in Table 3, i.e., number 1, to the network device to notify the network device that the terminal device is using correspondence 1. The numbering scheme in Table 3 is merely an example and does not constitute a limitation on the solution in this embodiment of the present application.

[0491] For an explanation of instruction information #2, please refer to Example 2-1. Further details will not be explained here.

[0492] Examples 2-1 and 2-2 may be used interchangeably or in combination. For example, the third component may be the first component, and the parameter value of the third component may be determined based on the range of the third component. See Example 2-1 for a detailed explanation.

[0493] Example 2-3

[0494] The precision range of channel information #1 is configured or predefined by the network device. The terminal device may determine some or all of the parameter values ​​of the components in the first feedback configuration within the precision range of channel information #1.

[0495] In this case, the size range of channel information #1 is predetermined or determined by the network device. The terminal device may determine the specific size of channel information #1 within that range.

[0496] Optionally, method 500 may further include a step in which the terminal device determines the parameter values ​​of some or all of the components in the first feedback configuration based on threshold #1 (an example of a fourth threshold). The precision of channel information #1 is greater than or equal to threshold #1.

[0497] A terminal device may notify a network device of parameter values ​​determined by the terminal device.

[0498] Optionally, method 500 may further include the step of a terminal device transmitting instruction information #2 to a network device, wherein instruction information #2 indicates parameter values ​​for some or all of the configuration items.

[0499] For an explanation of instruction information #2, please refer to Example 2-1. Further details will not be explained here.

[0500] Optionally, prior to step 510, step 500 may further include a step in which a terminal device receives instruction information #5 (an example of eighth instruction information) transmitted by a network device, where instruction information #5 indicates the precision range of channel information #1, for example, threshold #1.

[0501] The accuracy of channel information may be indicated by the correlation or error between the channel information and the reference channel information of the channel information.

[0502] The reference channel information for channel information may be the initial channel information corresponding to the channel information, specifically, the channel information acquired by the terminal device through measurement.

[0503] A higher correlation between channel information and the reference channel information of the channel information indicates higher accuracy of the channel information.

[0504] A smaller error between channel information and the reference information for channel information indicates higher accuracy of the channel information.

[0505] For example, the accuracy of channel information #1 may be represented by the correlation between channel information #1 and the initial channel information.

[0506] For example, the accuracy of channel information #1 may be the generalized cosine similarity (GCS) or the squared generalized cosine similarity (SGCS) between channel information #1 and the initial channel information.

[0507] SGCS is used as an example. For instance, threshold #1 is 0.9, and the precision range of channel information #1 is SGCS ≥ 0.9. The terminal device may determine a first feedback configuration based on the actual status of channel information #1, such as the overhead of channel information #1, the importance of each part of the initial channel information, and the similarity between different parts of the initial channel information, to allow the SGCS between channel information #1 and the initial channel information to be greater than or equal to 0.9.

[0508] For example, the accuracy of channel information #1 may be expressed by the error between channel information #1 and the initial channel information.

[0509] For example, the accuracy of channel information #1 may be expressed by the normalized mean square error (NMSE) between channel information #1 and the initial channel information.

[0510] The precision of channel information #1 may alternatively be expressed by the error between channel information #1 and the initial channel information. The precision range of channel information #1 may be as follows: the error between channel information #1 and the initial channel information is less than or equal to threshold #2. In this case, indicator information #5 may alternatively indicate threshold #2.

[0511] If a feedback configuration is pre-configured, for example, if a network device indicates feedback configuration #1, the terminal device may further decide whether to adjust feedback configuration #1. The terminal device may further send instruction information to the network device to notify the network device whether the terminal device has adjusted feedback configuration #1. If feedback configuration #1 has been adjusted, the instruction information may indicate the adjusted feedback configuration #1, i.e., the first feedback configuration.

[0512] For example, a terminal device may decide whether to adjust feedback configuration #1 based on the overhead of channel information #1 within feedback configuration #1. If the overhead of channel information #1 within feedback configuration #1 exceeds the maximum code length supported by UCI, feedback configuration #1 is adjusted within the precision range of channel information #1 so that the overhead of channel information #1 falls within the code length range supported by UCI. If the overhead of channel information #1 within feedback configuration #1 is within the code length range supported by UCI, feedback configuration #1 may be used as a first feedback configuration.

[0513] The multiple implementations in Example 2 may be used independently or in combination.

[0514] For example, Examples 2-1 and 2-2 are combined. The correspondence between some parameter values ​​of the components in the first feedback configuration is configured or predefined by the network device, and the range of several components in the first feedback configuration other than some of the components is configured or predefined by the network device.

[0515] For example, Examples 2-1 and 2-3 are combined. Some ranges of the components within the first feedback configuration are configured or predefined by the network device, and the precision range of channel information #1 is configured or predefined by the network device.

[0516] For example, Examples 2-2 and 2-3 are combined. The correspondence between some parameter values ​​of the components in the first feedback configuration is configured or predefined by the network device, and the precision range of channel information #1 is configured or predefined by the network device.

[0517] For example, Examples 2-1, 2-2, and 2-3 are combined. The correspondence between some parameter values ​​of the components in the first feedback configuration is configured or predefined by the network device, the range of several components in the first feedback configuration other than some of the components is configured or predefined by the network device, and the precision range of channel information #1 is configured or predefined by the network device.

[0518] Example 3

[0519] The terminal device determines a first feedback configuration and then reports channel information based on the first feedback configuration.

[0520] In Example 3, the terminal device has complete freedom. For example, the terminal device may decide to adjust the feedback overhead in one or more of the aforementioned methods 1 to 4 based on the actual status of channel information #1, e.g., the overhead of channel information #1, the importance of each part of the initial channel information, and the similarity between different parts of the initial channel information; in other words, the terminal device may decide on a first feedback configuration.

[0521] Optionally, method 500 may further include the step of a terminal device transmitting instruction information #2 to a network device, wherein instruction information #2 indicates parameter values ​​for some or all of the components in the first feedback configuration.

[0522] If a feedback configuration is pre-configured, for example, if a network device indicates feedback configuration #1, the terminal device may further decide whether to adjust feedback configuration #1. The terminal device may further send instruction information to the network device to notify the network device whether the terminal device has adjusted feedback configuration #1. If feedback configuration #1 has been adjusted, the instruction information may indicate the adjusted feedback configuration #1, i.e., the first feedback configuration.

[0523] For example, a terminal device may decide whether to adjust feedback configuration #1 based on the overhead of channel information #1 within feedback configuration #1. If the overhead of channel information #1 within feedback configuration #1 exceeds the maximum code length supported by UCI, feedback configuration #1 is adjusted so that the overhead of channel information #1 falls within the code length range supported by UCI. If the overhead of channel information #1 within feedback configuration #1 is within the code length range supported by UCI, feedback configuration #1 may be used as a first feedback configuration.

[0524] In this embodiment of the present application, channel information #1 may be transmitted using one UCI.

[0525] In the solution of this embodiment of the present application, the first feedback configuration enables the feedback overhead of channel information to be included within the code length range supported by UCI, thereby ensuring 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, which helps ensure that the network device can obtain high-precision channel information by using UCI.

[0526] Figure 9 is a schematic flowchart of another communication method according to one embodiment of the present invention.

[0527] As shown in Figure 9, Method 700 may include the following steps:

[0528] 710: The terminal device generates channel information #3 (an example of the first channel information), where channel information #3 contains K segments, and K is an integer greater than 1. The type of channel information #3 is ground truth channel information. The length of each segment is less than or equal to threshold #3 (an example of the first threshold). Channel information #3 is one of the following: channel response, channel eigenvector matrix, precoding matrix, RSRP, or SINR.

[0529] 720: The terminal device transmits some or all of K UCIs to the network device, where each of the K UCIs corresponds to one of K segments.

[0530] In this embodiment of the present application, UCI is information used before encoding. A single UCI may be understood as a single UCI bit sequence used before encoding, specifically, a bit sequence in which channel coding is performed independently. After channel coding has been performed separately for K UCIs, the K encoded UCIs may be transmitted using uplink resources.

[0531] For example, the uplink resource may be PUCCH or PUSCH.

[0532] The fact that K UCIs each correspond to K segments indicates that each segment is transmitted as an independent UCI, or in other words, that each UCI contains the content of one segment. Channel coding may be performed separately for the K segments. Transmitting K UCIs means transmitting K segments using K UCIs. The length of the K segments may be understood as the number of bits in the K segments, specifically the number of bits in the K UCIs corresponding to the K segments.

[0533] For example, Channel information #3 may be part 2 in the CSI report.

[0534] For example, threshold #3 is related to the maximum code length supported by UCI. In other words, threshold #3 is determined based on the maximum code length supported by UCI.

[0535] The maximum code length supported by UCI is the maximum code length supported by UCI without channel coding.

[0536] Optionally, threshold #3 is less than or equal to the maximum code length supported by UCI.

[0537] For example, threshold #3 may be predefined or configured by a network device.

[0538] Optionally, a network device may receive instruction information #10 (an example of first instruction information) transmitted by the network device, where instruction information #10 indicates threshold #3.

[0539] In the solution of this embodiment of the present application, ground truth channel information is divided into multiple segments and transmitted using multiple UCIs, and as a result, the network device can acquire channel information with high feedback overhead, i.e., high-precision channel information.

[0540] Ground truth channel information has high accuracy and, consequently, high feedback overhead. This feedback overhead may exceed the maximum code length supported by UCI. In the solution of this embodiment, the length of each segment may be less than the maximum code length supported by UCI, and as a result, segments can be transmitted using multiple UCIs.

[0541] For example, channel information #3 may be obtained by performing scalar quantization on the initial channel information.

[0542] For example, channel information #3 may be obtained by performing codebook-based quantization on the initial channel information.

[0543] For specific feedback modes, please refer to the explanation in Method 500. Further details will not be provided here. Alternatively, channel information #3 may be acquired using a different feedback mode.

[0544] The K segments of channel information #3 can also be referred to as the K parts of channel information #3. Specifically, channel information #3 is divided into K parts.

[0545] The lengths of the K segments may be the same or different. Specifically, the K UCIs may contain the same or different numbers of bits.

[0546] The following describes a method for dividing into K segments, relating to Examples 71 to 73.

[0547] Example 71

[0548] The K segments may be arbitrarily determined based on the contents of the K segments.

[0549] Specifically, the terminal device may segment channel information #3 based on the specific information contained in each segment.

[0550] For example, the contents of each of the K segments may be predefined or configured by network devices.

[0551] In possible implementations, channel information #3 may be obtained by performing scalar quantization on the initial channel information.

[0552] Optionally, the dimension of channel information #3 obtained through scalar quantization is the same as the dimension of channel information that has not undergone scalar quantization.

[0553] For example, channel information #3 is F × N tx It may be a 2D matrix with the following dimensions: F represents the bandwidth. tx This indicates the number of antenna ports on the network device.

[0554] For example, channel information #3 is F × N tx ×N rank It may be a 3-dimensional matrix having the dimension N. rank This indicates the rank number of the eigenvector.

[0555] For example, channel information #3 is F × N tx ×N rx It may be a 3-dimensional matrix having the dimension N. rx This indicates the number of antenna ports on the terminal device.

[0556] The content of each of the K segments may be an element in the matrix mentioned above. The terminal device may segment channel information #3 based on a specific element contained in each segment.

[0557] For example, the content of each segment may be indicated by the dimensional range corresponding to that segment. The dimensional range corresponding to that segment is the range of the content contained in that segment in each dimension. The content of each segment lies within the dimensional range corresponding to that segment.

[0558] The dimensional range corresponding to each segment may be predefined or may be constructed by a network.

[0559] For example, the dimensional range may be continuous or discontinuous.

[0560] The following shows that channel information #3 is F×N tx ×N rank This is a 3-dimensional matrix with the following dimensions, and is an example for explanation purposes. To make the explanation easier, in the following example, an example in which the index of the dimension of channel information #3 is a consecutive index will be used for explanation.

[0561] For example, the dimensional range corresponding to segment m among K segments is x m From the second subband (x m+1 -1) The first subband, y of the network device m (y m+1 -1) Antenna port or z m From the second stream (z m+1It may include at least one of the (-1)th streams. m , x m+1 -1, y m , y m+1 -1, z m and z m+1 -1 is a positive integer. m This indicates the minimum value of the subband index within segment m, and y m This indicates the minimum value of the antenna port index of network devices within segment m, and z m This indicates the minimum value of the stream index within segment m.

[0562] For example, the dimensional range corresponding to segment m among K segments is x m From the second subband (x m+1 -1) The first subband, y of the network device m (y m+1 -1) Antenna port and z m From the second stream (z m+1 It may include the -1)th stream. Segment m is [x m ,x m+1 -1] Subband index within [y m ,y m+1 -1] Antenna port index of network devices and [z m ,z m+1 Includes elements in channel information #3 that correspond to the stream index in -1].

[0563] In another example, the dimensional range corresponding to segment m among K segments is x m x starting from the second subband m 'Individual subbands, network devices y m The network device y starting from the second antenna port m 'Individual antenna ports or z m Starting from the second stream, z m It may include at least one of the streams. m', y m 'and z m ' is a positive integer.

[0564] The above description is merely an exemplary way of representing a continuous range. Dimensional ranges may be represented in alternative ways, and this is not limited to the present embodiment of the application. For example, a dimensional range corresponding to segment m may include at least one of a set of subbands, a set of antenna ports of a network device, or a set of streams. The elements within the set may be discontinuous.

[0565] Alternatively, the content of each of the K segments may be determined by the terminal device.

[0566] For example, with respect to channel information #3 obtained through scalar quantization, the terminal device may determine the dimensional range corresponding to each segment.

[0567] In this case, the terminal device may notify the network device of the dimensional range corresponding to each segment.

[0568] Furthermore, the order of elements within a segment may be predefined or configured by the network device. The order of elements within a segment is the same as the order of elements in the corresponding UCI.

[0569] For example, in a given segment, the elements within channel information #3 belonging to that segment are sorted in the following order: ascending order of frequency domain index, ascending order of network device antenna port index, and ascending order of stream index.

[0570] For example, for an element within segment m, the frequency domain index is x m x m+1 -1, and the antenna port index of the network device is y m from y m+1 -1, and the stream index is z m from zm+1 The value is -1. The elements within segment m may be represented as follows after being sorted in ascending order of frequency domain index, ascending order of network device antenna port index, and ascending order of stream index. (x m ,y m ,z m ),(x m +1, y m ,z m ),...,(x m+1 -1, y m ,z m ),(x m ,y m +1, z m ),(x m +1, y m +1, z m ),...,(x m+1 -1, y m +1, z m ),(x m ,y m +2, z m ),(x m +1, y m +2, z m ),...,(x m+1 -1, y m +2, z m ),...,(x m+1 -1, y m+1 -1,z m ),(x m ,y m ,z m +1),(x m +1, y m ,z m +1),...,(x m+1 -1, y m ,z m +1),(x m ,y m +1, z m +1),(x m +1, y m +1, z m +1),...,(x m+1 -1, y m +1, z m +1),(x m ,y m +2, zm +1),(x m +1, y m +2, z m +1),...,(x m+1 -1, y m +2, z m +1),...,(x m+1 -1, y m+1 -1,z m +1),...,(x m+1 -1, y m+1 -1,z m+1 -1)

[0571] In another example, in a given segment, the elements within channel information #3 belonging to that segment are sorted in the following order: ascending order of network device antenna port index, ascending order of frequency domain index, and ascending order of stream index.

[0572] In another example, in a given segment, the elements within channel information #3 belonging to that segment are sorted in the following order: descending order of network device antenna port index, descending order of frequency domain index, and descending order of stream index.

[0573] The above explanation is merely an example and should not be considered a limitation on the solution provided in this embodiment of the application.

[0574] Alternatively, the order of elements within a segment may be determined by the terminal device. In this case, the terminal device may notify the network device of the order of elements within the segment.

[0575] In possible implementations, channel information #3 may be obtained by performing codebook-based quantization on the initial channel information.

[0576] For channel information #3 obtained through codebook-based quantization, the content of channel information #3 may include at least one of the following: basis selection information, coefficient selection information, coefficient phase information, coefficient amplitude information, or the same.

[0577] Base selection information indicates a specific selected basis. Coefficient selection information indicates a specific selected non-zero coefficient. Coefficient amplitude information and coefficient phase information may be collectively referred to as coefficient value information. Coefficient value information indicates the value of the non-zero coefficient.

[0578] For example, Channel information #3 is i 1,1 i 1,2 i 1,8,l i 2,3,l i 1,5 i i,6,l i 2,4,l i 2,5,l or i 1,7,l It may include one or more of the following: i 1,1 This indicates spatial domain basis selection information, i 1,2 This indicates oversampling selection information, i 1,8,l This indicates the coefficient with the maximum value among the non-zero coefficients in each layer, i 2,3,l This indicates the reference amplitude information, i 1,5 This indicates common frequency domain basis selection information, i i,6,l This shows the frequency domain basis selection information for each layer, i 2,4,l This shows the amplitude information of each coefficient in each layer, i 2,5,l This shows the phase information of each coefficient in each layer, i 1,7,l This shows the non-zero coefficient selection information for each layer. The basis selection information is i 1,1 i 1,2 i 1,5 and i i,6,l It may include the coefficient selection information, i 1,7,l It may include the coefficient phase information, i 2,5,l It may include the coefficient amplitude information, i 2,4,l It may include.

[0579] The contents of each segment may be predefined or configured by the network. Specifically, the specific information contained in each segment within channel information #3 is determined by a predefined method or through network configuration.

[0580] For example, a segment may contain one or more content items.

[0581] For example, among the K segments, segment 1 may include basis selection information and coefficient selection information, segment 2 may include coefficient amplitude information, and segment 3 may include coefficient phase information.

[0582] For example, one segment may, alternatively, contain only a portion of the content of one content item. Specifically, one content item may be distributed across multiple segments.

[0583] For example, among the K segments, segment 1 may include basis selection information and coefficient selection information, segment 2 may include coefficient amplitude information, segment 3 may include a part of the coefficient phase information, and segment 4 may include another part of the coefficient phase information.

[0584] Please understand that the content of the aforementioned segments is merely an example and does not constitute a limitation on the solution in this embodiment of the present application.

[0585] Alternatively, the content of each of the K segments may be determined by the terminal device.

[0586] In this case, the terminal device may notify the network device of the contents of each segment.

[0587] Furthermore, the order of the segment contents may be predetermined or configured by the network device.

[0588] For example, segment 1 among K segments may contain basis selection information and coefficient selection information, and the order of the contents of segment 1 may be as follows: spatial domain basis selection information, oversampling selection information, common frequency domain basis selection information, frequency domain basis selection information for each layer, the coefficient with the maximum value among the non-zero coefficients for each layer, and non-zero coefficient selection information for each layer.

[0589] Alternatively, the order of multiple content items may be determined by the terminal device. In this case, the terminal device may notify the network device of the order of the multiple content items.

[0590] Example 72

[0591] Optionally, step 710 may include the step of a terminal device generating channel information #3, segmenting channel information #3 based on segment length, or segmenting channel information #3 based on K. The contents of channel information #3 are sorted in a first order.

[0592] In other words, the contents of channel information #3 are sorted in the first order, and then channel information #3 is segmented based on the length of each segment or based on the number of segments K.

[0593] The first sequence may be predefined or may be configured by network devices.

[0594] The first order will be explained below in relation to an example.

[0595] In possible implementations, channel information #3 may be obtained by performing scalar quantization on the initial channel information.

[0596] The channel information #3 obtained through scalar quantization may contain elements of the aforementioned matrix. The first order may be determined based on the index of each dimension of the matrix.

[0597] For example, channel information #3 is F × N tx ×N rank This is a 3D matrix with the following dimensions. For example, the elements in the 3D matrix are sorted in ascending order according to the following rule (an example of the first order): ascending order of frequency domain index, ascending order of network device antenna port index, and ascending order of stream index.

[0598] For example, the frequency domain index ranges from 1 to F, while the antenna port index for network devices ranges from 1 to N. tx The stream index ranges from 1 to N. rank The channel information #3 may be expressed as follows after being sorted in the first order: (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,N tx ,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,N tx ,2),...,(F,N tx ,N rank ).

[0599] (1,1,1) represents the element corresponding to frequency domain index 1, network device antenna port index 1, and stream index 1. (2,1,1) represents the element corresponding to frequency domain index 2, network device antenna port index 1, and stream index 1. By analogy, (F,N tx ,N rank ) is the frequency domain index F, and the antenna port index N of the network device. tx and Stream Index N rank This shows the corresponding elements.

[0600] For example, channel information #3 is F × N tx This is a two-dimensional matrix with the following dimensions. For example, the elements in the two-dimensional matrix are sorted in ascending order according to the following rule (an example of the first order): the frequency domain index and the antenna port index of the network device.

[0601] For example, channel information #3 is F × N tx ×N rxThis is a 3D matrix with the following dimensions. For example, the elements in the 3D matrix are sorted in ascending order according to the following rule (an example of the first order): ascending order of frequency domain index, ascending order of antenna port index of network devices, and ascending order of antenna port index of terminal devices.

[0602] The above explanation is merely an example, and it should be understood that the first order may be alternatively different. This is not limited to the present embodiment of the application.

[0603] In possible implementations, channel information #3 may be obtained by performing codebook-based quantization on the initial channel information.

[0604] For channel information #3 obtained through codebook-based quantization, the content of channel information #3 may include at least one of basis selection information, coefficient selection information, coefficient value information, and similar information.

[0605] For example, Channel information #3 is i 1,1 i 1,2 i 1,8,l i 2,3,l i 1,5 i i,6,l i 2,4,l i 2,5,l or i 1,7,l It may include one or more of the following: i 1,1 This indicates spatial domain basis selection information, i 1,2 This indicates oversampling selection information, i 1,8,l This indicates the coefficient with the maximum value among the non-zero coefficients in each layer, i 2,3,l This indicates the reference amplitude information, i 1,5 This indicates common frequency domain basis selection information, i i,6,l This shows the frequency domain basis selection information for each layer, i 2,4,l This shows the amplitude information of each coefficient in each layer, i 2,5,l This shows the phase information of each coefficient in each layer, i 1,7,l This shows the non-zero coefficient selection information for each layer.

[0606] For example, the first order may be the following: spatial domain basis selection information, oversampling selection information, the coefficient with the maximum value among the non-zero coefficients in each layer, reference amplitude information in each layer, common frequency domain basis selection information, frequency domain basis selection information in each layer, part of the amplitude information of each coefficient in each layer, part of the phase information of each coefficient in each layer, part of the non-zero coefficient selection information in each layer, part of the amplitude information of each coefficient in each layer, part of the phase information of each coefficient in each layer, and part of the non-zero coefficient selection information in each layer.

[0607] In another example, the first order may be as follows: spatial domain basis selection information, oversampling selection information, common frequency domain basis selection information, frequency domain basis selection information for each layer, non-zero coefficient selection information for each layer, the coefficient with the maximum value among the non-zero coefficients for each layer, reference amplitude information, amplitude information for each coefficient in each layer, and phase information for each coefficient in each layer.

[0608] It should be understood that the first order is merely an example of an order and does not constitute a limitation on the content of channel information #3. For example, if channel information #3 does not contain one of the contents described above, and channel information #3 is sorted in the first order, that contents may be ignored. For example, channel information #3 includes spatial domain basis selection information, oversampling selection information, the coefficient with the maximum value among the non-zero coefficients in each layer, reference amplitude information, common frequency domain basis selection information, frequency domain basis 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 may 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, the coefficient with the maximum 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.

[0609] For example, the first order may alternatively be determined by a terminal device. In this case, the terminal device may notify the network device of the first order.

[0610] The following describes, in relation to an example, how a terminal device divides channel information #3 into multiple segments based on the segment length.

[0611] In this case, the value of K may be determined based on the total length of channel information #3 and the length of each segment. The total length of channel information #3 is the number of bits used to represent channel information #3.

[0612] In possible implementations, the segment length may be predefined. The length of each segment is less than or equal to the maximum code length supported by UCI.

[0613] For example, threshold #3 may represent the lengths of at least K-1 segments among K segments. Threshold #3 may be predefined.

[0614] For example, the length of at least K-1 segments among K segments is threshold #3.

[0615] The terminal device may divide channel information #3 based on threshold #3, where the length of K-1 segments is threshold #3, and the length of the remaining segments may be determined based on the total length of channel information #3 and the total length of K-1 segments. The length of the remaining segments is less than or equal to threshold #3.

[0616] K may be determined based on threshold #3 and the total length of channel information #3. For example, K-1 may be the quotient obtained by dividing q by Q. q represents the total length of channel information #3. N is an integer greater than 1. The length of the remaining segments is qQ × (K-1), specifically the remainder obtained by dividing q by Q. Q represents the length of each of the K-1 segments, and Q is a positive integer. q represents the total length of channel information #3, and q is an integer greater than 1.

[0617] In another possible implementation, the segment length may be determined by the network devices.

[0618] For example, threshold #3 may represent the lengths of at least K-1 segments out of K segments. Threshold #3 may consist of network devices. For specific segmentation methods, please refer to the explanation above. Further details will not be explained again here.

[0619] For example, method 700 may further include the step of a terminal device receiving instruction information #6 transmitted by a network device, where instruction information #6 indicates the length of a segment. The lengths of the segments may be different. For example, instruction information #6 may indicate a set of candidate segment lengths.

[0620] In possible implementations, the segment length range may be predefined.

[0621] For example, threshold #3 may represent the maximum length of the segment. Threshold #3 may be predefined.

[0622] The terminal device may determine the length of each segment so that the length of each segment is less than or equal to threshold #3.

[0623] For example, threshold #3 may be the maximum code length supported by UCI.

[0624] In another possible implementation, the segment length range may be comprised of network devices.

[0625] The segment length range may be explicitly defined.

[0626] For example, threshold #3 may represent the maximum length of the segment. Threshold #3 may be configured by network devices.

[0627] In this case, please refer to the explanation above for the specific segmentation method. Further details will not be explained here.

[0628] For example, a network device may directly indicate the range of segment lengths transmitted in each of the K uplink resources used to transmit channel information #3. Each of the K uplink resources is used to transmit K UCIs.

[0629] K uplink resources may be understood as uplink resources scheduled K times by a network device. Alternatively, K uplink resources may be understood as K periodic uplink resources configured by a network device. Alternatively, uplink resources scheduled once by a network device are distributed across K time resource units. A time resource unit may be one or a combination of multiple slots. K uplink resources may be understood as K time resource units.

[0630] The segment length range may be implicitly or alternatively constructed.

[0631] For example, method 700 may further include the step of a terminal device receiving uplink resource configuration information #1 transmitted by a network device, where uplink resource configuration information #1 indicates K uplink resources used to transmit channel information #3, and each of the K uplink resources is used to transmit K UCIs. The terminal device determines the length of each segment based on each uplink resource and MCS. In this case, the K uplink resources may be understood as K time resource units within an uplink resource scheduled at once by the network device.

[0632] For example, a single uplink resource may contain multiple resource elements (resource elements, REs). A terminal device may determine the number of bits that can be transmitted using the uplink resource based on the number of REs in the uplink resource used to transmit the MCS and UCI, and then determine the number of uncoded bits that can be carried in the uplink resource. This number may be used as the maximum length of UCI that can be carried in the uplink resource, in other words, the maximum length of a segment that can be carried in the uplink resource. The terminal device may determine the length of each segment based on the maximum length of a segment that can be carried in the uplink resource so that the length of each segment is less than or equal to the length of UCI that can be carried in the uplink resource used to transmit that segment.

[0633] The following describes, in relation to an example, how a terminal device divides channel information #3 into multiple segments based on K.

[0634] In possible implementations, the value of K may be predefined.

[0635] In possible implementations, the value of K may be determined by the network device.

[0636] For example, a network device may recognize the total length of channel information #3 and configure an appropriate value for K based on the total length of channel information #3. For example, the feedback configuration corresponding to channel information #3 may be predefined or configured by the network device. In this case, the network device may recognize the total length of channel information #3 and configure an appropriate value for K based on the total length of channel information #3.

[0637] In another example, the network device may be aware of the total range of channel information #3 and configure an appropriate value for K based on the total range of channel information #3. For example, the range of parameters in the feedback configuration corresponding to channel information #3 may be predefined or configured by the network device. In this case, the network device may be aware of the total range of channel information #3 and configure an appropriate value for K based on the total range of channel information #3.

[0638] Optionally, method 700 further includes the step of a network device transmitting instruction information #8 (an example of second instruction information) to a terminal device, where instruction information #8 indicates a value of K.

[0639] Network devices may explicitly configure the value of K. In other words, instruction information #8 may explicitly indicate the value of K. For example, instruction information #8 may include the value of K.

[0640] The network device may implicitly configure the value of K as an alternative. In other words, instruction information #8 may implicitly indicate the value of K.

[0641] For example, method 700 may further include the step of a terminal device receiving uplink resource configuration information #1 transmitted by a network device.

[0642] In this case, uplink resource configuration information #1 may be used as instruction information #8. The network device may implicitly configure the value of K by using the number of scheduled uplink resources used to transmit channel information #3. The number of uplink resources used to transmit channel information #3, i.e., the number of time resource units, is the value of K. In other words, one UCI is transmitted by default across each uplink resource.

[0643] The terminal device may decide on a method for dividing channel information #3 to obtain K segments.

[0644] For example, the length of the first K-1 segments in K segments is Q.

number

number

[0645] For example, channel information #3 contains 2000 bits, K=2, and one of the two segments contains the first 1000 bits, while the other segment contains the last 1000 bits.

[0646] For example, the terminal device may alternatively obtain K segments by performing a partition at an arbitrary location, provided that the length of each of the K segments is less than threshold #3.

[0647] In another possible implementation, the value of K and the segment length may, alternatively, be entirely determined by the terminal device.

[0648] In the aforementioned case where a network device constitutes a segmentation scheme, it may be understood that the correspondence between channel information #3 and UCI, or the correspondence between K UCIs, is constituted by the network device.

[0649] In the aforementioned case where the terminal device determines the segmentation method, it may be understood that the correspondence between channel information #3 and UCI, or the correspondence between K UCIs, is determined by the terminal device and shown to the network device. For example, the terminal device may notify the network device of at least one of the values ​​of K or the lengths of the K segments.

[0650] Example 73

[0651] Optionally, step 730 may include a step in which the terminal device generates channel information #3 and segments channel information #3 based on the boundaries of various individual pieces of information within channel information #3. The contents of channel information #3 are sorted in a first order.

[0652] Each piece of information within channel information #3 is the shortest piece of information that has physical meaning. In other words, each segment contains one or more pieces of information.

[0653] This helps ensure the completeness of information within a segment.

[0654] For channel information #3 obtained through scalar quantization, one piece of information may be one element. For example, during scalar quantization, the initial channel information is quantized to 4 bits. In this case, each element in channel information #3 is represented by 4 bits, and 4 bits representing one element constitute one piece of information. 4 bits belonging to the same element are in the same segment.

[0655] For channel information #3 obtained through codebook-based quantization, one piece of information may be any one of the following: spatial domain basis selection information, oversampling selection information, reference amplitude information for each layer, frequency domain basis selection information for 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 phase information of the same coefficient are in the same segment.

[0656] Example 73 may be used in combination with some of the implementations in Example 72. Examples will be used below for illustrative purposes.

[0657] For example, a terminal device may divide channel information #3 based on the length range of each segment and the boundaries of each piece of information within channel information #3.

[0658] In this case, the length of each segment is within the length range of that segment, and the segment contains one or more pieces of information.

[0659] For channel information #3 obtained through scalar quantization, if bits belonging to the same element are included in two segments, and the segment length range is satisfied, all bits belonging to that element may be distributed to either the first or last segment.

[0660] For example, channel information #3 obtained through scalar quantization contains a total of 12 bits, and each element within channel information #3 is represented by 4 bits. The length of each segment is less than or equal to 6 bits. For example, segment 1 contains 6 bits, segment 2 contains 2 bits, and segment 3 contains 4 bits. In this case, bits belonging to the same element are contained in two segments, segment 1 and segment 2. All bits belonging to that element may be distributed to segment 2.

[0661] For channel information #3 obtained through codebook-based quantization, if the same bits of information are contained in two segments, and the segment length range is satisfied, all of the bits of that information may be distributed to either the first or last segment.

[0662] For example, with respect to channel information #3 obtained through codebook-based quantization, if the same phase information bits for the same coefficient are included in two segments, all of the phase information bits for that coefficient may be distributed to either the first or last segment.

[0663] For example, a terminal device may divide channel information #3 based on K items and the boundaries of each piece of information within channel information #3.

[0664] In this case, each segment contains one or more pieces of information, and channel information #3 is divided into a total of K segments.

[0665] For a detailed explanation, please refer to the explanation given above. Further details will not be explained here.

[0666] In some of the aforementioned implementations, the length of each segment is determined by the terminal device. In this case, the network device is unaware of the length of each segment, and the terminal device may inform the network device of the length of each segment, in other words, it may inform the network device of the length of each UCI.

[0667] Optionally, the terminal device may send instruction information #9 (an example of third instruction information) to the network device to indicate the length of each of the K UCIs, or the length of each of the K segments.

[0668] In this way, network devices can decode each UCI to obtain each segment of channel information #3.

[0669] K UCIs may be transmitted using J uplink resources, where J is a positive integer.

[0670] The following describes the uplink resources used to transmit K UCIs, in relation to an example.

[0671] K UCIs may be transmitted using the same uplink resource; that is, J=1.

[0672] Alternatively, K UCIs may be transmitted using multiple uplink resources, i.e., J > 1.

[0673] Multiple uplink resources may be understood as uplink resources scheduled multiple times by a network device. Alternatively, multiple uplink resources may be understood as multiple periodic uplink resources configured by a network device. Alternatively, an uplink resource scheduled once by a network device may be distributed across multiple time resource units. A time resource unit may be one or a combination of multiple slots. Multiple uplink resources may be understood as multiple time resource units.

[0674] In this case, even when the length of channel information #3 exceeds the limit of the length of UCI that can be carried by a single uplink resource, the remaining portion of channel information #3 does not need to be discarded, and each of the K UCIs may be transmitted using multiple uplink resources, and as a result, the network device can obtain the complete channel information #3. Furthermore, if the length of a segment exceeds the limit of the length of UCI that can be carried by a single uplink resource, that segment may be transmitted using multiple uplink resources, and as a result, the network device can obtain the complete channel information #3.

[0675] If J > 1, one or more of the K UCIs may be transmitted at each uplink resource. The number of UCIs transmitted at all uplink resources may be the same or different.

[0676] With respect to uplink resources, a network device may decode each UCI based on the number of UCIs transmitted in the uplink resource and the length of each UCI transmitted in the uplink resource, and obtain K segments contained in the UCIs transmitted in the uplink resource.

[0677] If a network device is unaware of the number of UCIs transmitted at each uplink resource, or the length of each UCI, the terminal device may notify the network device of the number of UCIs transmitted at each uplink resource and / or the length of each UCI, thereby enabling the network device to decode the UCIs transmitted at each uplink resource.

[0678] Below, we will explain the case where J=1, in relation to the example.

[0679] For example, K may be configured by a network device or may be predefined. In this case, the network device is aware of the value of K. The terminal device divides channel information #3 based on the value of K, and the length of the K segments is determined by the terminal device. In this case, the terminal device may notify the network device of the length of the K segments to be transmitted in the uplink resource.

[0680] In another example, the lengths of K-1 segments out of K segments may be configured or predefined by the network device, and the lengths of the remaining segments and the value of K 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 is unaware of the total length of channel information #3 or the value of K, the terminal device may inform the network device of at least two of the following: the lengths of the remaining segments, the value of K, or the total length of channel information #3.

[0681] In another example, the maximum segment length is configured or predefined by the network device. The terminal device divides channel information #3 so that the length of each segment is less than or equal to the maximum segment length. The terminal device may notify the network device of the length of each segment. The terminal device may further notify the network device of the value of K or the total length of channel information #3.

[0682] The following section explains the case where J > 1, in relation to the example.

[0683] For example, the number of UCIs transmitted in each uplink resource may be determined by the network device or may be predetermined.

[0684] Optionally, a network device may send instruction information #11 (an example of the fifth instruction information) to a terminal device, where instruction information #11 indicates the number of segments transmitted at each uplink resource. The number of segments transmitted at each uplink resource is the number of UCIs transmitted at each uplink resource.

[0685] For example, the specific segments transmitted in each of the J uplink resources may be predefined or configured by network devices.

[0686] Optionally, instruction information #11 may further indicate identifiers of segments transmitted at each uplink resource. In other words, instruction information #11 may further indicate specific segments transmitted at each uplink resource. For example, instruction information #11 may indicate the number of segments transmitted at each uplink resource, including the number of each segment to be transmitted, or one or more of the following information: the start number of the transmitted segment, the number of segments, or the end number of the transmitted segment. The portion of one or more items not indicated by instruction information #11 may be obtained in another way, for example, by being predefined in the protocol. The number of each segment may indicate the position of that segment among K segments. In other words, the numbers of the K segments may indicate the order of the K segments. Instruction information #11 may indicate the order of segments transmitted at each uplink resource by indicating the number of segments transmitted at each uplink resource.

[0687] In the aforementioned case where a network device performs configuration, it may be understood that the correspondence between channel information #3 and the uplink resource, or the correspondence between multiple uplink resources, is configured by the network device.

[0688] Alternatively, the terminal device may determine the number of segments transmitted at each uplink resource based on the length of the UCI that can be carried at each of the J uplink resources, so that the total length of the UCI transmitted at each uplink resource is less than or equal to the length of the UCI that can be carried at that uplink resource.

[0689] The terminal device may notify the network device of the number of UCIs transmitted in each uplink resource.

[0690] Optionally, the terminal device may send instruction information #14 (an example of the sixth instruction information) to the network device, where instruction information #14 may indicate the number of UCIs transmitted in each uplink resource.

[0691] Optionally, instruction information #14 may further indicate the identifier of the UCI transmitted at each uplink resource, in other words, it may indicate the specific UCI transmitted at each uplink resource.

[0692] In other words, a terminal device may notify a network device of the order of segments transmitted at each uplink resource; specifically, it may notify the network device of the location of the segments included in the UCI transmitted at each uplink resource among the K segments.

[0693] For example, instruction information #14 may indicate, for example, the number of each segment to be transmitted in the uplink resource, or one or more of the following information: the start number of the transmitted segment, the number of segments, or the end number of the transmitted segment. The portion of one or more items not indicated by instruction information #14 may be obtained in another way, for example, by being predefined in the protocol. The number of each segment indicates the position of that segment among K segments. The numbers of the K segments may indicate the order of the K segments.

[0694] The length of UCI that can be transported at each uplink resource may be predetermined or configured by the network device.

[0695] Furthermore, if the network device is unaware of the length of the segments transmitted at each uplink resource, the terminal device may inform the network device of the length of the segments transmitted at each uplink resource. For example, the length of K segments may be determined by the terminal device. In this case, the terminal device may inform the network device of the length of the segments transmitted at each uplink resource.

[0696] Optionally, a terminal device may send instruction information #15 (an example of the seventh instruction information) to a network device, where instruction information #15 indicates that multiple uplink resources correspond to the same channel information #3.

[0697] In other words, instruction information #15 may indicate the specific uplink resource used to transmit channel information #3.

[0698] A terminal device may notify a network device of the channel information to which the information transmitted at each uplink resource belongs. In other words, a terminal device may notify a network device of the specific uplink resource to which the same channel information is transmitted.

[0699] For example, each uplink resource may carry an identifier, which is used to distinguish channel information. If two uplink resources carry the same identifier, the information transmitted using these two uplink resources will indicate the same channel information. If two uplink resources carry different identifiers, the information transmitted using these two uplink resources will indicate different channel information. The identifier may be used as instruction information #15.

[0700] In the aforementioned case, where a terminal device notifies a network device of the specific uplink resources used to transmit UCI, the number of UCIs transmitted in each uplink resource, and the specific UCIs transmitted in each uplink resource, it can be understood that the correspondence between channel information #3 and the uplink resources, or the correspondence between multiple uplink resources, is determined by the UE and shown to the base station.

[0701] If J is greater than 1, the types of the J uplink resources may be the same or different.

[0702] For example, J uplink resources may be resources dedicated to channel information transmission. Resources dedicated to channel information transmission are resources used to transmit only channel information without transmitting uplink data.

[0703] For example, J uplink resources may be resources that are reused for channel information and uplink data. Resources that are reused for channel information and uplink data indicate that the uplink resources may be used to transmit channel information and uplink data.

[0704] For example, if J is greater than 1, some uplink resources may be dedicated to transmitting channel information, while other uplink resources may be used again for both channel information and uplink data.

[0705] In a possible implementation, the terminal device receives uplink resource configuration information #2 (an example of first uplink resource configuration information) transmitted by the network device, where uplink resource configuration information #2 indicates uplink resource #1 (an example of first uplink resource) used to transmit channel information #3. Step 720 may include a step in which the terminal device transmits K UCIs on uplink resource #1.

[0706] Optionally, uplink resource configuration information #2 may further indicate whether uplink resource #1 can be used to transmit UCI. If uplink resource #1 can be used to transmit UCI, the terminal device may transmit K UCIs on uplink resource #1.

[0707] For example, uplink resource #1 can be considered as a single uplink resource.

[0708] For example, uplink resource #1 may be distributed across J time resource units, and uplink resource #1 may be considered as J uplink resources. Specifically, the network device schedules J uplink resources at once. For example, uplink resource configuration information #2 may indicate the number of segments transmitted in each time resource unit, and / or the specific segments transmitted in each time resource unit. In other words, uplink resource configuration information #2 may be used as instruction information #11.

[0709] In another possible implementation, a network device may configure J periodic uplink resources. Each period includes an uplink resource used to transmit UCIs. The network device may decode the UCIs in each uplink resource based on the number of UCIs transmitted in that uplink resource and the length of each UCI transmitted in that uplink resource to obtain the segments contained in the UCIs transmitted in that uplink resource.

[0710] In a possible implementation, the terminal device receives uplink resource configuration information #3 (an example of second uplink resource configuration information) transmitted by the network device, where uplink resource configuration information #3 indicates uplink resource #2 (an example of second uplink resource). Step 720 may include a step in which the terminal device transmits a portion of K UCIs in uplink resource #2.

[0711] Optionally, uplink resource configuration information #3 may further indicate whether uplink resource #2 can be used to transmit UCI. If uplink resource #2 can be used to transmit UCI, the terminal device may transmit a portion of K UCIs in uplink resource #2.

[0712] Uplink resource #2 may be considered as one uplink resource, and uplink resource #2 belongs to J uplink resources.

[0713] For example, uplink resource #2 may be the first uplink resource used to transmit K UCIs, and step 720 may include the step in which the terminal device transmits the UCIs that are included in the first k segments of the K segments, among the K UCIs, via uplink resource #2, where k is a positive integer.

[0714] The first k UCIs are the first k transmitted UCIs out of K UCIs.

[0715] Optionally, uplink resource configuration information #3 may further indicate the number of UCIs transmitted in uplink resource #2, and / or a specific UCI to be transmitted among K UCIs. For example, uplink resource configuration information #3 may indicate the number of the UCI to be transmitted in uplink resource #2. Uplink resource configuration information #3 may be used as instruction information #11.

[0716] Furthermore, the transmission of a portion of K UCIs by a terminal device in uplink resource #2 may include the transmission of a portion of K UCIs and instruction information #12 (an example of the fourth instruction information) in uplink resource #2. Instruction information #12 indicates at least one of the following: the total length of the untransmitted UCI among the K UCIs, or whether the K UCIs include the untransmitted UCI. Alternatively, if a portion of K UCIs includes the first UCI, instruction information #12 indicates at least one of the following: the total length of channel information #3, the total length of the untransmitted UCI among the K UCIs, or whether the K UCIs include the untransmitted UCI.

[0717] Whether K UCIs include any UCIs that have not been transmitted can be indicated in multiple ways.

[0718] For example, instruction information #12 may indicate the number of UCIs transmitted in uplink resource #2 and / or the identifier of a UCI; more specifically, it may indicate a specific UCI transmitted in uplink resource #2. The network device may determine whether there are any untransmitted UCIs based on the number of UCIs transmitted in uplink resource #2, the number of transmitted UCIs, and the value of K. If the value of K is determined by the terminal device, the terminal device may notify the network device of the value of K. In this case, instruction information #12 and instruction information #14 may be the same information.

[0719] For example, instruction information #12 may directly indicate whether there are any untransmitted UCIs. For example, if there are untransmitted UCIs, the corresponding flag bit may be "1"; or if there are no untransmitted UCIs, the flag bit may be "0".

[0720] For example, instruction information #12 indicates at least one of the following: the total length of the untransmitted UCI among the K UCIs, an identifier indicating whether the K UCIs contain the untransmitted UCI, the number of UCIs to be transmitted in uplink resource #2, or the identifier of the UCI.

[0721] The first UCI is the first UCI to be transmitted among the K UCIs, or the UCI used to transmit the segment ranked first in channel information #3. For example, the first UCI may be the UCI included in the first segment among the K segments.

[0722] Instruction information #12 may be used as an independent UCI and transmitted in uplink resource #2 along with a portion of K UCIs.

[0723] Untransmitted UCI is an untransmitted segment.

[0724] Alternatively, the terminal device may transmit instruction information #12 by using another uplink resource.

[0725] For example, if K UCIs include untransmitted UCIs, the terminal device may wait for the network device to schedule another uplink resource to transmit the untransmitted UCIs among the K UCIs.

[0726] For example, a terminal device receives uplink resource configuration information #31 transmitted by a network device, where uplink resource configuration information #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 the transmission of UCI.

[0727] Furthermore, uplink resource configuration information #31 may further indicate the number of UCIs transmitted in the uplink resource, and / or the specific UCIs to be transmitted among the remaining UCIs. Uplink resource configuration information #31 may be used as instruction information #12.

[0728] Alternatively, if K UCIs include untransmitted UCIs, the terminal device may transmit the remaining untransmitted UCIs by using one or more other subsequent uplink resources, for example, by using an uplink resource used to transmit uplink data. In other words, the remaining UCIs are transmitted by using an uplink resource that is again used for UCIs and uplink data.

[0729] Optionally, method 700 may further include the step of a terminal device receiving uplink resource configuration information #4 transmitted by a network device, where uplink resource configuration information #4 (an example of third uplink resource configuration information) indicates uplink resource #3 (an example of a third uplink resource). The terminal device transmits instruction information #13 at uplink resource #3, where instruction information #13 indicates the full length of channel information #3.

[0730] In this case, uplink resource #3 does not belong to any of the J uplink resources.

[0731] For example, a terminal device may wait for a network device to schedule another uplink resource in order to transmit K UCIs.

[0732] For example, a terminal device receives uplink resource configuration information #41 transmitted by a network device, where 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 the transmission of UCI.

[0733] In the solution of this embodiment of the present application, the terminal device may request uplink resources from the network device to transmit untransmitted segments. This helps to make appropriate use of uplink resources and avoid resource waste.

[0734] Optionally, step 720 may include a step in which a terminal device transmits a portion of K UCIs to a network device. Method 700 may further include a step of discarding any untransmitted UCIs among the K UCIs, where the timing starting from the transmission time of the first UCI among the K UCIs is greater than or equal to threshold #5 (an example of a second threshold).

[0735] In other words, starting from the transmission start time of the CSI report in channel information #3, if the transmission duration of the transmitted segments among the K segments is greater than or equal to threshold #5, the untransmitted segments among the K segments are discarded; in other words, the untransmitted segments are no longer transmitted.

[0736] For example, Timer #1 is started at the time of transmission of the first UCI, and if the timing of Timer #1 is greater than or equal to threshold #5, any untransmitted UCIs among the K UCIs are discarded.

[0737] For example, the transmission time of the first UCI may be the start or end time of the transmission of the first UCI, or another time that is used as a reference to the start or end time of the transmission of the first UCI, provided that such time can represent the duration for which channel information is transmitted by using the UCI. This is not limited to the foregoing.

[0738] In another example, it is determined whether the duration between the start of transmission of a segment and the start of transmission of the CSI report for channel information #3 is greater than or equal to threshold #5. If yes, the segment and all remaining segments are discarded. If no, the segment is transmitted.

[0739] If the duration of transmitting channel information #3 is excessively long, the terminal device may determine that the transmission of channel information #3 has failed and discard the remaining segment. This helps to avoid wasting resources.

[0740] Optionally, step 720 may include a step in which a terminal device transmits a portion of K UCIs to a network device. Method 700 may further include a step in which untransmitted UCIs among the K UCIs are discarded, where the timing starting from the transmission time of the 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.

[0741] Alternatively, channel information #3 may be referred to as the label corresponding to channel information #4.

[0742] Channel information #4 and channel information #3 are channel information that have a corresponding relationship.

[0743] For example, channel information #4 and channel information #3 may correspond to the same initial channel information. Specifically, channel information #4 and channel information #3 may be obtained based on the same initial channel information.

[0744] Optionally, a terminal device may send instruction information #16 to a network device, where instruction information #16 may indicate specific channel information #4 corresponding to channel information #3. For example, instruction information #16 may indicate an index of a CSI report for transmitting channel information #4, an index of a resource for transmitting channel information #4, an index of a reference signal for measuring channel information #4, or an index of a resource for transmitting a reference signal.

[0745] For example, the index of the resource for sending channel information #4 may be the identifier of the transmission slot of the resource to which channel information #4 will be transmitted.

[0746] For example, the index of a resource for transmitting a reference signal may be the identifier of the transmission slot of the resource for transmitting the reference signal.

[0747] For example, the identifier of a transmission slot may be represented by the identifier of the starting slot for transmission, or by the identifier of the starting slot for transmission and the number of transmission slots. Alternatively, the identifier of a transmission slot may be represented by the identifier of the ending slot for transmission and the number of transmission slots. Alternatively, the identifier of a transmission slot may be represented by the identifier of the starting slot for transmission and the identifier of the ending slot for transmission. Alternatively, the identifier of a transmission slot may be represented by a bitmap of the transmission slots.

[0748] Optionally, channel information #3 and at least one segment within channel information #4 may be transmitted over the same uplink resource. For example, the UCI used to transmit channel information #4 and the first UCI used to transmit channel information #3 may be transmitted over the same uplink resource.

[0749] For example, channel information #4 may be a compressed CSI reported in a conventional mode (e.g., based on the R16 codebook).

[0750] In another example, channel information #4 may be channel information reported in AI-based feedback mode. Specifically, channel information #4 may be obtained based on an AI model.

[0751] For example, the AI ​​model may be a bidirectional model. A submodel of the bidirectional model deployed on a terminal device may be used to generate channel information that is fed back to the network device. A submodel deployed on the network device may be used to reconstruct the channel information. In other words, in a bidirectional model, the channel information that is fed back to the network device may be generated by a submodel of the AI ​​model.

[0752] For example, the AI ​​model may include a CSI generator and a CSI reconfigurator. The CSI generator may be deployed on a terminal device, and the CSI reconfigurator may be deployed on a network device. The terminal device may use the CSI generator to generate CSI feedback information, i.e., channel information to be fed back to the network device, based on the initial channel information, and may use a CSI report to feed back the channel information to the network device. The network device may use the CSI reconfigurator to reconstruct the CSI information and obtain CSI restoration information. The CSI restoration information may be used as channel information #4.

[0753] For a detailed explanation of the CSI generator and CSI reconfigurator, please refer to the previous explanation. To avoid repetition, the details will not be explained again here.

[0754] The above description is merely an example, and it should be understood that the AI ​​model may be of a different type. This is not limited to this embodiment of the Application. For the sake of clarity, the example in this embodiment of the Application in which the AI ​​model includes a CSI generator and a CSI reconfigurator is used primarily for illustrative purposes and does not constitute a limitation on the solution in this embodiment of the Application.

[0755] In this case, the use of channel information #3 to measure the accuracy of channel information #4 may be understood as channel information #3 being used to measure the performance of the AI ​​model, that is, being used for model monitoring. Specifically, when channel information #3 is used for model monitoring, if the duration elapsed since the transmission of channel information #4 during the transmission of channel information #3 is greater than or equal to threshold #6, the terminal device may determine that the transmission of channel information #3 has failed and may discard the remaining segment; in other words, it will no longer transmit the segment that has not been transmitted.

[0756] For example, the transmission time of channel information #4 may be the start time of the transmission of channel information #4. Alternatively, the transmission time of channel information #4 may be the completion time of the transmission of channel information #4. Alternatively, the transmission time of channel information #4 may be another time point used as a reference to the start or end time of the transmission of channel information #4, provided that such time point can represent the duration of the transmission of channel information #4. This is not limited to the foregoing.

[0757] If, during the transmission of channel information #3, the duration between the current time and the transmission time of channel information #4 is greater than or equal to threshold #6, the untransmitted segment will be discarded.

[0758] For example, Timer #2 is started at the time of transmission of channel information #4, and if the timing of Timer #2 is greater than or equal to threshold #6, any untransmitted UCIs among the K UCIs are discarded.

[0759] In another example, it is determined whether the duration between the start of transmission of a segment and the transmission time of channel information #4 is greater than or equal to threshold #6. If yes, the segment and all remaining segments are discarded. If no, the segment is transmitted.

[0760] Channel information #3 is used to measure the accuracy of channel information #4. If an excessively long time has elapsed since the transmission of channel information #4, the actual channel information may have changed, making it difficult to measure the current performance of the model using channel information #3 and channel information #4. The terminal device may determine that the transmission of channel information #3 has failed and discard the remaining segment. This helps to avoid wasting resources.

[0761] Figure 10 shows yet another communication method according to one embodiment of the present invention.

[0762] As shown in Figure 10, Method 800 may include the following steps:

[0763] 810: The terminal device generates channel information #5 (an example of the fifth channel information), where the type of channel information #5 is ground truth channel information.

[0764] 820: The terminal device transmits channel information #5 to the network device using higher-layer signaling.

[0765] Channel information #5 may be used for model monitoring, model training, or similar purposes.

[0766] The network device may perform data processing based on channel information #5, or it may forward channel information #5.

[0767] For example, performing data processing based on channel information #5 may include performing model training or model monitoring based on channel information #5.

[0768] For example, transferring channel information #5 may include transferring channel information #5 to another device having an AI module. The AI ​​module is configured to implement a corresponding AI function, such as model monitoring or model training. For example, the AI ​​module may be the RIC shown in Figure 2.

[0769] For example, channel information #5 may be obtained by performing scalar quantization on the initial channel information.

[0770] For example, channel information #5 may be obtained by performing codebook-based quantization on the initial channel information.

[0771] For example, channel information #5 may be generated based on the first feedback configuration. In this case, channel information #5 and channel information #1 may be the same channel information.

[0772] For specific feedback modes, please refer to the explanation in Method 500. Further details will not be provided here. Alternatively, channel information #5 may be generated in a different manner.

[0773] In the solution provided in this embodiment of the present invention, channel information may be transmitted using upper-layer signaling, and as a result, the network device can acquire channel information with high overhead, i.e., high-precision channel information.

[0774] Optionally, higher-level signaling may include RRC messages or medium access control elements (MAC CEs).

[0775] For the sake of clarity, in this embodiment of the present application, the RRC message is used primarily as an example for illustrative purposes.

[0776] A single RRC message may be used to transmit one or more channel information of the ground truth channel information type.

[0777] Optionally, an RRC message (an example of a first RRC message) may be used to transmit channel information #6 (an example of a sixth channel information), and channel information #5 may be used to measure the accuracy of channel information #6.

[0778] Alternatively, channel information #5 may be referred to as the label corresponding to channel information #6.

[0779] In other words, channel information #5 and channel information #6 may be transmitted in the same RRC message.

[0780] Channel information #5 and channel information #6 are corresponding channel information. For a detailed explanation, please refer to channel information #4 and channel information #3 in the explanation above.

[0781] For example, channel information #6 may be channel information that is fed back based on AI. In this case, channel information #5 may be used for model monitoring.

[0782] If channel information #6 is not transmitted in the RRC message, the terminal device may further notify the network device of the correspondence between channel information #5 and channel information #6. Specifically, the terminal device may notify the network device of two corresponding channel information items.

[0783] Optionally, the RRC message may further indicate the correspondence between channel information #5 and channel information #6.

[0784] For example, the RRC message may further include a UCI containing channel information #6.

[0785] In other words, the RRC message may further indicate a specific UCI that includes channel information #6 corresponding to channel information #5.

[0786] For example, a UCI containing channel information #6 may be indicated by the transmission time of the UCI. Specifically, the RRC message may further indicate the transmission time of the UCI containing channel information #6. The transmission time of the UCI may be indicated by the identifier of the transmission slot of the UCI.

[0787] The identifier of a transmission slot may be represented by the identifier of the start slot for transmission, or by the identifier of the start slot for transmission and the number of transmission slots. Alternatively, the identifier of a transmission slot may be represented by the identifier of the end slot for transmission and the number of transmission slots. Alternatively, the identifier of a transmission slot may be represented by the identifier of the start slot for transmission and the identifier of the end slot for transmission. Alternatively, the identifier of a transmission slot may be represented by the bitmap of the transmission slots.

[0788] For example, the transmission time of a UCI may be represented by the identifier of the start slot for transmitting the UCI and the number of transmission slots. In another example, the transmission time of a UCI may be represented by the identifier of the start slot for transmitting the UCI and the identifier of the end slot for transmitting the UCI. In yet another example, the transmission time of a UCI may be represented by a bitmap of the UCI transmission slots. For example, the transmission time of a UCI may be represented by the identifier of the end slot for transmitting the UCI and the number of transmission slots.

[0789] In another example, the RRC message may further indicate the index of the reference signal used to measure channel information #6 or the index of the resource used to transmit the reference signal, for example, the identifier of the resource's transmission slot.

[0790] The above explanation is merely an example, and it should be understood that the terminal device may alternatively indicate the correspondence between channel information #5 and channel information #6 in a different manner. For example, the terminal device may further transmit other instructional information to indicate uplink resources for transmitting channel information #5 and uplink resources for transmitting channel information #6. For example, uplink resources may carry identifiers, and channel information transmitted in uplink resources having the same identifier is corresponding channel information.

[0791] Optionally, the RRC message may further indicate common support information #1 for one or more channel information of ground truth channel information type transmitted using the RRC message, and one or more channel information of ground truth channel information type includes channel information #5.

[0792] For example, support information #1 may be represented in the form of an ID. For example, support information #1 may include one or more of the following: the vendor ID of the terminal device, the model ID of the terminal device, the type ID of the terminal device, or the same. In another example, support information #1 may include one or more of the following: the vendor ID of the chip, the type ID of the chip, the model ID of the chip, or the same.

[0793] For example, support information #1 may be expressed as specific content. For example, support information #1 may include one or more of the following: the vendor of the terminal device, the type of the terminal device, the model of the terminal device, or the like. In another example, support information #1 may include one or more of the following: the vendor of the chip, the type of the chip, the model of the chip, or the like.

[0794] Optionally, the RRC message may further indicate supporting information #2 for channel information #5. Supporting information #2 is supporting information specific to channel information #5.

[0795] For example, support information #2 may be represented in the form of an ID. For example, support information #2 may include the ID of the time of the CSI measurement and / or the ID of the reference signal configuration of the CSI measurement. The time of the CSI measurement may be the measurement time of the initial channel information corresponding to channel information #5.

[0796] For example, support information #2 may be expressed as specific content. Support information #2 may include the timing of the CSI measurement, the accuracy of channel information #5, and / or similar information.

[0797] The following describes RRC messages for transmitting ground truth channel information type, using an example.

[0798] For example, the RRC information element for transmitting channel information #5 may be a CSI-groundtruth message. Each CSI-groundtruth message may contain one or more channel information of the groundtruth channel information type, and the channel information of the groundtruth channel information type may be indicated by CSI-groundtruth.

[0799] For example, a CSI-Ground Truth-Message may further include at least one of the following: the message identifier (ID) or common support information #1 of one or more Ground Truth CSIs within the message.

[0800] Each CSI-Ground Truth may contain one channel information of the Ground Truth channel information type.

[0801] Furthermore, CSI-Ground Truth may also include the ID of channel information #5.

[0802] Furthermore, the CSI-Ground Truth may further include channel information #6, or a UCI identifier used to transmit channel information #6.

[0803] Furthermore, CSI-Ground Truth may include supporting information #2 for channel information #5.

[0804] Furthermore, research has shown that training AI typically requires a large amount of training data. When training data is transmitted using terminal devices, significant air interface overhead occurs on these devices.

[0805] With this in mind, one embodiment of the present invention further provides a communication method. The training dataset is divided into multiple subsets, and each of the multiple subsets is transmitted to the training device through multiple terminal devices, thereby avoiding the significant air interface overhead of the terminal devices.

[0806] Figure 11 shows a communication method according to one embodiment of the present invention.

[0807] As shown in Figure 11, method 900 may include the following steps:

[0808] 910: The second device receives the first training dataset from the first device. The first training dataset contains T1 training data points, where T1 is a positive integer. The first training dataset is a subset of the third training dataset. The third training dataset is used for model training.

[0809] 920: The third device receives the second training dataset from the first device. The second training dataset contains T2 training data points, where T2 is a positive integer. The second training dataset is a subset of the third training dataset. The second and first training datasets are distinct subsets of the third training dataset.

[0810] Optionally, method 900 may further include steps 930 to 950. 930: The second device transmits the first training dataset to the fourth device.

[0811] 940: The third device sends the second training dataset to the fourth device.

[0812] 950: The fourth device trains the model based on the fourth training dataset. The fourth training dataset includes at least the first training dataset and the second training dataset.

[0813] It should be noted that the step numbers in Method 900 are intended solely for ease of explanation and do not constitute a limitation on the order in which the steps in Method 900 are performed. For example, steps 910 and 920 may be performed simultaneously, and steps 930 and 940 may be performed simultaneously.

[0814] Each training data set is a training sample input to the AI ​​model, or each training data set is a training sample and its corresponding label.

[0815] For example, one training sample may be one piece of channel information. For example, the type of channel information may be any one of the following: ground truth channel information, channel response, channel eigenvector matrix, precoding matrix, or similar.

[0816] In the solution of this embodiment of the present application, the first device divides the third training dataset into multiple subsets, transmits the multiple subsets through multiple terminal devices, and the devices receiving the multiple subsets reassemble the multiple subsets into a training dataset and perform model training based on the reassembled training dataset. This avoids the significant air interface overhead of the terminal devices.

[0817] In some scenarios, network devices need to send training datasets to terminal devices in order to enable them to train AI models.

[0818] For example, the first device may be a network device, the second and third devices may be terminal devices, and the fourth device may be a server or cloud server.

[0819] Terminal devices from the same vendor or of the same model can typically use the same AI model, and model training is usually performed by the terminal device vendor's server. As shown in Figure 12, the network device divides training dataset #1 (an example of a third training dataset) into multiple subsets, e.g., subset #1, subset #2 and subset #3 in Figure 12; and transmits these subsets to the terminal device server through multiple terminal devices, e.g., terminal device #1, terminal device #2 and terminal device #3 in Figure 12, so that the server can receive the subsets and reassemble them into training dataset #2 (an example of a fourth training dataset).

[0820] The number of subsets obtained through partitioning and the number of devices in Figure 12 are merely examples and should not constitute a limitation on the solution in this embodiment of the application.

[0821] In some scenarios, a terminal device may send a training dataset to a network device, which then trains an AI model.

[0822] For example, the first device may be a server or a cloud server, the second and third devices may be terminal devices, and the fourth device may be a network device.

[0823] The network device may be a network device on which one or more AI modules are deployed.

[0824] For example, the network device may be one or more of the following devices shown in Figure 1: core network device, access network node (RAN node), or OAM. For example, the AI ​​module may be an RIC shown in Figure 2, for example, a quasi-real-time RIC or a non-real-time RIC. For example, a quasi-real-time RIC is deployed on a RAN node (e.g., CU or DU), and a non-real-time RIC is deployed on an OAM, cloud server, core network device, or another network device. The RIC may acquire a subset from multiple terminal devices from a RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU), reassemble the subset into training dataset #2, and perform training based on training dataset #2.

[0825] For example, quasi-real-time RICs and non-real-time RICs may be deployed independently as network elements, and network devices may be either quasi-real-time RICs or non-real-time RICs.

[0826] As shown in Figure 13, the terminal device server divides training dataset #1 into multiple subsets and transmits these subsets to the network device through multiple terminal devices (e.g., the second and third devices). As a result, the network device receives the subsets and can reassemble them into a training dataset, for example, training dataset #2.

[0827] For the sake of clarity, the example in Method 900 in which the first device is a network device is used primarily for illustrative purposes and does not constitute a limitation on the solution in this embodiment of the Application.

[0828] The solution in this embodiment of the present application may be applied to independent training scenarios for both-sided models. A CSI feedback model is used as an example for illustrative purposes below. The CSI feedback model includes a CSI generator and a CSI reconfigurator. A first device trains a first CSI feedback model, which includes a first CSI generator and a first CSI reconfigurator.

[0829] For example, the inputs and outputs of a trained first CSI generator may be used as training data in a third training dataset. Specifically, the inputs of the first CSI generator may be used as training samples, and the outputs of the first CSI generator may be used as labels corresponding to the training samples. A fourth device may train a second CSI generator based on a fourth training dataset, enabling the second CSI generator to output the same CSI feedback information as that output by the first CSI generator. The first CSI generator is compatible with the first CSI reconfigurator, and the training data for the second CSI generator is obtained based on the inputs and outputs of the first CSI generator. In this way, the trained second CSI generator can be used in conjunction with the first CSI reconfigurator. For example, the first device is an RIC, or a network device including an RIC, which may train the first CSI feedback model. In addition, the RIC obtains the output of the trained first CSI generator. The inputs and outputs of the trained first CSI generator are used as training data in a third training dataset and may be transmitted to multiple terminal devices via a RAN node or directly to multiple terminal devices.

[0830] For example, the inputs and outputs of a trained first CSI reconfigurator may be used as training data in a third training dataset. The inputs of the first CSI reconfigurator may be used as training samples, and the outputs of the first CSI reconfigurator may be used as labels corresponding to the training samples. A fourth device may train a second CSI reconfigurator based on a fourth training dataset, enabling the second CSI reconfigurator to output the same CSI reconfiguration information as that output by the first CSI reconfigurator. The first CSI generator is compatible with the first CSI reconfigurator, and the training data for the second CSI reconfigurator is obtained based on the inputs and outputs of the first CSI reconfigurator. In this way, the trained second CSI reconfigurator can be used in conjunction with the first CSI generator. For example, the first device is an RIC, or a network device including an RIC, which may train a first CSI feedback model. In addition, the RIC obtains the output of the trained first CSI reconfigurator. The inputs and outputs of the trained first CSI reconfigurator are used as training data in a third training dataset and may be transmitted to multiple terminal devices via a RAN node or directly to multiple terminal devices.

[0831] Optionally, step 910 may include a step in which a second device receives a first training dataset and first information from the first device. The first information describes the attributes of the first training dataset.

[0832] The first training dataset and the first information may be transmitted in the same message, or they may be transmitted in different methods or messages. For example, the first information may be transmitted using an air interface message, and the first training dataset may be transmitted using a message not defined in the protocol.

[0833] The attributes of the first training dataset may include at least one of the following: an identifier for the third training dataset, the identifier for the first training dataset, the value of T1, the positions of T1 training data in the third training dataset, the amount of training data in the third training dataset, the minimum amount of training data in the third training dataset that is sufficient for training, the time-domain attributes of T1 training data, quantization information for the first training dataset, and quantizer information corresponding to the third training dataset.

[0834] The value of T1 is the size of the first training dataset, specifically the amount of training data within the first training dataset.

[0835] For example, the location of T1 training data points in the third training dataset may be represented in the following way:

[0836] For example, the third training dataset may be divided into multiple subsets. The identifier is the set of each subset, and the identifier of a subset may indicate the location of the subset within the third training dataset. The identifier of the first training dataset, or the identifier of a subset contained in the first training dataset, may indicate the location of T1 training data within the third training dataset.

[0837] In another example, identifiers are set for all training data in a third training dataset. Each training data identifier may indicate the location of the training data within the third training dataset. T1 training data identifiers may indicate the location of T1 training data within the third training dataset.

[0838] In another example, consecutive identifiers are assigned to all the training data in the third training dataset. Each training data identifier may indicate the location of the training data in the first training dataset. Any identifier of any one of the T1 training data may indicate the location of T1 training data in the third training dataset. For example, the identifier of the first training data in T1 training data, or the identifier of the last training data in T1 training data, may indicate the location of T1 training data in the third training dataset.

[0839] The minimum amount of training data w sufficient for training in the third training dataset is the minimum amount of training data w required for model training. w is less than or equal to the amount of training data in the third training dataset. w is a positive integer. If the amount of training data received by the fourth device is greater than or equal to w, the dataset may be considered successfully received and model training can be performed.

[0840] For example, if T1 is greater than 1, the time-domain attributes of the T1 training data may include whether the T1 training data are continuous training data within the time domain, an identifier for the continuous training data within the time domain among the T1 training data, and at least one of the time interval or period or the terminal device's moving speed between the continuous training data within the time domain among the T1 training data.

[0841] Whether training data is continuous in the time domain indicates whether the training data is correlated in the time domain. For example, training data is channel information. If multiple training data are multiple pieces of channel information acquired by the same device through periodic measurements, then the multiple training data are continuous in the time domain.

[0842] An identifier for a training data point that is continuous in the time domain within a set of T1 training data points indicates a specific training data point that is continuous in the time domain within that set of T1 training data points.

[0843] The time-domain attributes of training data play a crucial role in the performance of AI models that include time-domain dimensions. AI models that include time-domain dimensions demonstrate that the model's inputs and outputs are correlated with time. For example, an AI model that includes time-domain dimensions may be an AI model used for CSI prediction or an AI model used for time-domain compression of channel information. For specific details, please refer to the explanation above. Further details will not be explained again here.

[0844] The quantization information for the first training dataset indicates the quantization mode of the training data within the first training dataset.

[0845] For example, the quantization information of the first training dataset may include at least one of the following: quantization precision in a feedback mode based on scalar quantization, basis selection information in a feedback mode based on codebook-based quantization, coefficient selection information in a feedback mode based on codebook-based quantization, coefficient quantization precision in a codebook-based quantization mode, or similar.

[0846] For example, the training data in the first training dataset may be channel information obtained through scalar quantization. In this case, the quantization information of the first training dataset may include quantization precision in a feedback mode based on scalar quantization.

[0847] In another example, the training data in the first training dataset may be channel information obtained through codebook-based quantization. In this case, the quantization information of the first training dataset may include at least one of the following: basis selection information for the training data, coefficient selection information for the training data, coefficient quantization precision for the training data, or the same.

[0848] For a detailed explanation of basis selection information, coefficient selection information, or coefficient quantization precision, please refer to the explanation above. Further details will not be explained here.

[0849] In a CSI feedback scenario, the terminal device and the network device must agree on the CSI quantization mode. When the first device transmits a training dataset, it may transmit quantizer information corresponding to the training dataset. The quantizer may be understood as a quantizer corresponding to the first CSI generator or a quantizer corresponding to the first CSI reconfigurator.

[0850] The quantizer information corresponding to the third training dataset may be a quantizer or an index of a quantizer.

[0851] Optionally, step 920 may include a step in which a third device receives a second training dataset and second information from the first device. The second information describes the attributes of the second training dataset.

[0852] The second training dataset and the second information may be transmitted in the same message. Alternatively, the second training dataset and the second information may be transmitted using different methods or messages. For example, the second information may be transmitted using an air interface message, and the second training dataset may be transmitted using a message not defined in the protocol.

[0853] The attributes of the second training dataset may include at least one of the following: an identifier for the third training dataset, an identifier for the second training dataset, a value of T2, the positions of T2 training data in the third training dataset, the amount of training data in the third training dataset, the minimum amount of training data in the third training dataset that is sufficient for training, the time-domain attributes of T2 training data, quantization information for the second training dataset, and quantizer information corresponding to the third training dataset.

[0854] The value of T2 is the size of the second training dataset, specifically the amount of training data within the second training dataset.

[0855] For a description of the attributes of the second training dataset, please refer to the previously mentioned description of the attributes of the first training dataset. To avoid repetition, we will not go into detail again here.

[0856] Optionally, method 900 further includes a step in which a fifth device transmits first request information to the first device. The first request information is used to request a fifth training dataset, the fifth training dataset containing T3 training data, where T3 is a positive integer. The fifth training dataset is a subset of the third training dataset.

[0857] The fifth device may be either the second device or the third device. Alternatively, the fifth device may be a different device from the second and third devices.

[0858] In other words, the fifth device may request specific training data from the first device.

[0859] For example, after receiving multiple training data from the third training dataset, the fifth device may discover that there is abnormally received training data and request the abnormally received training data from the first device (e.g., the fifth training dataset). For example, the fifth device may be the second device. After receiving the first training dataset, the fifth device may discover that there is abnormally received training data and request the fifth training dataset, i.e., the abnormally received training data from the first device. The fifth training dataset may be part or all of the first training dataset. In another example, the fifth device may be the third device. After receiving the second training dataset, the fifth device may discover that there is abnormally received training data and request the fifth training dataset, i.e., the abnormally received training data from the first device. The fifth training dataset may be part or all of the second training dataset. In another example, the fifth device may be any device other than the second and third devices, and the fifth training dataset may include part or all of the first training dataset, or part or all of the second training dataset, or may not include any training data from the first or second training dataset.

[0860] As described above, an identifier may be a set of training data within the third training dataset, and the identifier of each training data may indicate the location of the training data within the third training dataset. For example, the third training dataset contains a total of 1000 training data, and the identifiers of the 1000 training data are consecutive identifiers from 1 to 1000. The fifth device receives 500 training data with identifiers from 1 to 500, and 300 training data with identifiers from 701 to 1000. The fifth device may request 200 training data with identifiers from 501 to 700.

[0861] For example, after the fourth device has received multiple training data points from the third training dataset, if the amount of training data received is less than w, the fifth device may request unreceived training data from the first device in the third training dataset.

[0862] Optionally, the first request information may include at least one of the identifiers for the third training dataset, the fifth training dataset, the identifiers for T3 training data, or the identifiers for received training data.

[0863] For example, the identifiers for T3 training data may be the identifiers for each training data within T3 training data identifiers. In another example, if the identifiers for training data in a third training dataset are consecutive, the identifiers for T3 training data may be the identifier of the first training data within T3 training data identifiers and the value of T3. Alternatively, the identifiers for T3 training data may be the identifier of the last training data within T3 training data and the value of T3.

[0864] It can be understood that the names of the information used in some of the embodiments described above are merely examples and do not constitute a limitation on the scope of protection of the embodiments of this application.

[0865] It can be further understood that the formulas used in the embodiments of this application are merely illustrative examples and do not constitute limitations on the scope of protection of the embodiments of this application. In calculating the parameters described above, in order to satisfy the calculation results of the formulas described above, the calculations may be performed based on the formulas described above, or based on a variation of the formulas described above, or the calculations may be performed in any other way.

[0866] It can be further understood that some optional features in embodiments of the present invention may be independent of other features in some scenarios, or may be combined with other features in some scenarios. This is not limited to the present invention.

[0867] The solutions in the embodiments of this application may be appropriately combined for use, and it can be further understood that the definitions or descriptions of terms in the embodiments may be mutually referenced or explained in the embodiments. This is not limited to these definitions.

[0868] It can be further understood that the various numerical sequence numbers in the embodiments of this application do not signify an execution order, but are merely intended as distinctions for ease of explanation, and therefore should not constitute any limitation on the implementation process of the embodiments of this application.

[0869] In embodiments of the methods described above, it may be further understood that methods and operations implemented by a certain device may, alternatively, be implemented by components of that device (e.g., chips or circuits).

[0870] In correspondence with the method provided in the embodiments of the method described above, embodiments of the present application further provide a corresponding apparatus. The apparatus includes a corresponding module for performing the embodiments of the method described above. The module may be software, hardware, or a combination of software and hardware. It can be understood that the technical features described in the embodiments of the method are also applicable to the following embodiments of the apparatus.

[0871] Figure 14 is a diagram of a communication device 1700 according to one embodiment of the present application. The device 1700 includes a transceiver unit 1710 and a processing unit 1720. The transceiver unit 1710 may be configured to implement a corresponding communication function. The transceiver unit 1710 may also be referred to as a communication interface, communication unit, etc. The processing unit 1720 may be configured, for example, to configure resources to implement a corresponding processing function. The processing unit 1720 may also be referred to as a processor, etc.

[0872] Optionally, the device 1700 further includes a storage unit. The storage unit may be configured to store instructions and / or data. The processing unit 1720 may read instructions and / or data from the storage unit, thereby the device implementing the operation of the device or network element in the embodiments of the method described above.

[0873] The device 1700 may be a terminal device, or a communication device that can implement a communication method executed on the terminal device side, used within or in conjunction with a terminal device. Alternatively, the device 1700 may be a network device, or a communication device that can implement a communication method executed on the network device side, used within or in conjunction with a network device.

[0874] When the device 1700 is used within a terminal device, the device 1700 may implement steps or processes performed by the terminal device in the embodiments of the method described above. The transceiver unit 1710 may be configured to perform the transmit / receive related operations of the terminal device in the embodiments of the method described above. The processing unit 1720 may be configured to perform the processing related operations of the terminal device in the embodiments of the method described above.

[0875] When the device 1700 is used within a network device, the device 1700 may implement steps or processes performed by the network device in the embodiments of the method described above. The transceiver unit 1710 may be configured to perform the transmit / receive related operations of the network device in t...

Claims

1. A step of generating first channel information, wherein the first channel information comprises K segments, where K is an integer greater than 1, the length of each of the K segments is less than or equal to a first threshold, the type of the first channel information is ground truth channel information, and the first channel information is one of the following: channel response, channel eigenvector matrix, precoding matrix, reference signal received power, or signal-to-interference plus noise ratio; and A step of transmitting some or all of K uplink control information UCIs to a network device, where each of the K UCIs includes the K segments. A communication method that includes the following features.

2. The method according to claim 1, wherein the first threshold is less than or equal to the maximum code length supported by the UCI.

3. The first threshold is predetermined, or the method is Step 1: Receiving first instruction information from the network device, where the first instruction information indicates the first threshold The method according to claim 1 or 2, further comprising:

4. The method according to any one of claims 1 to 3, wherein the length of each of at least K-1 segments among the K segments is equal to the first threshold.

5. The aforementioned method, In the step of receiving a second instruction from the network device, the second instruction indicates the value of K. The method according to claim 1 or 2, further comprising:

6. The aforementioned method, The third instruction information is transmitted to the network device, where the third instruction information indicates the length of the K segments. The method according to any one of claims 1 to 5, further comprising:

7. The aforementioned method, The first step involves receiving first uplink resource configuration information from the network device, where the first uplink resource configuration information indicates the first uplink resource. The further step is to include the following: and to transmit some or all of the K uplink control information UCIs to the network device, The step of transmitting the K UCIs to the network device using the first uplink resource. Having, The method according to any one of claims 1 to 6.

8. The aforementioned method, The second uplink resource configuration information is received from the network device, where the second uplink resource configuration information indicates the second uplink resource. The further step is to include the following: and to transmit some or all of the K uplink control information UCIs to the network device, The step of transmitting a portion of the K UCIs to the network device by using the second uplink resource. Having, The method according to any one of claims 1 to 6.

9. The step of transmitting a portion of the K UCIs to the network device by using the second uplink resource is as follows: The step of transmitting a portion of the K UCIs and the fourth instruction information to the network device using the second uplink resource, wherein the fourth instruction information indicates at least one of the following: the total length of the untransmitted UCIs among the K UCIs, or whether the K UCIs include any untransmitted UCIs; or If a portion of the K UCIs includes the first UCI among the K UCIs, the fourth instruction information indicates at least one of the following: the total length of the first channel information, the total length of the untransmitted UCI among the K UCIs, or whether the K UCIs include the untransmitted UCI. including, The method according to claim 8.

10. The step of transmitting some or all of the K uplink control information UCIs to the network device is: The step of transmitting some or all of the K UCIs to the network device by using multiple uplink resources. Having; and the method, The fifth instruction information is received from the network device, where the fifth instruction information indicates the number of UCIs transmitted in each of the plurality of uplink resources. The method according to any one of claims 1 to 6, further comprising:

11. The step of transmitting some or all of the K uplink control information UCIs to the network device is: The step of transmitting some or all of the K UCIs to the network device by using multiple uplink resources. Having; and the method, The sixth instruction information is transmitted to the network device, where the sixth instruction information indicates the number of UCIs to be transmitted in each of the plurality of uplink resources. The method according to any one of claims 1 to 6, further comprising:

12. The step of transmitting some or all of the K uplink control information UCIs to the network device is: The step of transmitting some or all of the K UCIs to the network device by using multiple uplink resources. Having; and the method, The seventh instruction information is transmitted to the network device, where the seventh instruction information indicates that the multiple uplink resources correspond to the same first channel information. The method according to any one of claims 1 to 6, further comprising:

13. The step of transmitting some or all of the K uplink control information UCIs to the network device is: The step of transmitting a portion of the K UCIs to the network device. Having; and the method, The step of discarding the untransmitted UCIs among the K UCIs, where the timing starting from the transmission time of the first UCI among the K UCIs is greater than or equal to a second threshold. The method according to any one of claims 1 to 12, further comprising:

14. The step of transmitting some or all of the K uplink control information UCIs to the network device is: The step of transmitting a portion of the K UCIs to the network device. Having; and the method, The step of discarding the untransmitted UCIs among the K UCIs, where the timing starting from the transmission time of the second channel information is greater than or equal to the third threshold, and the first channel information is used to measure the accuracy of the second channel information. The method according to any one of claims 1 to 12, further comprising:

15. A step of generating third channel information based on a first feedback configuration, such that the total length of the third channel information is less than or equal to the maximum code length supported by the UCI, wherein the type of the third channel information is ground truth channel information; The first step is to transmit a first UCI to a network device, wherein the first UCI includes the third channel information; A step of generating fourth channel information based on a second feedback configuration, wherein the accuracy of the fourth channel information is lower than that of the third channel information, and the type of the fourth channel information is not ground truth channel information; and The second UCI is transmitted to the network device, wherein the second UCI includes the fourth channel information. A communication method that includes the following features.

16. The method according to claim 15, wherein the accuracy of the third channel information is greater than or equal to a fourth threshold.

17. The method according to claim 16, wherein the fourth threshold is predetermined, or the method further comprises the step of receiving an eighth instruction information from the network device, wherein the eighth instruction information indicates the fourth threshold.

18. The method according to any one of claims 15 to 17, wherein the constituent elements of the first feedback configuration include at least one of the following: the subband configuration of the third channel information, the layer configuration of the third channel information, the quantization accuracy configuration in a feedback mode based on scalar quantization, the base configuration in a feedback mode based on codebook-based quantization, or the non-zero coefficient configuration in a feedback mode based on codebook-based quantization.

19. The method according to any one of claims 15 to 18, wherein the parameter value of the first component in the component of the first feedback configuration is based on the range of the first component.

20. The method according to claim 19, wherein the range of the first component is predetermined, or the method further comprises the step of receiving a ninth instruction information from the network device, wherein the ninth instruction information indicates the range of the first component.

21. The first component includes at least one of the following: the subband configuration of the third channel information, the layer configuration of the third channel information, the quantization accuracy configuration in the feedback mode based on scalar quantization, the base configuration in the feedback mode based on codebook-based quantization, or the non-zero coefficient configuration in the feedback mode based on codebook-based quantization; The range of the subband configuration includes at least one of the following: the range of the number of subbands of the third channel information, the set of subband combinations of the third channel information, or the range of the subband granularity of the third channel information; The range of the layer configuration includes at least one of the range of values ​​for the number of layers of the third channel information, or the set of layer combinations of the third channel information; The range of the quantization accuracy configuration in the feedback mode based on scalar quantization includes the range of values ​​for the quantization accuracy in the feedback mode based on scalar quantization; The range of the base configuration in the codebook-based quantization feedback mode includes at least one of a range of values ​​indicating the number of bases of the third channel information in the codebook-based quantization feedback mode, or a set indicating the base combinations of the third channel information in the codebook-based quantization feedback mode; or The range of the non-zero coefficient configuration in the codebook-based quantization feedback mode includes at least one of the following: a range of values ​​indicating the number of non-zero coefficients of the third channel information in the codebook-based quantization feedback mode, or a range of values ​​indicating the non-zero coefficient quantization precision of the third channel information in the codebook-based quantization feedback mode. The method according to claim 19 or 20.

22. The method according to any one of claims 15 to 21, wherein the parameter values ​​of the plurality of components in the first feedback configuration are based on the correspondence between the parameter values ​​of the plurality of components in the first feedback configuration.

23. The method according to claim 22, wherein the parameter value of the second component in the first feedback configuration is based on the correspondence between the parameter value of the third component in the first feedback configuration and the parameter values ​​of the plurality of components in the first feedback configuration, and the third component and the second component belong to the plurality of components.

24. The method according to claim 22 or 23, wherein the correspondence between the parameter values ​​of the plurality of components is predetermined, or the method further comprises the step of receiving a tenth instruction information from the network device, wherein the tenth instruction information indicates the correspondence between the parameter values ​​of the plurality of components.

25. The method according to any one of claims 15 to 24, further comprising the step of transmitting eleventh instruction information to the network device, wherein the eleventh instruction information indicates parameter values ​​of some or all of the components in the first feedback configuration.

26. A step of generating a fifth channel information, wherein the type of the fifth channel information is ground truth channel information; and The step of transmitting the fifth channel information to a network device using upper-layer signaling. A communication method that includes the following features.

27. The method according to claim 26, wherein the upper layer signaling includes a first radio resource control RRC message.

28. The method according to claim 27, wherein the first RRC message is further used to transmit a sixth channel information, and the fifth channel information is used to measure the accuracy of the sixth channel information.

29. The method according to claim 27, wherein the first RRC message indicates a correspondence 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.

30. The step of sending a first training dataset to a second device, where the first training dataset contains T1 training data, where T1 is a positive integer; and The second training dataset is sent to a third device, where the second training dataset contains T2 training data, T2 is a positive integer, the second training dataset and the first training dataset are distinct subsets of the third training dataset, and the third training dataset is used for model training. A communication method that includes the following features.

31. The step of sending the first training dataset to the second device is: The first step involves transmitting the first training dataset and the first information to the second device, where the first information represents the attributes of the first training dataset. Having, The method according to claim 30.

32. The method according to claim 31, wherein the first training dataset and the first information are transmitted by different methods or messages.

33. The method according to claim 31 or 32, wherein the attributes of the first training dataset include at least one of the identifier of the third training dataset, the identifier of the first training dataset, the value of T1, the position of the T1 training data in the third training dataset, the amount of training data in the third training dataset, the minimum amount of training data in the third training dataset that is sufficient for training, the time-domain attributes of the T1 training data, the quantization information of the first training dataset, and the quantizer information corresponding to the third training dataset.

34. The aforementioned method, The first step involves receiving a first request from a fifth device, where the first request is used to request a fifth training dataset, the fifth training dataset containing T3 training data, where T3 is a positive integer, and the fifth training dataset being a subset of the third training dataset. The method according to any one of claims 30 to 33, further comprising:

35. The method according to claim 34, wherein the first request information includes at least one of the identifier of the third training dataset, the identifier of the fifth training dataset, the identifier of the T3 training data, or the identifier of the received training data.

36. The step of receiving some or all of K UCIs from a terminal device, where each of the K UCIs includes K segments of first channel information, where K is an integer greater than 1, the length of each of the K segments is less than or equal to a first threshold, the type of the first channel information is ground truth channel information, and the first channel information is one of the following: channel response, channel eigenvector matrix, precoding matrix, reference signal received power, or signal-to-interference plus noise ratio; and A step of obtaining segments included in part or all of the K UCIs based on part or all of the K UCIs. A communication method that includes the following features.

37. The method according to claim 36, wherein the first threshold is less than or equal to the maximum code length supported by the UCI.

38. The first threshold is predetermined, or the method is Step 1: Send the first instruction information to the terminal device, where the first instruction information indicates the first threshold The method according to claim 36 or 37, further comprising:

39. The method according to any one of claims 36 to 38, wherein the length of each of at least K-1 segments among the K segments is equal to the first threshold.

40. The aforementioned method, In the step of transmitting a second instruction to the terminal device, the second instruction indicates the value of K. The method according to claim 36 or 37, further comprising:

41. The aforementioned method, In the step of receiving a third instruction information from the terminal device, the third instruction information indicates the length of the K segments. The method according to any one of claims 36 to 40, further comprising:

42. The aforementioned method, Step 1: Transmit the first uplink resource configuration information to the terminal device, where the first uplink resource configuration information indicates the first uplink resource. The further step is to receive some or all of the K UCIs from the terminal device, The step of receiving the K UCIs from the terminal device by using the first uplink resource. Having, The method according to any one of claims 36 to 41.

43. The aforementioned method, The second uplink resource configuration information is transmitted to the terminal device, where the second uplink resource configuration information indicates the second uplink resource. The further step is to receive some or all of the K UCIs from the terminal device, The step of receiving a portion of the K UCIs from the terminal device by using the second uplink resource. Having, The method according to any one of claims 36 to 41.

44. The step of receiving a portion of the K UCIs from the terminal device by using the second uplink resource is as follows: The step of receiving a portion of the K UCIs and a fourth instruction information from the terminal device by using the second uplink resource, wherein the fourth instruction information indicates at least one of the following: the total length of the untransmitted UCIs among the K UCIs, or whether the K UCIs include any untransmitted UCIs; or If a portion of the K UCIs includes the first UCI among the K UCIs, the fourth instruction information indicates at least one of the following: the total length of the first channel information, the total length of the untransmitted UCI among the K UCIs, or whether the K UCIs include an untransmitted UCI. including, The method according to claim 43.

45. The step of receiving some or all of the K UCIs from the terminal device is: The step of receiving some or all of the K UCIs from the terminal device by using multiple uplink resources. Having; and the method, The fifth instruction information is transmitted to the terminal device, where the fifth instruction information indicates the number of UCIs transmitted in each of the plurality of uplink resources. The method according to any one of claims 36 to 41, further comprising:

46. The step of receiving some or all of the K UCIs from the terminal device is: The step of receiving some or all of the K UCIs from the terminal device by using multiple uplink resources. Having; and the method, The sixth instruction information is received from the terminal device, where the sixth instruction information indicates the number of UCIs transmitted in each of the plurality of uplink resources. The method according to any one of claims 36 to 41, further comprising:

47. The step of receiving some or all of the K UCIs from the terminal device is: The step of receiving some or all of the K UCIs from the terminal device by using multiple uplink resources. Having; and the method, In the step of receiving a seventh instruction information from the terminal device, the seventh instruction information indicates that the multiple uplink resources correspond to the same first channel information. The method according to any one of claims 36 to 41, further comprising:

48. The step of receiving a first UCI from a terminal device, wherein the first UCI includes third channel information, the third channel information corresponds to a first feedback configuration, and the type of the third channel information is ground truth channel information; and The second UCI is received from the terminal device, wherein the second UCI includes fourth channel information, the fourth channel information corresponds to the second feedback configuration, the accuracy of the fourth channel information is lower than that of the third channel information, and the type of the fourth channel information is not ground truth channel information. A communication method that includes the following features.

49. The method according to claim 48, wherein the accuracy of the third channel information is greater than or equal to a fourth threshold.

50. The fourth threshold is predetermined, or the method is The eighth instruction information is transmitted to the terminal device, where the eighth instruction information indicates the fourth threshold. The method according to claim 49, further comprising:

51. The method according to any one of claims 48 to 50, wherein the constituent elements of the first feedback configuration include at least one of the following: the subband configuration of the third channel information, the layer configuration of the third channel information, the quantization accuracy configuration in a feedback mode based on scalar quantization, the base configuration in a feedback mode based on codebook-based quantization, or the non-zero coefficient configuration in a feedback mode based on codebook-based quantization.

52. The method according to any one of claims 48 to 51, wherein the parameter value of the first component in the component of the first feedback configuration is based on the range of the first component.

53. The range of the first component is predetermined, or the method is In the step of transmitting the ninth instruction information to the terminal device, the ninth instruction information indicates the range of the first component item. The method according to claim 52, further comprising:

54. The first component includes at least one of the following: the subband configuration of the third channel information, the layer configuration of the third channel information, the quantization accuracy configuration in the feedback mode based on scalar quantization, the base configuration in the feedback mode based on codebook-based quantization, or the non-zero coefficient configuration in the feedback mode based on codebook-based quantization; The range of the subband configuration includes at least one of the following: the range of the number of subbands of the third channel information, the set of subband combinations of the third channel information, or the range of the subband granularity of the third channel information; The range of the layer configuration includes at least one of the range of values ​​for the number of layers of the third channel information, or the set of layer combinations of the third channel information; The range of the quantization accuracy configuration in the feedback mode based on scalar quantization includes the range of values ​​for the quantization accuracy in the feedback mode based on scalar quantization; The range of the base configuration in the codebook-based quantization feedback mode includes at least one of a range of values ​​indicating the number of bases of the third channel information in the codebook-based quantization feedback mode, or a set indicating the base combinations of the third channel information in the codebook-based quantization feedback mode; or The range of the non-zero coefficient configuration in the codebook-based quantization feedback mode includes at least one of the following: a range of values ​​indicating the number of non-zero coefficients of the third channel information in the codebook-based quantization feedback mode, or a range of values ​​indicating the non-zero coefficient quantization precision of the third channel information in the codebook-based quantization feedback mode. The method according to claim 52 or 53.

55. The method according to any one of claims 48 to 54, wherein the parameter values ​​of the plurality of components in the first feedback configuration are based on the correspondence between the parameter values ​​of the plurality of components in the first feedback configuration.

56. The method according to claim 55, wherein the parameter value of the second component in the first feedback configuration is based on the correspondence between the parameter value of the third component in the first feedback configuration and the parameter values ​​of the plurality of components in the first feedback configuration, and the third component and the second component belong to the plurality of components.

57. The correspondence between the parameter values ​​of the plurality of components is predetermined, or the method is In the step of transmitting the tenth instruction information to the terminal device, the tenth instruction information indicates the correspondence between the parameter values ​​of the plurality of component items. The method according to claim 55 or 56, further comprising:

58. The aforementioned method, In the step of receiving 11th instruction information from the terminal device, where the 11th instruction information indicates some or all of the parameter values ​​of the component items in the first feedback configuration. The method according to any one of claims 48 to 57, further comprising:

59. The process involves receiving a fifth channel information from a terminal device using upper-layer signaling, where the type of the fifth channel information is ground truth channel information; and A step in which data processing is performed based on the fifth channel information, or the fifth channel information is transferred. A communication method that includes the following features.

60. The method according to claim 59, wherein the upper-layer signaling includes a first RRC message.

61. The method according to claim 60, wherein the first RRC message is further used to transmit sixth channel information, and the fifth channel information is used to measure the accuracy of the sixth channel information.

62. The method according to claim 60, wherein the first RRC message indicates a correspondence 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.

63. Communication method, where the said method is The step of receiving a first training dataset from a first device, where the first training dataset includes T1 training data, where T1 is a positive integer; and The step of transmitting the first training dataset to a fourth device so that the fourth device can train a model based on the fourth training dataset, wherein the fourth training dataset includes at least the first training dataset and the second training dataset, the first and second training datasets being distinct subsets of the third training dataset, and the second training dataset containing T2 training data, where T2 is a positive integer. A communication method that includes the following features.

64. The step of receiving the first training dataset from the first device is: The first step involves receiving the first training dataset and the first information from the first device, where the first information represents the attributes of the first training dataset. It further possesses, The method according to claim 63.

65. The method according to claim 64, wherein the first training dataset and the first information are transmitted by different methods or messages.

66. The method according to claim 64 or 65, wherein the attributes of the first training dataset include at least one of the identifier of the third training dataset, the identifier of the first training dataset, the value of T1, the positions of the T1 training data in the third training dataset, the amount of training data in the third training dataset, the minimum amount of training data in the third training dataset that is sufficient for training, the time-domain attributes of the T1 training data, the quantization information of the first training dataset, and the quantizer information corresponding to the third training dataset.

67. The aforementioned method, The first step involves sending a first request information to the first device, where the first request message is used to request a fifth training dataset, the fifth training dataset containing T3 training data, where T3 is a positive integer, and the fifth training dataset being a subset of the third training dataset. The method according to any one of claims 63 to 66, further comprising:

68. The method according to claim 67, wherein the first request information includes at least one of the identifier of the third training dataset, the identifier of the fifth training dataset, the identifier of the T3 training data, or the identifier of the received training data.

69. A computer-readable storage medium, wherein the computer-readable storage medium comprises instructions, and when the instructions are executed by a processor, the method according to any one of claims 1 to 14 is implemented, the method according to any one of claims 15 to 25 is implemented, the method according to any one of claims 26 to 29 is implemented, the method according to any one of claims 30 to 35 is implemented, the method according to any one of claims 36 to 47 is implemented, the method according to any one of claims 48 to 58 is implemented, the method according to any one of claims 59 to 62 is implemented, or the method according to any one of claims 63 to 68 is implemented.

70. A communication device, wherein the communication device comprises a processor and a storage medium, the storage medium storing instructions, and when the instructions are executed by the processor, the communication device is capable of performing the method according to any one of claims 1 to 14, the method according to any one of claims 15 to 25, the method according to any one of claims 26 to 29, the method according to any one of claims 30 to 35, the method according to any one of claims 36 to 47, the method according to any one of claims 48 to 58, the method according to any one of claims 59 to 62, or the method according to any one of claims 63 to 68.

71. A communication device comprising a processor, wherein the processor is configured to process data and / or information to implement the method according to any one of claims 1 to 14, the method according to any one of claims 15 to 25, the method according to any one of claims 26 to 29, the method according to any one of claims 30 to 35, the method according to any one of claims 36 to 47, the method according to any one of claims 48 to 58, the method according to any one of claims 59 to 62, or the method according to any one of claims 63 to 68.

72. A chip comprising a processor, wherein the processor is configured to execute a program or instruction to implement the method according to any one of claims 1 to 14, the method according to any one of claims 15 to 25, the method according to any one of claims 26 to 29, the method according to any one of claims 30 to 35, the method according to any one of claims 36 to 47, the method according to any one of claims 48 to 58, the method according to any one of claims 59 to 62, or the method according to any one of claims 63 to 68.

73. A computer program product comprising computer program code or instructions, wherein when the computer program code or instructions are executed, the method according to any one of claims 1 to 14 is implemented, the method according to any one of claims 15 to 25 is implemented, the method according to any one of claims 26 to 29 is implemented, the method according to any one of claims 30 to 35 is implemented, the method according to any one of claims 36 to 47 is implemented, the method according to any one of claims 48 to 58 is implemented, the method according to any one of claims 59 to 62 is implemented, or the method according to any one of claims 63 to 68 is implemented.

74. A communication system comprising one or a combination of a communication device for performing the method according to any one of claims 1 to 14, a communication device for the method according to any one of claims 15 to 25, a communication device for the method according to any one of claims 26 to 29, a communication device for the method according to any one of claims 30 to 35, a communication device for the method according to any one of claims 36 to 47, a communication device for the method according to any one of claims 48 to 58, a communication device for the method according to any one of claims 59 to 62, or a communication device for the method according to any one of claims 63 to 68.

Images