CN116017543A

CN116017543A - Channel state information feedback enhancement method, device, system and storage medium

Info

Publication number: CN116017543A
Application number: CN202211680505.8A
Authority: CN
Inventors: 陈林; 杨波; 丁宝国; 刘重军; 杨雨翰; 高嘉和
Original assignee: Comba Network Systems Co Ltd
Current assignee: Comba Network Systems Co Ltd
Priority date: 2022-12-27
Filing date: 2022-12-27
Publication date: 2023-04-25
Also published as: WO2024140150A1

Abstract

The application relates to a channel state information feedback enhancement method, a device, a system and a storage medium. The method comprises the following steps: acquiring capability information reported by a user terminal; acquiring current service scene information; obtaining a Channel State Information (CSI) measurement mode according to the capability information and the service scene information; configuring and outputting Channel State Information (CSI) measurement parameters according to a CSI measurement mode; acquiring a Channel State Information (CSI) measurement result reported by a user terminal; training an artificial intelligent model according to the Channel State Information (CSI) measurement result to obtain a target model; and obtaining Channel State Information (CSI) specific information according to the target model so as to schedule the current service. By identifying the current scene, a corresponding target model is generated according to different scenes, so that the feedback load of Channel State Information (CSI) can be reduced, and the CSI feedback precision can be improved on the premise of having the same CSI feedback load.

Description

Channel state information feedback enhancement method, device, system and storage medium

Technical Field

The present disclosure relates to the field of wireless communications technologies, and in particular, to a method, an apparatus, a system, and a storage medium for enhancing channel state information feedback.

Background

Wireless communication systems have been widely deployed for everyday voice, video, data, and text messaging services. Mobile communication has advanced through several stages 2G (GSM, global System for Mobile Communications), 3G (TD-SCDMA, UMTS) and 4G (LTE, long Term Evolution), and has now entered the development and deployment stage of 5G (NR, new Radio).

The channel state information CSI (Channel State Information) plays a vital role in the accurate scheduling of traffic. The 3GPP introduces a Type I codebook and a Type II codebook in R15, and in the design of the Type I codebook, a terminal adopts an oversampling DFT (Discrete Fourier Transformation) vector as a feedback vector so as to select the best beam for the whole bandwidth; in the Type II codebook design, feedback with finer granularity for the spatial and frequency domains is provided, resulting in a larger feedback overhead. The 3GPP optimizes the design of the Type II codebook in the R16 and R17 protocol versions, and compresses the space domain and the frequency domain to reduce the feedback overhead. However, in the CSI measurement configuration, when the number of antenna ports and the number of subbands configured by the base station for the user terminal are large, the terminal still needs to feedback the information amount of tens or hundreds of bits, which results in a large feedback load of channel state information.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a channel state information feedback enhancement method, apparatus, system, and storage medium that can reduce the load of channel state information feedback.

In a first aspect, the present application provides a channel state information feedback enhancement method. The method is applied to a base station, and comprises the following steps:

acquiring capability information reported by a user terminal; wherein the capability information comprises model types of artificial intelligence models supported by the user terminal;

acquiring current service scene information; wherein, the business scenario information comprises: a Channel State Information (CSI) feedback period, a user terminal moving speed and a Channel State Information (CSI) feedback bit number;

obtaining a Channel State Information (CSI) measurement mode according to the capability information and the service scene information; the Channel State Information (CSI) measurement mode comprises one of a prediction measurement mode, a compression measurement mode and a compression and prediction measurement mode;

configuring and outputting Channel State Information (CSI) measurement parameters according to the CSI measurement mode;

acquiring a Channel State Information (CSI) measurement result reported by the user terminal; the Channel State Information (CSI) measurement result is obtained by measuring the CSI by the user terminal according to the CSI measurement parameter;

Training the artificial intelligent model according to the Channel State Information (CSI) measurement result to obtain a target model;

and obtaining Channel State Information (CSI) specific information according to the target model so as to schedule the current service.

In a second aspect, the present application further provides a channel state information feedback enhancement method. The method is applied to the user terminal, and comprises the following steps:

reporting capability information to a base station; wherein the capability information comprises model types of artificial intelligence models supported by the user terminal;

acquiring Channel State Information (CSI) measurement parameters; the base station obtains the Channel State Information (CSI) measurement parameters according to a CSI measurement mode, wherein the CSI measurement mode is obtained by the base station according to the capability information and the service scene information, the CSI measurement mode comprises one of a prediction measurement mode, a compression measurement mode and a compression and prediction measurement mode, and the service scene information comprises: a Channel State Information (CSI) feedback period, a user terminal moving speed and a Channel State Information (CSI) feedback bit number;

measuring Channel State Information (CSI) according to the CSI measurement parameters to obtain a CSI measurement result;

Acquiring a target model, and acquiring Channel State Information (CSI) specific information according to the target model; the target model is obtained by training the artificial intelligent model by the base station according to the Channel State Information (CSI) measurement result, wherein the Channel State Information (CSI) specific information is used for scheduling the current service.

In a third aspect, the present application further provides a channel state information feedback enhancing apparatus. The apparatus is applied to a base station, and the apparatus includes:

the capability information acquisition module is used for acquiring capability information reported by the user terminal; wherein the capability information comprises model types of artificial intelligence models supported by the user terminal;

the service scene information acquisition module is used for acquiring current service scene information; wherein, the business scenario information comprises: a Channel State Information (CSI) feedback period, a user terminal moving speed and a Channel State Information (CSI) feedback bit number;

the measurement mode calculation module is used for obtaining a Channel State Information (CSI) measurement mode according to the capability information and the service scene information; the Channel State Information (CSI) measurement mode comprises one of a prediction measurement mode, a compression measurement mode and a compression and prediction measurement mode;

The measurement parameter output module is used for configuring and outputting Channel State Information (CSI) measurement parameters according to the CSI measurement mode;

the measurement result acquisition module is used for acquiring a Channel State Information (CSI) measurement result reported by the user terminal; the Channel State Information (CSI) measurement result is obtained by measuring the CSI by the user terminal according to the CSI measurement parameter;

the model training module is used for training the artificial intelligent model according to the Channel State Information (CSI) measurement result to obtain a target model;

and the specific information calculation module is used for obtaining the Channel State Information (CSI) specific information according to the target model so as to schedule the current service.

In a fourth aspect, the present application further provides a channel state information feedback enhancing apparatus. The apparatus is applied to a user terminal, and the apparatus includes:

the capacity information reporting module is used for reporting the capacity information to the base station; wherein the capability information comprises model types of artificial intelligence models supported by the user terminal;

the measuring parameter acquisition module is used for acquiring Channel State Information (CSI) measuring parameters; the base station obtains the Channel State Information (CSI) measurement parameters according to a CSI measurement mode, wherein the CSI measurement mode is obtained by the base station according to the capability information and the service scene information, the CSI measurement mode comprises one of a prediction measurement mode, a compression measurement mode and a compression and prediction measurement mode, and the service scene information comprises: a Channel State Information (CSI) feedback period, a user terminal moving speed and a Channel State Information (CSI) feedback bit number;

The measurement result calculation module is used for measuring the Channel State Information (CSI) according to the Channel State Information (CSI) measurement parameters to obtain a Channel State Information (CSI) measurement result;

the model acquisition module is used for acquiring a target model and acquiring Channel State Information (CSI) specific information according to the target model; the target model is obtained by training the artificial intelligent model by the base station according to the Channel State Information (CSI) measurement result, wherein the Channel State Information (CSI) specific information is used for scheduling the current service.

In a fifth aspect, the present application further provides a channel state information feedback enhancement system, including a base station and a user terminal connected to the base station; wherein: the base station is configured to perform the steps of the method described in the first aspect; the user terminal is adapted to perform the steps of the method of the second aspect described above.

In a sixth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the above method.

According to the channel state information feedback enhancement method, device, system and storage medium, the current Channel State Information (CSI) measurement mode is judged by acquiring the capability information reported by the user terminal and the service scene information in the current scene, and the Channel State Information (CSI) measurement result is obtained. Training a corresponding artificial intelligent model according to the Channel State Information (CSI) measurement result to obtain a target model, and scheduling the current service according to the Channel State Information (CSI) specific information obtained by calculating the target model. By identifying the current scene, a corresponding target model is generated according to different scenes, so that the feedback load of Channel State Information (CSI) can be reduced, and the CSI feedback precision can be improved on the premise of having the same CSI feedback load.

Drawings

FIG. 1 is a diagram of an application environment for a channel state information feedback enhancement method in one embodiment;

fig. 2 is a flow chart of a channel state information feedback enhancement method implemented from a base station perspective in one embodiment;

FIG. 3 is a schematic diagram of CSI compression based on a CSI compression model in one embodiment;

fig. 4 is a schematic diagram of CSI prediction performed by a ue in one embodiment;

FIG. 5 is a schematic diagram of base station side CSI prediction in one embodiment;

fig. 6 is a flow chart of a method for obtaining CSI measurement implemented from a base station perspective in one embodiment;

fig. 7 is a schematic flow chart of obtaining specific information of channel state information CSI from a base station perspective in an embodiment;

FIG. 8 is a diagram of a user terminal performing CSI compression and CSI prediction functions in one embodiment;

fig. 9 is a schematic flow chart of obtaining specific information of channel state information CSI from a base station perspective in another embodiment;

FIG. 10 is a schematic diagram of a base station performing a CSI prediction function in one embodiment;

fig. 11 is a flow chart of a channel state information feedback enhancement method implemented from the perspective of a user terminal in one embodiment;

fig. 12 is a schematic flow chart of obtaining specific information of channel state information CSI, which is implemented from the perspective of a user terminal in one embodiment;

Fig. 13 is a schematic flow chart of obtaining specific information of channel state information CSI, which is implemented from the perspective of a user terminal in another embodiment;

FIG. 14 is a diagram illustrating signaling interactions between a base station and a user terminal in one embodiment;

fig. 15 is a schematic diagram of signaling interaction between a base station and a user terminal in another embodiment;

FIG. 16 is a block diagram of a channel state information feedback enhancement device implemented from the perspective of a base station in one embodiment;

fig. 17 is a block diagram of a channel state information feedback enhancing apparatus implemented from the perspective of a user terminal in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

The channel state information feedback enhancement method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the user terminal 102 communicates with the base station 104 via a wireless network. The user terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like.

In one embodiment, as shown in fig. 2, a method for enhancing feedback of channel state information is provided, and the method is applied to the base station 104 in fig. 1 for illustration, and includes the following steps:

step S110, obtaining capability information reported by a user terminal; wherein the capability information includes model types of artificial intelligence models supported by the user terminal.

Specifically, the base station 104 may send a ue capability query message uecapability query to the ue 102, and after the ue 102 receives the ue capability query message, the ue 102 reports capability information to the base station 104. The capability information is used to characterize whether the current user terminal 102 supports an artificial intelligence model, and the model type of the artificial intelligence model that the current user terminal 102 supports in the case of supporting an artificial intelligence model. It is understood that the model types include CSI compression model types (e.g., CNN, RNN, transformer, resNet, etc.) and CSI prediction model types (e.g., FCN, RNN, 3D-CNN, etc.). The CSI compression model may compress and reconstruct CSI to reduce the data amount and feedback overhead of CSI. The CSI prediction model may predict CSI values at a certain time in the future based on historical CSI measurements to solve the problem of inaccuracy of channel state information due to latency.

Step S120, current service scene information is obtained; the service scene information comprises: a Channel State Information (CSI) feedback period, a user terminal moving speed and a Channel State Information (CSI) feedback bit number.

Specifically, the base station 104 determines the CSI feedback period and the CSI feedback bit number according to the service type scheduled by the ue 102. The base station 104 may obtain the moving speed of the current user terminal 102 in several ways, for example, estimate the moving speed of the user terminal 102 according to the downlink channel information and the probability of the precoding matrix indication change; under the condition that the transmitter continuously transmits a special fixed signal, the moving speed of the user terminal is obtained by calculating an autocorrelation function of a time domain received signal; and calculating an estimated value of the complex channel autocorrelation function according to the sampling of the transmitted signal, and estimating the maximum Doppler frequency shift by combining the angle difference of the arrival angles of the transmitted signal, thereby obtaining the moving speed of the user terminal 102. The manner of calculating the moving speed of the user terminal can be changed according to the requirements of different application scenes, and the method is not limited herein.

Step S130, a Channel State Information (CSI) measurement mode is obtained according to the capability information and the service scene information; the Channel State Information (CSI) measurement mode comprises one of a prediction measurement mode, a compression measurement mode and a compression and prediction measurement mode.

Specifically, the base station 104 may obtain the CSI measurement mode according to the service scenario information when determining that the ue 102 supports the corresponding artificial intelligence model according to the capability information. Or firstly acquiring the service scene information and then judging the Channel State Information (CSI) measurement mode by combining the acquired capability information. The CSI measurement is used to determine whether the base station 104 and the ue 102 perform CSI compression and/or CSI prediction. For example, if the base station 104 determines that only the CSI compression model is supported by the current user terminal 102 according to the capability information, and determines that the CSI compression function can be performed in the current service scenario according to the service scenario information, at this time, the CSI measurement mode of the channel state information is determined to be the compression measurement mode. Similarly, when the user terminal 102 supports both the CSI compression model and the CSI prediction model and the CSI compression function and the CSI prediction function can be performed in the current traffic scenario, the CSI measurement mode of the channel state information is determined as the compression and prediction measurement mode.

Step S140, the CSI measurement parameters are configured and output according to the CSI measurement mode. Specifically, under different CSI measurement modes, the training data of the artificial intelligence model required by the base station 104 is also different, so that the base station 104 needs to configure corresponding CSI measurement parameters according to the CSI measurement mode, and send the CSI measurement parameters to the ue 102, so that the ue 102 collects the corresponding training data. For example, when the CSI measurement mode is determined to be the predictive measurement mode, the training data is a plurality of CSI values at the historical moment, and at this time, the ue 102 needs to control itself to obtain the plurality of CSI values at the historical moment by receiving the corresponding CSI measurement parameter; when the CSI measurement mode is determined to be the compression measurement mode, the training data may be the CSI value at the current time, and the ue 102 needs to control itself to obtain the CSI value at the current time by receiving the corresponding CSI measurement parameter.

Step S150, obtaining a Channel State Information (CSI) measurement result reported by a user terminal; the measurement result of the Channel State Information (CSI) is obtained by measuring the Channel State Information (CSI) according to the measurement parameter of the Channel State Information (CSI) by the user terminal. Specifically, the ue 102 measures CSI according to the CSI measurement parameter configured by the bs 104, and then sends the CSI measurement result obtained by the measurement to the bs 104. For example, when the CSI measurement mode is determined to be the predictive measurement mode, the CSI measurement parameters are a plurality of CSI values for configuring the measurement history of the ue 102, and the plurality of CSI values are reported to the bs 104 as CSI measurement results.

Step S160, training the artificial intelligent model according to the channel state information CSI measurement result to obtain a target model.

Specifically, the base station 104 trains the corresponding artificial intelligent model according to the channel state information CSI measurement result reported by the user terminal 102, thereby obtaining the target model. It is understood that the target model may include a CSI compression model and/or a CSI prediction model. When the Channel State Information (CSI) measurement mode is determined to be a prediction measurement mode, the target model obtained through training is the CSI prediction model; when the Channel State Information (CSI) measurement mode is determined to be a compression measurement mode, the target model obtained through training is a CSI compression model; when the Channel State Information (CSI) measurement mode is determined to be the compression and prediction measurement mode, the target model obtained through training comprises a CSI compression model and a CSI prediction model. It may be appreciated that, when the base station 104 trains the CSI compression model and the CSI prediction model, a specific training manner is determined according to the model type of the artificial intelligence model in the capability information reported by the user terminal 102.

Step S170, obtaining the channel state information CSI specific information according to the target model so as to schedule the current service. Specifically, after training to obtain the target model, the CSI specific information may be obtained by calculating according to the target model, and the base station 104 may schedule the current service according to the CSI specific information.

For a specific example, when the CSI measurement mode is determined to be the compression measurement mode, the target model obtained by training by the base station 104 is the CSI compression model. Fig. 3 is a schematic diagram of CSI compression based on a CSI compression model in one embodiment. The user terminal 102 performs preprocessing on the channel matrix H, and calculates a feature vector V of the channel matrix for each subband. The obtained characteristic vector is input into a CSI compression model for AI compression, the size of the output compressed CSI is smaller than that of the original characteristic vector V, and the compressed CSI obtained by the CSI compression model is output as a floating point vector. Since the CSI compression model cannot directly process complex inputs, the real and imaginary parts of the feature vector V need to be extracted and combined together for processing during processing. The user terminal 102 side converts the compressed CSI of the floating point vector into a quantized bit sequence through quantization to satisfy the bit width of CSI feedback. In preprocessing and post-processing, adaptive processing for bandwidth, feedback load and antenna port number needs to be considered. The CSI feedback information is transmitted from the ue 102 side to the base station side through a wireless channel, and after the base station side performs preprocessing, dequantization, AI decompression and post-processing on the CSI feedback information in sequence, a channel matrix H 'is obtained, where the channel matrix H' is used for scheduling the current service of the ue 102.

When the CSI measurement mode is determined to be the prediction measurement mode, the target model obtained by training by the base station 104 is the CSI prediction model. The CSI prediction model may predict CSI at the user terminal 102 side or the base station side to obtain corresponding specific CSI information. Fig. 4 is a schematic diagram illustrating CSI prediction performed by the ue 102 in one embodiment. The user terminal 102 predicts the value of CSItN at a later time by the CSI prediction model based on several (e.g., 16) historical CSIs measurements, namely CSIt-15, …, CSIt-1, CSIt 0. As shown in fig. 5, in an embodiment, a base station side CSI prediction diagram is shown, and after reporting a channel state information CSI measurement result to a base station 104, a base station side predicts a CSI value corresponding to a radio channel at a future scheduling time tN. It may be appreciated that, when the CSI measurement mode is determined to be the compression and prediction measurement mode, the target model obtained by training by the base station 104 is the CSI compression model and the CSI prediction model, and the specific processing procedure is the combination of the above processing procedures.

In the process of obtaining the specific information of the Channel State Information (CSI), the current scene is identified, and the corresponding target model is generated according to different scenes, so that the feedback load of the Channel State Information (CSI) can be reduced, and the CSI feedback precision can be improved on the premise of having the same feedback load of the Channel State Information (CSI).

In one embodiment, as shown in fig. 6, in step S130, a step of obtaining a channel state information CSI measurement mode according to the capability information and the service scenario information includes:

step S131, judging whether the user terminal supports the target model type according to the capability information.

Specifically, in this embodiment, after the base station 104 acquires the capability information and the service scenario information, it is first required to determine whether the user terminal 102 supports the target model type. It is to be appreciated that the target model type is a model type of the artificial intelligence model used by the base station 104 in performing CSI compression and/or CSI prediction functions. The target model type can be one or more, and a user can set the target model type according to the needs. The model type of the CSI compression model may be CNN, RNN, transformer, resNet, and the model type of the CSI prediction model may be FCN, RNN, 3D-CNN, and the like. The capability information includes a model type of the artificial intelligence model supported by the user terminal 102, and when the model type supported by the user terminal 102 is the same as the target model type, the base station 104 performs the subsequent steps to perform the CSI compression and/or CSI prediction function.

Step S132, if the target model type is supported, judging the channel state information CSI measurement mode according to the service scene information.

Specifically, the judgment is performed according to the capability information reported by the ue 102, and if the current ue 102 supports the target model type, it is indicated that the current ue 102 and the base station 104 may perform subsequent CSI compression and/or CSI prediction functions together, and at this time, the CSI measurement mode can be continuously judged according to the service scenario information. If the current ue 102 does not support the target model type, it indicates that the ue 102 does not have this function, and the base station 104 may notify the ue 102 to perform conventional CSI measurement through RRC (Radio Resource Control ) signaling.

In one embodiment, in step S132, the step of determining the CSI measurement mode according to the traffic scenario information includes: if the Channel State Information (CSI) feedback period is greater than a first threshold value or the moving speed of the user terminal is greater than a second threshold value, determining a CSI measurement mode as a prediction measurement mode; for a specific example, the first threshold may be set to 20ms, the second threshold may be set to 30km/h, and when the base station 104 detects that the CSI feedback period of the CSI in the traffic scenario information is greater than 20ms, or the moving speed of the ue is greater than 30km/h, the CSI measurement mode may be determined to be a prediction measurement mode, and the base station 104 and the ue 102 may start to perform the CSI prediction function. If the number of the Channel State Information (CSI) feedback bits is greater than a third threshold, determining a Channel State Information (CSI) measurement mode as a compression measurement mode; for example, the third threshold may be set to 40bits, and when the base station 104 detects that the number of CSI feedback bits of the channel state information in the service scenario information is greater than 40bits, the CSI measurement mode may be determined to be a compression measurement mode at this time, and the base station 104 and the ue 102 may start to perform the CSI compression function. If the Channel State Information (CSI) feedback period is greater than a first threshold or the moving speed of the user terminal is greater than a second threshold and the number of the CSI feedback bits of the channel state information is greater than a third threshold, determining the CSI measurement mode as a compression and prediction measurement mode; for example, when the above two conditions are satisfied at the same time, the CSI measurement mode is determined to be the compression and prediction measurement mode, and the base station 104 and the ue 102 start to perform CSI compression and CSI prediction functions. Through the judgment of the service scene information, the current service scene can be accurately identified, and the Channel State Information (CSI) measurement mode suitable for the current service scene is determined so as to execute the corresponding CSI compression and/or CSI prediction functions, thereby achieving the purposes of reducing the CSI feedback load or improving the CSI feedback precision on the premise of the same CSI feedback load and further improving the downlink system throughput.

In one embodiment, as shown in FIG. 7, the object model includes: in step S170, a step of obtaining specific information of channel state information CSI according to a target model includes:

step S171, the channel state information CSI compression model and the channel state information CSI prediction model are transmitted to the user terminal.

Specifically, in the embodiment of the present application, the channel state information CSI measurement mode determined according to the capability information and the service scenario information is a compression and prediction measurement mode, so that the target model trained by the base station 104 according to the channel state information CSI measurement result includes a channel state information CSI compression model and a channel state information CSI prediction model. After the base station 104 trains the target model, the CSI compression model and the CSI prediction model are sent to the user terminal 102. When the base station 104 sends the CSI compression model, the user terminal 102 may be first notified of the model type and the compression parameters of the CSI compression model, where the model type of the CSI compression model includes: CNN, RNN, transformer, etc., the compression parameters include: pretreatment mode, quantization mode, etc.; when the base station 104 sends the CSI prediction model, the user terminal 102 may be first notified of the model type and the prediction parameters of the CSI prediction model, where the model type of the CSI prediction model includes: FCN, RNN, 3D-CNN, etc., the prediction parameters include: predicted delay times (3 ms, 4ms, 5 ms), etc. Based on The obtained model type and compression parameters of The CSI compression model, the model type and prediction parameters of The CSI prediction model, the user terminal 102 downloads The corresponding CSI compression model and CSI prediction model from an OTT (Over-The-Top) server, so as to obtain a channel state information CSI compression model and a channel state information CSI prediction model in The user terminal 102.

Step S172, obtaining first channel state information CSI compression information reported by a user terminal; the user terminal predicts the first Channel State Information (CSI) measurement information according to the Channel State Information (CSI) prediction model.

Specifically, in this embodiment, the ue 102 performs CSI compression and CSI prediction functions. As shown in fig. 8, a schematic diagram of the user terminal 102 performing CSI compression and CSI prediction functions is shown. The ue 102 performs CSI measurement according to parameters configured by the bs 104 to obtain first CSI measurement information, performs CSI prediction according to a configured CSI prediction model (including a predicted delay time, etc.), to obtain first CSI prediction information, and performs CSI compression on the first CSI prediction information according to a configured CSI compression model, to obtain first CSI compression information. After obtaining the first channel state information CSI compression information, the user terminal 102 performs CSI reporting through an air interface, and the base station side can obtain the first channel state information CSI compression information.

Step S173 decompresses the first CSI compression information according to the CSI compression model to obtain CSI specific information. Specifically, after the base station 104 obtains the first CSI compressed information, the CSI is decompressed according to the CSI compressed model to obtain CSI specific information, and the base station 104 schedules the current service according to the CSI specific information to complete data transmission with the ue 102.

In one embodiment, as shown in FIG. 9, the object model includes: in step S170, a step of obtaining specific information of channel state information CSI according to a target model includes:

step S174, the channel state information CSI compression model is sent to the user terminal.

Specifically, in the embodiment of the present application, the channel state information CSI measurement mode determined according to the capability information and the service scenario information is a compression and prediction measurement mode, so that the target model trained by the base station 104 according to the channel state information CSI measurement result includes a channel state information CSI compression model and a channel state information CSI prediction model. After the base station 104 trains the target model, only the CSI compression model needs to be sent to the user terminal 102. When the base station 104 sends the CSI compression model, the user terminal 102 may be first notified of the model type and the compression parameters of the CSI compression model, where the model type of the CSI compression model includes: CNN, RNN, transformer, etc., the compression parameters include: preprocessing mode, quantization mode, etc. Based on The obtained model type and compression parameters of The CSI compression model, the user terminal 102 downloads The corresponding CSI compression model from an OTT (Over-The-Top) server, thereby obtaining a channel state information CSI compression model in The user terminal 102.

Step S175, obtaining second Channel State Information (CSI) compression information reported by a user terminal; the second Channel State Information (CSI) compression information is obtained by compressing second Channel State Information (CSI) measurement information by the user terminal according to a Channel State Information (CSI) compression model.

Specifically, in the present embodiment, the CSI compression function is performed in the user terminal 102, and the CSI prediction function is performed in the base station 104. As shown in fig. 10, the base station 104 performs CSI prediction. The user terminal 102 firstly performs CSI measurement according to parameters configured by the base station 104 to obtain second channel state information CSI measurement information, and then performs CSI compression on the second channel state information CSI measurement information according to a configured channel state information CSI compression model to obtain second channel state information CSI compression information. After obtaining the second channel state information CSI compressed information, the user terminal 102 performs CSI reporting through the air interface, so that the base station 104 obtains the second channel state information CSI compressed information.

Step S176, decompressing the second Channel State Information (CSI) compressed information according to the Channel State Information (CSI) compressed model to obtain second Channel State Information (CSI) decompressed information. Specifically, after obtaining the second channel state information CSI compression information, the base station 104 decompresses the second channel state information CSI compression information by using a trained channel state information CSI compression model, so as to obtain second channel state information CSI decompression information.

Step S177, the second channel state information CSI decompression information is predicted according to the channel state information CSI prediction model, and the channel state information CSI specific information is obtained. Specifically, after obtaining the second CSI decompression information, the base station 104 performs CSI prediction through the CSI prediction model, so as to obtain CSI specific information. The base station 104 then schedules the current service according to the CSI specific information, so as to complete data transmission with the ue 102.

In the above embodiment, the CSI prediction function is performed by the ue 102 and the bs 104, and the user may flexibly select according to a specific usage scenario. In the case where the computing power of the user terminal 102 is insufficient, the base station 104 may be used to perform CSI prediction functions, reducing the resource occupation of the user terminal 102. In case of higher load of the base station 104, the CSI prediction function can be performed using the user terminal 102, reducing the resource occupation of the base station 104.

In one embodiment, as shown in fig. 11, the present application further provides a channel state information feedback enhancement method, which is described by taking the application of the method to the ue 102 in fig. 1 as an example, and includes the following steps:

Step S210, reporting capability information to a base station; wherein the capability information includes model types of artificial intelligence models supported by the user terminal.

Step S220, obtaining Channel State Information (CSI) measurement parameters; the base station obtains the Channel State Information (CSI) measurement parameters according to a CSI measurement mode, wherein the CSI measurement mode is obtained by the base station according to capability information and service scene information, the CSI measurement mode comprises one of a prediction measurement mode, a compression measurement mode and a compression and prediction measurement mode, and the service scene information comprises: a Channel State Information (CSI) feedback period, a user terminal moving speed and a Channel State Information (CSI) feedback bit number.

The base station 104 may further obtain a channel state information CSI measurement mode according to the service scenario information when it is determined that the user terminal 102 supports the corresponding artificial intelligence model according to the capability information. Or firstly acquiring the service scene information and then judging the Channel State Information (CSI) measurement mode by combining the acquired capability information. The CSI measurement is used to determine whether the base station 104 and the ue 102 perform CSI compression and/or CSI prediction. For example, if the base station 104 determines that only the CSI compression model is supported by the current user terminal 102 according to the capability information, and determines that the CSI compression function can be performed in the current service scenario according to the service scenario information, at this time, the CSI measurement mode of the channel state information is determined to be the compression measurement mode. Similarly, when the user terminal 102 supports both the CSI compression model and the CSI prediction model and the CSI compression function and the CSI prediction function can be performed in the current traffic scenario, the CSI measurement mode of the channel state information is determined as the compression and prediction measurement mode.

Under different CSI measurement modes, the training data required by the base station 104 to train the artificial intelligence model is also different, so that the base station 104 needs to configure corresponding CSI measurement parameters according to the CSI measurement mode and send the CSI measurement parameters to the ue 102, so that the ue 102 collects the corresponding training data. For example, when the CSI measurement mode is determined to be the predictive measurement mode, the training data is a plurality of CSI values at the historical moment, and at this time, the ue 102 needs to control itself to obtain the plurality of CSI values at the historical moment by receiving the corresponding CSI measurement parameter; when the CSI measurement mode is determined to be the compression measurement mode, the training data may be the CSI value at the current time, and the ue 102 needs to control itself to obtain the CSI value at the current time by receiving the corresponding CSI measurement parameter.

Step S230, the channel state information CSI is measured according to the channel state information CSI measurement parameter, and the channel state information CSI measurement result is obtained. Specifically, the ue 102 measures CSI according to the CSI measurement parameter configured by the bs 104, and then sends the CSI measurement result obtained by the measurement to the bs 104. For example, when the CSI measurement mode is determined to be the predictive measurement mode, the CSI measurement parameters are a plurality of CSI values for configuring the measurement history of the ue 102, and the plurality of CSI values are reported to the bs 104 as CSI measurement results.

Step S240, a target model is obtained, and channel state information CSI specific information is obtained according to the target model; the target model is obtained by training an artificial intelligent model by the base station according to a Channel State Information (CSI) measurement result, and the Channel State Information (CSI) specific information is used for scheduling the current service.

Specifically, the base station 104 trains the corresponding artificial intelligent model according to the channel state information CSI measurement result reported by the user terminal 102, thereby obtaining the target model. It is understood that the target model may include a CSI compression model and/or a CSI prediction model. When the Channel State Information (CSI) measurement mode is determined to be a prediction measurement mode, the target model obtained through training is the CSI prediction model; when the Channel State Information (CSI) measurement mode is determined to be a compression measurement mode, the target model obtained through training is a CSI compression model; when the Channel State Information (CSI) measurement mode is determined to be the compression and prediction measurement mode, the target model obtained through training comprises a CSI compression model and a CSI prediction model. It may be appreciated that, when the base station 104 trains the CSI compression model and the CSI prediction model, a specific training manner is determined according to the model type of the artificial intelligence model in the capability information reported by the user terminal 102. The training CSI compression model and the CSI prediction model are the same as those in the above embodiments, and will not be described in detail here.

In one embodiment, the channel state information CSI measurement method is obtained by the base station according to the capability information and the service scenario information, and includes: the capability information is used for indicating the base station to judge whether the user terminal 102 supports the target model type, and if so, judging the channel state information CSI measurement mode according to the service scene information.

Specifically, in this embodiment, after the base station 104 acquires the capability information and the service scenario information, it is first required to determine whether the user terminal 102 supports the target model type. It is to be appreciated that the target model type is a model type of the artificial intelligence model used by the base station 104 in performing CSI compression and/or CSI prediction functions. The target model type can be one or more, and a user can set the target model type according to the needs. The model type of the CSI compression model may be CNN, RNN, transformer, resNet, and the model type of the CSI prediction model may be FCN, RNN, 3D-CNN, and the like. The capability information includes a model type of the artificial intelligence model supported by the user terminal 102, and when the model type supported by the user terminal 102 is the same as the target model type, the base station 104 performs the subsequent steps to perform the CSI compression and/or CSI prediction function. The base station 104 determines according to the capability information reported by the user terminal 102, if the current user terminal 102 supports the target model type, it is indicated that the current user terminal 102 and the base station 104 can perform the subsequent CSI compression and/or CSI prediction functions together, and at this time, the channel state information CSI measurement mode can be determined continuously according to the service scenario information. If the current ue 102 does not support the target model type, it indicates that the ue 102 does not have this function, and the base station 104 may notify the ue 102 to perform conventional CSI measurement through RRC (Radio Resource Control ) signaling.

In one embodiment, the step of determining the CSI measurement mode according to the traffic scenario information includes: if the Channel State Information (CSI) feedback period is greater than a first threshold value or the moving speed of the user terminal is greater than a second threshold value, determining a CSI measurement mode as a prediction measurement mode; for a specific example, the first threshold may be set to 20ms, the second threshold may be set to 30km/h, and when the base station 104 detects that the CSI feedback period of the CSI in the traffic scenario information is greater than 20ms, or the moving speed of the ue is greater than 30km/h, the CSI measurement mode may be determined to be a prediction measurement mode, and the base station 104 and the ue 102 may start to perform the CSI prediction function. If the number of the Channel State Information (CSI) feedback bits is greater than a third threshold, determining a Channel State Information (CSI) measurement mode as a compression measurement mode; for example, the third threshold may be set to 40bits, and when the base station 104 detects that the number of CSI feedback bits of the channel state information in the service scenario information is greater than 40bits, the CSI measurement mode may be determined to be a compression measurement mode at this time, and the base station 104 and the ue 102 may start to perform the CSI compression function. If the Channel State Information (CSI) feedback period is greater than a first threshold or the moving speed of the user terminal is greater than a second threshold and the number of the CSI feedback bits of the channel state information is greater than a third threshold, determining the CSI measurement mode as a compression and prediction measurement mode; for example, when the above two conditions are satisfied at the same time, the CSI measurement mode is determined to be the compression and prediction measurement mode, and the base station 104 and the ue 102 start to perform CSI compression and CSI prediction functions. Through the judgment of the service scene information, the current service scene can be accurately identified, and the Channel State Information (CSI) measurement mode suitable for the current service scene is determined so as to execute the corresponding CSI compression and/or CSI prediction functions, thereby achieving the purposes of reducing the CSI feedback load or improving the CSI feedback precision on the premise of the same CSI feedback load and further improving the downlink system throughput.

In one embodiment, as shown in FIG. 12, the object model includes: in step S240, a target model is obtained, and specific information of channel state information CSI is obtained according to the target model, including:

step S241, a channel state information CSI compression model and a channel state information CSI prediction model sent by the base station are obtained.

In step S242, the first CSI measurement information is predicted according to the CSI prediction model, so as to obtain the CSI prediction information. Specifically, in this embodiment, the ue 102 performs CSI compression and CSI prediction functions. As shown in fig. 8, a schematic diagram of the user terminal 102 performing CSI compression and CSI prediction functions is shown. The ue 102 performs CSI measurement according to parameters configured by the bs 104 to obtain CSI measurement information of the first channel state information, and performs CSI prediction according to a configured CSI prediction model (including a predicted delay time and the like), thereby obtaining CSI prediction information of the first channel state information.

Step S243, compressing the first channel state information CSI prediction information according to the channel state information CSI compression model to obtain first channel state information CSI compression information. Specifically, after obtaining the first CSI prediction information, the ue 102 performs CSI compression on the first CSI prediction information according to the configured CSI compression model, so as to obtain CSI compression information of the first CSI.

Step S244, reporting the first Channel State Information (CSI) compression information to a base station to obtain the specific information of the Channel State Information (CSI); the specific information of the Channel State Information (CSI) is obtained by decompressing the first Channel State Information (CSI) according to a CSI compression model by a base station. Specifically, after obtaining the CSI compressed information of the first channel state information, the ue 102 performs CSI reporting through an air interface, and the base station side may obtain the CSI compressed information of the first channel state information. After the base station 104 obtains the first channel state information CSI compressed information, the first channel state information CSI compressed information is subjected to CSI decompression according to the channel state information CSI compressed model, so that channel state information CSI specific information can be obtained, and the base station 104 can complete data transmission with the user terminal 102 by subsequently scheduling the current service according to the channel state information CSI specific information.

In one embodiment, as shown in FIG. 13, the object model includes: in step S240, a target model is obtained, and specific information of channel state information CSI is obtained according to the target model, including:

step S245, a channel state information CSI compression model sent by a base station is obtained.

Step S246, compressing the second CSI measurement information according to the CSI compression model to obtain the second CSI compression information.

Step S247, reporting second Channel State Information (CSI) compression information to the base station to obtain Channel State Information (CSI) specific information; the base station predicts second Channel State Information (CSI) decompression information according to the CSI prediction model, and the second Channel State Information (CSI) decompression information is obtained by decompressing second Channel State Information (CSI) compression information according to the CSI compression model.

Specifically, after obtaining the second channel state information CSI compression information, the base station 104 decompresses the second channel state information CSI compression information by using a trained channel state information CSI compression model, so as to obtain second channel state information CSI decompression information. After obtaining the second CSI decompression information, the base station 104 performs CSI prediction through the CSI prediction model, so as to obtain CSI specific information. The base station 104 then schedules the current service according to the CSI specific information, so as to complete data transmission with the ue 102.

The channel state information feedback enhancement method of the present application is described in detail below in one specific embodiment. As shown in fig. 14, in one embodiment, the signaling interaction between the base station 104 and the ue 102 is schematically shown, and the CSI prediction function is performed by the ue 102, specifically, the following steps are performed:

In step S300, the base station 104 sends a capability query message uecapability requirement to the user terminal 102 to obtain whether the user terminal 102 supports CSI compression based on an artificial intelligence model or CSI prediction capability based on an artificial intelligence model, and obtains the CSI compression model type (CNN, RNN, transformer, resNet, etc.) and CSI prediction model type (FCN, RNN, 3D-CNN, etc.) supported by the user terminal 102 from the capability information.

In step S301, the ue 102 sends a capability query result, i.e. capability information uecapability information, to the base station 104, and two cells are newly added in the capability information of the ue 102, which is specifically as follows:

ai-CsiEncoderDecoder ENUMERATED{supported}OPTIONAL，

ai-CsiPrediction ENUMERATED{supported}OPTIONAL，

ai-CsiEncoderDecoder&Prediction ENUMERATED{supported}OPTIONAL，

ai-CsiEncoderDecoder-Type ENUMERATED{CNN,RNN,Transformer,ResNet,…}OPTIONAL，

ai-CsiPrediction-Type ENUMERATED{FCN,RNN,3D-CNN,…}OPTIONAL，

in step S302, the base station 104 determines whether to execute the CSI compression and CSI prediction functions based on the capability information reported by the ue 102 and the current service scenario information, and if the specific determination conditions are the same as those in the above embodiment, the step S303 is proceeded to if the current base station 104 determines that the ue 102 satisfies the CSI compression and CSI prediction functions.

In step S303, the base station 104 configures CSI measurement parameters for artificial intelligence model training through an rrcrecon configuration message according to the capability information of the user terminal 102 acquired in step S301.

In step S304, the user terminal 102 measures CSI according to the CSI measurement parameters configured by the base station 104, and transmits the CSI measurement result as CSI training data to the base station 104 through the user plane to perform training of the CSI compression model and the CSI prediction model.

In step S305, the base station 104 performs training of the model and parameters according to the flow in fig. 3 and 4 according to the CSI training data acquired from the user terminal 102 and the CSI compression model and CSI prediction model supported by the user terminal 102 acquired in step S301.

In step S306, after completing the training of the CSI compression model and the CSI prediction model, the base station 104 notifies the user terminal 102 of the type and compression parameter of the CSI compression model, the type and prediction parameter of the CSI prediction model, wherein: types of CSI compression models include: CNN, RNN, transformer, etc., CSI compression parameters include: pretreatment mode, quantization mode, etc.; types of CSI prediction models include: FCN, RNN, 3D-CNN, etc., and CSI prediction parameters include: predicted delay times (e.g., 3ms, 4ms, 5ms, etc.), etc.

In step S307, the base station 104 configures CSI measurement parameters for traffic scheduling by the rrcrecon configuration message.

In step S308, the user terminal 102 downloads The CSI prediction model from The OTT (Over-The-Top) server based on The type and The prediction parameters of The CSI prediction model obtained in step S306, and performs CSI prediction reasoning with reference to The flow in fig. 4 after CSI measurement.

In step S309, based on the type and the compression parameters of the CSI compression model acquired in step S306, the user terminal 102 downloads the CSI compression model from the OTT server, and performs CSI compression reasoning on the compressed CSI generated in step S309 with reference to the flow in fig. 8.

Step S310, the user terminal 102 reports compressed CSI information;

in step S311, the base station 104 performs CSI decompression reasoning on the compressed CSI information reported by the user terminal 102, and obtains CSI specific information reported by the user terminal 102.

In step S312, the base station 104 schedules the current service based on the acquired CSI specific information, and transmits the data to the user terminal 102.

The channel state information feedback enhancement method of the present application is described in detail below in another specific embodiment. As shown in fig. 15, in another embodiment, signaling interaction between the base station 104 and the ue 102 is schematically shown, and the CSI prediction function is performed by the base station 104, specifically, the following steps are performed:

in step S400, the base station 104 sends a capability query message uecapability requirement to the user terminal 102 to obtain whether the user terminal 102 supports CSI compression based on an artificial intelligence model or CSI prediction capability based on an artificial intelligence model, and obtains the CSI compression model type (CNN, RNN, transformer, resNet, etc.) and CSI prediction model type (FCN, RNN, 3D-CNN, etc.) supported by the user terminal 102 from the capability information.

In step S401, the ue 102 sends a capability query result, i.e. capability information uecapability information, to the base station 104, and two cells are newly added in the capability information of the ue 102, which is specifically as follows:

ai-CsiEncoderDecoder ENUMERATED{supported}OPTIONAL，

ai-CsiPrediction ENUMERATED{supported}OPTIONAL，

ai-CsiEncoderDecoder&Prediction ENUMERATED{supported}OPTIONAL，

ai-CsiEncoderDecoder-Type ENUMERATED{CNN,RNN,Transformer,ResNet,…}OPTIONAL，

ai-CsiPrediction-Type ENUMERATED{FCN,RNN,3D-CNN,…}OPTIONAL，

In step S402, the base station 104 determines whether to execute the CSI compression and CSI prediction functions based on the capability information reported by the ue 102 and the current service scenario information, and if the specific determination conditions are the same as those in the above embodiment, the step S403 is proceeded to if the current base station 104 determines that the ue 102 satisfies the CSI compression and CSI prediction functions.

In step S403, the base station 104 configures CSI measurement parameters for artificial intelligence model training through an rrcrecon configuration message according to the capability information of the user terminal 102 acquired in step S401.

In step S404, the user terminal 102 measures CSI according to the CSI measurement parameters configured by the base station 104, and transmits the CSI measurement result as CSI training data to the base station 104 through the user plane to perform training of the CSI compression model and the CSI prediction model.

In step S405, the base station 104 performs training of the model and parameters according to the flow in fig. 3 and 4 according to the CSI training data acquired from the user terminal 102 and the CSI compression model and CSI prediction model supported by the user terminal 102 acquired in step S401.

In step S406, after the base station 104 completes training of the CSI compression model and the CSI prediction model, only the type and compression parameters of the CSI compression model to be used need to be notified to the user terminal 102, wherein: types of CSI compression models include: CNN, RNN, transformer, etc., CSI compression parameters include: preprocessing mode, quantization mode, etc.

In step S407, the base station 104 configures CSI measurement parameters for traffic scheduling by an rrcrecon configuration message.

In step S408, the user terminal 102 downloads The CSI compression model from The OTT (Over-The-Top) server based on The type and compression parameters of The CSI compression model acquired in step S406, and performs CSI compression reasoning with reference to The flow in fig. 3 after CSI measurement.

In step S409, the user terminal 102 reports the compressed CSI information.

In step S410, the base station 104 performs CSI decompression reasoning on the compressed CSI information reported by the user terminal 102, and obtains a CSI compression reasoning result reported by the user terminal 102.

In step S411, based on the CSI compression reasoning result obtained in step S410, based on the CSI prediction model, the base station 104 performs CSI prediction reasoning with reference to the flow of the left block diagram in fig. 10, to obtain CSI specific information.

In step S412, the base station 104 schedules the current service based on the acquired CSI specific information, and transmits the data to the user terminal 102.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a channel state information feedback enhancing device for implementing the above related channel state information feedback enhancing method. The implementation of the solution provided by the apparatus is similar to the implementation described in the above method, so the specific limitation in the embodiments of the channel state information feedback enhancing apparatus provided below may refer to the limitation of the channel state information feedback enhancing method hereinabove, and will not be repeated herein.

In one embodiment, as shown in fig. 16, a channel state information feedback enhancing apparatus is provided, applied to a base station 104, and includes: the system comprises a capability information acquisition module 510, a business scenario information acquisition module 520, a measurement mode calculation module 530, a measurement parameter output module 540, a measurement result acquisition module 550, a model training module 560 and a specific information calculation module 570, wherein:

the capability information obtaining module 510 is configured to obtain capability information reported by the user terminal 102; wherein the capability information includes model types of artificial intelligence models supported by the user terminal 102;

the service scenario information obtaining module 520 is configured to obtain current service scenario information; the service scene information comprises: a Channel State Information (CSI) feedback period, a user terminal moving speed and a Channel State Information (CSI) feedback bit number;

A measurement mode calculation module 530, configured to obtain a channel state information CSI measurement mode according to the capability information and the service scenario information; the Channel State Information (CSI) measurement mode comprises one of a prediction measurement mode, a compression measurement mode and a compression and prediction measurement mode;

a measurement parameter output module 540, configured to configure and output a channel state information CSI measurement parameter according to a channel state information CSI measurement mode;

a measurement result obtaining module 550, configured to obtain a measurement result of channel state information CSI reported by the user terminal 102; the measurement result of the channel state information CSI is obtained by the user terminal 102 measuring the channel state information CSI according to the measurement parameter of the channel state information CSI;

the model training module 560 is configured to train the artificial intelligent model according to the CSI measurement result to obtain a target model;

the specific information calculating module 570 is configured to obtain the specific information of the channel state information CSI according to the target model, so as to schedule the current service.

For specific limitations of the channel state information feedback enhancing apparatus implemented from the perspective of the base station 104, reference may be made to the above limitation of the channel state information feedback enhancing method implemented from the perspective of the base station 104, and no further description is given here. The various modules in the channel state information feedback enhancement device implemented from the perspective of the base station 104 described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules. It should be noted that, in the embodiment of the present application, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation.

In one embodiment, as shown in fig. 17, there is further provided a channel state information feedback enhancing apparatus, applied to the user terminal 102, including: the capability information reporting module 610, the measurement parameter acquiring module 620, the measurement result calculating module 630 and the model acquiring module 640, wherein:

a capability information reporting module 610, configured to report capability information to a base station; wherein the capability information includes model types of artificial intelligence models supported by the user terminal 102;

a measurement parameter acquisition module 620, configured to acquire a channel state information CSI measurement parameter; the base station obtains the Channel State Information (CSI) measurement parameters according to a CSI measurement mode, wherein the CSI measurement mode is obtained by the base station according to capability information and service scene information, the CSI measurement mode comprises one of a prediction measurement mode, a compression measurement mode and a compression and prediction measurement mode, and the service scene information comprises: a Channel State Information (CSI) feedback period, a user terminal moving speed and a Channel State Information (CSI) feedback bit number;

the measurement result calculation module 630 is configured to measure the channel state information CSI according to the channel state information CSI measurement parameter, to obtain a channel state information CSI measurement result;

The model acquisition module 640 is configured to acquire a target model, and obtain channel state information CSI specific information according to the target model; the target model is obtained by training an artificial intelligent model by the base station according to a Channel State Information (CSI) measurement result, and the Channel State Information (CSI) specific information is used for scheduling the current service.

For specific limitations on the channel state information feedback enhancement device implemented from the perspective of the user terminal 102, reference may be made to the above limitation on the channel state information feedback enhancement method implemented from the perspective of the user terminal 102, and no further description is given here. The respective modules in the channel state information feedback enhancing apparatus implemented from the perspective of the user terminal 102 may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules. It should be noted that, in the embodiment of the present application, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation.

In one embodiment, a channel state information feedback enhancement system is provided, including a base station and a user terminal 102 connected to the base station; wherein: the base station is used for executing the channel state information feedback enhancement method implemented from the base station angle; the user terminal 102 is configured to perform the steps of the channel state information feedback enhancement method implemented from the perspective of the user terminal 102 described above.

In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the steps of the method embodiments described above.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. A method for enhancing feedback of channel state information, wherein the method is applied to a base station, and the method comprises:

2. The method for enhancing channel state information feedback according to claim 1, wherein the step of obtaining the CSI measurement mode according to the capability information and the traffic scenario information comprises:

judging whether the user terminal supports a target model type according to the capability information;

And if the target model type is supported, judging the Channel State Information (CSI) measurement mode according to the service scene information.

3. The method for enhancing channel state information feedback according to claim 2, wherein the step of determining the CSI measurement mode according to the traffic scenario information comprises:

if the Channel State Information (CSI) feedback period is greater than a first threshold value or the moving speed of the user terminal is greater than a second threshold value, determining the CSI measurement mode as a prediction measurement mode;

if the number of the Channel State Information (CSI) feedback bits is larger than a third threshold, determining the Channel State Information (CSI) measurement mode as a compression measurement mode;

and if the Channel State Information (CSI) feedback period is greater than a first threshold or the moving speed of the user terminal is greater than a second threshold and the number of the CSI feedback bits is greater than a third threshold, determining the CSI measurement mode as a compression and prediction measurement mode.

4. The channel state information feedback enhancement method of claim 1, wherein the target model comprises: the step of obtaining the specific information of the Channel State Information (CSI) according to the target model comprises the following steps:

Transmitting the Channel State Information (CSI) compression model and the CSI prediction model to the user terminal;

acquiring first Channel State Information (CSI) compression information reported by the user terminal; the user terminal compresses first Channel State Information (CSI) prediction information according to the CSI compression model, and the first Channel State Information (CSI) prediction information is obtained by predicting first Channel State Information (CSI) measurement information according to the CSI prediction model;

decompressing the first Channel State Information (CSI) compressed information according to the Channel State Information (CSI) compressed model to obtain the specific information of the Channel State Information (CSI).

5. The channel state information feedback enhancement method of claim 1, wherein the target model comprises: the step of obtaining the specific information of the Channel State Information (CSI) according to the target model comprises the following steps:

transmitting the Channel State Information (CSI) compression model to the user terminal;

Acquiring second Channel State Information (CSI) compression information reported by the user terminal; the user terminal compresses second Channel State Information (CSI) measurement information according to the CSI compression model;

decompressing the second Channel State Information (CSI) compression information according to the Channel State Information (CSI) compression model to obtain second CSI decompression information;

and predicting the second Channel State Information (CSI) decompression information according to the Channel State Information (CSI) prediction model to obtain the Channel State Information (CSI) specific information.

6. A method for enhancing feedback of channel state information, wherein the method is applied to a user terminal, and the method comprises:

7. The method for enhancing channel state information feedback according to claim 6, wherein the channel state information CSI measurement method is obtained by the base station according to the capability information and the service scenario information, and includes: the capability information is used for indicating the base station to judge whether the user terminal supports a target model type, and if the user terminal supports the target model type, judging the Channel State Information (CSI) measurement mode according to the service scene information.

8. The method for enhancing channel state information feedback according to claim 7, wherein the step of determining the CSI measurement mode according to the traffic scenario information comprises:

9. The channel state information feedback enhancement method of claim 6, wherein the target model comprises: the step of obtaining the target model and obtaining the specific information of the Channel State Information (CSI) according to the target model comprises the following steps:

acquiring the Channel State Information (CSI) compression model and the Channel State Information (CSI) prediction model sent by the base station;

predicting the first Channel State Information (CSI) measurement information according to the CSI prediction model to obtain first CSI prediction information;

Compressing the first Channel State Information (CSI) prediction information according to the Channel State Information (CSI) compression model to obtain first CSI compression information;

reporting the first Channel State Information (CSI) compression information to the base station to obtain the specific information of the Channel State Information (CSI); the specific information of the Channel State Information (CSI) is obtained by decompressing the first Channel State Information (CSI) compressed information according to the CSI compression model by the base station.

10. The channel state information feedback enhancement method of claim 6, wherein the target model comprises: the step of obtaining the target model and obtaining the specific information of the Channel State Information (CSI) according to the target model comprises the following steps:

acquiring the Channel State Information (CSI) compression model sent by the base station;

compressing second Channel State Information (CSI) measurement information according to the CSI compression model to obtain second CSI compression information;

reporting the second Channel State Information (CSI) compression information to the base station to obtain the Channel State Information (CSI) specific information; the base station predicts second Channel State Information (CSI) decompression information according to the CSI prediction model, and the second Channel State Information (CSI) decompression information is obtained by decompressing the second Channel State Information (CSI) compression information according to the CSI compression model.

11. A channel state information feedback enhancement device, wherein the device is applied to a base station, and the device comprises:

12. A channel state information feedback enhancement device, wherein the device is applied to a user terminal, the device comprising:

13. The channel state information feedback enhancement system is characterized by comprising a base station and a user terminal connected with the base station; wherein:

the base station being adapted to perform the steps of the method of any one of claims 1 to 5;

the user terminal being adapted to perform the steps of the method of any of claims 6 to 10.

14. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 10.