Communication method, computer readable storage medium and communication device

Abstract

The invention discloses a communication method, a computer readable storage medium and a communication device, and relates to the technical field of communication. The method comprises the following steps: sending target channel information on an uplink resource, wherein the target channel information is obtained based on compression processing and / or first processing of a first model; wherein the first treatment comprises pre-treatment and / or post-treatment. Through the scheme provided by the invention, the first model deployed on the terminal equipment can be suitable for feedback of channel information of different sizes.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a communication method, a computer-readable storage medium, and a communication device. Background Art

[0002] The intelligence of wireless networks is an important evolutionary trend. Currently, the industry is widely discussing the introduction of intelligent models in communication systems to support communication between terminal devices and network devices. As a typical application, an intelligent model can be introduced in the application scenario of Channel State Information (CSI) feedback to support the compression and recovery of CSI, and can reduce the overhead of terminal device feedback of CSI on the premise that the network device obtains CSI. Summary of the Invention

[0003] One of the technical objectives of the embodiments of this application is to provide a communication method, a computer-readable storage medium, and a communication device, which can make the first model deployed on the terminal device applicable to the feedback of channel information of various different sizes.

[0004] In a first aspect, the embodiments of this application provide a communication method, and the method includes: sending target channel information on an uplink resource, where the target channel information is obtained based on compression processing and / or first processing of a first model, and the first processing includes: pre-processing and / or post-processing.

[0005] In the above solution, the size of the channel information input to the first model can be made to match the input size of the first model through pre-processing, and / or the channel information output by the first model can be made to match the uplink resource through post-processing. Therefore, the solution provided by the embodiments of this application can make the first model deployed on the terminal device applicable to the feedback of channel information of various different sizes.

[0006] Optionally, the method further includes: receiving first indication information, where the first indication information includes: indication information of the pre-processing method and / or indication information of the post-processing method.

[0007] Optionally, the method further includes: sending second indication information, where the second indication information includes: indication information of the pre-processing method and / or indication information of the post-processing method.

[0008] Optionally, the second indication information is carried in CSI part 1 of a CSI report.

[0009] Optionally, the pre-processing method and / or the post-processing method are predefined by a protocol.

[0010] Optionally, the pre - processing method and / or the post - processing method are determined based on the satisfied conditions.

[0011] Optionally, the conditions include at least one of the following: the computing resources of the terminal device are greater than or equal to a first threshold; the computing resources of the terminal device are less than a second threshold; the time interval between a first time unit and a second time unit is greater than or equal to a third threshold, where the first time unit refers to: the transmission time unit or the measurement time unit of the reference signal for measuring channel information, and the second time unit is the transmission time unit of the target channel information; the time interval between the first time unit and the second time unit is less than a fourth threshold.

[0012] Optionally, the pre - processing is any one or more of the following methods: performing adaptive processing on the first channel information to obtain the channel information input to the first model; truncating or padding the first channel information to obtain the channel information input to the first model; grouping the first channel information based on channel resources and / or antenna ports to obtain the channel information input to the first model, where the channel information input to the first model includes multiple second channel information, and the size of each second channel information is the input size; adjusting the size of the channel resources corresponding to the first channel information to obtain the channel information input to the first model.

[0013] Optionally, the post - processing is any one or more of the following methods: performing adaptive processing on the channel information output by the first model to obtain the target channel information, where the size of the target channel information matches the size of the uplink resources; truncating or padding the channel information output by the first model to obtain the target channel information; discarding at least one third channel information to obtain the target channel information, where the channel information output by the first model includes multiple third channel information.

[0014] Optionally, the post - processing is: discarding the at least one third channel information according to the priorities of the multiple third channel information.

[0015] Optionally, the priorities of the multiple third channel information are determined based on at least one of the following: the index information of the channel resources corresponding to the third channel information; the index information of the antenna ports corresponding to the third channel information; the index information of the layers corresponding to the third channel information.

[0016] In a second aspect, an embodiment of the present application provides a communication method, and the method includes: receiving target channel information on uplink resources, where the target channel information is obtained based on compression processing and / or first processing of a first model, and the first processing includes: pre - processing and / or post - processing.

[0017] Optionally, the method further includes: sending first indication information, where the first indication information includes indication information of the pre - processing manner and / or indication information of the post - processing manner.

[0018] Optionally, the method further includes: receiving second indication information, where the second indication information includes indication information of the pre - processing manner and / or indication information of the post - processing manner.

[0019] Optionally, the second indication information is carried in CSI part 1 of the channel state information CSI report.

[0020] Optionally, the pre - processing manner and / or the post - processing manner are predefined by a protocol.

[0021] Optionally, the pre - processing manner and / or the post - processing manner are determined based on the satisfied conditions.

[0022] Optionally, the conditions include at least one of the following: the computing resources of the terminal device are greater than or equal to a first threshold; the computing resources of the terminal device are less than a second threshold; the time interval between a first time unit and a second time unit is greater than or equal to a third threshold, where the first time unit refers to the transmission time unit or measurement time unit of the reference signal for measuring channel information, and the second time unit is the transmission time unit of the target channel information; the time interval between the first time unit and the second time unit is less than a fourth threshold.

[0023] Optionally, the pre - processing is any one or more of the following manners: adaptively processing the first channel information to obtain the channel information input to the first model; truncating or padding the first channel information to obtain the channel information input to the first model; grouping the first channel information based on channel resources and / or antenna ports to obtain the channel information input to the first model, where the channel information input to the first model includes multiple second channel information, and the size of each second channel information is the input size; adjusting the size of the channel resources corresponding to the first channel information to obtain the channel information input to the first model.

[0024] Optionally, the post - processing is any one or more of the following manners: adaptively processing the channel information output by the first model to obtain the target channel information, where the size of the target channel information matches the size of the uplink resources; truncating or padding the channel information output by the first model to obtain the target channel information; discarding at least one third channel information to obtain the target channel information, where the channel information output by the first model includes multiple third channel information.

[0025] Optionally, the post-processing is: discarding the at least one third channel information according to the priorities of the multiple third channel information.

[0026] Optionally, the priorities of the multiple third channel information are determined based on at least one of the following: the index information of the channel resources corresponding to the third channel information; the index information of the antenna ports corresponding to the third channel information; the index information of the layers corresponding to the third channel information.

[0027] In a third aspect, an embodiment of the present application provides a communication device, including: a sending module, configured to send target channel information on an uplink resource, where the target channel information is obtained based on compression processing and / or first processing of a first model, and where the first processing includes: pre-processing and / or post-processing.

[0028] In a fourth aspect, an embodiment of the present application provides a communication device, including: a receiving module, configured to send target channel information on an uplink resource, where the target channel information is obtained based on compression processing and / or first processing of a first model, and where the first processing includes: pre-processing and / or post-processing.

[0029] In a fifth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a computer, it executes the steps of the communication method provided in the first aspect or the second aspect.

[0030] In a sixth aspect, an embodiment of the present application further provides a communication device, including a memory and a processor. A computer program is stored on the memory and can run on the processor. When the processor runs the computer program, it executes the communication method provided in the first aspect above.

[0031] In a seventh aspect, an embodiment of the present application further provides a communication device, including a memory and a processor. A computer program is stored on the memory and can run on the processor. When the processor runs the computer program, it executes the communication method provided in the second aspect above.

[0032] In an eighth aspect, an embodiment of the present application provides a chip (or a communication device). A computer program is stored on the chip. When the computer program is executed by the chip, the method provided in the first aspect or the second aspect above is executed.

[0033] In a ninth aspect, an embodiment of the present application provides a chip module. A computer program is stored on the chip module. When the computer program is executed by the chip module, the method provided in the first aspect or the second aspect above is executed.

[0034] In a tenth aspect, an embodiment of the present application provides a computer program product, which includes a computer program. When the computer program runs on a computer, it causes the computer to execute the method provided in the first aspect or the second aspect above.

[0035] In an eleventh aspect, an embodiment of the present application provides a communication system, which includes a device for executing the communication method provided in the first aspect and a device for executing the communication method provided in the second aspect. Description of the Drawings

[0036] Figure 1 is a schematic diagram of an application scenario of a communication method in an embodiment of the present application;

[0037] Figure 2 is a schematic flowchart of a communication method in an embodiment of the present application;

[0038] Figure 3 is a schematic diagram of the generation process of a target channel information in an embodiment of the present application;

[0039] Figure 4 is a schematic diagram of signaling interaction of the first communication method in an embodiment of the present application;

[0040] Figure 5 is a schematic diagram of signaling interaction of the second communication method in an embodiment of the present application;

[0041] Figure 6 is a schematic diagram of signaling interaction of the third communication method in an embodiment of the present application;

[0042] Figure 7 is a schematic diagram of signaling interaction of the fourth communication method in an embodiment of the present application;

[0043] Figure 8 is a schematic structural diagram of a communication device in an embodiment of the present application;

[0044] Figure 9 is a schematic structural diagram of another communication device in an embodiment of the present application;

[0045] Figure 10 is a schematic hardware architecture diagram of a communication device in an embodiment of the present application. Detailed Embodiments

[0046] It should be understood that the "and / or" appearing in the embodiments of the present application is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article indicates that the associated objects before and after are in an "or" relationship.

[0047] In the embodiments of the present application, "at least one" means one or more. "Multiple" in the embodiments of the present application means two or more.

[0048] In the embodiments of the present application, the first, second, etc. descriptions are only used for indicating and distinguishing the described objects, without order, and do not represent a special limitation on the number of devices in the embodiments of the present application, and cannot constitute any limitation to the embodiments of the present application.

[0049] The communication systems applicable to the embodiments of the present application include, but are not limited to, long term evolution (LTE) systems, 5th-generation (5G) systems (such as New Radio (NR) systems), and future evolved systems or multiple communication convergence systems. Among them, the 5G system can be a non-standalone (NSA) 5G system or a standalone (SA) 5G system. The solutions of the embodiments of the present application can also be applicable to future new communication systems, for example, 6th generation (6G) communication systems, etc.

[0050] The present application mainly relates to the communication between terminal devices and network devices. The network device can be a network device in non-terrestrial networks (NTN) communication or a network device in a terrestrial network communication system.

[0051] First, some terms in the embodiments of the present application will be explained below.

[0052] 1. Terminal device

[0053] The terminal equipment in the embodiments of this application may refer to user equipment (UE), access terminal, user unit, user station, mobile station (MS), remote station, remote terminal, mobile device, user terminal, wireless communication device, user agent or user device, etc. For example, the terminal equipment may be a cellular phone, cordless phone, Session Initiation Protocol (SIP) phone, Wireless Local Loop (WLL) station, Personal Digital Assistant (PDA), a handheld device with wireless communication function, a computing device or other processing devices connected to a wireless modem, in-vehicle device, wearable device, a terminal in a future 5G network or a terminal equipment in a future evolved Public Land Mobile Network (PLMN). The embodiments of this application are not limited thereto. In some embodiments of this application, the terminal equipment may be an electronic device with data wireless transmission function. In some other embodiments of this application, the terminal equipment may also be a device with transceiver function, such as a chip system. The chip system may include a chip and may also include other discrete devices.

[0054] 2. Network equipment

[0055] The network device in the embodiments of the present application may refer to a device that provides wireless communication functions for terminal devices. The network device may be referred to as an access network device, such as a radio access network (RAN) device, or an access network network element, etc. Among them, the network device may support at least one wireless communication technology, such as LTE, NR, etc. For example, the network device may be a base station (BS) (which may also be referred to as a base station device), a base transceiver station (BTS), a Node B, an evolved Node B (eNB), a device that provides base station functions in a 5G network, such as a next generation node B (gNB) and a further evolved Node B (ng-eNB), where communication between the gNB and the terminal device uses NR technology, and communication between the ng-eNB and the terminal device uses Evolved Universal Terrestrial Radio Access (E-UTRA) technology. Both the gNB and the ng-eNB can be connected to the 5G core network. In a wireless local area network (WLAN), the device that provides base station functions is an access point (AP). The network device in the embodiments of the present application also includes devices that provide wireless communication functions in future new communication systems, etc. In some embodiments, the network device may also be a device having a function of providing wireless communication for terminal devices, such as a chip system. By way of example, the chip system may include a chip and may also include other discrete devices.

[0056] In some embodiments, the network device may refer to the centralized unit (CU) of the base station, or the distributed unit (DU) of the base station, or the CU control plane (CU-CP) of the base station, or the DU user plane (DU up) of the base station, etc.

[0057] 3. Channel Information

[0058] The channel information in the embodiments of the present application can be used to characterize channel characteristics or properties. For example, the channel information may be channel matrix information and / or CSI and / or channel feature vectors. Or, the channel information may also be a CSI report. Or, the channel information may also be the time-domain information, frequency-domain information, time-frequency domain information, or delay-doppler domain channel information of the channel, etc. The embodiments of the present application do not limit this.

[0059] Among them, the channel matrix information may refer to the information used to describe the channel matrix. For example, the channel matrix information may include at least one of the following: channel matrix H, equivalent channel matrix, precoding matrix W (the precoding matrix W can be derived from the channel matrix H), right singular vector V of the channel matrix H, square matrix H T Eigenvector v of H i , vectors associated with the channel matrix H (such as vectors under certain deformations of the channel matrix H), etc.

[0060] Among them, CSI may refer to the information used to describe the channel quality. For example, CSI describes the propagation process of wireless signals between the transmitter and the receiver, including the effects of distance, scattering, fading, etc. on the signals. For downlink transmission, CSI can be used for the terminal device to feedback the downlink channel quality to the network device, so that the network device can perform beam management, mobility management, etc. based on the CSI. The CSI sent by the terminal device to the network device can be carried in the CSI report. For example, CSI may also include at least one of the following: channel state information-reference signal resource indicator (CRI), rank indicator (RI), channel quality indicator (CQI), precoding matrix indicator (PMI), layer indicator (LI), layer 1-reference signal receiving power (L1-RSRP), layer 1-signal to interference plus noise ratio (L1-SINR), time-domain channel properties (TDCP), etc.

[0061] 4. First channel information

[0062] In the solution of the embodiment of the present application, the first channel information may refer to the channel information obtained by the terminal device through channel measurement using downlink reference signals. Among them, measurement can also be described as evaluation, detection, estimation, etc. Among them, the downlink reference signal may be at least one of the following: channel state information-reference signal (CSI-RS), synchronization signal block (SSB), physical broadcast channel demodulation reference signal (PBCH DMRS), positioning reference signal (PRS), etc.

[0063] Exemplarily, the terminal device may perform downlink channel measurement based on CSI-RS to obtain the first channel information.

[0064] 5. First Model

[0065] In the solution of the embodiment of the present application, the first model may refer to an artificial intelligence (AI) model or a machine learning (ML) model. Exemplarily, the model may include a supervised learning model, an unsupervised learning model, a reinforcement learning model, a neural network model, etc. In the scenario of channel information feedback, the first model may be used to compress the channel information.

[0066] The following will describe in detail the specific embodiments of the present application with reference to the accompanying drawings.

[0067] It should be noted that the actions performed by the network device in this article can be executed by the network device, devices in the network device (such as processors, chips), chips, etc., and the actions performed by the terminal device can be executed by the terminal device, devices in the terminal device (such as processors, chips), chips, etc. The present application does not make any restrictions. For the convenience of description, the embodiments provided in the present application are described below by taking the execution entities as the network device and the terminal device as examples.

[0068] Refer to Figure 1 , Figure 1 is a schematic diagram of an application scenario of a communication method in an embodiment of the present application.

[0069] As shown Figure 1 in the figure, a first model 11 may be deployed in the terminal device. The terminal device may perform channel estimation based on the downlink reference signal, and then use the first model 11 to compress the estimated CSI / channel information. Among them, the first model 11 may also be referred to as a compression model, and the first model 11 may be used to perform compression processing on the CSI / channel information. Further, the terminal device may feedback the compressed CSI to the network device. A second model 12 corresponding to the first model 11 may be deployed in the network device. After receiving the compressed CSI, the network device may use the second model 12 to recover the compressed CSI. Among them, the second model 12 may also be referred to as a recovery model, and the second model 12 may be used to perform recovery processing on the compressed CSI. In this way, both the overhead of the terminal device for feedbacking CSI can be effectively reduced, and it can be ensured that the network device can obtain high-precision CSI. Among them, the above 12 may also be an AI model or an ML model.

[0070] In the solution of the embodiment of the present application, considering that the sizes of the input data and output data of the AI model or ML model are usually fixed, however, in different situations, the size of the channel information estimated by the terminal device may be inconsistent with the size of the input data of the first model 11, or the output data of the first model 11 does not match the uplink resource for channel information feedback, etc.

[0071] In view of this, the embodiment of the present application provides a communication method. In the solution of the embodiment of the present application, target channel information is sent on the uplink resource, and the target channel information is obtained based on the compression processing of the first model and the first processing. Among them, the first processing includes: pre-processing and / or post-processing. Specifically, the pre-processing may be used to make the channel information input into the first model adapt to the input size of the first model, and / or, the post-processing may be used to make the size of the channel information output by the first model match the size of the uplink resource. Thus, in the solution of the embodiment of the present application, the size of the channel information input into the first model is made to match the input size of the first model through pre-processing, and / or, the channel information output by the first model is made to match the uplink resource through post-processing. Therefore, the solution provided by the embodiment of the present application can make the first model deployed on the terminal device applicable to the feedback of various different sizes of channel information.

[0072] Embodiment 1

[0073] Referring to Figure 2 , Figure 2 is a schematic flowchart of a communication method in the embodiment of the present application. Figure 2 The method shown can be applied to the terminal device. Figure 2 The method shown may include S21.

[0074] S21: Transmit the target channel information on the uplink resource, where the target channel information is obtained based on the compression processing and the first processing of the first model; wherein, the first processing includes: pre-processing and / or post-processing.

[0075] Wherein, the pre-processing can be used to adapt the channel information input to the first model to the input size of the first model, and / or, the post-processing can be used to match the size of the channel information output by the first model with the size of the uplink resource.

[0076] Specifically, the terminal device can transmit the target channel information to the network device on the uplink resource. It should be noted that the "target channel information" in the embodiments of the present application refers to the channel information transmitted or fed back by the terminal device to the network device, and the uplink resource refers to the uplink resource used to carry the target channel information, and the uplink resource can be a resource pre-configured by the network device and / or a resource scheduled and configured by the network device.

[0077] Wherein, the target channel information can be obtained by performing compression processing and the first processing on the first channel information, and the first processing includes pre-processing and / or post-processing.

[0078] Refer to Figure 3 , Figure 3 is a schematic diagram of the generation process of a kind of target channel information in the embodiments of the present application. The following combines Figure 2 and Figure 3 to give an exemplary description of the pre-processing and post-processing in the embodiments of the present application.

[0079] Considering the diversity of parameter configurations, the size of the first channel information estimated by the terminal device is variable, but the input size of the first model is fixed. Therefore, in the solution of the embodiments of the present application, if the size of the first channel information is inconsistent with the input size of the first model, pre-processing needs to be performed on the first channel information so that the size of the channel information input to the first model is adapted to the input size of the first model. Wherein, the size of the channel information input to the first model being adapted to the input size of the first model can mean that the size of the channel information input to the first model is the same as the input size of the first model.

[0080] It should be noted that the pre-processing is an optional step.

[0081] It should also be noted that the input size of the first model in the embodiments of the present application may refer to at least one of the following: the number of rows and / or columns of the input matrix of the first model, the data volume of the input data of the first model, the length of the input data of the first model, the number of channel resources corresponding to the input data of the first model, the number of antenna ports corresponding to the input data of the first model, the time domain width corresponding to the input data of the first model, the frequency domain width corresponding to the input data of the first model, the rank corresponding to the input data of the first model, the number of data streams corresponding to the input data of the first model, the number of layers corresponding to the input data of the first model, etc., the number of data samples of the input data of the first model, the number of bits / bit bytes of the input data of the first model, etc. It can be understood that a data sample can be a floating point, or a fixed point, or a matrix, or a tensor, or a vector, or a scalar, etc. It can be understood that a data sample can be the channel information corresponding to a channel resource. It should be noted that the above is only an exemplary description of the "data sample", and the "data sample" can also adopt other definitions or interpretations, and the definition of the "data sample" in this article is not limited. For example, the "data sample" can be adapted and modified based on the modification or change of the protocol, or the "data sample" can be adapted and modified based on the definition, content or interpretation of the "channel information", and the modified content is also within the scope of protection required by the present application.

[0082] It should be noted that the above is only an exemplary description of the "input size of the first model", and the "input size of the first model" can also adopt other definitions or interpretations. The embodiments of the present application do not limit the meaning of the "input size of the first model". For example, the "input size of the first model" can be adapted and modified based on the modification or change of the protocol, or the "input size of the first model" can be adapted and modified based on the definition, content or interpretation of the "channel information", and the modified content is also within the scope of protection required by the present application.

[0083] Among them, the channel resources in this article can be subcarriers, or resource blocks, or subbands, or antenna ports, etc., and this embodiment does not limit this. The antenna ports in this article can refer to transmit antenna ports and / or receive antenna ports.

[0084] In the solution of this embodiment, the terminal device can perform preprocessing in any one of the manners 1 to 4, but is not limited to the manners described below. That is, the preprocessing can at least have the following several optional manners or types, but is not limited thereto.

[0085] Manner 1: Adaptive processing.

[0086] Specifically, the terminal device can adaptively process the first channel information to obtain the channel information input into the first model. That is to say, through adaptive processing, the first channel information is transformed into channel information that conforms to the input size of the first model.

[0087] In one example, the quantization granularity of the first channel information can be adaptively processed so that the size of the processed channel information is consistent with the input size of the first model.

[0088] Method 2: Truncation processing or padding processing.

[0089] Specifically, if the size of the first channel information is greater than the input size of the first model, the terminal device can truncate the first channel information so that the size of the truncated first information is consistent with the input size of the first model.

[0090] If the size of the first channel information is less than the input size of the first model, the terminal device can pad the first channel information so that the size of the padded first information is consistent with the input size of the first model. Among them, the padding method can be zero padding.

[0091] Method 3: Grouping processing.

[0092] In the first implementation manner, the terminal device can group the first channel information based on channel resources to obtain the channel information input into the first model. Among them, the channel information input into the first model includes one or more second channel information, and the size of each second channel information is the input size of the first model. That is to say, the terminal device can group the first channel information according to channel resources to obtain one or more second channel information. The number of second channel information can depend on the number of channel resources corresponding to the first channel information and the number of channel resources corresponding to the input data of the first model.

[0093] Specifically, the terminal device can group the first channel information according to channel resources. Specifically, assume that the first channel information corresponds to M channel resources, that is, the first channel information contains the channel information of M channel resources, and the number of channel resources corresponding to the input data of the first model is X, then the first channel information can be divided into second channel information, where represents rounding up, and both M and X are positive integers. In one example, M can be greater than X, and the channel resources corresponding to each second channel information are a part of the channel resources corresponding to the first channel information, and the channel resources corresponding to different second channel information are different. In other examples, M can also be equal to X, or M can be less than X. In the case where M is less than X or M is equal to X, the number of second channel information can be 1.

[0094] In the second implementation, the terminal device may group the first channel information based on antenna ports to obtain the channel information input to the first model. The channel information input to the first model includes one or more second channel information, and the size of each second channel information is the input size of the first model. That is, the terminal device may group the first channel information according to antenna ports to obtain one or more second channel information. The number of second channel information may depend on the number of antenna ports corresponding to the first channel information and the number of antenna ports corresponding to the input data of the first model.

[0095] Specifically, the terminal device may group the first channel information according to antenna ports. Specifically, assume that the first channel information corresponds to N antenna ports, that is, the first channel information includes the channel information of N antenna ports, and the number of antenna ports corresponding to the input data of the first model is Y. Then the first channel information may be divided into second channel information, where represents rounding up, and both N and Y are positive integers. In one example, N may be greater than Y. Each second channel information corresponds to a part of the antenna ports corresponding to the first channel information, and the antenna ports corresponding to different second channel information are different. In other examples, N may also be equal to Y, or N may be less than Y. When N is less than Y or N is equal to Y, the number of second channel information may be 1.

[0096] In the third implementation, the terminal device may group the first channel information based on channel resources and antenna ports to obtain the channel information input to the first model. The channel information input to the first model includes one or more second channel information, and the size of each second channel information is the input size of the first model. The number of second channel information may depend on the number of channel resources corresponding to the first channel information, the number of antenna ports corresponding to the first channel information, the number of channel resources corresponding to the input data of the first model, and the number of antenna ports corresponding to the input data of the first model.

[0097] Specifically, the terminal device may group the first channel information according to antenna ports and channel resources. Specifically, assume that the first channel information corresponds to M channel resources and N antenna ports, that is, the first channel information includes the channel information of N antenna ports and M channel resources, and the number of channel resources corresponding to the input data of the first model is X' and the number of antenna ports corresponding to the input data of the first model is Y'. Then the first channel information may be divided into second channel information. Among them, M, N, X', and Y' are all positive integers. M may be greater than X' or M may be equal to X' or M may be less than X', and / or N may be greater than Y' or N may be equal to Y' or N may be less than Y'.

[0098] Method 4: Adjust the size of the channel resources.

[0099] Specifically, the terminal device can adjust the size of the channel resources corresponding to the first channel information to obtain the channel information input into the first model. That is to say, by adjusting the size of the channel resources corresponding to the first channel information, the first channel information is converted into channel information that conforms to the input size of the first model.

[0100] For example, assuming that the bandwidth of a single channel resource corresponding to the first channel information is the first width, the terminal device can adjust the bandwidth of the single channel resource to the second width so that the number of channel resources corresponding to the first channel information is the same as the number of channel resources corresponding to the input data of the first model.

[0101] In addition, considering the diversity of resource allocation, the size of the uplink resources for feedback channel information is variable, but the output size of the first model is fixed. Therefore, in the solution of the embodiments of the present application, if the size of the channel information output by the first model does not match the size of the uplink resources, post-processing needs to be performed on the channel information output by the first model so that the size of the target channel information obtained through the post-processing matches the size of the uplink resources. Among them, the fact that the size of the target channel information matches the size of the uplink resources may mean that the uplink resources can accommodate the target channel information.

[0102] It should be noted that the post-processing is an optional step.

[0103] It should also be noted that the output size of the first model may refer to at least one of the following: the number of rows and / or columns of the output matrix of the first model, the amount of data of the output data of the first model, the length of the output data of the first model, the number of channel resources corresponding to the output data of the first model, the number of antenna ports corresponding to the output data of the first model, the time domain width corresponding to the output data of the first model, the frequency domain width corresponding to the output data of the first model, the rank corresponding to the output data of the first model, the number of data streams corresponding to the output data of the first model, the number of layers corresponding to the output data of the first model, etc., the number of data samples of the output data of the first model, the number of bits / bit bytes of the output data of the first model, etc. It can be understood that a data sample can be a floating point, or a fixed point, or a matrix, or a tensor, or a vector, or a scalar, etc. It can be understood that a data sample can correspond to the channel information corresponding to a channel resource. It should be noted that the above is only an exemplary description of the "data sample", and the "data sample" can also adopt other definitions or interpretations. The definition of the "data sample" in this article is not limited. For example, the "data sample" can be adapted and modified based on the modification or change of the protocol, or the "data sample" can be adapted and modified based on the definition, content or interpretation of the "channel information", and the modified content is also within the scope of protection required by this application.

[0104] It should be noted that the above is only an exemplary description of the "output size of the first model", and the "output size of the first model" can also adopt other definitions or interpretations. The embodiments of this application do not limit the meaning of the "output size of the first model". For example, the "output size of the first model" can be adapted and modified based on the modification or change of the protocol, or the "output size of the first model" can be adapted and modified based on the definition, content or interpretation of the "channel information", and the modified content is also within the scope of protection required by this application.

[0105] In the solution of this embodiment, the terminal device can perform post-processing in any one of manners a to c, but is not limited to the manners described below.

[0106] Manner a: Adaptive processing.

[0107] Specifically, the terminal device can perform adaptive processing on the channel information output by the first model to obtain the target channel information.

[0108] In one example, the quantization granularity of the channel information output by the first model can be adaptively processed to obtain the target channel information.

[0109] Manner b: Truncation processing or padding processing.

[0110] Specifically, if the size of the channel information output by the first model is greater than the data volume that the uplink resource can carry, the terminal device may truncate the channel information output by the first model to obtain the target channel information. If the size of the channel information output by the first model is less than the data volume that the uplink resource can carry, the terminal device may pad the channel information output by the first model to obtain the target channel information. Among them, the padding method may be to fill with zeros.

[0111] Method c: Discarding process.

[0112] Specifically, if the size of the channel information output by the first model is greater than the data volume that the uplink resource can carry, the terminal device may discard at least a part of the channel information output by the first model to obtain the target channel information.

[0113] It should be noted that different from the truncation process in the above text, the discarding process may selectively discard a part of the channel information. For example, the discarding process may be performed based on the priority of the channel information.

[0114] In an example, in the pre-processing, the terminal device performs grouping processing on the first channel information to obtain a plurality of second channel information. Assuming that the number of the second channel information is K, and the K second channel information are respectively input into the first model 11, K third channel information can be obtained. That is, the channel information output by the first model 11 may include K third channel information, and the third channel information and the second channel information may be in one-to-one correspondence. K is a positive integer greater than 1. In the post-processing, at least one of the third channel information may be discarded to obtain the target channel information. For example, the discarding may be performed according to the priority of the third channel information. For example, the lower the priority, the earlier it is discarded.

[0115] The priority of the third channel information is described exemplarily below. Among them, the priority of the third channel information may be the same as the priority of the second channel information corresponding to the third channel information.

[0116] Specifically, the priority of the third channel information may be determined based on at least one of the following: the index information of the channel resource corresponding to the third channel information, the index information of the antenna port corresponding to the third channel information. Among them, the channel resource corresponding to the third channel information may be the same as the channel resource corresponding to the second channel information; the antenna port corresponding to the third channel information may be the same as the antenna port corresponding to the second channel information.

[0117] In the first example, the priority of the third channel information can be determined only based on the index information of the channel resources corresponding to the third channel information. Among them, the smaller the index information of the channel resources, the higher the priority of the third channel information, or the larger the index information of the channel resources, the higher the priority of the third channel information.

[0118] In the second example, the priority of the third channel information can be determined only based on the index information of the antenna ports corresponding to the third channel information. Among them, the smaller the index information of the antenna ports, the higher the priority of the third channel information, or the larger the index information of the antenna ports, the higher the priority of the third channel information.

[0119] In the third example, the priority of the third channel information can be determined based on the index information of the channel resources and the index information of the antenna ports corresponding to the third channel information.

[0120] Exemplarily, the priority of the third channel information can be determined by using Equation (1) or Equation (2):

[0121] f(i, j) = P × i + j, Equation (1)

[0122] f(i, j) = Q × j + i, Equation (2)

[0123] Among them, f(i, j) represents the priority of the third channel information, i represents the index information of the channel resources corresponding to the third channel information, j represents the index information of the antenna ports corresponding to the third channel information, Q represents the number of third channel information corresponding to the channel resource dimension when grouping the first channel information based on the channel resources, and P represents the number of third channel information corresponding to the antenna port dimension when grouping the first channel information based on the antenna ports. Specifically, Q in Equation (1) or Equation (2) can be the or P can be the or

[0124] In one embodiment, the first model can be a hierarchical processing model, and the priority of the third channel information can be determined by the method described above. Or, when the first model is a hierarchical processing model, the priority of the third channel information can also be determined based on the index information of the layer corresponding to the third channel information. Among them, the index information of the layer corresponding to the third channel information can be the same as the index information of the layer corresponding to the second channel information.

[0125] In the fourth example, the priority of the third channel information can be determined only based on the index information of the layer corresponding to the third channel information. Among them, the smaller the index information of the layer, the higher the priority of the third channel information, or the larger the index information of the layer, the higher the priority of the third channel information.

[0126] In the fifth example, the priority of the third channel information can be determined based on the index information of the layer corresponding to the third channel information and the index information of the channel resources.

[0127] Exemplarily, the priority of the third channel information can be determined using Equation (3) or Equation (4):

[0128] f(i, l) = P × i + l, Equation (3)

[0129] f(i, l) = R × l + i, Equation (4)

[0130] In Equation (3) or Equation (4), f(i, l) represents the priority of the third channel information, l represents the index information of the channel resources corresponding to the third channel information, i represents the index information of the layer corresponding to the third channel information, R represents the total number of layers corresponding to the first channel information, or R represents the rank of the first channel information. P represents the number of third channel information corresponding to the channel resource dimension when the first channel information is grouped based on the channel resources. Specifically, P in Equation (3) can be the or

[0131] In the sixth example, the priority of the third channel information can be determined based on the index information of the layer corresponding to the third channel information and the index information of the antenna ports.

[0132] Exemplarily, the priority of the third channel information can be determined using Equation (5) or Equation (6):

[0133] f(j, l) = Q × j + l, Equation (5)

[0134] f(j, l) = R × l + j, Equation (6)

[0135] In Equation (5) or Equation (6), f(j, l) represents the priority of the third channel information, l represents the index information of the antenna ports corresponding to the third channel information, j represents the index information of the layer corresponding to the third channel information, R represents the total number of layers corresponding to the first channel information, or R represents the rank of the first channel information. Q represents the number of third channel information corresponding to the antenna port dimension when the first channel information is grouped based on the antenna ports. Specifically, Q in Equation (5) can be the or

[0136] In the sixth example, the priority of the third channel information can be determined based on the index information of the layer corresponding to the third channel information, the index information of the channel resources, and the index information of the antenna ports.

[0137] Exemplarily, the priority of the third channel information can be determined by Equation (7):

[0138] f(i,j,l) = R×Q×i + R×j + l, Equation (7)

[0139] In Equation (7), f(i,j,l) represents the priority of the third channel information, i represents the index information of the channel resource corresponding to the third channel information, j represents the index information of the antenna port corresponding to the third channel information, l represents the index information of the layer corresponding to the third channel information, R represents the total number of layers corresponding to the first channel information, or R represents the rank of the first channel information. Q represents the number of third channel information corresponding to the antenna port dimension when the first channel information is grouped based on the antenna port. Specifically, Q in Equation (7) can be the or

[0140] As described above, in the solution of Embodiment 1, through preprocessing, the size of the channel information input to the first model is made to match the input size of the first model, and / or through postprocessing, the channel information output by the first model is made to match the uplink resources. Thus, the first model deployed on the terminal device is applicable to the feedback of channel information of various different sizes.

[0141] It should be noted that in specific implementation, the preprocessing and / or postprocessing performed by the terminal device (that is, the preprocessing method and the postprocessing method adopted by the terminal device) can be defined by the protocol, or can be indicated by the network device, or can be determined by the terminal device itself.

[0142] For more content about Embodiment 1, reference can be made to the relevant descriptions of other embodiments in this article, which will not be elaborated here.

[0143] Embodiment 2

[0144] Refer to Figure 4 , Figure 4 which is a signaling interaction diagram of the first communication method in the embodiments of the present application. As Figure 4 shown, Figure 4 the method shown can include S41 and S42.

[0145] S41, the network device sends first indication information to the terminal device, and the first indication information includes indication information of the preprocessing method and / or indication information of the postprocessing method. Correspondingly, the terminal device receives the first indication information.

[0146] In a specific implementation, the first indication information may be carried in downlink control information, medium access control-control element (MAC CE) signaling, or radio resource control (RRC), but is not limited thereto.

[0147] Specifically, S41 may be executed in a functionality identification process or in a model identification process, but is not limited thereto. In the solution of the embodiments of the present application, the first indication information may be used to indicate to the terminal device which type of pre-processing and / or which type of post-processing to perform, and the terminal device may determine the pre-processing method and / or the post-processing method to be used when feeding back subsequent channel information based on the first indication information.

[0148] It should be noted that the "pre-processing method" in the embodiments of the present application may also be referred to as the "pre-processing type", and the "post-processing method" may also be referred to as the "post-processing type".

[0149] It should also be noted that S41 is an optional step.

[0150] S42, the terminal device sends the target channel information to the network device on the uplink resource. Correspondingly, the network device receives the target channel information on the uplink resource.

[0151] As described above, in the solution of Embodiment 2, the network device indicates the pre-processing method and / or the post-processing method to the terminal device through the first indication information, the terminal device determines the pre-processing method and / or the post-processing method based on the indication of the network device, and the pre-processing method and / or the post-processing method adopted by the terminal device are visible to the network device. Therefore, after receiving the target channel information, the network device can process the target channel information using the corresponding processing method to achieve the restoration of the channel information.

[0152] For more content of Embodiment 2, reference may be made to the relevant descriptions of other embodiments in this article, which will not be elaborated herein.

[0153] Embodiment 3

[0154] Refer to Figure 5 , Figure 5 which is a signaling interaction diagram of the second communication method in the embodiments of the present application. As Figure 5 shown, Figure 5 the method shown may include S51 and S52.

[0155] S51. The terminal device sends second indication information to the network device. The second indication information includes indication information on the pre - processing method and / or indication information on the post - processing method. Correspondingly, the network device receives the second indication information.

[0156] Among them, the terminal device may execute S21 before generating the target channel information, or the terminal device may also execute S21 after generating the target channel information. This embodiment does not limit this.

[0157] In the solution of the embodiment of the present application, the second indication information can be used to indicate to the network device which pre - processing method the terminal device executes and / or to indicate to the network device which post - processing method the terminal device executes.

[0158] It should be noted that S51 is an optional step.

[0159] S52. The terminal device sends the target channel information to the network device on the uplink resource. Correspondingly, the network device receives the target channel information on the uplink resource.

[0160] It should be noted that this article does not limit the execution order of S51 and S52. S51 can be executed before S52. Or, S51 can also be executed after S52. Or, S51 and S52 can also be executed simultaneously. For example, both the first indication information and the target channel information can be carried in the CSI report. In one example, the second indication information is carried in CSI part 1 of the CSI report.

[0161] As above, in the solution of Embodiment 3, the terminal device indicates the pre - processing method and / or the post - processing method it adopts to the network device through the second indication information. The network device learns the pre - processing method and / or the post - processing method adopted by the terminal device based on the second indication information. Thus, the pre - processing method and the post - processing method adopted by the terminal device are visible to the network device. After receiving the target channel information, the network device can use the corresponding processing method to recover the target channel information.

[0162] For more content about Embodiment 3, reference can be made to the relevant descriptions of other embodiments in this article, which will not be elaborated here.

[0163] Embodiment 4

[0164] Refer to Figure 6 , Figure 6 which is a signaling interaction diagram of the third communication method in the embodiment of the present application. As Figure 6 shown, Figure 6 the method shown can include S61 and S62.

[0165] S61. The terminal device interacts with the network device to confirm the pre - processing method and / or the post - processing method adopted by the terminal device.

[0166] Exemplarily, S61 can be executed during the function confirmation process of the first model or during the model confirmation process of the first model.

[0167] As a possible implementation, the network device can send the first indication information to the terminal device. In response to receiving the first indication information, the terminal device can send a response to the first indication information to the network device. Thus, the terminal device and the network device reach an agreement on the pre - processing method and / or the post - processing method adopted by the terminal device.

[0168] As another possible implementation, the terminal device can send the second indication information to the network device, and the network device can send a response to the second indication information to the terminal device. For example, the network device can send a response to the second indication information to indicate the confirmation of the pre - processing method and / or the post - processing method indicated by the second indication information. For another example, the network device can indicate the pre - processing method and / or the post - processing method in the response to the second indication information, and the pre - processing method and / or the post - processing method indicated by the response to the second indication information is different from that indicated by the second indication information. After receiving the response to the second indication information, the terminal device can take the content indicated by the response to the second indication information as the standard. Thus, the terminal device and the network device reach an agreement on the pre - processing method and / or the post - processing method adopted by the terminal device.

[0169] S61 can be executed before S62. After executing S61, the terminal device can determine the pre - processing method and / or the post - processing method to be adopted when feeding back subsequent channel information.

[0170] It should be noted that S61 is an optional step.

[0171] S62. The terminal device sends target channel information to the network device on the uplink resource. Correspondingly, the network device receives the target channel information on the uplink resource.

[0172] Thus, in the solution of Embodiment 4, the terminal device and the network device reach an agreement on the pre - processing method and / or the post - processing method adopted by the terminal device through interaction. Thus, the pre - processing method and / or the post - processing method adopted by the terminal device is visible to the network device. After receiving the target channel information, the network device can use the corresponding processing method to recover the target channel information.

[0173] For more content about Embodiment 4, reference can be made to the relevant descriptions of other embodiments in this article, which will not be elaborated here.

[0174] Example 5

[0175] Refer to Figure 7 , Figure 7 which is a signaling interaction diagram of the fourth communication method in the embodiments of the present application. As Figure 7 shown Figure 7 the method shown may include S71 and S72.

[0176] S71, the terminal device determines the pre - processing method and / or the post - processing method.

[0177] As a possible implementation, the pre - processing method and / or the post - processing method adopted by the terminal device may be defined by the protocol. Thus, the terminal device can determine the pre - processing method and / or the post - processing method adopted when feeding back channel information based on the protocol agreement.

[0178] As another possible implementation, the terminal device can determine the pre - processing method and / or the post - processing method based on conditions (or, which can be called events).

[0179] In one example, the conditions for determining the pre - processing method and / or the post - processing method may include at least one of the following: the computing resources of the terminal device are greater than or equal to the first threshold, and the computing resources of the terminal device are less than the second threshold. Wherein, the first threshold is greater than or equal to the second threshold. Thus, the terminal device can determine the pre - processing and / or post - processing adopted based on its own computing resources. Wherein, the first threshold and / or the second threshold may be configured by the network device or defined by the protocol.

[0180] For example, if the computing resources of the terminal device are less than the second threshold (that is, the computing resources of the terminal device are limited), the pre - processing method adopted by the terminal device may be truncation processing or padding processing, and / or the post - processing method may be discard processing. If the computing resources of the terminal device are greater than the first threshold (that is, the computing resources of the terminal device are sufficient), the pre - processing method adopted by the terminal device may be adaptive processing, and / or the post - processing method adopted by the terminal device may be adaptive processing.

[0181] In another example, the conditions for determining the pre - processing method and / or the post - processing method may include at least one of the following: the time interval between the first time unit and the second time unit is greater than or equal to the third threshold, and the time interval between the first time unit and the second time unit is less than the fourth threshold. Wherein, the third threshold and / or the fourth threshold may be configured by the network device or defined by the protocol.

[0182] Among them, the first time unit refers to the transmission time unit or measurement time unit of the reference signal for measuring channel information, and the second time unit is the transmission time unit of the target channel information. It should be noted that the time unit in this article can be a symbol, a slot, a frame, a sub-frame, etc. in this article, but is not limited thereto.

[0183] For example, if the time interval between the first time unit and the second time unit is less than the fourth threshold, the pre-processing method adopted by the terminal device can be truncation processing / filling processing, and / or the post-processing method can be discarding processing. If the time interval between the first time unit and the second time unit is greater than the third threshold, the pre-processing method adopted by the terminal device can be adaptive processing, and / or the post-processing method adopted by the terminal device can be adaptive processing. In specific implementation, the conditions for determining the pre-processing method and / or the post-processing method can be defined by the protocol, or can also be configured by the network device.

[0184] In other embodiments, the terminal device can adopt the scheme described above to determine the pre-processing method and / or the post-processing method.

[0185] Thus, the terminal device can perform processing using the determined pre-processing method and / or post-processing method to obtain the target channel information.

[0186] S72, the terminal device sends the target channel information to the network device on the uplink resource. Correspondingly, the network device receives the target channel information on the uplink resource.

[0187] For more content of Embodiment 5, reference can be made to the relevant descriptions of Embodiments 1 to 4 above, and details are not described herein again.

[0188] It should be understood that the above embodiments can be used alone or in combination with each other to achieve different technical effects.

[0189] It can be understood that in specific implementation, the above method can be implemented in the form of a software program, and the software program runs in a processor integrated inside a chip or a chip module; or, the method can be implemented in a hardware or a combination of hardware and software manner, for example, implemented by a dedicated chip or a chip module, or implemented by a dedicated chip or a chip module in combination with a software program.

[0190] Refer to Figure 8 , Figure 8 is a schematic structural diagram of a communication device in an embodiment of the present application. Figure 8 The shown communication device can be deployed in the above-mentioned terminal device, Figure 8 The shown device may include: a sending module 81;

[0191] A transmitting module 81, configured to transmit target channel information on an uplink resource, where the target channel information is obtained based on compression processing of a first model and / or first processing, and the first processing includes: pre-processing and / or post-processing.

[0192] In a specific implementation, Figure 8 The illustrated communication device may correspond to a chip with a communication function in a terminal device; or correspond to a terminal device including a chip or a chip module with a communication function, or correspond to a terminal device.

[0193] Referring to Figure 9 , Figure 9 is a schematic structural diagram of another communication device in an embodiment of the present application. Figure 9 The illustrated communication device may be deployed in the above-mentioned network device. Figure 9 The illustrated device may include: a receiving module 91, where

[0194] The receiving module 91 is configured to receive target channel information on an uplink resource, where the target channel information is obtained based on compression processing of a first model and / or first processing, and the first processing includes: pre-processing and / or post-processing.

[0195] In a specific implementation, Figure 9 The illustrated communication device may correspond to a chip with a communication function in a network device; or correspond to a network device including a chip or a chip module with a communication function, or correspond to a network device.

[0196] For more content such as the working principle, working method, and beneficial effects of the communication device in the embodiment of the present application, reference may be made to the related description of the communication method above, and details are not described herein again.

[0197] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the above-mentioned communication method is executed. The storage medium may include ROM, RAM, a magnetic disk, or an optical disc, etc. The storage medium may also include a non-volatile memory or a non-transitory memory, etc.

[0198] An embodiment of the present application further provides a communication device, including a memory and a processor. A computer program that can run on the processor is stored on the memory. When the processor runs the computer program, the steps of the above-mentioned communication method are executed. The communication device may be the network device in the above text or the terminal device in the above text.

[0199] Referring to Figure 10 ,Figure 10 It is a schematic diagram of the hardware structure of a communication device in an embodiment of the present application. Figure 10 The illustrated communication device may be the network device in the above text, or may be the terminal device in the above text. Figure 10 The illustrated communication device includes a memory 101, a processor 102, and a transceiver 103. The processor 102 is coupled to the memory 101 and the transceiver 103. The memory 101 may be located inside or outside the communication device. The memory 101, the processor 102, and the transceiver 103 may be connected through a communication bus. The transceiver 103 is used to communicate with other devices. A computer program that can run on the processor 102 is stored on the memory 101. When the processor 102 runs the computer program, it executes the steps in the method provided in the above embodiment, and / or when the processor 102 runs the computer program, the transceiver 103 executes the steps in the method provided in the above embodiment.

[0200] It should be understood that in an embodiment of the present application, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0201] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink dynamic random access memory (SLDRAM), and direct rambus random access memory (DR RAM).

[0202] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer program can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless manner.

[0203] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0204] In several embodiments provided in the present application, it should be understood that the disclosed methods, apparatuses, and systems can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of the apparatus or unit can be in electrical, mechanical, or other forms.

[0205] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0206] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can be physically included separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware, or in the form of hardware plus software functional units. For example, for each device or product applied to or integrated in a chip, each module / unit included therein can be implemented in the form of hardware such as circuits, or at least some modules / units can be implemented in the form of software programs, and the software program runs on the processor integrated inside the chip, and the remaining (if any) part of the modules / units can be implemented in the form of hardware such as circuits; for each device or product applied to or integrated in a chip module, each module / unit included therein can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (such as a chip, a circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented in the form of software programs, and the software program runs on the processor integrated inside the chip module, and the remaining (if any) part of the modules / units can be implemented in the form of hardware such as circuits; for each device or product applied to or integrated in a terminal device, each module / unit included therein can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (such as a chip, a circuit module, etc.) or different components inside the terminal device, or at least some modules / units can be implemented in the form of software programs, and the software program runs on the processor integrated inside the terminal device, and the remaining (if any) part of the modules / units can be implemented in the form of hardware such as circuits.

[0207] The integrated unit implemented in the form of software functional units can be stored in a computer-readable storage medium. The above-mentioned software functional units are stored in a storage medium and include several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute some steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0208] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application should be subject to the scope defined by the claims.

Claims

1. A communication method, characterized in that, the method includes: sending target channel information on uplink resources, where the target channel information is obtained based on compression processing of a first model and / or first processing, and wherein the first processing includes: pre-processing and / or post-processing.

2. The communication method according to claim 1, characterized in that, the method further includes: receiving first indication information, where the first indication information includes: indication information of the pre-processing method and / or indication information of the post-processing method.

3. The communication method according to claim 1, characterized in that, the method further includes: sending second indication information, where the second indication information includes: indication information of the pre-processing method and / or indication information of the post-processing method.

4. The communication method according to claim 3, characterized in that, the second indication information is carried in CSI part 1 of a channel state information CSI report.

5. The communication method according to claim 1, characterized in that, the pre-processing method and / or the post-processing method are predefined by a protocol.

6. The communication method according to claim 1, characterized in that, the pre-processing method and / or the post-processing method are determined based on the conditions satisfied.

7. The communication method according to claim 6, characterized in that, the conditions include at least one of the following: the computing resources of the terminal device are greater than or equal to a first threshold; the computing resources of the terminal device are less than a second threshold; the time interval between a first time unit and a second time unit is greater than or equal to a third threshold, where the first time unit refers to: the transmission time unit or measurement time unit of a reference signal for measuring channel information, and the second time unit is the transmission time unit of the target channel information; the time interval between the first time unit and the second time unit is less than a fourth threshold.

8. The communication method according to claim 1, characterized in that, the pre-processing is any one or more of the following methods: performing adaptive processing on first channel information to obtain the channel information input to the first model; truncating or padding the first channel information to obtain the channel information input to the first model; grouping the first channel information based on channel resources and / or antenna ports to obtain the channel information input to the first model, where the channel information input to the first model includes multiple second channel information, and the size of each second channel information is the input size; adjusting the size of the channel resources corresponding to the first channel information to obtain the channel information input to the first model.

9. The communication method according to claim 1, characterized in that, the post-processing is any one or more of the following methods: performing adaptive processing on the channel information output by the first model to obtain the target channel information, where the size of the target channel information matches the size of the uplink resources; truncating or padding the channel information output by the first model to obtain the target channel information; Discard at least one piece of third channel information to obtain the target channel information, where the channel information output by the first model includes a plurality of pieces of the third channel information.

10. The communication method according to claim 9, wherein, the post-processing is: discarding the at least one piece of third channel information according to the priorities of the plurality of pieces of third channel information.

11. The communication method according to claim 10, wherein, the priorities of the plurality of pieces of third channel information are determined based on at least one of the following: index information of channel resources corresponding to the third channel information; index information of antenna ports corresponding to the third channel information; index information of layers corresponding to the third channel information.

12. A communication method, wherein, the method includes: receiving target channel information on an uplink resource, where the target channel information is obtained based on compression processing and / or first processing of a first model, and the first processing includes: pre-processing and / or post-processing.

13. The communication method according to claim 12, wherein, the method further includes: sending first indication information, where the first indication information includes: indication information of the manner of the pre-processing and / or indication information of the manner of the post-processing.

14. The communication method according to claim 12, wherein, the method further includes: receiving second indication information, where the second indication information includes: indication information of the manner of the pre-processing and / or indication information of the manner of the post-processing.

15. The communication method according to claim 14, wherein, the second indication information is carried in CSI part 1 of a channel state information CSI report.

16. The communication method according to claim 12, wherein, the manner of the pre-processing and / or the manner of the post-processing are predefined by a protocol.

17. The communication method according to claim 12, wherein, the manner of the pre-processing and / or the manner of the post-processing are determined based on conditions satisfied.

18. The communication method according to claim 17, wherein, the conditions include at least one of the following: the computing resources of the terminal device are greater than or equal to a first threshold; the computing resources of the terminal device are less than a second threshold; the time interval between a first time unit and a second time unit is greater than or equal to a third threshold, where the first time unit refers to: a transmission time unit or a measurement time unit of a reference signal for measuring channel information, and the second time unit is the transmission time unit of the target channel information; the time interval between the first time unit and the second time unit is less than a fourth threshold.

19. The communication method according to claim 12, wherein, the pre-processing is any one or more of the following manners: performing adaptive processing on first channel information to obtain the channel information input to the first model; truncating or padding the first channel information to obtain the channel information input to the first model; Group the first channel information based on channel resources and / or antenna ports to obtain the channel information input to the first model. The channel information input to the first model includes a plurality of second channel information, and the size of each second channel information is the input size; Adjust the size of the channel resources corresponding to the first channel information to obtain the channel information input to the first model.

20. The communication method according to claim 12, wherein, The post-processing is any one or more of the following methods: Perform adaptive processing on the channel information output by the first model to obtain the target channel information, and the size of the target channel information matches the size of the uplink resources; Truncate or pad the channel information output by the first model to obtain the target channel information; Discard at least one third channel information to obtain the target channel information, where the channel information output by the first model includes a plurality of the third channel information.

21. The communication method according to claim 20, wherein, The post-processing is: Discard the at least one third channel information according to the priorities of the plurality of third channel information.

22. The communication method according to claim 21, wherein, The priorities of the plurality of third channel information are determined based on at least one of the following: The index information of the channel resources corresponding to the third channel information; The index information of the antenna ports corresponding to the third channel information; The index information of the layers corresponding to the third channel information.

23. A communication device, wherein, The device includes: A sending module, configured to send target channel information on uplink resources, where the target channel information is obtained based on the compression processing and / or the first processing of a first model, and the first processing includes: pre-processing and / or post-processing.

24. A communication device, wherein, The device includes: A receiving module, configured to send target channel information on uplink resources, where the target channel information is obtained based on the compression processing and / or the first processing of a first model, and the first processing includes: pre-processing and / or post-processing.

25. A computer-readable storage medium, on which a computer program is stored, wherein, When the computer program is run by a processor, the communication method according to any one of claims 1 to 11 or the communication method according to any one of claims 12 to 22 is executed.

26. A communication device, including a memory and a processor, and a computer program that can run on the processor is stored on the memory, wherein, When the processor runs the computer program, the steps of the communication method according to any one of claims 1 to 11 are executed.

27. A communication device, including a memory and a processor, and a computer program that can run on the processor is stored on the memory, wherein, When the processor runs the computer program, the steps of the communication method according to any one of claims 12 to 22 are executed.

Images