WO2025140233A1 - Csi prediction method and apparatus, csi prediction result monitoring method and apparatus, device, and readable storage medium - Google Patents

Abstract

The present application relates to the technical field of communications, and in particular to a CSI prediction method and apparatus, a CSI prediction result monitoring method and apparatus, a device, and a readable storage medium. The CSI prediction method comprises: a terminal receives first configuration information from a network side device; the terminal sends first CSI to the network side device on the basis of the first configuration information; the terminal receives a first AI unit from the network side device; and the terminal performs CSI prediction by means of the first AI unit, wherein the first configuration information is used for configuring the terminal to determine the first CSI on the basis of a first CSI-RS on a target resource and send the first CSI, the target resource comprises at least one of a time domain resource, a frequency domain resource and a spatial domain resource, the first CSI is used for generating training data of the first AI unit, and the first AI unit is an AI unit obtained by performing training by the network side device on the basis of the first CSI.

Description

CSI prediction method, CSI prediction result monitoring method, device, equipment and readable storage medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese Patent Application No. 202311870970.2 filed in China on December 29, 2023, the entire contents of which are incorporated herein by reference.

Technical Field

The present application belongs to the field of communication technology, and specifically relates to a CSI prediction method, a monitoring method, device, equipment and a readable storage medium for CSI prediction results.

Background Art

At present, the scheme for channel state information (CSI) prediction only involves time domain prediction. However, other CSI prediction functions can also be realized in related technologies, such as CSI time domain interpolation, CSI frequency domain interpolation, CSI spatial domain interpolation, CSI frequency domain extrapolation/prediction, CSI spatial domain prediction/extrapolation, etc. Therefore, there is an urgent need for an implementation method that can support multiple CSI prediction functions.

Summary of the invention

The embodiments of the present application provide a CSI prediction method, a monitoring method, an apparatus, a device and a readable storage medium for CSI prediction results, which can support multiple CSI prediction functions.

In a first aspect, a CSI prediction method is provided, including:

The terminal receives first configuration information from the network side device;

The terminal sends a first CSI to the network side device according to the first configuration information;

The terminal receives a first AI unit from the network side device;

The terminal performs CSI prediction through the first AI unit;

Among them, the first configuration information is used to configure the terminal to determine the first CSI and send the first CSI based on the first channel state information reference signal CSI-RS on the target resource, the target resource includes at least one of time domain resources, frequency domain resources and spatial domain resources, the first CSI is used to generate training data for the first AI unit, and the first AI unit is an AI unit obtained by the network side device training according to the first CSI.

In a second aspect, a CSI prediction method is provided, including:

The network side device sends first configuration information to the terminal;

The network side device receives first CSI from the terminal;

The network side device trains a first AI unit according to the first CSI;

The network side device sends the first AI unit to the terminal;

The first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI-RS on the target resource, the target resource includes at least one of a time domain resource, a frequency domain resource, and a spatial domain resource, the first CSI is used to generate training data for the first AI unit, and the first AI unit is used for the terminal to perform CSI prediction.

In a third aspect, a method for monitoring a CSI prediction result is provided, including:

The terminal receives a third CSI-RS from the network side device;

The terminal determines a third CSI according to the third CSI-RS;

The terminal monitors the predicted CSI predicted by the first AI unit according to the third CSI;

The predicted CSI is the CSI predicted by the first AI unit according to the fourth CSI, and the resource locations of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

In a fourth aspect, a method for monitoring a CSI prediction result is provided, including:

The network side device sends a third CSI-RS to the terminal;

Among them, the third CSI-RS is used by the terminal to determine the third CSI, the third CSIS is used by the terminal to monitor the predicted CSI predicted and output by the first AI unit, the predicted CSI is the CSI obtained by the first AI unit based on the fourth CSI prediction, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located in different resource locations.

In a fifth aspect, a CSI prediction device is provided, including:

A first receiving module, used for the terminal to receive first configuration information from a network side device;

A first sending module, configured for the terminal to send a first CSI to the network side device according to the first configuration information;

A second receiving module, configured for the terminal to receive a first AI unit from the network side device;

A prediction module, configured for the terminal to perform CSI prediction through the first AI unit;

Among them, the first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI-RS on the target resource, the target resource includes at least one of time domain resources, frequency domain resources and spatial domain resources, the first CSI is used to generate training data for the first AI unit, and the first AI unit is an AI unit obtained by the network side device training according to the first CSI.

In a sixth aspect, a CSI prediction device is provided, including:

A second sending module, used for the network side device to send the first configuration information to the terminal;

A third receiving module, configured for the network side device to receive the first CSI from the terminal;

A training module, configured for the network side device to train a first AI unit according to the first CSI;

A third sending module, configured for the network side device to send the first AI unit to the terminal;

The first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI-RS on the target resource, the target resource includes at least one of a time domain resource, a frequency domain resource, and a spatial domain resource, the first CSI is used to generate training data for the first AI unit, and the first AI unit is used for the terminal to perform CSI prediction.

In a seventh aspect, a monitoring device for a CSI prediction result is provided, including:

A fourth receiving module, configured for the terminal to receive a third CSI-RS from a network side device;

A first determining module, configured for the terminal to determine a third CSI according to the third CSI-RS;

A monitoring module, configured for the terminal to monitor the predicted CSI predicted by the first AI unit according to the third CSI;

The predicted CSI is the CSI predicted by the first AI unit according to the fourth CSI, and the resource locations of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

In an eighth aspect, a monitoring device for a CSI prediction result is provided, including:

A fourth sending module, configured for the network side device to send a third CSI-RS to the terminal;

Among them, the third CSI-RS is used by the terminal to determine the third CSI, the third CSIS is used by the terminal to monitor the predicted CSI predicted and output by the first AI unit, the predicted CSI is the CSI obtained by the first AI unit based on the fourth CSI prediction, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located in different resource locations.

In the ninth aspect, a terminal is provided, which includes a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the third aspect are implemented.

In a tenth aspect, a terminal is provided, comprising a processor and a communication interface;

The communication interface is used for the terminal to receive first configuration information from the network side device; the terminal sends the first CSI to the network side device according to the first configuration information; the terminal receives the first AI unit from the network side device;

The processor is used for the terminal to perform CSI prediction through the first AI unit;

Among them, the first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI-RS on the target resource, the target resource includes at least one of time domain resources, frequency domain resources and spatial domain resources, the first CSI is used to generate training data for the first AI unit, and the first AI unit is an AI unit obtained by the network side device training according to the first CSI.

Alternatively, the communication interface is used for the terminal to receive a third CSI-RS from a network side device;

The processor is used for the terminal to determine the third CSI according to the third CSI-RS; the terminal monitors the predicted CSI predicted by the first AI unit according to the third CSI;

The predicted CSI is the CSI predicted by the first AI unit according to the fourth CSI, and the resource locations of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

In the eleventh aspect, a network side device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the second aspect are implemented, or the steps of the method described in the fourth aspect are implemented.

In a twelfth aspect, a network side device is provided, including a processor and a communication interface;

The communication interface is used for the network side device to send the first configuration information to the terminal; the network side device receives the first CSI from the terminal;

The processor is used for the network side device to train a first AI unit according to the first CSI;

The communication interface is used by the network side device to send the first AI unit to the terminal;

The first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI-RS on the target resource, the target resource includes at least one of a time domain resource, a frequency domain resource, and a spatial domain resource, the first CSI is used to generate training data for the first AI unit, and the first AI unit is used for the terminal to perform CSI prediction.

Alternatively, the communication interface is used by the network side device to send a third CSI-RS to the terminal;

Among them, the third CSI-RS is used by the terminal to determine the third CSI, the third CSIS is used by the terminal to monitor the predicted CSI predicted and output by the first AI unit, the predicted CSI is the CSI obtained by the first AI unit based on the fourth CSI prediction, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located in different resource locations.

In the twelfth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented, or the steps of the method described in the third aspect are implemented, or the steps of the method described in the fourth aspect are implemented.

In the thirteenth aspect, a wireless communication system is provided, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the method described in the first aspect or the third aspect, and the network side device can be used to execute the steps of the method described in the second aspect or the fourth aspect.

In the fourteenth aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instructions to implement the steps of the method described in the first aspect, or the steps of the method described in the second aspect, or the steps of the method described in the third aspect, or the steps of the method described in the fourth aspect.

In the fifteenth aspect, a computer program/program product is provided, which is stored in a storage medium, and the program/program product is executed by at least one processor to implement the steps of the method described in the first aspect, or the steps of the method described in the second aspect, the steps of the method described in the third aspect, or the steps of the method described in the fourth aspect.

In an embodiment of the present application, the network side device provides the terminal with the configuration information of CSI-RS, the terminal determines the first CSI according to the configuration information and sends it to the network side device, the first CSI is used as training data to train the first AI unit on the network side, the network side device sends the first AI unit to the terminal, and the terminal predicts CSI through the first AI unit. In this way, for various types of CSI prediction, it is only necessary to provide different CSI-RS configuration information to the terminal based on the above process, the terminal feeds back the corresponding training data to the network side device, the network side trains the corresponding AI unit based on the training data and sends it to the terminal, the terminal implements CSI prediction based on the AI unit, and based on the same set of signaling processes, the data collection and reasoning process required for various AI-based prediction functions can be realized, which can greatly reduce the signaling overhead, improve the resource utilization of the system, and help improve the throughput of the system.

In an embodiment of the present application, in the monitoring stage, the network side device sends a CSI-RS to the terminal at a resource location different from the CSI-RS in the reasoning stage. The terminal monitors the results predicted by the AI unit based on the CSI-RS in the monitoring stage to ensure the accuracy of the prediction results. Moreover, based on the same set of signaling processes, the monitoring process required for various AI-based prediction functions can be implemented, which can greatly reduce signaling overhead, improve system resource utilization, and help improve system throughput.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1a is a block diagram of a wireless communication system applicable to an embodiment of the present application;

Fig. 1b is a schematic diagram of a neural network;

Figure 1c is a schematic diagram of a neuron;

FIG1d is a schematic diagram of CSI prediction based on AI;

FIG1e is a performance diagram of AI-based CSI prediction;

FIG2 is a flow chart of a CSI prediction method according to an embodiment of the present application;

FIG3 is a second flow chart of the CSI prediction method provided in an embodiment of the present application;

FIG4 is a flow chart of a method for monitoring CSI prediction results according to an embodiment of the present application;

FIG5 is a second flow chart of a method for monitoring CSI prediction results provided in an embodiment of the present application;

FIG6 is a schematic diagram of a structure of a CSI prediction device provided in an embodiment of the present application;

FIG7 is a second schematic diagram of the structure of the CSI prediction device provided in an embodiment of the present application;

FIG8 is a schematic diagram of a structure of a monitoring device for CSI prediction results provided in an embodiment of the present application;

FIG9 is a second schematic diagram of the structure of the monitoring device for CSI prediction results provided in an embodiment of the present application;

FIG10 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application;

FIG11 is a schematic diagram of the structure of a terminal provided in an embodiment of the present application;

FIG12 is a schematic diagram of a structure of a network side device according to an embodiment of the present application;

FIG. 13 is a second schematic diagram of the structure of the network side device provided in an embodiment of the present application.

DETAILED DESCRIPTION

The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of this application.

The terms "first", "second", etc. of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of one type, and the number of objects is not limited, for example, the first object can be one or more. In addition, "or" in the present application represents at least one of the connected objects. For example, "A or B" covers three schemes, namely, Scheme 1: including A but not including B; Scheme 2: including B but not including A; Scheme 3: including both A and B. The character "/" generally indicates that the objects associated with each other are in an "or" relationship.

The term "indication" in this application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, operations to be performed, or request results in the sent indication; an indirect indication can be understood as the receiver determining the corresponding information according to the indication sent by the sender, or making a judgment and determining the operation to be performed or the request result according to the judgment result.

It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE)/LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used for the above-mentioned systems and radio technologies as well as other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in most of the following description, but these techniques may also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems.

FIG1a shows a block diagram of a wireless communication system applicable to an embodiment of the present application. The wireless communication system includes a terminal 11 and a network side device 12 . Among them, the terminal 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (Ultra-mobile Personal Computer, UMPC), a mobile Internet device (Mobile Internet Device, MID), an augmented reality (Augmented Reality, AR), a virtual reality (Virtual Reality, VR) device, a robot, a wearable device (Wearable Device), a flight vehicle (flight vehicle), a vehicle user equipment (VUE), a shipborne equipment, a pedestrian terminal (Pedestrian User Equipment, PUE), a smart home (home appliances with wireless communication functions, such as refrigerators, televisions, washing machines or furniture, etc.), a game console, a personal computer (Personal Computer, PC), a teller machine or a self-service machine and other terminal side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device may also be called a radio access network (Radio Access Network, RAN) device, a radio access network function or a radio access network unit. The access network device may include a base station, a wireless local area network (Wireless Local Area Network, WLAN) access point (Access Point, AS) or a wireless fidelity (Wireless Fidelity, WiFi) node, etc. Among them, the base station can be called Node B (Node B, NB), Evolved Node B (Evolved Node B, eNB), the next generation Node B (the next generation Node B, gNB), New Radio Node B (New Radio Node B, NR Node B), access point, Relay Base Station (Relay Base Station, RBS), Serving Base Station (Serving Base Station, SBS), Base Transceiver Station (Base Transceiver Station, BTS), radio base station, radio transceiver, base Basic Service Set (BSS), Extended Service Set (ESS), home Node B (HNB), home evolved Node B (home evolved Node B), Transmission Reception Point (TRP) or other appropriate term in the field, as long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that, in the embodiments of the present application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

The core network equipment may include but is not limited to at least one of the following: core network nodes, core network functions, mobility management entity (Mobility Management Entity, MME), access mobility management function (Access and Mobility Management Function, AMF), session management function (Session Management Function, SMF), user plane function (User Plane Function, UPF), policy control function (Policy Control Function, PCF), policy and charging rules function unit (Policy and Charging Rules Function, PCRF), edge application service discovery function (Edge Application Server Discovery, Function, EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (L-NEF), Binding Support Function (BSF), Application Function (AF), etc. It should be noted that in the embodiments of the present application, only the core network device in the NR system is taken as an example for introduction, and the specific type of the core network device is not limited.

In order to better understand the technical solution of this application, the following contents are first introduced:

Artificial Intelligence (AI) is currently widely used in various fields. There are many ways to implement AI modules, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. This application uses neural networks as an example for illustration, but does not limit the specific type of AI modules.

A schematic diagram of a neural network is shown in Figure 1b:

The neural network is composed of neurons, and the schematic diagram of neurons is as follows. Where a _1, a _2, ...a _K are inputs, w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Common activation functions include Sigmoid, tanh, Rectified Linear Unit (ReLU, also called rectified linear unit), etc.

The parameters of the neural network are optimized using a gradient optimization algorithm. A gradient optimization algorithm is a type of algorithm that minimizes or maximizes an objective function (sometimes called a loss function), and the objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we build a neural network model f(.). With the model, we can get the predicted output f(x) based on the input x, and we can calculate the difference between the predicted value and the true value (f(x)-Y), which is the loss function. Our goal is to find a suitable W,b to minimize the value of the above loss function. The smaller the loss value, the closer our model is to the actual situation.

As shown in Figure 1c, the common optimization algorithms currently used are basically based on the error back propagation (BP) algorithm. The basic idea of the BP algorithm is that the learning process consists of two processes: the forward propagation of the signal and the back propagation of the error. During the forward propagation, the input sample is transmitted from the input layer, processed by each hidden layer layer by layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, it will enter the error back propagation stage. Error back propagation is to propagate the output error layer by layer through the hidden layer to the input layer in some form, and distribute the error to all units in each layer, so as to obtain the error signal of each layer unit, and this error signal is used as the basis for correcting the weights of each unit. This process of adjusting the weights of each layer of the signal forward propagation and error back propagation is repeated over and over again. The process of continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the pre-set number of learning times is reached.

Depending on the type of solution, the selected AI algorithm and the AI model used are also different. At present, the main way to improve the network performance of the fifth generation mobile communication technology (5th Generation Mobile Communication Technology, 5G) with the help of AI is to enhance or replace the existing algorithms or processing modules through algorithms and AI models based on neural networks. In specific scenarios, algorithms and AI models based on neural networks can achieve better performance than those based on deterministic algorithms. The more commonly used neural networks include deep neural networks, convolutional neural networks, and recurrent neural networks. With the help of existing AI tools, the construction, training and verification of neural networks can be achieved.

Replacing modules in existing systems with AI/machine learning (ML) methods can effectively improve system performance.

For example, in the following CSI prediction, the historical CSI is input into the AI model, which analyzes the time domain variation characteristics of the channel and outputs the future CSI. This is shown in Figure 1d.

The corresponding system performance is shown in Figure 1e. It can be seen that CSI prediction has a very large performance gain compared to the non-prediction solution. At the same time, the prediction accuracy that can be achieved will also be different depending on the future time of the prediction.

The above-mentioned CSI prediction is only a time domain prediction, and the current standard discussion only involves time domain prediction. Based on AI, other CSI prediction functions such as CSI time domain interpolation, CSI frequency domain interpolation, CSI spatial domain interpolation, CSI frequency domain extrapolation/prediction, and CSI spatial domain prediction/extrapolation can also be realized. However, the solutions and standards for time domain prediction cannot fully support the above-mentioned other CSI prediction functions. In this regard, this patent proposes a unified implementation method for AI-based CSI prediction services, which, based on the same set of signaling processes, can realize the acquisition of CSI information required for data collection, reasoning, and monitoring processes required for various AI-based prediction functions.

The CSI prediction method and the method for monitoring the CSI prediction results provided in the embodiments of the present application are described in detail below with reference to the accompanying drawings through some embodiments and their application scenarios.

First, the nouns involved in this application are described:

AI Unit/AI Model

The AI unit/AI model described in this application may also be referred to as an AI unit, an AI model, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI characteristic, a machine learning model, a neural network, a neural network function, a neural network function, etc., or the AI unit/AI model may also refer to a processing unit capable of implementing specific algorithms, formulas, processing procedures, capabilities, etc. related to AI, or the AI unit/AI model may be a processing method, algorithm, function, module or unit for a specific data set, or the AI unit/AI model may be a processing method, algorithm, function, module or unit running on AI/ML related hardware such as a graphics processor (GPU), a neural network processor (NPU), a tensor processor (TPU), an application specific integrated circuit (ASIC), etc., and this application does not make specific limitations on this. Optionally, the specific data set includes the input and/or output of the AI unit/AI model.

Optionally, the identifier of the AI unit/AI model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI unit/AI model, or an identifier of a specific scenario, environment, channel feature, or device related to the AI/ML, or an identifier of a function, feature, capability, or module related to the AI/ML, and this application does not specifically limit this.

CSI prediction involves the following process:

Data collection: refers to the process of obtaining data corresponding to the input or output of an AI unit. Data collection can be used for different purposes, such as training, reasoning, monitoring, selection, and updating of AI units.

Reasoning: refers to the process of running the AI unit and obtaining the output of the AI unit.

Monitoring: refers to the process of evaluating the reasoning performance of an AI unit, which can be achieved in a variety of ways, such as monitoring based on calculating the reasoning accuracy of the AI unit based on the output of the AI unit, monitoring based on the input/output distribution of the AI unit, and monitoring based on the communication performance of the communication system.

Referring to FIG. 2 , an embodiment of the present application provides a CSI prediction method, the execution subject of the method is a terminal, and the method includes:

Step 201: The terminal receives first configuration information from a network side device;

Step 202: The terminal sends the first CSI to the network side device according to the first configuration information;

Step 203: The terminal receives a first AI unit from a network-side device;

Step 204: The terminal performs CSI prediction through the first AI unit;

Among them, the first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI reference signal (CSI Reference Signal, CSI-RS) on the target resource, that is, the first configuration information is used to inform the terminal of the relevant configuration of the first CSI-RS sending, and the terminal can correctly receive the first CSI-RS according to the first configuration information. The first CSI-RS is used to collect training data of the first AI unit. The terminal determines the first CSI according to the first CSI-RS. The first CSI is used to generate training data for the first AI unit. Specifically, the number of first CSI-RS sent by the network side device is multiple, and the corresponding terminal determines multiple CSIs according to the multiple first CSI-RSs. These CSIs constitute CSI samples, that is, one CSI-RS obtains one sample, and a large number of samples are used as model training data for the network side device to train the first AI unit.

The target resources include at least one of time domain resources, frequency domain resources and spatial domain resources; depending on the target resources, the terminal can feedback CSI for different resources, and then train AI units for different resources on the network side. Different AI units can predict different categories of CSI. For example, if the target resource is a time domain resource, the trained AI unit can be applied to CSI prediction of the time domain type. If the target resource is a frequency domain resource, the trained AI unit can be applied to CSI prediction of the frequency domain type. If the target resource is a spatial domain resource, the trained AI unit can be applied to CSI prediction of the frequency domain type.

The first AI unit in the embodiment of the present application may be used to implement channel state information related processing, such as CSI time domain prediction, CSI time domain interpolation, CSI frequency domain interpolation, CSI spatial domain interpolation, CSI frequency domain extrapolation/prediction, CSI spatial domain prediction/extrapolation, and a combination of the above multiple functions (such as CSI time domain and frequency domain joint prediction), etc.

The above-mentioned airspace resources can specifically be antennas, ports, etc. The embodiment of the present application does not limit the specific category of the airspace.

The first AI unit is an AI unit obtained by the network side device according to the first CSI training, that is, the AI unit training is performed on the network side, and the more powerful computing power on the network side is used to efficiently train the AI unit.

In an embodiment of the present application, the network side device provides the terminal with the configuration information of CSI-RS, the terminal determines the first CSI according to the configuration information and sends it to the network side device, the first CSI is used as training data to train the first AI unit on the network side, the network side device sends the first AI unit to the terminal, and the terminal predicts CSI through the first AI unit. In this way, for various types of CSI prediction, it is only necessary to provide different CSI-RS configuration information to the terminal based on the above process, the terminal feeds back the corresponding training data to the network side device, the network side trains the corresponding AI unit based on the training data and sends it to the terminal, the terminal implements CSI prediction based on the AI unit, and based on the same set of signaling processes, the data collection and reasoning process required for various AI-based prediction functions can be realized, which can greatly reduce the signaling overhead, improve the resource utilization of the system, and help improve the throughput of the system.

In a possible implementation manner, the first configuration information includes at least one of the following:

(1) first time domain configuration information, used to indicate time information corresponding to the first CSI-RS and time difference information between adjacent first CSI-RSs;

Time domain configuration is used to determine the time points at which CSI-RS is used to measure CSI, as well as the time difference between CSI before and after the time domain. Traditional CSI-RS is generally sent with equal periods in the time domain. CSI-RS for CSI prediction can be sent in clusters in the time domain. The CSI in each cluster is not of equal periodicity, but has a time domain pattern. Here, the CSI-RS of a cluster is used to obtain a CSI prediction sample, and a CSI prediction sample contains CSI at multiple times. For example, a sample contains CSI at 5 time points, and the time difference between CSI at adjacent time points is 5ms. It is also possible that the first CSI is at time 0, the second CSI is at time +5ms, the third CSI is at time +10ms, the fourth CSI is at time +30ms, and the fifth CSI is at time +35ms. Therefore, the time domain pattern of the corresponding CSI-RS in a cluster can also be unequally spaced.

(2) first frequency domain configuration information, used to indicate frequency information corresponding to the first CSI-RS and frequency difference information between adjacent first CSI-RSs;

Frequency domain configuration is used to determine which frequency points the CSI-RS is used to measure CSI at, as well as the frequency difference between the CSI before and after the frequency domain. Traditional CSI-RS are equally spaced in the frequency domain, but CSI-RS used for CSI prediction (especially CSI frequency domain prediction) can be unequally spaced, so it is necessary to indicate the frequency domain position of the CSI-RS or the frequency domain interval between the CSI-RS before and after the frequency domain.

(3) first spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI-RS;

Taking the airspace as a port as an example, the port configuration is used to determine the CSI on which ports the CSI-RS is used to measure. The case where the airspace is an antenna is similar to the case where the airspace is a port, and will not be repeated.

(4) Sample quantity information, used to indicate the quantity of the first CSI;

The number of samples refers to the total number of samples that need to be collected.

(5) first mode information, used to indicate a mode in which the terminal sends the first CSI to the network side device;

The terminal feeds back the first CSI in two ways: immediate feedback (feeding back a sample immediately after the terminal generates one sample) and non-immediate feedback (feeding back on a specific resource or a specific data channel after the terminal accumulates a certain number of samples).

(6) first condition information, used to indicate a condition that must be met when the terminal sends the first CSI to the network side device;

The feedback condition for the terminal to feed back the first CSI refers to condition information that the samples used for feeding back CSI prediction must satisfy.

(7) A first identifier, used to indicate that the first CSI-RS is used to obtain training data of the first AI unit.

It can be called a functional attribute label, which indicates that the CSI-RS is a CSI-RS sent specifically for data collection by the first AI unit.

In a possible implementation manner, before sending the first CSI to the network side device, the method further includes:

The terminal sends second configuration information to the network side device;

The terminal reports the data used for training the first AI unit to the network side, that is, a series of CSI samples. A CSI sample contains CSI at multiple times, frequencies or ports. Prior to this, the terminal sends the configuration information of the CSI sample to the network side. The configuration information is used to describe the content of the CSI sample to be reported later.

The second configuration information includes at least one of the following:

(1) second time domain configuration information, used to indicate time information corresponding to the first CSI and time difference information between adjacent first CSIs;

The time domain configuration can be described by the timestamps of multiple CSIs in the time domain within a CSI sample and the time difference between adjacent CSIs in the time domain.

(2) second frequency domain configuration information, used to indicate frequency information corresponding to the first CSI and frequency difference information between adjacent first CSIs;

The frequency domain configuration can be described by the frequency stamps of multiple CSIs in the frequency domain within a CSI sample and the frequency difference between adjacent CSIs in the frequency domain.

(3) second spatial domain configuration information, used to indicate the spatial domain information corresponding to the first CSI;

Taking the airspace as a port as an example, the port configuration is generally described by a set of port identifiers associated with a CSI sample. The case where the airspace is an antenna is similar to the case where the airspace is a port, and will not be repeated.

(4) A second identifier, used to indicate that the first CSI is used for training the first AI unit.

It can be called a functional attribute label, which indicates that the CSI is specifically used to report data collection or model training for the first AI unit.

In a possible implementation manner, the terminal receives the first AI unit from the network side device, including:

The terminal receives a file of the first AI unit, input configuration information of the first AI unit, and output configuration information of the first AI unit from the network side device;

The network side sends the file of the first AI unit to the terminal. The file of the first unit can be a file in the Open Neural Network Exchange (ONNX) format, a file in the pth format, or a file in other private or public formats, as well as the input configuration information and output configuration information of the first AI unit.

The input configuration information includes at least one of the following:

(1) Input dimension information;

What dimension of data is the input, such as a matrix with M rows and N columns;

(2) The relationship between input and CSI;

How to use CSI information to form the input of the first AI unit, and which CSI is placed at which input position of the first AI;

(3) The relationship between input and auxiliary information;

The auxiliary information may include at least one of the following:

Delay information, delay spread information, speed information, Doppler information, Doppler spread information, channel time domain correlation information, channel frequency domain correlation information, perception information, etc.

The output configuration information includes at least one of the following:

(1) Output dimension information;

What dimension of data is the output, such as a matrix with M rows and N columns;

(2) The relationship between output and CSI.

How to map the output of the first AI unit into CSI information.

In a possible implementation manner, the terminal performs CSI prediction through the first AI unit, including:

(1) The terminal receives a second CSI-RS from a network-side device;

(2) The terminal determines the second CSI according to the second CSI-RS;

(3) The terminal inputs the second CSI into the first AI unit and outputs the predicted CSI according to the file, input configuration information and output configuration information of the first AI unit.

In the inference stage, the network side device sends a second CSI-RS to the terminal. The second CSI-RS can be called the CSI-RS in the inference stage. The terminal determines the second CSI based on the second CSI-RS, and uses the second CSI as input to predict the CSI using the first AI unit.

In a possible implementation, the method further includes:

The terminal receives first information from the network side device;

The first information includes at least one of the following:

(1) Single reasoning start time information of the first AI unit;

(2) Single reasoning end time information of the first AI unit;

(3) The maximum time information of a single inference of the first AI unit; the terminal side is required to complete the inference of a single first AI unit within this time.

(4) CSI reporting time information: The terminal is required to report the CSI report at this time.

The network side sends the timeline requirement information of the first AI unit as described in (1) to (4) above to the terminal side, so that the terminal can clearly understand the time requirement for CSI prediction through the first AI unit.

Referring to FIG. 3 , an embodiment of the present application provides a CSI prediction method, the execution subject of the method is a network side device, and the method includes:

Step 301: The network side device sends first configuration information to the terminal;

Step 302: The network side device receives the first CSI from the terminal;

Step 303: The network-side device trains a first AI unit according to the first CSI;

Step 304: The network side device sends the first AI unit to the terminal;

Among them, the first configuration information is used to configure the terminal to determine the first CSI and send the first CSI based on the first CSI-RS on the target resource, the target resource includes at least one of time domain resources, frequency domain resources and spatial domain resources, the first CSI is used to generate training data for the first AI unit, and the first AI unit is used for the terminal to perform CSI prediction.

It should be noted that the network side device is the opposite side device that interacts with the terminal. The network side and the terminal side maintain the same understanding of the same information to ensure normal information interaction on both sides. For the content of the interactive information, you can directly refer to the relevant description in the terminal side method above, and no repetition will be made here.

In a possible implementation manner, the first configuration information includes at least one of the following:

First time domain configuration information, used to indicate time information corresponding to the first CSI-RS and time difference information between adjacent first CSI-RSs;

First frequency domain configuration information, used to indicate frequency information corresponding to the first CSI-RS and frequency difference information between adjacent first CSI-RSs;

First spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI-RS;

Sample quantity information, used to indicate the quantity of the first CSI;

The first mode information is used to indicate a mode in which the terminal sends the first CSI to the network side device;

The first condition information is used to indicate the conditions that need to be met when the terminal sends the first CSI to the network side device;

The first identifier is used to indicate that the first CSI-RS is used to obtain training data of the first AI unit.

In a possible implementation manner, before the network side device receives the first CSI from the terminal, the method further includes:

The network side device receives second configuration information from the terminal;

The second configuration information includes at least one of the following:

The second time domain configuration information is used to indicate the time information corresponding to the first CSI and the time difference information between adjacent first CSIs;

Second frequency domain configuration information, used to indicate frequency information corresponding to the first CSI, and frequency difference information between adjacent first CSIs;

Second airspace configuration information, used to indicate airspace information corresponding to the first CSI;

The second identifier is used to indicate that the first CSI is used for training the first AI unit.

In a possible implementation manner, the network side device sends the first AI unit to the terminal, including:

The network side device sends the file of the first AI unit, the input configuration information of the first AI unit, and the output configuration information of the first AI unit to the terminal;

The input configuration information includes at least one of the following:

Enter dimension information;

The relationship between input and CSI;

The relationship between input and auxiliary information;

The output configuration information includes at least one of the following:

Output dimension information;

The relationship between output and CSI.

In a possible implementation, the method further includes:

The network side device sends a second CSI-RS to the terminal;

The second CSI-RS is used by the terminal to perform CSI prediction through the first AI unit.

In a possible implementation, the method further includes:

The network side device sends first information to the terminal;

The first information includes at least one of the following:

Single inference start time information of the first AI unit;

Single reasoning end time information of the first AI unit;

The maximum time information of a single inference of the first AI unit;

CSI reporting time information.

Referring to FIG. 4 , an embodiment of the present application provides a method for monitoring a CSI prediction result. The method is performed by a terminal and includes:

Step 401: The terminal receives a third CSI-RS from a network side device;

Step 402: The terminal determines a third CSI according to a third CSI-RS;

Step 403: The terminal monitors the predicted CSI obtained by the first AI unit according to the third CSI;

Among them, the predicted CSI is the CSI predicted by the first AI unit based on the fourth CSI, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located in different resource locations, and the different resource locations can specifically be different time-frequency-space (time domain, frequency domain, and spatial domain) resource locations. That is, in the monitoring stage, the CSI-RS used for monitoring and the CSI-RS used for reasoning are different CSI-RS. Optionally, the third CSI can be called a monitoring-specific CSI-RS, and the fourth CSI can be called a CSI-RS in the reasoning stage.

The CSI-RS in the inference phase only needs to measure the CSI corresponding to the input of the first AI unit, and the CSI-RS in the monitoring phase also needs to additionally measure the CSI corresponding to the output of the first AI unit. That is to say, the time-frequency-space resource range of the CSI that needs to be measured in the monitoring phase is larger than that in the inference phase. The CSI in the monitoring phase may also require higher measurement accuracy, so interference (such as neighboring cell interference) may be reduced by adjusting the resource configuration of the CSI-RS.

In an embodiment of the present application, in the monitoring stage, the network side device sends a CSI-RS to the terminal at a resource location different from the CSI-RS in the reasoning stage. The terminal monitors the results predicted by the AI unit based on the CSI-RS in the monitoring stage to ensure the accuracy of the prediction results. Moreover, based on the same set of signaling processes, the monitoring process required for various AI-based prediction functions can be implemented, which can greatly reduce signaling overhead, improve system resource utilization, and help improve system throughput.

In a possible implementation manner, when the third CSI is all CSI determined by the terminal according to the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a CSI-RS different from the third CSI-RS;

In a possible implementation, when the third CSI is CSI determined by the terminal according to the first part of CSI-RS in the third CSI-RS, the fourth CSI is CSI determined by the terminal according to the second part of CSI-RS in the third CSI-RS.

The resource locations of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different, which can be specifically divided into two situations:

Case 1: The third CSI is all CSIs determined by the terminal according to the third CSI-RS, that is, the monitoring-dedicated CSI-RS is sent separately to the terminal by the network side device, and the network side specifically sends a CSI-RS for the terminal to monitor the prediction results of the AI unit.

Case 2: The third CSI is the CSI determined by the terminal according to the first part of the CSI-RS in the third CSI-RS, and the fourth CSI is the CSI determined by the terminal according to the second part of the CSI-RS in the third CSI-RS, that is, a part of the third CSI-RS sent by the network side device to the terminal is used for reasoning of the AI unit for CSI prediction, and the other part is used for monitoring the AI unit to monitor the CSI prediction results.

In a possible implementation manner, the sequence settings of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different, or the transmission powers of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

The sequence setting of the monitoring-specific CSI-RS is different from that of the CSI-RS in the inference phase. Since the CSI time-frequency-space resource range that needs to be measured in the monitoring phase is larger than that in the inference phase, the length of the sequence will also be different. Different measurement accuracy requirements will also lead to different sequences (for example, the CSI-RS used in the inference phase is based on the Zadoffchu sequence, and the CSI-RS used in the monitoring phase is based on the m sequence).

The transmission power of the dedicated monitoring CSI-RS is different from that of the CSI-RS in the reasoning phase, and the power of the dedicated monitoring CSI-RS of the first AI unit may be higher than that of the CSI-RS in the reasoning phase.

Optionally, before the network side device sends the dedicated CSI-RS for monitoring of the first AI unit to the terminal, the network side device sends configuration information of the dedicated CSI-RS for monitoring of the first AI unit to the terminal. The configuration information mainly includes the time-frequency-space resource position or sequence setting of the dedicated CSI-RS for monitoring of the first AI unit.

In a possible implementation manner, the second CSI-RS has a third identifier, the third CSI-RS has a fourth identifier, and the third identifier is different from the fourth identifier.

The monitoring-dedicated CSI-RS and the CSI-RS in the reasoning stage may have different identifiers, so that the terminal can determine which CSI-RS are used for reasoning and which CSI-RS are used for monitoring.

Referring to FIG. 5 , an embodiment of the present application provides a method for monitoring a CSI prediction result. The method is performed by a network-side device and includes:

Step 501: The network side device sends a third CSI-RS to the terminal;

Among them, the third CSI-RS is used by the terminal to determine the third CSI, and the third CSIS is used by the terminal to monitor the predicted CSI output by the first AI unit. The predicted CSI is the CSI obtained by the first AI unit based on the fourth CSI prediction. The CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located in different resource locations.

It should be noted that the network side device is the opposite side device that interacts with the terminal. The network side and the terminal side maintain the same understanding of the same information to ensure normal information interaction on both sides. For the content of the interactive information, you can directly refer to the relevant description in the terminal side method above, and no repetition will be made here.

In a possible implementation manner, when the third CSI is all CSI determined by the terminal according to the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a CSI-RS different from the third CSI-RS;

In the case where the third CSI is CSI determined by the terminal according to the first part of the CSI-RS in the third CSI-RS, the fourth CSI is CSI determined by the terminal according to the second part of the CSI-RS in the third CSI-RS.

In a possible implementation manner, the sequence settings of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different, or the transmission powers of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

In a possible implementation manner, the second CSI-RS has a third identifier, the third CSI-RS has a fourth identifier, and the third identifier is different from the fourth identifier.

In a possible implementation manner, the network side device sends the third CSI-RS to the terminal, including:

(1) The network device stops sending the CSI-RS corresponding to the fourth CSI to the terminal, and sends the CSI-RS corresponding to the third CSI to the terminal;

(2) The network device sends the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI to the terminal at the same time.

There are two implementation methods for the first AI unit to monitor the dedicated CSI-RS:

(a) The CSI-RS in the inference phase is turned off, and all CSI information required for monitoring by the first AI unit is obtained by measuring the dedicated CSI-RS monitored by the first AI unit.

(b) The CSI-RS in the inference phase is maintained, and the additional CSI information required for the first AI unit to monitor is obtained by measuring the dedicated CSI-RS for the first AI unit to monitor. The additional CSI information refers to the remaining CSI information in all the CSI information required for the first AI unit to monitor, except for the CSI information obtained by measuring the CSI-RS in the inference phase.

The application of the technical solution of this application is described in combination with specific application examples:

Generally speaking, the technical solutions of this application are all cases of obtaining another part of CSI from a part of CSI. The part can be viewed in the time domain, frequency domain, or spatial domain. The part can be continuous or discrete.

CSI time domain prediction: Use historical CSI as the input of the first AI unit and output the CSI at the future time. For example, if the input is the CSI at the [1,2,3,4,5] time slot, the output is the CSI at the [6,7,8,9] time slot.

CSI time domain interpolation: multiple discrete CSIs in the time domain are used as the input of the first AI unit, and other CSIs between the discrete CSIs in the time domain are output. For example, if the input is the CSI of the [1,5,9]th time slot, the output is the CSI of the [3,7]th time slot, the CSI of the [1,3,5,7,9]th time slot, the CSI of the [2,3,4,6,7,8]th time slot, or the CSI of the [1,2,3,4,5,6,7,8,9]th time slot, etc.

CSI frequency domain interpolation: Similar to time domain interpolation. Multiple CSIs in the frequency domain are used as input to the first AI unit, and other CSIs between the CSIs in the frequency domain are output. For example, if the input is the CSI on the [1,5,9]th resource block, the output is the CSI on the [3,7]th resource block, the CSI on the [1,3,5,7,9]th resource block, the CSI on the [2,3,4,6,7,8]th resource block, or the CSI on the [1,2,3,4,5,6,7,8,9]th resource block, and so on.

CSI spatial interpolation: Similar to time domain interpolation. Multiple spatially discrete CSIs are used as input to the first AI unit, and other CSIs between the spatially discrete CSIs are output. The spatial domain can be an antenna, port, etc. For example, the input is the CSI on the [1,3,5,7,9]th port, and the output is the CSI on the [2,4,6]th port block.

CSI frequency domain extrapolation/prediction: Similar to time domain prediction. Take a portion of CSI in the frequency domain that is closer or closer to the front in the specified bandwidth as the input of the first AI unit, and output the CSI in the frequency domain that is closer or closer to the front in the frequency domain. For example, if the input is the CSI on the [1,2,3,4,5]th resource block, the output is the CSI on the [6,7,8,9]th resource block.

CSI spatial prediction/extrapolation: Similar to time domain prediction. A portion of CSI at the front or back of the spatial domain is used as the input of the first AI unit, and the CSI at another portion at the back or front of the spatial domain is output. For example, the input is the CSI at the [1,2,3,4]th port, and the output is the CSI at the [5,6,7,8]th port block.

Referring to FIG. 6 , an embodiment of the present application provides a CSI prediction device, which can be applied to a terminal, and includes:

The first receiving module 601 is used for the terminal to receive first configuration information from the network side device;

A first sending module 602, configured for the terminal to send a first CSI to the network side device according to the first configuration information;

A second receiving module 603 is used for the terminal to receive a first AI unit from the network side device;

A prediction module 604, configured for the terminal to perform CSI prediction through the first AI unit;

Among them, the first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI-RS on the target resource, the target resource includes at least one of time domain resources, frequency domain resources and spatial domain resources, the first CSI is used to generate training data for the first AI unit, and the first AI unit is an AI unit obtained by the network side device training according to the first CSI.

Optionally, the first configuration information includes at least one of the following:

First time domain configuration information, used to indicate time information corresponding to the first CSI-RS and time difference information between adjacent first CSI-RSs;

First frequency domain configuration information, used to indicate frequency information corresponding to the first CSI-RS and frequency difference information between adjacent first CSI-RSs;

First spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI-RS;

Sample quantity information, used to indicate the quantity of the first CSI;

First mode information, used to indicate a mode in which the terminal sends the first CSI to the network side device;

First condition information, used to indicate a condition that needs to be met when the terminal sends the first CSI to the network side device;

The first identifier is used to indicate that the first CSI-RS is used to obtain training data of the first AI unit.

Optionally, the device further comprises:

A fifth sending module, configured to, before sending the first CSI to the network side device, send, by the terminal, second configuration information to the network side device;

The second configuration information includes at least one of the following:

Second time domain configuration information, used to indicate time information corresponding to the first CSI, and time difference information between adjacent first CSIs;

Second frequency domain configuration information, used to indicate frequency information corresponding to the first CSI, and frequency difference information between adjacent first CSIs;

Second spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI;

The second identifier is used to indicate that the first CSI is used for training the first AI unit.

Optionally, the second receiving module is specifically configured to:

The terminal receives a file of the first AI unit, input configuration information of the first AI unit, and output configuration information of the first AI unit from the network side device;

The input configuration information includes at least one of the following:

Enter dimension information;

The relationship between input and CSI;

The relationship between input and auxiliary information;

The output configuration information includes at least one of the following:

Output dimension information;

The relationship between output and CSI.

Optionally, the prediction module is specifically used to:

The terminal receives a second CSI-RS from the network side device;

The terminal determines a second CSI according to the second CSI-RS;

The terminal inputs the second CSI into the first AI unit and outputs the predicted CSI according to the file of the first AI unit, the input configuration information and the output configuration information.

Optionally, the device further comprises:

A fifth receiving module, configured for the terminal to receive first information from the network side device;

The first information includes at least one of the following:

Single inference start time information of the first AI unit;

Single reasoning end time information of the first AI unit;

The maximum time information of a single reasoning of the first AI unit;

CSI reporting time information.

Referring to FIG. 7 , an embodiment of the present application provides a CSI prediction device, which can be applied to a network side device, and includes:

The second sending module 701 is used for the network side device to send the first configuration information to the terminal;

A third receiving module 702 is configured for the network side device to receive the first CSI from the terminal;

A training module 703, configured for the network side device to train a first AI unit according to the first CSI;

A third sending module 704 is configured for the network side device to send the first AI unit to the terminal;

The first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI-RS on the target resource, the target resource includes at least one of a time domain resource, a frequency domain resource, and a spatial domain resource, the first CSI is used to generate training data for the first AI unit, and the first AI unit is used for the terminal to perform CSI prediction.

Optionally, the first configuration information includes at least one of the following:

First time domain configuration information, used to indicate time information corresponding to the first CSI-RS and time difference information between adjacent first CSI-RSs;

First frequency domain configuration information, used to indicate frequency information corresponding to the first CSI-RS and frequency difference information between adjacent first CSI-RSs;

First spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI-RS;

Sample quantity information, used to indicate the quantity of the first CSI;

First mode information, used to indicate a mode in which the terminal sends the first CSI to the network side device;

First condition information, used to indicate a condition that needs to be met when the terminal sends the first CSI to the network side device;

The first identifier is used to indicate that the first CSI-RS is used to obtain training data of the first AI unit.

Optionally, the device further comprises:

A sixth receiving module, configured to receive, by the network side device, second configuration information from the terminal before the network side device receives the first CSI from the terminal;

The second configuration information includes at least one of the following:

Second time domain configuration information, used to indicate time information corresponding to the first CSI, and time difference information between adjacent first CSIs;

Second frequency domain configuration information, used to indicate frequency information corresponding to the first CSI, and frequency difference information between adjacent first CSIs;

Second spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI;

The second identifier is used to indicate that the first CSI is used for training the first AI unit.

Optionally, the third sending module is specifically configured to:

The network-side device sends the file of the first AI unit, the input configuration information of the first AI unit, and the output configuration information of the first AI unit to the terminal;

The input configuration information includes at least one of the following:

Enter dimension information;

The relationship between input and CSI;

The relationship between input and auxiliary information;

The output configuration information includes at least one of the following:

Output dimension information;

The relationship between output and CSI.

Optionally, the device further comprises:

A sixth sending module, configured for the network side device to send a second CSI-RS to the terminal;

The second CSI-RS is used by the terminal to perform CSI prediction through the first AI unit.

Optionally, the device further comprises:

A seventh sending module, configured for the network side device to send first information to the terminal;

The first information includes at least one of the following:

Single inference start time information of the first AI unit;

Single reasoning end time information of the first AI unit;

The maximum time information of a single reasoning of the first AI unit;

CSI reporting time information.

Referring to FIG. 8 , an embodiment of the present application provides a monitoring device for a CSI prediction result, which can be applied to a terminal, and includes:

The fourth receiving module 801 is used for the terminal to receive a third CSI-RS from the network side device;

A first determining module 802, configured for the terminal to determine a third CSI according to the third CSI-RS;

A monitoring module 803, configured for the terminal to monitor the predicted CSI predicted by the first AI unit according to the third CSI;

The predicted CSI is the CSI predicted by the first AI unit according to the fourth CSI, and the resource locations of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

Optionally, in a case where the third CSI is all CSI determined by the terminal according to the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a CSI-RS different from the third CSI-RS;

In a case where the third CSI is CSI determined by the terminal according to a first part of CSI-RSs in the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a second part of CSI-RSs in the third CSI-RS.

Optionally, the sequence settings of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different, or the transmission powers of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

Optionally, the second CSI-RS has a third identifier, the third CSI-RS has a fourth identifier, and the third identifier is different from the fourth identifier.

Referring to FIG. 9 , an embodiment of the present application provides a monitoring device for a CSI prediction result, which can be applied to a network side device, and includes:

The fourth sending module 901 is configured for the network side device to send a third CSI-RS to the terminal;

Among them, the third CSI-RS is used by the terminal to determine the third CSI, the third CSIS is used by the terminal to monitor the predicted CSI predicted and output by the first AI unit, the predicted CSI is the CSI obtained by the first AI unit based on the fourth CSI prediction, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located in different resource locations.

Optionally, in a case where the third CSI is all CSI determined by the terminal according to the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a CSI-RS different from the third CSI-RS;

In a case where the third CSI is CSI determined by the terminal according to a first part of CSI-RSs in the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a second part of CSI-RSs in the third CSI-RS.

Optionally, the sequence settings of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different, or the transmission powers of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

Optionally, the second CSI-RS has a third identifier, the third CSI-RS has a fourth identifier, and the third identifier is different from the fourth identifier.

Optionally, the fourth sending module is specifically configured to:

The network device stops sending the CSI-RS corresponding to the fourth CSI to the terminal, and sends the CSI-RS corresponding to the third CSI to the terminal;

or,

The network device simultaneously sends the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI to the terminal.

The device in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal, or may be other devices other than a terminal. Exemplarily, the terminal may include but is not limited to the types of terminal 11 listed above, and other devices may be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.

The device provided in the embodiment of the present application can implement each process implemented by the method embodiments of Figures 2 to 5 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

As shown in FIG10 , the embodiment of the present application further provides a communication device 1000, including a processor 1001 and a memory 1002, wherein the memory 1002 stores a program or instruction that can be run on the processor 1001. For example, when the communication device 1000 is a terminal, the program or instruction is executed by the processor 1001 to implement the various steps of the above method embodiment, and can achieve the same technical effect. When the communication device 1000 is a network side device, the program or instruction is executed by the processor 1001 to implement the various steps of the above method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

The embodiment of the present application also provides a terminal, including a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps in the method embodiment shown in Figures 2 and 4. This terminal embodiment corresponds to the above-mentioned terminal side method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to the terminal embodiment and can achieve the same technical effect. Specifically, Figure 11 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

The terminal 1100 includes but is not limited to: a radio frequency unit 1101, a network module 1102, an audio output unit 1103, an input unit 1104, a sensor 1105, a display unit 1106, a user input unit 1107, an interface unit 1108, a memory 1109 and at least some of the components of a processor 1110.

Those skilled in the art will appreciate that the terminal 1100 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 1110 through a power management system, so as to implement functions such as managing charging, discharging, and power consumption management through the power management system. The terminal structure shown in FIG11 does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently, which will not be described in detail here.

It should be understood that in the embodiment of the present application, the input unit 1104 may include a graphics processing unit (GPU) 11041 and a microphone 11042, and the graphics processor 11041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 1106 may include a display panel 11061, and the display panel 11061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1107 includes a touch panel 11071 and at least one of other input devices 11072. The touch panel 11071 is also called a touch screen. The touch panel 11071 may include two parts: a touch detection device and a touch controller. Other input devices 11072 may include, but are not limited to, a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

In the embodiment of the present application, after receiving downlink data from the network side device, the RF unit 1101 can transmit the data to the processor 1110 for processing; in addition, the RF unit 1101 can send uplink data to the network side device. Generally, the RF unit 1101 includes but is not limited to an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

The memory 1109 can be used to store software programs or instructions and various data. The memory 1109 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instruction required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 1109 may include a volatile memory or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 1109 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

The processor 1110 may include one or more processing units; optionally, the processor 1110 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 1110.

When the above-mentioned monitoring method of CSI prediction results is implemented:

Processor 1110, configured for the terminal to receive first configuration information from a network side device;

Processor 1110, configured for the terminal to send first CSI to the network side device according to the first configuration information;

Processor 1110, configured for the terminal to receive a first AI unit from the network side device;

Processor 1110, configured for the terminal to perform CSI prediction through the first AI unit;

Among them, the first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI-RS on the target resource, the target resource includes at least one of time domain resources, frequency domain resources and spatial domain resources, and the first AI unit is the AI unit obtained by the network side device according to the first CSI training.

Optionally, the first configuration information includes at least one of the following:

First time domain configuration information, used to indicate time information corresponding to the first CSI-RS and time difference information between adjacent first CSI-RSs;

First frequency domain configuration information, used to indicate frequency information corresponding to the first CSI-RS and frequency difference information between adjacent first CSI-RSs;

First spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI-RS;

Sample quantity information, used to indicate the quantity of the first CSI;

First mode information, used to indicate a mode in which the terminal sends the first CSI to the network side device;

First condition information, used to indicate a condition that needs to be met when the terminal sends the first CSI to the network side device;

The first identifier is used to indicate that the first CSI-RS is used for training of the first AI unit.

Optionally, the processor 1110 is configured to, before sending the first CSI to the network side device, the terminal sending second configuration information to the network side device;

The second configuration information includes at least one of the following:

Second time domain configuration information, used to indicate time information corresponding to the first CSI, and time difference information between adjacent first CSIs;

Second frequency domain configuration information, used to indicate frequency information corresponding to the first CSI, and frequency difference information between adjacent first CSIs;

Second spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI;

The second identifier is used to indicate that the first CSI is used for training the first AI unit.

Optionally, the processor 1110 is specifically configured to:

The terminal receives a file of the first AI unit, input configuration information of the first AI unit, and output configuration information of the first AI unit from the network side device;

The input configuration information includes at least one of the following:

Enter dimension information;

The relationship between input and CSI;

The relationship between input and auxiliary information;

The output configuration information includes at least one of the following:

Output dimension information;

The relationship between output and CSI.

Optionally, the processor 1110 is specifically configured to:

The terminal receives a second CSI-RS from the network side device;

The terminal determines a second CSI according to the second CSI-RS;

The terminal inputs the second CSI into the first AI unit and outputs the predicted CSI according to the file of the first AI unit, the input configuration information and the output configuration information.

Optionally, the processor 1110 is configured for the terminal to receive first information from the network side device;

The first information includes at least one of the following:

Single inference start time information of the first AI unit;

Single reasoning end time information of the first AI unit;

The maximum time information of a single reasoning of the first AI unit;

CSI reporting time information.

In the case of implementing the above monitoring CSI prediction method:

Processor 1110, configured for the terminal to receive a third CSI-RS from a network side device;

A first determining module, configured for the terminal to determine a third CSI according to the third CSI-RS;

A monitoring module, configured for the terminal to monitor the predicted CSI predicted by the first AI unit according to the third CSI;

The predicted CSI is the CSI predicted by the first AI unit according to the fourth CSI, and the resource locations of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

Optionally, in a case where the third CSI is all CSI determined by the terminal according to the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a CSI-RS different from the third CSI-RS;

In a case where the third CSI is CSI determined by the terminal according to a first part of CSI-RSs in the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a second part of CSI-RSs in the third CSI-RS.

Optionally, the sequence settings of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different, or the transmission powers of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

Optionally, the second CSI-RS has a third identifier, the third CSI-RS has a fourth identifier, and the third identifier is different from the fourth identifier.

It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the method embodiment and achieve the same or corresponding technical effect. To avoid repetition, it will not be repeated here.

The embodiment of the present application also provides a network side device, including a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the method embodiment shown in Figures 3 and 5. The network side device embodiment corresponds to the above-mentioned network side device method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to the network side device embodiment, and can achieve the same technical effect.

Specifically, the embodiment of the present application also provides a network side device, which is an access network device. As shown in Figure 12, the network side device 1200 includes: an antenna 121, a radio frequency device 122, a baseband device 123, a processor 124 and a memory 125. The antenna 121 is connected to the radio frequency device 122. In the uplink direction, the radio frequency device 122 receives information through the antenna 121 and sends the received information to the baseband device 123 for processing. In the downlink direction, the baseband device 123 processes the information to be sent and sends it to the radio frequency device 122. The radio frequency device 122 processes the received information and sends it out through the antenna 121.

The method executed by the network-side device in the above embodiment may be implemented in the baseband device 123, which includes a baseband processor.

The baseband device 123 may include, for example, at least one baseband board, on which multiple chips are arranged, as shown in Figure 12, one of which is, for example, a baseband processor, which is connected to the memory 125 through a bus interface to call the program in the memory 125 and execute the network device operations shown in the above method embodiment.

The network side device may also include a network interface 126, which is, for example, a Common Public Radio Interface (CPRI).

Specifically, the network side device 1200 of the embodiment of the present application also includes: instructions or programs stored in the memory 125 and executable on the processor 124. The processor 124 calls the instructions or programs in the memory 125 to execute the methods executed by the modules shown in Figures 7 and 9, and achieves the same technical effect. To avoid repetition, it will not be repeated here.

Specifically, the embodiment of the present application further provides a network side device, which is a core network device. As shown in FIG13 , the network side device 1300 includes: a processor 1301, a network interface 1302, and a memory 1303. Among them, the network interface 1302 is, for example, a common public radio interface (CPRI).

Specifically, the network side device 1300 of the embodiment of the present application also includes: instructions or programs stored in the memory 1303 and executable on the processor 1301. The processor 1301 calls the instructions or programs in the memory 1303 to execute the methods executed by the modules shown in Figures 7 and 8, and achieves the same technical effect. To avoid repetition, it will not be repeated here.

An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

The embodiments of the present application further provide a computer program/program product, which is stored in a storage medium and is executed by at least one processor to implement the various processes of the above-mentioned method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described here.

An embodiment of the present application also provides a wireless communication system, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the terminal side method as described above, and the network side device can be used to execute the steps of the network side method as described above.

Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

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

In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks or optical disks.

Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be realized by controlling the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises one..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general hardware platform, and of course, can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, disk, CD, etc.), including several instructions to enable a terminal or a network-side device to execute the methods described in each embodiment of the present application.

The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of the present application and the scope of protection of the claims, and these implementation methods are all within the protection of the present application.

Claims (36)

A channel state information (CSI) prediction method, comprising: The terminal receives first configuration information from the network side device; The terminal sends a first CSI to the network side device according to the first configuration information; The terminal receives a first artificial intelligence AI unit from the network side device; The terminal performs CSI prediction through the first AI unit; Among them, the first configuration information is used to configure the terminal to determine the first CSI and send the first CSI based on the first channel state information reference signal CSI-RS on the target resource, the target resource includes at least one of time domain resources, frequency domain resources and spatial domain resources, the first CSI is used to generate training data for the first AI unit, and the first AI unit is an AI unit obtained by the network side device training according to the first CSI. The method according to claim 1, wherein the first configuration information includes at least one of the following: First time domain configuration information, used to indicate time information corresponding to the first CSI-RS and time difference information between adjacent first CSI-RSs; First frequency domain configuration information, used to indicate frequency information corresponding to the first CSI-RS and frequency difference information between adjacent first CSI-RSs; First spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI-RS; Sample quantity information, used to indicate the quantity of the first CSI; First mode information, used to indicate a mode in which the terminal sends the first CSI to the network side device; First condition information, used to indicate a condition that needs to be met when the terminal sends the first CSI to the network side device; The first identifier is used to indicate that the first CSI-RS is used to obtain training data of the first AI unit. The method according to claim 1, wherein, before sending the first CSI to the network side device, the method further comprises: The terminal sends second configuration information to the network side device; The second configuration information includes at least one of the following: Second time domain configuration information, used to indicate time information corresponding to the first CSI, and time difference information between adjacent first CSIs; Second frequency domain configuration information, used to indicate frequency information corresponding to the first CSI, and frequency difference information between adjacent first CSIs; Second spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI; The second identifier is used to indicate that the first CSI is used for training the first AI unit. The method according to claim 1, wherein the terminal receives the first AI unit from the network side device, comprising: The terminal receives a file of the first AI unit, input configuration information of the first AI unit, and output configuration information of the first AI unit from the network side device; The input configuration information includes at least one of the following: Enter dimension information; The relationship between input and CSI; The relationship between input and auxiliary information; The output configuration information includes at least one of the following: Output dimension information; The relationship between output and CSI. The method according to claim 4, wherein the terminal performs CSI prediction through the first AI unit, comprising: The terminal receives a second CSI-RS from the network side device; The terminal determines a second CSI according to the second CSI-RS; The terminal inputs the second CSI into the first AI unit and outputs the predicted CSI according to the file of the first AI unit, the input configuration information and the output configuration information. The method according to claim 1, further comprising: The terminal receives first information from the network side device; The first information includes at least one of the following: Single inference start time information of the first AI unit; Single reasoning end time information of the first AI unit; The maximum time information of a single reasoning of the first AI unit; CSI reporting time information. A CSI prediction method, comprising: The network side device sends first configuration information to the terminal; The network side device receives first CSI from the terminal; The network-side device trains a first AI unit according to the first CSI; The network side device sends the first AI unit to the terminal; The first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI-RS on the target resource, the target resource includes at least one of a time domain resource, a frequency domain resource, and a spatial domain resource, the first CSI is used to generate training data for the first AI unit, and the first AI unit is used for the terminal to perform CSI prediction. The method according to claim 7, wherein the first configuration information includes at least one of the following: First time domain configuration information, used to indicate time information corresponding to the first CSI-RS and time difference information between adjacent first CSI-RSs; First frequency domain configuration information, used to indicate frequency information corresponding to the first CSI-RS and frequency difference information between adjacent first CSI-RSs; First spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI-RS; Sample quantity information, used to indicate the quantity of the first CSI; First mode information, used to indicate a mode in which the terminal sends the first CSI to the network side device; First condition information, used to indicate a condition that needs to be met when the terminal sends the first CSI to the network side device; The first identifier is used to indicate that the first CSI-RS is used to obtain training data of the first AI unit. The method according to claim 7, wherein, before the network side device receives the first CSI from the terminal, the method further comprises: The network side device receives second configuration information from the terminal; The second configuration information includes at least one of the following: Second time domain configuration information, used to indicate time information corresponding to the first CSI, and time difference information between adjacent first CSIs; Second frequency domain configuration information, used to indicate frequency information corresponding to the first CSI, and frequency difference information between adjacent first CSIs; Second spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI; The second identifier is used to indicate that the first CSI is used for training the first AI unit. The method according to claim 7, wherein the network side device sends the first AI unit to the terminal, comprising: The network-side device sends the file of the first AI unit, the input configuration information of the first AI unit, and the output configuration information of the first AI unit to the terminal; The input configuration information includes at least one of the following: Enter dimension information; The relationship between input and CSI; The relationship between input and auxiliary information; The output configuration information includes at least one of the following: Output dimension information; The relationship between output and CSI. The method according to claim 7, further comprising: The network side device sends a second CSI-RS to the terminal; The second CSI-RS is used by the terminal to perform CSI prediction through the first AI unit. The method according to claim 7, further comprising: The network side device sends first information to the terminal; The first information includes at least one of the following: Single inference start time information of the first AI unit; Single reasoning end time information of the first AI unit; The maximum time information of a single reasoning of the first AI unit; CSI reporting time information. A method for monitoring a CSI prediction result, comprising: The terminal receives a third CSI-RS from the network side device; The terminal determines a third CSI according to the third CSI-RS; The terminal monitors the predicted CSI predicted by the first AI unit according to the third CSI; The predicted CSI is the CSI predicted by the first AI unit according to the fourth CSI, and the resource locations of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different. The method according to claim 13, wherein In a case where the third CSI is all CSI determined by the terminal according to the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a CSI-RS different from the third CSI-RS; In a case where the third CSI is CSI determined by the terminal according to a first part of CSI-RSs in the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a second part of CSI-RSs in the third CSI-RS. The method according to claim 13 or 14, wherein the sequence settings of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different, or the transmission power of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different. The method according to claim 13 or 14, wherein the second CSI-RS has a third identifier, the third CSI-RS has a fourth identifier, and the third identifier is different from the fourth identifier. A method for monitoring a CSI prediction result, comprising: The network side device sends a third CSI-RS to the terminal; Among them, the third CSI-RS is used by the terminal to determine the third CSI, the third CSIS is used by the terminal to monitor the predicted CSI predicted and output by the first AI unit, the predicted CSI is the CSI obtained by the first AI unit based on the fourth CSI prediction, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located in different resource locations. The method according to claim 17, wherein In a case where the third CSI is all CSI determined by the terminal according to the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a CSI-RS different from the third CSI-RS; In a case where the third CSI is CSI determined by the terminal according to a first part of CSI-RSs in the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a second part of CSI-RSs in the third CSI-RS. The method according to claim 17 or 18, wherein the sequence settings of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different, or the transmission power of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different. The method according to claim 17 or 18, wherein the second CSI-RS has a third identifier, the third CSI-RS has a fourth identifier, and the third identifier is different from the fourth identifier. The method according to claim 17 or 18, wherein the network side device sends a third CSI-RS to the terminal, comprising: The network device stops sending the CSI-RS corresponding to the fourth CSI to the terminal, and sends the CSI-RS corresponding to the third CSI to the terminal; or, The network device simultaneously sends the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI to the terminal. A CSI prediction device, comprising: A first receiving module, used for the terminal to receive first configuration information from a network side device; A first sending module, configured for the terminal to send a first CSI to the network side device according to the first configuration information; A second receiving module, configured for the terminal to receive a first AI unit from the network side device; A prediction module, configured for the terminal to perform CSI prediction through the first AI unit; Among them, the first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI-RS on the target resource, the target resource includes at least one of time domain resources, frequency domain resources and spatial domain resources, the first CSI is used to generate training data for the first AI unit, and the first AI unit is an AI unit obtained by the network side device training according to the first CSI. The apparatus according to claim 22, wherein the first configuration information comprises at least one of the following: First time domain configuration information, used to indicate time information corresponding to the first CSI-RS and time difference information between adjacent first CSI-RSs; First frequency domain configuration information, used to indicate frequency information corresponding to the first CSI-RS and frequency difference information between adjacent first CSI-RSs; First spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI-RS; Sample quantity information, used to indicate the quantity of the first CSI; First mode information, used to indicate a mode in which the terminal sends the first CSI to the network side device; First condition information, used to indicate a condition that needs to be met when the terminal sends the first CSI to the network side device; The first identifier is used to indicate that the first CSI-RS is used to obtain training data of the first AI unit. The device according to claim 22, wherein the second receiving module is specifically configured to: The terminal receives a file of the first AI unit, input configuration information of the first AI unit, and output configuration information of the first AI unit from the network side device; The input configuration information includes at least one of the following: Enter dimension information; The relationship between input and CSI; The relationship between input and auxiliary information; The output configuration information includes at least one of the following: Output dimension information; The relationship between output and CSI. A CSI prediction device, comprising: A second sending module, used for the network side device to send the first configuration information to the terminal; A third receiving module, configured for the network side device to receive the first CSI from the terminal; A training module, configured for the network side device to train a first AI unit according to the first CSI; A third sending module, configured for the network side device to send the first AI unit to the terminal; The first configuration information is used to configure the terminal to determine the first CSI and send the first CSI according to the first CSI-RS on the target resource, the target resource includes at least one of a time domain resource, a frequency domain resource, and a spatial domain resource, the first CSI is used to generate training data for the first AI unit, and the first AI unit is used for the terminal to perform CSI prediction. The apparatus according to claim 25, wherein the first configuration information comprises at least one of the following: First time domain configuration information, used to indicate time information corresponding to the first CSI-RS and time difference information between adjacent first CSI-RSs; First frequency domain configuration information, used to indicate frequency information corresponding to the first CSI-RS and frequency difference information between adjacent first CSI-RSs; First spatial domain configuration information, used to indicate spatial domain information corresponding to the first CSI-RS; Sample quantity information, used to indicate the quantity of the first CSI; First mode information, used to indicate a mode in which the terminal sends the first CSI to the network side device; First condition information, used to indicate a condition that needs to be met when the terminal sends the first CSI to the network side device; The first identifier is used to indicate that the first CSI-RS is used to obtain training data of the first AI unit. The device according to claim 25, wherein the third sending module is specifically configured to: The network-side device sends the file of the first AI unit, the input configuration information of the first AI unit, and the output configuration information of the first AI unit to the terminal; The input configuration information includes at least one of the following: Enter dimension information; The relationship between input and CSI; The relationship between input and auxiliary information; The output configuration information includes at least one of the following: Output dimension information; The relationship between output and CSI. A monitoring device for CSI prediction results, comprising: A fourth receiving module, configured for the terminal to receive a third CSI-RS from a network side device; A first determining module, configured for the terminal to determine a third CSI according to the third CSI-RS; A monitoring module, configured for the terminal to monitor the predicted CSI predicted by the first AI unit according to the third CSI; The predicted CSI is the CSI predicted by the first AI unit according to the fourth CSI, and the resource locations of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different. The device according to claim 28, wherein In a case where the third CSI is all CSI determined by the terminal according to the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a CSI-RS different from the third CSI-RS; In a case where the third CSI is CSI determined by the terminal according to a first part of CSI-RSs in the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a second part of CSI-RSs in the third CSI-RS. The device according to claim 28 or 29, wherein the sequence settings of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different, or the transmission power of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different. A monitoring device for CSI prediction results, comprising: A fourth sending module, configured for the network side device to send a third CSI-RS to the terminal; Among them, the third CSI-RS is used by the terminal to determine the third CSI, the third CSIS is used by the terminal to monitor the predicted CSI predicted and output by the first AI unit, the predicted CSI is the CSI obtained by the first AI unit based on the fourth CSI prediction, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located in different resource locations. The device according to claim 31, wherein In a case where the third CSI is all CSI determined by the terminal according to the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a CSI-RS different from the third CSI-RS; In a case where the third CSI is CSI determined by the terminal according to a first part of CSI-RSs in the third CSI-RS, the fourth CSI is CSI determined by the terminal according to a second part of CSI-RSs in the third CSI-RS. The device according to claim 31 or 32, wherein the sequence settings of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different, or the transmission power of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different. A terminal comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the CSI prediction method according to any one of claims 1 to 6 are implemented, or the steps of the method for monitoring the CSI prediction result according to any one of claims 13 to 16 are implemented. A network side device comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the CSI prediction method as described in any one of claims 7 to 12 are implemented, or the steps of the method for monitoring the CSI prediction results as described in any one of claims 17 to 21 are implemented. A readable storage medium, wherein the readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the program or instruction implements the steps of the CSI prediction method according to any one of claims 1 to 6, or the steps of the CSI prediction method according to any one of claims 7 to 12, or the steps of the CSI prediction result monitoring method according to any one of claims 13 to 16, or the steps of the CSI prediction result monitoring method according to any one of claims 17 to 21.