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

Abstract

The invention belongs to the technical field of communication, and particularly relates to a CSI (Channel State Information) prediction method, a CSI prediction result monitoring method, device and equipment and a readable storage medium, and the method comprises the steps that a terminal receives first configuration information from network side equipment; 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; wherein the first configuration information is used for configuring the terminal to determine the first CSI according to 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 space domain resource, and the first CSI is used for generating training data of the first AI unit; the first AI unit is an AI unit obtained by the network side device according to the first CSI training.

Description

Technical Field

[0001] This application belongs to the field of communication technologies, and particularly relates to a CSI prediction method, a method for monitoring CSI prediction results, an apparatus, a device, and a readable storage medium. Background Art

[0002] Currently, CSI prediction solutions only involve time-domain prediction. However, other CSI prediction functions can also be implemented 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 a method that can support the implementation of various CSI prediction functions. Summary of the Invention

[0003] Embodiments of this application provide a CSI prediction method, a method for monitoring CSI prediction results, an apparatus, a device, and a readable storage medium, which can support various CSI prediction functions.

[0004] In a first aspect, a CSI prediction method is provided, including:

[0005] A terminal receives first configuration information from a network-side device;

[0006] The terminal sends a first CSI to the network-side device according to the first configuration information;

[0007] The terminal receives a first AI unit from the network-side device;

[0008] The terminal performs CSI prediction through the first AI unit;

[0009] Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first channel state information reference signal CSI-RS on a target resource and send the first CSI. 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 trained by the network-side device according to the first CSI.

[0010] In a second aspect, a CSI prediction method is provided, including:

[0011] A network-side device sends first configuration information to a terminal;

[0012] The network-side device receives a first CSI from the terminal;

[0013] The network-side device trains a first AI unit according to the first CSI;

[0014] The network-side device sends the first AI unit to the terminal;

[0015] Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on the target resource and send the first CSI. The target resource includes at least one of time-domain resource, frequency-domain resource, and spatial-domain resource. The first CSI is used to generate training data for the first AI unit, and the first AI unit is used by the terminal for CSI prediction.

[0016] In a third aspect, a method for monitoring a CSI prediction result is provided, including:

[0017] The terminal receives a third CSI-RS from the network-side device;

[0018] The terminal determines a third CSI according to the third CSI-RS;

[0019] The terminal monitors the predicted CSI predicted by the first AI unit according to the third CSI;

[0020] Wherein, the predicted CSI is the CSI predicted by the first AI unit according to a fourth CSI, and the resource positions of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

[0021] In a fourth aspect, a method for monitoring a CSI prediction result is provided, including:

[0022] The network-side device sends a third CSI-RS to the terminal;

[0023] Wherein, the third CSI-RS is used for the terminal to determine a third CSI, and the third CSI is used for the terminal to monitor the predicted CSI predicted by the first AI unit. The predicted CSI is the CSI predicted by the first AI unit according to a fourth CSI, and the resource positions of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

[0024] In a fifth aspect, a CSI prediction device is provided, which is characterized by including:

[0025] A first receiving module, configured to receive first configuration information by the terminal from the network-side device;

[0026] A first sending module, configured to send a first CSI to the network-side device by the terminal according to the first configuration information;

[0027] A second receiving module, configured to receive a first AI unit by the terminal from the network-side device;

[0028] A prediction module, configured to perform CSI prediction by the terminal through the first AI unit;

[0029] Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on the target resource and send the first CSI, the target resource includes at least one of time domain resource, frequency domain resource and spatial domain resource, the first CSI is used to generate training data for the first AI unit, and the first AI unit is an AI unit trained by the network-side device according to the first CSI.

[0030] In a sixth aspect, there is provided a CSI prediction apparatus, characterized by comprising:

[0031] A second sending module, configured to send first configuration information from the network-side device to the terminal;

[0032] A third receiving module, configured to receive the first CSI from the terminal by the network-side device;

[0033] A training module, configured to train a first AI unit by the network-side device according to the first CSI;

[0034] A third sending module, configured to send the first AI unit from the network-side device to the terminal;

[0035] Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on the target resource and send the first CSI, the target resource includes at least one of time domain resource, frequency domain resource and 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.

[0036] In a seventh aspect, there is provided a monitoring apparatus for CSI prediction results, characterized by comprising:

[0037] A fourth receiving module, configured to receive a third CSI-RS from the network-side device by the terminal;

[0038] A first determining module, configured to determine a third CSI by the terminal according to the third CSI-RS;

[0039] A monitoring module, configured to monitor the predicted CSI predicted by the first AI unit by the terminal according to the third CSI;

[0040] Wherein, the predicted CSI is the CSI predicted by the first AI unit according to a fourth CSI, and the resource positions of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

[0041] In an eighth aspect, a monitoring device for CSI prediction results is provided, which is characterized by including:

[0042] A fourth sending module, configured to send a third CSI-RS from a network-side device to a terminal;

[0043] Wherein, the third CSI-RS is used for the terminal to determine a third CSI, the third CSI is used for the terminal to monitor the predicted CSI predicted and output by the first AI unit, the predicted CSI is the CSI predicted by the first AI unit according to a fourth CSI, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located at different resource positions.

[0044] In a ninth aspect, a terminal is provided, which includes a processor and a memory. The memory stores a program or instruction that can run on the processor. 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.

[0045] In a tenth aspect, a terminal is provided, including a processor and a communication interface;

[0046] Wherein, the communication interface is used for the terminal to receive first configuration information from a 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;

[0047] The processor is used for the terminal to perform CSI prediction through the first AI unit;

[0048] Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on a target resource and send the first CSI, 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 of the first AI unit, and the first AI unit is an AI unit trained by the network-side device according to the first CSI.

[0049] Alternatively, the communication interface is used for the terminal to receive a third CSI-RS from a network-side device;

[0050] The processor is used for the terminal to determine 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;

[0051] Wherein, the predicted CSI is the CSI predicted by the first AI unit based on the fourth CSI, and the resource positions where the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located are different.

[0052] In an eleventh aspect, a network-side device is provided. The network-side device includes a processor and a memory. The memory stores a program or instruction that can run on the processor. When the program or instruction is 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.

[0053] In a twelfth aspect, a network-side device is provided, including a processor and a communication interface;

[0054] Wherein, the communication interface is used for the network-side device to send first configuration information to a terminal; the network-side device receives first CSI from the terminal;

[0055] The processor is used for the network-side device to train a first AI unit according to the first CSI;

[0056] The communication interface is used for the network-side device to send the first AI unit to the terminal;

[0057] Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on the target resource and send the first CSI. 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.

[0058] Alternatively, the communication interface is used for the network-side device to send third CSI-RS to the terminal;

[0059] Wherein, the third CSI-RS is used for the terminal to determine third CSI, and the third CSI is used for the terminal to monitor the predicted CSI predicted and output by the first AI unit. The predicted CSI is the CSI predicted by the first AI unit based on the fourth CSI, and the resource positions where the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located are different.

[0060] In a twelfth aspect, a readable storage medium is provided. A program or instruction is stored on the readable storage medium. 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, 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.

[0061] In a thirteenth aspect, a wireless communication system is provided, including: a terminal and a network-side device. 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.

[0062] In a fourteenth aspect, a chip is provided. The chip includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect, to implement the steps of the method described in the third aspect, or to implement the steps of the method described in the fourth aspect.

[0063] In a fifteenth aspect, a computer program / program product is provided. The computer program / program product is stored in a storage medium. The program / program product is executed by at least one processor to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect, to implement the steps of the method described in the third aspect, or to implement the steps of the method described in the fourth aspect.

[0064] In an embodiment of the present application, the network-side device provides the configuration information of CSI-RS for the terminal. 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 performs CSI prediction through the first AI unit. In this way, for various different types of CSI predictions, based on the above process, the network side only needs to provide different CSI-RS configuration information for the terminal. 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 realizes CSI prediction based on the AI unit. Based on the same set of signaling processes, the data collection and inference processes required for multiple AI-based prediction functions can be realized, which can greatly reduce the signaling overhead, improve the resource utilization rate of the system, and help improve the throughput of the system.

[0065] In an embodiment of the present application, in the monitoring stage, the network-side device sends CSI-RS with a resource location different from that of the CSI-RS in the inference stage to the terminal. The terminal monitors the result predicted by the AI unit according to the CSI-RS in the monitoring stage to ensure the accuracy of the prediction result. Moreover, based on the same set of signaling processes, the monitoring processes required for multiple AI-based prediction functions can be realized, which can greatly reduce the signaling overhead, improve the resource utilization rate of the system, and help improve the throughput of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1aIt is a block diagram of a wireless communication system to which the embodiments of the present application can be applied;

[0067] Figure 1b It is a schematic diagram of a neural network;

[0068] Figure 1c It is a schematic diagram of a neuron;

[0069] Figure 1d It is a schematic diagram of AI-based CSI prediction;

[0070] Figure 1e It is a performance schematic diagram of AI-based CSI prediction;

[0071] Figure 2 It is one of the schematic flowcharts of the CSI prediction method provided by the embodiments of the present application;

[0072] Figure 3 It is the second schematic flowchart of the CSI prediction method provided by the embodiments of the present application;

[0073] Figure 4 It is one of the schematic flowcharts of the monitoring method for the CSI prediction result provided by the embodiments of the present application;

[0074] Figure 5 It is the second schematic flowchart of the monitoring method for the CSI prediction result provided by the embodiments of the present application;

[0075] Figure 6 It is one of the schematic structural diagrams of the CSI prediction device provided by the embodiments of the present application;

[0076] Figure 7 It is the second schematic structural diagram of the CSI prediction device provided by the embodiments of the present application;

[0077] Figure 8 It is one of the schematic structural diagrams of the monitoring device for the CSI prediction result provided by the embodiments of the present application;

[0078] Figure 9 It is the second schematic structural diagram of the monitoring device for the CSI prediction result provided by the embodiments of the present application;

[0079] Figure 10 It is the schematic structural diagram of the communication device provided by the embodiments of the present application;

[0080] Figure 11 It is the schematic structural diagram of the terminal provided by the embodiments of the present application;

[0081] Figure 12 It is one of the schematic structural diagrams of the network-side device provided by the embodiments of the present application;

[0082] Figure 13This is the second schematic structural diagram of the network-side device provided by the embodiments of the present application. Detailed implementation manners

[0083] Next, the technical solutions in the embodiments of the present application will be clearly described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application belong to the scope of protection of the present application.

[0084] The terms "first", "second", etc. in the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances 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 the same type, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "or" in the present application means at least one of the connected objects. For example, "A or B" covers three scenarios, namely, Scenario 1: including A and not including B; Scenario 2: including B and not including A; Scenario 3: including both A and B. The character " / " generally indicates an "or" relationship between the associated objects before and after.

[0085] The term "indication" in the present application can be either a direct indication (or an explicit indication) or an indirect indication (or an implicit indication). Among them, a direct indication can be understood as that the sender clearly informs the receiver of specific information, operations to be performed, or request results, etc. in the sent indication; an indirect indication can be understood as that the receiver determines the corresponding information according to the indication sent by the sender, or makes a judgment and determines the operations to be performed or request results, etc. according to the judgment result.

[0086] It should be noted that the technology described in the embodiments of this application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, and 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 this application are often used interchangeably, and the described technology can be used not only in the systems and radio technologies mentioned above, but also in other systems and radio technologies. The following description describes the New Radio (NR) system for example purposes, and uses the NR term in most of the following descriptions, but these technologies can also be applied to systems other than the NR system, such as the 6th Generation (6G) communication system.

[0087] Figure 1aThe block diagram of a wireless communication system to which the embodiments of the present application can be applied is shown. 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 personal computer, a laptop computer, a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device, a flight vehicle, a vehicle user equipment (VUE), a shipborne device, a pedestrian user equipment (PUE), a smart home (home devices with wireless communication functions, such as refrigerators, TVs, washing machines or furniture, etc.), a game console, a personal computer (PC), a teller machine or a self-service machine, etc. Wearable devices include: smart watches, smart bracelets, smart earphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart ankle chains, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle user equipment can also be referred to as a vehicle terminal, a vehicle controller, a vehicle module, a vehicle component, a vehicle chip or a vehicle unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. Among them, the access network device can also be referred to as a radio access network (RAN) device, a radio access network function or a radio access network unit. The access network device can include a base station, a wireless local area network (WLAN) access point (AP) or a wireless fidelity (WiFi) node, etc.Among them, the base station may be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), home Node B (HNB), home evolved Node B, Transmission Reception Point (TRP), or some other suitable term in the art. As long as the same technical effect is achieved, the base station is not limited to specific technical terms. It should be noted that in the embodiments of this 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.

[0088] The core network device may include, but is not limited to, at least one of the following: core network nodes, core network functions, Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), 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 this application, only the core network devices in the NR system are taken as examples for introduction, and the specific types of core network devices are not limited.

[0089] To better understand the technical solution of this application, the following content is introduced first:

[0090] Artificial Intelligence (AI) has currently been widely applied in various fields. There are multiple implementation methods for the AI module, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. In this application, a neural network is taken as an example for illustration, but the specific type of the AI module is not limited.

[0091] A schematic diagram of a neural network is as Figure 1b shown:

[0092] Among them, the neural network is composed of neurons, and the schematic diagram of neurons is as follows. Among them, a 1， a 2， …a K is the input, w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Common activation functions include Sigmoid, tanh, ReLU (Rectified Linear Unit), etc.

[0093] The parameters of the neural network are optimized by gradient optimization algorithms. Gradient optimization algorithms are a class of algorithms that minimize or maximize the objective function (sometimes also called the 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 construct a neural network model f(.). After having the model, according to the input x, we can get the predicted output f(x), and we can calculate the gap between the predicted value and the true value (f(x) - Y), which is the loss function. Our goal is to find the appropriate W and b to minimize the value of the above loss function. The smaller the loss value, the closer our model is to the real situation.

[0094] As Figure 1c shown, currently common optimization algorithms are basically based on the error BackPropagation (BP) algorithm. The basic idea of the BP algorithm is that the learning process consists of two processes: the forward propagation of signals and the backward propagation of errors. During forward propagation, the input samples are input from the input layer, and after being processed layer by layer through each hidden layer, they are transmitted to the output layer. If the actual output of the output layer does not match the expected output, it will enter the stage of backward propagation of errors. Error backpropagation is to backpropagate the output error in a certain form through the hidden layer to the input layer layer by layer, and distribute the error to all units of each layer, so as to obtain the error signals of each layer of units. This error signal is used as the basis for correcting the weights of each unit. This process of adjusting the weights of each layer in the forward propagation of signals and the backward propagation of errors is carried out cyclically. The process of continuously adjusting the weights is also 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 preset number of learning times is reached.

[0095] Depending on the type of problem to be solved, the selected AI algorithms and adopted AI models also vary. Currently, the main method to improve 5G network performance with the help of AI is to enhance or replace existing algorithms or processing modules through neural network-based algorithms and AI models. In specific scenarios, neural network-based algorithms and AI models can achieve better performance than deterministic algorithms. Commonly used neural networks include deep neural networks, convolutional neural networks, and recurrent neural networks, etc. With existing AI tools, the construction, training, and verification of neural networks can be realized.

[0096] Replacing modules in the existing system through AI / machine learning (ML) methods can effectively improve system performance.

[0097] For example, in the following CSI prediction, historical CSI is input into the AI model, and the AI model analyzes the time-domain change characteristics of the channel and outputs future CSI. Specifically, as Figure 1d shown.

[0098] The corresponding system performance is as Figure 1e shown. It can be seen that CSI prediction has a very large performance gain compared to the non-prediction scheme. At the same time, different future moments for prediction may result in different prediction accuracies.

[0099] The above CSI prediction is only time-domain prediction, and currently, only time-domain prediction is involved in the standard discussion. Based on AI, other CSI prediction-related 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 other CSI prediction-related functions. For this reason, this patent proposes a unified implementation method for CSI prediction-related services based on AI. Based on the same set of signaling processes, the CSI information required in the data collection, inference, and monitoring processes for various AI-based prediction-related functions can be obtained.

[0100] Next, in conjunction with the accompanying drawings, through some embodiments and their application scenarios, the CSI prediction method and the monitoring method for CSI prediction results provided by the embodiments of this application will be described in detail.

[0101] First, the nouns involved in this application will be described:

[0102] AI unit / AI model

[0103] 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 feature, 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 flows, 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 Graphic Processing Unit (GPU), a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), an Application-Specific Integrated Circuits (ASIC), etc. This application does not make specific limitations in this regard. Optionally, the specific data set includes the input and / or output of the AI unit / AI model.

[0104] Optionally, the identifier of the AI unit / AI model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or the identifier of a specific data set associated with the AI unit / AI model, or the identifier of a specific scenario, environment, channel feature, device related to AI / ML, or the identifier of a function, feature, capability, or module related to AI / ML. This application does not make specific limitations in this regard.

[0105] CSI prediction involves the following processes:

[0106] Data collection: refers to the process of obtaining data corresponding to the input or output of the AI unit. Data collection can be used for different purposes, such as training, inference, monitoring, selection, update, etc. of the AI unit.

[0107] Inference: refers to the process of running the AI unit to obtain the output of the AI unit.

[0108] Monitoring: refers to the process of evaluating the inference performance of the AI unit, which can be implemented in various ways, such as monitoring the inference accuracy of the AI unit by calculating 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.

[0109] See Figure 2 , this embodiment of the application provides a CSI prediction method. The execution subject of this method is a terminal. The method includes:

[0110] Step 201: The terminal receives first configuration information from a network-side device;

[0111] Step 202: The terminal sends a first CSI to the network-side device according to the first configuration information;

[0112] Step 203: The terminal receives a first AI unit from the network-side device;

[0113] Step 204: The terminal performs CSI prediction through the first AI unit;

[0114] Among them, the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on the target resource and send the first CSI. That is, the first configuration information is used to inform the terminal of the relevant configuration for sending the first CSI-RS. The terminal can correctly receive the first CSI-RS according to this first configuration information. The first CSI-RS is used to collect the 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 the training data of the first AI unit. Specifically, the number of the first CSI-RS sent by the network-side device is multiple. Correspondingly, the terminal determines multiple CSIs according to the multiple first CSI-RS. These CSIs form a CSI sample. That is, one CSI-RS obtains one sample. A large number of samples are used as the data for model training for the network-side device to train the first AI unit.

[0115] The target resource includes at least one of time-domain resource, frequency-domain resource, and spatial-domain resource; according to the difference of the target resource, the terminal can feedback the CSI for different resources, and then an AI unit for different resources can be trained on the network side. Different AI units can perform CSI prediction for different categories of CSIs. For example, if the target resource is a time-domain resource, the trained AI unit can be applied to time-domain CSI prediction. If the target resource is a frequency-domain resource, the trained AI unit can be applied to frequency-domain CSI prediction. If the target resource is a spatial-domain resource, the trained AI unit can be applied to frequency-domain CSI prediction.

[0116] The first AI unit in the embodiments of the present application can 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 mixture of the above multiple functions (such as CSI time-domain and frequency-domain joint prediction), etc.

[0117] The above spatial-domain resource can specifically be an antenna, a port, etc. The embodiments of the present application do not limit the specific category of the spatial domain.

[0118] The first AI unit is an AI unit trained by the network-side device based on the first CSI, that is, the training of the AI unit is performed on the network side, and the more powerful computing power on the network side is utilized for the efficient training of the AI unit.

[0119] In the embodiment of the present application, the network-side device provides the configuration information of CSI-RS for the terminal. 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 performs CSI prediction through the first AI unit. In this way, for various different types of CSI predictions, based on the above process, the network side only needs to provide different CSI-RS configuration information for the terminal, 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, and the terminal realizes CSI prediction based on the AI unit. Based on the same set of signaling processes, the data collection and inference processes required for multiple AI-based prediction functions can be realized, which can greatly reduce the signaling overhead, improve the resource utilization rate of the system, and contribute to improving the throughput of the system.

[0120] In a possible implementation manner, the first configuration information includes at least one of the following:

[0121] (1) The first time-domain configuration information, which is used to indicate the time information corresponding to the first CSI-RS and the time difference information between adjacent first CSI-RSs;

[0122] The time-domain configuration is used to determine which time points the CSI-RS is used to measure the CSI, and the time difference between the front and back CSI in the time domain. Traditional CSI-RSs are generally sent at equal intervals in the time domain. The CSI-RS for CSI prediction can be sent in clusters in the time domain. The CSI within each cluster is not sent at equal intervals, but has a time-domain pattern. Here, a cluster of CSI-RSs is used to obtain a CSI prediction sample, and a CSI prediction sample contains CSI at multiple moments. For example, a sample contains CSI at 5 time points, and the time difference between adjacent CSI is 5 ms. It is also possible that the first CSI is at the 0 moment, the second CSI is at the +5 ms moment, the third CSI is at the +10 ms moment, the fourth CSI is at the +30 ms moment, and the fifth CSI is at the +35 ms moment. Therefore, the time-domain pattern of the corresponding CSI-RS within a cluster can also be non-uniformly spaced.

[0123] (2) The first frequency-domain configuration information, which is used to indicate the frequency information corresponding to the first CSI-RS and the frequency difference information between adjacent first CSI-RSs;

[0124] The frequency domain configuration is used to determine which frequency points of the CSI are measured by the CSI-RS, as well as the frequency difference between the CSI before and after the CSI-RS in the frequency domain. Traditional CSI-RS is equally spaced in the frequency domain, but the CSI-RS for CSI prediction (especially CSI frequency domain prediction) can be non-equally spaced. Therefore, it is necessary to indicate the frequency domain position where the CSI-RS is located or the frequency domain interval between the CSI-RS before and after the CSI-RS in the frequency domain.

[0125] (3) The first spatial domain configuration information is used to indicate the spatial domain information corresponding to the first CSI-RS;

[0126] Taking the spatial domain as a port as an example, the port configuration is used to determine which ports of the CSI are measured by the CSI-RS. The case where the spatial domain is an antenna is similar to the case where the spatial domain is a port and will not be repeated.

[0127] (4) The sample quantity information is used to indicate the quantity of the first CSI;

[0128] The number of samples refers to the total number of samples that need to be collected in total.

[0129] (5) The first mode information is used to indicate the mode in which the terminal sends the first CSI to the network side device;

[0130] The feedback mode for the terminal to feedback the first CSI includes immediate feedback (the terminal side feeds back one sample immediately after generating one sample) and non-immediate feedback (the terminal side accumulates a certain number of samples and then feeds them back on a specific resource or a specific data channel).

[0131] (6) 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;

[0132] The feedback condition for the terminal to feedback the first CSI refers to the condition information that the samples used for CSI prediction need to meet.

[0133] (7) The first identifier is used to indicate that the first CSI-RS is used to obtain the training data of the first AI unit.

[0134] It can be called functional attribute annotation, which indicates that the CSI-RS is a CSI-RS specially sent for data collection of the first AI unit.

[0135] In a possible implementation manner, before sending the first CSI to the network side device, the method further includes:

[0136] The terminal sends second configuration information to the network side device;

[0137] The terminal reports data for the training of the first AI unit to the network side, namely a series of CSI samples. A CSI sample contains CSI on multiple times, frequencies, or ports. Before this, the terminal sends configuration information of the CSI samples to the network side. This configuration information is used to describe the content of the CSI samples to be reported later.

[0138] Among them, the second configuration information includes at least one of the following:

[0139] (1) 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;

[0140] The time-domain configuration can be described by the timestamps of multiple CSIs in the time domain within the CSI sample and the time difference between adjacent CSIs in the time domain.

[0141] (2) The second frequency-domain configuration information is used to indicate the frequency information corresponding to the first CSI and the frequency difference information between adjacent first CSIs;

[0142] The frequency-domain configuration can be described by the frequency stamps of multiple CSIs in the frequency domain within the CSI sample and the frequency difference between adjacent CSIs in the frequency domain.

[0143] (3) The second spatial-domain configuration information is used to indicate the spatial-domain information corresponding to the first CSI;

[0144] Taking the spatial domain as a port as an example, the port configuration is generally described by a set of port identifiers associated with a CSI sample. The situation where the spatial domain is an antenna is similar to the situation where the spatial domain is a port and will not be repeated.

[0145] (4) The second identifier is used to indicate that the first CSI is used for the training of the first AI unit.

[0146] It can be called functional attribute annotation, which indicates that the CSI is a CSI specifically reported for data collection or model training of the first AI unit.

[0147] In a possible implementation manner, the terminal receives the first AI unit from the network-side device, including:

[0148] The terminal receives 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 from the network-side device;

[0149] 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 pth format file, or other private or public format files, etc., as well as the input configuration information and output configuration information of the first AI unit.

[0150] Among them, the input configuration information includes at least one of the following:

[0151] (1) Input dimension information;

[0152] What dimension data is the input, such as a matrix of M rows and N columns;

[0153] (2) The association relationship between the input and CSI;

[0154] How to form the input of the first AI unit with CSI information, and which CSI is placed in which input position of the first AI;

[0155] (3) The association relationship between the input and the auxiliary information;

[0156] The auxiliary information may include at least one of the following:

[0157] Delay information, delay spread information, speed information, Doppler information, Doppler spread information, channel time-domain correlation information, channel frequency-domain correlation information, sensing information, etc.

[0158] The output configuration information includes at least one of the following:

[0159] (1) Output dimension information;

[0160] What dimension data is the output, such as a matrix of M rows and N columns;

[0161] (2) The association relationship between the output and CSI.

[0162] How to map the output of the first AI unit into CSI information.

[0163] In a possible implementation manner, the terminal performs CSI prediction through the first AI unit, including:

[0164] (1) The terminal receives the second CSI-RS from the network-side device;

[0165] (2) The terminal determines the second CSI according to the second CSI-RS;

[0166] (3) The terminal inputs the second CSI into the first AI unit according to the file, input configuration information and output configuration information of the first AI unit, and then outputs the predicted CSI.

[0167] In the inference stage, the network-side device sends the 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 according to the second CSI-RS, and uses the second CSI as the input to predict CSI using the first AI unit.

[0168] In a possible implementation manner, the method further includes:

[0169] The terminal receives first information from the network-side device;

[0170] Wherein, the first information includes at least one of the following:

[0171] (1) The single-inference start time information of the first AI unit;

[0172] (2) The single-inference end time information of the first AI unit;

[0173] (3) The single-inference maximum time information of the first AI unit; it is required that the terminal side must complete the single inference of the first AI unit within this time.

[0174] (4) The CSI reporting time information. It is required that the terminal must report the CSI report at this time.

[0175] 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 clarify the time requirements for CSI prediction through the first AI unit.

[0176] See Figure 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:

[0177] Step 301: The network-side device sends first configuration information to the terminal;

[0178] Step 302: The network-side device receives the first CSI from the terminal;

[0179] Step 303: The network-side device trains the first AI unit according to the first CSI;

[0180] Step 304: The network-side device sends the first AI unit to the terminal;

[0181] Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on the target resource and send the first CSI. 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 the training data of the first AI unit, and the first AI unit is used for the terminal to perform CSI prediction.

[0182] It should be noted that, as the opposite device interacting with the terminal, the network side and the terminal side have the same understanding of the same information to ensure the normal interaction of information on both sides. For the content of the interactive information, the relevant descriptions in the above terminal-side method can be directly referred to, and will not be repeated here.

[0183] In a possible implementation, the first configuration information includes at least one of the following:

[0184] The first time domain configuration information, used to indicate the time information corresponding to the first CSI-RS and the time difference information between adjacent first CSI-RSs;

[0185] The first frequency domain configuration information, used to indicate the frequency information corresponding to the first CSI-RS and the frequency difference information between adjacent first CSI-RSs;

[0186] The first spatial domain configuration information, used to indicate the spatial domain information corresponding to the first CSI-RS;

[0187] The sample quantity information, used to indicate the quantity of the first CSI;

[0188] The first mode information, used to indicate the mode for the terminal to send the first CSI to the network side device;

[0189] The first condition information, used to indicate the conditions that need to be met when the terminal sends the first CSI to the network side device;

[0190] The first identifier, used to indicate that the first CSI-RS is used to obtain the training data of the first AI unit.

[0191] In a possible implementation, before the network side device receives the first CSI from the terminal, the method further includes:

[0192] The network side device receives second configuration information from the terminal;

[0193] Wherein, the second configuration information includes at least one of the following:

[0194] The second time domain configuration information, used to indicate the time information corresponding to the first CSI and the time difference information between adjacent first CSIs;

[0195] The second frequency domain configuration information, used to indicate the frequency information corresponding to the first CSI and the frequency difference information between adjacent first CSIs;

[0196] The second spatial domain configuration information, used to indicate the spatial domain information corresponding to the first CSI;

[0197] The second identifier, used to indicate that the first CSI is used for the training of the first AI unit.

[0198] In a possible implementation, the network side device sends the first AI unit to the terminal, including:

[0199] 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;

[0200] Among them, the input configuration information includes at least one of the following:

[0201] Input dimension information;

[0202] The association relationship between the input and CSI;

[0203] The association relationship between the input and the auxiliary information;

[0204] The output configuration information includes at least one of the following:

[0205] Output dimension information;

[0206] The association relationship between the output and CSI.

[0207] In a possible implementation manner, the method further includes:

[0208] The network side device sends a second CSI-RS to the terminal;

[0209] Among them, the second CSI-RS is used for the terminal to perform CSI prediction through the first AI unit.

[0210] In a possible implementation manner, the method further includes:

[0211] The network side device sends the first information to the terminal;

[0212] Among them, the first information includes at least one of the following:

[0213] The single-inference start time information of the first AI unit;

[0214] The single-inference end time information of the first AI unit;

[0215] The single-inference maximum time information of the first AI unit;

[0216] CSI reporting time information.

[0217] See Figure 4 , this application embodiment provides a method for monitoring CSI prediction results. The execution subject of this method is the terminal, and the method includes:

[0218] Step 401: The terminal receives a third CSI-RS from the network side device;

[0219] Step 402: The terminal determines a third CSI according to the third CSI-RS;

[0220] Step 403: The terminal monitors the predicted CSI predicted by the first AI unit according to the third CSI;

[0221] Among them, the predicted CSI is the CSI predicted by the first AI unit based on the fourth CSI. The CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located at different resource positions. The different resource positions can specifically be time-frequency-space (time domain, frequency domain, spatial domain) resource positions. That is, in the monitoring phase, the CSI-RS used for monitoring and the CSI-RS used for inference are different CSI-RS. Optionally, the above-mentioned third CSI can be called the dedicated CSI-RS for monitoring, and the above-mentioned fourth CSI can be called the CSI-RS in the inference phase.

[0222] The CSI-RS in the inference phase only needs to measure the CSI corresponding to the input of the first AI unit. 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 have higher requirements for measurement accuracy. Therefore, the interference (such as adjacent cell interference) may be reduced by adjusting the resource configuration of the CSI-RS.

[0223] In the embodiment of the present application, in the monitoring phase, the network side device sends a CSI-RS with a resource position different from that of the CSI-RS in the inference phase to the terminal. The terminal monitors the result predicted by the AI unit according to the CSI-RS in the monitoring phase to ensure the accuracy of the prediction result. Moreover, based on the same signaling process, the monitoring process required for various AI-based prediction functions can be realized, which can greatly reduce the signaling overhead, improve the resource utilization rate of the system, and help improve the throughput of the system.

[0224] In a possible implementation manner, when the third CSI is all the CSI determined by the terminal according to the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to the CSI-RS different from the third CSI-RS;

[0225] In a possible implementation manner, when the third CSI is the CSI determined by the terminal according to the first part of the CSI-RS in the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to the second part of the CSI-RS in the third CSI-RS.

[0226] The different resource positions of the CSI-RS corresponding to the above-mentioned third CSI and the CSI-RS corresponding to the fourth CSI can be specifically divided into two cases:

[0227] Case 1: The third CSI is all the CSI determined by the terminal according to the third CSI-RS. That is, the dedicated CSI-RS for monitoring is sent by the network side device to the terminal separately. The network side specifically sends a kind of CSI-RS for the terminal to monitor the prediction result of the AI unit.

[0228] Case 2: The third CSI is the CSI determined by the terminal based on the first part of the CSI-RS in the third CSI-RS, and the fourth CSI is the CSI determined by the terminal based on the second part of the CSI-RS in the third CSI-RS. That is, in the third CSI-RS sent by the network device to the terminal, one part is used for the inference of the AI unit for CSI prediction, and the other part is used for the monitoring of the AI unit to monitor the CSI prediction result.

[0229] In a possible implementation, the sequence settings of the CSI-RS corresponding to the third CSI are different from those of the CSI-RS corresponding to the fourth CSI, or the transmission powers of the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are different.

[0230] The sequence settings of the monitoring-specific CSI-RS are different from those of the CSI-RS in the inference phase. Since the time-frequency-space resource range of the CSI 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 requirements for measurement accuracy will also result in different sequences used (for example, the CSI-RS used in the inference phase is constructed based on the Zadoff-Chu sequence, and the CSI-RS used in the monitoring phase is constructed based on the m-sequence).

[0231] The transmission power of the monitoring-specific CSI-RS is different from that of the CSI-RS in the inference phase, and the power of the monitoring-specific CSI-RS of the first AI unit can be higher than that of the CSI-RS in the inference phase.

[0232] Optionally, before the network device sends the monitoring-specific CSI-RS of the first AI unit to the terminal, the network device sends the configuration information of the monitoring-specific CSI-RS of the first AI unit to the terminal. The configuration information mainly includes the time-frequency-space resource location or sequence settings of the monitoring-specific CSI-RS of the first AI unit.

[0233] In a possible implementation, the second CSI-RS has a third identifier, and the third CSI-RS has a fourth identifier, and the third identifier is different from the fourth identifier.

[0234] The monitoring-specific CSI-RS and the CSI-RS in the inference phase can have different identifiers, which are used for the terminal to determine and confirm which CSI-RS is used for inference and which CSI-RS is used for monitoring.

[0235] See Figure 5 , this application embodiment provides a method for monitoring the CSI prediction result. The execution subject of this method is the network device, and the method includes:

[0236] Step 501: The network device sends the third CSI-RS to the terminal;

[0237] Among them, the third CSI-RS is used for the terminal to determine the third CSI, and the third CSIS is used for the terminal to monitor the predicted CSI output by the first AI unit. The predicted CSI is the CSI predicted by the first AI unit according to the fourth CSI. The resource positions where the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located are different.

[0238] It should be noted that the network-side device, as the opposite device interacting with the terminal, the network side and the terminal side have the same understanding of the same information to ensure the normal interaction of information on both sides. For the content of the interactive information, the relevant descriptions in the above terminal-side method can be directly referred to and will not be repeated here.

[0239] In a possible implementation manner, when the third CSI is all the CSI determined by the terminal according to the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to the CSI-RS different from the third CSI-RS;

[0240] When the third CSI is the CSI determined by the terminal according to the first part of the CSI-RS in the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to the second part of the CSI-RS in the third CSI-RS.

[0241] 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.

[0242] In a possible implementation manner, the second CSI-RS has a third identifier, and the third CSI-RS has a fourth identifier, and the third identifier is different from the fourth identifier.

[0243] In a possible implementation manner, the network-side device sends the third CSI-RS to the terminal, including:

[0244] (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;

[0245] (2) 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.

[0246] There are two implementation manners for the first AI unit to monitor the dedicated CSI-RS:

[0247] (a) During the inference phase, the CSI-RS is turned off, and all the CSI information required for the first AI unit to monitor is obtained by measuring the dedicated CSI-RS monitored by the first AI unit.

[0248] (b) During the inference phase, the CSI-RS is maintained, and the additional CSI information required for the first AI unit to monitor is obtained by measuring the dedicated CSI-RS monitored by the first AI unit. The additional CSI information refers to the remaining CSI information other than the CSI information obtained by measuring the CSI-RS during the inference phase among all the CSI information required for the first AI unit to monitor.

[0249] The application of the technical solution of this application will be described in combination with specific application examples:

[0250] Generally speaking, the technical solutions of this application are all cases of obtaining one part of CSI from another part of CSI. The one part can be viewed in terms of time domain, frequency domain, and spatial domain. The one part can be continuous or discrete.

[0251] CSI time-domain prediction: Using historical CSI as the input of the first AI unit, the CSI at future moments is output. For example, if the input is the CSI at time slots [1, 2, 3, 4, 5], the output is the CSI at time slots [6, 7, 8, 9].

[0252] CSI time-domain interpolation: Using multiple time-domain discrete CSI as the input of the first AI unit, the other CSI between the time-domain discrete CSI is output. For example, if the input is the CSI at time slots [1, 5, 9], the output can be the CSI at time slots [3, 7], the CSI at time slots [1, 3, 5, 7, 9], the CSI at time slots [2, 3, 4, 6, 7, 8], or the CSI at time slots [1, 2, 3, 4, 5, 6, 7, 8, 9], etc.

[0253] CSI frequency-domain interpolation: Similar to time-domain interpolation. Using multiple frequency-domain discrete CSI as the input of the first AI unit, the other CSI between the frequency-domain discrete CSI is output. For example, if the input is the CSI on resource blocks [1, 5, 9], the output can be the CSI on resource blocks [3, 7], the CSI on resource blocks [1, 3, 5, 7, 9], the CSI on resource blocks [2, 3, 4, 6, 7, 8], or the CSI on resource blocks [1, 2, 3, 4, 5, 6, 7, 8, 9], etc.

[0254] CSI spatial domain interpolation: Similar to time domain interpolation. Using multiple CSIs discretized in the spatial domain as the input of the first AI unit, and outputting other CSIs between the CSIs discretized in the spatial domain. The spatial domain can be an antenna, a port, etc. For example, if the input is the CSI on ports [1, 3, 5, 7, 9], the output is the CSI on port block [2, 4, 6].

[0255] CSI frequency domain extrapolation / prediction: Similar to time domain prediction. Using a part of the CSI at the front or back in the frequency domain within a specified bandwidth as the input of the first AI unit, and outputting the CSI at another part of the frequency domain position at the back or front within the specified bandwidth. For example, if the input is the CSI on resource blocks [1, 2, 3, 4, 5], the output is the CSI on resource blocks [6, 7, 8, 9].

[0256] CSI spatial domain prediction / extrapolation: Similar to time domain prediction. Using a part of the CSI at the front or back in the spatial domain as the input of the first AI unit, and outputting the CSI at another part of the position at the back or front in the spatial domain. For example, if the input is the CSI on ports [1, 2, 3, 4], the output is the CSI on port block [5, 6, 7, 8].

[0257] See Figure 6 , an embodiment of the present application provides a CSI prediction device, which can be applied to a terminal. The device includes:

[0258] The first receiving module 601 is configured to receive first configuration information by the terminal from a network-side device;

[0259] The first sending module 602 is configured to send the first CSI to the network-side device by the terminal according to the first configuration information;

[0260] The second receiving module 603 is configured to receive the first AI unit by the terminal from the network-side device;

[0261] The prediction module 604 is configured to perform CSI prediction by the terminal through the first AI unit;

[0262] Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on the target resource and send the first CSI. 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 of the first AI unit, and the first AI unit is an AI unit trained by the network-side device according to the first CSI.

[0263] Optionally, the first configuration information includes at least one of the following:

[0264] The first time domain configuration information is used to indicate the time information corresponding to the first CSI-RS and the time difference information between adjacent first CSI-RSs;

[0265] The first frequency domain configuration information is used to indicate the frequency information corresponding to the first CSI-RS and the frequency difference information between adjacent first CSI-RSs;

[0266] The first spatial domain configuration information is used to indicate the spatial domain information corresponding to the first CSI-RS;

[0267] The sample quantity information is used to indicate the quantity of the first CSI;

[0268] The first mode information is used to indicate the mode by which the terminal sends the first CSI to the network side device;

[0269] The first condition information is used to indicate the conditions that need to be satisfied when the terminal sends the first CSI to the network side device;

[0270] The first identifier is used to indicate that the first CSI-RS is used to obtain the training data of the first AI unit.

[0271] Optionally, the device further includes:

[0272] The fifth sending module is used to send second configuration information from the terminal to the network side device before sending the first CSI to the network side device;

[0273] Wherein, the second configuration information includes at least one of the following:

[0274] 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;

[0275] The second frequency domain configuration information is used to indicate the frequency information corresponding to the first CSI and the frequency difference information between adjacent first CSIs;

[0276] The second spatial domain configuration information is used to indicate the spatial domain information corresponding to the first CSI;

[0277] The second identifier is used to indicate that the first CSI is used for the training of the first AI unit.

[0278] Optionally, the second receiving module is specifically configured to:

[0279] The terminal receives 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 from the network side device;

[0280] Among them, the input configuration information includes at least one of the following:

[0281] Input dimension information;

[0282] The association relationship between the input and CSI;

[0283] The association relationship between the input and auxiliary information;

[0284] The output configuration information includes at least one of the following:

[0285] Output dimension information;

[0286] The association relationship between the output and CSI.

[0287] Optionally, the prediction module is specifically configured to:

[0288] The terminal receives a second CSI-RS from the network-side device;

[0289] The terminal determines a second CSI according to the second CSI-RS;

[0290] The terminal inputs the second CSI into the first AI unit and outputs a predicted CSI according to the file of the first AI unit, the input configuration information, and the output configuration information.

[0291] Optionally, the device further includes:

[0292] A fifth receiving module, configured to receive first information by the terminal from the network-side device;

[0293] Among them, the first information includes at least one of the following:

[0294] The single-inference start time information of the first AI unit;

[0295] The single-inference end time information of the first AI unit;

[0296] The single-inference maximum time information of the first AI unit;

[0297] CSI reporting time information.

[0298] See Figure 7 , an embodiment of the present application provides a CSI prediction device, which can be applied to a network-side device. The device includes:

[0299] A second sending module 701, configured to send first configuration information by the network-side device to the terminal;

[0300] A third receiving module 702, configured to receive a first CSI by the network-side device from the terminal;

[0301] A training module 703, configured to enable the network-side device to train a first AI unit according to the first CSI;

[0302] A third sending module 704, configured to enable the network-side device to send the first AI unit to the terminal;

[0303] Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on the target resource and send the first CSI, 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.

[0304] Optionally, the first configuration information includes at least one of the following:

[0305] First time domain configuration information, used to indicate the time information corresponding to the first CSI-RS and the time difference information between adjacent first CSI-RSs;

[0306] First frequency domain configuration information, used to indicate the frequency information corresponding to the first CSI-RS and the frequency difference information between adjacent first CSI-RSs;

[0307] First spatial domain configuration information, used to indicate the spatial domain information corresponding to the first CSI-RS;

[0308] Sample quantity information, used to indicate the quantity of the first CSI;

[0309] First mode information, used to indicate the mode for the terminal to send the first CSI to the network-side device;

[0310] First condition information, used to indicate the conditions that need to be met when the terminal sends the first CSI to the network-side device;

[0311] A first identifier, used to indicate that the first CSI-RS is used to obtain training data for the first AI unit.

[0312] Optionally, the apparatus further includes:

[0313] A sixth receiving module, configured to enable the network-side device to receive second configuration information from the terminal before receiving the first CSI from the terminal;

[0314] Wherein, the second configuration information includes at least one of the following:

[0315] Second time domain configuration information, used to indicate the time information corresponding to the first CSI, and the time difference information between adjacent first CSIs;

[0316] Second frequency domain configuration information, used to indicate the frequency information corresponding to the first CSI, and the frequency difference information between adjacent first CSIs;

[0317] Second spatial domain configuration information, used to indicate the spatial domain information corresponding to the first CSI;

[0318] Second identifier, used to indicate that the first CSI is used for the training of the first AI unit.

[0319] Optionally, the third sending module is specifically configured to:

[0320] 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;

[0321] Wherein, the input configuration information includes at least one of the following:

[0322] Input dimension information;

[0323] Association relationship between the input and the CSI;

[0324] Association relationship between the input and the auxiliary information;

[0325] The output configuration information includes at least one of the following:

[0326] Output dimension information;

[0327] Association relationship between the output and the CSI.

[0328] Optionally, the device further includes:

[0329] The sixth sending module, used for the network side device to send the second CSI-RS to the terminal;

[0330] Wherein, the second CSI-RS is used for the terminal to perform CSI prediction through the first AI unit.

[0331] Optionally, the device further includes:

[0332] The seventh sending module, used for the network side device to send the first information to the terminal;

[0333] Wherein, the first information includes at least one of the following:

[0334] Single inference start time information of the first AI unit;

[0335] The single-inference end time information of the first AI unit;

[0336] The maximum time information of the single inference of the first AI unit;

[0337] CSI reporting time information.

[0338] See Figure 8 , an embodiment of the present application provides a monitoring device for CSI prediction results, which can be applied to a terminal. The device includes:

[0339] A fourth receiving module 801, configured to receive a third CSI-RS from a network-side device by the terminal;

[0340] A first determining module 802, configured to determine a third CSI by the terminal according to the third CSI-RS;

[0341] A monitoring module 803, configured to monitor the predicted CSI predicted by the first AI unit by the terminal according to the third CSI;

[0342] Wherein, the predicted CSI is the CSI predicted by the first AI unit according to a fourth CSI, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located at different resource positions.

[0343] Optionally, when the third CSI is all the CSI determined by the terminal according to the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to a CSI-RS different from the third CSI-RS;

[0344] When the third CSI is the CSI determined by the terminal according to the first part of the CSI-RS in the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to the second part of the CSI-RS in the third CSI-RS.

[0345] Optionally, the sequence setting of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI, or the transmission power of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI.

[0346] 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.

[0347] See Figure 9 , an embodiment of the present application provides a monitoring device for CSI prediction results, which can be applied to a network-side device. The device includes:

[0348] The fourth transmission module 901 is configured to send a third CSI-RS from a network-side device to a terminal;

[0349] Wherein, the third CSI-RS is used for the terminal to determine a third CSI, and the third CSI is used for the terminal to monitor the predicted CSI predicted and output by the first AI unit. The predicted CSI is the CSI predicted by the first AI unit according to a fourth CSI, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located at different resource positions.

[0350] Optionally, when the third CSI is all the CSI determined by the terminal according to the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to a CSI-RS different from the third CSI-RS;

[0351] When the third CSI is the CSI determined by the terminal according to a first part of the CSI-RS in the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to a second part of the CSI-RS in the third CSI-RS.

[0352] Optionally, the sequence setting of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI, or the transmission power of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI.

[0353] 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.

[0354] Optionally, the fourth transmission module is specifically configured to:

[0355] 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;

[0356] Or,

[0357] 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.

[0358] The device in the embodiments of the present application can 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 can be a terminal or other devices other than terminals. Exemplarily, the terminal can include, but is not limited to, the types of the terminal 11 listed above, and other devices can be servers, Network Attached Storage (NAS), etc., which are not specifically limited in the embodiments of the present application.

[0359] The device provided in the embodiments of the present application can implement Figures 2 to 5 each process implemented by the method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein again.

[0360] As Figure 10 shown, the embodiments of the present application further provide a communication device 1000, including a processor 1001 and a memory 1002. A program or instruction that can run on the processor 1001 is stored on the memory 1002. For example, when the communication device 1000 is a terminal, when the program or instruction is executed by the processor 1001, each step of the above method embodiments is implemented and the same technical effects can be achieved. When the communication device 1000 is a network-side device, when the program or instruction is executed by the processor 1001, each step of the above method embodiments is implemented and the same technical effects can be achieved. To avoid repetition, details are not described herein again.

[0361] The embodiments of the present application further provide 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 embodiments as Figure 2 , Figure 4 shown. This terminal embodiment corresponds to the above terminal-side method embodiments. Each implementation process and implementation manner of the above method embodiments can be applied to this terminal embodiment and the same technical effects can be achieved. Specifically, Figure 11 is a schematic diagram of the hardware structure of a terminal for implementing the embodiments of the present application.

[0362] The terminal 1100 includes, but is not limited to, at least some components such as 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 a processor 1110.

[0363] Those skilled in the art can understand that the terminal 1100 may further include a power supply (such as a battery) for supplying power to each component. The power supply can be logically connected to the processor 1110 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system.Figure 11 The terminal structure shown does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0364] It should be understood that in the embodiments of the present application, the input unit 1104 may include a Graphics Processing Unit (GPU) 11041 and a microphone 11042. The graphics processor 11041 processes the image data of static pictures or videos obtained by an 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 at least one of a touch panel 11071 and 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. The other input devices 11072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, which will not be elaborated here.

[0365] In the embodiments of the present application, after receiving the downlink data from the network-side device, the radio frequency unit 1101 may transmit it to the processor 1110 for processing; in addition, the radio frequency unit 1101 may send the uplink data to the network-side device. Generally, the radio frequency unit 1101 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[0366] 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. Among them, the first storage area may store an operating system, application programs or instructions required for at least one function (such as a sound playback function, an image playback function, 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 (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM), and a direct rambus random access memory (DRRAM). The memory 1109 in the embodiments of the present application includes, but is not limited to, these and any other suitable types of memories.

[0367] The processor 1110 may include one or more processing units; optionally, the processor 1110 integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above modem processor may not be integrated into the processor 1110.

[0368] In the case of implementing the above CSI prediction result monitoring method:

[0369] The processor 1110 is configured to receive first configuration information by the terminal from a network-side device;

[0370] The processor 1110 is configured to send a first CSI by the terminal to the network-side device according to the first configuration information;

[0371] A processor 1110, configured to enable the terminal to receive a first AI unit from the network side device;

[0372] A processor 1110, configured to enable the terminal to perform CSI prediction through the first AI unit;

[0373] Wherein, the first configuration information is used to configure the terminal to determine the first CSI based on the first CSI-RS on the target resource and send the first CSI, the target resource includes at least one of time domain resources, frequency domain resources, and spatial domain resources, and the first AI unit is an AI unit trained by the network side device based on the first CSI.

[0374] Optionally, the first configuration information includes at least one of the following:

[0375] First time domain configuration information, used to indicate the time information corresponding to the first CSI-RS and the time difference information between adjacent first CSI-RSs;

[0376] First frequency domain configuration information, used to indicate the frequency information corresponding to the first CSI-RS and the frequency difference information between adjacent first CSI-RSs;

[0377] First spatial domain configuration information, used to indicate the spatial domain information corresponding to the first CSI-RS;

[0378] Sample quantity information, used to indicate the quantity of the first CSI;

[0379] First mode information, used to indicate the mode for the terminal to send the first CSI to the network side device;

[0380] First condition information, used to indicate the conditions that need to be met when the terminal sends the first CSI to the network side device;

[0381] A first identifier, used to indicate that the first CSI-RS is used for the training of the first AI unit.

[0382] Optionally, the processor 1110 is configured to enable the terminal to send second configuration information to the network side device before sending the first CSI to the network side device;

[0383] Wherein, the second configuration information includes at least one of the following:

[0384] Second time domain configuration information, used to indicate the time information corresponding to the first CSI and the time difference information between adjacent first CSIs;

[0385] The second frequency domain configuration information is used to indicate the frequency information corresponding to the first CSI and the frequency difference information between adjacent first CSIs;

[0386] The second spatial domain configuration information is used to indicate the spatial domain information corresponding to the first CSI;

[0387] The second identifier is used to indicate that the first CSI is used for the training of the first AI unit.

[0388] Optionally, the processor 1110 is specifically configured to:

[0389] The terminal receives 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 from the network side device;

[0390] Wherein, the input configuration information includes at least one of the following:

[0391] Input dimension information;

[0392] The association relationship between the input and the CSI;

[0393] The association relationship between the input and the auxiliary information;

[0394] The output configuration information includes at least one of the following:

[0395] Output dimension information;

[0396] The association relationship between the output and the CSI.

[0397] Optionally, the processor 1110 is specifically configured to:

[0398] The terminal receives the second CSI-RS from the network side device;

[0399] The terminal determines the second CSI according to the second CSI-RS;

[0400] 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.

[0401] Optionally, the processor 1110 is used for the terminal to receive the first information from the network side device;

[0402] Wherein, the first information includes at least one of the following:

[0403] The single inference start time information of the first AI unit;

[0404] The single inference end time information of the first AI unit;

[0405] The maximum single inference time information of the first AI unit;

[0406] CSI reporting time information.

[0407] In the case of implementing the above monitoring CSI prediction method:

[0408] A processor 1110, configured to enable the terminal to receive a third CSI-RS from a network-side device;

[0409] A first determination module, configured to enable the terminal to determine a third CSI according to the third CSI-RS;

[0410] A monitoring module, configured to enable the terminal to monitor the predicted CSI predicted by the first AI unit according to the third CSI;

[0411] Wherein, the predicted CSI is the CSI predicted by the first AI unit according to a fourth CSI, and the resource positions where the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located are different.

[0412] Optionally, in the case where the third CSI is all the CSI determined by the terminal according to the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to a CSI-RS different from the third CSI-RS;

[0413] In the case where the third CSI is the CSI determined by the terminal according to a first part of the CSI-RS in the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to a second part of the CSI-RS in the third CSI-RS.

[0414] 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.

[0415] 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.

[0416] It can be understood that the implementation processes of the implementation manners mentioned in this embodiment may refer to the relevant descriptions of the method embodiment and achieve the same or corresponding technical effects. To avoid repetition, they are not described herein again.

[0417] The embodiments of the present application further provide a network-side device, including a processor and a communication interface. The communication interface is coupled to the processor. The processor is configured to run programs or instructions to implement the steps of the method embodiments as shown in Figure 3 , Figure 5 . The steps of the method embodiments of the network-side device correspond to those of the above-mentioned network-side device method embodiments. Each implementation process and implementation manner of the above method embodiments can be applied to the network-side device embodiments, and the same technical effects can be achieved.

[0418] Specifically, the embodiments of the present application further provide a network-side device, and this network-side device 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. After processing the received information, the radio frequency device 122 sends it out through the antenna 121.

[0419] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 123, and the baseband device 123 includes a baseband processor.

[0420] The baseband device 123 may include, for example, at least one baseband board, and a plurality of chips are provided on this baseband board. As shown in Figure 12 , one of the chips is, for example, a baseband processor, which is connected to the memory 125 through a bus interface to call the programs in the memory 125 and execute the network device operations shown in the above method embodiments.

[0421] The network-side device may further include a network interface 126, and this interface is, for example, a Common Public Radio Interface (CPRI).

[0422] Specifically, the network-side device 1200 of the embodiments of the present application further includes: instructions or programs stored on 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 Figure 7 , Figure 9 , and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0423] Specifically, the embodiments of the present application further provide a network-side device, and this network-side device is a core network device. As shown in Figure 13As shown, 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).

[0424] Specifically, the network-side device 1300 in the embodiment of the present application further includes: instructions or programs stored on the memory 1303 and executable on the processor 1301. The processor 1301 calls the instructions or programs in the memory 1303 to execute Figure 7 , Figure 8 the methods executed by the modules shown, and achieves the same technical effects. To avoid repetition, it will not be elaborated here.

[0425] The embodiment of the present application further provides a readable storage medium. Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the various processes of the above method embodiments are implemented, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0426] Among them, the processor is the processor in the terminal described in the above embodiment. The readable storage medium includes computer-readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disks, or optical discs, etc. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0427] The embodiment of the present application further provides a chip. The chip includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above method embodiments, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0428] It should be understood that the chip mentioned in the embodiment of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[0429] The embodiment of the present application further provides a computer program / program product. The computer program / program product is stored in a storage medium. The computer program / program product is executed by at least one processor to implement the various processes of the above method embodiments, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0430] The embodiment of the present application further provides a wireless communication system, including: a terminal and a network-side device. The terminal can be used to execute the steps of the terminal-side method described above, and the network-side device can be used to execute the steps of the network-side method described above.

[0431] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also other elements not explicitly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising such element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but may also include performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0432] From the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus the necessary general hardware platforms, and of course, they can also be implemented by hardware. The computer software products are stored in storage media (such as ROM, RAM, magnetic disks, optical discs, etc.) and include several instructions for causing a terminal or a network-side device to execute the methods described in various embodiments of the present application.

[0433] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms of embodiments without departing from the purpose of the present application and the scope protected by the claims. These embodiments are all within the protection scope of the present application.

Claims

1. A channel state information CSI prediction method, characterized in that Including: The terminal receives first configuration information from a network-side device; The terminal sends 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; Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first channel state information reference signal (CSI-RS) on target resources and send the first CSI, the target resources include 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 trained by the network-side device according to the first CSI.

2. 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 the time information corresponding to the first CSI-RS and the time difference information between adjacent first CSI-RSs; First frequency-domain configuration information, used to indicate the frequency information corresponding to the first CSI-RS and the frequency difference information between adjacent first CSI-RSs; First spatial-domain configuration information, used to indicate the 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 the mode for the terminal to send the first CSI to the network-side device; First condition information, used to indicate the conditions that need to be met when the terminal sends the first CSI to the network-side device; First identifier, used to indicate that the first CSI-RS is used to obtain training data for the first AI unit.

3. The method according to claim 1, characterized in that 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; Wherein, the second configuration information includes at least one of the following: Second time-domain configuration information, 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 the frequency information corresponding to the first CSI and the frequency difference information between adjacent first CSIs; Second spatial-domain configuration information, used to indicate the spatial-domain information corresponding to the first CSI; Second identifier, used to indicate that the first CSI is used for training of the first AI unit.

4. The method according to claim 1, characterized in that, The terminal receiving the first AI unit from the network-side device includes: The terminal receives 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 from the network-side device; Wherein, the input configuration information includes at least one of the following: Input dimension information; Association relationship between the input and CSI; Association relationship between the input and auxiliary information; The output configuration information includes at least one of the following: Output dimension information; Association relationship between the output and CSI.

5. The method according to claim 4, characterized in that, The terminal performing CSI prediction through the first AI unit includes: 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 according to the file of the first AI unit, the input configuration information, and the output configuration information, and then outputs a predicted CSI.

6. The method according to claim 1, wherein The method further includes: The terminal receives first information from the network device; Wherein, the first information includes at least one of the following: Single-inference start time information of the first AI unit; Single-inference end time information of the first AI unit; Single-inference maximum time information of the first AI unit; CSI reporting time information.

7. A CSI prediction method, characterized in that, Including: The network device sends first configuration information to the terminal; The network device receives a first CSI from the terminal; The network device trains a first AI unit according to the first CSI; The network device sends the first AI unit to the terminal; Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on the target resource and send the first CSI. 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 by the terminal for CSI prediction.

8. 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 the time information corresponding to the first CSI-RS and the time difference information between adjacent first CSI-RSs; First frequency domain configuration information, used to indicate the frequency information corresponding to the first CSI-RS and the frequency difference information between adjacent first CSI-RSs; First spatial domain configuration information, used to indicate the 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 the mode for the terminal to send the first CSI to the network device; First condition information, used to indicate the conditions that need to be met when the terminal sends the first CSI to the network device; First identifier, used to indicate that the first CSI-RS is used to obtain training data for the first AI unit.

9. The method according to claim 7, characterized in that, Before the network device receives the first CSI from the terminal, the method further includes: The network device receives second configuration information from the terminal; Wherein, the second configuration information includes at least one of the following: Second time domain configuration information, 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 the frequency information corresponding to the first CSI and the frequency difference information between adjacent first CSIs; Second spatial domain configuration information, used to indicate the spatial domain information corresponding to the first CSI; Second identifier, used to indicate that the first CSI is used for training the first AI unit.

10. The method according to claim 7, characterized in that The network device sending the first AI unit to the terminal includes: 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; Wherein, the input configuration information includes at least one of the following: Input dimension information; The association relationship between the input and CSI; The association relationship between the input and auxiliary information; The output configuration information includes at least one of the following: Output dimension information; The association relationship between the output and CSI.

11. The method according to claim 7, wherein The method further includes: The network-side device sends a second CSI-RS to the terminal; Wherein, the second CSI-RS is used for the terminal to perform CSI prediction through the first AI unit.

12. The method according to claim 7, wherein The method further includes: The network-side device sends first information to the terminal; Wherein, the first information includes at least one of the following: The single-inference start time information of the first AI unit; The single-inference end time information of the first AI unit; The single-inference maximum time information of the first AI unit; CSI reporting time information.

13. A method for monitoring CSI prediction results, characterized in that, 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; Wherein, the predicted CSI is the CSI predicted by the first AI unit according to a fourth CSI, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located at different resource positions.

14. The method according to claim 13, wherein When the third CSI is all the CSI determined by the terminal according to the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to a CSI-RS different from the third CSI-RS; When the third CSI is the CSI determined by the terminal according to the first part of the CSI-RS in the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to the second part of the CSI-RS in the third CSI-RS.

15. The method according to claim 13 or 14, characterized in that, The sequence setting of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI, or the transmission power of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI.

16. The method according to claim 13 or 14, characterized in that, The second CSI-RS has a third identifier, and the third CSI-RS has a fourth identifier, and the third identifier is different from the fourth identifier.

17. A method for monitoring the CSI prediction result, characterized in that Including: The network-side device sends a third CSI-RS to the terminal; Wherein, the third CSI-RS is used for the terminal to determine a third CSI, and the third CSI is used for the terminal to monitor the predicted CSI predicted by the first AI unit. The predicted CSI is the CSI predicted by the first AI unit according to a fourth CSI, and the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located at different resource positions.

18. The method according to claim 17, wherein when the third CSI is all the CSI determined by the terminal according to the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to a CSI-RS different from the third CSI-RS; when the third CSI is the CSI determined by the terminal according to the first part of the CSI-RS in the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to the second part of the CSI-RS in the third CSI-RS.

19. The method according to claim 17 or 18, characterized in that, The sequence setting of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI, or the transmission power of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI.

20. The method according to claim 17 or 18, characterized in that, The second CSI-RS has a third identifier, and the third CSI-RS has a fourth identifier, and the third identifier is different from the fourth identifier.

21. The method according to claim 17 or 18, characterized in that, The network device sending the third CSI-RS to the terminal includes: 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.

22. A CSI prediction device, characterized in that, including: A first receiving module, configured to receive first configuration information by the terminal from the network device; A first sending module, configured to send a first CSI by the terminal to the network device according to the first configuration information; A second receiving module, configured to receive a first AI unit by the terminal from the network device; A prediction module, configured to perform CSI prediction by the terminal through the first AI unit; wherein the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on a target resource and send the first CSI, 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 of the first AI unit, and the first AI unit is an AI unit trained by the network device according to the first CSI.

23. The device according to claim 22, characterized in that, The first configuration information includes at least one of the following: First time domain configuration information, used to indicate the time information corresponding to the first CSI-RS and the time difference information between adjacent first CSI-RSs; First frequency domain configuration information, used to indicate the frequency information corresponding to the first CSI-RS and the frequency difference information between adjacent first CSI-RSs; First spatial domain configuration information, used to indicate the 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 the mode for the terminal to send the first CSI to the network device; First condition information, used to indicate the conditions that need to be met when the terminal sends the first CSI to the network device. A first identifier, used to indicate that the first CSI-RS is used to obtain training data for the first AI unit.

24. The device according to claim 22, wherein The second receiving module is specifically configured to: The terminal receives 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 from the network-side device; Wherein, the input configuration information includes at least one of the following: Input dimension information; The association relationship between the input and the CSI; The association relationship between the input and the auxiliary information; The output configuration information includes at least one of the following: Output dimension information; The association relationship between the output and the CSI.

25. A CSI prediction device, characterized in that, Includes: A second sending module, used for the network-side device to send first configuration information to the terminal; A third receiving module, used for the network-side device to receive the first CSI from the terminal; A training module, used for the network-side device to train the first AI unit according to the first CSI; A third sending module, used for the network-side device to send the first AI unit to the terminal; Wherein, the first configuration information is used to configure the terminal to determine the first CSI according to the first CSI-RS on the target resource and send the first CSI. 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.

26. The device according to claim 25, characterized in that, The first configuration information includes at least one of the following: First time domain configuration information, used to indicate the time information corresponding to the first CSI-RS and the time difference information between adjacent first CSI-RSs; First frequency domain configuration information, used to indicate the frequency information corresponding to the first CSI-RS and the frequency difference information between adjacent first CSI-RSs; First spatial domain configuration information, used to indicate the 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 the mode for the terminal to send the first CSI to the network-side device; First condition information, used to indicate the conditions that need to be met when the terminal sends the first CSI to the network-side device; A first identifier, used to indicate that the first CSI-RS is used to obtain training data for the first AI unit.

27. The method 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; Wherein, the input configuration information includes at least one of the following: Input dimension information; The association relationship between the input and the CSI; The association relationship between the input and the auxiliary information; The output configuration information includes at least one of the following: Output dimension information; The association relationship between the output and the CSI.

28. A monitoring device for CSI prediction results, characterized in that, Includes: A fourth receiving module, used for the terminal to receive the third CSI-RS from the network-side device; A first determining module, used for the terminal to determine the third CSI according to the third CSI-RS; A monitoring module, configured to monitor, by the terminal, the predicted CSI predicted by the first AI unit according to the third CSI; Wherein, the predicted CSI is the CSI predicted by the first AI unit according to the fourth CSI, and the resource positions where the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located are different.

29. The apparatus according to claim 28, wherein: When the third CSI is all the CSI determined by the terminal according to the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to a CSI-RS different from the third CSI-RS; When the third CSI is the CSI determined by the terminal according to the first part of the CSI-RS in the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to the second part of the CSI-RS in the third CSI-RS.

30. The device according to claim 28 or 29, characterized in that, The sequence setting of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI, or the transmission power of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI.

31. A monitoring device for CSI prediction results, characterized in that, Comprising: A fourth transmission module, configured to send, by the network-side device, a third CSI-RS to the terminal; Wherein, the third CSI-RS is used for the terminal to determine the third CSI, and the third CSI is used for the terminal to monitor the predicted CSI predicted and output by the first AI unit. The predicted CSI is the CSI predicted by the first AI unit according to the fourth CSI, and the resource positions where the CSI-RS corresponding to the third CSI and the CSI-RS corresponding to the fourth CSI are located are different.

32. The apparatus according to claim 31, wherein: When the third CSI is all the CSI determined by the terminal according to the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to a CSI-RS different from the third CSI-RS; When the third CSI is the CSI determined by the terminal according to the first part of the CSI-RS in the third CSI-RS, the fourth CSI is the CSI determined by the terminal according to the second part of the CSI-RS in the third CSI-RS.

33. The device according to claim 31 or 32, characterized in that, The sequence setting of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI, or the transmission power of the CSI-RS corresponding to the third CSI is different from that of the CSI-RS corresponding to the fourth CSI.

34. A terminal, characterized in that, Comprising a processor and a memory, where the memory stores a program or instruction that can run on the processor. 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 monitoring method for the CSI prediction result according to any one of claims 13 to 16 are implemented.

35. A network-side device, characterized in that, It includes a processor and a memory. The memory stores programs or instructions that can run on the processor. When the programs or instructions are executed by the processor, the steps of the CSI prediction method according to any one of claims 7 to 12 are implemented, or the steps of the monitoring method for the CSI prediction result according to any one of claims 17 to 21 are implemented.

36. A readable storage medium, characterized in that, Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the steps of the CSI prediction method according to any one of claims 1 to 6 are implemented, or the steps of the CSI prediction method according to any one of claims 7 to 12 are implemented, or the steps of the monitoring method for the CSI prediction result according to any one of claims 13 to 16 are implemented, or the steps of the monitoring method for the CSI prediction result according to any one of claims 17 to 21 are implemented.

Images