Method, apparatus, communication device and storage medium for channel state information feedback

Abstract

Embodiments of the present application provide a channel state information feedback method, device, communication equipment and storage medium. The method comprises: a terminal device sends first information to a network device, wherein the first information at least comprises: indication information of a channel state information (CSI) feedback method, or error information of different CSI feedback methods and the number of bits required for CSI feedback, or the number of bits required for CSI feedback corresponding to a CSI feedback method meeting a requirement.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and specifically to a method, apparatus, communication device, and storage medium for channel state information (CSI) feedback. Background Technology

[0002] Type I and Type II codebooks are used by User Equipment (UE) to provide feedback on the Precoding Matrix Indicator (PMI). Type I is a standard-precision codebook, while Type II is a high-precision codebook. Type I is a transverse-mode codebook, designed to reduce the complexity of codebook search for the UE. Type II decomposes spatial channel information into a set of basis vectors, with the UE reporting the main spatial components and weighting coefficients. Considering feedback overhead, neither Type I nor Type II codebook feedback mechanisms directly compress the channel information, preventing the base station from obtaining full channel information.

[0003] To provide more complete CSI information across all channels to the base station, a neural network-based CSI compression feedback method has been proposed. The terminal sends the compressed bits to the base station, and the base station uses the neural network to recover the compressed bits into full-channel CSI information or a feature vector of full-channel CSI information.

[0004] Currently, there is no effective solution for how to trigger different CSI feedbacks, especially neural network-based CSI feedbacks. Summary of the Invention

[0005] To address the existing technical problems, embodiments of the present invention provide a method, apparatus, communication device, and storage medium for channel state information feedback.

[0006] To achieve the above objectives, the technical solution of this invention is implemented as follows:

[0007] In a first aspect, embodiments of the present invention provide a method for channel state information feedback, the method comprising:

[0008] The terminal device sends first information to the network device, the first information including at least:

[0009] CSI feedback method indication information, or

[0010] Error information for different CSI feedback methods and the number of bits required for CSI feedback, or

[0011] The number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements.

[0012] In the above scheme, the CSI feedback method includes at least one of the following: a codebook-based CSI feedback method, a neural network-based full-channel CSI compression feedback method, and a neural network-based full-channel CSI feature vector compression feedback method.

[0013] In the above scheme, when the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compression feedback method or a neural network-based full-channel CSI feature vector compression feedback method, the first information also includes the number of bits required for CSI feedback and neural network parameters.

[0014] In the above scheme, the CSI feedback method that meets the requirements includes: a CSI feedback method in which the error information of the CSI feedback method is less than a first preset threshold.

[0015] In the above scheme, where the first information at least includes: error information of different CSI feedback methods and the number of bits required for CSI feedback, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements, the method further includes:

[0016] The terminal device receives second information sent by the network device, the second information including indication information of the CSI feedback method.

[0017] In the above scheme, when the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compressed feedback method or a neural network-based full-channel CSI feature vector compressed feedback method, the method further includes:

[0018] The terminal device sends third information to the network device, the third information including the neural network parameters corresponding to the CSI feedback method.

[0019] In the above scheme, the method further includes: the terminal device training and updating the parameters of the neural network when the first preset condition is met.

[0020] In the above scheme, satisfying the first preset condition includes:

[0021] When the error information of the CSI feedback method related to the neural network exceeds a second preset threshold, it is determined that the first preset condition is met; or,

[0022] When the terminal device receives the first indication information from the network device, it determines that the first preset condition is met. The first indication information is used to notify the terminal device to fall back to the codebook-based CSI feedback method.

[0023] In the above scheme, the method further includes: the terminal device sending fourth information to the network device, the fourth information including: the updated number of bits required for the CSI feedback of the CSI feedback method related to the neural network and the updated neural network parameters.

[0024] In the above scheme, when the error information of the CSI feedback method related to the neural network exceeds a second preset threshold, satisfying the first preset condition, the method further includes:

[0025] The terminal device sends a second instruction to the network device, the second instruction being used to notify the network device to fall back to the codebook-based CSI feedback method.

[0026] Secondly, embodiments of the present invention also provide a method for channel state information feedback, the method comprising:

[0027] The network device receives first information sent by the terminal device, the first information including at least:

[0028] CSI feedback method indication information, or

[0029] Error information for different CSI feedback methods and the number of bits required for CSI feedback, or

[0030] The number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements.

[0031] In the above scheme, the CSI feedback method includes at least one of the following: a codebook-based CSI feedback method, a neural network-based full-channel CSI compression feedback method, and a neural network-based full-channel CSI feature vector compression feedback method.

[0032] In the above scheme, the CSI feedback method that meets the requirements includes: a CSI feedback method in which the error information of the CSI feedback method is less than a first preset threshold.

[0033] In the above scheme, where the first information at least includes: error information of different CSI feedback methods and the number of bits required for CSI feedback, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements, the method further includes:

[0034] The network device sends a second message to the terminal device, the second message including indication information of the CSI feedback method.

[0035] In the above scheme, when the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compressed feedback method or a neural network-based full-channel CSI feature vector compressed feedback method, the method further includes:

[0036] The network device receives third information sent by the terminal device, the third information including neural network parameters corresponding to the CSI feedback method.

[0037] In the above scheme, the method further includes: when the network device does not meet the second preset condition, it sends a first indication information to the terminal device, the first indication information being used to notify the terminal device to fall back to the codebook-based CSI feedback method.

[0038] In the above scheme, the method further includes: the network device receiving second indication information sent by the terminal device, the second indication information being used to notify the network device to fall back to the codebook-based CSI feedback method.

[0039] In the above scheme, the method further includes: the network device receiving fourth information sent by the terminal device, the fourth information including: the updated number of bits required for the CSI feedback of the CSI feedback method related to the neural network and the updated neural network parameters.

[0040] Thirdly, embodiments of the present invention also provide a channel state information feedback apparatus, the apparatus comprising: a first communication unit, configured to send first information to a network device, the first information comprising at least:

[0041] CSI feedback method indication information, or

[0042] Error information for different CSI feedback methods and the number of bits required for CSI feedback, or

[0043] The number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements.

[0044] Fourthly, embodiments of the present invention also provide a channel state information feedback apparatus, the apparatus comprising: a second communication unit, configured to receive first information sent by a terminal device, the first information including at least:

[0045] CSI feedback method indication information, or

[0046] Error information for different CSI feedback methods and the number of bits required for CSI feedback, or

[0047] The number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements.

[0048] Fifthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the methods described in the first or second aspects of the present invention.

[0049] In a sixth aspect, embodiments of the present invention also provide a communication device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method described in the first or second aspect of the present invention.

[0050] The channel state information (CSI) feedback method, apparatus, communication device, and storage medium provided in this invention embodiment allow a terminal device to send first information to a network device. This first information includes at least: indication information for a CSI feedback method, or error information and the number of bits required for CSI feedback for different CSI feedback methods, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements. By employing the technical solution of this invention embodiment, the terminal device indicates a CSI feedback method to the network device, indicating which CSI feedback to trigger, or sends error information and the number of bits required for CSI feedback for different CSI feedback methods, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements, to the network device to select a CSI feedback method. This allows the network device to decide which CSI feedback to use, thereby solving the problem of triggering CSI feedback when multiple CSI feedback methods are available. Furthermore, the network device selects a CSI feedback method based on the error information and the number of bits required for CSI feedback for different CSI feedback methods, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements. This selection between error information and feedback overhead is beneficial for the network device in scheduling uplink channel resources. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating the channel state information feedback method according to an embodiment of the present invention. Figure 1 ;

[0052] Figure 2 This is a flowchart illustrating the channel state information feedback method according to an embodiment of the present invention. Figure 2 ;

[0053] Figure 3 This is a flowchart illustrating the channel state information feedback method according to an embodiment of the present invention. Figure 3 ;

[0054] Figure 4 This is a schematic diagram of the interaction flow of the channel state information feedback method according to an embodiment of the present invention. Figure 1 ;

[0055] Figure 5 This is a schematic diagram of the interaction flow of the channel state information feedback method according to an embodiment of the present invention. Figure 2 ;

[0056] Figure 6 This is a schematic diagram of the interaction flow of the channel state information feedback method according to an embodiment of the present invention. Figure 3 ;

[0057] Figure 7 This is a schematic diagram of the structure of the channel state information feedback device according to an embodiment of the present invention. Figure 1 ;

[0058] Figure 8 This is a schematic diagram of the structure of the channel state information feedback device according to an embodiment of the present invention. Figure 2 ;

[0059] Figure 9 This is a schematic diagram of the hardware composition structure of a communication device according to an embodiment of the present invention. Detailed Implementation

[0060] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0061] The technical solutions of this invention can be applied to various communication systems, such as GSM (Global System of Mobile communication), LTE (Long Term Evolution), or 5G systems. Optionally, a 5G system or 5G network can also be referred to as a New Radio (NR) system or NR network.

[0062] For example, the communication system used in this embodiment of the invention may include network devices and terminal devices (also referred to as terminals, communication terminals, etc.); the network device may be a device that communicates with the terminal device. The network device can provide communication coverage within a certain area and can communicate with terminals located within that area. Optionally, the network device may be a base station in various communication systems, such as an evolved Node B (eNB) in an LTE system, or a gNB in ​​a 5G or NR system.

[0063] It should be understood that devices with communication functions in the network / system of this application embodiment can be referred to as communication devices. Communication devices may include network devices and terminals with communication functions. Network devices and terminal devices can be the specific devices described above, which will not be repeated here. Communication devices may also include other devices in the communication system, such as network controllers, mobility management entities, and other network entities. This embodiment of the present invention does not limit these.

[0064] It should be understood that the terms "system" and "network" are often used interchangeably in this document. The term "and / or" in this document merely describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Furthermore, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0065] The terms “first,” “second,” etc., used in the specification and claims of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0066] This invention provides a method for channel state information feedback. Figure 1 This is a flowchart illustrating the channel state information feedback method according to an embodiment of the present invention. Figure 1 ;like Figure 1 As shown, the method includes:

[0067] Step 101: The terminal device sends first information to the network device. The first information includes at least: indication information of the CSI feedback method, or error information of different CSI feedback methods and the number of bits required for CSI feedback, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements.

[0068] In this embodiment, the CSI feedback method includes at least one of the following: a codebook-based CSI feedback method, a neural network-based full-channel CSI compression feedback method, and a neural network-based full-channel CSI feature vector compression feedback method.

[0069] The aforementioned codebook-based CSI feedback method can be, for example, a Type I codebook or a Type II codebook feedback method. The aforementioned neural network-based full-channel CSI compression feedback method specifically involves bit compression of the full-channel CSI information based on a neural network; the receiving end then restores the compressed full-channel CSI information to its original state. The aforementioned neural network-based full-channel CSI feature vector compression feedback method specifically involves bit compression of the full-channel CSI information based on a neural network, and the receiving end then restores the compressed full-channel CSI information to its feature vector.

[0070] In this embodiment, CSI feedback can be triggered in at least three ways: The first way is that the terminal device determines the CSI feedback method and indicates the CSI feedback method to the network device; the second way is that the terminal device sends the error information of each CSI feedback method and the number of bits required for CSI feedback to the network device, and the network device selects the CSI feedback method; the third way is that the terminal device first determines the CSI feedback methods that meet the requirements, and then sends the number of bits required for CSI feedback corresponding to the CSI feedback methods that meet the requirements to the network device, that is, the terminal device first determines some of the CSI feedback methods that meet the requirements, and then the network device selects the CSI feedback method.

[0071] The technical solution of this invention involves a terminal device instructing a network device on a CSI feedback method, indicating which CSI feedback to trigger, or sending error information and the number of bits required for different CSI feedback methods, or the number of bits required for a suitable CSI feedback method, to the network device. This allows the network device to select the appropriate CSI feedback method, thus resolving the issue of triggering CSI feedback when multiple methods are available. Furthermore, the network device's selection of the CSI feedback method based on the error information and the number of bits required, or the number of bits required for a suitable CSI feedback method, facilitates uplink channel resource scheduling by the network device.

[0072] In the first method described above, the terminal device compares the error information and / or the number of bits required for CSI feedback of different CSI feedback methods, and determines the CSI feedback method based on the comparison result. Optionally, the terminal device compares the error information of different CSI feedback methods and selects the CSI feedback method with the smallest error represented by the error information as the CSI feedback method; or, the terminal device compares the error information of different CSI feedback methods, determines at least one CSI feedback method whose error information is less than a preset threshold, and selects the CSI feedback method with the smallest number of bits required for CSI feedback from the at least one CSI feedback method as the CSI feedback method. Specifically, the error information refers to the error between the CSI information recovered by the network device and the CSI information sent by the terminal device. For example, this error can specifically be the Normalized Mean Squared Error (NMSE). Of course, the calculation method of this error is not limited in this embodiment. For example, the terminal device can select the CSI feedback method with the smallest error from among the various CSI feedback methods as the CSI feedback method. For example, the terminal device can select the CSI feedback method with the least error and the fewest feedback bits from among the various CSI feedback methods as the CSI feedback method.

[0073] In the first approach described above, optionally, when the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compressed feedback method or a neural network-based full-channel CSI feature vector compressed feedback method, the first information further includes the number of bits required for CSI feedback and the neural network parameters. This allows the network device to perform uplink channel resource scheduling based on the number of bits required for CSI feedback, and to set the parameters of the network-side neural network according to the neural network parameters.

[0074] In the second method described above, the terminal device sends error information for each CSI feedback method and the number of bits required for CSI feedback to the network device, which then selects the appropriate CSI feedback method. Optionally, the network device may select the CSI feedback method based on the error information and / or the number of bits required for CSI feedback for each method.

[0075] In the third method described above, the terminal device first determines a satisfactory CSI feedback method, and then sends the required number of bits for CSI feedback corresponding to the satisfactory CSI feedback method to the network device, which then selects the CSI feedback method. Optionally, the satisfactory CSI feedback method includes a CSI feedback method where the error information of the CSI feedback method is less than a first preset threshold. Specifically, the error information refers to the error between the CSI information recovered by the network device and the CSI information sent by the terminal device; for example, this error can be NMSE. Of course, the calculation method for this error is not limited in this embodiment.

[0076] Based on this, in the second and third methods described above, when the first information includes at least: error information of different CSI feedback methods and the number of bits required for CSI feedback, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements, the method further includes: the terminal device receiving second information sent by the network device, the second information including indication information of the CSI feedback method.

[0077] In some optional embodiments of the present invention, when the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compression feedback method or a neural network-based full-channel CSI feature vector compression feedback method, the method further includes: the terminal device sending third information to the network device, the third information including neural network parameters corresponding to the CSI feedback method determined by the network device.

[0078] In this embodiment, when the CSI feedback method determined by the network device is a neural network-based full-channel CSI compression feedback method or a neural network-based full-channel CSI feature vector compression feedback method, the terminal device will also send the neural network parameters corresponding to the determined CSI feedback method to the network device so that the network device can set the parameters of the neural network on the network side according to the neural network parameters.

[0079] In some optional embodiments, the method further includes: the terminal device receiving configuration information sent by the network device, and performing CSI feedback based on the configuration information.

[0080] In some alternative embodiments of the present invention, such as Figure 2 As shown, the method further includes: the terminal device training and updating the parameters of the neural network when a first preset condition is met.

[0081] In this embodiment, after a period of time using the CSI feedback method related to the neural network, the channel environment may change significantly, so it is necessary to update the parameters of the neural network.

[0082] In some optional embodiments, satisfying the first preset condition includes: determining that the first preset condition is satisfied when the error information of the CSI feedback method related to the neural network exceeds a second preset threshold; or, determining that the first preset condition is satisfied when the terminal device receives the first indication information from the network device, wherein the first indication information is used to notify the terminal device to fall back to the codebook-based CSI feedback method.

[0083] In this embodiment, at least two methods can be used to trigger the parameter update of the neural network: the first method is that the terminal device triggers the neural network to update the parameters; the second method is that the network device triggers the neural network to update the parameters. Specifically, when the network device detects that the update conditions are met, it sends a first indication information to the terminal device. The terminal device, on the one hand, reverts to the codebook-based CSI feedback method according to the indication of the first indication information, and on the other hand, trains and updates the parameters of the neural network according to the indication of the first indication information.

[0084] In the first parameter update method described above, when the terminal device detects that the error information of the CSI feedback method related to the neural network exceeds a second preset threshold, it determines that the first preset condition is met, and then trains and updates the parameters of the neural network. For example, the terminal device may store the parameters of the neural network on both the terminal side and the network side, and use sample CSI information to simulate the CSI feedback process, thereby calculating the error information (e.g., NMSE) between the sample CSI information emitted by the terminal device and the CSI information recovered by the network side. If this error information exceeds the second preset threshold, it can be determined that the first preset condition is met, and the parameters of the neural network need to be updated.

[0085] In some optional embodiments, when the error information of the CSI feedback method related to the neural network exceeds a second preset threshold, the method further includes: the terminal device sending second indication information to the network device, the second indication information being used to notify the network device to fall back to the codebook-based CSI feedback method.

[0086] In this embodiment, specifically when using the first parameter update method described above, the terminal device sends a second indication message to the network device. This second indication message is used to notify the network device to revert to the codebook-based CSI feedback method. This allows the terminal device and the network device to employ the codebook-based CSI feedback method during neural network training. For example, the terminal device can send the second indication message to the network device via signaling.

[0087] In the second parameter update method described above, when the second preset condition is not met, the network device sends a first indication message to the terminal device. This first indication message is used to notify the terminal device to fall back to the codebook-based CSI feedback method; that is, the first indication message triggers the terminal device to update the parameters of the neural network. For example, the network device can determine whether the second preset condition is met based on Hybrid Automatic Repeat Request (HARQ) feedback information and / or detected channel state information with the terminal device. For instance, if the number of negative responses (NACKs) received by the network device reaches a certain threshold, it determines that the second preset condition is not met; or, for example, if the network device detects that the terminal device's transmission rate is lower than a certain threshold, or detects that parameters such as transmission quality parameters and reliability parameters with the terminal device are lower than a certain threshold, it can determine that the second preset condition is not met, and then the network device sends the first indication message to the terminal device.

[0088] For example, the terminal device receives the first indication information sent by the network device via signaling.

[0089] In some optional embodiments, training and updating the parameters of the neural network includes: the terminal device iteratively training the neural network based on pre-obtained sample CSI data to obtain error information of the CSI feedback method related to the neural network; and adjusting the parameters of the neural network based on the error information until the error information is less than a third preset threshold.

[0090] In this embodiment, the terminal device iteratively trains the neural network based on sample CSI data, terminal-side neural network parameters, and network-side neural network parameters. Specifically, the sample CSI data is input into the terminal-side neural network to obtain compressed CSI data, and then the compressed CSI data is input into the network-side neural network to obtain recovered CSI data. The error is calculated using the initially input sample CSI data and the recovered CSI data, and the parameters of the terminal-side and network-side neural networks are adjusted according to the error. The above process is repeated until the obtained error is less than a third preset threshold.

[0091] In some optional embodiments of the present invention, the method further includes: the terminal device sending fourth information to the network device, the fourth information including: the updated number of bits required for the CSI feedback of the CSI feedback method related to the neural network and the updated neural network parameters.

[0092] In this embodiment, after the neural network training is completed, i.e., when the aforementioned error information is less than the third preset threshold, the terminal device sends the updated number of bits required for CSI feedback and the updated neural network parameters to the network device using the CSI feedback method related to the neural network. Specifically, the updated neural network parameters on the network side are sent to the network device so that the network device can update the neural network parameters. In this way, the terminal device and the network device can continue to use the CSI feedback method related to the neural network for CSI feedback.

[0093] Based on the above embodiments, this invention also provides a method for channel state information feedback. Figure 3 This is a flowchart illustrating the channel state information feedback method according to an embodiment of the present invention. Figure 3 ;like Figure 3 As shown, the method includes:

[0094] Step 201: The network device receives first information sent by the terminal device, the first information including at least: indication information of the CSI feedback method, or error information of different CSI feedback methods and the number of bits required for CSI feedback, or the number of bits required for CSI feedback corresponding to the CSI feedback method that meets the requirements.

[0095] In this embodiment, the CSI feedback method includes at least one of the following: a codebook-based CSI feedback method, a neural network-based full-channel CSI compression feedback method, and a neural network-based full-channel CSI feature vector compression feedback method.

[0096] In this embodiment, CSI feedback can be triggered in at least three ways: The first way is that the terminal device determines the CSI feedback method and indicates the CSI feedback method to the network device; the second way is that the terminal device sends the error information of each CSI feedback method and the number of bits required for CSI feedback to the network device, and the network device selects the CSI feedback method; the third way is that the terminal device first determines the CSI feedback methods that meet the requirements, and then sends the number of bits required for CSI feedback corresponding to the CSI feedback methods that meet the requirements to the network device, that is, the terminal device first determines some of the CSI feedback methods that meet the requirements, and then the network device selects the CSI feedback method.

[0097] The specific details of the three methods described above can be found in the embodiments described above, and will not be repeated here.

[0098] The technical solution of this invention involves a terminal device instructing a network device on a CSI feedback method, indicating which CSI feedback to trigger, or sending error information and the number of bits required for different CSI feedback methods, or the number of bits required for a suitable CSI feedback method, to the network device. This allows the network device to select the appropriate CSI feedback method, thus resolving the issue of triggering CSI feedback when multiple methods are available. Furthermore, the network device's selection of the CSI feedback method based on the error information and the number of bits required, or the number of bits required for a suitable CSI feedback method, facilitates uplink channel resource scheduling by the network device.

[0099] In some optional embodiments of the present invention, the CSI feedback method that meets the requirements includes: a CSI feedback method in which the error information of the CSI feedback method is less than a first preset threshold.

[0100] In some optional embodiments of the present invention, where the first information at least includes: error information of different CSI feedback methods and the number of bits required for CSI feedback, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements, the method further includes: the network device determining the CSI feedback method based on the first information and sending second information to the terminal device, the second information including indication information of the CSI feedback method. For example, the network device may send the second information to the terminal device via signaling.

[0101] In this embodiment, when the first information includes at least the error information of different CSI feedback methods and the number of bits required for CSI feedback, the network device can select a CSI feedback method based on the error information and / or the number of bits required for CSI feedback of each CSI feedback method. For example, the network device can compare the error information of different CSI feedback methods and select the CSI feedback method with the smallest error information as the CSI feedback method (e.g., when uplink channel resources are sufficient), or it can select at least one CSI feedback method with an error less than a preset threshold, and then select the CSI feedback method with the smallest number of bits required for CSI feedback from among the at least one CSI feedback method as the CSI feedback method (e.g., when uplink channel resources are scarce).

[0102] If the first information includes at least the number of bits required for CSI feedback corresponding to the CSI feedback method that meets the requirements, the network device can select the CSI feedback method according to the number of bits required for CSI feedback, for example, selecting the CSI feedback method with the smallest number of bits required for CSI feedback as the CSI feedback method.

[0103] In some optional embodiments, where the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compression feedback method or a neural network-based full-channel CSI feature vector compression feedback method, the method further includes: the network device receiving third information sent by the terminal device, the third information including neural network parameters corresponding to the CSI feedback method determined by the network device.

[0104] In this embodiment, when the CSI feedback method determined by the network device is a neural network-based full-channel CSI compression feedback method or a neural network-based full-channel CSI feature vector compression feedback method, the terminal device will also send the neural network parameters corresponding to the determined CSI feedback method to the network device so that the network device can set the parameters of the neural network on the network side according to the neural network parameters.

[0105] In some optional embodiments, the method further includes: the network device sending configuration information to the terminal device, the configuration information being used by the terminal device to perform CSI feedback; and receiving CSI sent by the terminal device.

[0106] In some optional embodiments of the present invention, the method further includes: when the network device does not meet the second preset condition, sending first indication information to the terminal device, the first indication information being used to notify the terminal device to fall back to the codebook-based CSI feedback method.

[0107] In this embodiment, when the second preset condition is not met, the network device sends a first indication message to the terminal device. This first indication message is used to notify the terminal device to fall back to the codebook-based CSI feedback method; that is, the first indication message is used to trigger the terminal device to update the parameters of the neural network. For example, the network device can determine whether the second preset condition is met based on HARQ feedback information and / or detected channel state information with the terminal device. For instance, if the number of negative responses (NACKs) received by the network device reaches a certain threshold, it determines that the second preset condition is not met; or, for example, if the network device detects that the transmission rate of the terminal device is lower than a certain threshold, or detects that parameters such as transmission quality parameters and reliability parameters between the network device and the terminal device are lower than a certain threshold, it can determine that the second preset condition is not met, and then the network device sends the first indication message to the terminal device.

[0108] In some optional embodiments of the present invention, the method further includes: the network device receiving second indication information sent by the terminal device, the second indication information being used to notify the network device to fall back to the codebook-based CSI feedback method.

[0109] In this embodiment, when the terminal device triggers an update to the parameters of the neural network, the terminal device sends a second indication message to the network device to notify the network device to revert to the codebook-based CSI feedback method. This allows the terminal device and the network device to employ the codebook-based CSI feedback method during neural network training. For example, the terminal device can send the second indication message to the network device via signaling.

[0110] In some optional embodiments of the present invention, the method further includes: the network device receiving fourth information sent by the terminal device, the fourth information including: the updated number of bits required for the CSI feedback of the CSI feedback method related to the neural network and the updated neural network parameters.

[0111] In this embodiment, after the neural network training is completed—that is, when the terminal device trains the neural network to the point that the error information corresponding to the neural network is less than a third preset threshold—the terminal device sends the updated number of bits required for CSI feedback and the updated neural network parameters to the network device using the CSI feedback method related to the neural network. Specifically, the updated neural network parameters on the network side are sent to the network device so that the network device can update the neural network parameters. In this way, the terminal device and the network device can continue to use the CSI feedback method related to the neural network for CSI feedback.

[0112] The method for channel state information feedback according to an embodiment of the present invention will be described in detail below with specific examples.

[0113] Example 1

[0114] Figure 4 This is a schematic diagram of the interaction flow of the channel state information feedback method according to an embodiment of the present invention. Figure 1 ;like Figure 4 As shown, the method includes:

[0115] Step 301: The terminal device sends first information to the network device, the first information including the CSI feedback method;

[0116] Step 302: The network device sends a CSI configuration report to the terminal device;

[0117] Step 303: The terminal device sends CSI feedback to the network device.

[0118] In the case where the CSI feedback method is a neural network-based full-channel CSI compressed feedback method or a neural network-based full-channel CSI feature vector compressed feedback method, the first information also includes the number of bits required for CSI feedback and the neural network parameters.

[0119] In this example, we assume the errors of the codebook-based CSI feedback method, the neural network-based full-channel CSI compressed feedback method, and the neural network-based full-channel CSI feature vector compression feedback method are 0.1, 0.06, and 0.04, respectively, and the number of bits required for each CSI feedback method is 150, 250, and 180 bits, respectively. When the terminal device's selection criterion is minimum error, it chooses the neural network-based full-channel CSI feature vector compression feedback method. When the terminal device's selection criterion is error less than a threshold and minimum number of feedback bits (assuming a threshold of 0.05), it chooses the neural network-based full-channel CSI feature vector compression feedback method.

[0120] The terminal device sends the selected CSI feedback method to the network device (e.g., base station) via a Medium Access Control-Control Element (MAC-CE). If the selected CSI feedback method is a neural network-based full-channel CSI compressed feedback method or a neural network-based full-channel CSI feature vector compressed feedback method, the terminal device also sends the required number of bits and neural network parameters to the network device via MAC-CE. The network device determines the CSI reporting configuration based on the required number of bits and sends the CSI reporting configuration to the terminal device via Radio Resource Control (RRC) signaling. The terminal device then performs CSI feedback according to the CSI reporting configuration.

[0121] Example 2

[0122] Figure 5 This is a schematic diagram of the interaction flow of the channel state information feedback method according to an embodiment of the present invention. Figure 2 ;like Figure 5 As shown, the method includes:

[0123] Step 401: The terminal device sends first information to the network device, the first information including error information of different CSI feedback methods and the number of bits required for CSI feedback;

[0124] Step 402: The network device sends CSI feedback to the terminal device;

[0125] Step 403: The terminal device sends neural network parameters to the network device;

[0126] Step 404: The network device sends a CSI configuration report to the terminal device;

[0127] Step 405: The terminal device sends CSI feedback to the network device.

[0128] In this example, step 403 is executed only if the CSI feedback method is a neural network-based full-channel CSI compressed feedback method or a neural network-based full-channel CSI feature vector compressed feedback method.

[0129] In this example, the errors of the codebook-based CSI feedback method, the neural network-based full-channel CSI compressed feedback method, and the neural network-based full-channel CSI feature vector compressed feedback method are assumed to be 0.1, 0.02, and 0.04, respectively, and the number of bits required for each CSI feedback method is 150, 250, and 180 bits, respectively. The terminal device sends the error information and the number of bits required for feedback of the three CSI feedback methods to the network device (e.g., a base station). When uplink channel resources are sufficient, the network device can choose the method with the smallest error, in which case it selects the neural network-based full-channel CSI compressed feedback method. When uplink channel resources are scarce, the network device can choose the method with the smallest error and the fewest feedback bits, assuming the threshold is 0.05, in which case it selects the neural network-based full-channel CSI feature vector compressed feedback method and informs the terminal device via signaling. The terminal device sends the neural network parameters to the network device via MAC-CE. The network device determines the CSI reporting configuration based on the number of bits required for feedback and sends the CSI reporting configuration to the terminal device via RRC signaling. The terminal device then performs CSI feedback according to the CSI reporting configuration.

[0130] Example 3

[0131] Figure 6 This is a schematic diagram of the interaction flow of the channel state information feedback method according to an embodiment of the present invention. Figure 3 ;like Figure 6 As shown, the method includes:

[0132] Step 501: The terminal device sends first information to the network device, the first information including the number of bits required for CSI feedback corresponding to the CSI feedback method that meets the requirements;

[0133] Step 502: The network device sends CSI feedback to the terminal device;

[0134] Step 503: The terminal device sends neural network parameters to the network device;

[0135] Step 504: The network device sends a CSI configuration report to the terminal device;

[0136] Step 505: The terminal device sends CSI feedback to the network device.

[0137] In this example, step 503 is executed only if the CSI feedback method is a neural network-based full-channel CSI compressed feedback method or a neural network-based full-channel CSI feature vector compressed feedback method.

[0138] In this example, assume the errors of the codebook-based CSI feedback method, the neural network-based full-channel CSI compressed feedback method, and the neural network-based full-channel CSI feature vector compressed feedback method are 0.1, 0.02, and 0.04, respectively, and the number of bits required for each CSI feedback method is 150, 250, and 180 bits, respectively. Assuming a threshold of 0.05, the terminal device determines that the feedback methods with errors less than the threshold are the neural network-based full-channel CSI compressed feedback method and the neural network-based full-channel CSI feature vector compressed feedback method, and sends the required number of bits for these two feedback methods to the network device (e.g., a base station). The network device selects the neural network-based full-channel CSI feature vector compressed feedback method with the fewest feedback bits and informs the terminal device via signaling. The terminal device sends the neural network parameters to the network device via MAC-CE. The network device determines the CSI reporting configuration based on the required number of bits for feedback and sends the CSI reporting configuration to the terminal device via RRC signaling. The terminal device then performs CSI feedback according to the CSI reporting configuration.

[0139] This invention also provides a channel state information feedback device, which is applied in a terminal device. Figure 7 This is a schematic diagram of the structure of the channel state information feedback device according to an embodiment of the present invention. Figure 1 ;like Figure 7 As shown, the device includes: a first communication unit 11, used to send first information to a network device, the first information including at least:

[0140] CSI feedback method indication information, or

[0141] Error information for different CSI feedback methods and the number of bits required for CSI feedback, or

[0142] The number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements.

[0143] In some optional embodiments of the present invention, the CSI feedback method includes at least one of the following: a codebook-based CSI feedback method, a neural network-based full-channel CSI compression feedback method, and a feature vector compression feedback method for full-channel CSI based on the neural network.

[0144] In some optional embodiments of the present invention, when the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compression feedback method or a neural network-based full-channel CSI feature vector compression feedback method, the first information further includes the number of bits required for CSI feedback and neural network parameters.

[0145] In some optional embodiments of the present invention, the CSI feedback method that meets the requirements includes: a CSI feedback method in which the error information of the CSI feedback method is less than a first preset threshold.

[0146] In some optional embodiments of the present invention, the first communication unit 11 is further configured to receive second information sent by the network device when the first information includes at least: error information of different CSI feedback methods and the number of bits required for CSI feedback, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements, the second information including indication information of CSI feedback method.

[0147] In some optional embodiments of the present invention, the first communication unit 11 is further configured to send third information to the network device when the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compression feedback method or a neural network-based full-channel CSI feature vector compression feedback method, the third information including neural network parameters corresponding to the CSI feedback method.

[0148] In some optional embodiments of the present invention, the device further includes a first processing unit 12, used to train and update the parameters of the neural network when a first preset condition is met.

[0149] In some optional embodiments of the present invention, satisfying the first preset condition includes:

[0150] When the error information of the CSI feedback method related to the neural network exceeds a second preset threshold, it is determined that the first preset condition is met; or,

[0151] When the first communication unit 11 receives the first indication information from the network device, it determines that the first preset condition is met. The first indication information is used to notify the fallback to the codebook-based CSI feedback method.

[0152] In some optional embodiments of the present invention, the first communication unit 11 is further configured to send fourth information to the network device, the fourth information including: the updated number of bits required for the CSI feedback of the CSI feedback method related to the neural network and the updated neural network parameters.

[0153] In some optional embodiments of the present invention, the first communication unit 11 is further configured to send second indication information to the network device when the error information of the CSI feedback method related to the neural network exceeds a second preset threshold, provided that the first preset condition is met. The second indication information is used to notify the network device to fall back to the codebook-based CSI feedback method.

[0154] In this embodiment of the invention, the first processing unit 12 in the device can be implemented by a central processing unit (CPU), a digital signal processor (DSP), a microcontroller unit (MCU), or a field-programmable gate array (FPGA) in practical applications; the first communication unit 11 in the device can be implemented by a communication module (including: basic communication kit, operating system, communication module, standardized interface and protocol, etc.) and a transceiver antenna in practical applications.

[0155] This invention also provides a channel state information feedback device, which is applied in a network device. Figure 8 This is a schematic diagram of the structure of the channel state information feedback device according to an embodiment of the present invention. Figure 2 ;like Figure 8 As shown, the device includes: a second communication unit 21, configured to receive first information sent by a terminal device, the first information including at least:

[0156] CSI feedback method indication information, or

[0157] Error information for different CSI feedback methods and the number of bits required for CSI feedback, or

[0158] The number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements.

[0159] In some optional embodiments of the present invention, the CSI feedback method includes at least one of the following: a codebook-based CSI feedback method, a neural network-based full-channel CSI compression feedback method, and a feature vector compression feedback method for full-channel CSI based on the neural network.

[0160] In some optional embodiments of the present invention, the CSI feedback method that meets the requirements includes: a CSI feedback method in which the error information of the CSI feedback method is less than a first preset threshold.

[0161] In some optional embodiments of the present invention, the apparatus further includes a second processing unit 22, configured to determine the CSI feedback method based on the first information when the first information includes at least: error information of different CSI feedback methods and the number of bits required for CSI feedback, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements;

[0162] The second communication unit 21 is also used to send second information to the terminal device, the second information including indication information of the CSI feedback method.

[0163] In some optional embodiments of the present invention, the second communication unit 21 is further configured to receive third information sent by the terminal device when the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compression feedback method or a neural network-based full-channel CSI feature vector compression feedback method, the third information including neural network parameters corresponding to the CSI feedback method.

[0164] In some optional embodiments of the present invention, the second communication unit 21 is further configured to send a first indication information to the terminal device when the second preset condition is not met, the first indication information being used to notify the terminal device to fall back to the codebook-based CSI feedback method.

[0165] In some optional embodiments of the present invention, the second communication unit 21 is further configured to receive second indication information sent by the terminal device, the second indication information being used to notify the network device to fall back to the codebook-based CSI feedback method.

[0166] In some optional embodiments of the present invention, the second communication unit 21 is further configured to receive fourth information sent by the terminal device, the fourth information including: the updated number of bits required for the CSI feedback of the CSI feedback method related to the neural network and the updated neural network parameters.

[0167] In this embodiment of the invention, the second processing unit 22 in the device can be implemented by a CPU, DSP, MCU or FPGA in practical applications; the second communication unit 21 in the device can be implemented by a communication module (including: basic communication kit, operating system, communication module, standardized interface and protocol, etc.) and transceiver antenna in practical applications.

[0168] It should be noted that the channel state information feedback device provided in the above embodiments is only illustrated by the division of the above program modules. In practical applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the channel state information feedback device and the channel state information feedback method embodiment provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiment, which will not be repeated here.

[0169] This invention also provides a communication device, which may be the terminal device or network device described in the foregoing embodiments. Figure 9 This is a schematic diagram of the hardware composition structure of the communication device according to an embodiment of the present invention, such as... Figure 9 As shown, the communication device includes a memory 32, a processor 31, and a computer program stored in the memory 32 and executable on the processor 31. When the processor 31 executes the program, it implements the steps of the channel state information feedback method applied to a terminal device according to the embodiments of the present invention; or, when the processor 31 executes the program, it implements the steps of the channel state information feedback method applied to a network device according to the embodiments of the present invention.

[0170] Optionally, the communication device further includes one or more network interfaces 33. The various components in the communication device are coupled together via a bus system 34. It is understood that the bus system 34 is used to implement communication between these components. In addition to a data bus, the bus system 34 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 9 The general labeled all buses as Bus System 34.

[0171] It is understood that memory 32 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 32 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0172] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 31. Processor 31 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 31 or by instructions in software form. The processor 31 may be a general-purpose processor, DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 31 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of the present invention can be directly manifested as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in memory 32. Processor 31 reads the information in memory 32 and completes the steps of the aforementioned method in combination with its hardware.

[0173] In an exemplary embodiment, the communication device may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), FPGAs, general-purpose processors, controllers, MCUs, microprocessors, or other electronic components to perform the aforementioned method.

[0174] In an exemplary embodiment, the present invention also provides a computer-readable storage medium, such as a memory 32 including a computer program, which can be executed by a processor 31 of a communication device to perform the steps described in the foregoing method. The computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM; or it may be various devices including one or any combination of the above-mentioned memories.

[0175] The computer-readable storage medium provided in the embodiments of the present invention stores a computer program thereon, which, when executed by a processor, implements the steps of the channel state information feedback method applied to a terminal device according to the embodiments of the present invention; or, when executed by a processor, the program implements the steps of the condition configuration method applied to a network device according to the embodiments of the present invention.

[0176] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0177] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0178] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0179] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0180] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0181] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0182] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0183] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0184] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for channel state information feedback, characterized in that, The method includes: The terminal device sends first information to the network device, the first information including at least: Error information and the number of bits required for CSI feedback for different Channel State Information (CSI) feedback methods, or The number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements; The error information and the number of bits required for CSI feedback of the different CSI feedback methods, or the number of bits required for CSI feedback corresponding to the CSI feedback method that meets the requirements, are used by the network device to select a CSI feedback method. The CSI feedback method includes at least one of the following: a codebook-based CSI feedback method, a neural network-based full-channel CSI compression feedback method, and a feature vector compression feedback method for full-channel CSI based on the neural network. The CSI feedback method that meets the requirements includes a CSI feedback method in which the error information of the CSI feedback method is less than a first preset threshold.

2. The method according to claim 1, characterized in that, When the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compressed feedback method or a neural network-based full-channel CSI feature vector compressed feedback method, the first information also includes the number of bits required for CSI feedback and the neural network parameters.

3. The method according to claim 1, characterized in that, When the first information includes at least: error information of different CSI feedback methods and the number of bits required for CSI feedback, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements, the method further includes: The terminal device receives second information sent by the network device, the second information including indication information of the CSI feedback method.

4. The method according to claim 3, characterized in that, When the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compressed feedback method or a neural network-based full-channel CSI eigenvector compressed feedback method, the method further includes: The terminal device sends third information to the network device, the third information including the neural network parameters corresponding to the CSI feedback method.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: The terminal device trains and updates the parameters of the neural network when the first preset condition is met.

6. The method according to claim 5, characterized in that, The condition of satisfying the first preset condition includes: When the error information of the CSI feedback method related to the neural network exceeds a second preset threshold, it is determined that the first preset condition is met; or, When the terminal device receives the first indication information from the network device, it determines that the first preset condition is met. The first indication information is used to notify the terminal device to fall back to the codebook-based CSI feedback method.

7. The method according to claim 5, characterized in that, The method further includes: The terminal device sends a fourth piece of information to the network device, the fourth piece of information including: the updated number of bits required for the CSI feedback and the updated neural network parameters of the CSI feedback method related to the neural network.

8. The method according to claim 6, characterized in that, If the error information of the CSI feedback method related to the neural network exceeds a second preset threshold, satisfying the first preset condition, the method further includes: The terminal device sends a second instruction message to the network device, the second instruction message being used to notify the network device to fall back to the codebook-based CSI feedback method.

9. A method for channel state information feedback, characterized in that, The method includes: The network device receives first information sent by the terminal device, the first information including at least: Error information for different CSI feedback methods and the number of bits required for CSI feedback, or The number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements; The error information and the number of bits required for CSI feedback of the different CSI feedback methods, or the number of bits required for CSI feedback corresponding to the CSI feedback method that meets the requirements, are used by the network device to select a CSI feedback method. The CSI feedback method includes at least one of the following: a codebook-based CSI feedback method, a neural network-based full-channel CSI compression feedback method, and a feature vector compression feedback method for full-channel CSI based on the neural network. The CSI feedback method that meets the requirements includes a CSI feedback method in which the error information of the CSI feedback method is less than a first preset threshold.

10. The method according to claim 9, characterized in that, When the first information includes at least: error information of different CSI feedback methods and the number of bits required for CSI feedback, or the number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements, the method further includes: The network device sends a second message to the terminal device, the second message including indication information of the CSI feedback method.

11. The method according to claim 10, characterized in that, When the indication information of the CSI feedback method is used to indicate a neural network-based full-channel CSI compressed feedback method or a neural network-based full-channel CSI eigenvector compressed feedback method, the method further includes: The network device receives third information sent by the terminal device, the third information including neural network parameters corresponding to the CSI feedback method.

12. The method according to claim 9, characterized in that, The method further includes: When the second preset condition is not met, the network device sends a first indication message to the terminal device. The first indication message is used to notify the terminal device to fall back to the codebook-based CSI feedback method.

13. The method according to claim 9, characterized in that, The method further includes: The network device receives a second indication information sent by the terminal device, the second indication information being used to notify the network device to fall back to the codebook-based CSI feedback method.

14. The method according to any one of claims 9 to 13, characterized in that, The method further includes: The network device receives fourth information sent by the terminal device, the fourth information including: the updated number of bits required for the CSI feedback and the updated neural network parameters of the CSI feedback method related to the neural network.

15. A device for channel state information feedback, characterized in that, The device includes: a first communication unit, configured to send first information to a network device, the first information including at least: Error information for different CSI feedback methods and the number of bits required for CSI feedback, or The number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements; The error information and the number of bits required for CSI feedback of the different CSI feedback methods, or the number of bits required for CSI feedback corresponding to the CSI feedback method that meets the requirements, are used by the network device to select a CSI feedback method. The CSI feedback method includes at least one of the following: a codebook-based CSI feedback method, a neural network-based full-channel CSI compression feedback method, and a feature vector compression feedback method for full-channel CSI based on the neural network. The CSI feedback method that meets the requirements includes a CSI feedback method in which the error information of the CSI feedback method is less than a first preset threshold.

16. A device for channel state information feedback, characterized in that, The device includes: a second communication unit, configured to receive first information sent by a terminal device, the first information including at least: Error information for different CSI feedback methods and the number of bits required for CSI feedback, or The number of bits required for CSI feedback corresponding to a CSI feedback method that meets the requirements; The error information and the number of bits required for CSI feedback of the different CSI feedback methods, or the number of bits required for CSI feedback corresponding to the CSI feedback method that meets the requirements, are used to select the CSI feedback method. The CSI feedback method includes at least one of the following: a codebook-based CSI feedback method, a neural network-based full-channel CSI compression feedback method, and a feature vector compression feedback method for full-channel CSI based on the neural network. The CSI feedback method that meets the requirements includes: a CSI feedback method in which the error information of the CSI feedback method is less than a first preset threshold.

17. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1 to 8; or... When executed by a processor, the program implements the steps of the method according to any one of claims 9 to 13.

18. A communication device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 8; or... When the processor executes the program, it implements the steps of the method according to any one of claims 9 to 13.

Images